From ae7927023243dcc7389b2d59b16c09cbbeaecc36 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 Dec 2020 17:14:08 +0100 Subject: [PATCH] sched: Optimize finish_lock_switch() The kernel test robot measured a -1.6% performance regression on will-it-scale/sched_yield due to commit: 2558aacff858 ("sched/hotplug: Ensure only per-cpu kthreads run during hotplug") Even though we were careful to replace a single load with another single load from the same cacheline. Restore finish_lock_switch() to the exact state before the offending patch and solve the problem differently. Fixes: 2558aacff858 ("sched/hotplug: Ensure only per-cpu kthreads run during hotplug") Reported-by: kernel test robot Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201210161408.GX3021@hirez.programming.kicks-ass.net --- kernel/sched/core.c | 40 +++++++++++++++------------------------- kernel/sched/sched.h | 13 +++++-------- 2 files changed, 20 insertions(+), 33 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7af80c3fce12..0ca7d2dc16d5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3985,15 +3985,20 @@ static void do_balance_callbacks(struct rq *rq, struct callback_head *head) } } +static void balance_push(struct rq *rq); + +struct callback_head balance_push_callback = { + .next = NULL, + .func = (void (*)(struct callback_head *))balance_push, +}; + static inline struct callback_head *splice_balance_callbacks(struct rq *rq) { struct callback_head *head = rq->balance_callback; lockdep_assert_held(&rq->lock); - if (head) { + if (head) rq->balance_callback = NULL; - rq->balance_flags &= ~BALANCE_WORK; - } return head; } @@ -4014,21 +4019,6 @@ static inline void balance_callbacks(struct rq *rq, struct callback_head *head) } } -static void balance_push(struct rq *rq); - -static inline void balance_switch(struct rq *rq) -{ - if (likely(!rq->balance_flags)) - return; - - if (rq->balance_flags & BALANCE_PUSH) { - balance_push(rq); - return; - } - - __balance_callbacks(rq); -} - #else static inline void __balance_callbacks(struct rq *rq) @@ -4044,10 +4034,6 @@ static inline void balance_callbacks(struct rq *rq, struct callback_head *head) { } -static inline void balance_switch(struct rq *rq) -{ -} - #endif static inline void @@ -4075,7 +4061,7 @@ static inline void finish_lock_switch(struct rq *rq) * prev into current: */ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); - balance_switch(rq); + __balance_callbacks(rq); raw_spin_unlock_irq(&rq->lock); } @@ -7256,6 +7242,10 @@ static void balance_push(struct rq *rq) lockdep_assert_held(&rq->lock); SCHED_WARN_ON(rq->cpu != smp_processor_id()); + /* + * Ensure the thing is persistent until balance_push_set(.on = false); + */ + rq->balance_callback = &balance_push_callback; /* * Both the cpu-hotplug and stop task are in this case and are @@ -7305,9 +7295,9 @@ static void balance_push_set(int cpu, bool on) rq_lock_irqsave(rq, &rf); if (on) - rq->balance_flags |= BALANCE_PUSH; + rq->balance_callback = &balance_push_callback; else - rq->balance_flags &= ~BALANCE_PUSH; + rq->balance_callback = NULL; rq_unlock_irqrestore(rq, &rf); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index f5acb6c5ce49..12ada79d40f3 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -975,7 +975,6 @@ struct rq { unsigned long cpu_capacity_orig; struct callback_head *balance_callback; - unsigned char balance_flags; unsigned char nohz_idle_balance; unsigned char idle_balance; @@ -1226,6 +1225,8 @@ struct rq_flags { #endif }; +extern struct callback_head balance_push_callback; + /* * Lockdep annotation that avoids accidental unlocks; it's like a * sticky/continuous lockdep_assert_held(). @@ -1243,9 +1244,9 @@ static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf) #ifdef CONFIG_SCHED_DEBUG rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP); rf->clock_update_flags = 0; -#endif #ifdef CONFIG_SMP - SCHED_WARN_ON(rq->balance_callback); + SCHED_WARN_ON(rq->balance_callback && rq->balance_callback != &balance_push_callback); +#endif #endif } @@ -1408,9 +1409,6 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p) #ifdef CONFIG_SMP -#define BALANCE_WORK 0x01 -#define BALANCE_PUSH 0x02 - static inline void queue_balance_callback(struct rq *rq, struct callback_head *head, @@ -1418,13 +1416,12 @@ queue_balance_callback(struct rq *rq, { lockdep_assert_held(&rq->lock); - if (unlikely(head->next || (rq->balance_flags & BALANCE_PUSH))) + if (unlikely(head->next || rq->balance_callback == &balance_push_callback)) return; head->func = (void (*)(struct callback_head *))func; head->next = rq->balance_callback; rq->balance_callback = head; - rq->balance_flags |= BALANCE_WORK; } #define rcu_dereference_check_sched_domain(p) \ -- 2.20.1