Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752711AbbFKPcW (ORCPT ); Thu, 11 Jun 2015 11:32:22 -0400 Received: from relay.parallels.com ([195.214.232.42]:44830 "EHLO relay.parallels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750698AbbFKPcS (ORCPT ); Thu, 11 Jun 2015 11:32:18 -0400 Message-ID: <1434036728.1649.9.camel@odin.com> Subject: Re: [PATCH 01/18] sched: Replace post_schedule with a balance callback list From: Kirill Tkhai To: Peter Zijlstra CC: , , , , , , , , , Date: Thu, 11 Jun 2015 18:32:08 +0300 In-Reply-To: <20150611124742.424032725@infradead.org> References: <20150611124636.448700267@infradead.org> <20150611124742.424032725@infradead.org> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.12.11-1 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Originating-IP: [10.30.16.109] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8939 Lines: 268 A just came thought В Чт, 11/06/2015 в 14:46 +0200, Peter Zijlstra пишет: > 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) > --- > 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 > @@ -2277,23 +2277,35 @@ static struct rq *finish_task_switch(str > #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( > /* 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) > @@ -2822,7 +2834,7 @@ 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) > @@ -7216,7 +7228,7 @@ 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; > --- 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); > } > > 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 > 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(st > if (hrtick_enabled(rq)) > start_hrtick_dl(rq, p); > > - set_post_schedule(rq); > + queue_push_tasks(rq); > > return p; > } > @@ -1544,11 +1551,6 @@ static int pull_dl_task(struct rq *this_ > 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 > > --- a/kernel/sched/rt.c > +++ b/kernel/sched/rt.c > @@ -354,13 +354,16 @@ 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) > @@ -417,7 +420,7 @@ 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 */ > @@ -1497,7 +1500,7 @@ pick_next_task_rt(struct rq *rq, struct > /* 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 @@ static int pull_rt_task(struct rq *this_ > 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 > --- 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_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; > +} Maybe, we should queue a higher priority callback at the head? And set aside a callback, which class's priority lower rq->curr's. > + > 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); > > > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/