mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-07-22 17:27:37 -04:00
sched/deadline: Stop dl_server before CPU goes offline
IBM CI tool reported kernel warning[1] when running a CPU removal operation through drmgr[2]. i.e "drmgr -c cpu -r -q 1" WARNING: CPU: 0 PID: 0 at kernel/sched/cpudeadline.c:219 cpudl_set+0x58/0x170 NIP [c0000000002b6ed8] cpudl_set+0x58/0x170 LR [c0000000002b7cb8] dl_server_timer+0x168/0x2a0 Call Trace: [c000000002c2f8c0] init_stack+0x78c0/0x8000 (unreliable) [c0000000002b7cb8] dl_server_timer+0x168/0x2a0 [c00000000034df84] __hrtimer_run_queues+0x1a4/0x390 [c00000000034f624] hrtimer_interrupt+0x124/0x300 [c00000000002a230] timer_interrupt+0x140/0x320 Git bisects to: commit4ae8d9aa9f("sched/deadline: Fix dl_server getting stuck") This happens since: - dl_server hrtimer gets enqueued close to cpu offline, when kthread_park enqueues a fair task. - CPU goes offline and drmgr removes it from cpu_present_mask. - hrtimer fires and warning is hit. Fix it by stopping the dl_server before CPU is marked dead. [1]: https://lore.kernel.org/all/8218e149-7718-4432-9312-f97297c352b9@linux.ibm.com/ [2]: https://github.com/ibm-power-utilities/powerpc-utils/tree/next/src/drmgr [sshegde: wrote the changelog and tested it] Fixes:4ae8d9aa9f("sched/deadline: Fix dl_server getting stuck") Closes: https://lore.kernel.org/all/8218e149-7718-4432-9312-f97297c352b9@linux.ibm.com Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com> Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Marek Szyprowski <m.szyprowski@samsung.com> Tested-by: Shrikanth Hegde <sshegde@linux.ibm.com>
This commit is contained in:
committed by
Peter Zijlstra
parent
3a86608788
commit
ee6e44dfe6
@@ -8571,10 +8571,12 @@ int sched_cpu_dying(unsigned int cpu)
|
||||
sched_tick_stop(cpu);
|
||||
|
||||
rq_lock_irqsave(rq, &rf);
|
||||
update_rq_clock(rq);
|
||||
if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) {
|
||||
WARN(true, "Dying CPU not properly vacated!");
|
||||
dump_rq_tasks(rq, KERN_WARNING);
|
||||
}
|
||||
dl_server_stop(&rq->fair_server);
|
||||
rq_unlock_irqrestore(rq, &rf);
|
||||
|
||||
calc_load_migrate(rq);
|
||||
|
||||
@@ -1582,6 +1582,9 @@ void dl_server_start(struct sched_dl_entity *dl_se)
|
||||
if (!dl_server(dl_se) || dl_se->dl_server_active)
|
||||
return;
|
||||
|
||||
if (WARN_ON_ONCE(!cpu_online(cpu_of(rq))))
|
||||
return;
|
||||
|
||||
dl_se->dl_server_active = 1;
|
||||
enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
|
||||
if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
|
||||
|
||||
Reference in New Issue
Block a user