From: Andrea Righi <arighi@nvidia.com>
To: Tejun Heo <tj@kernel.org>, David Vernet <void@manifault.com>,
Changwoo Min <changwoo@igalia.com>
Cc: Kuba Piecuch <jpiecuch@google.com>,
Christian Loehle <christian.loehle@arm.com>,
Daniel Hodges <hodgesd@meta.com>,
sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: [PATCHSET v3 sched_ext/for-6.20] sched_ext: Fix ops.dequeue() semantics
Date: Mon, 26 Jan 2026 09:41:48 +0100 [thread overview]
Message-ID: <20260126084258.3798129-1-arighi@nvidia.com> (raw)
The callback ops.dequeue() is provided to let BPF schedulers observe when a
task leaves the scheduler, either because it is dispatched or due to a task
property change. However, this callback is currently unreliable and not
invoked systematically, which can result in missed ops.dequeue() events.
In particular, once a task is removed from the scheduler (whether for
dispatch or due to a property change) the BPF scheduler loses visibility of
the task and the sched_ext core may not always trigger ops.dequeue().
This breaks accurate accounting (i.e., per-DSQ queued runtime sums) and
prevents reliable tracking of task lifecycle transitions.
This patch set fixes the semantics of ops.dequeue(), ensuring that every
ops.enqueue() is balanced by a corresponding ops.dequeue() invocation. In
addition, ops.dequeue() is now properly invoked when tasks are removed from
the sched_ext class, such as on task property changes.
To distinguish between a "regular" dequeue and a property change dequeue a
new dequeue flag is introduced: %SCX_DEQ_SCHED_CHANGE. BPF schedulers can
use this flag to distinguish between regular dispatch dequeues
(%SCX_DEQ_SCHED_CHANGE unset) and property change dequeues
(%SCX_DEQ_SCHED_CHANGE set).
Together, these changes allow BPF schedulers to reliably track task
ownership and maintain accurate accounting.
Changes in v3:
- Rename SCX_DEQ_ASYNC to SCX_DEQ_SCHED_CHANGE
- Handle core-sched dequeues (Kuba)
- Link to v2: https://lore.kernel.org/all/20260121123118.964704-1-arighi@nvidia.com/
Changes in v2:
- Distinguish between "dispatch" dequeues and "property change" dequeues
(flag SCX_DEQ_ASYNC)
- Link to v1: https://lore.kernel.org/all/20251219224450.2537941-1-arighi@nvidia.com
Andrea Righi (2):
sched_ext: Fix ops.dequeue() semantics
selftests/sched_ext: Add test to validate ops.dequeue() semantics
Documentation/scheduler/sched-ext.rst | 33 ++++
include/linux/sched/ext.h | 11 ++
kernel/sched/ext.c | 89 +++++++++-
kernel/sched/ext_internal.h | 7 +
tools/sched_ext/include/scx/enum_defs.autogen.h | 2 +
tools/sched_ext/include/scx/enums.autogen.bpf.h | 2 +
tools/sched_ext/include/scx/enums.autogen.h | 1 +
tools/testing/selftests/sched_ext/Makefile | 1 +
tools/testing/selftests/sched_ext/dequeue.bpf.c | 209 ++++++++++++++++++++++++
tools/testing/selftests/sched_ext/dequeue.c | 182 +++++++++++++++++++++
10 files changed, 534 insertions(+), 3 deletions(-)
create mode 100644 tools/testing/selftests/sched_ext/dequeue.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/dequeue.c
next reply other threads:[~2026-01-26 8:43 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-26 8:41 Andrea Righi [this message]
2026-01-26 8:41 ` [PATCH 1/2] " Andrea Righi
2026-01-27 16:38 ` Emil Tsalapatis
2026-01-27 16:41 ` Kuba Piecuch
2026-01-30 7:34 ` Andrea Righi
2026-01-30 13:14 ` Kuba Piecuch
2026-01-31 6:54 ` Andrea Righi
2026-01-31 16:45 ` Kuba Piecuch
2026-01-31 17:24 ` Andrea Righi
2026-01-28 21:21 ` Tejun Heo
2026-01-30 11:54 ` Kuba Piecuch
2026-01-31 9:02 ` Andrea Righi
2026-01-31 17:53 ` Kuba Piecuch
2026-01-31 20:26 ` Andrea Righi
2026-02-02 15:19 ` Tejun Heo
2026-02-02 15:30 ` Andrea Righi
2026-02-01 17:43 ` Tejun Heo
2026-02-02 15:52 ` Andrea Righi
2026-02-02 16:23 ` Kuba Piecuch
2026-01-26 8:41 ` [PATCH 2/2] selftests/sched_ext: Add test to validate " Andrea Righi
2026-01-27 16:53 ` Emil Tsalapatis
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=20260126084258.3798129-1-arighi@nvidia.com \
--to=arighi@nvidia.com \
--cc=changwoo@igalia.com \
--cc=christian.loehle@arm.com \
--cc=hodgesd@meta.com \
--cc=jpiecuch@google.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
Powered by JetHome