From: Tejun Heo <tj@kernel.org>
To: David Vernet <void@manifault.com>,
Andrea Righi <arighi@nvidia.com>,
Changwoo Min <changwoo@igalia.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
linux-kernel@vger.kernel.org, sched-ext@lists.linux.dev,
bpf@vger.kernel.org
Subject: [PATCHSET sched_ext/for-6.19] sched_ext: Fix SCX_KICK_WAIT reliability
Date: Tue, 21 Oct 2025 11:03:52 -1000 [thread overview]
Message-ID: <20251021210354.89570-1-tj@kernel.org> (raw)
SCX_KICK_WAIT is used to synchronously wait for a target CPU to complete a
reschedule, which is needed for implementing operations like core scheduling.
This broke when scx_next_task_picked() was replaced with switch_class() in
commit b999e365c298, because the sequence counter increment that SCX_KICK_WAIT
depends on was no longer reliably called.
This patchset fixes the regression by moving the sequence counter update to
put_prev_task_scx() and refining the semantics to work correctly with the
updated scheduler structure. The first patch adds a prerequisite check to
skip kicking CPUs running higher sched classes, which SCX has no control over.
Based on sched_ext/for-6.19 (2dbbdeda77a6).
0001 sched_ext: Don't kick CPUs running higher classes
0002 sched_ext: Fix SCX_KICK_WAIT to work reliably
Git tree: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git scx-fix-kick_wait
kernel/sched/ext.c | 42 ++++++++++++++++++++++++++----------------
kernel/sched/ext_internal.h | 6 ++++--
2 files changed, 30 insertions(+), 18 deletions(-)
--
tejun
next reply other threads:[~2025-10-21 21:03 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-21 21:03 Tejun Heo [this message]
2025-10-21 21:03 ` sched_ext: Don't kick CPUs running higher classes Tejun Heo
2025-10-21 21:03 ` sched_ext: Fix SCX_KICK_WAIT to work reliably Tejun Heo
2025-10-22 7:43 ` Andrea Righi
2025-10-22 18:37 ` Tejun Heo
2025-10-22 19:25 ` Andrea Righi
2025-10-22 8:03 ` Peter Zijlstra
2025-10-22 18:38 ` 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=20251021210354.89570-1-tj@kernel.org \
--to=tj@kernel.org \
--cc=arighi@nvidia.com \
--cc=bpf@vger.kernel.org \
--cc=changwoo@igalia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=sched-ext@lists.linux.dev \
--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