perf tools: Add --pmu-filter option for filtering PMUs

This patch adds a new --pmu-filter option to perf-stat command to allow
filtering events on specific PMUs. This is useful when there are
multiple PMUs with same type (e.g. hisi_sicl2_cpa0 and hisi_sicl0_cpa0).

[root@localhost tmp]# perf stat -M cpa_p0_avg_bw
 Performance counter stats for 'system wide':

    19,417,779,115      hisi_sicl0_cpa0/cpa_cycles/      #     0.00 cpa_p0_avg_bw
                 0      hisi_sicl0_cpa0/cpa_p0_wr_dat/
                 0      hisi_sicl0_cpa0/cpa_p0_rd_dat_64b/
                 0      hisi_sicl0_cpa0/cpa_p0_rd_dat_32b/
    19,417,751,103      hisi_sicl10_cpa0/cpa_cycles/     #     0.00 cpa_p0_avg_bw
                 0      hisi_sicl10_cpa0/cpa_p0_wr_dat/
                 0      hisi_sicl10_cpa0/cpa_p0_rd_dat_64b/
                 0      hisi_sicl10_cpa0/cpa_p0_rd_dat_32b/
    19,417,730,679      hisi_sicl2_cpa0/cpa_cycles/      #     0.31 cpa_p0_avg_bw
        75,635,749      hisi_sicl2_cpa0/cpa_p0_wr_dat/
        18,520,640      hisi_sicl2_cpa0/cpa_p0_rd_dat_64b/
                 0      hisi_sicl2_cpa0/cpa_p0_rd_dat_32b/
    19,417,674,227      hisi_sicl8_cpa0/cpa_cycles/      #     0.00 cpa_p0_avg_bw
                 0      hisi_sicl8_cpa0/cpa_p0_wr_dat/
                 0      hisi_sicl8_cpa0/cpa_p0_rd_dat_64b/
                 0      hisi_sicl8_cpa0/cpa_p0_rd_dat_32b/

      19.417734480 seconds time elapsed

[root@localhost tmp]# perf stat --pmu-filter hisi_sicl2_cpa0 -M cpa_p0_avg_bw
 Performance counter stats for 'system wide':

     6,234,093,559      cpa_cycles                       #     0.60 cpa_p0_avg_bw
        50,548,465      cpa_p0_wr_dat
         7,552,182      cpa_p0_rd_dat_64b
                 0      cpa_p0_rd_dat_32b

       6.234139320 seconds time elapsed

Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

tools/perf/Documentation/perf-stat.txt

@@ -578,6 +578,10 @@ $ perf config stat.no-csv-summary=true
 Only enable events on applying cpu with this type for hybrid platform
 (e.g. core or atom)"
 
+--pmu-filter::
+Only enable events on applying pmu with specified for multiple
+pmus with same type (e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)
+
 EXAMPLES
 --------
 

tools/perf/builtin-stat.c

@@ -1214,6 +1214,21 @@ static int parse_cputype(const struct option *opt,
 	return 0;
 }
 
+static int parse_pmu_filter(const struct option *opt,
+			   const char *str,
+			   int unset __maybe_unused)
+{
+	struct evlist *evlist = *(struct evlist **)opt->value;
+
+	if (!list_empty(&evlist->core.entries)) {
+		fprintf(stderr, "Must define pmu-filter before events/metrics\n");
+		return -1;
+	}
+
+	parse_events_option_args.pmu_filter = str;
+	return 0;
+}
+
 static int parse_cache_level(const struct option *opt,
 			     const char *str,
 			     int unset __maybe_unused)
@@ -2564,6 +2579,10 @@ int cmd_stat(int argc, const char **argv)
 			"Only enable events on applying cpu with this type "
 			"for hybrid platform (e.g. core or atom)",
 			parse_cputype),
+		OPT_CALLBACK(0, "pmu-filter", &evsel_list, "pmu",
+			"Only enable events on applying pmu with specified "
+			"for multiple pmus with same type(e.g. hisi_sicl2_cpa0 or hisi_sicl0_cpa0)",
+			parse_pmu_filter),
 #ifdef HAVE_LIBPFM
 		OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
 			"libpfm4 event selector. use 'perf list' to list available events",

tools/perf/util/metricgroup.c

@@ -387,8 +387,13 @@ static bool match_pm_metric_or_groups(const struct pmu_metric *pm, const char *p
 				      const char *metric_or_groups)
 {
 	const char *pm_pmu = pm->pmu ?: "cpu";
+	struct perf_pmu *perf_pmu = NULL;
 
-	if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu))
+	if (pm->pmu)
+		perf_pmu = perf_pmus__find(pm->pmu);
+
+	if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu) &&
+	   (perf_pmu && !perf_pmu__name_wildcard_match(perf_pmu, pmu)))
 		return false;
 
 	return match_metric_or_groups(pm->metric_group, metric_or_groups) ||
@@ -1259,7 +1264,8 @@ static int build_combined_expr_ctx(const struct list_head *metric_list,
 static int parse_ids(bool metric_no_merge, bool fake_pmu,
 		     struct expr_parse_ctx *ids, const char *modifier,
 		     bool group_events, const bool tool_events[TOOL_PMU__EVENT_MAX],
-		     struct evlist **out_evlist)
+		     struct evlist **out_evlist,
+		     const char *filter_pmu)
 {
 	struct parse_events_error parse_error;
 	struct evlist *parsed_evlist;
@@ -1313,7 +1319,7 @@ static int parse_ids(bool metric_no_merge, bool fake_pmu,
 	}
 	pr_debug("Parsing metric events '%s'\n", events.buf);
 	parse_events_error__init(&parse_error);
-	ret = __parse_events(parsed_evlist, events.buf, /*pmu_filter=*/NULL,
+	ret = __parse_events(parsed_evlist, events.buf, filter_pmu,
 			     &parse_error, fake_pmu, /*warn_if_reordered=*/false,
 			     /*fake_tp=*/false);
 	if (ret) {
@@ -1416,7 +1422,8 @@ static int parse_groups(struct evlist *perf_evlist,
 					/*modifier=*/NULL,
 					/*group_events=*/false,
 					tool_events,
-					&combined_evlist);
+					&combined_evlist,
+					(pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
 		}
 		if (combined)
 			expr__ctx_free(combined);
@@ -1471,7 +1478,8 @@ static int parse_groups(struct evlist *perf_evlist,
 		}
 		if (!metric_evlist) {
 			ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
-					m->group_events, tool_events, &m->evlist);
+					m->group_events, tool_events, &m->evlist,
+					(pmu && strcmp(pmu, "all") == 0) ? NULL : pmu);
 			if (ret)
 				goto out;
 

tools/perf/util/parse-events.c

@@ -429,7 +429,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 	if (parse_state->pmu_filter == NULL)
 		return false;
 
-	return strcmp(parse_state->pmu_filter, pmu->name) != 0;
+	return perf_pmu__wildcard_match(pmu, parse_state->pmu_filter) == 0;
 }
 
 static int parse_events_add_pmu(struct parse_events_state *parse_state,