sched: Allow put_prev_task() to drop rq->lock

Currently the pick_next_task() loop is convoluted and ugly because of
how it can drop the rq->lock and needs to restart the picking.

For the RT/Deadline classes, it is put_prev_task() where we do
balancing, and we could do this before the picking loop. Make this
possible.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Aaron Lu <aaron.lwe@gmail.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/e4519f6850477ab7f3d257062796e6425ee4ba7c.1559129225.git.vpillai@digitalocean.com

kernel/sched/core.c

@@ -6090,7 +6090,7 @@ static struct task_struct *__pick_migrate_task(struct rq *rq)
 	for_each_class(class) {
 		next = class->pick_next_task(rq, NULL, NULL);
 		if (next) {
-			next->sched_class->put_prev_task(rq, next);
+			next->sched_class->put_prev_task(rq, next, NULL);
 			return next;
 		}
 	}

kernel/sched/deadline.c

@@ -1804,13 +1804,25 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	return p;
 }
 
-static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 {
 	update_curr_dl(rq);
 
 	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1);
 	if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
+
+	if (rf && !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);
+	}
 }
 
 /*

kernel/sched/fair.c

@@ -6901,7 +6901,7 @@ done: __maybe_unused;
 /*
  * Account for a descheduled task:
  */
-static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct sched_entity *se = &prev->se;
 	struct cfs_rq *cfs_rq;

kernel/sched/idle.c

@@ -374,7 +374,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 	resched_curr(rq);
 }
 
-static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 }
 

kernel/sched/rt.c

@@ -1592,7 +1592,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	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 +1604,18 @@ 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

kernel/sched/sched.h

@@ -1710,7 +1710,7 @@ struct sched_class {
 	struct task_struct * (*pick_next_task)(struct rq *rq,
 					       struct task_struct *prev,
 					       struct rq_flags *rf);
-	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
+	void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
@@ -1756,7 +1756,7 @@ struct sched_class {
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	WARN_ON_ONCE(rq->curr != prev);
-	prev->sched_class->put_prev_task(rq, prev);
+	prev->sched_class->put_prev_task(rq, prev, NULL);
 }
 
 static inline void set_next_task(struct rq *rq, struct task_struct *next)

kernel/sched/stop_task.c

@@ -59,7 +59,7 @@ static void yield_task_stop(struct rq *rq)
 	BUG(); /* the stop task should never yield, its pointless. */
 }
 
-static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct task_struct *curr = rq->curr;
 	u64 delta_exec;