The following commit has been merged into the sched/urgent branch of tip:

Commit-ID:     d68803506ffb4f72cbeaea94a3a745a6faf62bdd
Gitweb:        https://git.kernel.org/tip/d68803506ffb4f72cbeaea94a3a745a6faf62bdd
Author:        Mike Galbraith <efault@gmx.de>
AuthorDate:    Fri, 08 Nov 2024 01:24:35 +01:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Mon, 11 Nov 2024 11:49:44 +01:00

sched/fair: Dequeue sched_delayed tasks when waking to a busy CPU

Phil Auld (Redhat) reported an fio benchmark regression having been found
to have been caused by addition of the DELAY_DEQUEUE feature, suggested it
may be related to wakees losing the ability to migrate, and confirmed that
restoration of same indeed did restore previous performance.

(de-uglified-a-lot-by)

Fixes: 152e11f6df29 ("sched/fair: Implement delayed dequeue")
Reported-by: Phil Auld <pauld@redhat.com>
Suggested-by: Phil Auld <pauld@redhat.com>
Reviewed-by: Phil Auld <pauld@redhat.com>
Tested-by: Jirka Hladky <jhladky@redhat.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/20241101124715.GA689589@pauld.westford.=
 kernel/sched/core.c  |   48 +++++++++++++++++++++++++++++-------------------
 kernel/sched/sched.h |    5 +++++
 2 files changed, 34 insertions(+), 19 deletions(-)
---
 kernel/sched/core.c  | 46 ++++++++++++++++++++++++++-----------------
 kernel/sched/sched.h |  5 +++++-
 2 files changed, 33 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 719e0ed..b35752f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3734,28 +3734,38 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
  */
 static int ttwu_runnable(struct task_struct *p, int wake_flags)
 {
-	struct rq_flags rf;
-	struct rq *rq;
-	int ret = 0;
+	CLASS(__task_rq_lock, rq_guard)(p);
+	struct rq *rq = rq_guard.rq;
 
-	rq = __task_rq_lock(p, &rf);
-	if (task_on_rq_queued(p)) {
-		update_rq_clock(rq);
-		if (p->se.sched_delayed)
-			enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED);
-		if (!task_on_cpu(rq, p)) {
-			/*
-			 * When on_rq && !on_cpu the task is preempted, see if
-			 * it should preempt the task that is current now.
-			 */
-			wakeup_preempt(rq, p, wake_flags);
+	if (!task_on_rq_queued(p))
+		return 0;
+
+	update_rq_clock(rq);
+	if (p->se.sched_delayed) {
+		int queue_flags = ENQUEUE_DELAYED | ENQUEUE_NOCLOCK;
+
+		/*
+		 * Since sched_delayed means we cannot be current anywhere,
+		 * dequeue it here and have it fall through to the
+		 * select_task_rq() case further along the ttwu() path.
+		 */
+		if (rq->nr_running > 1 && p->nr_cpus_allowed > 1) {
+			dequeue_task(rq, p, DEQUEUE_SLEEP | queue_flags);
+			return 0;
 		}
-		ttwu_do_wakeup(p);
-		ret = 1;
+
+		enqueue_task(rq, p, queue_flags);
 	}
-	__task_rq_unlock(rq, &rf);
+	if (!task_on_cpu(rq, p)) {
+		/*
+		 * When on_rq && !on_cpu the task is preempted, see if
+		 * it should preempt the task that is current now.
+		 */
+		wakeup_preempt(rq, p, wake_flags);
+	}
+	ttwu_do_wakeup(p);
 
-	return ret;
+	return 1;
 }
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6c54a57..97f7936 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1779,6 +1779,11 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 }
 
+DEFINE_LOCK_GUARD_1(__task_rq_lock, struct task_struct,
+		    _T->rq = __task_rq_lock(_T->lock, &_T->rf),
+		    __task_rq_unlock(_T->rq, &_T->rf),
+		    struct rq *rq; struct rq_flags rf)
+
 DEFINE_LOCK_GUARD_1(task_rq_lock, struct task_struct,
 		    _T->rq = task_rq_lock(_T->lock, &_T->rf),
 		    task_rq_unlock(_T->rq, _T->lock, &_T->rf),