linux-kernel - [PATCHSET v2 sched_ext/for-6.16] sched_ext: Extend usability of scx_bpf_select_cpu

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250515191716.327518-1-arighi@nvidia.com>
Date: Thu, 15 May 2025 21:11:41 +0200
From: Andrea Righi <arighi@...dia.com>
To: Tejun Heo <tj@...nel.org>,
	David Vernet <void@...ifault.com>,
	Changwoo Min <changwoo@...lia.com>
Cc: linux-kernel@...r.kernel.org
Subject: [PATCHSET v2 sched_ext/for-6.16] sched_ext: Extend usability of scx_bpf_select_cpu_and()

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(-)