Merge tag 'sched-core-2025-12-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Scalability and load-balancing improvements:

   - Enable scheduler feature NEXT_BUDDY (Mel Gorman)

   - Reimplement NEXT_BUDDY to align with EEVDF goals (Mel Gorman)

   - Skip sched_balance_running cmpxchg when balance is not due (Tim
     Chen)

   - Implement generic code for architecture specific sched domain NUMA
     distances (Tim Chen)

   - Optimize the NUMA distances of the sched-domains builds of Intel
     Granite Rapids (GNR) and Clearwater Forest (CWF) platforms (Tim
     Chen)

   - Implement proportional newidle balance: a randomized algorithm that
     runs newidle balancing proportional to its success rate. (Peter
     Zijlstra)

  Scheduler infrastructure changes:

   - Implement the 'sched_change' scoped_guard() pattern for the entire
     scheduler (Peter Zijlstra)

   - More broadly utilize the sched_change guard (Peter Zijlstra)

   - Add support to pick functions to take runqueue-flags (Joel
     Fernandes)

   - Provide and use set_need_resched_current() (Peter Zijlstra)

  Fair scheduling enhancements:

   - Forfeit vruntime on yield (Fernand Sieber)

   - Only update stats for allowed CPUs when looking for dst group (Adam
     Li)

  CPU-core scheduling enhancements:

   - Optimize core cookie matching check (Fernand Sieber)

  Deadline scheduler fixes:

   - Only set free_cpus for online runqueues (Doug Berger)

   - Fix dl_server time accounting (Peter Zijlstra)

   - Fix dl_server stop condition (Peter Zijlstra)

  Proxy scheduling fixes:

   - Yield the donor task (Fernand Sieber)

  Fixes and cleanups:

   - Fix do_set_cpus_allowed() locking (Peter Zijlstra)

   - Fix migrate_disable_switch() locking (Peter Zijlstra)

   - Remove double update_rq_clock() in __set_cpus_allowed_ptr_locked()
     (Hao Jia)

   - Increase sched_tick_remote timeout (Phil Auld)

   - sched/deadline: Use cpumask_weight_and() in dl_bw_cpus() (Shrikanth
     Hegde)

   - sched/deadline: Clean up select_task_rq_dl() (Shrikanth Hegde)"

* tag 'sched-core-2025-12-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  sched: Provide and use set_need_resched_current()
  sched/fair: Proportional newidle balance
  sched/fair: Small cleanup to update_newidle_cost()
  sched/fair: Small cleanup to sched_balance_newidle()
  sched/fair: Revert max_newidle_lb_cost bump
  sched/fair: Reimplement NEXT_BUDDY to align with EEVDF goals
  sched/fair: Enable scheduler feature NEXT_BUDDY
  sched: Increase sched_tick_remote timeout
  sched/fair: Have SD_SERIALIZE affect newidle balancing
  sched/fair: Skip sched_balance_running cmpxchg when balance is not due
  sched/deadline: Minor cleanup in select_task_rq_dl()
  sched/deadline: Use cpumask_weight_and() in dl_bw_cpus
  sched/deadline: Document dl_server
  sched/deadline: Fix dl_server stop condition
  sched/deadline: Fix dl_server time accounting
  sched/core: Remove double update_rq_clock() in __set_cpus_allowed_ptr_locked()
  sched/eevdf: Fix min_vruntime vs avg_vruntime
  sched/core: Add comment explaining force-idle vruntime snapshots
  sched/core: Optimize core cookie matching check
  sched/proxy: Yield the donor task
  ...

1 files changed, 162 insertions, 238 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f754a60de848..0c4ff93eeb78 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -121,6 +121,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DEFINE_PER_CPU(struct rnd_state, sched_rnd_state);
 
 #ifdef CONFIG_SCHED_PROXY_EXEC
 DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec);
@@ -583,8 +584,8 @@ EXPORT_SYMBOL(__trace_set_current_state);
  *
  * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
  *
- *   is set by activate_task() and cleared by deactivate_task(), under
- *   rq->lock. Non-zero indicates the task is runnable, the special
+ *   is set by activate_task() and cleared by deactivate_task()/block_task(),
+ *   under rq->lock. Non-zero indicates the task is runnable, the special
  *   ON_RQ_MIGRATING state is used for migration without holding both
  *   rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
  *
@@ -2089,6 +2090,7 @@ 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);
@@ -2121,6 +2123,7 @@ 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);
 }
 
@@ -2169,37 +2172,6 @@ inline int task_curr(const struct task_struct *p)
 	return cpu_curr(task_cpu(p)) == p;
 }
 
-/*
- * ->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)
-		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);
-}
-
 void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *donor = rq->donor;
@@ -2362,7 +2334,7 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
 }
 
 static void
-__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);
+do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);
 
 static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
 {
@@ -2377,10 +2349,8 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
 	if (p->cpus_ptr != &p->cpus_mask)
 		return;
 
-	/*
-	 * Violates locking rules! See comment in __do_set_cpus_allowed().
-	 */
-	__do_set_cpus_allowed(p, &ac);
+	scoped_guard (task_rq_lock, p)
+		do_set_cpus_allowed(p, &ac);
 }
 
 void ___migrate_enable(void)
@@ -2613,7 +2583,8 @@ static int migration_cpu_stop(void *data)
 		 */
 		WARN_ON_ONCE(!pending->stop_pending);
 		preempt_disable();
-		task_rq_unlock(rq, p, &rf);
+		rq_unlock(rq, &rf);
+		raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
 		stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
 				    &pending->arg, &pending->stop_work);
 		preempt_enable();
@@ -2622,7 +2593,8 @@ static int migration_cpu_stop(void *data)
 out:
 	if (pending)
 		pending->stop_pending = false;
-	task_rq_unlock(rq, p, &rf);
+	rq_unlock(rq, &rf);
+	raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
 
 	if (complete)
 		complete_all(&pending->done);
@@ -2693,56 +2665,19 @@ 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)
+do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
 {
-	struct rq *rq = task_rq(p);
-	bool queued, running;
-
-	/*
-	 * This here violates the locking rules for affinity, since we're only
-	 * supposed to change these variables while holding both rq->lock and
-	 * p->pi_lock.
-	 *
-	 * HOWEVER, it magically works, because ttwu() is the only code that
-	 * accesses these variables under p->pi_lock and only does so after
-	 * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
-	 * before finish_task().
-	 *
-	 * XXX do further audits, this smells like something putrid.
-	 */
-	if (ctx->flags & SCA_MIGRATE_DISABLE)
-		WARN_ON_ONCE(!p->on_cpu);
-	else
-		lockdep_assert_held(&p->pi_lock);
-
-	queued = task_on_rq_queued(p);
-	running = task_current_donor(rq, p);
-
-	if (queued) {
-		/*
-		 * Because __kthread_bind() calls this on blocked tasks without
-		 * holding rq->lock.
-		 */
-		lockdep_assert_rq_held(rq);
-		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
+	scoped_guard (sched_change, p, DEQUEUE_SAVE) {
+		p->sched_class->set_cpus_allowed(p, ctx);
+		mm_set_cpus_allowed(p->mm, ctx->new_mask);
 	}
-	if (running)
-		put_prev_task(rq, p);
-
-	p->sched_class->set_cpus_allowed(p, ctx);
-	mm_set_cpus_allowed(p->mm, ctx->new_mask);
-
-	if (queued)
-		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
-	if (running)
-		set_next_task(rq, p);
 }
 
 /*
  * Used for kthread_bind() and select_fallback_rq(), in both cases the user
  * affinity (if any) should be destroyed too.
  */
-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+void set_cpus_allowed_force(struct task_struct *p, const struct cpumask *new_mask)
 {
 	struct affinity_context ac = {
 		.new_mask  = new_mask,
@@ -2754,7 +2689,8 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 		struct rcu_head rcu;
 	};
 
-	__do_set_cpus_allowed(p, &ac);
+	scoped_guard (__task_rq_lock, p)
+		do_set_cpus_allowed(p, &ac);
 
 	/*
 	 * Because this is called with p->pi_lock held, it is not possible
@@ -2792,7 +2728,7 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
 	 * Use pi_lock to protect content of user_cpus_ptr
 	 *
 	 * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
-	 * do_set_cpus_allowed().
+	 * set_cpus_allowed_force().
 	 */
 	raw_spin_lock_irqsave(&src->pi_lock, flags);
 	if (src->user_cpus_ptr) {
@@ -3064,8 +3000,6 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
 	unsigned int dest_cpu;
 	int ret = 0;
 
-	update_rq_clock(rq);
-
 	if (kthread || is_migration_disabled(p)) {
 		/*
 		 * Kernel threads are allowed on online && !active CPUs,
@@ -3120,7 +3054,7 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
 		goto out;
 	}
 
-	__do_set_cpus_allowed(p, ctx);
+	do_set_cpus_allowed(p, ctx);
 
 	return affine_move_task(rq, p, rf, dest_cpu, ctx->flags);
 
@@ -3529,13 +3463,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 			}
 			fallthrough;
 		case possible:
-			/*
-			 * XXX When called from select_task_rq() we only
-			 * hold p->pi_lock and again violate locking order.
-			 *
-			 * More yuck to audit.
-			 */
-			do_set_cpus_allowed(p, task_cpu_fallback_mask(p));
+			set_cpus_allowed_force(p, task_cpu_fallback_mask(p));
 			state = fail;
 			break;
 		case fail:
@@ -3777,7 +3705,7 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
 		ttwu_do_wakeup(p);
 		ret = 1;
 	}
-	__task_rq_unlock(rq, &rf);
+	__task_rq_unlock(rq, p, &rf);
 
 	return ret;
 }
@@ -4231,7 +4159,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 * __schedule().  See the comment for smp_mb__after_spinlock().
 		 *
 		 * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
-		 * schedule()'s deactivate_task() has 'happened' and p will no longer
+		 * schedule()'s block_task() has 'happened' and p will no longer
 		 * care about it's own p->state. See the comment in __schedule().
 		 */
 		smp_acquire__after_ctrl_dep();
@@ -4370,7 +4298,7 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg)
 	ret = func(p, arg);
 
 	if (rq)
-		rq_unlock(rq, &rf);
+		__task_rq_unlock(rq, p, &rf);
 
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
 	return ret;
@@ -5692,7 +5620,7 @@ static void sched_tick_remote(struct work_struct *work)
 				 * reasonable amount of time.
 				 */
 				u64 delta = rq_clock_task(rq) - curr->se.exec_start;
-				WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+				WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 30);
 			}
 			curr->sched_class->task_tick(rq, curr, 0);
 
@@ -5916,19 +5844,6 @@ static void prev_balance(struct rq *rq, struct task_struct *prev,
 	const struct sched_class *start_class = prev->sched_class;
 	const struct sched_class *class;
 
-#ifdef CONFIG_SCHED_CLASS_EXT
-	/*
-	 * SCX requires a balance() call before every pick_task() including when
-	 * waking up from SCHED_IDLE. If @start_class is below SCX, start from
-	 * SCX instead. Also, set a flag to detect missing balance() call.
-	 */
-	if (scx_enabled()) {
-		rq->scx.flags |= SCX_RQ_BAL_PENDING;
-		if (sched_class_above(&ext_sched_class, start_class))
-			start_class = &ext_sched_class;
-	}
-#endif
-
 	/*
 	 * We must do the balancing pass before put_prev_task(), such
 	 * that when we release the rq->lock the task is in the same
@@ -5972,7 +5887,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		/* Assume the next prioritized class is idle_sched_class */
 		if (!p) {
-			p = pick_task_idle(rq);
+			p = pick_task_idle(rq, rf);
 			put_prev_set_next_task(rq, prev, p);
 		}
 
@@ -5984,11 +5899,15 @@ restart:
 
 	for_each_active_class(class) {
 		if (class->pick_next_task) {
-			p = class->pick_next_task(rq, prev);
+			p = class->pick_next_task(rq, prev, rf);
+			if (unlikely(p == RETRY_TASK))
+				goto restart;
 			if (p)
 				return p;
 		} else {
-			p = class->pick_task(rq);
+			p = class->pick_task(rq, rf);
+			if (unlikely(p == RETRY_TASK))
+				goto restart;
 			if (p) {
 				put_prev_set_next_task(rq, prev, p);
 				return p;
@@ -6018,7 +5937,11 @@ static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
 	return a->core_cookie == b->core_cookie;
 }
 
-static inline struct task_struct *pick_task(struct rq *rq)
+/*
+ * Careful; this can return RETRY_TASK, it does not include the retry-loop
+ * itself due to the whole SMT pick retry thing below.
+ */
+static inline struct task_struct *pick_task(struct rq *rq, struct rq_flags *rf)
 {
 	const struct sched_class *class;
 	struct task_struct *p;
@@ -6026,7 +5949,7 @@ static inline struct task_struct *pick_task(struct rq *rq)
 	rq->dl_server = NULL;
 
 	for_each_active_class(class) {
-		p = class->pick_task(rq);
+		p = class->pick_task(rq, rf);
 		if (p)
 			return p;
 	}
@@ -6041,7 +5964,7 @@ static void queue_core_balance(struct rq *rq);
 static struct task_struct *
 pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	struct task_struct *next, *p, *max = NULL;
+	struct task_struct *next, *p, *max;
 	const struct cpumask *smt_mask;
 	bool fi_before = false;
 	bool core_clock_updated = (rq == rq->core);
@@ -6126,7 +6049,10 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * and there are no cookied tasks running on siblings.
 	 */
 	if (!need_sync) {
-		next = pick_task(rq);
+restart_single:
+		next = pick_task(rq, rf);
+		if (unlikely(next == RETRY_TASK))
+			goto restart_single;
 		if (!next->core_cookie) {
 			rq->core_pick = NULL;
 			rq->core_dl_server = NULL;
@@ -6146,6 +6072,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 *
 	 * Tie-break prio towards the current CPU
 	 */
+restart_multi:
+	max = NULL;
 	for_each_cpu_wrap(i, smt_mask, cpu) {
 		rq_i = cpu_rq(i);
 
@@ -6157,7 +6085,11 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		if (i != cpu && (rq_i != rq->core || !core_clock_updated))
 			update_rq_clock(rq_i);
 
-		rq_i->core_pick = p = pick_task(rq_i);
+		p = pick_task(rq_i, rf);
+		if (unlikely(p == RETRY_TASK))
+			goto restart_multi;
+
+		rq_i->core_pick = p;
 		rq_i->core_dl_server = rq_i->dl_server;
 
 		if (!max || prio_less(max, p, fi_before))
@@ -6179,7 +6111,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 			if (cookie)
 				p = sched_core_find(rq_i, cookie);
 			if (!p)
-				p = idle_sched_class.pick_task(rq_i);
+				p = idle_sched_class.pick_task(rq_i, rf);
 		}
 
 		rq_i->core_pick = p;
@@ -6812,6 +6744,7 @@ static void __sched notrace __schedule(int sched_mode)
 
 	local_irq_disable();
 	rcu_note_context_switch(preempt);
+	migrate_disable_switch(rq, prev);
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
@@ -6918,7 +6851,6 @@ keep_resched:
 		 */
 		++*switch_count;
 
-		migrate_disable_switch(rq, prev);
 		psi_account_irqtime(rq, prev, next);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev) ||
 					     prev->se.sched_delayed);
@@ -7326,7 +7258,7 @@ void rt_mutex_post_schedule(void)
  */
 void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 {
-	int prio, oldprio, queued, running, queue_flag =
+	int prio, oldprio, queue_flag =
 		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	const struct sched_class *prev_class, *next_class;
 	struct rq_flags rf;
@@ -7388,64 +7320,51 @@ 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 && p->se.sched_delayed)
-		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
-
-	queued = task_on_rq_queued(p);
-	running = task_current_donor(rq, p);
-	if (queued)
-		dequeue_task(rq, p, queue_flag);
-	if (running)
-		put_prev_task(rq, p);
+	if (prev_class != next_class)
+		queue_flag |= DEQUEUE_CLASS;
 
-	/*
-	 * Boosting condition are:
-	 * 1. -rt task is running and holds mutex A
-	 *      --> -dl task blocks on mutex A
-	 *
-	 * 2. -dl task is running and holds mutex A
-	 *      --> -dl task blocks on mutex A and could preempt the
-	 *          running task
-	 */
-	if (dl_prio(prio)) {
-		if (!dl_prio(p->normal_prio) ||
-		    (pi_task && dl_prio(pi_task->prio) &&
-		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
-			p->dl.pi_se = pi_task->dl.pi_se;
-			queue_flag |= ENQUEUE_REPLENISH;
+	scoped_guard (sched_change, p, queue_flag) {
+		/*
+		 * Boosting condition are:
+		 * 1. -rt task is running and holds mutex A
+		 *      --> -dl task blocks on mutex A
+		 *
+		 * 2. -dl task is running and holds mutex A
+		 *      --> -dl task blocks on mutex A and could preempt the
+		 *          running task
+		 */
+		if (dl_prio(prio)) {
+			if (!dl_prio(p->normal_prio) ||
+			    (pi_task && dl_prio(pi_task->prio) &&
+			     dl_entity_preempt(&pi_task->dl, &p->dl))) {
+				p->dl.pi_se = pi_task->dl.pi_se;
+				scope->flags |= ENQUEUE_REPLENISH;
+			} else {
+				p->dl.pi_se = &p->dl;
+			}
+		} else if (rt_prio(prio)) {
+			if (dl_prio(oldprio))
+				p->dl.pi_se = &p->dl;
+			if (oldprio < prio)
+				scope->flags |= ENQUEUE_HEAD;
 		} else {
-			p->dl.pi_se = &p->dl;
+			if (dl_prio(oldprio))
+				p->dl.pi_se = &p->dl;
+			if (rt_prio(oldprio))
+				p->rt.timeout = 0;
 		}
-	} else if (rt_prio(prio)) {
-		if (dl_prio(oldprio))
-			p->dl.pi_se = &p->dl;
-		if (oldprio < prio)
-			queue_flag |= ENQUEUE_HEAD;
-	} else {
-		if (dl_prio(oldprio))
-			p->dl.pi_se = &p->dl;
-		if (rt_prio(oldprio))
-			p->rt.timeout = 0;
-	}
 
-	p->sched_class = next_class;
-	p->prio = prio;
-
-	check_class_changing(rq, p, prev_class);
-
-	if (queued)
-		enqueue_task(rq, p, queue_flag);
-	if (running)
-		set_next_task(rq, p);
-
-	check_class_changed(rq, p, prev_class, oldprio);
+		p->sched_class = next_class;
+		p->prio = prio;
+	}
 out_unlock:
 	/* Avoid rq from going away on us: */
 	preempt_disable();
 
 	rq_unpin_lock(rq, &rf);
 	__balance_callbacks(rq);
-	raw_spin_rq_unlock(rq);
+	rq_repin_lock(rq, &rf);
+	__task_rq_unlock(rq, p, &rf);
 
 	preempt_enable();
 }
@@ -8084,26 +8003,9 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
  */
 void sched_setnuma(struct task_struct *p, int nid)
 {
-	bool queued, running;
-	struct rq_flags rf;
-	struct rq *rq;
-
-	rq = task_rq_lock(p, &rf);
-	queued = task_on_rq_queued(p);
-	running = task_current_donor(rq, p);
-
-	if (queued)
-		dequeue_task(rq, p, DEQUEUE_SAVE);
-	if (running)
-		put_prev_task(rq, p);
-
-	p->numa_preferred_nid = nid;
-
-	if (queued)
-		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
-	if (running)
-		set_next_task(rq, p);
-	task_rq_unlock(rq, p, &rf);
+	guard(task_rq_lock)(p);
+	scoped_guard (sched_change, p, DEQUEUE_SAVE)
+		p->numa_preferred_nid = nid;
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
@@ -8141,18 +8043,15 @@ static int __balance_push_cpu_stop(void *arg)
 	struct rq_flags rf;
 	int cpu;
 
-	raw_spin_lock_irq(&p->pi_lock);
-	rq_lock(rq, &rf);
-
-	update_rq_clock(rq);
-
-	if (task_rq(p) == rq && task_on_rq_queued(p)) {
+	scoped_guard (raw_spinlock_irq, &p->pi_lock) {
 		cpu = select_fallback_rq(rq->cpu, p);
-		rq = __migrate_task(rq, &rf, p, cpu);
-	}
 
-	rq_unlock(rq, &rf);
-	raw_spin_unlock_irq(&p->pi_lock);
+		rq_lock(rq, &rf);
+		update_rq_clock(rq);
+		if (task_rq(p) == rq && task_on_rq_queued(p))
+			rq = __migrate_task(rq, &rf, p, cpu);
+		rq_unlock(rq, &rf);
+	}
 
 	put_task_struct(p);
 
@@ -8591,6 +8490,8 @@ void __init sched_init_smp(void)
 {
 	sched_init_numa(NUMA_NO_NODE);
 
+	prandom_init_once(&sched_rnd_state);
+
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
 	 * CPU masks are stable and all blatant races in the below code cannot
@@ -9207,38 +9108,23 @@ static void sched_change_group(struct task_struct *tsk)
  */
 void sched_move_task(struct task_struct *tsk, bool for_autogroup)
 {
-	int queued, running, queue_flags =
-		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
+	unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
+	bool resched = false;
 	struct rq *rq;
 
 	CLASS(task_rq_lock, rq_guard)(tsk);
 	rq = rq_guard.rq;
 
-	update_rq_clock(rq);
-
-	running = task_current_donor(rq, tsk);
-	queued = task_on_rq_queued(tsk);
-
-	if (queued)
-		dequeue_task(rq, tsk, queue_flags);
-	if (running)
-		put_prev_task(rq, tsk);
-
-	sched_change_group(tsk);
-	if (!for_autogroup)
-		scx_cgroup_move_task(tsk);
+	scoped_guard (sched_change, tsk, queue_flags) {
+		sched_change_group(tsk);
+		if (!for_autogroup)
+			scx_cgroup_move_task(tsk);
+		if (scope->running)
+			resched = true;
+	}
 
-	if (queued)
-		enqueue_task(rq, tsk, queue_flags);
-	if (running) {
-		set_next_task(rq, tsk);
-		/*
-		 * After changing group, the running task may have joined a
-		 * throttled one but it's still the running task. Trigger a
-		 * resched to make sure that task can still run.
-		 */
+	if (resched)
 		resched_curr(rq);
-	}
 }
 
 static struct cgroup_subsys_state *
@@ -10894,37 +10780,75 @@ void sched_mm_cid_fork(struct task_struct *t)
 }
 #endif /* CONFIG_SCHED_MM_CID */
 
-#ifdef CONFIG_SCHED_CLASS_EXT
-void sched_deq_and_put_task(struct task_struct *p, int queue_flags,
-			    struct sched_enq_and_set_ctx *ctx)
+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 *ctx = this_cpu_ptr(&sched_change_ctx);
 	struct rq *rq = task_rq(p);
 
+	/*
+	 * Must exclusively use matched flags since this is both dequeue and
+	 * enqueue.
+	 */
+	WARN_ON_ONCE(flags & 0xFFFF0000);
+
 	lockdep_assert_rq_held(rq);
 
-	*ctx = (struct sched_enq_and_set_ctx){
+	if (!(flags & DEQUEUE_NOCLOCK)) {
+		update_rq_clock(rq);
+		flags |= DEQUEUE_NOCLOCK;
+	}
+
+	if (flags & DEQUEUE_CLASS) {
+		if (p->sched_class->switching_from)
+			p->sched_class->switching_from(rq, p);
+	}
+
+	*ctx = (struct sched_change_ctx){
 		.p = p,
-		.queue_flags = queue_flags,
+		.flags = flags,
 		.queued = task_on_rq_queued(p),
-		.running = task_current(rq, p),
+		.running = task_current_donor(rq, p),
 	};
 
-	update_rq_clock(rq);
+	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, queue_flags | DEQUEUE_NOCLOCK);
+		dequeue_task(rq, p, flags);
 	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;
 }
 
-void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx)
+void sched_change_end(struct sched_change_ctx *ctx)
 {
-	struct rq *rq = task_rq(ctx->p);
+	struct task_struct *p = ctx->p;
+	struct rq *rq = task_rq(p);
 
 	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, ctx->p, ctx->queue_flags | ENQUEUE_NOCLOCK);
+		enqueue_task(rq, p, ctx->flags);
 	if (ctx->running)
-		set_next_task(rq, ctx->p);
+		set_next_task(rq, p);
+
+	if (ctx->flags & ENQUEUE_CLASS) {
+		if (p->sched_class->switched_to)
+			p->sched_class->switched_to(rq, p);
+	} else {
+		p->sched_class->prio_changed(rq, p, ctx->prio);
+	}
 }
-#endif /* CONFIG_SCHED_CLASS_EXT */