sched: Random collection of patches

index da46c31..aa033e4 100644
@@ -3693,7 +3693,7 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
  */
 #define add_positive(_ptr, _val) do {                           \
 	typeof(_ptr) ptr = (_ptr);                              \
-	typeof(_val) val = (_val);                              \
+	__signed_scalar_typeof(*ptr) val = (_val);              \
 	typeof(*ptr) res, var = READ_ONCE(*ptr);                \
 								\
 	res = var + val;                                        \

@@ -3705,23 +3705,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 } while (0)
 
 /*
- * Unsigned subtract and clamp on underflow.
- *
- * Explicitly do a load-store to ensure the intermediate value never hits
- * memory. This allows lockless observations without ever seeing the negative
- * values.
- */
-#define sub_positive(_ptr, _val) do {				\
-	typeof(_ptr) ptr = (_ptr);				\
-	typeof(*ptr) val = (_val);				\
-	typeof(*ptr) res, var = READ_ONCE(*ptr);		\
-	res = var - val;					\
-	if (res > var)						\
-		res = 0;					\
-	WRITE_ONCE(*ptr, res);					\
-} while (0)
-
-/*
  * Remove and clamp on negative, from a local variable.
  *
  * A variant of sub_positive(), which does not use explicit load-store

@@ -3732,21 +3715,37 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	*ptr -= min_t(typeof(*ptr), *ptr, _val);		\
 } while (0)
 
+
+/*
+ * Because of rounding, se->util_sum might ends up being +1 more than
+ * cfs->util_sum. Although this is not a problem by itself, detaching
+ * a lot of tasks with the rounding problem between 2 updates of
+ * util_avg (~1ms) can make cfs->util_sum becoming null whereas
+ * cfs_util_avg is not.
+ *
+ * Check that util_sum is still above its lower bound for the new
+ * util_avg. Given that period_contrib might have moved since the last
+ * sync, we are only sure that util_sum must be above or equal to
+ *    util_avg * minimum possible divider
+ */
+#define __update_sa(sa, name, delta_avg, delta_sum) do {	\
+	add_positive(&(sa)->name##_avg, delta_avg);		\
+	add_positive(&(sa)->name##_sum, delta_sum);		\
+	(sa)->name##_sum = max_t(typeof((sa)->name##_sum),	\
+			       (sa)->name##_sum,		\
+			       (sa)->name##_avg * PELT_MIN_DIVIDER); \
+} while (0)
+
 static inline void
 enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	cfs_rq->avg.load_avg += se->avg.load_avg;
-	cfs_rq->avg.load_sum += se_weight(se) * se->avg.load_sum;
+	__update_sa(&cfs_rq->avg, load, se->avg.load_avg, se->avg.load_sum);
 }
 
 static inline void
 dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
-	sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum);
-	/* See update_cfs_rq_load_avg() */
-	cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum,
-					  cfs_rq->avg.load_avg * PELT_MIN_DIVIDER);
+	__update_sa(&cfs_rq->avg, load, -se->avg.load_avg, -se->avg.load_sum);
 }
 
 static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags);

@@ -4242,7 +4241,6 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
 	 */
 	divider = get_pelt_divider(&cfs_rq->avg);
 
-
 	/* Set new sched_entity's utilization */
 	se->avg.util_avg = gcfs_rq->avg.util_avg;
 	new_sum = se->avg.util_avg * divider;

@@ -4250,12 +4248,7 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
 	se->avg.util_sum = new_sum;
 
 	/* Update parent cfs_rq utilization */
-	add_positive(&cfs_rq->avg.util_avg, delta_avg);
-	add_positive(&cfs_rq->avg.util_sum, delta_sum);
-
-	/* See update_cfs_rq_load_avg() */
-	cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum,
-					  cfs_rq->avg.util_avg * PELT_MIN_DIVIDER);
+	__update_sa(&cfs_rq->avg, util, delta_avg, delta_sum);
 }
 
 static inline void

@@ -4281,11 +4274,7 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf
 	se->avg.runnable_sum = new_sum;
 
 	/* Update parent cfs_rq runnable */
-	add_positive(&cfs_rq->avg.runnable_avg, delta_avg);
-	add_positive(&cfs_rq->avg.runnable_sum, delta_sum);
-	/* See update_cfs_rq_load_avg() */
-	cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum,
-					      cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER);
+	__update_sa(&cfs_rq->avg, runnable, delta_avg, delta_sum);
 }
 
 static inline void

@@ -4349,11 +4338,7 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
 
 	se->avg.load_sum = runnable_sum;
 	se->avg.load_avg = load_avg;
-	add_positive(&cfs_rq->avg.load_avg, delta_avg);
-	add_positive(&cfs_rq->avg.load_sum, delta_sum);
-	/* See update_cfs_rq_load_avg() */
-	cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum,
-					  cfs_rq->avg.load_avg * PELT_MIN_DIVIDER);
+	__update_sa(&cfs_rq->avg, load, delta_avg, delta_sum);
 }
 
 static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum)

@@ -4552,33 +4537,13 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 		raw_spin_unlock(&cfs_rq->removed.lock);
 
 		r = removed_load;
-		sub_positive(&sa->load_avg, r);
-		sub_positive(&sa->load_sum, r * divider);
-		/* See sa->util_sum below */
-		sa->load_sum = max_t(u32, sa->load_sum, sa->load_avg * PELT_MIN_DIVIDER);
+		__update_sa(sa, load, -r, -r*divider);
 
 		r = removed_util;
-		sub_positive(&sa->util_avg, r);
-		sub_positive(&sa->util_sum, r * divider);
-		/*
-		 * Because of rounding, se->util_sum might ends up being +1 more than
-		 * cfs->util_sum. Although this is not a problem by itself, detaching
-		 * a lot of tasks with the rounding problem between 2 updates of
-		 * util_avg (~1ms) can make cfs->util_sum becoming null whereas
-		 * cfs_util_avg is not.
-		 * Check that util_sum is still above its lower bound for the new
-		 * util_avg. Given that period_contrib might have moved since the last
-		 * sync, we are only sure that util_sum must be above or equal to
-		 *    util_avg * minimum possible divider
-		 */
-		sa->util_sum = max_t(u32, sa->util_sum, sa->util_avg * PELT_MIN_DIVIDER);
+		__update_sa(sa, util, -r, -r*divider);
 
 		r = removed_runnable;
-		sub_positive(&sa->runnable_avg, r);
-		sub_positive(&sa->runnable_sum, r * divider);
-		/* See sa->util_sum above */
-		sa->runnable_sum = max_t(u32, sa->runnable_sum,
-					      sa->runnable_avg * PELT_MIN_DIVIDER);
+		__update_sa(sa, runnable, -r, -r*divider);
 
 		/*
 		 * removed_runnable is the unweighted version of removed_load so we

@@ -4663,17 +4628,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	dequeue_load_avg(cfs_rq, se);
-	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
-	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
-	/* See update_cfs_rq_load_avg() */
-	cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum,
-					  cfs_rq->avg.util_avg * PELT_MIN_DIVIDER);
-
-	sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg);
-	sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum);
-	/* See update_cfs_rq_load_avg() */
-	cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum,
-					      cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER);
+	__update_sa(&cfs_rq->avg, util, -se->avg.util_avg, -se->avg.util_sum);
+	__update_sa(&cfs_rq->avg, runnable, -se->avg.runnable_avg, -se->avg.runnable_sum);
 
 	add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);
 

index 1280693..280b4ac 100644
@@ -586,6 +586,25 @@ struct ftrace_likely_data {
 			 __scalar_type_to_expr_cases(long long),	\
 			 default: (x)))
 
+/*
+ * __signed_scalar_typeof(x) - Declare a signed scalar type, leaving
+ *			       non-scalar types unchanged.
+ */
+
+#define __scalar_type_to_signed_cases(type)				\
+		unsigned type:	(signed type)0,				\
+		signed type:	(signed type)0
+
+#define __signed_scalar_typeof(x) typeof(				\
+		_Generic((x),						\
+			 char:	(signed char)0,				\
+			 __scalar_type_to_signed_cases(char),		\
+			 __scalar_type_to_signed_cases(short),		\
+			 __scalar_type_to_signed_cases(int),		\
+			 __scalar_type_to_signed_cases(long),		\
+			 __scalar_type_to_signed_cases(long long),	\
+			 default: (x)))
+
 /* Is this type a native word size -- useful for atomic operations */
 #define __native_word(t) \
 	(sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \

index aa033e4..708ad01 100644
@@ -9905,15 +9905,11 @@ static unsigned long task_h_load(struct task_struct *p)
 }
 #endif /* !CONFIG_FAIR_GROUP_SCHED */
 
-static void sched_balance_update_blocked_averages(int cpu)
+static void __sched_balance_update_blocked_averages(struct rq *rq)
 {
 	bool decayed = false, done = true;
-	struct rq *rq = cpu_rq(cpu);
-	struct rq_flags rf;
 
-	rq_lock_irqsave(rq, &rf);
 	update_blocked_load_tick(rq);
-	update_rq_clock(rq);
 
 	decayed |= __update_blocked_others(rq, &done);
 	decayed |= __update_blocked_fair(rq, &done);

@@ -9921,7 +9917,15 @@ static void sched_balance_update_blocked_averages(int cpu)
 	update_blocked_load_status(rq, !done);
 	if (decayed)
 		cpufreq_update_util(rq, 0);
-	rq_unlock_irqrestore(rq, &rf);
+}
+
+static void sched_balance_update_blocked_averages(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+	guard(rq_lock_irqsave)(rq);
+	update_rq_clock(rq);
+	__sched_balance_update_blocked_averages(rq);
 }
 
 /********** Helpers for sched_balance_find_src_group ************************/

@@ -12868,12 +12872,17 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 	}
 	rcu_read_unlock();
 
+	/*
+	 * Include sched_balance_update_blocked_averages() in the cost
+	 * calculation because it can be quite costly -- this ensures we skip
+	 * it when avg_idle gets to be very low.
+	 */
+	t0 = sched_clock_cpu(this_cpu);
+	__sched_balance_update_blocked_averages(this_rq);
+
 	rq_modified_clear(this_rq);
 	raw_spin_rq_unlock(this_rq);
 
-	t0 = sched_clock_cpu(this_cpu);
-	sched_balance_update_blocked_averages(this_cpu);
-
 	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
 		u64 domain_cost;

index 44a359d..496a30a 100644
@@ -12856,21 +12856,16 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 	 */
 	rq_unpin_lock(this_rq, rf);
 
-	rcu_read_lock();
 	sd = rcu_dereference_sched_domain(this_rq->sd);
-	if (!sd) {
-		rcu_read_unlock();
+	if (!sd)
 		goto out;
-	}
 
 	if (!get_rd_overloaded(this_rq->rd) ||
 	    this_rq->avg_idle < sd->max_newidle_lb_cost) {
 
 		update_next_balance(sd, &next_balance);
-		rcu_read_unlock();
 		goto out;
 	}
-	rcu_read_unlock();
 
 	/*
 	 * Include sched_balance_update_blocked_averages() in the cost

@@ -12883,7 +12878,6 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 	rq_modified_clear(this_rq);
 	raw_spin_rq_unlock(this_rq);
 
-	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
 		u64 domain_cost;
 

@@ -12933,7 +12927,6 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 		if (pulled_task || !continue_balancing)
 			break;
 	}
-	rcu_read_unlock();
 
 	raw_spin_rq_lock(this_rq);
 

index 41ba0be..4479f7d 100644
@@ -10782,6 +10782,7 @@ struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int 
 
 	*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),

@@ -10812,6 +10813,11 @@ 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);
 

@@ -10823,6 +10829,13 @@ 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 this was a degradation in class someone should have set
+		 * need_resched by now.
+		 */
+		WARN_ON_ONCE(sched_class_above(ctx->class, p->sched_class) &&
+			     !test_tsk_need_resched(p));
 	} else {
 		p->sched_class->prio_changed(rq, p, ctx->prio);
 	}

index 67cff7d..a40582d 100644
@@ -3968,6 +3968,7 @@ extern void balance_callbacks(struct rq *rq, struct balance_callback *head);
 struct sched_change_ctx {
 	u64			prio;
 	struct task_struct	*p;
+	const struct sched_class *class;
 	int			flags;
 	bool			queued;
 	bool			running;

index 4479f7d..7d0a862 100644
@@ -2090,7 +2090,6 @@ 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);

@@ -2123,7 +2122,6 @@ 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);
 }
 

@@ -2174,10 +2172,14 @@ 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

@@ -6804,6 +6806,7 @@ 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)

@@ -8650,6 +8653,8 @@ 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;

@@ -10775,10 +10780,8 @@ 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,

@@ -10831,6 +10834,17 @@ void sched_change_end(struct sched_change_ctx *ctx)
 			p->sched_class->switched_to(rq, p);
 
 		/*
+		 * 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 (ctx->running && 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 someone should have set
 		 * need_resched by now.
 		 */

index 319439f..80c9559 100644
@@ -2499,9 +2499,16 @@ static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
  * Only called when both the current and waking task are -deadline
  * tasks.
  */
-static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p,
-				  int flags)
+static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags)
 {
+	/*
+	 * Can only get preempted by stop-class, and those should be
+	 * few and short lived, doesn't really make sense to push
+	 * anything away for that.
+	 */
+	if (p->sched_class != &dl_sched_class)
+		return;
+
 	if (dl_entity_preempt(&p->dl, &rq->donor->dl)) {
 		resched_curr(rq);
 		return;

@@ -3346,9 +3353,6 @@ static int task_is_throttled_dl(struct task_struct *p, int cpu)
 #endif
 
 DEFINE_SCHED_CLASS(dl) = {
-
-	.queue_mask		= 8,
-
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,

index 05f5a49..8015ab6 100644
@@ -3075,7 +3075,8 @@ static void switched_from_scx(struct rq *rq, struct task_struct *p)
 	scx_disable_task(p);
 }
 
-static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {}
+static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p, int wake_flags) {}
+
 static void switched_to_scx(struct rq *rq, struct task_struct *p) {}
 
 int scx_check_setscheduler(struct task_struct *p, int policy)

@@ -3336,8 +3337,6 @@ static void scx_cgroup_unlock(void) {}
  *   their current sched_class. Call them directly from sched core instead.
  */
 DEFINE_SCHED_CLASS(ext) = {
-	.queue_mask		= 1,
-
 	.enqueue_task		= enqueue_task_scx,
 	.dequeue_task		= dequeue_task_scx,
 	.yield_task		= yield_task_scx,

index f79951f..ea276d8 100644
@@ -8700,7 +8700,7 @@ preempt_sync(struct rq *rq, int wake_flags,
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int wake_flags)
+static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_flags)
 {
 	enum preempt_wakeup_action preempt_action = PREEMPT_WAKEUP_PICK;
 	struct task_struct *donor = rq->donor;

@@ -8708,6 +8708,12 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int 
 	struct cfs_rq *cfs_rq = task_cfs_rq(donor);
 	int cse_is_idle, pse_is_idle;
 
+	/*
+	 * XXX Getting preempted by higher class, try and find idle CPU?
+	 */
+	if (p->sched_class != &fair_sched_class)
+		return;
+
 	if (unlikely(se == pse))
 		return;
 

@@ -12875,7 +12881,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 	t0 = sched_clock_cpu(this_cpu);
 	__sched_balance_update_blocked_averages(this_rq);
 
-	rq_modified_clear(this_rq);
+	this_rq->next_class = &fair_sched_class;
 	raw_spin_rq_unlock(this_rq);
 
 	for_each_domain(this_cpu, sd) {

@@ -12942,7 +12948,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 		pulled_task = 1;
 
 	/* If a higher prio class was modified, restart the pick */
-	if (rq_modified_above(this_rq, &fair_sched_class))
+	if (sched_class_above(this_rq->next_class, &fair_sched_class))
 		pulled_task = -1;
 
 out:

@@ -13846,15 +13852,12 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
  * All the scheduling class methods:
  */
 DEFINE_SCHED_CLASS(fair) = {
-
-	.queue_mask		= 2,
-
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
 	.yield_to_task		= yield_to_task_fair,
 
-	.wakeup_preempt		= check_preempt_wakeup_fair,
+	.wakeup_preempt		= wakeup_preempt_fair,
 
 	.pick_task		= pick_task_fair,
 	.pick_next_task		= pick_next_task_fair,

index c174afe..65eb8f8 100644
@@ -536,9 +536,6 @@ static void update_curr_idle(struct rq *rq)
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
 DEFINE_SCHED_CLASS(idle) = {
-
-	.queue_mask		= 0,
-
 	/* no enqueue/yield_task for idle tasks */
 
 	/* dequeue is not valid, we print a debug message there: */

index f1867fe..0a9b2cd 100644
@@ -1615,6 +1615,12 @@ static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *donor = rq->donor;
 
+	/*
+	 * XXX If we're preempted by DL, queue a push?
+	 */
+	if (p->sched_class != &rt_sched_class)
+		return;
+
 	if (p->prio < donor->prio) {
 		resched_curr(rq);
 		return;

@@ -2568,9 +2574,6 @@ static int task_is_throttled_rt(struct task_struct *p, int cpu)
 #endif /* CONFIG_SCHED_CORE */
 
 DEFINE_SCHED_CLASS(rt) = {
-
-	.queue_mask		= 4,
-
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,

index a40582d..467ea31 100644
@@ -1121,7 +1121,6 @@ struct rq {
 	raw_spinlock_t		__lock;
 
 	/* Per class runqueue modification mask; bits in class order. */
-	unsigned int		queue_mask;
 	unsigned int		nr_running;
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int		nr_numa_running;

@@ -1181,6 +1180,7 @@ struct rq {
 	struct sched_dl_entity	*dl_server;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
+	const struct sched_class *next_class;
 	unsigned long		next_balance;
 	struct mm_struct	*prev_mm;
 

@@ -2428,15 +2428,6 @@ struct sched_class {
 #ifdef CONFIG_UCLAMP_TASK
 	int uclamp_enabled;
 #endif
-	/*
-	 * idle:  0
-	 * ext:   1
-	 * fair:  2
-	 * rt:    4
-	 * dl:    8
-	 * stop: 16
-	 */
-	unsigned int queue_mask;
 
 	/*
 	 * move_queued_task/activate_task/enqueue_task: rq->lock

@@ -2595,20 +2586,6 @@ struct sched_class {
 #endif
 };
 
-/*
- * Does not nest; only used around sched_class::pick_task() rq-lock-breaks.
- */
-static inline void rq_modified_clear(struct rq *rq)
-{
-	rq->queue_mask = 0;
-}
-
-static inline bool rq_modified_above(struct rq *rq, const struct sched_class * class)
-{
-	unsigned int mask = class->queue_mask;
-	return rq->queue_mask & ~((mask << 1) - 1);
-}
-
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	WARN_ON_ONCE(rq->donor != prev);

@@ -3901,6 +3878,7 @@ void move_queued_task_locked(struct rq *src_rq, struct rq *dst_rq, struct task_s
 	deactivate_task(src_rq, task, 0);
 	set_task_cpu(task, dst_rq->cpu);
 	activate_task(dst_rq, task, 0);
+	wakeup_preempt(dst_rq, task, 0);
 }
 
 static inline

index 4f9192b..f95798b 100644
@@ -97,9 +97,6 @@ static void update_curr_stop(struct rq *rq)
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
 DEFINE_SCHED_CLASS(stop) = {
-
-	.queue_mask		= 16,
-
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
 	.yield_task		= yield_task_stop,

index 4479f7d..7d0a862 100644
@@ -2090,7 +2090,6 @@ 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);

@@ -2123,7 +2122,6 @@ 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);
 }
 

@@ -2174,10 +2172,14 @@ 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

@@ -6804,6 +6806,7 @@ 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)

@@ -8650,6 +8653,8 @@ 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;

@@ -10775,10 +10780,8 @@ 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,

@@ -10831,6 +10834,17 @@ void sched_change_end(struct sched_change_ctx *ctx)
 			p->sched_class->switched_to(rq, p);
 
 		/*
+		 * 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 (ctx->running && 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 someone should have set
 		 * need_resched by now.
 		 */

index 319439f..80c9559 100644
@@ -2499,9 +2499,16 @@ static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
  * Only called when both the current and waking task are -deadline
  * tasks.
  */
-static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p,
-				  int flags)
+static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags)
 {
+	/*
+	 * Can only get preempted by stop-class, and those should be
+	 * few and short lived, doesn't really make sense to push
+	 * anything away for that.
+	 */
+	if (p->sched_class != &dl_sched_class)
+		return;
+
 	if (dl_entity_preempt(&p->dl, &rq->donor->dl)) {
 		resched_curr(rq);
 		return;

@@ -3346,9 +3353,6 @@ static int task_is_throttled_dl(struct task_struct *p, int cpu)
 #endif
 
 DEFINE_SCHED_CLASS(dl) = {
-
-	.queue_mask		= 8,
-
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,

index 05f5a49..3058777 100644
@@ -2431,7 +2431,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	/* see kick_cpus_irq_workfn() */
 	smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
 
-	rq_modified_clear(rq);
+	rq->next_class = &fair_sched_class;
 
 	rq_unpin_lock(rq, rf);
 	balance_one(rq, prev);

@@ -3075,7 +3075,8 @@ static void switched_from_scx(struct rq *rq, struct task_struct *p)
 	scx_disable_task(p);
 }
 
-static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {}
+static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p, int wake_flags) {}
+
 static void switched_to_scx(struct rq *rq, struct task_struct *p) {}
 
 int scx_check_setscheduler(struct task_struct *p, int policy)

@@ -3336,8 +3337,6 @@ static void scx_cgroup_unlock(void) {}
  *   their current sched_class. Call them directly from sched core instead.
  */
 DEFINE_SCHED_CLASS(ext) = {
-	.queue_mask		= 1,
-
 	.enqueue_task		= enqueue_task_scx,
 	.dequeue_task		= dequeue_task_scx,
 	.yield_task		= yield_task_scx,

index d588eb8..76f5e4b 100644
@@ -8736,7 +8736,7 @@ preempt_sync(struct rq *rq, int wake_flags,
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int wake_flags)
+static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_flags)
 {
 	enum preempt_wakeup_action preempt_action = PREEMPT_WAKEUP_PICK;
 	struct task_struct *donor = rq->donor;

@@ -8744,6 +8744,12 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int 
 	struct cfs_rq *cfs_rq = task_cfs_rq(donor);
 	int cse_is_idle, pse_is_idle;
 
+	/*
+	 * XXX Getting preempted by higher class, try and find idle CPU?
+	 */
+	if (p->sched_class != &fair_sched_class)
+		return;
+
 	if (unlikely(se == pse))
 		return;
 

@@ -12911,7 +12917,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 	t0 = sched_clock_cpu(this_cpu);
 	__sched_balance_update_blocked_averages(this_rq);
 
-	rq_modified_clear(this_rq);
+	this_rq->next_class = &fair_sched_class;
 	raw_spin_rq_unlock(this_rq);
 
 	for_each_domain(this_cpu, sd) {

@@ -12978,7 +12984,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 		pulled_task = 1;
 
 	/* If a higher prio class was modified, restart the pick */
-	if (rq_modified_above(this_rq, &fair_sched_class))
+	if (sched_class_above(this_rq->next_class, &fair_sched_class))
 		pulled_task = -1;
 
 out:

@@ -13882,15 +13888,12 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
  * All the scheduling class methods:
  */
 DEFINE_SCHED_CLASS(fair) = {
-
-	.queue_mask		= 2,
-
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
 	.yield_to_task		= yield_to_task_fair,
 
-	.wakeup_preempt		= check_preempt_wakeup_fair,
+	.wakeup_preempt		= wakeup_preempt_fair,
 
 	.pick_task		= pick_task_fair,
 	.pick_next_task		= pick_next_task_fair,

index c174afe..65eb8f8 100644
@@ -536,9 +536,6 @@ static void update_curr_idle(struct rq *rq)
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
 DEFINE_SCHED_CLASS(idle) = {
-
-	.queue_mask		= 0,
-
 	/* no enqueue/yield_task for idle tasks */
 
 	/* dequeue is not valid, we print a debug message there: */

index f1867fe..0a9b2cd 100644
@@ -1615,6 +1615,12 @@ static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *donor = rq->donor;
 
+	/*
+	 * XXX If we're preempted by DL, queue a push?
+	 */
+	if (p->sched_class != &rt_sched_class)
+		return;
+
 	if (p->prio < donor->prio) {
 		resched_curr(rq);
 		return;

@@ -2568,9 +2574,6 @@ static int task_is_throttled_rt(struct task_struct *p, int cpu)
 #endif /* CONFIG_SCHED_CORE */
 
 DEFINE_SCHED_CLASS(rt) = {
-
-	.queue_mask		= 4,
-
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,

index ab1bfa0..bdb1e74 100644
@@ -1119,7 +1119,6 @@ struct rq {
 	raw_spinlock_t		__lock;
 
 	/* Per class runqueue modification mask; bits in class order. */
-	unsigned int		queue_mask;
 	unsigned int		nr_running;
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int		nr_numa_running;

@@ -1179,6 +1178,7 @@ struct rq {
 	struct sched_dl_entity	*dl_server;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
+	const struct sched_class *next_class;
 	unsigned long		next_balance;
 	struct mm_struct	*prev_mm;
 

@@ -2426,15 +2426,6 @@ struct sched_class {
 #ifdef CONFIG_UCLAMP_TASK
 	int uclamp_enabled;
 #endif
-	/*
-	 * idle:  0
-	 * ext:   1
-	 * fair:  2
-	 * rt:    4
-	 * dl:    8
-	 * stop: 16
-	 */
-	unsigned int queue_mask;
 
 	/*
 	 * move_queued_task/activate_task/enqueue_task: rq->lock

@@ -2593,20 +2584,6 @@ struct sched_class {
 #endif
 };
 
-/*
- * Does not nest; only used around sched_class::pick_task() rq-lock-breaks.
- */
-static inline void rq_modified_clear(struct rq *rq)
-{
-	rq->queue_mask = 0;
-}
-
-static inline bool rq_modified_above(struct rq *rq, const struct sched_class * class)
-{
-	unsigned int mask = class->queue_mask;
-	return rq->queue_mask & ~((mask << 1) - 1);
-}
-
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	WARN_ON_ONCE(rq->donor != prev);

@@ -3899,6 +3876,7 @@ void move_queued_task_locked(struct rq *src_rq, struct rq *dst_rq, struct task_s
 	deactivate_task(src_rq, task, 0);
 	set_task_cpu(task, dst_rq->cpu);
 	activate_task(dst_rq, task, 0);
+	wakeup_preempt(dst_rq, task, 0);
 }
 
 static inline

index 4f9192b..f95798b 100644
@@ -97,9 +97,6 @@ static void update_curr_stop(struct rq *rq)
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
 DEFINE_SCHED_CLASS(stop) = {
-
-	.queue_mask		= 16,
-
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
 	.yield_task		= yield_task_stop,

index 4479f7d..7d0a862 100644
@@ -2090,7 +2090,6 @@ 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);

@@ -2123,7 +2122,6 @@ 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);
 }
 

@@ -2174,10 +2172,14 @@ 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

@@ -6804,6 +6806,7 @@ 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)

@@ -8650,6 +8653,8 @@ 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;

@@ -10775,10 +10780,8 @@ 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,

@@ -10831,6 +10834,17 @@ void sched_change_end(struct sched_change_ctx *ctx)
 			p->sched_class->switched_to(rq, p);
 
 		/*
+		 * 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 (ctx->running && 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 someone should have set
 		 * need_resched by now.
 		 */

index 319439f..80c9559 100644
@@ -2499,9 +2499,16 @@ static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
  * Only called when both the current and waking task are -deadline
  * tasks.
  */
-static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p,
-				  int flags)
+static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags)
 {
+	/*
+	 * Can only get preempted by stop-class, and those should be
+	 * few and short lived, doesn't really make sense to push
+	 * anything away for that.
+	 */
+	if (p->sched_class != &dl_sched_class)
+		return;
+
 	if (dl_entity_preempt(&p->dl, &rq->donor->dl)) {
 		resched_curr(rq);
 		return;

@@ -3346,9 +3353,6 @@ static int task_is_throttled_dl(struct task_struct *p, int cpu)
 #endif
 
 DEFINE_SCHED_CLASS(dl) = {
-
-	.queue_mask		= 8,
-
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,

index 05f5a49..3b32e64 100644
@@ -2431,7 +2431,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	/* see kick_cpus_irq_workfn() */
 	smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
 
-	rq_modified_clear(rq);
+	rq->next_class = &ext_sched_class;
 
 	rq_unpin_lock(rq, rf);
 	balance_one(rq, prev);

@@ -2446,7 +2446,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	 * If @force_scx is true, always try to pick a SCHED_EXT task,
 	 * regardless of any higher-priority sched classes activity.
 	 */
-	if (!force_scx && rq_modified_above(rq, &ext_sched_class))
+	if (!force_scx && sched_class_above(rq->next_class, &ext_sched_class))
 		return RETRY_TASK;
 
 	keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;

@@ -3075,7 +3075,8 @@ static void switched_from_scx(struct rq *rq, struct task_struct *p)
 	scx_disable_task(p);
 }
 
-static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {}
+static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p, int wake_flags) {}
+
 static void switched_to_scx(struct rq *rq, struct task_struct *p) {}
 
 int scx_check_setscheduler(struct task_struct *p, int policy)

@@ -3336,8 +3337,6 @@ static void scx_cgroup_unlock(void) {}
  *   their current sched_class. Call them directly from sched core instead.
  */
 DEFINE_SCHED_CLASS(ext) = {
-	.queue_mask		= 1,
-
 	.enqueue_task		= enqueue_task_scx,
 	.dequeue_task		= dequeue_task_scx,
 	.yield_task		= yield_task_scx,

index d588eb8..76f5e4b 100644
@@ -8736,7 +8736,7 @@ preempt_sync(struct rq *rq, int wake_flags,
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int wake_flags)
+static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_flags)
 {
 	enum preempt_wakeup_action preempt_action = PREEMPT_WAKEUP_PICK;
 	struct task_struct *donor = rq->donor;

@@ -8744,6 +8744,12 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int 
 	struct cfs_rq *cfs_rq = task_cfs_rq(donor);
 	int cse_is_idle, pse_is_idle;
 
+	/*
+	 * XXX Getting preempted by higher class, try and find idle CPU?
+	 */
+	if (p->sched_class != &fair_sched_class)
+		return;
+
 	if (unlikely(se == pse))
 		return;
 

@@ -12911,7 +12917,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 	t0 = sched_clock_cpu(this_cpu);
 	__sched_balance_update_blocked_averages(this_rq);
 
-	rq_modified_clear(this_rq);
+	this_rq->next_class = &fair_sched_class;
 	raw_spin_rq_unlock(this_rq);
 
 	for_each_domain(this_cpu, sd) {

@@ -12978,7 +12984,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 		pulled_task = 1;
 
 	/* If a higher prio class was modified, restart the pick */
-	if (rq_modified_above(this_rq, &fair_sched_class))
+	if (sched_class_above(this_rq->next_class, &fair_sched_class))
 		pulled_task = -1;
 
 out:

@@ -13882,15 +13888,12 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
  * All the scheduling class methods:
  */
 DEFINE_SCHED_CLASS(fair) = {
-
-	.queue_mask		= 2,
-
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
 	.yield_to_task		= yield_to_task_fair,
 
-	.wakeup_preempt		= check_preempt_wakeup_fair,
+	.wakeup_preempt		= wakeup_preempt_fair,
 
 	.pick_task		= pick_task_fair,
 	.pick_next_task		= pick_next_task_fair,

index c174afe..65eb8f8 100644
@@ -536,9 +536,6 @@ static void update_curr_idle(struct rq *rq)
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
 DEFINE_SCHED_CLASS(idle) = {
-
-	.queue_mask		= 0,
-
 	/* no enqueue/yield_task for idle tasks */
 
 	/* dequeue is not valid, we print a debug message there: */

index f1867fe..0a9b2cd 100644
@@ -1615,6 +1615,12 @@ static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *donor = rq->donor;
 
+	/*
+	 * XXX If we're preempted by DL, queue a push?
+	 */
+	if (p->sched_class != &rt_sched_class)
+		return;
+
 	if (p->prio < donor->prio) {
 		resched_curr(rq);
 		return;

@@ -2568,9 +2574,6 @@ static int task_is_throttled_rt(struct task_struct *p, int cpu)
 #endif /* CONFIG_SCHED_CORE */
 
 DEFINE_SCHED_CLASS(rt) = {
-
-	.queue_mask		= 4,
-
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,

index ab1bfa0..3ceaa9d 100644
@@ -1118,8 +1118,6 @@ struct rq {
 	/* runqueue lock: */
 	raw_spinlock_t		__lock;
 
-	/* Per class runqueue modification mask; bits in class order. */
-	unsigned int		queue_mask;
 	unsigned int		nr_running;
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int		nr_numa_running;

@@ -1179,6 +1177,7 @@ struct rq {
 	struct sched_dl_entity	*dl_server;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
+	const struct sched_class *next_class;
 	unsigned long		next_balance;
 	struct mm_struct	*prev_mm;
 

@@ -2426,15 +2425,6 @@ struct sched_class {
 #ifdef CONFIG_UCLAMP_TASK
 	int uclamp_enabled;
 #endif
-	/*
-	 * idle:  0
-	 * ext:   1
-	 * fair:  2
-	 * rt:    4
-	 * dl:    8
-	 * stop: 16
-	 */
-	unsigned int queue_mask;
 
 	/*
 	 * move_queued_task/activate_task/enqueue_task: rq->lock

@@ -2593,20 +2583,6 @@ struct sched_class {
 #endif
 };
 
-/*
- * Does not nest; only used around sched_class::pick_task() rq-lock-breaks.
- */
-static inline void rq_modified_clear(struct rq *rq)
-{
-	rq->queue_mask = 0;
-}
-
-static inline bool rq_modified_above(struct rq *rq, const struct sched_class * class)
-{
-	unsigned int mask = class->queue_mask;
-	return rq->queue_mask & ~((mask << 1) - 1);
-}
-
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	WARN_ON_ONCE(rq->donor != prev);

@@ -3899,6 +3875,7 @@ void move_queued_task_locked(struct rq *src_rq, struct rq *dst_rq, struct task_s
 	deactivate_task(src_rq, task, 0);
 	set_task_cpu(task, dst_rq->cpu);
 	activate_task(dst_rq, task, 0);
+	wakeup_preempt(dst_rq, task, 0);
 }
 
 static inline

index 4f9192b..f95798b 100644
@@ -97,9 +97,6 @@ static void update_curr_stop(struct rq *rq)
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
 DEFINE_SCHED_CLASS(stop) = {
-
-	.queue_mask		= 16,
-
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
 	.yield_task		= yield_task_stop,