Re: [PATCH v2 4/7] sched/deadline: reschedule if stop task slip in after pull operations

[Peter Zijlstra <peterz@infradead.org>]

On Wed, May 13, 2015 at 02:01:04PM +0800, Wanpeng Li wrote:
> pull_dl_task can drop (and re-acquire) rq->lock, this means a stop task
> can slip in, in which case we need to reschedule. This patch add the
> reschedule when the scenario occurs.
> 
> Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
> ---
>  kernel/sched/deadline.c | 16 +++++++++++++++-
>  1 file changed, 15 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index e49b1e6..7d4c4fc 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -1750,7 +1750,13 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
>  	if (!task_on_rq_queued(p) || rq->dl.dl_nr_running)
>  		return;
>  
> -	if (pull_dl_task(rq))
> +	/*
> +	 * pull_dl_task() can drop (and re-acquire) rq->lock; this
> +	 * means a stop task can slip in, in which case we need to
> +	 * reschedule.
> +	 */
> +	if (pull_dl_task(rq) ||
> +		(rq->stop && task_on_rq_queued(rq->stop)))
>  		resched_curr(rq);

But, the waking of the stop task will already have done the preemption
check and won (obviously). So the wakeup should already have done the
resched_curr().

So why?