[4.14,31/75] perf/core: Fix __perf_read_group_add() locking
diff mbox series

Message ID 20171207130820.020591977@linuxfoundation.org
State New, archived
Headers show
  • 4.14.5-stable review
Related show

Commit Message

Greg KH Dec. 7, 2017, 1:07 p.m. UTC
4.14-stable review patch.  If anyone has any objections, please let me know.


From: Peter Zijlstra <peterz@infradead.org>

[ Upstream commit a9cd8194e1e6bd09619954721dfaf0f94fe2003e ]

Event timestamps are serialized using ctx->lock, make sure to hold it
over reading all values.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 kernel/events/core.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff mbox series

--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4433,6 +4433,8 @@  static int __perf_read_group_add(struct
 	if (ret)
 		return ret;
+	raw_spin_lock_irqsave(&ctx->lock, flags);
 	 * Since we co-schedule groups, {enabled,running} times of siblings
 	 * will be identical to those of the leader, so we only publish one
@@ -4455,8 +4457,6 @@  static int __perf_read_group_add(struct
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(leader);
-	raw_spin_lock_irqsave(&ctx->lock, flags);
 	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
 		values[n++] += perf_event_count(sub);
 		if (read_format & PERF_FORMAT_ID)