Re: [PATCH] sched: Avoid that __wait_on_bit_lock() hangs

[Peter Zijlstra]

On Wed, Aug 03, 2016 at 09:35:03AM -0700, Bart Van Assche wrote:
> If try_to_wakeup() reads the task state before abort_exclusive_wait()
> sets the task state and if autoremove_wake_function() is called after
> abort_exclusive_wait() has removed a task from a wait list then the
> cascading mechanism for exclusive wakeups in abort_exclusive_wait()
> won't be triggered. Avoid this by serializing the task state change
> in abort_exclusive_wait() and try_to_wakeup().

I'm dense.. what!?

        CPU0                    CPU1                    CPU2

        

                                __lock_page_killable()
                                  __wait_on_bit_lock()
                                    bit_wait_io()
                                      schedule()
        __wake_up_bit()
          __wake_up(.nr_exclusive=1)
            spin_lock(&q->lock)
            __wake_up_common()
              autoremove_wake_func()
                try_to_wake_up(p, TASK_NORMAL)
                list_del_init(&wait->task_list)
            spin_unlock(&q->lock)

                                                        complete_signal(p)
                                                          signal_wake_up(p, 1)
                                                            
sigaddset(&p->pending.signal, SIGKILL)
                                                            try_to_wake_up(p, 
TASK_WAKEKILL)

                                      if (signal_pending_state(TASK_KILLABLE))
                                        return -EINTR;
                                    abort_exclusive_wait()
                                      __set_current_state(RUNNING)
                                      spin_lock(q->lock)
                                      if (!list_empty()) /* empty */
                                      else if (waitqueue_active()) /* pending ? 
*/
                                        __wake_up_locked_key(q, mode, key)
                                      spin_unlock(q->lock)


That seems to do the right thing, so clearly I misunderstand. Please
clarify.


> +++ b/kernel/sched/wait.c
> @@ -277,10 +277,17 @@ void abort_exclusive_wait(wait_queue_head_t *q, 
> wait_queue_t *wait,
>                       unsigned int mode, void *key)
>  {
>       unsigned long flags;
> +     long wake_up;
> +
> +     /* Serialize against try_to_wake_up() */
> +     raw_spin_lock_irqsave(&current->pi_lock, flags);
> +     wake_up = current->state & (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE);
> +     if (wake_up)
> +             __set_current_state(TASK_RUNNING);
> +     raw_spin_unlock_irqrestore(&current->pi_lock, flags);
>  
> -     __set_current_state(TASK_RUNNING);
>       spin_lock_irqsave(&q->lock, flags);
> -     if (!list_empty(&wait->task_list))
> +     if (wake_up)
>               list_del_init(&wait->task_list);
>       else if (waitqueue_active(q))
>               __wake_up_locked_key(q, mode, key);

That just feels wrong,.. very wrong.