From fd99f91aa007ba255aac44fe6cf21c1db398243a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 9 Apr 2014 15:35:08 +0200 Subject: [PATCH] sched/idle: Avoid spurious wakeup IPIs Because mwait_idle_with_hints() gets called from !idle context it must call current_clr_polling(). This however means that resched_task() is very likely to send an IPI even when we were polling: CPU0 CPU1 if (current_set_polling_and_test()) goto out; __monitor(&ti->flags); if (!need_resched()) __mwait(eax, ecx); set_tsk_need_resched(p); smp_mb(); out: current_clr_polling(); if (!tsk_is_polling(p)) smp_send_reschedule(cpu); So while it is correct (extra IPIs aren't a problem, whereas a missed IPI would be) it is a performance problem (for some). Avoid this issue by using fetch_or() to atomically set NEED_RESCHED and test if POLLING_NRFLAG is set. Since a CPU stuck in mwait is unlikely to modify the flags word, contention on the cmpxchg is unlikely and thus we should mostly succeed in a single go. Signed-off-by: Peter Zijlstra Acked-by: Nicolas Pitre Cc: Andy Lutomirski Cc: Linus Torvalds Link: http://lkml.kernel.org/n/tip-kf5suce6njh5xf5d3od13rr0@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 41 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 36 insertions(+), 5 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1c9c3b7b26af..4b82622b6252 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -506,6 +506,39 @@ static inline void init_hrtick(void) #endif /* CONFIG_SCHED_HRTICK */ /* + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#define fetch_or(ptr, val) \ +({ typeof(*(ptr)) __old, __val = *(ptr); \ + for (;;) { \ + __old = cmpxchg((ptr), __val, __val | (val)); \ + if (__old == __val) \ + break; \ + __val = __old; \ + } \ + __old; \ +}) + +#ifdef TIF_POLLING_NRFLAG +/* + * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, + * this avoids any races wrt polling state changes and thereby avoids + * spurious IPIs. + */ +static bool set_nr_and_not_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); +} +#else +static bool set_nr_and_not_polling(struct task_struct *p) +{ + set_tsk_need_resched(p); + return true; +} +#endif + +/* * resched_task - mark a task 'to be rescheduled now'. * * On UP this means the setting of the need_resched flag, on SMP it @@ -521,17 +554,15 @@ void resched_task(struct task_struct *p) if (test_tsk_need_resched(p)) return; - set_tsk_need_resched(p); - cpu = task_cpu(p); + if (cpu == smp_processor_id()) { + set_tsk_need_resched(p); set_preempt_need_resched(); return; } - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(p)) + if (set_nr_and_not_polling(p)) smp_send_reschedule(cpu); } -- 2.11.0