[PATCH 3.16 109/114] sched: Replace post_schedule with a balance callback list

[Ben Hutchings]

3.16.36-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

commit e3fca9e7cbfb72694a21c886fcdf9f059cfded9c 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@xxxxxxxxxxxxx>
Cc: ktkhai@xxxxxxxxxxxxx
Cc: rostedt@xxxxxxxxxxx
Cc: juri.lelli@xxxxxxxxx
Cc: pang.xunlei@xxxxxxxxxx
Cc: oleg@xxxxxxxxxx
Cc: wanpeng.li@xxxxxxxxxxxxxxx
Cc: umgwanakikbuti@xxxxxxxxx
Link: http://lkml.kernel.org/r/20150611124742.424032725@xxxxxxxxxxxxx
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
[Conflicts: kernel/sched/core.c]
Signed-off-by: Byungchul Park <byungchul.park@xxxxxxx>
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
 kernel/sched/core.c     | 36 ++++++++++++++++++++++++------------
 kernel/sched/deadline.c | 21 +++++++++++----------
 kernel/sched/rt.c       | 25 +++++++++++--------------
 kernel/sched/sched.h    | 19 +++++++++++++++++--
 4 files changed, 63 insertions(+), 38 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2258,23 +2258,35 @@ static void finish_task_switch(struct rq
 #ifdef CONFIG_SMP
 
 /* 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
 
-static inline void post_schedule(struct rq *rq)
+static inline void balance_callback(struct rq *rq)
 {
 }
 
@@ -2295,7 +2307,7 @@ asmlinkage __visible void schedule_tail(
 	 * 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 */
@@ -2822,7 +2834,7 @@ need_resched:
 	} else
 		raw_spin_unlock_irq(&rq->lock);
 
-	post_schedule(rq);
+	balance_callback(rq);
 
 	sched_preempt_enable_no_resched();
 	if (need_resched())
@@ -7001,7 +7013,7 @@ void __init sched_init(void)
 		rq->sd = NULL;
 		rq->rd = NULL;
 		rq->cpu_capacity = SCHED_CAPACITY_SCALE;
-		rq->post_schedule = 0;
+		rq->balance_callback = NULL;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
 		rq->push_cpu = 0;
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -213,9 +213,16 @@ static inline bool need_pull_dl_task(str
 	return dl_task(prev);
 }
 
-static inline void set_post_schedule(struct rq *rq)
+static DEFINE_PER_CPU(struct callback_head, dl_balance_head);
+
+static void push_dl_tasks(struct rq *);
+
+static inline void queue_push_tasks(struct rq *rq)
 {
-	rq->post_schedule = has_pushable_dl_tasks(rq);
+	if (!has_pushable_dl_tasks(rq))
+		return;
+
+	queue_balance_callback(rq, &per_cpu(dl_balance_head, rq->cpu), push_dl_tasks);
 }
 
 #else
@@ -250,7 +257,7 @@ static inline int pull_dl_task(struct rq
 	return 0;
 }
 
-static inline void set_post_schedule(struct rq *rq)
+static inline void queue_push_tasks(struct rq *rq)
 {
 }
 #endif /* CONFIG_SMP */
@@ -1043,7 +1050,7 @@ struct task_struct *pick_next_task_dl(st
 		start_hrtick_dl(rq, p);
 #endif
 
-	set_post_schedule(rq);
+	queue_push_tasks(rq);
 
 	return p;
 }
@@ -1452,11 +1459,6 @@ skip:
 	return ret;
 }
 
-static void post_schedule_dl(struct rq *rq)
-{
-	push_dl_tasks(rq);
-}
-
 /*
  * Since the task is not running and a reschedule is not going to happen
  * anytime soon on its runqueue, we try pushing it away now.
@@ -1644,7 +1646,6 @@ const struct sched_class dl_sched_class
 	.set_cpus_allowed       = set_cpus_allowed_dl,
 	.rq_online              = rq_online_dl,
 	.rq_offline             = rq_offline_dl,
-	.post_schedule		= post_schedule_dl,
 	.task_woken		= task_woken_dl,
 #endif
 
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -338,13 +338,16 @@ static inline int has_pushable_tasks(str
 	return !plist_head_empty(&rq->rt.pushable_tasks);
 }
 
-static inline void set_post_schedule(struct rq *rq)
+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)
 {
-	/*
-	 * 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);
+	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)
@@ -401,7 +404,7 @@ static inline int pull_rt_task(struct rq
 	return 0;
 }
 
-static inline void set_post_schedule(struct rq *rq)
+static inline void queue_push_tasks(struct rq *rq)
 {
 }
 #endif /* CONFIG_SMP */
@@ -1472,7 +1475,7 @@ pick_next_task_rt(struct rq *rq, struct
 	if (p)
 		dequeue_pushable_task(rq, p);
 
-	set_post_schedule(rq);
+	queue_push_tasks(rq);
 
 	return p;
 }
@@ -1852,11 +1855,6 @@ skip:
 	return ret;
 }
 
-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
@@ -2128,7 +2126,6 @@ const struct sched_class rt_sched_class
 	.set_cpus_allowed       = set_cpus_allowed_rt,
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,
-	.post_schedule		= post_schedule_rt,
 	.task_woken		= task_woken_rt,
 	.switched_from		= switched_from_rt,
 #endif
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -569,9 +569,10 @@ struct rq {
 
 	unsigned long cpu_capacity;
 
+	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;
@@ -670,6 +671,21 @@ extern int migrate_swap(struct task_stru
 
 #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;
+}
+
 extern void sched_ttwu_pending(void);
 
 #define rcu_dereference_check_sched_domain(p) \
@@ -1127,7 +1143,6 @@ struct sched_class {
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
 	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
 
-	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);