perf pmu-events: Reduce processed events by passing PMU

Pass the PMU to pmu_events_table__for_each_event so that entries that
don't match don't need to be processed by callback.

If a NULL PMU is passed then all PMUs are processed.

'perf bench internals pmu-scan's "Average PMU scanning" performance is
reduced by about 5% on an Intel tigerlake.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20230824041330.266337-8-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/pmu-events/empty-pmu-events.c

@@ -266,12 +266,16 @@ static const struct pmu_sys_events pmu_sys_event_tables[] = {
 	},
 };
 
-int pmu_events_table__for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn,
+int pmu_events_table__for_each_event(const struct pmu_events_table *table, struct perf_pmu *pmu,
-				    void *data)
+				     pmu_event_iter_fn fn, void *data)
 {
 	for (const struct pmu_event *pe = &table->entries[0]; pe->name; pe++) {
-		int ret = fn(pe, table, data);
+		int ret;
 
+                if (pmu && !pmu__name_match(pmu, pe->pmu))
+                        continue;
+
+		ret = fn(pe, table, data);
 		if (ret)
 			return ret;
 	}
@@ -371,7 +375,8 @@ const struct pmu_metrics_table *find_core_metrics_table(const char *arch, const
 int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data)
 {
 	for (const struct pmu_events_map *tables = &pmu_events_map[0]; tables->arch; tables++) {
-		int ret = pmu_events_table__for_each_event(&tables->event_table, fn, data);
+		int ret = pmu_events_table__for_each_event(&tables->event_table,
+							   /*pmu=*/ NULL, fn, data);
 
 		if (ret)
 			return ret;
@@ -408,7 +413,7 @@ int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data)
 	for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0];
 	     tables->name;
 	     tables++) {
-		int ret = pmu_events_table__for_each_event(&tables->table, fn, data);
+		int ret = pmu_events_table__for_each_event(&tables->table, /*pmu=*/ NULL, fn, data);
 
 		if (ret)
 			return ret;

tools/perf/pmu-events/jevents.py

@@ -826,14 +826,20 @@ static int pmu_events_table__for_each_event_pmu(const struct pmu_events_table *t
  }
 
 int pmu_events_table__for_each_event(const struct pmu_events_table *table,
+                                    struct perf_pmu *pmu,
                                     pmu_event_iter_fn fn,
                                     void *data)
 {
         for (size_t i = 0; i < table->num_pmus; i++) {
-                int ret = pmu_events_table__for_each_event_pmu(table, &table->pmus[i],
+                const struct pmu_table_entry *table_pmu = &table->pmus[i];
-                                                               fn, data);
+                const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset];
+                int ret;
 
-                if (ret)
+                if (pmu && !pmu__name_match(pmu, pmu_name))
+                        continue;
+
+                ret = pmu_events_table__for_each_event_pmu(table, table_pmu, fn, data);
+                if (pmu || ret)
                         return ret;
         }
         return 0;
@@ -955,7 +961,8 @@ int pmu_for_each_core_event(pmu_event_iter_fn fn, void *data)
         for (const struct pmu_events_map *tables = &pmu_events_map[0];
              tables->arch;
              tables++) {
-                int ret = pmu_events_table__for_each_event(&tables->event_table, fn, data);
+                int ret = pmu_events_table__for_each_event(&tables->event_table,
+                                                           /*pmu=*/ NULL, fn, data);
 
                 if (ret)
                         return ret;
@@ -992,7 +999,8 @@ int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data)
         for (const struct pmu_sys_events *tables = &pmu_sys_event_tables[0];
              tables->name;
              tables++) {
-                int ret = pmu_events_table__for_each_event(&tables->event_table, fn, data);
+                int ret = pmu_events_table__for_each_event(&tables->event_table,
+                                                           /*pmu=*/ NULL, fn, data);
 
                 if (ret)
                         return ret;

tools/perf/pmu-events/pmu-events.h

@@ -77,7 +77,9 @@ typedef int (*pmu_metric_iter_fn)(const struct pmu_metric *pm,
 				  const struct pmu_metrics_table *table,
 				  void *data);
 
-int pmu_events_table__for_each_event(const struct pmu_events_table *table, pmu_event_iter_fn fn,
+int pmu_events_table__for_each_event(const struct pmu_events_table *table,
+				    struct perf_pmu *pmu,
+				    pmu_event_iter_fn fn,
 				    void *data);
 int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, pmu_metric_iter_fn fn,
 				     void *data);

tools/perf/tests/pmu-events.c

@@ -483,12 +483,14 @@ static int test__pmu_event_table(struct test_suite *test __maybe_unused,
 	if (!table || !sys_event_table)
 		return -1;
 
-	err = pmu_events_table__for_each_event(table, test__pmu_event_table_core_callback,
+	err = pmu_events_table__for_each_event(table, /*pmu=*/ NULL,
+					      test__pmu_event_table_core_callback,
 					      &map_events);
 	if (err)
 		return err;
 
-	err = pmu_events_table__for_each_event(sys_event_table, test__pmu_event_table_sys_callback,
+	err = pmu_events_table__for_each_event(sys_event_table, /*pmu=*/ NULL,
+					      test__pmu_event_table_sys_callback,
 					      &map_events);
 	if (err)
 		return err;

tools/perf/util/pmu.c

@@ -859,28 +859,14 @@ out:
 	return res;
 }
 
-struct pmu_add_cpu_aliases_map_data {
-	/* List being added to. */
-	struct list_head *head;
-	/* If a pmu_event lacks a given PMU the default used. */
-	char *default_pmu_name;
-	/* The PMU that we're searching for events for. */
-	struct perf_pmu *pmu;
-};
-
 static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
 					const struct pmu_events_table *table __maybe_unused,
 					void *vdata)
 {
-	struct pmu_add_cpu_aliases_map_data *data = vdata;
+	struct list_head *head = vdata;
-	const char *pname = pe->pmu ?: data->default_pmu_name;
 
-	if (!strcmp(pname, data->pmu->name) ||
+	/* need type casts to override 'const' */
-	    (data->pmu->is_uncore && pmu_uncore_alias_match(pname, data->pmu->name))) {
+	__perf_pmu__new_alias(head, -1, (char *)pe->name, (char *)pe->desc, (char *)pe->event, pe);
-		/* need type casts to override 'const' */
-		__perf_pmu__new_alias(data->head, -1, (char *)pe->name, (char *)pe->desc,
-				      (char *)pe->event, pe);
-	}
 	return 0;
 }
 
@@ -890,14 +876,7 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
  */
 void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_table *table)
 {
-	struct pmu_add_cpu_aliases_map_data data = {
+	pmu_events_table__for_each_event(table, pmu, pmu_add_cpu_aliases_map_callback, &pmu->aliases);
-		.head = &pmu->aliases,
-		.default_pmu_name = perf_pmus__default_pmu_name(),
-		.pmu = pmu,
-	};
-
-	pmu_events_table__for_each_event(table, pmu_add_cpu_aliases_map_callback, &data);
-	free(data.default_pmu_name);
 }
 
 static void pmu_add_cpu_aliases(struct perf_pmu *pmu)
@@ -1713,6 +1692,12 @@ int perf_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_
 	return ret;
 }
 
+bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name)
+{
+	return !strcmp(pmu->name, pmu_name) ||
+		(pmu->is_uncore && pmu_uncore_alias_match(pmu_name, pmu->name));
+}
+
 bool perf_pmu__is_software(const struct perf_pmu *pmu)
 {
 	if (pmu->is_core || pmu->is_uncore || pmu->auxtrace)

tools/perf/util/pmu.h

@@ -198,6 +198,7 @@ bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu);
 bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name);
 size_t perf_pmu__num_events(const struct perf_pmu *pmu);
 int perf_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_callback cb);
+bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name);
 
 /**
  * perf_pmu_is_software - is the PMU a software PMU as in it uses the