perf stat: Merge uncore events by default for hybrid platform

On a hybrid platform, by default 'perf stat' aggregates and reports the
event counts per PMU. For example,

  # perf stat -e cycles -a true

   Performance counter stats for 'system wide':

           1,400,445      cpu_core/cycles/
             680,881      cpu_atom/cycles/

         0.001770773 seconds time elapsed

But for uncore events that's not a suitable method. Uncore has nothing
to do with hybrid. So for uncore events, we aggregate event counts from
all PMUs and report the counts without PMUs.

Before:

  # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ -a true

   Performance counter stats for 'system wide':

               2,058      uncore_arb_0/event=0x81,umask=0x1/
               2,028      uncore_arb_1/event=0x81,umask=0x1/
                   0      uncore_arb_0/event=0x84,umask=0x1/
                   0      uncore_arb_1/event=0x84,umask=0x1/

         0.000614498 seconds time elapsed

After:

  # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ -a true

   Performance counter stats for 'system wide':

               3,996      arb/event=0x81,umask=0x1/
                   0      arb/event=0x84,umask=0x1/

         0.000630046 seconds time elapsed

Of course, we also keep the '--no-merge' working for uncore events.

  # perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ --no-merge true

   Performance counter stats for 'system wide':

               1,952      uncore_arb_0/event=0x81,umask=0x1/
               1,921      uncore_arb_1/event=0x81,umask=0x1/
                   0      uncore_arb_0/event=0x84,umask=0x1/
                   0      uncore_arb_1/event=0x84,umask=0x1/

         0.000575536 seconds time elapsed
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210707055652.962-1-yao.jin@linux.intel.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-stat.c

@@ -2445,9 +2445,6 @@ int cmd_stat(int argc, const char **argv)
 
 	evlist__check_cpu_maps(evsel_list);
 
-	if (perf_pmu__has_hybrid())
-		stat_config.no_merge = true;
-
 	/*
 	 * Initialize thread_map with comm names,
 	 * so we could print it out on output.

tools/perf/util/stat-display.c

@@ -596,6 +596,18 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c
 	}
 }
 
+static bool is_uncore(struct evsel *evsel)
+{
+	struct perf_pmu *pmu = evsel__find_pmu(evsel);
+
+	return pmu && pmu->is_uncore;
+}
+
+static bool hybrid_uniquify(struct evsel *evsel)
+{
+	return perf_pmu__has_hybrid() && !is_uncore(evsel);
+}
+
 static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
 			    void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
 				       bool first),
@@ -604,7 +616,7 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
 	if (counter->merged_stat)
 		return false;
 	cb(config, counter, data, true);
-	if (config->no_merge)
+	if (config->no_merge || hybrid_uniquify(counter))
 		uniquify_event_name(counter);
 	else if (counter->auto_merge_stats)
 		collect_all_aliases(config, counter, cb, data);