sched: Rework pick_next_task() slow-path

Avoid the RETRY_TASK case in the pick_next_task() slow path.

By doing the put_prev_task() early, we get the rt/deadline pull done,
and by testing rq->nr_running we know if we need newidle_balance().

This then gives a stable state to pick a task from.

Since the fast-path is fair only; it means the other classes will
always have pick_next_task(.prev=NULL, .rf=NULL) and we can simplify.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Aaron Lu <aaron.lwe@gmail.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: mingo@kernel.org
Cc: Phil Auld <pauld@redhat.com>
Cc: Julien Desfossez <jdesfossez@digitalocean.com>
Cc: Nishanth Aravamudan <naravamudan@digitalocean.com>
Link: https://lkml.kernel.org/r/aa34d24b36547139248f32a30138791ac6c02bd6.1559129225.git.vpillai@digitalocean.com

kernel/sched/core.c

@@ -3791,7 +3791,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		p = fair_sched_class.pick_next_task(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
-			goto again;
+			goto restart;
 
 		/* Assumes fair_sched_class->next == idle_sched_class */
 		if (unlikely(!p))
@@ -3800,14 +3800,19 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		return p;
 	}
 
-again:
+restart:
+	/*
+	 * Ensure that we put DL/RT tasks before the pick loop, such that they
+	 * can PULL higher prio tasks when we lower the RQ 'priority'.
+	 */
+	prev->sched_class->put_prev_task(rq, prev, rf);
+	if (!rq->nr_running)
+		newidle_balance(rq, rf);
+
 	for_each_class(class) {
-		p = class->pick_next_task(rq, prev, rf);
-		if (p) {
-			if (unlikely(p == RETRY_TASK))
-				goto again;
+		p = class->pick_next_task(rq, NULL, NULL);
+		if (p)
 			return p;
-		}
 	}
 
 	/* The idle class should always have a runnable task: */

kernel/sched/deadline.c

@@ -1761,39 +1761,13 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	struct task_struct *p;
 	struct dl_rq *dl_rq;
 
+	WARN_ON_ONCE(prev || rf);
+
 	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))
 		return NULL;
 
-	put_prev_task(rq, prev);
-
 	dl_se = pick_next_dl_entity(rq, dl_rq);
 	BUG_ON(!dl_se);
 

kernel/sched/fair.c

@@ -6770,7 +6770,7 @@ again:
 		goto idle;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	if (prev->sched_class != &fair_sched_class)
+	if (!prev || prev->sched_class != &fair_sched_class)
 		goto simple;
 
 	/*
@@ -6847,8 +6847,8 @@ again:
 	goto done;
 simple:
 #endif
-
-	put_prev_task(rq, prev);
+	if (prev)
+		put_prev_task(rq, prev);
 
 	do {
 		se = pick_next_entity(cfs_rq, NULL);
@@ -6876,6 +6876,9 @@ done: __maybe_unused;
 	return p;
 
 idle:
+	if (!rf)
+		return NULL;
+
 	new_tasks = newidle_balance(rq, rf);
 
 	/*

kernel/sched/idle.c

@@ -389,7 +389,9 @@ pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 {
 	struct task_struct *next = rq->idle;
 
-	put_prev_task(rq, prev);
+	if (prev)
+		put_prev_task(rq, prev);
+
 	set_next_task_idle(rq, next);
 
 	return next;

kernel/sched/rt.c

@@ -1553,38 +1553,11 @@ 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_rt(rq, p);

kernel/sched/sched.h

@@ -1700,12 +1700,15 @@ struct sched_class {
 	void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
 
 	/*
-	 * It is the responsibility of the pick_next_task() method that will
-	 * return the next task to call put_prev_task() on the @prev task or
-	 * something equivalent.
+	 * Both @prev and @rf are optional and may be NULL, in which case the
+	 * caller must already have invoked put_prev_task(rq, prev, rf).
 	 *
-	 * May return RETRY_TASK when it finds a higher prio class has runnable
-	 * tasks.
+	 * Otherwise it is the responsibility of the pick_next_task() to call
+	 * put_prev_task() on the @prev task or something equivalent, IFF it
+	 * returns a next task.
+	 *
+	 * In that case (@rf != NULL) it may return RETRY_TASK when it finds a
+	 * higher prio class has runnable tasks.
 	 */
 	struct task_struct * (*pick_next_task)(struct rq *rq,
 					       struct task_struct *prev,

kernel/sched/stop_task.c

@@ -33,10 +33,11 @@ pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 {
 	struct task_struct *stop = rq->stop;
 
+	WARN_ON_ONCE(prev || rf);
+
 	if (!stop || !task_on_rq_queued(stop))
 		return NULL;
 
-	put_prev_task(rq, prev);
 	set_next_task_stop(rq, stop);
 
 	return stop;