sched: Fold sched_class::switch{ing,ed}_{to,from}() into the change pattern

Add {DE,EN}QUEUE_CLASS and fold the sched_class::switch* methods into
the change pattern. This completes and makes the pattern more
symmetric.

This changes the order of callbacks slightly:

  OLD                              NEW
				|
				|  switching_from()
  dequeue_task();		|  dequeue_task()
  put_prev_task();		|  put_prev_task()
				|  switched_from()
				|
  ... change task ...		|  ... change task ...
				|
  switching_to();		|  switching_to()
  enqueue_task();		|  enqueue_task()
  set_next_task();		|  set_next_task()
  prev_class->switched_from()	|
  switched_to()			|  switched_to()
				|

Notably, it moves the switched_from() callback right after the
dequeue/put. Existing implementations don't appear to be affected by
this change in location -- specifically the task isn't enqueued on the
class in question in either location.

Make (CLASS)^(SAVE|MOVE), because there is nothing to save-restore
when changing scheduling classes.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>

kernel/sched/core.c

@@ -2169,34 +2169,9 @@ inline int task_curr(const struct task_struct *p)
 	return cpu_curr(task_cpu(p)) == p;
 }
 
-/*
+void check_prio_changed(struct rq *rq, struct task_struct *p, int oldprio)
- * ->switching_to() is called with the pi_lock and rq_lock held and must not
- * mess with locking.
- */
-void check_class_changing(struct rq *rq, struct task_struct *p,
-			  const struct sched_class *prev_class)
 {
-	if (prev_class != p->sched_class && p->sched_class->switching_to)
+	if (oldprio != p->prio || dl_task(p))
-		p->sched_class->switching_to(rq, p);
-}
-
-/*
- * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
- * use the balance_callback list if you want balancing.
- *
- * this means any call to check_class_changed() must be followed by a call to
- * balance_callback().
- */
-void check_class_changed(struct rq *rq, struct task_struct *p,
-			 const struct sched_class *prev_class,
-			 int oldprio)
-{
-	if (prev_class != p->sched_class) {
-		if (prev_class->switched_from)
-			prev_class->switched_from(rq, p);
-
-		p->sched_class->switched_to(rq, p);
-	} else if (oldprio != p->prio || dl_task(p))
 		p->sched_class->prio_changed(rq, p, oldprio);
 }
 
@@ -7388,6 +7363,9 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	prev_class = p->sched_class;
 	next_class = __setscheduler_class(p->policy, prio);
 
+	if (prev_class != next_class)
+		queue_flag |= DEQUEUE_CLASS;
+
 	if (prev_class != next_class && p->se.sched_delayed)
 		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
 
@@ -7424,11 +7402,10 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 
 		p->sched_class = next_class;
 		p->prio = prio;
-
-		check_class_changing(rq, p, prev_class);
 	}
 
-	check_class_changed(rq, p, prev_class, oldprio);
+	if (!(queue_flag & DEQUEUE_CLASS))
+		check_prio_changed(rq, p, oldprio);
 out_unlock:
 	/* Avoid rq from going away on us: */
 	preempt_disable();
@@ -10862,6 +10839,11 @@ struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int
 
 	lockdep_assert_rq_held(rq);
 
+	if (flags & DEQUEUE_CLASS) {
+		if (p->sched_class->switching_from)
+			p->sched_class->switching_from(rq, p);
+	}
+
 	*ctx = (struct sched_change_ctx){
 		.p = p,
 		.flags = flags,
@@ -10874,6 +10856,9 @@ struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int
 	if (ctx->running)
 		put_prev_task(rq, p);
 
+	if ((flags & DEQUEUE_CLASS) && p->sched_class->switched_from)
+		p->sched_class->switched_from(rq, p);
+
 	return ctx;
 }
 
@@ -10884,8 +10869,14 @@ void sched_change_end(struct sched_change_ctx *ctx)
 
 	lockdep_assert_rq_held(rq);
 
+	if ((ctx->flags & ENQUEUE_CLASS) && p->sched_class->switching_to)
+		p->sched_class->switching_to(rq, p);
+
 	if (ctx->queued)
 		enqueue_task(rq, p, ctx->flags | ENQUEUE_NOCLOCK);
 	if (ctx->running)
 		set_next_task(rq, p);
+
+	if ((ctx->flags & ENQUEUE_CLASS) && p->sched_class->switched_to)
+		p->sched_class->switched_to(rq, p);
 }

kernel/sched/ext.c

@@ -3912,21 +3912,26 @@ static void scx_disable_workfn(struct kthread_work *work)
 
 	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
+		unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 		const struct sched_class *old_class = p->sched_class;
 		const struct sched_class *new_class =
 			__setscheduler_class(p->policy, p->prio);
 
 		update_rq_clock(task_rq(p));
 
+		if (old_class != new_class)
+			queue_flags |= DEQUEUE_CLASS;
+
 		if (old_class != new_class && p->se.sched_delayed)
 			dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
 
-		scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK) {
+		scoped_guard (sched_change, p, queue_flags) {
 			p->sched_class = new_class;
-			check_class_changing(task_rq(p), p, old_class);
 		}
 
-		check_class_changed(task_rq(p), p, old_class, p->prio);
+		if (!(queue_flags & DEQUEUE_CLASS))
+			check_prio_changed(task_rq(p), p, p->prio);
+
 		scx_exit_task(p);
 	}
 	scx_task_iter_stop(&sti);
@@ -4655,6 +4660,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	percpu_down_write(&scx_fork_rwsem);
 	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
+		unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 		const struct sched_class *old_class = p->sched_class;
 		const struct sched_class *new_class =
 			__setscheduler_class(p->policy, p->prio);
@@ -4664,16 +4670,20 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 
 		update_rq_clock(task_rq(p));
 
+		if (old_class != new_class)
+			queue_flags |= DEQUEUE_CLASS;
+
 		if (old_class != new_class && p->se.sched_delayed)
 			dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
 
-		scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK) {
+		scoped_guard (sched_change, p, queue_flags) {
 			p->scx.slice = SCX_SLICE_DFL;
 			p->sched_class = new_class;
-			check_class_changing(task_rq(p), p, old_class);
 		}
 
-		check_class_changed(task_rq(p), p, old_class, p->prio);
+		if (!(queue_flags & DEQUEUE_CLASS))
+			check_prio_changed(task_rq(p), p, p->prio);
+
 		put_task_struct(p);
 	}
 	scx_task_iter_stop(&sti);

kernel/sched/idle.c

@@ -498,7 +498,7 @@ static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
 {
 }
 
-static void switched_to_idle(struct rq *rq, struct task_struct *p)
+static void switching_to_idle(struct rq *rq, struct task_struct *p)
 {
 	BUG();
 }
@@ -536,6 +536,6 @@ DEFINE_SCHED_CLASS(idle) = {
 	.task_tick		= task_tick_idle,
 
 	.prio_changed		= prio_changed_idle,
-	.switched_to		= switched_to_idle,
+	.switching_to		= switching_to_idle,
 	.update_curr		= update_curr_idle,
 };

kernel/sched/rt.c

@@ -2589,8 +2589,8 @@ DEFINE_SCHED_CLASS(rt) = {
 
 	.get_rr_interval	= get_rr_interval_rt,
 
-	.prio_changed		= prio_changed_rt,
 	.switched_to		= switched_to_rt,
+	.prio_changed		= prio_changed_rt,
 
 	.update_curr		= update_curr_rt,
 

kernel/sched/sched.h

@@ -20,7 +20,6 @@
 #include <linux/sched/task_flags.h>
 #include <linux/sched/task.h>
 #include <linux/sched/topology.h>
-
 #include <linux/atomic.h>
 #include <linux/bitmap.h>
 #include <linux/bug.h>
@@ -2369,6 +2368,7 @@ extern const u32		sched_prio_to_wmult[40];
 
 #define DEQUEUE_MIGRATING	0x0010 /* Matches ENQUEUE_MIGRATING */
 #define DEQUEUE_DELAYED		0x0020 /* Matches ENQUEUE_DELAYED */
+#define DEQUEUE_CLASS		0x0040 /* Matches ENQUEUE_CLASS */
 
 #define DEQUEUE_SPECIAL		0x00010000
 #define DEQUEUE_THROTTLE	0x00020000
@@ -2380,6 +2380,7 @@ extern const u32		sched_prio_to_wmult[40];
 
 #define ENQUEUE_MIGRATING	0x0010
 #define ENQUEUE_DELAYED		0x0020
+#define ENQUEUE_CLASS		0x0040
 
 #define ENQUEUE_HEAD		0x00010000
 #define ENQUEUE_REPLENISH	0x00020000
@@ -2443,14 +2444,11 @@ struct sched_class {
 	void (*task_fork)(struct task_struct *p);
 	void (*task_dead)(struct task_struct *p);
 
-	/*
+	void (*switching_from)(struct rq *this_rq, struct task_struct *task);
-	 * The switched_from() call is allowed to drop rq->lock, therefore we
+	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
-	 * cannot assume the switched_from/switched_to pair is serialized by
+	void (*switching_to)  (struct rq *this_rq, struct task_struct *task);
-	 * rq->lock. They are however serialized by p->pi_lock.
+	void (*switched_to)   (struct rq *this_rq, struct task_struct *task);
-	 */
+
-	void (*switching_to) (struct rq *this_rq, struct task_struct *task);
-	void (*switched_from)(struct rq *this_rq, struct task_struct *task);
-	void (*switched_to)  (struct rq *this_rq, struct task_struct *task);
 	void (*reweight_task)(struct rq *this_rq, struct task_struct *task,
 			      const struct load_weight *lw);
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
@@ -3879,11 +3877,7 @@ extern void set_load_weight(struct task_struct *p, bool update_load);
 extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags);
 extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags);
 
-extern void check_class_changing(struct rq *rq, struct task_struct *p,
+extern void check_prio_changed(struct rq *rq, struct task_struct *p, int oldprio);
-				 const struct sched_class *prev_class);
-extern void check_class_changed(struct rq *rq, struct task_struct *p,
-				const struct sched_class *prev_class,
-				int oldprio);
 
 extern struct balance_callback *splice_balance_callbacks(struct rq *rq);
 extern void balance_callbacks(struct rq *rq, struct balance_callback *head);

kernel/sched/stop_task.c

@@ -75,7 +75,7 @@ static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
 {
 }
 
-static void switched_to_stop(struct rq *rq, struct task_struct *p)
+static void switching_to_stop(struct rq *rq, struct task_struct *p)
 {
 	BUG(); /* its impossible to change to this class */
 }
@@ -112,6 +112,6 @@ DEFINE_SCHED_CLASS(stop) = {
 	.task_tick		= task_tick_stop,
 
 	.prio_changed		= prio_changed_stop,
-	.switched_to		= switched_to_stop,
+	.switching_to		= switching_to_stop,
 	.update_curr		= update_curr_stop,
 };

kernel/sched/syscalls.c

@@ -684,6 +684,9 @@ int __sched_setscheduler(struct task_struct *p,
 	prev_class = p->sched_class;
 	next_class = __setscheduler_class(policy, newprio);
 
+	if (prev_class != next_class)
+		queue_flags |= DEQUEUE_CLASS;
+
 	if (prev_class != next_class && p->se.sched_delayed)
 		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
 
@@ -695,7 +698,6 @@ int __sched_setscheduler(struct task_struct *p,
 			p->prio = newprio;
 		}
 		__setscheduler_uclamp(p, attr);
-		check_class_changing(rq, p, prev_class);
 
 		if (scope->queued) {
 			/*
@@ -707,7 +709,8 @@ int __sched_setscheduler(struct task_struct *p,
 		}
 	}
 
-	check_class_changed(rq, p, prev_class, oldprio);
+	if (!(queue_flags & DEQUEUE_CLASS))
+		check_prio_changed(rq, p, oldprio);
 
 	/* Avoid rq from going away on us: */
 	preempt_disable();