1 files changed, 64 insertions, 22 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d78d7b6d30bb..23406f037dde 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -119,6 +119,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_entry_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_exit_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_set_need_resched_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 DEFINE_PER_CPU(struct rnd_state, sched_rnd_state);
@@ -1141,6 +1144,7 @@ void __trace_set_need_resched(struct task_struct *curr, int tif)
 {
 	trace_sched_set_need_resched_tp(curr, smp_processor_id(), tif);
 }
+EXPORT_SYMBOL_GPL(__trace_set_need_resched);
 
 void resched_curr(struct rq *rq)
 {
@@ -2095,7 +2099,6 @@ void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	 */
 	uclamp_rq_inc(rq, p, flags);
 
-	rq->queue_mask |= p->sched_class->queue_mask;
 	p->sched_class->enqueue_task(rq, p, flags);
 
 	psi_enqueue(p, flags);
@@ -2128,7 +2131,6 @@ inline bool dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 	 * and mark the task ->sched_delayed.
 	 */
 	uclamp_rq_dec(rq, p);
-	rq->queue_mask |= p->sched_class->queue_mask;
 	return p->sched_class->dequeue_task(rq, p, flags);
 }
 
@@ -2179,10 +2181,14 @@ void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *donor = rq->donor;
 
-	if (p->sched_class == donor->sched_class)
-		donor->sched_class->wakeup_preempt(rq, p, flags);
-	else if (sched_class_above(p->sched_class, donor->sched_class))
+	if (p->sched_class == rq->next_class) {
+		rq->next_class->wakeup_preempt(rq, p, flags);
+
+	} else if (sched_class_above(p->sched_class, rq->next_class)) {
+		rq->next_class->wakeup_preempt(rq, p, flags);
 		resched_curr(rq);
+		rq->next_class = p->sched_class;
+	}
 
 	/*
 	 * A queue event has occurred, and we're going to schedule.  In
@@ -3620,6 +3626,18 @@ static inline void ttwu_do_wakeup(struct task_struct *p)
 	trace_sched_wakeup(p);
 }
 
+void update_rq_avg_idle(struct rq *rq)
+{
+	u64 delta = rq_clock(rq) - rq->idle_stamp;
+	u64 max = 2*rq->max_idle_balance_cost;
+
+	update_avg(&rq->avg_idle, delta);
+
+	if (rq->avg_idle > max)
+		rq->avg_idle = max;
+	rq->idle_stamp = 0;
+}
+
 static void
 ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		 struct rq_flags *rf)
@@ -3655,18 +3673,6 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		p->sched_class->task_woken(rq, p);
 		rq_repin_lock(rq, rf);
 	}
-
-	if (rq->idle_stamp) {
-		u64 delta = rq_clock(rq) - rq->idle_stamp;
-		u64 max = 2*rq->max_idle_balance_cost;
-
-		update_avg(&rq->avg_idle, delta);
-
-		if (rq->avg_idle > max)
-			rq->avg_idle = max;
-
-		rq->idle_stamp = 0;
-	}
 }
 
 /*
@@ -6836,6 +6842,7 @@ static void __sched notrace __schedule(int sched_mode)
 pick_again:
 	next = pick_next_task(rq, rq->donor, &rf);
 	rq_set_donor(rq, next);
+	rq->next_class = next->sched_class;
 	if (unlikely(task_is_blocked(next))) {
 		next = find_proxy_task(rq, next, &rf);
 		if (!next)
@@ -7580,7 +7587,7 @@ int preempt_dynamic_mode = preempt_dynamic_undefined;
 
 int sched_dynamic_mode(const char *str)
 {
-# ifndef CONFIG_PREEMPT_RT
+# if !(defined(CONFIG_PREEMPT_RT) || defined(CONFIG_ARCH_HAS_PREEMPT_LAZY))
 	if (!strcmp(str, "none"))
 		return preempt_dynamic_none;
 
@@ -8512,6 +8519,9 @@ int sched_cpu_dying(unsigned int cpu)
 		dump_rq_tasks(rq, KERN_WARNING);
 	}
 	dl_server_stop(&rq->fair_server);
+#ifdef CONFIG_SCHED_CLASS_EXT
+	dl_server_stop(&rq->ext_server);
+#endif
 	rq_unlock_irqrestore(rq, &rf);
 
 	calc_load_migrate(rq);
@@ -8687,6 +8697,8 @@ void __init sched_init(void)
 		rq->rt.rt_runtime = global_rt_runtime();
 		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
 #endif
+		rq->next_class = &idle_sched_class;
+
 		rq->sd = NULL;
 		rq->rd = NULL;
 		rq->cpu_capacity = SCHED_CAPACITY_SCALE;
@@ -8715,6 +8727,9 @@ void __init sched_init(void)
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
 		fair_server_init(rq);
+#ifdef CONFIG_SCHED_CLASS_EXT
+		ext_server_init(rq);
+#endif
 
 #ifdef CONFIG_SCHED_CORE
 		rq->core = rq;
@@ -9146,6 +9161,7 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup)
 {
 	unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
 	bool resched = false;
+	bool queued = false;
 	struct rq *rq;
 
 	CLASS(task_rq_lock, rq_guard)(tsk);
@@ -9157,10 +9173,13 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup)
 			scx_cgroup_move_task(tsk);
 		if (scope->running)
 			resched = true;
+		queued = scope->queued;
 	}
 
 	if (resched)
 		resched_curr(rq);
+	else if (queued)
+		wakeup_preempt(rq, tsk, 0);
 
 	__balance_callbacks(rq, &rq_guard.rf);
 }
@@ -10883,13 +10902,12 @@ struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int
 		flags |= DEQUEUE_NOCLOCK;
 	}
 
-	if (flags & DEQUEUE_CLASS) {
-		if (p->sched_class->switching_from)
-			p->sched_class->switching_from(rq, p);
-	}
+	if ((flags & DEQUEUE_CLASS) && p->sched_class->switching_from)
+		p->sched_class->switching_from(rq, p);
 
 	*ctx = (struct sched_change_ctx){
 		.p = p,
+		.class = p->sched_class,
 		.flags = flags,
 		.queued = task_on_rq_queued(p),
 		.running = task_current_donor(rq, p),
@@ -10920,6 +10938,11 @@ void sched_change_end(struct sched_change_ctx *ctx)
 
 	lockdep_assert_rq_held(rq);
 
+	/*
+	 * Changing class without *QUEUE_CLASS is bad.
+	 */
+	WARN_ON_ONCE(p->sched_class != ctx->class && !(ctx->flags & ENQUEUE_CLASS));
+
 	if ((ctx->flags & ENQUEUE_CLASS) && p->sched_class->switching_to)
 		p->sched_class->switching_to(rq, p);
 
@@ -10931,6 +10954,25 @@ void sched_change_end(struct sched_change_ctx *ctx)
 	if (ctx->flags & ENQUEUE_CLASS) {
 		if (p->sched_class->switched_to)
 			p->sched_class->switched_to(rq, p);
+
+		if (ctx->running) {
+			/*
+			 * If this was a class promotion; let the old class
+			 * know it got preempted. Note that none of the
+			 * switch*_from() methods know the new class and none
+			 * of the switch*_to() methods know the old class.
+			 */
+			if (sched_class_above(p->sched_class, ctx->class)) {
+				rq->next_class->wakeup_preempt(rq, p, 0);
+				rq->next_class = p->sched_class;
+			}
+			/*
+			 * If this was a degradation in class; make sure to
+			 * reschedule.
+			 */
+			if (sched_class_above(ctx->class, p->sched_class))
+				resched_curr(rq);
+		}
 	} else {
 		p->sched_class->prio_changed(rq, p, ctx->prio);
 	}