[PATCH sched_ext/for-6.11] sched, sched_ext: Replace scx_next_task_picked() with sched_class->switch_class()

[Tejun Heo <tj@kernel.org>]

From b999e365c2982dbd50f01fec520215d3c61ea2aa Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 20 Jun 2024 12:15:02 -1000

scx_next_task_picked() is used by sched_ext to notify the BPF scheduler when
a CPU is taken away by a task dispatched from a higher priority sched_class
so that the BPF scheduler can, e.g., punt the task[s] which was running or
were waiting for the CPU to other CPUs.

Replace the sched_ext specific hook scx_next_task_picked() with a new
sched_class operation switch_class().

The changes are straightforward and the code looks better afterwards.
However, when !CONFIG_SCHED_CLASS_EXT, this ends up adding an unused hook
which is unlikely to be useful to other sched_classes. For further
discussion on this subject, please refer to the following:

  http://lkml.kernel.org/r/CAHk-=wjFPLqo7AXu8maAGEGnOy6reUg-F4zzFhVB0Kyu22h7pw@mail.gmail.com

Signed-off-by: Tejun Heo <tj@kernel.org>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
Hello,

Applied to sched_ext/for-6.11. The only difference from the previous posting
is the description.

Thanks.

 kernel/sched/core.c  |  5 ++++-
 kernel/sched/ext.c   | 20 ++++++++++----------
 kernel/sched/ext.h   |  4 ----
 kernel/sched/sched.h |  2 ++
 4 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5eec6639773b..1092955a7d6e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5907,7 +5907,10 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	for_each_active_class(class) {
 		p = class->pick_next_task(rq);
 		if (p) {
-			scx_next_task_picked(rq, p, class);
+			const struct sched_class *prev_class = prev->sched_class;
+
+			if (class != prev_class && prev_class->switch_class)
+				prev_class->switch_class(rq, p);
 			return p;
 		}
 	}
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index f814e84ceeb3..390623a4a376 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2749,10 +2749,9 @@ preempt_reason_from_class(const struct sched_class *class)
 	return SCX_CPU_PREEMPT_UNKNOWN;
 }
 
-void scx_next_task_picked(struct rq *rq, struct task_struct *p,
-			  const struct sched_class *active)
+static void switch_class_scx(struct rq *rq, struct task_struct *next)
 {
-	lockdep_assert_rq_held(rq);
+	const struct sched_class *next_class = next->sched_class;
 
 	if (!scx_enabled())
 		return;
@@ -2769,12 +2768,11 @@ void scx_next_task_picked(struct rq *rq, struct task_struct *p,
 
 	/*
 	 * The callback is conceptually meant to convey that the CPU is no
-	 * longer under the control of SCX. Therefore, don't invoke the
-	 * callback if the CPU is is staying on SCX, or going idle (in which
-	 * case the SCX scheduler has actively decided not to schedule any
-	 * tasks on the CPU).
+	 * longer under the control of SCX. Therefore, don't invoke the callback
+	 * if the next class is below SCX (in which case the BPF scheduler has
+	 * actively decided not to schedule any tasks on the CPU).
 	 */
-	if (likely(active >= &ext_sched_class))
+	if (sched_class_above(&ext_sched_class, next_class))
 		return;
 
 	/*
@@ -2789,8 +2787,8 @@ void scx_next_task_picked(struct rq *rq, struct task_struct *p,
 	if (!rq->scx.cpu_released) {
 		if (SCX_HAS_OP(cpu_release)) {
 			struct scx_cpu_release_args args = {
-				.reason = preempt_reason_from_class(active),
-				.task = p,
+				.reason = preempt_reason_from_class(next_class),
+				.task = next,
 			};
 
 			SCX_CALL_OP(SCX_KF_CPU_RELEASE,
@@ -3496,6 +3494,8 @@ DEFINE_SCHED_CLASS(ext) = {
 	.put_prev_task		= put_prev_task_scx,
 	.set_next_task		= set_next_task_scx,
 
+	.switch_class		= switch_class_scx,
+
 #ifdef CONFIG_SMP
 	.balance		= balance_scx,
 	.select_task_rq		= select_task_rq_scx,
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index c41d742b5d62..bf6f2cfa49d5 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -33,8 +33,6 @@ static inline bool task_on_scx(const struct task_struct *p)
 	return scx_enabled() && p->sched_class == &ext_sched_class;
 }
 
-void scx_next_task_picked(struct rq *rq, struct task_struct *p,
-			  const struct sched_class *active);
 void scx_tick(struct rq *rq);
 void init_scx_entity(struct sched_ext_entity *scx);
 void scx_pre_fork(struct task_struct *p);
@@ -82,8 +80,6 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
 #define scx_enabled()		false
 #define scx_switched_all()	false
 
-static inline void scx_next_task_picked(struct rq *rq, struct task_struct *p,
-					const struct sched_class *active) {}
 static inline void scx_tick(struct rq *rq) {}
 static inline void scx_pre_fork(struct task_struct *p) {}
 static inline int scx_fork(struct task_struct *p) { return 0; }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c0d6e42c99cc..3989bf8f2a1b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2355,6 +2355,8 @@ struct sched_class {
 	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
 
+	void (*switch_class)(struct rq *rq, struct task_struct *next);
+
 #ifdef CONFIG_SMP
 	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
-- 
2.45.2