perf stat: Add requires_cpu flag for uncore

Uncore events require a CPU i.e. it cannot be -1.

The evsel system_wide flag is intended for events that should be on every
CPU, which does not make sense for uncore events because uncore events do
not map one-to-one with CPUs.

These 2 requirements are not exactly the same, so introduce a new flag
'requires_cpu' for the uncore case.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Link: https://lore.kernel.org/r/20220524075436.29144-13-adrian.hunter@intel.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/lib/perf/evlist.c

@@ -43,7 +43,9 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 	if (!evsel->own_cpus || evlist->has_user_cpus) {
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
-	} else if (!evsel->system_wide && perf_cpu_map__empty(evlist->user_requested_cpus)) {
+	} else if (!evsel->system_wide &&
+		   !evsel->requires_cpu &&
+		   perf_cpu_map__empty(evlist->user_requested_cpus)) {
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
 	} else if (evsel->cpus != evsel->own_cpus) {

tools/lib/perf/include/internal/evsel.h

@@ -50,6 +50,7 @@ struct perf_evsel {
 	/* parse modifier helper */
 	int			 nr_members;
 	bool			 system_wide;
+	bool			 requires_cpu;
 	int			 idx;
 };
 

tools/perf/builtin-stat.c

@@ -382,9 +382,6 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_
 	if (!counter->supported)
 		return -ENOENT;
 
-	if (counter->core.system_wide)
-		nthreads = 1;
-
 	for (thread = 0; thread < nthreads; thread++) {
 		struct perf_counts_values *count;
 
@@ -2261,7 +2258,7 @@ static void setup_system_wide(int forks)
 		struct evsel *counter;
 
 		evlist__for_each_entry(evsel_list, counter) {
-			if (!counter->core.system_wide &&
+			if (!counter->core.requires_cpu &&
 			    strcmp(counter->name, "duration_time")) {
 				return;
 			}

tools/perf/util/evsel.c

@@ -409,6 +409,7 @@ struct evsel *evsel__clone(struct evsel *orig)
 	evsel->core.threads = perf_thread_map__get(orig->core.threads);
 	evsel->core.nr_members = orig->core.nr_members;
 	evsel->core.system_wide = orig->core.system_wide;
+	evsel->core.requires_cpu = orig->core.requires_cpu;
 
 	if (orig->name) {
 		evsel->name = strdup(orig->name);

tools/perf/util/parse-events.c

@@ -365,7 +365,7 @@ __add_event(struct list_head *list, int *idx,
 	(*idx)++;
 	evsel->core.cpus = cpus;
 	evsel->core.own_cpus = perf_cpu_map__get(cpus);
-	evsel->core.system_wide = pmu ? pmu->is_uncore : false;
+	evsel->core.requires_cpu = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 
 	if (name)