sched: Move sched_class::prio_changed() into the change pattern

Move sched_class::prio_changed() into the change pattern.

And while there, extend it with sched_class::get_prio() in order to
fix the deadline sitation.

Suggested-by: Tejun Heo <tj@kernel.org>
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

@@ -2169,12 +2169,6 @@ 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)
-{
-	if (oldprio != p->prio || dl_task(p))
-		p->sched_class->prio_changed(rq, p, oldprio);
-}
-
 void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *donor = rq->donor;
@@ -7400,9 +7394,6 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 		p->sched_class = next_class;
 		p->prio = prio;
 	}
-
-	if (!(queue_flag & DEQUEUE_CLASS))
-		check_prio_changed(rq, p, oldprio);
 out_unlock:
 	/* Avoid rq from going away on us: */
 	preempt_disable();
@@ -10855,6 +10846,13 @@ struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int
 		.running = task_current_donor(rq, p),
 	};
 
+	if (!(flags & DEQUEUE_CLASS)) {
+		if (p->sched_class->get_prio)
+			ctx->prio = p->sched_class->get_prio(rq, p);
+		else
+			ctx->prio = p->prio;
+	}
+
 	if (ctx->queued)
 		dequeue_task(rq, p, flags);
 	if (ctx->running)
@@ -10881,6 +10879,10 @@ void sched_change_end(struct sched_change_ctx *ctx)
 	if (ctx->running)
 		set_next_task(rq, p);
 
-	if ((ctx->flags & ENQUEUE_CLASS) && p->sched_class->switched_to)
+	if (ctx->flags & ENQUEUE_CLASS) {
-		p->sched_class->switched_to(rq, p);
+		if (p->sched_class->switched_to)
+			p->sched_class->switched_to(rq, p);
+	} else {
+		p->sched_class->prio_changed(rq, p, ctx->prio);
+	}
 }

kernel/sched/deadline.c

@@ -3042,23 +3042,24 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 	}
 }
 
+static u64 get_prio_dl(struct rq *rq, struct task_struct *p)
+{
+	return p->dl.deadline;
+}
+
 /*
  * If the scheduling parameters of a -deadline task changed,
  * a push or pull operation might be needed.
  */
-static void prio_changed_dl(struct rq *rq, struct task_struct *p,
+static void prio_changed_dl(struct rq *rq, struct task_struct *p, u64 old_deadline)
-			    int oldprio)
 {
 	if (!task_on_rq_queued(p))
 		return;
 
-	/*
+	if (p->dl.deadline == old_deadline)
-	 * This might be too much, but unfortunately
+		return;
-	 * we don't have the old deadline value, and
+
-	 * we can't argue if the task is increasing
+	if (dl_time_before(old_deadline, p->dl.deadline))
-	 * or lowering its prio, so...
-	 */
-	if (!rq->dl.overloaded)
 		deadline_queue_pull_task(rq);
 
 	if (task_current_donor(rq, p)) {
@@ -3113,6 +3114,7 @@ DEFINE_SCHED_CLASS(dl) = {
 	.task_tick		= task_tick_dl,
 	.task_fork              = task_fork_dl,
 
+	.get_prio		= get_prio_dl,
 	.prio_changed           = prio_changed_dl,
 	.switched_from		= switched_from_dl,
 	.switched_to		= switched_to_dl,

kernel/sched/ext.c

@@ -2961,7 +2961,7 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p,
 				 p, p->scx.weight);
 }
 
-static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio)
+static void prio_changed_scx(struct rq *rq, struct task_struct *p, u64 oldprio)
 {
 }
 
@@ -3926,9 +3926,6 @@ static void scx_disable_workfn(struct kthread_work *work)
 			p->sched_class = new_class;
 		}
 
-		if (!(queue_flags & DEQUEUE_CLASS))
-			check_prio_changed(task_rq(p), p, p->prio);
-
 		scx_exit_task(p);
 	}
 	scx_task_iter_stop(&sti);
@@ -4675,9 +4672,6 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 			p->sched_class = new_class;
 		}
 
-		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/fair.c

@@ -13150,11 +13150,14 @@ static void task_fork_fair(struct task_struct *p)
  * the current task.
  */
 static void
-prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
+prio_changed_fair(struct rq *rq, struct task_struct *p, u64 oldprio)
 {
 	if (!task_on_rq_queued(p))
 		return;
 
+	if (p->prio == oldprio)
+		return;
+
 	if (rq->cfs.nr_queued == 1)
 		return;
 
@@ -13166,8 +13169,9 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 	if (task_current_donor(rq, p)) {
 		if (p->prio > oldprio)
 			resched_curr(rq);
-	} else
+	} else {
 		wakeup_preempt(rq, p, 0);
+	}
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED

kernel/sched/idle.c

@@ -504,8 +504,11 @@ static void switching_to_idle(struct rq *rq, struct task_struct *p)
 }
 
 static void
-prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
+prio_changed_idle(struct rq *rq, struct task_struct *p, u64 oldprio)
 {
+	if (p->prio == oldprio)
+		return;
+
 	BUG();
 }
 

kernel/sched/rt.c

@@ -2437,11 +2437,14 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
  * us to initiate a push or pull.
  */
 static void
-prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
+prio_changed_rt(struct rq *rq, struct task_struct *p, u64 oldprio)
 {
 	if (!task_on_rq_queued(p))
 		return;
 
+	if (p->prio == oldprio)
+		return;
+
 	if (task_current_donor(rq, p)) {
 		/*
 		 * If our priority decreases while running, we

kernel/sched/sched.h

@@ -2451,8 +2451,10 @@ struct sched_class {
 
 	void (*reweight_task)(struct rq *this_rq, struct task_struct *task,
 			      const struct load_weight *lw);
+
+	u64  (*get_prio)     (struct rq *this_rq, struct task_struct *task);
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
-			      int oldprio);
+			      u64 oldprio);
 
 	unsigned int (*get_rr_interval)(struct rq *rq,
 					struct task_struct *task);
@@ -3877,8 +3879,6 @@ 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_prio_changed(struct rq *rq, struct task_struct *p, int oldprio);
-
 extern struct balance_callback *splice_balance_callbacks(struct rq *rq);
 extern void balance_callbacks(struct rq *rq, struct balance_callback *head);
 
@@ -3899,6 +3899,7 @@ extern void balance_callbacks(struct rq *rq, struct balance_callback *head);
  * the task's queueing state is idempotent across the operation.
  */
 struct sched_change_ctx {
+	u64			prio;
 	struct task_struct	*p;
 	int			flags;
 	bool			queued;

kernel/sched/stop_task.c

@@ -81,8 +81,11 @@ static void switching_to_stop(struct rq *rq, struct task_struct *p)
 }
 
 static void
-prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
+prio_changed_stop(struct rq *rq, struct task_struct *p, u64 oldprio)
 {
+	if (p->prio == oldprio)
+		return;
+
 	BUG(); /* how!?, what priority? */
 }
 

kernel/sched/syscalls.c

@@ -95,12 +95,6 @@ void set_user_nice(struct task_struct *p, long nice)
 		old_prio = p->prio;
 		p->prio = effective_prio(p);
 	}
-
-	/*
-	 * If the task increased its priority or is running and
-	 * lowered its priority, then reschedule its CPU:
-	 */
-	p->sched_class->prio_changed(rq, p, old_prio);
 }
 EXPORT_SYMBOL(set_user_nice);
 
@@ -706,9 +700,6 @@ int __sched_setscheduler(struct task_struct *p,
 		}
 	}
 
-	if (!(queue_flags & DEQUEUE_CLASS))
-		check_prio_changed(rq, p, oldprio);
-
 	/* Avoid rq from going away on us: */
 	preempt_disable();
 	head = splice_balance_callbacks(rq);