perf stat: Add perf_stat_merge_counters()

The perf_stat_merge_counters() is to aggregate the same events in different
PMUs like in case of uncore or hybrid.  The same logic is in the stat-display
routines but I think it should be handled when it processes the event counters.

As it works on the aggr_counters, it doesn't change the output yet.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20221018020227.85905-16-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 838d29590bed9583867326201820bdfb2f7079e5..371d6e8969422d1e89aa10e30701c04fc9248145 100644 (file)
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -486,6 +486,8 @@ static void process_counters(void)
                        pr_warning("failed to process counter %s\n", counter->name);
                counter->err = 0;
        }
+
+       perf_stat_merge_counters(&stat_config, evsel_list);
 }
 
 static void process_interval(void)

diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index a4066f0d363792834d2b34555ef2c856c68dd6c6..aff1e7390585cdb56966f463678ad5877e95ac06 100644 (file)
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -595,6 +595,102 @@ int perf_stat_process_counter(struct perf_stat_config *config,
        return 0;
 }
 
+static int evsel__merge_aggr_counters(struct evsel *evsel, struct evsel *alias)
+{
+       struct perf_stat_evsel *ps_a = evsel->stats;
+       struct perf_stat_evsel *ps_b = alias->stats;
+       int i;
+
+       if (ps_a->aggr == NULL && ps_b->aggr == NULL)
+               return 0;
+
+       if (ps_a->nr_aggr != ps_b->nr_aggr) {
+               pr_err("Unmatched aggregation mode between aliases\n");
+               return -1;
+       }
+
+       for (i = 0; i < ps_a->nr_aggr; i++) {
+               struct perf_counts_values *aggr_counts_a = &ps_a->aggr[i].counts;
+               struct perf_counts_values *aggr_counts_b = &ps_b->aggr[i].counts;
+
+               /* NB: don't increase aggr.nr for aliases */
+
+               aggr_counts_a->val += aggr_counts_b->val;
+               aggr_counts_a->ena += aggr_counts_b->ena;
+               aggr_counts_a->run += aggr_counts_b->run;
+       }
+
+       return 0;
+}
+/* events should have the same name, scale, unit, cgroup but on different PMUs */
+static bool evsel__is_alias(struct evsel *evsel_a, struct evsel *evsel_b)
+{
+       if (strcmp(evsel__name(evsel_a), evsel__name(evsel_b)))
+               return false;
+
+       if (evsel_a->scale != evsel_b->scale)
+               return false;
+
+       if (evsel_a->cgrp != evsel_b->cgrp)
+               return false;
+
+       if (strcmp(evsel_a->unit, evsel_b->unit))
+               return false;
+
+       if (evsel__is_clock(evsel_a) != evsel__is_clock(evsel_b))
+               return false;
+
+       return !!strcmp(evsel_a->pmu_name, evsel_b->pmu_name);
+}
+
+static void evsel__merge_aliases(struct evsel *evsel)
+{
+       struct evlist *evlist = evsel->evlist;
+       struct evsel *alias;
+
+       alias = list_prepare_entry(evsel, &(evlist->core.entries), core.node);
+       list_for_each_entry_continue(alias, &evlist->core.entries, core.node) {
+               /* Merge the same events on different PMUs. */
+               if (evsel__is_alias(evsel, alias)) {
+                       evsel__merge_aggr_counters(evsel, alias);
+                       alias->merged_stat = true;
+               }
+       }
+}
+
+static bool evsel__should_merge_hybrid(struct evsel *evsel, struct perf_stat_config *config)
+{
+       struct perf_pmu *pmu;
+
+       if (!config->hybrid_merge)
+               return false;
+
+       pmu = evsel__find_pmu(evsel);
+       return pmu && pmu->is_hybrid;
+}
+
+static void evsel__merge_stats(struct evsel *evsel, struct perf_stat_config *config)
+{
+       /* this evsel is already merged */
+       if (evsel->merged_stat)
+               return;
+
+       if (evsel->auto_merge_stats || evsel__should_merge_hybrid(evsel, config))
+               evsel__merge_aliases(evsel);
+}
+
+/* merge the same uncore and hybrid events if requested */
+void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *evlist)
+{
+       struct evsel *evsel;
+
+       if (config->no_merge)
+               return;
+
+       evlist__for_each_entry(evlist, evsel)
+               evsel__merge_stats(evsel, config);
+}
+
 int perf_event__process_stat_event(struct perf_session *session,
                                   union perf_event *event)
 {

diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 809f9f0aff0c33cb1aee4dea2df02880583f7b17..728bbc823b0d29f2c2167fe4ae950c2a47293be7 100644 (file)
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -280,6 +280,8 @@ void evlist__reset_aggr_stats(struct evlist *evlist);
 
 int perf_stat_process_counter(struct perf_stat_config *config,
                              struct evsel *counter);
+void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *evlist);
+
 struct perf_tool;
 union perf_event;
 struct perf_session;