[tip: sched/core] sched/fair: Prepare pick_next_task() for delayed dequeue

[tip-bot2 for Peter Zijlstra]

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

Commit-ID:     f12e148892ede8d9ee82bcd3e469e6d01fc077ac
Gitweb:        https://git.kernel.org/tip/f12e148892ede8d9ee82bcd3e469e6d01fc077ac
Author:        Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate:    Thu, 23 May 2024 11:26:25 +02:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Sat, 17 Aug 2024 11:06:43 +02:00

sched/fair: Prepare pick_next_task() for delayed dequeue

Delayed dequeue's natural end is when it gets picked again. Ensure
pick_next_task() knows what to do with delayed tasks.

Note, this relies on the earlier patch that made pick_next_task()
state invariant -- it will restart the pick on dequeue, because
obviously the just dequeued task is no longer eligible.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Valentin Schneider <vschneid@xxxxxxxxxx>
Tested-by: Valentin Schneider <vschneid@xxxxxxxxxx>
Link: https://lkml.kernel.org/r/20240727105029.747330118@xxxxxxxxxxxxx
---
 kernel/sched/fair.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9a84903..a4f1f79 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5473,6 +5473,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
+static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags);
+
 /*
  * Pick the next process, keeping these things in mind, in this order:
  * 1) keep things fair between processes/task groups
@@ -5481,16 +5483,27 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * 4) do not run the "skip" process, if something else is available
  */
 static struct sched_entity *
-pick_next_entity(struct cfs_rq *cfs_rq)
+pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
 {
 	/*
 	 * Enabling NEXT_BUDDY will affect latency but not fairness.
 	 */
 	if (sched_feat(NEXT_BUDDY) &&
-	    cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next))
+	    cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next)) {
+		/* ->next will never be delayed */
+		SCHED_WARN_ON(cfs_rq->next->sched_delayed);
 		return cfs_rq->next;
+	}
+
+	struct sched_entity *se = pick_eevdf(cfs_rq);
+	if (se->sched_delayed) {
+		dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
+		SCHED_WARN_ON(se->sched_delayed);
+		SCHED_WARN_ON(se->on_rq);
 
-	return pick_eevdf(cfs_rq);
+		return NULL;
+	}
+	return se;
 }
 
 static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
@@ -8507,7 +8520,9 @@ again:
 		if (unlikely(check_cfs_rq_runtime(cfs_rq)))
 			goto again;
 
-		se = pick_next_entity(cfs_rq);
+		se = pick_next_entity(rq, cfs_rq);
+		if (!se)
+			goto again;
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);