1 files changed, 101 insertions, 57 deletions

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 46122edd8552..43323f875cb9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -287,7 +287,7 @@ static void task_non_contending(struct task_struct *p)
 
 	dl_se->dl_non_contending = 1;
 	get_task_struct(p);
-	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL);
+	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD);
 }
 
 static void task_contending(struct sched_dl_entity *dl_se, int flags)
@@ -529,6 +529,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq);
 static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p)
 {
 	struct rq *later_rq = NULL;
+	struct dl_bw *dl_b;
 
 	later_rq = find_lock_later_rq(p, rq);
 	if (!later_rq) {
@@ -557,6 +558,38 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
 		double_lock_balance(rq, later_rq);
 	}
 
+	if (p->dl.dl_non_contending || p->dl.dl_throttled) {
+		/*
+		 * Inactive timer is armed (or callback is running, but
+		 * waiting for us to release rq locks). In any case, when it
+		 * will fire (or continue), it will see running_bw of this
+		 * task migrated to later_rq (and correctly handle it).
+		 */
+		sub_running_bw(&p->dl, &rq->dl);
+		sub_rq_bw(&p->dl, &rq->dl);
+
+		add_rq_bw(&p->dl, &later_rq->dl);
+		add_running_bw(&p->dl, &later_rq->dl);
+	} else {
+		sub_rq_bw(&p->dl, &rq->dl);
+		add_rq_bw(&p->dl, &later_rq->dl);
+	}
+
+	/*
+	 * And we finally need to fixup root_domain(s) bandwidth accounting,
+	 * since p is still hanging out in the old (now moved to default) root
+	 * domain.
+	 */
+	dl_b = &rq->rd->dl_bw;
+	raw_spin_lock(&dl_b->lock);
+	__dl_sub(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span));
+	raw_spin_unlock(&dl_b->lock);
+
+	dl_b = &later_rq->rd->dl_bw;
+	raw_spin_lock(&dl_b->lock);
+	__dl_add(dl_b, p->dl.dl_bw, cpumask_weight(later_rq->rd->span));
+	raw_spin_unlock(&dl_b->lock);
+
 	set_task_cpu(p, later_rq->cpu);
 	double_unlock_balance(later_rq, rq);
 
@@ -923,7 +956,7 @@ static int start_dl_timer(struct task_struct *p)
 	 */
 	if (!hrtimer_is_queued(timer)) {
 		get_task_struct(p);
-		hrtimer_start(timer, act, HRTIMER_MODE_ABS);
+		hrtimer_start(timer, act, HRTIMER_MODE_ABS_HARD);
 	}
 
 	return 1;
@@ -1053,7 +1086,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->dl_timer;
 
-	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	timer->function = dl_task_timer;
 }
 
@@ -1292,7 +1325,7 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->inactive_timer;
 
-	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	timer->function = inactive_task_timer;
 }
 
@@ -1658,6 +1691,22 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
 	resched_curr(rq);
 }
 
+static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+{
+	if (!on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
+		/*
+		 * This is OK, because current is on_cpu, which avoids it being
+		 * picked for load-balance and preemption/IRQs are still
+		 * disabled avoiding further scheduler activity on it and we've
+		 * not yet started the picking loop.
+		 */
+		rq_unpin_lock(rq, rf);
+		pull_dl_task(rq);
+		rq_repin_lock(rq, rf);
+	}
+
+	return sched_stop_runnable(rq) || sched_dl_runnable(rq);
+}
 #endif /* CONFIG_SMP */
 
 /*
@@ -1694,12 +1743,23 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
 }
 #endif
 
-static inline void set_next_task(struct rq *rq, struct task_struct *p)
+static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 {
 	p->se.exec_start = rq_clock_task(rq);
 
 	/* You can't push away the running task */
 	dequeue_pushable_dl_task(rq, p);
+
+	if (!first)
+		return;
+
+	if (hrtick_enabled(rq))
+		start_hrtick_dl(rq, p);
+
+	if (rq->curr->sched_class != &dl_sched_class)
+		update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+
+	deadline_queue_push_tasks(rq);
 }
 
 static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
@@ -1713,61 +1773,19 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
 	return rb_entry(left, struct sched_dl_entity, rb_node);
 }
 
-static struct task_struct *
-pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static struct task_struct *pick_next_task_dl(struct rq *rq)
 {
 	struct sched_dl_entity *dl_se;
+	struct dl_rq *dl_rq = &rq->dl;
 	struct task_struct *p;
-	struct dl_rq *dl_rq;
-
-	dl_rq = &rq->dl;
 
-	if (need_pull_dl_task(rq, prev)) {
-		/*
-		 * This is OK, because current is on_cpu, which avoids it being
-		 * picked for load-balance and preemption/IRQs are still
-		 * disabled avoiding further scheduler activity on it and we're
-		 * being very careful to re-start the picking loop.
-		 */
-		rq_unpin_lock(rq, rf);
-		pull_dl_task(rq);
-		rq_repin_lock(rq, rf);
-		/*
-		 * pull_dl_task() can drop (and re-acquire) rq->lock; this
-		 * means a stop task can slip in, in which case we need to
-		 * re-start task selection.
-		 */
-		if (rq->stop && task_on_rq_queued(rq->stop))
-			return RETRY_TASK;
-	}
-
-	/*
-	 * When prev is DL, we may throttle it in put_prev_task().
-	 * So, we update time before we check for dl_nr_running.
-	 */
-	if (prev->sched_class == &dl_sched_class)
-		update_curr_dl(rq);
-
-	if (unlikely(!dl_rq->dl_nr_running))
+	if (!sched_dl_runnable(rq))
 		return NULL;
 
-	put_prev_task(rq, prev);
-
 	dl_se = pick_next_dl_entity(rq, dl_rq);
 	BUG_ON(!dl_se);
-
 	p = dl_task_of(dl_se);
-
-	set_next_task(rq, p);
-
-	if (hrtick_enabled(rq))
-		start_hrtick_dl(rq, p);
-
-	deadline_queue_push_tasks(rq);
-
-	if (rq->curr->sched_class != &dl_sched_class)
-		update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
-
+	set_next_task_dl(rq, p, true);
 	return p;
 }
 
@@ -1811,11 +1829,6 @@ static void task_fork_dl(struct task_struct *p)
 	 */
 }
 
-static void set_curr_task_dl(struct rq *rq)
-{
-	set_next_task(rq, rq->curr);
-}
-
 #ifdef CONFIG_SMP
 
 /* Only try algorithms three times */
@@ -2275,6 +2288,36 @@ void __init init_sched_dl_class(void)
 					GFP_KERNEL, cpu_to_node(i));
 }
 
+void dl_add_task_root_domain(struct task_struct *p)
+{
+	struct rq_flags rf;
+	struct rq *rq;
+	struct dl_bw *dl_b;
+
+	rq = task_rq_lock(p, &rf);
+	if (!dl_task(p))
+		goto unlock;
+
+	dl_b = &rq->rd->dl_bw;
+	raw_spin_lock(&dl_b->lock);
+
+	__dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span));
+
+	raw_spin_unlock(&dl_b->lock);
+
+unlock:
+	task_rq_unlock(rq, p, &rf);
+}
+
+void dl_clear_root_domain(struct root_domain *rd)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rd->dl_bw.lock, flags);
+	rd->dl_bw.total_bw = 0;
+	raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags);
+}
+
 #endif /* CONFIG_SMP */
 
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
@@ -2395,8 +2438,10 @@ const struct sched_class dl_sched_class = {
 
 	.pick_next_task		= pick_next_task_dl,
 	.put_prev_task		= put_prev_task_dl,
+	.set_next_task		= set_next_task_dl,
 
 #ifdef CONFIG_SMP
+	.balance		= balance_dl,
 	.select_task_rq		= select_task_rq_dl,
 	.migrate_task_rq	= migrate_task_rq_dl,
 	.set_cpus_allowed       = set_cpus_allowed_dl,
@@ -2405,7 +2450,6 @@ const struct sched_class dl_sched_class = {
 	.task_woken		= task_woken_dl,
 #endif
 
-	.set_curr_task		= set_curr_task_dl,
 	.task_tick		= task_tick_dl,
 	.task_fork              = task_fork_dl,