sched: Replace post_schedule with a balance callback list

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.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 41942a5f3315f893dfc7728227593fa089c0a0f2..fa32bc09dadf7041caf2e8b12b76942d48a4684d 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2277,23 +2277,35 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 #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)
 {
 }
 
@@ -2311,7 +2323,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
        /* finish_task_switch() drops rq->lock and enables preemtion */
        preempt_disable();
        rq = finish_task_switch(prev);
-       post_schedule(rq);
+       balance_callback(rq);
        preempt_enable();
 
        if (current->set_child_tid)
@@ -2823,7 +2835,7 @@ static void __sched __schedule(void)
        } else
                raw_spin_unlock_irq(&rq->lock);
 
-       post_schedule(rq);
+       balance_callback(rq);
 }
 
 static inline void sched_submit_work(struct task_struct *tsk)
@@ -7219,7 +7231,7 @@ void __init sched_init(void)
                rq->sd = NULL;
                rq->rd = NULL;
                rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
-               rq->post_schedule = 0;
+               rq->balance_callback = NULL;
                rq->active_balance = 0;
                rq->next_balance = jiffies;
                rq->push_cpu = 0;

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 7a08d590990e742b847bfa0a8919563c4111b439..d80523fb1de5baac74e7af2858337fd9dfd1f93d 100644 (file)
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -213,9 +213,16 @@ static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
        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);
 }
 
 static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq);
@@ -296,7 +303,7 @@ static inline int pull_dl_task(struct rq *rq)
        return 0;
 }
 
-static inline void set_post_schedule(struct rq *rq)
+static inline void queue_push_tasks(struct rq *rq)
 {
 }
 #endif /* CONFIG_SMP */
@@ -1126,7 +1133,7 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
        if (hrtick_enabled(rq))
                start_hrtick_dl(rq, p);
 
-       set_post_schedule(rq);
+       queue_push_tasks(rq);
 
        return p;
 }
@@ -1544,11 +1551,6 @@ 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.
@@ -1784,7 +1786,6 @@ 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
 

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7d7093c51f8d169cea027c78a9ca0321c8f15932..4f3726fe124682adcc4b16e64abd846364420322 100644 (file)
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -354,13 +354,16 @@ static inline int has_pushable_tasks(struct rq *rq)
        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)
@@ -417,7 +420,7 @@ static inline int pull_rt_task(struct rq *this_rq)
        return 0;
 }
 
-static inline void set_post_schedule(struct rq *rq)
+static inline void queue_push_tasks(struct rq *rq)
 {
 }
 #endif /* CONFIG_SMP */
@@ -1497,7 +1500,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
        /* The running task is never eligible for pushing */
        dequeue_pushable_task(rq, p);
 
-       set_post_schedule(rq);
+       queue_push_tasks(rq);
 
        return p;
 }
@@ -2042,11 +2045,6 @@ 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
@@ -2318,7 +2316,6 @@ 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

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f10a445910c9a3b070200408653bee3862f79abc..62949ab06bc2157e05417043497e85146140551f 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -624,9 +624,10 @@ struct rq {
        unsigned long cpu_capacity;
        unsigned long cpu_capacity_orig;
 
+       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;
@@ -767,6 +768,21 @@ extern int migrate_swap(struct task_struct *, struct task_struct *);
 
 #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) \
@@ -1192,7 +1208,6 @@ 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);