diff options
| author | Yicong Yang <yangyicong@hisilicon.com> | 2025-06-27 11:54:20 +0800 |
|---|---|---|
| committer | Peter Zijlstra <peterz@infradead.org> | 2025-08-26 10:46:01 +0200 |
| commit | 52d15521eb75f9b521744db675bee61025d2fa52 (patch) | |
| tree | 621231d5c8d3069e9601d6eb461abaeaed18fae5 | |
| parent | 421fc59cf58c64f898cafbbbbda0bc705837e7df (diff) | |
sched/deadline: Don't count nr_running for dl_server proxy tasks
On CPU offline the kernel stalled with below call trace:
INFO: task kworker/0:1:11 blocked for more than 120 seconds.
cpuhp hold the cpu hotplug lock endless and stalled vmstat_shepherd.
This is because we count nr_running twice on cpuhp enqueuing and failed
the wait condition of cpuhp:
enqueue_task_fair() // pick cpuhp from idle, rq->nr_running = 0
dl_server_start()
[...]
add_nr_running() // rq->nr_running = 1
add_nr_running() // rq->nr_running = 2
[switch to cpuhp, waiting on balance_hotplug_wait()]
rcuwait_wait_event(rq->nr_running == 1 && ...) // failed, rq->nr_running=2
schedule() // wait again
It doesn't make sense to count the dl_server towards runnable tasks,
since it runs other tasks.
Fixes: 63ba8422f876 ("sched/deadline: Introduce deadline servers")
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250627035420.37712-1-yangyicong@huawei.com
| -rw-r--r-- | kernel/sched/deadline.c | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 88c3bd64a8a0..f25301267e47 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1851,7 +1851,9 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) u64 deadline = dl_se->deadline; dl_rq->dl_nr_running++; - add_nr_running(rq_of_dl_rq(dl_rq), 1); + + if (!dl_server(dl_se)) + add_nr_running(rq_of_dl_rq(dl_rq), 1); inc_dl_deadline(dl_rq, deadline); } @@ -1861,7 +1863,9 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { WARN_ON(!dl_rq->dl_nr_running); dl_rq->dl_nr_running--; - sub_nr_running(rq_of_dl_rq(dl_rq), 1); + + if (!dl_server(dl_se)) + sub_nr_running(rq_of_dl_rq(dl_rq), 1); dec_dl_deadline(dl_rq, dl_se->deadline); } |