From: Kuba Piecuch <jpiecuch@google.com>
To: Tejun Heo <tj@kernel.org>, Peter Zijlstra <peterz@infradead.org>
Cc: Kuba Piecuch <jpiecuch@google.com>,
David Vernet <void@manifault.com>,
Andrea Righi <arighi@nvidia.com>,
Changwoo Min <changwoo@igalia.com>,
sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: [PATCH v2 0/2] sched: Fix SCX_ENQ_CPU_SELECTED for queued wakeups
Date: Mon, 26 Oct 2026 11:44:22 +0000 [thread overview]
Message-ID: <20261026114429.209588-1-jpiecuch@google.com> (raw)
SCX_ENQ_CPU_SELECTED is meant to tell ops.enqueue() whether
ops.select_cpu() ran for a wakeup. However, wakeups delivered through
the ttwu wakelist never have the flag set, because sched_ttwu_pending()
drops WF_RQ_SELECTED. Schedulers that set SCX_OPS_ALLOW_QUEUED_WAKEUP
therefore cannot tell whether ops.select_cpu() was skipped, and
SCX_EV_SELECT_CPU_FALLBACK is undercounted.
Patch 1 carries WF_RQ_SELECTED across the wakelist the same way
WF_MIGRATED already is. Patch 2 adds a selftest. In a 4-vCPU VM, without
patch 1 the test reports that all of the roughly 100k queued wakeups in
a 2s run had ops.select_cpu() called but SCX_ENQ_CPU_SELECTED clear.
With patch 1 there are none.
Patch 1 changes kernel/sched/core.c and include/linux/sched.h, but only
sched_ext sees the effect. Peter, Tejun: I'll leave it to you to decide
whether the series goes through tip or the sched_ext tree.
The bug was found, and the series was drafted, with the help of an AI
coding agent.
Changes in v2:
- Patch 1: Reword the description to distinguish the wakelist path
before ->select_task_rq() from the one after it, and fix the
ttwu_do_activate() name (Andrea). Add Acked-by from Tejun and
Reviewed-by from Andrea.
- Patch 2: Give each ping-pong task its own two CPUs and dispatch to
SCX_DSQ_LOCAL. The waker and the wakee then always run on different
CPUs, so the test no longer depends on tasks spreading out on their
own (Sashiko). Skip on systems with fewer than four CPUs.
v1: https://lore.kernel.org/r/20261023144811.2230393-1-jpiecuch@google.com
Kuba Piecuch (2):
sched/core: Preserve WF_RQ_SELECTED across queued wakeups
selftests/sched_ext: Test SCX_ENQ_CPU_SELECTED with queued wakeups
include/linux/sched.h | 6 +-
kernel/sched/core.c | 10 +-
tools/testing/selftests/sched_ext/Makefile | 1 +
.../sched_ext/enq_cpu_selected.bpf.c | 111 ++++++++++
.../selftests/sched_ext/enq_cpu_selected.c | 194 ++++++++++++++++++
5 files changed, 319 insertions(+), 3 deletions(-)
create mode 100644 tools/testing/selftests/sched_ext/enq_cpu_selected.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/enq_cpu_selected.c
base-commit: 734bef548a96e8774d6eef5dfa2026c6edc4e80b
--
2.56.0.257.gf7497c7d27-goog
next reply other threads:[~2026-10-26 11:44 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-26 11:44 Kuba Piecuch [this message]
2026-10-26 11:44 ` [PATCH v2 1/2] sched/core: Preserve WF_RQ_SELECTED across " Kuba Piecuch
2026-10-26 11:44 ` [PATCH v2 2/2] selftests/sched_ext: Test SCX_ENQ_CPU_SELECTED with " Kuba Piecuch
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=20261026114429.209588-1-jpiecuch@google.com \
--to=jpiecuch@google.com \
--cc=arighi@nvidia.com \
--cc=changwoo@igalia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.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
all inboxes | Powered by JetHome®