From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
commit 3ac6487e584a1eb54071dbe1212e05b884136704 upstream.
Norbert reported that it's possible to race sys_perf_event_open() such
that the looser ends up in another context from the group leader,
triggering many WARNs.
The move_group case checks for races against itself, but the
!move_group case doesn't, seemingly relying on the previous
group_leader->ctx == ctx check. However, that check is racy due to not
holding any locks at that time.
Therefore, re-check the result after acquiring locks and bailing
if they no longer match.
Additionally, clarify the not_move_group case from the
move_group-vs-move_group race.
Fixes: f63a8daa5812 ("perf: Fix event->ctx locking")
Reported-by: Norbert Slusarek <nslusarek@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
kernel/events/core.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11114,6 +11114,9 @@ SYSCALL_DEFINE5(perf_event_open,
* Do not allow to attach to a group in a different task
* or CPU context. If we're moving SW events, we'll fix
* this up later, so allow that.
+ *
+ * Racy, not holding group_leader->ctx->mutex, see comment with
+ * perf_event_ctx_lock().
*/
if (!move_group && group_leader->ctx != ctx)
goto err_context;
@@ -11181,6 +11184,7 @@ SYSCALL_DEFINE5(perf_event_open,
} else {
perf_event_ctx_unlock(group_leader, gctx);
move_group = 0;
+ goto not_move_group;
}
}
@@ -11197,7 +11201,17 @@ SYSCALL_DEFINE5(perf_event_open,
}
} else {
mutex_lock(&ctx->mutex);
+
+ /*
+ * Now that we hold ctx->lock, (re)validate group_leader->ctx == ctx,
+ * see the group_leader && !move_group test earlier.
+ */
+ if (group_leader && group_leader->ctx != ctx) {
+ err = -EINVAL;
+ goto err_locked;
+ }
}
+not_move_group:
if (ctx->task == TASK_TOMBSTONE) {
err = -ESRCH;
