perf stat: Display percore events properly

The recent change in the perf stat broke the percore event display.
Note that the aggr counts are already processed so that the every
sibling thread in the same core will get the per-core counter values.

Check percore evsels and skip the sibling threads in the display.

Signed-off-by: Namhyung Kim <[e-mail]>
Acked-by: Ian Rogers <[e-mail]>
Cc: Adrian Hunter <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Athira Jajeev <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: James Clark <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Kan Liang <[e-mail]>
Cc: Leo Yan <[e-mail]>
Cc: Michael Petlan <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Xing Zhengjun <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/builtin-stat.c

···
 	return perf_stat__get_aggr(config, perf_stat__get_cpu, cpu);
 }
 
-static bool term_percore_set(void)
-{
-	struct evsel *counter;
-
-	evlist__for_each_entry(evsel_list, counter) {
-		if (counter->percore)
-			return true;
-	}
-
-	return false;
-}
-
 static aggr_cpu_id_get_t aggr_mode__get_aggr(enum aggr_mode aggr_mode)
 {
 	switch (aggr_mode) {
···
 	case AGGR_NODE:
 		return aggr_cpu_id__node;
 	case AGGR_NONE:
-		if (term_percore_set())
-			return aggr_cpu_id__core;
 		return aggr_cpu_id__cpu;
 	case AGGR_GLOBAL:
 		return aggr_cpu_id__global;
···
 	case AGGR_NODE:
 		return perf_stat__get_node_cached;
 	case AGGR_NONE:
-		if (term_percore_set())
-			return perf_stat__get_core_cached;
 		return perf_stat__get_cpu_cached;
 	case AGGR_GLOBAL:
 		return perf_stat__get_global_cached;

tools/perf/util/stat-display.c

···
 {
 	bool metric_only = config->metric_only;
 	FILE *output = config->output;
-	int s;
+	struct cpu_aggr_map *core_map;
+	int s, c, i;
 	bool first = true;
 
 	if (!config->aggr_map || !config->aggr_get_id)
···
 	if (config->percore_show_thread)
 		return print_counter(config, counter, prefix);
 
-	for (s = 0; s < config->aggr_map->nr; s++) {
+	core_map = cpu_aggr_map__empty_new(config->aggr_map->nr);
+	if (core_map == NULL) {
+		fprintf(output, "Cannot allocate per-core aggr map for display\n");
+		return;
+	}
+
+	for (s = 0, c = 0; s < config->aggr_map->nr; s++) {
+		struct perf_cpu curr_cpu = config->aggr_map->map[s].cpu;
+		struct aggr_cpu_id core_id = aggr_cpu_id__core(curr_cpu, NULL);
+		bool found = false;
+
+		for (i = 0; i < c; i++) {
+			if (aggr_cpu_id__equal(&core_map->map[i], &core_id)) {
+				found = true;
+				break;
+			}
+		}
+		if (found)
+			continue;
+
 		if (prefix && metric_only)
 			fprintf(output, "%s", prefix);
 
 		print_counter_aggrdata(config, counter, s,
 				       prefix, metric_only, &first);
+
+		core_map->map[c++] = core_id;
 	}
+	free(core_map);
 
 	if (metric_only)
 		fputc('\n', output);