From 03f2357017c37d68e73d7d8d77abfcb72e12bc86 Mon Sep 17 00:00:00 2001 From: Weilin Wang <weilin.wang@intel.com> Date: Fri, 12 Apr 2024 14:07:41 -0700 Subject: [PATCH] perf stat: Add new field in stat_config to enable hardware aware grouping Hardware counter and event information could be used to help creating event groups that better utilize hardware counters and improve multiplexing. Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Weilin Wang <weilin.wang@intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Samantha Alt <samantha.alt@intel.com> Link: https://lore.kernel.org/r/20240412210756.309828-2-weilin.wang@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/builtin-stat.c | 5 +++++ tools/perf/util/metricgroup.c | 3 +++ tools/perf/util/metricgroup.h | 1 + tools/perf/util/stat.h | 1 + 4 files changed, 10 insertions(+) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 65388c57bb5d..65a3dd7ffac3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2085,6 +2085,7 @@ static int add_default_attributes(void) stat_config.metric_no_threshold, stat_config.user_requested_cpu_list, stat_config.system_wide, + stat_config.hardware_aware_grouping, &stat_config.metric_events); } @@ -2118,6 +2119,7 @@ static int add_default_attributes(void) stat_config.metric_no_threshold, stat_config.user_requested_cpu_list, stat_config.system_wide, + stat_config.hardware_aware_grouping, &stat_config.metric_events); } @@ -2152,6 +2154,7 @@ static int add_default_attributes(void) /*metric_no_threshold=*/true, stat_config.user_requested_cpu_list, stat_config.system_wide, + stat_config.hardware_aware_grouping, &stat_config.metric_events) < 0) return -1; } @@ -2193,6 +2196,7 @@ static int add_default_attributes(void) /*metric_no_threshold=*/true, stat_config.user_requested_cpu_list, stat_config.system_wide, + stat_config.hardware_aware_grouping, &stat_config.metric_events) < 0) return -1; @@ -2727,6 +2731,7 @@ int cmd_stat(int argc, const char **argv) stat_config.metric_no_threshold, stat_config.user_requested_cpu_list, stat_config.system_wide, + stat_config.hardware_aware_grouping, &stat_config.metric_events); zfree(&metrics); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 6ec083af14a1..9be406524617 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1690,12 +1690,15 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, + bool hardware_aware_grouping, struct rblist *metric_events) { const struct pmu_metrics_table *table = pmu_metrics_table__find(); if (!table) return -EINVAL; + if (hardware_aware_grouping) + pr_debug("Use hardware aware grouping instead of traditional metric grouping method\n"); return parse_groups(perf_evlist, pmu, str, metric_no_group, metric_no_merge, metric_no_threshold, user_requested_cpu_list, system_wide, diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index d5325c6ec8e1..779f6ede1b51 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -77,6 +77,7 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, + bool hardware_aware_grouping, struct rblist *metric_events); int metricgroup__parse_groups_test(struct evlist *evlist, const struct pmu_metrics_table *table, diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index d6e5c8787ba2..fd7a187551bd 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -87,6 +87,7 @@ struct perf_stat_config { bool metric_no_group; bool metric_no_merge; bool metric_no_threshold; + bool hardware_aware_grouping; bool stop_read_counter; bool iostat_run; char *user_requested_cpu_list; -- 2.30.9