[PATCH] perf: Fix perf_event_for_each() to use sibling

[Michael Ellerman <michael@ellerman.id.au>]

In perf_event_for_each() we call a function on an event, and then
iterate over the siblings of the event.

However we don't call the function on the siblings, we call it
repeatedly on the original event - it seems "obvious" that we should
be calling it with sibling as the argument.

It looks like this broke in commit 75f937f24bd9 ("Fix ctx->mutex
vs counter->mutex inversion").

The only effect of the bug is that the PERF_IOC_FLAG_GROUP parameter
to the ioctls doesn't work.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
---

This one seems so simple that I keep thinking I've missed something,
I'm sure someone will tell me if I have ;)

AFAICS tools/perf never exercises this, ie. it always individually
enables counters - which might explain how it could be broken and
no one has noticed.
---
 kernel/events/core.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1b5c081..b82121b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3097,7 +3097,7 @@ static void perf_event_for_each(struct perf_event *event,
 	perf_event_for_each_child(event, func);
 	func(event);
 	list_for_each_entry(sibling, &event->sibling_list, group_entry)
-		perf_event_for_each_child(event, func);
+		perf_event_for_each_child(sibling, func);
 	mutex_unlock(&ctx->mutex);
 }
 
-- 
1.7.5.4