From e67e3e738f088e6c5ccfab618a29318a3f08db41 Mon Sep 17 00:00:00 2001 From: K Prateek Nayak Date: Wed, 15 Oct 2025 06:03:59 +0000 Subject: [PATCH] sched/fair: Block delayed tasks on throttled hierarchy during dequeue 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 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 Signed-off-by: K Prateek Nayak Signed-off-by: Greg Kroah-Hartman --- 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 af61769b1d502..b3d9826e25b03 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; } /* -- 2.47.3