sched/deadline: Fix races between rt_mutex_setprio() and dl_task_timer()

dl_task_timer() is racy against several paths. Daniel noticed that
the replenishment timer may experience a race condition against an
enqueue_dl_entity() called from rt_mutex_setprio(). With his own
words:

 rt_mutex_setprio() resets p->dl.dl_throttled. So the pattern is:
 start_dl_timer() throttled = 1, rt_mutex_setprio() throlled = 0,
 sched_switch() -> enqueue_task(), dl_task_timer-> enqueue_task()
 throttled is 0

=> BUG_ON(on_dl_rq(dl_se)) fires as the scheduling entity is already
enqueued on the -deadline runqueue.

As we do for the other races, we just bail out in the replenishment
timer code.

Reported-by: Daniel Wagner <[email protected]>
Tested-by: Daniel Wagner <[email protected]>
Signed-off-by: Juri Lelli <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: [email protected]
Cc: Dario Faggioli <[email protected]>
Cc: Michael Trimarchi <[email protected]>
Cc: Fabio Checconi <[email protected]>
Cc: Linus Torvalds <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

1 files changed, 13 insertions, 5 deletions

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 92279eaf0ef2..46167899d852 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -518,12 +518,20 @@ again:
 	}
 
 	/*
-	 * We need to take care of a possible races here. In fact, the
-	 * task might have changed its scheduling policy to something
-	 * different from SCHED_DEADLINE or changed its reservation
-	 * parameters (through sched_setattr()).
+	 * We need to take care of several possible races here:
+	 *
+	 *   - the task might have changed its scheduling policy
+	 *     to something different than SCHED_DEADLINE
+	 *   - the task might have changed its reservation parameters
+	 *     (through sched_setattr())
+	 *   - the task might have been boosted by someone else and
+	 *     might be in the boosting/deboosting path
+	 *
+	 * In all this cases we bail out, as the task is already
+	 * in the runqueue or is going to be enqueued back anyway.
 	 */
-	if (!dl_task(p) || dl_se->dl_new)
+	if (!dl_task(p) || dl_se->dl_new ||
+	    dl_se->dl_boosted || !dl_se->dl_throttled)
 		goto unlock;
 
 	sched_clock_tick();