From e4e4ad0f2b72f5268fcff0b484b2bb2d31bfe1fc Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 24 May 2020 21:29:55 +0100 Subject: [PATCH] sched/core: Optimize ttwu() spinning on p->on_cpu Both Rik and Mel reported seeing ttwu() spend significant time on: smp_cond_load_acquire(&p->on_cpu, !VAL); Attempt to avoid this by queueing the wakeup on the CPU that owns the p->on_cpu value. This will then allow the ttwu() to complete without further waiting. Since we run schedule() with interrupts disabled, the IPI is guaranteed to happen after p->on_cpu is cleared, this is what makes it safe to queue early. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Mel Gorman Signed-off-by: Ingo Molnar Cc: Jirka Hladky Cc: Vincent Guittot Cc: valentin.schneider@arm.com Cc: Hillf Danton Cc: Rik van Riel Link: https://lore.kernel.org/r/20200524202956.27665-2-mgorman@techsingularity.net Change-Id: I5787935224793e065de57cf9763e08a5e6d40979 Signed-off-by: Alexander Winkowski --- kernel/sched/core.c | 52 +++++++++++++++++++++++++++------------------ 1 file changed, 31 insertions(+), 21 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 34015bdec12d..71e3c7f0860c 100755 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1890,7 +1890,7 @@ void scheduler_ipi(void) irq_exit(); } -static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags) +static void __ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags) { struct rq *rq = cpu_rq(cpu); @@ -1932,6 +1932,17 @@ bool cpus_share_cache(int this_cpu, int that_cpu) { return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); } + +static bool ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags) +{ + if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { + sched_clock_cpu(cpu); /* Sync clocks across CPUs */ + __ttwu_queue_remote(p, cpu, wake_flags); + return true; + } + + return false; +} #endif /* CONFIG_SMP */ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) @@ -1940,11 +1951,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) struct rq_flags rf; #if defined(CONFIG_SMP) - if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { - sched_clock_cpu(cpu); /* Sync clocks across CPUs */ - ttwu_queue_remote(p, cpu, wake_flags); + if (ttwu_queue_remote(p, cpu, wake_flags)) return; - } #endif rq_lock(rq, &rf); @@ -2165,7 +2173,15 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags, if (p->on_rq && ttwu_remote(p, wake_flags)) goto unlock; + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } + #ifdef CONFIG_SMP + p->sched_contributes_to_load = !!task_contributes_to_load(p); + p->state = TASK_WAKING; + /* * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be * possible to, falsely, observe p->on_cpu == 0. @@ -2185,6 +2201,16 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags, */ smp_rmb(); + /* + * If the owning (remote) CPU is still in the middle of schedule() with + * this task as prev, considering queueing p on the remote CPUs wake_list + * which potentially sends an IPI instead of spinning on p->on_cpu to + * let the waker make forward progress. This is safe because IRQs are + * disabled and the IPI will deliver after on_cpu is cleared. + */ + if (READ_ONCE(p->on_cpu) && ttwu_queue_remote(p, cpu, wake_flags)) + goto unlock; + /* * If the owning (remote) CPU is still in the middle of schedule() with * this task as prev, wait until its done referencing the task. @@ -2198,14 +2224,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags, walt_try_to_wake_up(p); - p->sched_contributes_to_load = !!task_contributes_to_load(p); - p->state = TASK_WAKING; - - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&task_rq(p)->nr_iowait); - } - cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags, sibling_count_hint); if (task_cpu(p) != cpu) { @@ -2213,14 +2231,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags, psi_ttwu_dequeue(p); set_task_cpu(p, cpu); } - -#else /* CONFIG_SMP */ - - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&task_rq(p)->nr_iowait); - } - #endif /* CONFIG_SMP */ ttwu_queue(p, cpu, wake_flags);