Re: [PATCH v7 10/23] sched: Split out __sched() deactivate task logic into a helper

[Metin Kaya]

On 20/12/2023 12:18 am, John Stultz wrote:
> As we're going to re-use the deactivation logic,
> split it into a helper.
>
> Cc: Joel Fernandes <joelaf@xxxxxxxxxx>
> Cc: Qais Yousef <qyousef@xxxxxxxxxx>
> Cc: Ingo Molnar <mingo@xxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
> Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
> Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
> Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
> Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
> Cc: Ben Segall <bsegall@xxxxxxxxxx>
> Cc: Zimuzo Ezeozue <zezeozue@xxxxxxxxxx>
> Cc: Youssef Esmat <youssefesmat@xxxxxxxxxx>
> Cc: Mel Gorman <mgorman@xxxxxxx>
> Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
> Cc: Will Deacon <will@xxxxxxxxxx>
> Cc: Waiman Long <longman@xxxxxxxxxx>
> Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
> Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
> Cc: Metin Kaya <Metin.Kaya@xxxxxxx>
> Cc: Xuewen Yan <xuewen.yan94@xxxxxxxxx>
> Cc: K Prateek Nayak <kprateek.nayak@xxxxxxx>
> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> Cc: kernel-team@xxxxxxxxxxx
> Signed-off-by: John Stultz <jstultz@xxxxxxxxxx>
> ---
> v6:
> * Define function as static to avoid "no previous prototype"
>    warnings as Reported-by: kernel test robot <lkp@xxxxxxxxx>
> v7:
> * Rename state task_state to be more clear, as suggested by
>    Metin Kaya
> ---
>   kernel/sched/core.c | 66 +++++++++++++++++++++++++--------------------
>   1 file changed, 37 insertions(+), 29 deletions(-)
>
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 0ce34f5c0e0c..34acd80b6bd0 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -6571,6 +6571,42 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
>   # define SM_MASK_PREEMPT	SM_PREEMPT
>   #endif
>   

* Better to have a comment (e.g., in which conditions 
try_to_deactivate_task() returns true or false) here.

* try_to_deactivate_task() is temporarily used by 2 commits in the patch 
set (i.e., it's only called by __schedule() just like in this patch at 
the end of the series). However, it's nice to make that big 
__scheduler() function a bit modular as we discussed off-list. So, 
should we move this function out of the Proxy Execution patch set to get 
it merged independently?

> +static bool try_to_deactivate_task(struct rq *rq, struct task_struct *p,
> +				   unsigned long task_state)
> +{
> +	if (signal_pending_state(task_state, p)) {
> +		WRITE_ONCE(p->__state, TASK_RUNNING);
> +	} else {
> +		p->sched_contributes_to_load =
> +			(task_state & TASK_UNINTERRUPTIBLE) &&
> +			!(task_state & TASK_NOLOAD) &&
> +			!(task_state & TASK_FROZEN);
> +
> +		if (p->sched_contributes_to_load)
> +			rq->nr_uninterruptible++;
> +
> +		/*
> +		 * __schedule()			ttwu()
> +		 *   prev_state = prev->state;    if (p->on_rq && ...)
> +		 *   if (prev_state)		    goto out;
> +		 *     p->on_rq = 0;		  smp_acquire__after_ctrl_dep();
> +		 *				  p->state = TASK_WAKING
> +		 *
> +		 * Where __schedule() and ttwu() have matching control dependencies.
> +		 *
> +		 * After this, schedule() must not care about p->state any more.
> +		 */
> +		deactivate_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
> +
> +		if (p->in_iowait) {
> +			atomic_inc(&rq->nr_iowait);
> +			delayacct_blkio_start();
> +		}
> +		return true;
> +	}
> +	return false;
> +}
> +
>   /*
>    * __schedule() is the main scheduler function.
>    *
> @@ -6662,35 +6698,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
>   	 */
>   	prev_state = READ_ONCE(prev->__state);
>   	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
> -		if (signal_pending_state(prev_state, prev)) {
> -			WRITE_ONCE(prev->__state, TASK_RUNNING);
> -		} else {
> -			prev->sched_contributes_to_load =
> -				(prev_state & TASK_UNINTERRUPTIBLE) &&
> -				!(prev_state & TASK_NOLOAD) &&
> -				!(prev_state & TASK_FROZEN);
> -
> -			if (prev->sched_contributes_to_load)
> -				rq->nr_uninterruptible++;
> -
> -			/*
> -			 * __schedule()			ttwu()
> -			 *   prev_state = prev->state;    if (p->on_rq && ...)
> -			 *   if (prev_state)		    goto out;
> -			 *     p->on_rq = 0;		  smp_acquire__after_ctrl_dep();
> -			 *				  p->state = TASK_WAKING
> -			 *
> -			 * Where __schedule() and ttwu() have matching control dependencies.
> -			 *
> -			 * After this, schedule() must not care about p->state any more.
> -			 */
> -			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
> -
> -			if (prev->in_iowait) {
> -				atomic_inc(&rq->nr_iowait);
> -				delayacct_blkio_start();
> -			}
> -		}
> +		try_to_deactivate_task(rq, prev, prev_state);
>   		switch_count = &prev->nvcsw;
>   	}
>