perf stat: Aggregate events using evsel->stats->aggr

Add a logic to aggregate counter values to the new evsel->stats->aggr.
This is not used yet so shadow stats are not updated.  But later patch
will convert the existing code to use it.

With that, we don't need to handle AGGR_GLOBAL specially anymore.  It
can use the same logic with counts, prev_counts and aggr_counts.
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/20221018020227.85905-10-namhyung@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-stat.c

@@ -963,9 +963,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		init_stats(&walltime_nsecs_stats);
 		update_stats(&walltime_nsecs_stats, t1 - t0);
 
-		if (stat_config.aggr_mode == AGGR_GLOBAL)
-			evlist__save_aggr_prev_raw_counts(evsel_list);
-
 		evlist__copy_prev_raw_counts(evsel_list);
 		evlist__reset_prev_raw_counts(evsel_list);
 		perf_stat__reset_shadow_per_stat(&rt_stat);

tools/perf/util/evsel.c

@@ -1526,13 +1526,8 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread,
 	if (!evsel->prev_raw_counts)
 		return;
 
-	if (cpu_map_idx == -1) {
-		tmp = evsel->prev_raw_counts->aggr;
-		evsel->prev_raw_counts->aggr = *count;
-	} else {
-		tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
-		*perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
-	}
+	tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
+	*perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
 
 	count->val = count->val - tmp.val;
 	count->ena = count->ena - tmp.ena;

tools/perf/util/scripting-engines/trace-event-python.c

@@ -1653,12 +1653,6 @@ static void python_process_stat(struct perf_stat_config *config,
 	struct perf_cpu_map *cpus = counter->core.cpus;
 	int cpu, thread;
 
-	if (config->aggr_mode == AGGR_GLOBAL) {
-		process_stat(counter, (struct perf_cpu){ .cpu = -1 }, -1, tstamp,
-			     &counter->counts->aggr);
-		return;
-	}
-
 	for (thread = 0; thread < threads->nr; thread++) {
 		for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
 			process_stat(counter, perf_cpu_map__cpu(cpus, cpu),

tools/perf/util/stat.c

@@ -387,6 +387,7 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 		       struct perf_counts_values *count)
 {
 	struct perf_counts_values *aggr = &evsel->counts->aggr;
+	struct perf_stat_evsel *ps = evsel->stats;
 	static struct perf_counts_values zero;
 	bool skip = false;
 
@@ -398,6 +399,44 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 	if (skip)
 		count = &zero;
 
+	if (!evsel->snapshot)
+		evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
+	perf_counts_values__scale(count, config->scale, NULL);
+
+	if (ps->aggr) {
+		struct perf_cpu cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx);
+		struct aggr_cpu_id aggr_id = config->aggr_get_id(config, cpu);
+		struct perf_stat_aggr *ps_aggr;
+		int i;
+
+		for (i = 0; i < ps->nr_aggr; i++) {
+			if (!aggr_cpu_id__equal(&aggr_id, &config->aggr_map->map[i]))
+				continue;
+
+			ps_aggr = &ps->aggr[i];
+			ps_aggr->nr++;
+
+			/*
+			 * When any result is bad, make them all to give
+			 * consistent output in interval mode.
+			 */
+			if (count->ena == 0 || count->run == 0 ||
+			    evsel->counts->scaled == -1) {
+				ps_aggr->counts.val = 0;
+				ps_aggr->counts.ena = 0;
+				ps_aggr->counts.run = 0;
+				ps_aggr->failed = true;
+			}
+
+			if (!ps_aggr->failed) {
+				ps_aggr->counts.val += count->val;
+				ps_aggr->counts.ena += count->ena;
+				ps_aggr->counts.run += count->run;
+			}
+			break;
+		}
+	}
+
 	switch (config->aggr_mode) {
 	case AGGR_THREAD:
 	case AGGR_CORE:
@@ -405,9 +444,6 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 	case AGGR_SOCKET:
 	case AGGR_NODE:
 	case AGGR_NONE:
-		if (!evsel->snapshot)
-			evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
-		perf_counts_values__scale(count, config->scale, NULL);
 		if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
 			perf_stat__update_shadow_stats(evsel, count->val,
 						       cpu_map_idx, &rt_stat);
@@ -469,10 +505,6 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 	if (config->aggr_mode != AGGR_GLOBAL)
 		return 0;
 
-	if (!counter->snapshot)
-		evsel__compute_deltas(counter, -1, -1, aggr);
-	perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled);
-
 	update_stats(&ps->res_stats, *count);
 
 	if (verbose > 0) {