Q: a bogus task_running() check in try_to_wake_up() ?
try_to_wake_up:
if (p->se.on_rq) goto out_running; ... if (unlikely(task_running(rq, p))) goto out_activate;
How it possible that rq->curr has on_rq == 0 ?
AFAICS, this can only happen if this task is rq->idle. But idle threads should not sleep, we have a special "scheduling from the idle thread!" check in schedule().
Thanks in advance,
Oleg.
Quoted 10 lines · Oleg Nesterov
try_to_wake_up:if (p->se.on_rq) goto out_running; ... if (unlikely(task_running(rq, p))) goto out_activate;
Quoted 5 lines
How it possible that
rq->currhason_rq== 0 ?AFAICS, this can only happen if this task is
rq->idle. But idle threads should not sleep, we have a special "scheduling from the idle thread!" check inschedule().
it's also possible if an arch uses __ARCH_WANT_INTERRUPTS_ON_CTXSW, right?
[ btw., we dont have a special "scheduling from the idle thread" check
in schedule() anymore, it's now in kernel/sched_idletask.c :-) ]
Ingo
Quoted 13 lines · Ingo Molnar
Quoted 10 lines · Oleg Nesterov
try_to_wake_up:if (p->se.on_rq) goto out_running; ... if (unlikely(task_running(rq, p))) goto out_activate;
Quoted 8 lines
Quoted 5 lines
How it possible that
rq->currhason_rq== 0 ?AFAICS, this can only happen if this task is
rq->idle. But idle threads should not sleep, we have a special "scheduling from the idle thread!" check inschedule().it's also possible if an arch uses
__ARCH_WANT_INTERRUPTS_ON_CTXSW, right?
Ah, got it. I guess you meant __ARCH_WANT_UNLOCKED_CTXSW though.
In that case schedule() drops rq->lock before the context switch, but doesn't clear ->oncpu. So, task_running(p) means we must not activate "p" on another CPU, otherwise it could be scheduled before the switch-in-progress completes.
Thanks a lot!
Oleg.