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) <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Jirka Hladky <jhladky@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: valentin.schneider@arm.com
Cc: Hillf Danton <hdanton@sina.com>
Cc: Rik van Riel <riel@surriel.com>
Link: https://lore.kernel.org/r/20200524202956.27665-2-mgorman@techsingularity.net

kernel/sched/core.c

@@ -2312,7 +2312,7 @@ static void wake_csd_func(void *info)
 	sched_ttwu_pending();
 }
 
-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);
 
@@ -2354,6 +2354,17 @@ 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)
@@ -2362,11 +2373,8 @@ 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)) {
+	if (ttwu_queue_remote(p, cpu, wake_flags))
-		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
-		ttwu_queue_remote(p, cpu, wake_flags);
 		return;
-	}
 #endif
 
 	rq_lock(rq, &rf);
@@ -2548,7 +2556,15 @@ 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.
@@ -2570,6 +2586,16 @@ 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.
@@ -2581,28 +2607,12 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 */
 	smp_cond_load_acquire(&p->on_cpu, !VAL);
 
-	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);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
 		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);