[PATCH v6.12] sched/fair: Block delayed tasks on throttled hierarchy during dequeue

[K Prateek Nayak <kprateek.nayak@amd.com>]

Dequeuing a fair task on a throttled hierarchy returns early on
encountering a throttled cfs_rq since the throttle path has already
dequeued the hierarchy above and has adjusted the h_nr_* accounting till
the root cfs_rq.

dequeue_entities() crucially misses calling __block_task() for delayed
tasks being dequeued on the throttled hierarchies, but this was mostly
harmless until commit b7ca5743a260 ("sched/core: Tweak
wait_task_inactive() to force dequeue sched_delayed tasks") since all
existing cases would re-enqueue the task if task_on_rq_queued() returned
true and the task would eventually be blocked at pick after the
hierarchy was unthrottled.

wait_task_inactive() is special as it expects the delayed task on
throttled hierarchy to reach the blocked state on dequeue but since
__block_task() is never called, task_on_rq_queued() continues to return
true. Furthermore, since the task is now off the hierarchy, the pick
never reaches it to fully block the task even after unthrottle leading
to wait_task_inactive() looping endlessly.

Remedy this by calling __block_task() if a delayed task is being
dequeued on a throttled hierarchy.

This fix is only required for stabled kernels implementing delay dequeue
(>= v6.12) before v6.18 since upstream commit e1fad12dcb66 ("sched/fair:
Switch to task based throttle model") indirectly fixes this by removing
the early return conditions in dequeue_entities() as part of the per-task
throttle feature.

Cc: stable@vger.kernel.org
Reported-by: Matt Fleming <matt@readmodwrite.com>
Closes: https://lore.kernel.org/all/20250925133310.1843863-1-matt@readmodwrite.com/
Fixes: b7ca5743a260 ("sched/core: Tweak wait_task_inactive() to force dequeue sched_delayed tasks")
Tested-by: Matt Fleming <mfleming@cloudflare.com>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
---
Greg, Sasha,

This fix cleanly applies on top of v6.16.y and v6.17.y stable kernels
too when cherry-picked from v6.12.y branch (or with 'git am -3'). Let me
know if you would like me to send a seperate patch for each.

As mentioned above, the upstream fixes this as a part of larger feature
and we would only like these bits backported. If there are any future
conflicts in this area during backporting, I would be more than happy to
help out resolve them.
---
 kernel/sched/fair.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index af61769b1d50..b3d9826e25b0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7187,6 +7187,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 	int h_nr_delayed = 0;
 	struct cfs_rq *cfs_rq;
 	u64 slice = 0;
+	int ret = 0;
 
 	if (entity_is_task(se)) {
 		p = task_of(se);
@@ -7218,7 +7219,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			return 0;
+			goto out;
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
@@ -7261,7 +7262,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			return 0;
+			goto out;
 	}
 
 	sub_nr_running(rq, h_nr_queued);
@@ -7273,6 +7274,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
 		rq->next_balance = jiffies;
 
+	ret = 1;
+out:
 	if (p && task_delayed) {
 		SCHED_WARN_ON(!task_sleep);
 		SCHED_WARN_ON(p->on_rq != 1);
@@ -7288,7 +7291,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		__block_task(rq, p);
 	}
 
-	return 1;
+	return ret;
 }
 
 /*
-- 
2.34.1