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>

3 files changed, 26 insertions, 11 deletions

diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c
index 807f2e55c17c..2d6f748280ac 100644
--- a/tools/perf/pmu-events/empty-pmu-events.c
+++ b/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,
-				    void *data)
+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 (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;
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 1ad20140114c..396af53e0e45 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/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],
-                                                               fn, data);
+                const struct pmu_table_entry *table_pmu = &table->pmus[i];
+                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;
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 6557381b7de1..c0303ba42e97 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/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);