1 files changed, 54 insertions, 33 deletions

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b52092f2636..3fa8fa6d940 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -350,6 +350,11 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 		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;
 }
 
 /*
@@ -506,16 +511,10 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 						     struct sched_dl_entity,
 						     dl_timer);
 	struct task_struct *p = dl_task_of(dl_se);
+	unsigned long flags;
 	struct rq *rq;
-again:
-	rq = task_rq(p);
-	raw_spin_lock(&rq->lock);
 
-	if (rq != task_rq(p)) {
-		/* Task was moved, retrying. */
-		raw_spin_unlock(&rq->lock);
-		goto again;
-	}
+	rq = task_rq_lock(current, &flags);
 
 	/*
 	 * We need to take care of several possible races here:
@@ -536,25 +535,41 @@ again:
 
 	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);
+
+	/*
+	 * If the throttle happened during sched-out; like:
+	 *
+	 *   schedule()
+	 *     deactivate_task()
+	 *       dequeue_task_dl()
+	 *         update_curr_dl()
+	 *           start_dl_timer()
+	 *         __dequeue_task_dl()
+	 *     prev->on_rq = 0;
+	 *
+	 * We can be both throttled and !queued. Replenish the counter
+	 * but do not enqueue -- wait for our wakeup to do that.
+	 */
+	if (!task_on_rq_queued(p)) {
+		replenish_dl_entity(dl_se, dl_se);
+		goto unlock;
+	}
+
+	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);
+	task_rq_unlock(rq, current, &flags);
 
 	return HRTIMER_NORESTART;
 }
@@ -613,10 +628,9 @@ static void update_curr_dl(struct rq *rq)
 
 	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 +867,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	 * 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);
@@ -898,6 +912,7 @@ static void yield_task_dl(struct rq *rq)
 		rq->curr->dl.dl_yielded = 1;
 		p->dl.runtime = 0;
 	}
+	update_rq_clock(rq);
 	update_curr_dl(rq);
 }
 
@@ -1073,7 +1088,13 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
 {
 	update_curr_dl(rq);
 
-	if (hrtick_enabled(rq) && queued && p->dl.runtime > 0)
+	/*
+	 * Even when we have runtime, update_curr_dl() might have resulted in us
+	 * not being the leftmost task anymore. In that case NEED_RESCHED will
+	 * be set and schedule() will start a new hrtick for the next task.
+	 */
+	if (hrtick_enabled(rq) && queued && p->dl.runtime > 0 &&
+	    is_leftmost(p, &rq->dl))
 		start_hrtick_dl(rq, p);
 }
 
@@ -1094,6 +1115,7 @@ static void task_dead_dl(struct task_struct *p)
 	 * Since we are TASK_DEAD we won't slip out of the domain!
 	 */
 	raw_spin_lock_irq(&dl_b->lock);
+	/* XXX we should retain the bw until 0-lag */
 	dl_b->total_bw -= p->dl.dl_bw;
 	raw_spin_unlock_irq(&dl_b->lock);
 
@@ -1165,9 +1187,6 @@ static int find_later_rq(struct task_struct *task)
 	 * We have to consider system topology and task affinity
 	 * first, then we can look for a suitable cpu.
 	 */
-	cpumask_copy(later_mask, task_rq(task)->rd->span);
-	cpumask_and(later_mask, later_mask, cpu_active_mask);
-	cpumask_and(later_mask, later_mask, &task->cpus_allowed);
 	best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
 			task, later_mask);
 	if (best_cpu == -1)
@@ -1562,6 +1581,7 @@ static void rq_online_dl(struct rq *rq)
 	if (rq->dl.overloaded)
 		dl_set_overload(rq);
 
+	cpudl_set_freecpu(&rq->rd->cpudl, rq->cpu);
 	if (rq->dl.dl_nr_running > 0)
 		cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1);
 }
@@ -1573,6 +1593,7 @@ static void rq_offline_dl(struct rq *rq)
 		dl_clear_overload(rq);
 
 	cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+	cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu);
 }
 
 void init_sched_dl_class(void)
@@ -1614,8 +1635,8 @@ static void cancel_dl_timer(struct rq *rq, struct task_struct *p)
 
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
+	/* XXX we should retain the bw until 0-lag */
 	cancel_dl_timer(rq, p);
-
 	__dl_clear_params(p);
 
 	/*