sched: Replace post_schedule with a balance callback list

commit e3fca9e7 upstream.

Generalize the post_schedule() stuff into a balance callback list.
This allows us to more easily use it outside of schedule() and cross
sched_class.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: ktkhai@parallels.com
Cc: rostedt@goodmis.org
Cc: juri.lelli@gmail.com
Cc: pang.xunlei@linaro.org
Cc: oleg@redhat.com
Cc: wanpeng.li@linux.intel.com
Cc: umgwanakikbuti@gmail.com
Link: http://lkml.kernel.org/r/20150611124742.424032725@infradead.orgSigned-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Byungchul Park <byungchul.park@lge.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>

kernel/sched/core.c

@@ -1911,18 +1911,30 @@ static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
 }
 
 /* rq->lock is NOT held, but preemption is disabled */
-static inline void post_schedule(struct rq *rq)
+static void __balance_callback(struct rq *rq)
 {
-	if (rq->post_schedule) {
-		unsigned long flags;
+	struct callback_head *head, *next;
+	void (*func)(struct rq *rq);
+	unsigned long flags;
 
-		raw_spin_lock_irqsave(&rq->lock, flags);
-		if (rq->curr->sched_class->post_schedule)
-			rq->curr->sched_class->post_schedule(rq);
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_lock_irqsave(&rq->lock, flags);
+	head = rq->balance_callback;
+	rq->balance_callback = NULL;
+	while (head) {
+		func = (void (*)(struct rq *))head->func;
+		next = head->next;
+		head->next = NULL;
+		head = next;
 
-		rq->post_schedule = 0;
+		func(rq);
 	}
+	raw_spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static inline void balance_callback(struct rq *rq)
+{
+	if (unlikely(rq->balance_callback))
+		__balance_callback(rq);
 }
 
 #else
@@ -1931,7 +1943,7 @@ static inline void pre_schedule(struct rq *rq, struct task_struct *p)
 {
 }
 
-static inline void post_schedule(struct rq *rq)
+static inline void balance_callback(struct rq *rq)
 {
 }
 
@@ -1952,7 +1964,7 @@ asmlinkage void schedule_tail(struct task_struct *prev)
 	 * FIXME: do we need to worry about rq being invalidated by the
 	 * task_switch?
 	 */
-	post_schedule(rq);
+	balance_callback(rq);
 
 #ifdef __ARCH_WANT_UNLOCKED_CTXSW
 	/* In this case, finish_task_switch does not reenable preemption */
@@ -2449,7 +2461,7 @@ static void __sched __schedule(void)
 	} else
 		raw_spin_unlock_irq(&rq->lock);
 
-	post_schedule(rq);
+	balance_callback(rq);
 
 	sched_preempt_enable_no_resched();
 	if (need_resched())
@@ -6516,7 +6528,7 @@ void __init sched_init(void)
 		rq->sd = NULL;
 		rq->rd = NULL;
 		rq->cpu_power = SCHED_POWER_SCALE;
-		rq->post_schedule = 0;
+		rq->balance_callback = NULL;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
 		rq->push_cpu = 0;

kernel/sched/rt.c

@@ -315,6 +315,18 @@ static inline int has_pushable_tasks(struct rq *rq)
 	return !plist_head_empty(&rq->rt.pushable_tasks);
 }
 
+static DEFINE_PER_CPU(struct callback_head, rt_balance_head);
+
+static void push_rt_tasks(struct rq *);
+
+static inline void queue_push_tasks(struct rq *rq)
+{
+	if (!has_pushable_tasks(rq))
+		return;
+
+	queue_balance_callback(rq, &per_cpu(rt_balance_head, rq->cpu), push_rt_tasks);
+}
+
 static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
 {
 	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
@@ -359,6 +371,9 @@ void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
 }
 
+static inline void queue_push_tasks(struct rq *rq)
+{
+}
 #endif /* CONFIG_SMP */
 
 static inline int on_rt_rq(struct sched_rt_entity *rt_se)
@@ -1344,11 +1359,7 @@ static struct task_struct *pick_next_task_rt(struct rq *rq)
 		dequeue_pushable_task(rq, p);
 
 #ifdef CONFIG_SMP
-	/*
-	 * We detect this state here so that we can avoid taking the RQ
-	 * lock again later if there is no need to push
-	 */
-	rq->post_schedule = has_pushable_tasks(rq);
+	queue_push_tasks(rq);
 #endif
 
 	return p;
@@ -1726,11 +1737,6 @@ static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
 		pull_rt_task(rq);
 }
 
-static void post_schedule_rt(struct rq *rq)
-{
-	push_rt_tasks(rq);
-}
-
 /*
  * If we are not running and we are not going to reschedule soon, we should
  * try to push tasks away now
@@ -2003,7 +2009,6 @@ const struct sched_class rt_sched_class = {
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,
 	.pre_schedule		= pre_schedule_rt,
-	.post_schedule		= post_schedule_rt,
 	.task_woken		= task_woken_rt,
 	.switched_from		= switched_from_rt,
 #endif

kernel/sched/sched.h

@@ -460,9 +460,10 @@ struct rq {
 
 	unsigned long cpu_power;
 
+	struct callback_head *balance_callback;
+
 	unsigned char idle_balance;
 	/* For active balancing */
-	int post_schedule;
 	int active_balance;
 	int push_cpu;
 	struct cpu_stop_work active_balance_work;
@@ -554,6 +555,21 @@ static inline u64 rq_clock_task(struct rq *rq)
 
 #ifdef CONFIG_SMP
 
+static inline void
+queue_balance_callback(struct rq *rq,
+		       struct callback_head *head,
+		       void (*func)(struct rq *rq))
+{
+	lockdep_assert_held(&rq->lock);
+
+	if (unlikely(head->next))
+		return;
+
+	head->func = (void (*)(struct callback_head *))func;
+	head->next = rq->balance_callback;
+	rq->balance_callback = head;
+}
+
 #define rcu_dereference_check_sched_domain(p) \
 	rcu_dereference_check((p), \
 			      lockdep_is_held(&sched_domains_mutex))
@@ -981,7 +997,6 @@ struct sched_class {
 	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
 
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
-	void (*post_schedule) (struct rq *this_rq);
 	void (*task_waking) (struct task_struct *task);
 	void (*task_woken) (struct rq *this_rq, struct task_struct *task);