From: Andrea Righi <arighi@nvidia.com>
To: Tejun Heo <tj@kernel.org>, David Vernet <void@manifault.com>,
Changwoo Min <changwoo@igalia.com>
Cc: linux-kernel@vger.kernel.org
Subject: [PATCHSET v2 sched_ext/for-6.16] sched_ext: Extend usability of scx_bpf_select_cpu_and()
Date: Thu, 15 May 2025 21:11:41 +0200 [thread overview]
Message-ID: <20250515191716.327518-1-arighi@nvidia.com> (raw)
Many scx schedulers implement their own idle CPU selection policy, which
may be invoked from different contexts, not just from ops.select_cpu().
For example, some schedulers may need to trigger a proactive CPU wakeup
from ops.enqueue() after enqueuing a task, while others may expose this
functionality to user space, relying on a BPF test_run call to pick an idle
CPU.
To maintain a consistent selection policy, these schedulers often implement
their own idle CPU selection logic, since the built-in one is only usable
from ops.select_cpu(), leading to unnecessary code duplication and
fragmentation.
To address this, allow scx_bpf_select_cpu_and() to be called not only from
ops.select_cpu() and ops.enqueue(), but also from unlocked contexts (e.g.,
when triggered from user space via a BPF test_run call).
This allows scx schedulers to consistently leverage the built-in idle CPU
selection logic, helping reduce code duplication and fragmentation.
This patchset is also available in the following git branch:
git://git.kernel.org/pub/scm/linux/kernel/git/arighi/linux.git scx-select-cpu-and
Changes in v2:
- Enable scx_bpf_select_cpu_and() to be called from ops.enqueue()
ops.select_cpu() and unlocked context
- Add locking validation to ensure safe access to p->cpus_ptr and
p->nr_cpus_allowed
- Extend selftest to cover scx_bpf_select_cpu_and() when invoked from user
space
- Link to v1: https://lore.kernel.org/all/20250512151743.42988-1-arighi@nvidia.com/
Andrea Righi (4):
sched_ext: Make scx_kf_allowed_if_unlocked() available outside ext.c
sched_ext: idle: Validate locking correctness in scx_bpf_select_cpu_and()
sched_ext: idle: Allow scx_bpf_select_cpu_and() from unlocked context
selftests/sched_ext: Add test for scx_bpf_select_cpu_and() via test_run
kernel/sched/ext.c | 5 ---
kernel/sched/ext.h | 5 +++
kernel/sched/ext_idle.c | 45 +++++++++++++++++-----
.../testing/selftests/sched_ext/allowed_cpus.bpf.c | 23 +++++++++++
tools/testing/selftests/sched_ext/allowed_cpus.c | 27 +++++++++++++
5 files changed, 91 insertions(+), 14 deletions(-)
next reply other threads:[~2025-05-15 19:17 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-15 19:11 Andrea Righi [this message]
2025-05-15 19:11 ` [PATCH 1/4] sched_ext: Make scx_kf_allowed_if_unlocked() available outside ext.c Andrea Righi
2025-05-15 19:11 ` [PATCH 2/4] sched_ext: idle: Validate locking correctness in scx_bpf_select_cpu_and() Andrea Righi
2025-05-15 19:11 ` [PATCH 3/4] sched_ext: idle: Allow scx_bpf_select_cpu_and() from unlocked context Andrea Righi
2025-05-17 17:54 ` David Vernet
2025-05-17 22:50 ` Andrea Righi
2025-05-18 0:40 ` David Vernet
2025-05-18 5:52 ` Andrea Righi
2025-05-18 13:49 ` David Vernet
2025-05-15 19:11 ` [PATCH 4/4] selftests/sched_ext: Add test for scx_bpf_select_cpu_and() via test_run Andrea Righi
2025-05-19 18:02 ` [PATCHSET v2 sched_ext/for-6.16] sched_ext: Extend usability of scx_bpf_select_cpu_and() 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=20250515191716.327518-1-arighi@nvidia.com \
--to=arighi@nvidia.com \
--cc=changwoo@igalia.com \
--cc=linux-kernel@vger.kernel.org \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.