The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Andrea Righi <arighi@nvidia.com>
To: Tejun Heo <tj@kernel.org>
Cc: David Vernet <void@manifault.com>,
	Changwoo Min <changwoo@igalia.com>,
	John Stultz <jstultz@google.com>, Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
	Valentin Schneider <vschneid@redhat.com>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	Christian Loehle <christian.loehle@arm.com>,
	David Dai <david.dai@linux.dev>, Koba Ko <kobak@nvidia.com>,
	Aiqun Yu <aiqun.yu@oss.qualcomm.com>,
	sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 08/17] sched_ext: Block proxy donors across scheduler transitions
Date: Mon, 17 Aug 2026 00:06:28 +0200	[thread overview]
Message-ID: <aoI0ZGIqYmc0iI0Q@gpd4> (raw)
In-Reply-To: <aoIsZGwElUYmeePF@slm.duckdns.org>

Hi Tejun,

On Sun, Aug 16, 2026 at 11:32:20AM -1000, Tejun Heo wrote:
> Hello,
> 
> On Sun, Aug 16, 2026 at 07:35:06PM +0200, Andrea Righi wrote:
> > @@ -11295,6 +11295,15 @@ sched_change_begin(struct task_struct *p, const struct sched_class *next_class,
> >  		flags |= DEQUEUE_NOCLOCK;
> >  	}
> >  
> > +	/*
> > +	 * Don't carry retained proxy state across scheduling class changes.
> > +	 * Compatible RT/DL PI transitions could preserve the session so that a
> > +	 * boosted donor continues proxy-executing its lock owner. Defining which
> > +	 * class transitions can safely retain that state is left for future work.
> > +	 */
> > +	if ((flags & DEQUEUE_CLASS) && next_class != p->sched_class)
> > +		sched_proxy_block_task(rq, p);
> > +
> 
> I suppose this prevents RT PI propagation through existing proxy execution
> chain regardless of sched class in use? That sounds pretty convoluted and
> overlapping anyway but John does this look okay to you?

rt_mutex PI propagation itself still takes place, what this prevents is carrying
the boosted scheduling context through an existing proxy chain when the boost
changes scheduling class. Same-class RT priority changes are preserved.

The reset was intended as a conservative way to avoid carrying retained state
into or out of sched_ext, but this also affects fair/RT/DL proxy transitions.

Maybe we can narrow the condition to transitions into or out of sched_ext, like:

#ifdef CONFIG_SCHED_CLASS_EXT
	/*
	 * Don't carry retained proxy state into or out of sched_ext. The BPF
	 * scheduler must explicitly admit blocked donors and cannot inherit a
	 * proxy session owned by another scheduling class.
  	 */
  	if ((flags & DEQUEUE_CLASS) &&
	    (p->sched_class == &ext_sched_class || next_class == &ext_sched_class))
		sched_proxy_block_task(rq, p);
#endif

This would preserve proxy execution across fair/RT/DL PI transitions while still
ending it before entering or leaving sched_ext. WDYT?

Thanks,
-Andrea

  reply	other threads:[~2026-08-16 22:06 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-16 17:34 [PATCHSET v12 sched_ext/for-7.3] sched: Make proxy execution compatible with sched_ext Andrea Righi
2026-08-16 17:34 ` [PATCH 01/17] sched/core: Drop mutex locks before proxy rescheduling Andrea Righi
2026-08-16 17:35 ` [PATCH 02/17] sched/core: Dequeue waking proxy donors before reset Andrea Righi
2026-08-16 20:20   ` Tejun Heo
2026-08-16 21:56     ` [PATCH v2] " Andrea Righi
2026-08-16 17:35 ` [PATCH 03/17] sched: Make NOHZ CFS bandwidth checks follow proxy donor Andrea Righi
2026-08-16 17:35 ` [PATCH 04/17] sched/core: Avoid false migration warning for proxy donors Andrea Righi
2026-08-16 17:35 ` [PATCH 05/17] sched: Pass next class to sched_change_begin() Andrea Righi
2026-08-16 17:35 ` [PATCH 06/17] sched: Add helper to block retained proxy donors Andrea Righi
2026-08-16 17:35 ` [PATCH 07/17] sched: Add sched_ext hooks for proxy execution Andrea Righi
2026-08-16 17:35 ` [PATCH 08/17] sched_ext: Block proxy donors across scheduler transitions Andrea Righi
2026-08-16 21:32   ` Tejun Heo
2026-08-16 22:06     ` Andrea Righi [this message]
2026-08-16 17:35 ` [PATCH 09/17] sched_ext: Fix ops.running/stopping() pairing for proxy-exec donors Andrea Righi
2026-08-16 22:10   ` Tejun Heo
2026-08-16 22:21     ` Andrea Righi
2026-08-16 22:29     ` [PATCH v2] " Andrea Righi
2026-08-16 17:35 ` [PATCH 10/17] sched_ext: Move reject DSQ draining into core Andrea Righi
2026-08-16 17:35 ` [PATCH 11/17] sched_ext: Generalize the reject DSQ reenqueue path Andrea Righi
2026-08-16 22:45   ` Tejun Heo
2026-08-17  6:29     ` Andrea Righi
2026-08-16 17:35 ` [PATCH 12/17] sched_ext: Handle proxy-exec races in remote DSQ transfers Andrea Righi
2026-08-16 23:54   ` Tejun Heo
2026-08-17  7:15     ` Andrea Righi
2026-08-17 17:17       ` Tejun Heo
2026-08-17 19:32         ` Andrea Righi
2026-08-17 19:49           ` Tejun Heo
2026-08-16 17:35 ` [PATCH 13/17] sched_ext: Split curr|donor references properly Andrea Righi
2026-08-16 17:35 ` [PATCH 14/17] sched_ext: Delegate proxy donor admission to BPF schedulers Andrea Righi
2026-08-17  3:02   ` Tejun Heo
2026-08-17 19:02     ` Andrea Righi
2026-08-17 20:24       ` Tejun Heo
2026-08-16 17:35 ` [PATCH 15/17] sched_ext: Add selftest for blocked donor admission Andrea Righi
2026-08-16 17:35 ` [PATCH 16/17] sched_ext: scx_qmap: Add proxy execution support Andrea Righi
2026-08-16 17:35 ` [PATCH 17/17] sched: Allow enabling proxy exec with sched_ext Andrea Righi

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=aoI0ZGIqYmc0iI0Q@gpd4 \
    --to=arighi@nvidia.com \
    --cc=aiqun.yu@oss.qualcomm.com \
    --cc=bsegall@google.com \
    --cc=changwoo@igalia.com \
    --cc=christian.loehle@arm.com \
    --cc=david.dai@linux.dev \
    --cc=dietmar.eggemann@arm.com \
    --cc=jstultz@google.com \
    --cc=juri.lelli@redhat.com \
    --cc=kobak@nvidia.com \
    --cc=kprateek.nayak@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=sched-ext@lists.linux.dev \
    --cc=tj@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=void@manifault.com \
    --cc=vschneid@redhat.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