Sched_ext development
 help / color / mirror / Atom feed
From: Andrea Righi <arighi@nvidia.com>
To: Tejun Heo <tj@kernel.org>
Cc: Changwoo Min <changwoo@igalia.com>,
	David Vernet <void@manifault.com>,
	Emil Tsalapatis <emil@etsalapatis.com>,
	linux-kernel@vger.kernel.org, sched-ext@lists.linux.dev
Subject: Re: [PATCH 2/2] sched_ext: Fix missing post-enqueue handling in move_local_task_to_local_dsq()
Date: Fri, 12 Dec 2025 00:27:28 +0100	[thread overview]
Message-ID: <aTtTYGJ6XxDpbmob@gpd4> (raw)
In-Reply-To: <20251211224809.3383633-3-tj@kernel.org>

On Thu, Dec 11, 2025 at 12:48:09PM -1000, Tejun Heo wrote:
> move_local_task_to_local_dsq() is used when moving a task from a non-local
> DSQ to a local DSQ on the same CPU. It directly manipulates the local DSQ
> without going through dispatch_enqueue() and was missing the post-enqueue
> handling that triggers preemption when SCX_ENQ_PREEMPT is set or the
> enqueued task should preempt a lower priority task.

Ditto, lower sched class / idle task maybe?

Thanks,
-Andrea

> 
> This was fine when the function was only used from consume_dispatch_q()
> where the CPU is already vacant and looking for the next task. However, the
> function is now also used by move_task_between_dsqs() which backs
> scx_bpf_dsq_move() which may be called while the CPU is busy.
> 
> Add local_dsq_post_enq() call to move_local_task_to_local_dsq(). As the
> dispatch path doesn't need post-enqueue handling, add SCX_RQ_IN_BALANCE
> early exit to keep consume_dispatch_q() behavior unchanged and avoid
> triggering unnecessary resched when scx_bpf_dsq_move() is used from the
> dispatch path.
> 
> Signed-off-by: Tejun Heo <tj@kernel.org>
> ---
>  kernel/sched/ext.c |   10 ++++++++++
>  1 file changed, 10 insertions(+)
> 
> --- a/kernel/sched/ext.c
> +++ b/kernel/sched/ext.c
> @@ -981,6 +981,14 @@ static void local_dsq_post_enq(struct sc
>  	struct rq *rq = container_of(dsq, struct rq, scx.local_dsq);
>  	bool preempt = false;
>  
> +	/*
> +	 * If @rq is in balance, the CPU is already vacant and looking for the
> +	 * next task to run. No need to preempt or trigger resched after moving
> +	 * @p into its local DSQ.
> +	 */
> +	if (rq->scx.flags & SCX_RQ_IN_BALANCE)
> +		return;
> +
>  	if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->curr &&
>  	    rq->curr->sched_class == &ext_sched_class) {
>  		rq->curr->scx.slice = 0;
> @@ -1629,6 +1637,8 @@ static void move_local_task_to_local_dsq
>  
>  	dsq_mod_nr(dst_dsq, 1);
>  	p->scx.dsq = dst_dsq;
> +
> +	local_dsq_post_enq(dst_dsq, p, enq_flags);
>  }
>  
>  /**

  reply	other threads:[~2025-12-11 23:27 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-11 22:48 [PATCHSET sched_ext/for-6.19-fixes] sched_ext: Fix missing post-enqueue handling in move_local_task_to_local_dsq() Tejun Heo
2025-12-11 22:48 ` [PATCH 1/2] sched_ext: Factor out local_dsq_post_enq() from dispatch_enqueue() Tejun Heo
2025-12-11 23:23   ` Andrea Righi
2025-12-11 22:48 ` [PATCH 2/2] sched_ext: Fix missing post-enqueue handling in move_local_task_to_local_dsq() Tejun Heo
2025-12-11 23:27   ` Andrea Righi [this message]
2025-12-11 23:35   ` Christian Loehle
2025-12-12  1:34     ` Tejun Heo
2025-12-11 23:29 ` [PATCHSET sched_ext/for-6.19-fixes] " Andrea Righi
2025-12-12  1:45 ` [PATCHSET v2 " Tejun Heo
2025-12-12  1:45   ` [PATCH 1/2] sched_ext: Factor out local_dsq_post_enq() from dispatch_enqueue() Tejun Heo
2025-12-12  5:50     ` Emil Tsalapatis
2025-12-12  1:45   ` [PATCH 2/2] sched_ext: Fix missing post-enqueue handling in move_local_task_to_local_dsq() Tejun Heo
2025-12-12  5:57     ` Emil Tsalapatis
2025-12-12 16:28   ` [PATCHSET v2 sched_ext/for-6.19-fixes] " Tejun Heo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=aTtTYGJ6XxDpbmob@gpd4 \
    --to=arighi@nvidia.com \
    --cc=changwoo@igalia.com \
    --cc=emil@etsalapatis.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=sched-ext@lists.linux.dev \
    --cc=tj@kernel.org \
    --cc=void@manifault.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox