perf tools fixes for 6.5: 2nd batch

- 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.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCZMwehwAKCRCyPKLppCJ+
 J6Q4AP9x8xOcwWnaeNlB6U1rQjcEojlRlwdPbKH3yp9oha+wfwD/biswcV1LclmX
 zF7FLZRHLpkDAfmzhMwu73Qu6dbQqw0=
 =U5VE
 -----END PGP SIGNATURE-----

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

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

@@ -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

@@ -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

@@ -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

@@ -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

@@ -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);
 		}
 	}

tools/perf/util/pmu.c

@@ -1440,6 +1440,17 @@ void perf_pmu__del_formats(struct list_head *formats)
 	}
 }
 
+bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name)
+{
+	struct perf_pmu_format *format;
+
+	list_for_each_entry(format, &pmu->format, list) {
+		if (!strcmp(format->name, name))
+			return true;
+	}
+	return false;
+}
+
 bool is_pmu_core(const char *name)
 {
 	return !strcmp(name, "cpu") || !strcmp(name, "cpum_cf") || is_sysfs_pmu_core(name);

tools/perf/util/pmu.h

@@ -234,6 +234,7 @@ int perf_pmu__new_format(struct list_head *list, char *name,
 void perf_pmu__set_format(unsigned long *bits, long from, long to);
 int perf_pmu__format_parse(int dirfd, struct list_head *head);
 void perf_pmu__del_formats(struct list_head *formats);
+bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name);
 
 bool is_pmu_core(const char *name);
 bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu);

tools/perf/util/pmus.c

@@ -152,16 +152,14 @@ static void pmu_read_sysfs(bool core_only)
 	}
 
 	closedir(dir);
-	if (core_only) {
-		if (!list_empty(&core_pmus))
-			read_sysfs_core_pmus = true;
-		else {
-			if (perf_pmu__create_placeholder_core_pmu(&core_pmus))
-				read_sysfs_core_pmus = true;
-		}
-	} else {
+	if (list_empty(&core_pmus)) {
+		if (!perf_pmu__create_placeholder_core_pmu(&core_pmus))
+			pr_err("Failure to set up any core PMUs\n");
+	}
+	if (!list_empty(&core_pmus)) {
 		read_sysfs_core_pmus = true;
-		read_sysfs_all_pmus = true;
+		if (!core_only)
+			read_sysfs_all_pmus = true;
 	}
 }