mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Hui Su <sh_def@163.com>
To: tj@kernel.org
Cc: void@manifault.com, arighi@nvidia.com, changwoo@igalia.com,
	mingo@redhat.com, peterz@infradead.org, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
	rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
	vschneid@redhat.com, kprateek.nayak@amd.com,
	sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org,
	bpf@vger.kernel.org, sh_def@163.com, stable@vger.kernel.org
Subject: [PATCH 0/2] sched_ext: Honor SCX_PICK_IDLE_CORE in CPU selection shortcuts
Date: Mon, 12 Oct 2026 15:51:12 +0900	[thread overview]
Message-ID: <20261012065114.3516902-1-sh_def@163.com> (raw)

The restricted select_cpu kfunc path and the normal WAKE_SYNC shortcuts can
bypass SCX_PICK_IDLE_CORE on SMT systems. The first patch skips the WAKE_SYNC
shortcuts when strict-core selection is requested and validates restricted
candidates against their idle SMT mask. The second patch covers the restricted
path and both WAKE_SYNC shortcuts while retaining the generic smoke test when
no SMT pair is available.

This series is based on:

  [PATCH v3] sched_ext: idle: Respect task affinity in restricted CPU selection
  https://lore.kernel.org/lkml/20261011173100.2090211-1-sh_def@163.com/

Testing:
- x86_64 KVM/QEMU: all three restricted/WAKE_SYNC differential cases
  reproduced the strict-core violation before the fix and returned -EBUSY
  after it.
- The sched_ext selftests passed apart from an unrelated dsp_local_on
  environment failure while opening system Kconfig.
- The strict-core test passed 50 consecutive runs; non-SMT coverage retained
  the generic smoke test and skipped the SMT-specific cases.

Hui Su (2):
  sched_ext: idle: Honor SCX_PICK_IDLE_CORE in CPU selection shortcuts
  selftests/sched_ext: Cover strict-core CPU selection shortcuts

 kernel/sched/ext/idle.c                       |   6 +-
 .../selftests/sched_ext/allowed_cpus.bpf.c    |  36 +-
 .../selftests/sched_ext/allowed_cpus.c        | 316 +++++++++++++++++-
 3 files changed, 347 insertions(+), 11 deletions(-)


base-commit: 9a2d086eba0f331eb5940d6a91efa7caa39080ad
-- 
2.55.0


             reply	other threads:[~2026-10-12  6:53 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-12  6:51 Hui Su [this message]
2026-10-12  6:51 ` [PATCH 1/2] sched_ext: idle: " Hui Su
2026-10-12  6:51 ` [PATCH 2/2] selftests/sched_ext: Cover strict-core " Hui Su

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=20261012065114.3516902-1-sh_def@163.com \
    --to=sh_def@163.com \
    --cc=arighi@nvidia.com \
    --cc=bpf@vger.kernel.org \
    --cc=bsegall@google.com \
    --cc=changwoo@igalia.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=juri.lelli@redhat.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=stable@vger.kernel.org \
    --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

all inboxes | Powered by JetHome®