[PATCHv2] perf stat: Ensure group is defined on top of the same cpu mask

[Jiri Olsa <jolsa@redhat.com>]

Jin Yao reported the issue (and posted first versions of this change)
with groups being defined over events with different cpu mask.

This causes assert aborts in get_group_fd, like:

  # perf stat -M "C2_Pkg_Residency" -a -- sleep 1
  perf: util/evsel.c:1464: get_group_fd: Assertion `!(fd == -1)' failed.
  Aborted

All the events in the group have to be defined over the same
cpus so the group_fd can be found for every leader/member pair.

Adding check to ensure this condition is met and removing the
group (with warning) if we detect mixed cpus, like:

  $ sudo perf stat -e '{power/energy-cores/,cycles},{instructions,power/energy-cores/}'
  WARNING: event cpu maps do not match, disabling group:
    anon group { power/energy-cores/, cycles }
    anon group { instructions, power/energy-cores/ }

Ian asked also for cpu maps details, it's displayed in verbose mode:

  $ sudo perf stat -e '{cycles,power/energy-cores/}' -v
  WARNING: group events cpu maps do not match, disabling group:
    anon group { power/energy-cores/, cycles }
       power/energy-cores/: 0
       cycles: 0-7
    anon group { instructions, power/energy-cores/ }
       instructions: 0-7
       power/energy-cores/: 0

Fixes: 6a4bb04caacc8 ("perf tools: Enable grouping logic for parsed events")
Co-developed-by: Jin Yao <yao.jin@linux.intel.com>
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 58 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)

v2 changes:
  - display mixed events maps in verbose mode

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b2b79aa161dd..dda60b9dbc63 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -190,6 +190,62 @@ static struct perf_stat_config stat_config = {
 	.big_num		= true,
 };
 
+static bool cpus_map_matched(struct evsel *a, struct evsel *b)
+{
+	if (!a->core.cpus && !b->core.cpus)
+		return true;
+
+	if (!a->core.cpus || !b->core.cpus)
+		return false;
+
+	if (a->core.cpus->nr != b->core.cpus->nr)
+		return false;
+
+	for (int i = 0; i < a->core.cpus->nr; i++) {
+		if (a->core.cpus->map[i] != b->core.cpus->map[i])
+			return false;
+	}
+
+	return true;
+}
+
+static void evlist__check_cpu_maps(struct evlist *evlist)
+{
+	struct evsel *evsel, *pos, *leader;
+	char buf[1024];
+
+	evlist__for_each_entry(evlist, evsel) {
+		leader = evsel->leader;
+
+		/* Check that leader matches cpus with each member. */
+		if (leader == evsel)
+			continue;
+		if (cpus_map_matched(leader, evsel))
+			continue;
+
+		/*
+		 * If there's mismatch display dismantle the
+		 * group and warn user.
+		 */
+		WARN_ONCE(1, "WARNING: group events cpu maps do not match, disabling group:\n");
+		evsel__group_desc(leader, buf, sizeof(buf));
+		pr_warning("  %s\n", buf);
+
+		if (verbose) {
+			cpu_map__snprint(leader->core.cpus, buf, sizeof(buf));
+			pr_warning("     %s: %s\n", leader->name, buf);
+			cpu_map__snprint(evsel->core.cpus, buf, sizeof(buf));
+			pr_warning("     %s: %s\n", evsel->name, buf);
+		}
+
+		for_each_group_evsel(pos, leader) {
+			pos->leader = pos;
+			pos->core.nr_members = 0;
+		}
+		evsel->leader->core.nr_members = 0;
+	}
+}
+
 static inline void diff_timespec(struct timespec *r, struct timespec *a,
 				 struct timespec *b)
 {
@@ -2113,6 +2169,8 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
+	evlist__check_cpu_maps(evsel_list);
+
 	/*
 	 * Initialize thread_map with comm names,
 	 * so we could print it out on output.
-- 
2.25.4