Re: [PATCH v5 2/3] sched/rt: Fix wrong SMP scheduler behavior for equal prio cases

[Steven Rostedt <rostedt@goodmis.org>]

On Thu,  9 Apr 2015 11:27:17 +0800
Xunlei Pang <xlpang@126.com> wrote:


> Suggested-by: Steven Rostedt <rostedt@goodmis.org>
> Signed-off-by: Xunlei Pang <pang.xunlei@linaro.org>
> ---
>  kernel/sched/rt.c | 26 ++++++++++++++++++++------
>  1 file changed, 20 insertions(+), 6 deletions(-)
> 
> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
> index 575da76..402162a 100644
> --- a/kernel/sched/rt.c
> +++ b/kernel/sched/rt.c
> @@ -359,11 +359,15 @@ static inline void set_post_schedule(struct rq *rq)
>  	rq->post_schedule = has_pushable_tasks(rq);
>  }
>  
> -static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
> +static void
> +enqueue_pushable_task(struct rq *rq, struct task_struct *p, bool head)
>  {
>  	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
>  	plist_node_init(&p->pushable_tasks, p->prio);
> -	plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks);
> +	if (head)
> +		plist_add_head(&p->pushable_tasks, &rq->rt.pushable_tasks);
> +	else
> +		plist_add_tail(&p->pushable_tasks, &rq->rt.pushable_tasks);
>  
>  	/* Update the highest prio pushable task */
>  	if (p->prio < rq->rt.highest_prio.next)
> @@ -385,7 +389,8 @@ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
>  
>  #else
>  
> -static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
> +static inline
> +void enqueue_pushable_task(struct rq *rq, struct task_struct *p, bool head)
>  {
>  }
>  
> @@ -1260,7 +1265,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
>  	enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
>  
>  	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
> -		enqueue_pushable_task(rq, p);
> +		enqueue_pushable_task(rq, p, false);

Hmm, I really don't like the "false" parameter all over the place, since
it's only needed in one place. Thinking about this more, what about
keeping enqueue_pushable_task() as is, and adding an
enqueue_pushable_task_preempted(). Having something like this:

static inline void
enqueue_pushable_task(struct rq *rq, struct task_struct *p)
{
	enqueue_pushable_task_preempted(rq, p, false);
}


>  }
>  
>  static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
> @@ -1507,7 +1512,16 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
>  	 * if it is still active
>  	 */
>  	if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
> -		enqueue_pushable_task(rq, p);
> +		/*
> +		 * put_prev_task_rt() is called by many functions,
> +		 * pick_next_task_rt() is the only one may have
> +		 * PREEMPT_ACTIVE set. So if detecting p(current
> +		 * task) is preempted in such case, we should
> +		 * enqueue it to the front of the pushable plist,
> +		 * as there may be multiple tasks with the same
> +		 * priority as p.
> +		 */
> +		enqueue_pushable_task(rq, p, !!(preempt_count() & PREEMPT_ACTIVE));

Then we don't need to touch any of the code but this place, and this
would be:

		enqueue_pushable_task_preempted(rq, p,
			 !!(preempt_count() & PREEMPT_ACTIVE));

I'm thinking this would be much more descriptive.

What do you think?

-- Steve

>  }
>  
>  #ifdef CONFIG_SMP
> @@ -2091,7 +2105,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
>  		rq->rt.rt_nr_migratory--;
>  	} else {
>  		if (!task_current(rq, p))
> -			enqueue_pushable_task(rq, p);
> +			enqueue_pushable_task(rq, p, false);
>  		rq->rt.rt_nr_migratory++;
>  	}
>