Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Jiri Olsa <jolsa@kernel.org>
To:     Arnaldo Carvalho de Melo <acme@kernel.org>
Cc:     Jin Yao <yao.jin@linux.intel.com>,
        lkml <linux-kernel@vger.kernel.org>,
        Ingo Molnar <mingo@kernel.org>,
        Namhyung Kim <namhyung@kernel.org>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Peter Zijlstra <a.p.zijlstra@chello.nl>,
        Michael Petlan <mpetlan@redhat.com>,
        Ian Rogers <irogers@google.com>,
        Stephane Eranian <eranian@google.com>,
        Andi Kleen <ak@linux.intel.com>
Subject: [PATCH] perf stat: Ensure group is defined on top of the same cpu mask
Date:   Sun, 31 May 2020 18:22:06 +0200
Message-Id: <20200531162206.911168-1-jolsa@kernel.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=WINDOWS-1252
Content-Transfer-Encoding: 8BIT
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

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/ }

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 | 51 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b2b79aa161dd..512a41363d07 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -190,6 +190,55 @@ 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);
+
+		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)
 {
@@ -1962,6 +2011,8 @@ int cmd_stat(int argc, const char **argv)
 	} else if (argc && !strncmp(argv[0], "rep", 3))
 		return __cmd_report(argc, argv);
 
+	evlist__check_cpu_maps(evsel_list);
+
 	interval = stat_config.interval;
 	timeout = stat_config.timeout;
 
-- 
2.25.4