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

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 88c3bd64a8a0568f2a6d14fe59729170b072597d..f25301267e4714802d7e12f47ef480036223d6ed 100644 (file)
--- 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);
 }