[PATCH 18/19] perf stat: Display percore events properly

[Namhyung Kim]

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 <namhyung@xxxxxxxxxx>
---
 tools/perf/builtin-stat.c      | 16 ----------------
 tools/perf/util/stat-display.c | 27 +++++++++++++++++++++++++--
 2 files changed, 25 insertions(+), 18 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d92815f4eae0..b3a39d4c86a7 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1403,18 +1403,6 @@ static struct aggr_cpu_id perf_stat__get_cpu_cached(struct perf_stat_config *con
 	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) {
@@ -1427,8 +1415,6 @@ static aggr_cpu_id_get_t aggr_mode__get_aggr(enum aggr_mode 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;
@@ -1452,8 +1438,6 @@ static aggr_get_id_t aggr_mode__get_id(enum aggr_mode aggr_mode)
 	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;
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 0c0e22c175a1..e0c0df99d40d 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -1094,7 +1094,8 @@ static void print_percore(struct perf_stat_config *config,
 {
 	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)
@@ -1103,13 +1104,35 @@ static void print_percore(struct perf_stat_config *config,
 	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);
-- 
2.38.0.rc1.362.ged0d419d3c-goog