1 files changed, 35 insertions, 52 deletions

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a532558a5176..ebaa4e619684 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -45,8 +45,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
 
 	raw_spin_lock_init(&rt_b->rt_runtime_lock);
 
-	hrtimer_init(&rt_b->rt_period_timer,
-			CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL_HARD);
 	rt_b->rt_period_timer.function = sched_rt_period_timer;
 }
 
@@ -67,7 +67,8 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 		 * to update the period.
 		 */
 		hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0));
-		hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
+		hrtimer_start_expires(&rt_b->rt_period_timer,
+				      HRTIMER_MODE_ABS_PINNED_HARD);
 	}
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
@@ -1498,12 +1499,22 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
 #endif
 }
 
-static inline void set_next_task(struct rq *rq, struct task_struct *p)
+static inline void set_next_task_rt(struct rq *rq, struct task_struct *p)
 {
 	p->se.exec_start = rq_clock_task(rq);
 
 	/* The running task is never eligible for pushing */
 	dequeue_pushable_task(rq, p);
+
+	/*
+	 * If prev task was rt, put_prev_task() has already updated the
+	 * utilization. We only care of the case where we start to schedule a
+	 * rt task
+	 */
+	if (rq->curr->sched_class != &rt_sched_class)
+		update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+
+	rt_queue_push_tasks(rq);
 }
 
 static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
@@ -1543,56 +1554,19 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	struct task_struct *p;
 	struct rt_rq *rt_rq = &rq->rt;
 
-	if (need_pull_rt_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_rt_task(rq);
-		rq_repin_lock(rq, rf);
-		/*
-		 * pull_rt_task() can drop (and re-acquire) rq->lock; this
-		 * means a dl or stop task can slip in, in which case we need
-		 * to re-start task selection.
-		 */
-		if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) ||
-			     rq->dl.dl_nr_running))
-			return RETRY_TASK;
-	}
-
-	/*
-	 * We may dequeue prev's rt_rq in put_prev_task().
-	 * So, we update time before rt_queued check.
-	 */
-	if (prev->sched_class == &rt_sched_class)
-		update_curr_rt(rq);
+	WARN_ON_ONCE(prev || rf);
 
 	if (!rt_rq->rt_queued)
 		return NULL;
 
-	put_prev_task(rq, prev);
-
 	p = _pick_next_task_rt(rq);
 
-	set_next_task(rq, p);
-
-	rt_queue_push_tasks(rq);
-
-	/*
-	 * If prev task was rt, put_prev_task() has already updated the
-	 * utilization. We only care of the case where we start to schedule a
-	 * rt task
-	 */
-	if (rq->curr->sched_class != &rt_sched_class)
-		update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+	set_next_task_rt(rq, p);
 
 	return p;
 }
 
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 {
 	update_curr_rt(rq);
 
@@ -1604,6 +1578,18 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 	 */
 	if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
+
+	if (rf && !on_rt_rq(&p->rt) && need_pull_rt_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_rt_task(rq);
+		rq_repin_lock(rq, rf);
+	}
 }
 
 #ifdef CONFIG_SMP
@@ -2304,8 +2290,10 @@ static void watchdog(struct rq *rq, struct task_struct *p)
 		}
 
 		next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ);
-		if (p->rt.timeout > next)
-			p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
+		if (p->rt.timeout > next) {
+			posix_cputimers_rt_watchdog(&p->posix_cputimers,
+						    p->se.sum_exec_runtime);
+		}
 	}
 }
 #else
@@ -2354,11 +2342,6 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	}
 }
 
-static void set_curr_task_rt(struct rq *rq)
-{
-	set_next_task(rq, rq->curr);
-}
-
 static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 {
 	/*
@@ -2380,6 +2363,7 @@ const struct sched_class rt_sched_class = {
 
 	.pick_next_task		= pick_next_task_rt,
 	.put_prev_task		= put_prev_task_rt,
+	.set_next_task          = set_next_task_rt,
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_rt,
@@ -2391,7 +2375,6 @@ const struct sched_class rt_sched_class = {
 	.switched_from		= switched_from_rt,
 #endif
 
-	.set_curr_task          = set_curr_task_rt,
 	.task_tick		= task_tick_rt,
 
 	.get_rr_interval	= get_rr_interval_rt,