[PATCH 03/15] sched: Pass next class to sched_change_begin()
From: Andrea Righi
Date: Mon Aug 10 2026 - 11:32:42 EST
sched_change_begin() currently only receives the task whose scheduling
state is being changed. It cannot distinguish a class transition from a
same-class update before recording the task queueing state.
Pass the incoming scheduling class to sched_change_begin() and update all
callers. This allows transition handling to run before the normal dequeue
and class change.
This is a preparatory change to support proxy execution with sched_ext.
Signed-off-by: Andrea Righi <arighi@xxxxxxxxxx>
---
kernel/sched/core.c | 12 +++++++-----
kernel/sched/ext/ext.c | 7 ++++---
kernel/sched/ext/sub.c | 9 ++++++---
kernel/sched/sched.h | 9 ++++++---
kernel/sched/syscalls.c | 4 ++--
5 files changed, 25 insertions(+), 16 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 96b8b01d43101..e71fd07254d6e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2785,7 +2785,7 @@ 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);
}
@@ -7687,7 +7687,7 @@ 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
@@ -8364,7 +8364,7 @@ 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 */
@@ -9481,7 +9481,7 @@ 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);
@@ -11185,7 +11185,9 @@ 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);
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 0bbe144c98111..17dab1543f012 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -6069,7 +6069,8 @@ void scx_bypass(struct scx_sched *sch, bool bypass)
scx_task_slice_ended(rq, p);
/* 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 */ ;
}
}
@@ -6350,7 +6351,7 @@ 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;
}
@@ -7716,7 +7717,7 @@ 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) {
scx_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 b81254be1b04c..9e1f1afd389f1 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -1253,7 +1253,8 @@ 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);
@@ -1283,7 +1284,8 @@ 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);
}
@@ -1937,7 +1939,8 @@ 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 63786712a1156..7779bcf7c6a12 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -4220,13 +4220,16 @@ 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