The perf_stat_config.aggr_map should have a correct size of the
aggregation map. Use it to allocate aggr_counts.
Also AGGR_NONE with per-core events can be tricky because it doesn't
aggreate basically but it needs to do so for per-core events only.
So only per-core evsels will have stats->aggr data.
Note that other caller of evlist__alloc_stat() might not have
stat_config or aggr_map.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/builtin-script.c | 4 ++--
tools/perf/builtin-stat.c | 6 +++---
tools/perf/tests/parse-metric.c | 2 +-
tools/perf/tests/pmu-events.c | 2 +-
tools/perf/util/stat.c | 9 +++++++--
tools/perf/util/stat.h | 3 ++-
6 files changed, 16 insertions(+), 10 deletions(-)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 7ca238277d83..691915a71c86 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2049,7 +2049,7 @@ static void perf_sample__fprint_metric(struct perf_script *script,
u64 val;
if (!evsel->stats)
- evlist__alloc_stats(script->session->evlist, false);
+ evlist__alloc_stats(&stat_config, script->session->evlist, false);
if (evsel_script(leader)->gnum++ == 0)
perf_stat__reset_shadow_stats();
val = sample->period * evsel->scale;
@@ -3632,7 +3632,7 @@ static int set_maps(struct perf_script *script)
perf_evlist__set_maps(&evlist->core, script->cpus, script->threads);
- if (evlist__alloc_stats(evlist, true))
+ if (evlist__alloc_stats(&stat_config, evlist, true))
return -ENOMEM;
script->allocated = true;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e5ddf60ab31d..eaddafbd7ff2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2124,7 +2124,7 @@ static int set_maps(struct perf_stat *st)
perf_evlist__set_maps(&evsel_list->core, st->cpus, st->threads);
- if (evlist__alloc_stats(evsel_list, true))
+ if (evlist__alloc_stats(&stat_config, evsel_list, true))
return -ENOMEM;
st->maps_allocated = true;
@@ -2571,10 +2571,10 @@ int cmd_stat(int argc, const char **argv)
goto out;
}
- if (evlist__alloc_stats(evsel_list, interval))
+ if (perf_stat_init_aggr_mode())
goto out;
- if (perf_stat_init_aggr_mode())
+ if (evlist__alloc_stats(&stat_config, evsel_list, interval))
goto out;
/*
diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index 68f5a2a03242..cb3a9b795c0f 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -103,7 +103,7 @@ static int __compute_metric(const char *name, struct value *vals,
if (err)
goto out;
- err = evlist__alloc_stats(evlist, false);
+ err = evlist__alloc_stats(NULL, evlist, false);
if (err)
goto out;
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 097e05c796ab..a5e1028dacfc 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -889,7 +889,7 @@ static int test__parsing_callback(const struct pmu_event *pe, const struct pmu_e
goto out_err;
}
- err = evlist__alloc_stats(evlist, false);
+ err = evlist__alloc_stats(NULL, evlist, false);
if (err)
goto out_err;
/*
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index c9d5aa295b54..374149628507 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -211,12 +211,17 @@ static int evsel__alloc_stats(struct evsel *evsel, int nr_aggr, bool alloc_raw)
return 0;
}
-int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
+int evlist__alloc_stats(struct perf_stat_config *config,
+ struct evlist *evlist, bool alloc_raw)
{
struct evsel *evsel;
+ int nr_aggr = 0;
+
+ if (config && config->aggr_map)
+ nr_aggr = config->aggr_map->nr;
evlist__for_each_entry(evlist, evsel) {
- if (evsel__alloc_stats(evsel, 0, alloc_raw))
+ if (evsel__alloc_stats(evsel, nr_aggr, alloc_raw))
goto out_free;
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index ea356e5aa351..74bd51a3cb36 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -257,7 +257,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
struct runtime_stat *st);
void perf_stat__collect_metric_expr(struct evlist *);
-int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw);
+int evlist__alloc_stats(struct perf_stat_config *config,
+ struct evlist *evlist, bool alloc_raw);
void evlist__free_stats(struct evlist *evlist);
void evlist__reset_stats(struct evlist *evlist);
void evlist__reset_prev_raw_counts(struct evlist *evlist);
--
2.38.0.rc1.362.ged0d419d3c-googOn Sun, Oct 9, 2022 at 10:36 PM Namhyung Kim <namhyung@kernel.org> wrote:
>
> The perf_stat_config.aggr_map should have a correct size of the
> aggregation map. Use it to allocate aggr_counts.
>
> Also AGGR_NONE with per-core events can be tricky because it doesn't
> aggreate basically but it needs to do so for per-core events only.
nit: s/aggreate/aggregate/
> So only per-core evsels will have stats->aggr data.
>
> Note that other caller of evlist__alloc_stat() might not have
> stat_config or aggr_map.
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Ian Rogers <irogers@google.com>
nit: Below there are use of constants true, false and NULL, it would
be nice to use the /*argument_name=*/... style parameter passing to be
clearer on what the parameter means.
Thanks,
Ian
> ---
> tools/perf/builtin-script.c | 4 ++--
> tools/perf/builtin-stat.c | 6 +++---
> tools/perf/tests/parse-metric.c | 2 +-
> tools/perf/tests/pmu-events.c | 2 +-
> tools/perf/util/stat.c | 9 +++++++--
> tools/perf/util/stat.h | 3 ++-
> 6 files changed, 16 insertions(+), 10 deletions(-)
>
> diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
> index 7ca238277d83..691915a71c86 100644
> --- a/tools/perf/builtin-script.c
> +++ b/tools/perf/builtin-script.c
> @@ -2049,7 +2049,7 @@ static void perf_sample__fprint_metric(struct perf_script *script,
> u64 val;
>
> if (!evsel->stats)
> - evlist__alloc_stats(script->session->evlist, false);
> + evlist__alloc_stats(&stat_config, script->session->evlist, false);
> if (evsel_script(leader)->gnum++ == 0)
> perf_stat__reset_shadow_stats();
> val = sample->period * evsel->scale;
> @@ -3632,7 +3632,7 @@ static int set_maps(struct perf_script *script)
>
> perf_evlist__set_maps(&evlist->core, script->cpus, script->threads);
>
> - if (evlist__alloc_stats(evlist, true))
> + if (evlist__alloc_stats(&stat_config, evlist, true))
> return -ENOMEM;
>
> script->allocated = true;
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index e5ddf60ab31d..eaddafbd7ff2 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -2124,7 +2124,7 @@ static int set_maps(struct perf_stat *st)
>
> perf_evlist__set_maps(&evsel_list->core, st->cpus, st->threads);
>
> - if (evlist__alloc_stats(evsel_list, true))
> + if (evlist__alloc_stats(&stat_config, evsel_list, true))
> return -ENOMEM;
>
> st->maps_allocated = true;
> @@ -2571,10 +2571,10 @@ int cmd_stat(int argc, const char **argv)
> goto out;
> }
>
> - if (evlist__alloc_stats(evsel_list, interval))
> + if (perf_stat_init_aggr_mode())
> goto out;
>
> - if (perf_stat_init_aggr_mode())
> + if (evlist__alloc_stats(&stat_config, evsel_list, interval))
> goto out;
>
> /*
> diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
> index 68f5a2a03242..cb3a9b795c0f 100644
> --- a/tools/perf/tests/parse-metric.c
> +++ b/tools/perf/tests/parse-metric.c
> @@ -103,7 +103,7 @@ static int __compute_metric(const char *name, struct value *vals,
> if (err)
> goto out;
>
> - err = evlist__alloc_stats(evlist, false);
> + err = evlist__alloc_stats(NULL, evlist, false);
> if (err)
> goto out;
>
> diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
> index 097e05c796ab..a5e1028dacfc 100644
> --- a/tools/perf/tests/pmu-events.c
> +++ b/tools/perf/tests/pmu-events.c
> @@ -889,7 +889,7 @@ static int test__parsing_callback(const struct pmu_event *pe, const struct pmu_e
> goto out_err;
> }
>
> - err = evlist__alloc_stats(evlist, false);
> + err = evlist__alloc_stats(NULL, evlist, false);
> if (err)
> goto out_err;
> /*
> diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> index c9d5aa295b54..374149628507 100644
> --- a/tools/perf/util/stat.c
> +++ b/tools/perf/util/stat.c
> @@ -211,12 +211,17 @@ static int evsel__alloc_stats(struct evsel *evsel, int nr_aggr, bool alloc_raw)
> return 0;
> }
>
> -int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
> +int evlist__alloc_stats(struct perf_stat_config *config,
> + struct evlist *evlist, bool alloc_raw)
> {
> struct evsel *evsel;
> + int nr_aggr = 0;
> +
> + if (config && config->aggr_map)
> + nr_aggr = config->aggr_map->nr;
>
> evlist__for_each_entry(evlist, evsel) {
> - if (evsel__alloc_stats(evsel, 0, alloc_raw))
> + if (evsel__alloc_stats(evsel, nr_aggr, alloc_raw))
> goto out_free;
> }
>
> diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
> index ea356e5aa351..74bd51a3cb36 100644
> --- a/tools/perf/util/stat.h
> +++ b/tools/perf/util/stat.h
> @@ -257,7 +257,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
> struct runtime_stat *st);
> void perf_stat__collect_metric_expr(struct evlist *);
>
> -int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw);
> +int evlist__alloc_stats(struct perf_stat_config *config,
> + struct evlist *evlist, bool alloc_raw);
> void evlist__free_stats(struct evlist *evlist);
> void evlist__reset_stats(struct evlist *evlist);
> void evlist__reset_prev_raw_counts(struct evlist *evlist);
> --
> 2.38.0.rc1.362.ged0d419d3c-goog
>
On Mon, Oct 10, 2022 at 4:03 PM Ian Rogers <irogers@google.com> wrote: > > On Sun, Oct 9, 2022 at 10:36 PM Namhyung Kim <namhyung@kernel.org> wrote: > > > > The perf_stat_config.aggr_map should have a correct size of the > > aggregation map. Use it to allocate aggr_counts. > > > > Also AGGR_NONE with per-core events can be tricky because it doesn't > > aggreate basically but it needs to do so for per-core events only. > > nit: s/aggreate/aggregate/ > > > So only per-core evsels will have stats->aggr data. > > > > Note that other caller of evlist__alloc_stat() might not have > > stat_config or aggr_map. > > > > Signed-off-by: Namhyung Kim <namhyung@kernel.org> > > Acked-by: Ian Rogers <irogers@google.com> > > nit: Below there are use of constants true, false and NULL, it would > be nice to use the /*argument_name=*/... style parameter passing to be > clearer on what the parameter means. Sounds good. Will add. Thanks, Namhyung
© 2016 - 2026 Red Hat, Inc.