All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: David Vernet <void@manifault.com>,
	Andrea Righi <arighi@nvidia.com>,
	Changwoo Min <changwoo@igalia.com>
Cc: Emil Tsalapatis <emil@etsalapatis.com>,
	sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org,
	Tejun Heo <tj@kernel.org>
Subject: [PATCHSET v4 sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops
Date: Wed, 29 Apr 2026 08:21:14 -1000	[thread overview]
Message-ID: <20260429182131.1780125-1-tj@kernel.org> (raw)

Hello,

v4:
- cmask: bump CMASK_CAS_TRIES to (1U << 23) so abort fires only after
  seconds of real spinning, not on plausible contention. The kfunc
  slow-path Changwoo suggested would let BPF loops keep banging a
  contended cacheline indefinitely - on multi-socket SPRs that path
  can stall the machine into hard lockups, so failing hard is the
  right behavior. A follow-up patch will add a kfunc to bail the BPF
  CAS loops immediately when sch->aborting is set. Switch
  __builtin_ctzll() to the ctzll() wrapper for clang compat.
- cid-qmap-port: cid-shard handling was wired against a future kfunc
  signature that didn't make it into v3, leaving the snapshot broken.
  Drop the shard test plumbing for v4, match the 2-arg
  scx_bpf_cid_override(), bound nr_cpu_ids for the verifier, and
  rename mode 3 from bad-mono to bad-range. (Changwoo, Andrea)
- Rebased over the exit_cpu plumbing in for-7.2:
    scx-error-header: scx_exit() and scx_verror() are macros now;
    move both plus the underlying __scx_exit() / scx_vexit()
    declarations to ext_internal.h.
    cid-struct-ops: dump_cpu callsite shifted into scx_dump_cpu()
    helper; the scx_cpu_arg() wrap moved with it.

v3: https://lore.kernel.org/r/20260428203545.181052-1-tj@kernel.org
v2: https://lore.kernel.org/r/20260424172721.3458520-1-tj@kernel.org
v1: https://lore.kernel.org/r/20260421071945.3110084-1-tj@kernel.org

This patchset introduces topological CPU IDs (cids) - dense,
topology-ordered cpu identifiers - and an alternative cid-form struct_ops
type that lets BPF schedulers operate in cid space directly.

Key pieces:

- cid space: scx_cid_init() walks nodes * LLCs * cores * threads and packs
  a dense cid mapping. The mapping can be overridden via
  scx_bpf_cid_override(). See "Topological CPU IDs" in ext_cid.h for the
  model.

- cmask: a base-windowed bitmap over cid space. Kernel and BPF helpers with
  identical semantics. Used by scx_qmap for per-task affinity and idle-cid
  tracking; meant to be the substrate for sub-sched cid allocation.

- bpf_sched_ext_ops_cid: a parallel struct_ops type whose callbacks take
  cids/cmasks instead of cpus/cpumasks. Kernel translates at the boundary
  via scx_cpu_arg() / scx_cpu_ret(); the two struct types share offsets up
  through @priv (verified by BUILD_BUG_ON) so the union view in scx_sched
  works without function-pointer casts. Sub-sched support is tied to
  cid-form: validate_ops() rejects cpu-form sub-scheds and cpu-form roots
  that expose sub_attach / sub_detach.

- cid-form kfuncs: scx_bpf_kick_cid, scx_bpf_cidperf_{cap,cur,set},
  scx_bpf_cid_curr, scx_bpf_task_cid, scx_bpf_this_cid,
  scx_bpf_nr_{cids,online_cids}, scx_bpf_cid_to_cpu, scx_bpf_cpu_to_cid.
  A cid-form program may not call cpu-only kfuncs (enforced at verifier
  load via scx_kfunc_context_filter); the reverse is intentionally
  permissive to ease migration.

- scx_qmap port: scx_qmap is converted to cid-form. It uses the cmask-based
  idle picker, per-task cid-space cpus_allowed, and cid-form kfuncs
  throughout. Sub-sched dispatching via scx_bpf_sub_dispatch() continues to
  work.

v4 re-tested on the 16-cpu QEMU VM with the v3 cut (only the 17 cid
patches applied): basic load + stress, cid-override modes
(shuffle/bad-dup/bad-range), and three enable/disable cycles all clean.
No BUG/WARNING/panic in the dump.

Based on sched_ext/for-7.2 (ee8391ba1164).

  0001-sched_ext-Add-ext_types.h-for-early-subsystem-wide-d.patch
  0002-sched_ext-Rename-ops_cpu_valid-to-scx_cpu_valid-and-.patch
  0003-sched_ext-Move-scx_exit-scx_error-and-friends-to-ext.patch
  0004-sched_ext-Shift-scx_kick_cpu-validity-check-to-scx_b.patch
  0005-sched_ext-Relocate-cpu_acquire-cpu_release-to-end-of.patch
  0006-sched_ext-Make-scx_enable-take-scx_enable_cmd.patch
  0007-sched_ext-Add-topological-CPU-IDs-cids.patch
  0008-sched_ext-Add-scx_bpf_cid_override-kfunc.patch
  0009-tools-sched_ext-Add-struct_size-helpers-to-common.bp.patch
  0010-sched_ext-Add-cmask-a-base-windowed-bitmap-over-cid-.patch
  0011-sched_ext-Add-cid-form-kfunc-wrappers-alongside-cpu-.patch
  0012-sched_ext-Add-bpf_sched_ext_ops_cid-struct_ops-type.patch
  0013-sched_ext-Forbid-cpu-form-kfuncs-from-cid-form-sched.patch
  0014-tools-sched_ext-scx_qmap-Restart-on-hotplug-instead-.patch
  0015-tools-sched_ext-scx_qmap-Add-cmask-based-idle-tracki.patch
  0016-tools-sched_ext-scx_qmap-Port-to-cid-form-struct_ops.patch
  0017-sched_ext-Require-cid-form-struct_ops-for-sub-sched-.patch

Git tree: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git scx-cid-v4

 kernel/sched/build_policy.c              |   3 +
 kernel/sched/ext.c                       | 660 ++++++++++++++++++++++++++----
 kernel/sched/ext_cid.c                   | 409 +++++++++++++++++++
 kernel/sched/ext_cid.h                   | 164 ++++++++
 kernel/sched/ext_idle.c                  |   8 +-
 kernel/sched/ext_internal.h              | 209 +++++++---
 kernel/sched/ext_types.h                 | 104 +++++
 tools/sched_ext/include/scx/cid.bpf.h    | 666 +++++++++++++++++++++++++++++++
 tools/sched_ext/include/scx/common.bpf.h |  23 ++
 tools/sched_ext/include/scx/compat.bpf.h |  24 ++
 tools/sched_ext/scx_qmap.bpf.c           | 350 +++++++++-------
 tools/sched_ext/scx_qmap.c               |  57 ++-
 tools/sched_ext/scx_qmap.h               |   2 +-
 13 files changed, 2387 insertions(+), 292 deletions(-)

Thanks.

--
tejun

             reply	other threads:[~2026-04-29 18:21 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-29 18:21 Tejun Heo [this message]
2026-04-29 18:21 ` [PATCH 01/17] sched_ext: Add ext_types.h for early subsystem-wide defs Tejun Heo
2026-04-29 18:21 ` [PATCH 02/17] sched_ext: Rename ops_cpu_valid() to scx_cpu_valid() and expose it Tejun Heo
2026-04-29 18:21 ` [PATCH 03/17] sched_ext: Move scx_exit(), scx_error() and friends to ext_internal.h Tejun Heo
2026-04-29 18:21 ` [PATCH 04/17] sched_ext: Shift scx_kick_cpu() validity check to scx_bpf_kick_cpu() Tejun Heo
2026-04-29 18:21 ` [PATCH 05/17] sched_ext: Relocate cpu_acquire/cpu_release to end of struct sched_ext_ops Tejun Heo
2026-04-29 18:21 ` [PATCH 06/17] sched_ext: Make scx_enable() take scx_enable_cmd Tejun Heo
2026-04-29 18:21 ` [PATCH 07/17] sched_ext: Add topological CPU IDs (cids) Tejun Heo
2026-04-29 18:21 ` [PATCH 08/17] sched_ext: Add scx_bpf_cid_override() kfunc Tejun Heo
2026-04-29 18:21 ` [PATCH 09/17] tools/sched_ext: Add struct_size() helpers to common.bpf.h Tejun Heo
2026-04-29 18:21 ` [PATCH 10/17] sched_ext: Add cmask, a base-windowed bitmap over cid space Tejun Heo
2026-04-29 18:21 ` [PATCH 11/17] sched_ext: Add cid-form kfunc wrappers alongside cpu-form Tejun Heo
2026-04-29 18:21 ` [PATCH 12/17] sched_ext: Add bpf_sched_ext_ops_cid struct_ops type Tejun Heo
2026-04-29 18:21 ` [PATCH 13/17] sched_ext: Forbid cpu-form kfuncs from cid-form schedulers Tejun Heo
2026-04-29 18:21 ` [PATCH 14/17] tools/sched_ext: scx_qmap: Restart on hotplug instead of cpu_online/offline Tejun Heo
2026-04-29 18:21 ` [PATCH 15/17] tools/sched_ext: scx_qmap: Add cmask-based idle tracking and cid-based idle pick Tejun Heo
2026-04-29 18:21 ` [PATCH 16/17] tools/sched_ext: scx_qmap: Port to cid-form struct_ops Tejun Heo
2026-04-29 18:21 ` [PATCH 17/17] sched_ext: Require cid-form struct_ops for sub-sched support Tejun Heo
2026-04-29 18:29 ` [PATCHSET v4 sched_ext/for-7.2] sched_ext: Topological CPU IDs and cid-form struct_ops 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=20260429182131.1780125-1-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=arighi@nvidia.com \
    --cc=changwoo@igalia.com \
    --cc=emil@etsalapatis.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=sched-ext@lists.linux.dev \
    --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.