sched: Push put_prev_task() into pick_next_task()

In order to avoid having to do put/set on a whole cgroup hierarchy
when we context switch, push the put into pick_next_task() so that
both operations are in the same function. Further changes then allow
us to possibly optimize away redundant work.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1328936700.2476.17.camel@laptopSigned-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/core.c

@@ -2579,18 +2579,11 @@ static inline void schedule_debug(struct task_struct *prev)
 	schedstat_inc(this_rq(), sched_count);
 }
 
-static void put_prev_task(struct rq *rq, struct task_struct *prev)
-{
-	if (prev->on_rq || rq->skip_clock_update < 0)
-		update_rq_clock(rq);
-	prev->sched_class->put_prev_task(rq, prev);
-}
-
 /*
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-pick_next_task(struct rq *rq)
+pick_next_task(struct rq *rq, struct task_struct *prev)
 {
 	const struct sched_class *class;
 	struct task_struct *p;
@@ -2600,13 +2593,13 @@ pick_next_task(struct rq *rq)
 	 * the fair class we can call that function directly:
 	 */
 	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
-		p = fair_sched_class.pick_next_task(rq);
+		p = fair_sched_class.pick_next_task(rq, prev);
 		if (likely(p))
 			return p;
 	}
 
 	for_each_class(class) {
-		p = class->pick_next_task(rq);
+		p = class->pick_next_task(rq, prev);
 		if (p)
 			return p;
 	}
@@ -2714,8 +2707,10 @@ static void __sched __schedule(void)
 			rq->idle_stamp = 0;
 	}
 
-	put_prev_task(rq, prev);
-	next = pick_next_task(rq);
+	if (prev->on_rq || rq->skip_clock_update < 0)
+		update_rq_clock(rq);
+
+	next = pick_next_task(rq, prev);
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
 	rq->skip_clock_update = 0;
@@ -4748,7 +4743,7 @@ static void migrate_tasks(unsigned int dead_cpu)
 		if (rq->nr_running == 1)
 			break;
 
-		next = pick_next_task(rq);
+		next = pick_next_task(rq, NULL);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 

kernel/sched/deadline.c

@@ -990,7 +990,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
 	return rb_entry(left, struct sched_dl_entity, rb_node);
 }
 
-struct task_struct *pick_next_task_dl(struct rq *rq)
+struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
 {
 	struct sched_dl_entity *dl_se;
 	struct task_struct *p;
@@ -1001,6 +1001,9 @@ struct task_struct *pick_next_task_dl(struct rq *rq)
 	if (unlikely(!dl_rq->dl_nr_running))
 		return NULL;
 
+	if (prev)
+		prev->sched_class->put_prev_task(rq, prev);
+
 	dl_se = pick_next_dl_entity(rq, dl_rq);
 	BUG_ON(!dl_se);
 

kernel/sched/fair.c

@@ -4655,7 +4655,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 		set_last_buddy(se);
 }
 
-static struct task_struct *pick_next_task_fair(struct rq *rq)
+static struct task_struct *
+pick_next_task_fair(struct rq *rq, struct task_struct *prev)
 {
 	struct task_struct *p;
 	struct cfs_rq *cfs_rq = &rq->cfs;
@@ -4664,6 +4665,9 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 	if (!cfs_rq->nr_running)
 		return NULL;
 
+	if (prev)
+		prev->sched_class->put_prev_task(rq, prev);
+
 	do {
 		se = pick_next_entity(cfs_rq);
 		set_next_entity(cfs_rq, se);

kernel/sched/idle_task.c

@@ -33,8 +33,12 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 	resched_task(rq->idle);
 }
 
-static struct task_struct *pick_next_task_idle(struct rq *rq)
+static struct task_struct *
+pick_next_task_idle(struct rq *rq, struct task_struct *prev)
 {
+	if (prev)
+		prev->sched_class->put_prev_task(rq, prev);
+
 	schedstat_inc(rq, sched_goidle);
 #ifdef CONFIG_SMP
 	/* Trigger the post schedule to do an idle_enter for CFS */

kernel/sched/rt.c

@@ -1310,15 +1310,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 {
 	struct sched_rt_entity *rt_se;
 	struct task_struct *p;
-	struct rt_rq *rt_rq;
-
-	rt_rq = &rq->rt;
-
-	if (!rt_rq->rt_nr_running)
-		return NULL;
-
-	if (rt_rq_throttled(rt_rq))
-		return NULL;
+	struct rt_rq *rt_rq  = &rq->rt;
 
 	do {
 		rt_se = pick_next_rt_entity(rq, rt_rq);
@@ -1332,9 +1324,22 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 	return p;
 }
 
-static struct task_struct *pick_next_task_rt(struct rq *rq)
+static struct task_struct *
+pick_next_task_rt(struct rq *rq, struct task_struct *prev)
 {
-	struct task_struct *p = _pick_next_task_rt(rq);
+	struct task_struct *p;
+	struct rt_rq *rt_rq = &rq->rt;
+
+	if (!rt_rq->rt_nr_running)
+		return NULL;
+
+	if (rt_rq_throttled(rt_rq))
+		return NULL;
+
+	if (prev)
+		prev->sched_class->put_prev_task(rq, prev);
+
+	p = _pick_next_task_rt(rq);
 
 	/* The running task is never eligible for pushing */
 	if (p)

kernel/sched/sched.h

@@ -1105,7 +1105,13 @@ struct sched_class {
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
-	struct task_struct * (*pick_next_task) (struct rq *rq);
+	/*
+	 * 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.
+	 */
+	struct task_struct * (*pick_next_task) (struct rq *rq,
+						struct task_struct *prev);
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP

kernel/sched/stop_task.c

@@ -23,16 +23,20 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
 	/* we're never preempted */
 }
 
-static struct task_struct *pick_next_task_stop(struct rq *rq)
+static struct task_struct *
+pick_next_task_stop(struct rq *rq, struct task_struct *prev)
 {
 	struct task_struct *stop = rq->stop;
 
-	if (stop && stop->on_rq) {
-		stop->se.exec_start = rq_clock_task(rq);
-		return stop;
-	}
+	if (!stop || !stop->on_rq)
+		return NULL;
 
-	return NULL;
+	if (prev)
+		prev->sched_class->put_prev_task(rq, prev);
+
+	stop->se.exec_start = rq_clock_task(rq);
+
+	return stop;
 }
 
 static void