perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown

Normally, --for-each-cgroup only works with AGGR_GLOBAL.  However
the --topdown on some cpu (e.g. Intel Skylake) converts it to the
AGGR_CORE internally.

To support those machines, add print_aggr_cgroup and handle the events
like in print_cgroup_events().

  $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1
  nmi_watchdog enabled with topdown. May give wrong results.
  Disable with echo 0 > /proc/sys/kernel/nmi_watchdog

   Performance counter stats for 'system wide':

                               retiring   bad speculation  frontend bound  backend bound
  S0-D0-C0  2  system.slice       49.0%            -46.6%           31.4%
  S0-D0-C1  2  system.slice       55.5%              8.0%           45.5%          -9.0%
  S0-D0-C2  2  system.slice       87.8%             22.1%           30.3%         -40.3%
  S0-D0-C3  2  system.slice       53.3%            -11.9%           45.2%          13.4%
  S0-D0-C0  2  user.slice        123.5%              4.0%           48.5%         -75.9%
  S0-D0-C1  2  user.slice         19.9%              6.5%           89.9%         -16.3%
  S0-D0-C2  2  user.slice         29.9%              7.9%           71.3%          -9.1
  S0-D0-C3  2  user.slice         28.0%              7.2%           43.3%          21.5%

         1.004136937 seconds time elapsed
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@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: Peter Zijlstra <peterz@infradead.org>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.orgSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/stat-display.c

@@ -900,6 +900,42 @@ static void print_aggr(struct perf_stat_config *config,
 	}
 }
 
+static void print_aggr_cgroup(struct perf_stat_config *config,
+			      struct evlist *evlist,
+			      char *prefix)
+{
+	bool metric_only = config->metric_only;
+	struct evsel *counter, *evsel;
+	struct cgroup *cgrp = NULL;
+	int s;
+
+	if (!config->aggr_map || !config->aggr_get_id)
+		return;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (cgrp == evsel->cgrp)
+			continue;
+
+		cgrp = evsel->cgrp;
+
+		for (s = 0; s < config->aggr_map->nr; s++) {
+			print_metric_begin(config, evlist, prefix, s, cgrp);
+
+			evlist__for_each_entry(evlist, counter) {
+				if (counter->merged_stat)
+					continue;
+
+				if (counter->cgrp != cgrp)
+					continue;
+
+				print_counter_aggrdata(config, counter, s, prefix,
+						       metric_only);
+			}
+			print_metric_end(config);
+		}
+	}
+}
+
 static void print_counter(struct perf_stat_config *config,
 			  struct evsel *counter, char *prefix)
 {
@@ -1361,7 +1397,10 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf
 	case AGGR_DIE:
 	case AGGR_SOCKET:
 	case AGGR_NODE:
-		print_aggr(config, evlist, prefix);
+		if (config->cgroup_list)
+			print_aggr_cgroup(config, evlist, prefix);
+		else
+			print_aggr(config, evlist, prefix);
 		break;
 	case AGGR_THREAD:
 	case AGGR_GLOBAL: