sched/deadline: Fix stale yield state

When we fail to start the deadline timer in update_curr_dl(), we
forget to clear ->dl_yielded, resulting in wrecked time keeping.

Since the natural place to clear both ->dl_yielded and ->dl_throttled
is in replenish_dl_entity(); both are after all waiting for that event;
make it so.

Luckily since 67dfa1b756f2 ("sched/deadline: Implement
cancel_dl_timer() to use in switched_from_dl()") the
task_on_rq_queued() condition in dl_task_timer() must be true, and can
therefore call enqueue_task_dl() unconditionally.

Reported-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1416962647-76792-4-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 7b684f9..a027799 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -350,6 +350,11 @@
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
 	}
+
+	if (dl_se->dl_yielded)
+		dl_se->dl_yielded = 0;
+	if (dl_se->dl_throttled)
+		dl_se->dl_throttled = 0;
 }
 
 /*
@@ -536,23 +541,19 @@
 
 	sched_clock_tick();
 	update_rq_clock(rq);
-	dl_se->dl_throttled = 0;
-	dl_se->dl_yielded = 0;
-	if (task_on_rq_queued(p)) {
-		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
-		if (dl_task(rq->curr))
-			check_preempt_curr_dl(rq, p, 0);
-		else
-			resched_curr(rq);
+	enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
+	if (dl_task(rq->curr))
+		check_preempt_curr_dl(rq, p, 0);
+	else
+		resched_curr(rq);
 #ifdef CONFIG_SMP
-		/*
-		 * Queueing this task back might have overloaded rq,
-		 * check if we need to kick someone away.
-		 */
-		if (has_pushable_dl_tasks(rq))
-			push_dl_task(rq);
+	/*
+	 * Queueing this task back might have overloaded rq,
+	 * check if we need to kick someone away.
+	 */
+	if (has_pushable_dl_tasks(rq))
+		push_dl_task(rq);
 #endif
-	}
 unlock:
 	raw_spin_unlock(&rq->lock);
 
@@ -613,10 +614,9 @@
 
 	dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
 	if (dl_runtime_exceeded(rq, dl_se)) {
+		dl_se->dl_throttled = 1;
 		__dequeue_task_dl(rq, curr, 0);
-		if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
-			dl_se->dl_throttled = 1;
-		else
+		if (unlikely(!start_dl_timer(dl_se, curr->dl.dl_boosted)))
 			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
 
 		if (!is_leftmost(curr, &rq->dl))
@@ -853,7 +853,7 @@
 	 * its rq, the bandwidth timer callback (which clearly has not
 	 * run yet) will take care of this.
 	 */
-	if (p->dl.dl_throttled)
+	if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH))
 		return;
 
 	enqueue_dl_entity(&p->dl, pi_se, flags);