Commit c1a515d3 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'perf-tools-fixes-for-v6.5-2-2023-08-03' of... 

Merge tag 'perf-tools-fixes-for-v6.5-2-2023-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix segfault in the powerpc specific arch_skip_callchain_idx
   function. The patch doing the reference count init/exit that went
   into 6.5 missed this function.

 - Fix regression reading the arm64 PMU cpu slots in sysfs, a patch
   removing some code duplication ended up duplicating the /sysfs prefix
   for these files.

 - Fix grouping of events related to topdown, addressing a regression on
   the CSV output produced by 'perf stat' noticed on the downstream tool
   toplev.

 - Fix the uprobe_from_different_cu 'perf test' entry, it is failing
   when gcc isn't available, so we need to check that and skip the test
   if it is not installed.

* tag 'perf-tools-fixes-for-v6.5-2-2023-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools:
  perf test parse-events: Test complex name has required event format
  perf pmus: Create placholder regardless of scanning core_only
  perf test uprobe_from_different_cu: Skip if there is no gcc
  perf parse-events: Only move force grouped evsels when sorting
  perf parse-events: When fixing group leaders always set the leader
  perf parse-events: Extra care around force grouped events
  perf callchain powerpc: Fix addr location init during arch_skip_callchain_idx function
  perf pmu arm64: Fix reading the PMU cpu slots in sysfs
parents 638c1913 07d2b820

tools/perf/arch/arm64/util/pmu.c

+4 −3
Original line number Diff line number Diff line
@@ -54,10 +54,11 @@ double perf_pmu__cpu_slots_per_cycle(void) 
		perf_pmu__pathname_scnprintf(path, sizeof(path),

					     pmu->name, "caps/slots");

		/*

		 * The value of slots is not greater than 32 bits, but sysfs__read_int

		 * can't read value with 0x prefix, so use sysfs__read_ull instead.

		 * The value of slots is not greater than 32 bits, but

		 * filename__read_int can't read value with 0x prefix,

		 * so use filename__read_ull instead.

		 */

		sysfs__read_ull(path, &slots);

		filename__read_ull(path, &slots);

	}



	return slots ? (double)slots : NAN;

tools/perf/arch/powerpc/util/skip-callchain-idx.c

+4 −0
Original line number Diff line number Diff line
@@ -250,6 +250,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) 
	if (!chain || chain->nr < 3)

		return skip_slot;



	addr_location__init(&al);

	ip = chain->ips[1];



	thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
@@ -259,6 +260,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) 


	if (!dso) {

		pr_debug("%" PRIx64 " dso is NULL\n", ip);

		addr_location__exit(&al);

		return skip_slot;

	}
@@ -279,5 +281,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) 
		 */

		skip_slot = 3;

	}



	addr_location__exit(&al);

	return skip_slot;

}

tools/perf/tests/parse-events.c

+11 −1
Original line number Diff line number Diff line
@@ -1631,6 +1631,16 @@ static bool test__pmu_cpu_valid(void) 
	return !!perf_pmus__find("cpu");

}



static bool test__pmu_cpu_event_valid(void)

{

	struct perf_pmu *pmu = perf_pmus__find("cpu");



	if (!pmu)

		return false;



	return perf_pmu__has_format(pmu, "event");

}



static bool test__intel_pt_valid(void)

{

	return !!perf_pmus__find("intel_pt");
@@ -2179,7 +2189,7 @@ static const struct evlist_test test__events_pmu[] = { 
	},

	{

		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp",

		.valid = test__pmu_cpu_valid,

		.valid = test__pmu_cpu_event_valid,

		.check = test__checkevent_complex_name,

		/* 3 */

	},

tools/perf/tests/shell/test_uprobe_from_different_cu.sh

+7 −1
Original line number Diff line number Diff line
@@ -4,6 +4,12 @@ 


set -e



# skip if there's no gcc

if ! [ -x "$(command -v gcc)" ]; then

        echo "failed: no gcc compiler"

        exit 2

fi



temp_dir=$(mktemp -d /tmp/perf-uprobe-different-cu-sh.XXXXXXXXXX)



cleanup()
@@ -11,7 +17,7 @@ cleanup() 
	trap - EXIT TERM INT

	if [[ "${temp_dir}" =~ ^/tmp/perf-uprobe-different-cu-sh.*$ ]]; then

		echo "--- Cleaning up ---"

		perf probe -x ${temp_dir}/testfile -d foo

		perf probe -x ${temp_dir}/testfile -d foo || true

		rm -f "${temp_dir}/"*

		rmdir "${temp_dir}"

	fi

tools/perf/util/parse-events.c

+36 −22
Original line number Diff line number Diff line
@@ -2100,16 +2100,16 @@ __weak int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) 
	return lhs->core.idx - rhs->core.idx;

}



static int evlist__cmp(void *state, const struct list_head *l, const struct list_head *r)

static int evlist__cmp(void *_fg_idx, const struct list_head *l, const struct list_head *r)

{

	const struct perf_evsel *lhs_core = container_of(l, struct perf_evsel, node);

	const struct evsel *lhs = container_of(lhs_core, struct evsel, core);

	const struct perf_evsel *rhs_core = container_of(r, struct perf_evsel, node);

	const struct evsel *rhs = container_of(rhs_core, struct evsel, core);

	int *leader_idx = state;

	int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret;

	int *force_grouped_idx = _fg_idx;

	int lhs_sort_idx, rhs_sort_idx, ret;

	const char *lhs_pmu_name, *rhs_pmu_name;

	bool lhs_has_group = false, rhs_has_group = false;

	bool lhs_has_group, rhs_has_group;



	/*

	 * First sort by grouping/leader. Read the leader idx only if the evsel
@@ -2121,15 +2121,25 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list 
	 */

	if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) {

		lhs_has_group = true;

		lhs_leader_idx = lhs_core->leader->idx;

		lhs_sort_idx = lhs_core->leader->idx;

	} else {

		lhs_has_group = false;

		lhs_sort_idx = *force_grouped_idx != -1 && arch_evsel__must_be_in_group(lhs)

			? *force_grouped_idx

			: lhs_core->idx;

	}

	if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) {

		rhs_has_group = true;

		rhs_leader_idx = rhs_core->leader->idx;

		rhs_sort_idx = rhs_core->leader->idx;

	} else {

		rhs_has_group = false;

		rhs_sort_idx = *force_grouped_idx != -1 && arch_evsel__must_be_in_group(rhs)

			? *force_grouped_idx

			: rhs_core->idx;

	}



	if (lhs_leader_idx != rhs_leader_idx)

		return lhs_leader_idx - rhs_leader_idx;

	if (lhs_sort_idx != rhs_sort_idx)

		return lhs_sort_idx - rhs_sort_idx;



	/* Group by PMU if there is a group. Groups can't span PMUs. */

	if (lhs_has_group && rhs_has_group) {
@@ -2146,10 +2156,10 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list 


static int parse_events__sort_events_and_fix_groups(struct list_head *list)

{

	int idx = 0, unsorted_idx = -1;

	int idx = 0, force_grouped_idx = -1;

	struct evsel *pos, *cur_leader = NULL;

	struct perf_evsel *cur_leaders_grp = NULL;

	bool idx_changed = false;

	bool idx_changed = false, cur_leader_force_grouped = false;

	int orig_num_leaders = 0, num_leaders = 0;

	int ret;
@@ -2174,12 +2184,14 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) 
		 */

		pos->core.idx = idx++;



		if (unsorted_idx == -1 && pos == pos_leader && pos->core.nr_members < 2)

			unsorted_idx = pos->core.idx;

		/* Remember an index to sort all forced grouped events together to. */

		if (force_grouped_idx == -1 && pos == pos_leader && pos->core.nr_members < 2 &&

		    arch_evsel__must_be_in_group(pos))

			force_grouped_idx = pos->core.idx;

	}



	/* Sort events. */

	list_sort(&unsorted_idx, list, evlist__cmp);

	list_sort(&force_grouped_idx, list, evlist__cmp);



	/*

	 * Recompute groups, splitting for PMUs and adding groups for events
@@ -2189,8 +2201,9 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) 
	list_for_each_entry(pos, list, core.node) {

		const struct evsel *pos_leader = evsel__leader(pos);

		const char *pos_pmu_name = pos->group_pmu_name;

		const char *cur_leader_pmu_name, *pos_leader_pmu_name;

		bool force_grouped = arch_evsel__must_be_in_group(pos);

		const char *cur_leader_pmu_name;

		bool pos_force_grouped = force_grouped_idx != -1 &&

			arch_evsel__must_be_in_group(pos);



		/* Reset index and nr_members. */

		if (pos->core.idx != idx)
@@ -2206,7 +2219,8 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) 
			cur_leader = pos;



		cur_leader_pmu_name = cur_leader->group_pmu_name;

		if ((cur_leaders_grp != pos->core.leader && !force_grouped) ||

		if ((cur_leaders_grp != pos->core.leader &&

		     (!pos_force_grouped || !cur_leader_force_grouped)) ||

		    strcmp(cur_leader_pmu_name, pos_pmu_name)) {

			/* Event is for a different group/PMU than last. */

			cur_leader = pos;
@@ -2216,14 +2230,14 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list) 
			 * group.

			 */

			cur_leaders_grp = pos->core.leader;

		}

		pos_leader_pmu_name = pos_leader->group_pmu_name;

		if (strcmp(pos_leader_pmu_name, pos_pmu_name) || force_grouped) {

			/*

			 * Event's PMU differs from its leader's. Groups can't

			 * span PMUs, so update leader from the group/PMU

			 * tracker.

			 * Avoid forcing events into groups with events that

			 * don't need to be in the group.

			 */

			cur_leader_force_grouped = pos_force_grouped;

		}

		if (pos_leader != cur_leader) {

			/* The leader changed so update it. */

			evsel__set_leader(pos, cur_leader);

		}

	}