[PATCH v1 15/25] perf pmu-events: Reduce processed events by passing PMU

From: Ian Rogers
Date: Wed Aug 23 2023 - 04:22:34 EST

Next message: Ian Rogers: "[PATCH v1 25/25] perf jevents: Sort strings in the big C string to reduce faults"
Previous message: Ian Rogers: "[PATCH v1 14/25] perf s390 s390_cpumcfdg_dump: Don't scan all PMUs"
In reply to: Ian Rogers: "[PATCH v1 14/25] perf s390 s390_cpumcfdg_dump: Don't scan all PMUs"
Next in thread: Ian Rogers: "[PATCH v1 25/25] perf jevents: Sort strings in the big C string to reduce faults"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

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
"Average PMU scanning" performance is reduced by about 5% on an Intel
tigerlake.

Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
tools/perf/pmu-events/empty-pmu-events.c | 15 ++++++----
tools/perf/pmu-events/jevents.py | 18 ++++++++----
tools/perf/pmu-events/pmu-events.h | 4 ++-
tools/perf/tests/pmu-events.c | 6 ++--
tools/perf/util/pmu.c | 35 +++++++-----------------
tools/perf/util/pmu.h | 1 +
6 files changed, 41 insertions(+), 38 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);
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 0b6efabc3d20..92d1f6f0e666 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/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;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0036e41f6baf..284962c133b3 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -855,28 +855,14 @@ static bool pmu_uncore_alias_match(const char *pmu_name, const char *name)
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;
- const char *pname = pe->pmu ?: data->default_pmu_name;
+ struct list_head *head = vdata;

- if (!strcmp(pname, data->pmu->name) ||
- (data->pmu->is_uncore && pmu_uncore_alias_match(pname, data->pmu->name))) {
- /* need type casts to override 'const' */
- __perf_pmu__new_alias(data->head, -1, (char *)pe->name, (char *)pe->desc,
- (char *)pe->event, pe);
- }
+ /* need type casts to override 'const' */
+ __perf_pmu__new_alias(head, -1, (char *)pe->name, (char *)pe->desc, (char *)pe->event, pe);
return 0;
}

@@ -886,14 +872,7 @@ 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 = {
- .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);
+ pmu_events_table__for_each_event(table, pmu, pmu_add_cpu_aliases_map_callback, &pmu->aliases);
}

static void pmu_add_cpu_aliases(struct perf_pmu *pmu)
@@ -1709,6 +1688,12 @@ 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)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 03211de345c1..2b1730152bc0 100644
--- a/tools/perf/util/pmu.h
+++ b/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
--
2.42.0.rc1.204.g551eb34607-goog

Next message: Ian Rogers: "[PATCH v1 25/25] perf jevents: Sort strings in the big C string to reduce faults"
Previous message: Ian Rogers: "[PATCH v1 14/25] perf s390 s390_cpumcfdg_dump: Don't scan all PMUs"
In reply to: Ian Rogers: "[PATCH v1 14/25] perf s390 s390_cpumcfdg_dump: Don't scan all PMUs"
Next in thread: Ian Rogers: "[PATCH v1 25/25] perf jevents: Sort strings in the big C string to reduce faults"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]