[PATCH 4.9 44/53] futex: Fix (possible) missed wakeup

[Greg Kroah-Hartman]

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

commit b061c38bef43406df8e73c5be06cbfacad5ee6ad upstream.

We must not rely on wake_q_add() to delay the wakeup; in particular
commit:

  1d0dcb3ad9d3 ("futex: Implement lockless wakeups")

moved wake_q_add() before smp_store_release(&q->lock_ptr, NULL), which
could result in futex_wait() waking before observing ->lock_ptr ==
NULL and going back to sleep again.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Fixes: 1d0dcb3ad9d3 ("futex: Implement lockless wakeups")
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 kernel/futex.c |   13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1553,11 +1553,7 @@ static void mark_wake_futex(struct wake_
 	if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
 		return;
 
-	/*
-	 * Queue the task for later wakeup for after we've released
-	 * the hb->lock. wake_q_add() grabs reference to p.
-	 */
-	wake_q_add(wake_q, p);
+	get_task_struct(p);
 	__unqueue_futex(q);
 	/*
 	 * The waiting task can free the futex_q as soon as
@@ -1566,6 +1562,13 @@ static void mark_wake_futex(struct wake_
 	 * store to lock_ptr from getting ahead of the plist_del.
 	 */
 	smp_store_release(&q->lock_ptr, NULL);
+
+	/*
+	 * Queue the task for later wakeup for after we've released
+	 * the hb->lock. wake_q_add() grabs reference to p.
+	 */
+	wake_q_add(wake_q, p);
+	put_task_struct(p);
 }
 
 /*