From: Andrea Righi <arighi@nvidia.com>
To: Tejun Heo <tj@kernel.org>, David Vernet <void@manifault.com>,
Changwoo Min <changwoo@igalia.com>,
John Stultz <jstultz@google.com>
Cc: Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Juri Lelli <juri.lelli@redhat.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Steven Rostedt <rostedt@goodmis.org>,
Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
Valentin Schneider <vschneid@redhat.com>,
K Prateek Nayak <kprateek.nayak@amd.com>,
Christian Loehle <christian.loehle@arm.com>,
David Dai <david.dai@linux.dev>, Koba Ko <kobak@nvidia.com>,
Aiqun Yu <aiqun.yu@oss.qualcomm.com>,
Shuah Khan <shuah@kernel.org>,
sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: [PATCH 04/14] sched: Add prepare_switch() class callback
Date: Sat, 25 Jul 2026 18:04:10 +0200 [thread overview]
Message-ID: <20260725160513.57477-5-arighi@nvidia.com> (raw)
In-Reply-To: <20260725160513.57477-1-arighi@nvidia.com>
sched_change_begin() only invokes callbacks on the outgoing class before
recording the task queueing state. An incoming class may need to prepare
a task while that state is still live, before the normal dequeue and
class transition take place.
Pass the incoming class to sched_change_begin() and invoke its optional
prepare_switch() callback before recording the queued and running state.
This is a preparatory change to support proxy execution with sched_ext.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
kernel/sched/core.c | 16 +++++++++++-----
kernel/sched/ext/ext.c | 7 ++++---
kernel/sched/ext/sub.c | 9 ++++++---
kernel/sched/sched.h | 10 +++++++---
kernel/sched/syscalls.c | 4 ++--
5 files changed, 30 insertions(+), 16 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9a9d4b5040089..474628f520a29 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2792,7 +2792,7 @@ void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx
static void
do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
{
- scoped_guard (sched_change, p, DEQUEUE_SAVE)
+ scoped_guard (sched_change, p, p->sched_class, DEQUEUE_SAVE)
p->sched_class->set_cpus_allowed(p, ctx);
}
@@ -7722,7 +7722,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
if (prev_class != next_class)
queue_flag |= DEQUEUE_CLASS;
- scoped_guard (sched_change, p, queue_flag) {
+ scoped_guard (sched_change, p, next_class, queue_flag) {
/*
* Boosting condition are:
* 1. -rt task is running and holds mutex A
@@ -8399,7 +8399,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
void sched_setnuma(struct task_struct *p, int nid)
{
guard(task_rq_lock)(p);
- scoped_guard (sched_change, p, DEQUEUE_SAVE)
+ scoped_guard (sched_change, p, p->sched_class, DEQUEUE_SAVE)
p->numa_preferred_nid = nid;
}
#endif /* CONFIG_NUMA_BALANCING */
@@ -9516,7 +9516,7 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup)
CLASS(task_rq_lock, rq_guard)(tsk);
rq = rq_guard.rq;
- scoped_guard (sched_change, tsk, queue_flags) {
+ scoped_guard (sched_change, tsk, tsk->sched_class, queue_flags) {
sched_change_group(tsk);
if (!for_autogroup)
scx_cgroup_move_task(tsk);
@@ -11220,7 +11220,9 @@ static inline void sched_mm_cid_fork(struct task_struct *t) { }
static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx);
-struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int flags)
+struct sched_change_ctx *
+sched_change_begin(struct task_struct *p, const struct sched_class *next_class,
+ unsigned int flags)
{
struct sched_change_ctx *ctx = this_cpu_ptr(&sched_change_ctx);
struct rq *rq = task_rq(p);
@@ -11238,6 +11240,10 @@ struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int
flags |= DEQUEUE_NOCLOCK;
}
+ if ((flags & DEQUEUE_CLASS) && next_class != p->sched_class &&
+ next_class->prepare_switch)
+ next_class->prepare_switch(rq, p);
+
if ((flags & DEQUEUE_CLASS) && p->sched_class->switching_from)
p->sched_class->switching_from(rq, p);
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 81c2d8eeae410..285bd8422193d 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -5859,7 +5859,8 @@ void scx_bypass(struct scx_sched *sch, bool bypass)
continue;
/* cycling deq/enq is enough, see the function comment */
- scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) {
+ scoped_guard (sched_change, p, p->sched_class,
+ DEQUEUE_SAVE | DEQUEUE_MOVE) {
/* nothing */ ;
}
}
@@ -6141,7 +6142,7 @@ static void scx_root_disable(struct scx_sched *sch)
if (old_class != new_class)
queue_flags |= DEQUEUE_CLASS;
- scoped_guard (sched_change, p, queue_flags) {
+ scoped_guard (sched_change, p, new_class, queue_flags) {
p->sched_class = new_class;
}
@@ -7477,7 +7478,7 @@ static void scx_root_enable_workfn(struct kthread_work *work)
if (old_class != new_class)
queue_flags |= DEQUEUE_CLASS;
- scoped_guard (sched_change, p, queue_flags) {
+ scoped_guard (sched_change, p, new_class, queue_flags) {
set_task_slice(p, READ_ONCE(sch->slice_dfl));
p->sched_class = new_class;
}
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 6da6c91e42870..765b516e06c95 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -791,7 +791,8 @@ static void scx_rehome_task(struct scx_sched *to, struct task_struct *p)
lockdep_assert_held(&p->pi_lock);
lockdep_assert_rq_held(task_rq(p));
- scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) {
+ scoped_guard (sched_change, p, p->sched_class,
+ DEQUEUE_SAVE | DEQUEUE_MOVE) {
scx_disable_and_exit_task(scx_task_sched(p), p);
scx_set_task_state(p, SCX_TASK_INIT_BEGIN);
scx_set_task_state(p, SCX_TASK_INIT);
@@ -821,7 +822,8 @@ static void scx_punt_task(struct scx_sched *to, struct task_struct *p)
lockdep_assert_rq_held(task_rq(p));
WARN_ON_ONCE(!READ_ONCE(to->bypass_depth));
- scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) {
+ scoped_guard (sched_change, p, p->sched_class,
+ DEQUEUE_SAVE | DEQUEUE_MOVE) {
scx_disable_and_exit_task(scx_task_sched(p), p);
scx_set_task_sched(p, to);
}
@@ -1471,7 +1473,8 @@ void scx_sub_enable_workfn(struct kthread_work *work)
if (!(p->scx.flags & SCX_TASK_SUB_INIT))
continue;
- scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) {
+ scoped_guard (sched_change, p, p->sched_class,
+ DEQUEUE_SAVE | DEQUEUE_MOVE) {
/*
* $p must be either READY or ENABLED. If ENABLED,
* __scx_disabled_and_exit_task() first disables and
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 437c4f68c9e53..ca436a8174d30 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2705,6 +2705,7 @@ struct sched_class {
/*
* sched_change
*/
+ void (*prepare_switch)(struct rq *this_rq, struct task_struct *task);
void (*switching_from)(struct rq *this_rq, struct task_struct *task);
void (*switched_from) (struct rq *this_rq, struct task_struct *task);
void (*switching_to) (struct rq *this_rq, struct task_struct *task);
@@ -4214,13 +4215,16 @@ struct sched_change_ctx {
bool running;
};
-struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int flags);
+struct sched_change_ctx *
+sched_change_begin(struct task_struct *p, const struct sched_class *next_class,
+ unsigned int flags);
void sched_change_end(struct sched_change_ctx *ctx);
DEFINE_CLASS(sched_change, struct sched_change_ctx *,
sched_change_end(_T),
- sched_change_begin(p, flags),
- struct task_struct *p, unsigned int flags)
+ sched_change_begin(p, next_class, flags),
+ struct task_struct *p, const struct sched_class *next_class,
+ unsigned int flags)
DEFINE_CLASS_IS_UNCONDITIONAL(sched_change)
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index b215b0ead9a60..bc32ce76ff4fe 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -85,7 +85,7 @@ void set_user_nice(struct task_struct *p, long nice)
return;
}
- scoped_guard (sched_change, p, DEQUEUE_SAVE) {
+ scoped_guard (sched_change, p, p->sched_class, DEQUEUE_SAVE) {
p->static_prio = NICE_TO_PRIO(nice);
set_load_weight(p, true);
old_prio = p->prio;
@@ -678,7 +678,7 @@ int __sched_setscheduler(struct task_struct *p,
if (prev_class != next_class)
queue_flags |= DEQUEUE_CLASS;
- scoped_guard (sched_change, p, queue_flags) {
+ scoped_guard (sched_change, p, next_class, queue_flags) {
if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
__setscheduler_params(p, attr);
--
2.55.0
next prev parent reply other threads:[~2026-07-25 16:05 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-25 16:04 [PATCHSET v9 sched_ext/for-7.3] sched: Make proxy execution compatible with sched_ext Andrea Righi
2026-07-25 16:04 ` [PATCH 01/14] sched/core: Avoid false migration warning for proxy donors Andrea Righi
2026-07-25 16:04 ` [PATCH 02/14] sched: Make NOHZ CFS bandwidth checks follow proxy donor Andrea Righi
2026-07-25 16:26 ` sashiko-bot
2026-07-25 16:04 ` [PATCH 03/14] sched: Add helper to block retained proxy donors Andrea Righi
2026-07-25 16:04 ` Andrea Righi [this message]
2026-07-25 16:25 ` [PATCH 04/14] sched: Add prepare_switch() class callback sashiko-bot
2026-07-25 16:04 ` [PATCH 05/14] sched: Add sched_ext hooks for proxy execution Andrea Righi
2026-07-25 16:14 ` sashiko-bot
2026-07-25 16:04 ` [PATCH 06/14] sched_ext: Block proxy donors across scheduler transitions Andrea Righi
2026-07-25 16:04 ` [PATCH 07/14] sched_ext: Fix ops.running/stopping() pairing for proxy-exec donors Andrea Righi
2026-07-25 16:04 ` [PATCH 08/14] sched_ext: Generalize the reject DSQ reenqueue path Andrea Righi
2026-07-25 16:04 ` [PATCH 09/14] sched_ext: Handle proxy-exec races in remote DSQ transfers Andrea Righi
2026-07-25 16:04 ` [PATCH 10/14] sched_ext: Split curr|donor references properly Andrea Righi
2026-07-25 16:04 ` [PATCH 11/14] sched_ext: Delegate proxy donor admission to BPF schedulers Andrea Righi
2026-07-25 16:04 ` [PATCH 12/14] sched_ext: Add selftest for blocked donor admission Andrea Righi
2026-07-25 16:04 ` [PATCH 13/14] sched_ext: scx_qmap: Add proxy execution support Andrea Righi
2026-07-25 16:04 ` [PATCH 14/14] sched: Allow enabling proxy exec with sched_ext Andrea Righi
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=20260725160513.57477-5-arighi@nvidia.com \
--to=arighi@nvidia.com \
--cc=aiqun.yu@oss.qualcomm.com \
--cc=bsegall@google.com \
--cc=changwoo@igalia.com \
--cc=christian.loehle@arm.com \
--cc=david.dai@linux.dev \
--cc=dietmar.eggemann@arm.com \
--cc=jstultz@google.com \
--cc=juri.lelli@redhat.com \
--cc=kobak@nvidia.com \
--cc=kprateek.nayak@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=sched-ext@lists.linux.dev \
--cc=shuah@kernel.org \
--cc=tj@kernel.org \
--cc=vincent.guittot@linaro.org \
--cc=void@manifault.com \
--cc=vschneid@redhat.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.