Merge tag 'sched-core-2026-04-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Fair scheduling updates:
   - Skip SCHED_IDLE rq for SCHED_IDLE tasks (Christian Loehle)
   - Remove superfluous rcu_read_lock() in the wakeup path (K Prateek Nayak)
   - Simplify the entry condition for update_idle_cpu_scan() (K Prateek Nayak)
   - Simplify SIS_UTIL handling in select_idle_cpu() (K Prateek Nayak)
   - Avoid overflow in enqueue_entity() (K Prateek Nayak)
   - Update overutilized detection (Vincent Guittot)
   - Prevent negative lag increase during delayed dequeue (Vincent Guittot)
   - Clear buddies for preempt_short (Vincent Guittot)
   - Implement more complex proportional newidle balance (Peter Zijlstra)
   - Increase weight bits for avg_vruntime (Peter Zijlstra)
   - Use full weight to __calc_delta() (Peter Zijlstra)

  RT and DL scheduling updates:
   - Fix incorrect schedstats for rt and dl thread (Dengjun Su)
   - Skip group schedulable check with rt_group_sched=0 (Michal Koutný)
   - Move group schedulability check to sched_rt_global_validate()
     (Michal Koutný)
   - Add reporting of runtime left & abs deadline to sched_getattr()
     for DEADLINE tasks (Tommaso Cucinotta)

  Scheduling topology updates by K Prateek Nayak:
   - Compute sd_weight considering cpuset partitions
   - Extract "imb_numa_nr" calculation into a separate helper
   - Allocate per-CPU sched_domain_shared in s_data
   - Switch to assigning "sd->shared" from s_data
   - Remove sched_domain_shared allocation with sd_data

  Energy-aware scheduling updates:
   - Filter false overloaded_group case for EAS (Vincent Guittot)
   - PM: EM: Switch to rcu_dereference_all() in wakeup path
     (Dietmar Eggemann)

  Infrastructure updates:
   - Replace use of system_unbound_wq with system_dfl_wq (Marco Crivellari)

  Proxy scheduling updates by John Stultz:
   - Make class_schedulers avoid pushing current, and get rid of proxy_tag_curr()
   - Minimise repeated sched_proxy_exec() checking
   - Fix potentially missing balancing with Proxy Exec
   - Fix and improve task::blocked_on et al handling
   - Add assert_balance_callbacks_empty() helper
   - Add logic to zap balancing callbacks if we pick again
   - Move attach_one_task() and attach_task() helpers to sched.h
   - Handle blocked-waiter migration (and return migration)
   - Add K Prateek Nayak to scheduler reviewers for proxy execution

  Misc cleanups and fixes by John Stultz, Joseph Salisbury, Peter
  Zijlstra, K Prateek Nayak, Michal Koutný, Randy Dunlap, Shrikanth
  Hegde, Vincent Guittot, Zhan Xusheng, Xie Yuanbin and Vincent Guittot"

* tag 'sched-core-2026-04-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  sched/eevdf: Clear buddies for preempt_short
  sched/rt: Cleanup global RT bandwidth functions
  sched/rt: Move group schedulability check to sched_rt_global_validate()
  sched/rt: Skip group schedulable check with rt_group_sched=0
  sched/fair: Avoid overflow in enqueue_entity()
  sched: Use u64 for bandwidth ratio calculations
  sched/fair: Prevent negative lag increase during delayed dequeue
  sched/fair: Use sched_energy_enabled()
  sched: Handle blocked-waiter migration (and return migration)
  sched: Move attach_one_task and attach_task helpers to sched.h
  sched: Add logic to zap balance callbacks if we pick again
  sched: Add assert_balance_callbacks_empty helper
  sched/locking: Add special p->blocked_on==PROXY_WAKING value for proxy return-migration
  sched: Fix modifying donor->blocked on without proper locking
  locking: Add task::blocked_lock to serialize blocked_on state
  sched: Fix potentially missing balancing with Proxy Exec
  sched: Minimise repeated sched_proxy_exec() checking
  sched: Make class_schedulers avoid pushing current, and get rid of proxy_tag_curr()
  MAINTAINERS: Add K Prateek Nayak to scheduler reviewers
  sched/core: Get this cpu once in ttwu_queue_cond()
  ...

1 files changed, 362 insertions, 151 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2be80780ff51..69361c63353a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -225,6 +225,7 @@ void __init sched_init_granularity(void)
 	update_sysctl();
 }
 
+#ifndef CONFIG_64BIT
 #define WMULT_CONST	(~0U)
 #define WMULT_SHIFT	32
 
@@ -283,6 +284,12 @@ static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight
 
 	return mul_u64_u32_shr(delta_exec, fact, shift);
 }
+#else
+static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw)
+{
+	return (delta_exec * weight) / lw->weight;
+}
+#endif
 
 /*
  * delta /= w
@@ -665,25 +672,83 @@ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Since zero_vruntime closely tracks the per-task service, these
  * deltas: (v_i - v0), will be in the order of the maximal (virtual) lag
  * induced in the system due to quantisation.
- *
- * Also, we use scale_load_down() to reduce the size.
- *
- * As measured, the max (key * weight) value was ~44 bits for a kernel build.
  */
+static inline unsigned long avg_vruntime_weight(struct cfs_rq *cfs_rq, unsigned long w)
+{
+#ifdef CONFIG_64BIT
+	if (cfs_rq->sum_shift)
+		w = max(2UL, w >> cfs_rq->sum_shift);
+#endif
+	return w;
+}
+
+static inline void
+__sum_w_vruntime_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	unsigned long weight = avg_vruntime_weight(cfs_rq, se->load.weight);
+	s64 w_vruntime, key = entity_key(cfs_rq, se);
+
+	w_vruntime = key * weight;
+	WARN_ON_ONCE((w_vruntime >> 63) != (w_vruntime >> 62));
+
+	cfs_rq->sum_w_vruntime += w_vruntime;
+	cfs_rq->sum_weight += weight;
+}
+
 static void
-sum_w_vruntime_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
+sum_w_vruntime_add_paranoid(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	unsigned long weight = scale_load_down(se->load.weight);
-	s64 key = entity_key(cfs_rq, se);
+	unsigned long weight;
+	s64 key, tmp;
+
+again:
+	weight = avg_vruntime_weight(cfs_rq, se->load.weight);
+	key = entity_key(cfs_rq, se);
+
+	if (check_mul_overflow(key, weight, &key))
+		goto overflow;
+
+	if (check_add_overflow(cfs_rq->sum_w_vruntime, key, &tmp))
+		goto overflow;
 
-	cfs_rq->sum_w_vruntime += key * weight;
+	cfs_rq->sum_w_vruntime = tmp;
 	cfs_rq->sum_weight += weight;
+	return;
+
+overflow:
+	/*
+	 * There's gotta be a limit -- if we're still failing at this point
+	 * there's really nothing much to be done about things.
+	 */
+	BUG_ON(cfs_rq->sum_shift >= 10);
+	cfs_rq->sum_shift++;
+
+	/*
+	 * Note: \Sum (k_i * (w_i >> 1)) != (\Sum (k_i * w_i)) >> 1
+	 */
+	cfs_rq->sum_w_vruntime = 0;
+	cfs_rq->sum_weight = 0;
+
+	for (struct rb_node *node = cfs_rq->tasks_timeline.rb_leftmost;
+	     node; node = rb_next(node))
+		__sum_w_vruntime_add(cfs_rq, __node_2_se(node));
+
+	goto again;
+}
+
+static void
+sum_w_vruntime_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	if (sched_feat(PARANOID_AVG))
+		return sum_w_vruntime_add_paranoid(cfs_rq, se);
+
+	__sum_w_vruntime_add(cfs_rq, se);
 }
 
 static void
 sum_w_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	unsigned long weight = scale_load_down(se->load.weight);
+	unsigned long weight = avg_vruntime_weight(cfs_rq, se->load.weight);
 	s64 key = entity_key(cfs_rq, se);
 
 	cfs_rq->sum_w_vruntime -= key * weight;
@@ -725,7 +790,7 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
 		s64 runtime = cfs_rq->sum_w_vruntime;
 
 		if (curr) {
-			unsigned long w = scale_load_down(curr->load.weight);
+			unsigned long w = avg_vruntime_weight(cfs_rq, curr->load.weight);
 
 			runtime += entity_key(cfs_rq, curr) * w;
 			weight += w;
@@ -735,7 +800,7 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
 		if (runtime < 0)
 			runtime -= (weight - 1);
 
-		delta = div_s64(runtime, weight);
+		delta = div64_long(runtime, weight);
 	} else if (curr) {
 		/*
 		 * When there is but one element, it is the average.
@@ -764,17 +829,44 @@ static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq);
  *
  *   -r_max < lag < max(r_max, q)
  */
-static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static s64 entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 avruntime)
 {
 	u64 max_slice = cfs_rq_max_slice(cfs_rq) + TICK_NSEC;
 	s64 vlag, limit;
 
+	vlag = avruntime - se->vruntime;
+	limit = calc_delta_fair(max_slice, se);
+
+	return clamp(vlag, -limit, limit);
+}
+
+/*
+ * Delayed dequeue aims to reduce the negative lag of a dequeued task. While
+ * updating the lag of an entity, check that negative lag didn't increase
+ * during the delayed dequeue period which would be unfair.
+ * Similarly, check that the entity didn't gain positive lag when DELAY_ZERO
+ * is set.
+ *
+ * Return true if the lag has been adjusted.
+ */
+static __always_inline
+bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	s64 vlag = entity_lag(cfs_rq, se, avg_vruntime(cfs_rq));
+	bool ret;
+
 	WARN_ON_ONCE(!se->on_rq);
 
-	vlag = avg_vruntime(cfs_rq) - se->vruntime;
-	limit = calc_delta_fair(max_slice, se);
+	if (se->sched_delayed) {
+		/* previous vlag < 0 otherwise se would not be delayed */
+		vlag = max(vlag, se->vlag);
+		if (sched_feat(DELAY_ZERO))
+			vlag = min(vlag, 0);
+	}
+	ret = (vlag == se->vlag);
+	se->vlag = vlag;
 
-	se->vlag = clamp(vlag, -limit, limit);
+	return ret;
 }
 
 /*
@@ -801,7 +893,7 @@ static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime)
 	long load = cfs_rq->sum_weight;
 
 	if (curr && curr->on_rq) {
-		unsigned long weight = scale_load_down(curr->load.weight);
+		unsigned long weight = avg_vruntime_weight(cfs_rq, curr->load.weight);
 
 		avg += entity_key(cfs_rq, curr) * weight;
 		load += weight;
@@ -1024,7 +1116,7 @@ static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq, bool protect)
 	/*
 	 * Picking the ->next buddy will affect latency but not fairness.
 	 */
-	if (sched_feat(PICK_BUDDY) &&
+	if (sched_feat(PICK_BUDDY) && protect &&
 	    cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next)) {
 		/* ->next will never be delayed */
 		WARN_ON_ONCE(cfs_rq->next->sched_delayed);
@@ -3841,23 +3933,125 @@ dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		    se_weight(se) * -se->avg.load_sum);
 }
 
-static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags);
+static void
+rescale_entity(struct sched_entity *se, unsigned long weight, bool rel_vprot)
+{
+	unsigned long old_weight = se->load.weight;
+
+	/*
+	 * VRUNTIME
+	 * --------
+	 *
+	 * COROLLARY #1: The virtual runtime of the entity needs to be
+	 * adjusted if re-weight at !0-lag point.
+	 *
+	 * Proof: For contradiction assume this is not true, so we can
+	 * re-weight without changing vruntime at !0-lag point.
+	 *
+	 *             Weight	VRuntime   Avg-VRuntime
+	 *     before    w          v            V
+	 *      after    w'         v'           V'
+	 *
+	 * Since lag needs to be preserved through re-weight:
+	 *
+	 *	lag = (V - v)*w = (V'- v')*w', where v = v'
+	 *	==>	V' = (V - v)*w/w' + v		(1)
+	 *
+	 * Let W be the total weight of the entities before reweight,
+	 * since V' is the new weighted average of entities:
+	 *
+	 *	V' = (WV + w'v - wv) / (W + w' - w)	(2)
+	 *
+	 * by using (1) & (2) we obtain:
+	 *
+	 *	(WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v
+	 *	==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v
+	 *	==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v
+	 *	==>	(V - v)*W/(W + w' - w) = (V - v)*w/w' (3)
+	 *
+	 * Since we are doing at !0-lag point which means V != v, we
+	 * can simplify (3):
+	 *
+	 *	==>	W / (W + w' - w) = w / w'
+	 *	==>	Ww' = Ww + ww' - ww
+	 *	==>	W * (w' - w) = w * (w' - w)
+	 *	==>	W = w	(re-weight indicates w' != w)
+	 *
+	 * So the cfs_rq contains only one entity, hence vruntime of
+	 * the entity @v should always equal to the cfs_rq's weighted
+	 * average vruntime @V, which means we will always re-weight
+	 * at 0-lag point, thus breach assumption. Proof completed.
+	 *
+	 *
+	 * COROLLARY #2: Re-weight does NOT affect weighted average
+	 * vruntime of all the entities.
+	 *
+	 * Proof: According to corollary #1, Eq. (1) should be:
+	 *
+	 *	(V - v)*w = (V' - v')*w'
+	 *	==>    v' = V' - (V - v)*w/w'		(4)
+	 *
+	 * According to the weighted average formula, we have:
+	 *
+	 *	V' = (WV - wv + w'v') / (W - w + w')
+	 *	   = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w')
+	 *	   = (WV - wv + w'V' - Vw + wv) / (W - w + w')
+	 *	   = (WV + w'V' - Vw) / (W - w + w')
+	 *
+	 *	==>  V'*(W - w + w') = WV + w'V' - Vw
+	 *	==>	V' * (W - w) = (W - w) * V	(5)
+	 *
+	 * If the entity is the only one in the cfs_rq, then reweight
+	 * always occurs at 0-lag point, so V won't change. Or else
+	 * there are other entities, hence W != w, then Eq. (5) turns
+	 * into V' = V. So V won't change in either case, proof done.
+	 *
+	 *
+	 * So according to corollary #1 & #2, the effect of re-weight
+	 * on vruntime should be:
+	 *
+	 *	v' = V' - (V - v) * w / w'		(4)
+	 *	   = V  - (V - v) * w / w'
+	 *	   = V  - vl * w / w'
+	 *	   = V  - vl'
+	 */
+	se->vlag = div64_long(se->vlag * old_weight, weight);
+
+	/*
+	 * DEADLINE
+	 * --------
+	 *
+	 * When the weight changes, the virtual time slope changes and
+	 * we should adjust the relative virtual deadline accordingly.
+	 *
+	 *	d' = v' + (d - v)*w/w'
+	 *	   = V' - (V - v)*w/w' + (d - v)*w/w'
+	 *	   = V  - (V - v)*w/w' + (d - v)*w/w'
+	 *	   = V  + (d - V)*w/w'
+	 */
+	if (se->rel_deadline)
+		se->deadline = div64_long(se->deadline * old_weight, weight);
+
+	if (rel_vprot)
+		se->vprot = div64_long(se->vprot * old_weight, weight);
+}
 
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
 	bool curr = cfs_rq->curr == se;
 	bool rel_vprot = false;
-	u64 vprot;
+	u64 avruntime = 0;
 
 	if (se->on_rq) {
 		/* commit outstanding execution time */
 		update_curr(cfs_rq);
-		update_entity_lag(cfs_rq, se);
-		se->deadline -= se->vruntime;
+		avruntime = avg_vruntime(cfs_rq);
+		se->vlag = entity_lag(cfs_rq, se, avruntime);
+		se->deadline -= avruntime;
 		se->rel_deadline = 1;
 		if (curr && protect_slice(se)) {
-			vprot = se->vprot - se->vruntime;
+			se->vprot -= avruntime;
 			rel_vprot = true;
 		}
 
@@ -3868,30 +4062,23 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	}
 	dequeue_load_avg(cfs_rq, se);
 
-	/*
-	 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
-	 * we need to scale se->vlag when w_i changes.
-	 */
-	se->vlag = div_s64(se->vlag * se->load.weight, weight);
-	if (se->rel_deadline)
-		se->deadline = div_s64(se->deadline * se->load.weight, weight);
-
-	if (rel_vprot)
-		vprot = div_s64(vprot * se->load.weight, weight);
+	rescale_entity(se, weight, rel_vprot);
 
 	update_load_set(&se->load, weight);
 
 	do {
 		u32 divider = get_pelt_divider(&se->avg);
-
 		se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider);
 	} while (0);
 
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
-		place_entity(cfs_rq, se, 0);
 		if (rel_vprot)
-			se->vprot = se->vruntime + vprot;
+			se->vprot += avruntime;
+		se->deadline += avruntime;
+		se->rel_deadline = 0;
+		se->vruntime = avruntime - se->vlag;
+
 		update_load_add(&cfs_rq->load, se->load.weight);
 		if (!curr)
 			__enqueue_entity(cfs_rq, se);
@@ -5165,6 +5352,7 @@ static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	u64 vslice, vruntime = avg_vruntime(cfs_rq);
+	bool update_zero = false;
 	s64 lag = 0;
 
 	if (!se->custom_slice)
@@ -5181,7 +5369,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	if (sched_feat(PLACE_LAG) && cfs_rq->nr_queued && se->vlag) {
 		struct sched_entity *curr = cfs_rq->curr;
-		unsigned long load;
+		long load, weight;
 
 		lag = se->vlag;
 
@@ -5239,17 +5427,44 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		 */
 		load = cfs_rq->sum_weight;
 		if (curr && curr->on_rq)
-			load += scale_load_down(curr->load.weight);
+			load += avg_vruntime_weight(cfs_rq, curr->load.weight);
 
-		lag *= load + scale_load_down(se->load.weight);
+		weight = avg_vruntime_weight(cfs_rq, se->load.weight);
+		lag *= load + weight;
 		if (WARN_ON_ONCE(!load))
 			load = 1;
-		lag = div_s64(lag, load);
+		lag = div64_long(lag, load);
+
+		/*
+		 * A heavy entity (relative to the tree) will pull the
+		 * avg_vruntime close to its vruntime position on enqueue. But
+		 * the zero_vruntime point is only updated at the next
+		 * update_deadline()/place_entity()/update_entity_lag().
+		 *
+		 * Specifically (see the comment near avg_vruntime_weight()):
+		 *
+		 *   sum_w_vruntime = \Sum (v_i - v0) * w_i
+		 *
+		 * Note that if v0 is near a light entity, both terms will be
+		 * small for the light entity, while in that case both terms
+		 * are large for the heavy entity, leading to risk of
+		 * overflow.
+		 *
+		 * OTOH if v0 is near the heavy entity, then the difference is
+		 * larger for the light entity, but the factor is small, while
+		 * for the heavy entity the difference is small but the factor
+		 * is large. Avoiding the multiplication overflow.
+		 */
+		if (weight > load)
+			update_zero = true;
 	}
 
 	se->vruntime = vruntime - lag;
 
-	if (se->rel_deadline) {
+	if (update_zero)
+		update_zero_vruntime(cfs_rq, -lag);
+
+	if (sched_feat(PLACE_REL_DEADLINE) && se->rel_deadline) {
 		se->deadline += se->vruntime;
 		se->rel_deadline = 0;
 		return;
@@ -5399,13 +5614,6 @@ static void clear_delayed(struct sched_entity *se)
 	}
 }
 
-static inline void finish_delayed_dequeue_entity(struct sched_entity *se)
-{
-	clear_delayed(se);
-	if (sched_feat(DELAY_ZERO) && se->vlag > 0)
-		se->vlag = 0;
-}
-
 static bool
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -5431,6 +5639,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		if (sched_feat(DELAY_DEQUEUE) && delay &&
 		    !entity_eligible(cfs_rq, se)) {
 			update_load_avg(cfs_rq, se, 0);
+			update_entity_lag(cfs_rq, se);
 			set_delayed(se);
 			return false;
 		}
@@ -5470,7 +5679,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_cfs_group(se);
 
 	if (flags & DEQUEUE_DELAYED)
-		finish_delayed_dequeue_entity(se);
+		clear_delayed(se);
 
 	if (cfs_rq->nr_queued == 0) {
 		update_idle_cfs_rq_clock_pelt(cfs_rq);
@@ -6866,16 +7075,15 @@ static inline void hrtick_update(struct rq *rq)
 
 static inline bool cpu_overutilized(int cpu)
 {
-	unsigned long  rq_util_min, rq_util_max;
+	unsigned long rq_util_max;
 
 	if (!sched_energy_enabled())
 		return false;
 
-	rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
 	rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
 
 	/* Return true only if the utilization doesn't fit CPU's capacity */
-	return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu);
+	return !util_fits_cpu(cpu_util_cfs(cpu), 0, rq_util_max, cpu);
 }
 
 /*
@@ -6913,9 +7121,15 @@ static int sched_idle_rq(struct rq *rq)
 			rq->nr_running);
 }
 
-static int sched_idle_cpu(int cpu)
+static int choose_sched_idle_rq(struct rq *rq, struct task_struct *p)
+{
+	return sched_idle_rq(rq) && !task_has_idle_policy(p);
+}
+
+static int choose_idle_cpu(int cpu, struct task_struct *p)
 {
-	return sched_idle_rq(cpu_rq(cpu));
+	return available_idle_cpu(cpu) ||
+	       choose_sched_idle_rq(cpu_rq(cpu), p);
 }
 
 static void
@@ -6931,18 +7145,14 @@ requeue_delayed_entity(struct sched_entity *se)
 	WARN_ON_ONCE(!se->sched_delayed);
 	WARN_ON_ONCE(!se->on_rq);
 
-	if (sched_feat(DELAY_ZERO)) {
-		update_entity_lag(cfs_rq, se);
-		if (se->vlag > 0) {
-			cfs_rq->nr_queued--;
-			if (se != cfs_rq->curr)
-				__dequeue_entity(cfs_rq, se);
-			se->vlag = 0;
-			place_entity(cfs_rq, se, 0);
-			if (se != cfs_rq->curr)
-				__enqueue_entity(cfs_rq, se);
-			cfs_rq->nr_queued++;
-		}
+	if (update_entity_lag(cfs_rq, se)) {
+		cfs_rq->nr_queued--;
+		if (se != cfs_rq->curr)
+			__dequeue_entity(cfs_rq, se);
+		place_entity(cfs_rq, se, 0);
+		if (se != cfs_rq->curr)
+			__enqueue_entity(cfs_rq, se);
+		cfs_rq->nr_queued++;
 	}
 
 	update_load_avg(cfs_rq, se, 0);
@@ -7475,7 +7685,7 @@ sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *
 		if (!sched_core_cookie_match(rq, p))
 			continue;
 
-		if (sched_idle_cpu(i))
+		if (choose_sched_idle_rq(rq, p))
 			return i;
 
 		if (available_idle_cpu(i)) {
@@ -7566,8 +7776,7 @@ static inline int sched_balance_find_dst_cpu(struct sched_domain *sd, struct tas
 
 static inline int __select_idle_cpu(int cpu, struct task_struct *p)
 {
-	if ((available_idle_cpu(cpu) || sched_idle_cpu(cpu)) &&
-	    sched_cpu_cookie_match(cpu_rq(cpu), p))
+	if (choose_idle_cpu(cpu, p) && sched_cpu_cookie_match(cpu_rq(cpu), p))
 		return cpu;
 
 	return -1;
@@ -7640,7 +7849,8 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 		if (!available_idle_cpu(cpu)) {
 			idle = false;
 			if (*idle_cpu == -1) {
-				if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, cpus)) {
+				if (choose_sched_idle_rq(cpu_rq(cpu), p) &&
+				    cpumask_test_cpu(cpu, cpus)) {
 					*idle_cpu = cpu;
 					break;
 				}
@@ -7675,7 +7885,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
 		 */
 		if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
 			continue;
-		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
+		if (choose_idle_cpu(cpu, p))
 			return cpu;
 	}
 
@@ -7714,21 +7924,26 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
 	int i, cpu, idle_cpu = -1, nr = INT_MAX;
-	struct sched_domain_shared *sd_share;
-
-	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
 
 	if (sched_feat(SIS_UTIL)) {
-		sd_share = rcu_dereference_all(per_cpu(sd_llc_shared, target));
-		if (sd_share) {
-			/* because !--nr is the condition to stop scan */
-			nr = READ_ONCE(sd_share->nr_idle_scan) + 1;
-			/* overloaded LLC is unlikely to have idle cpu/core */
-			if (nr == 1)
-				return -1;
-		}
+		/*
+		 * Increment because !--nr is the condition to stop scan.
+		 *
+		 * Since "sd" is "sd_llc" for target CPU dereferenced in the
+		 * caller, it is safe to directly dereference "sd->shared".
+		 * Topology bits always ensure it assigned for "sd_llc" abd it
+		 * cannot disappear as long as we have a RCU protected
+		 * reference to one the associated "sd" here.
+		 */
+		nr = READ_ONCE(sd->shared->nr_idle_scan) + 1;
+		/* overloaded LLC is unlikely to have idle cpu/core */
+		if (nr == 1)
+			return -1;
 	}
 
+	if (!cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr))
+		return -1;
+
 	if (static_branch_unlikely(&sched_cluster_active)) {
 		struct sched_group *sg = sd->groups;
 
@@ -7797,7 +8012,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 	for_each_cpu_wrap(cpu, cpus, target) {
 		unsigned long cpu_cap = capacity_of(cpu);
 
-		if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
+		if (!choose_idle_cpu(cpu, p))
 			continue;
 
 		fits = util_fits_cpu(task_util, util_min, util_max, cpu);
@@ -7868,7 +8083,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	 */
 	lockdep_assert_irqs_disabled();
 
-	if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
+	if (choose_idle_cpu(target, p) &&
 	    asym_fits_cpu(task_util, util_min, util_max, target))
 		return target;
 
@@ -7876,7 +8091,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	 * If the previous CPU is cache affine and idle, don't be stupid:
 	 */
 	if (prev != target && cpus_share_cache(prev, target) &&
-	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
+	    choose_idle_cpu(prev, p) &&
 	    asym_fits_cpu(task_util, util_min, util_max, prev)) {
 
 		if (!static_branch_unlikely(&sched_cluster_active) ||
@@ -7908,7 +8123,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	if (recent_used_cpu != prev &&
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
-	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
+	    choose_idle_cpu(recent_used_cpu, p) &&
 	    cpumask_test_cpu(recent_used_cpu, p->cpus_ptr) &&
 	    asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
 
@@ -8408,10 +8623,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 	struct perf_domain *pd;
 	struct energy_env eenv;
 
-	rcu_read_lock();
 	pd = rcu_dereference_all(rd->pd);
 	if (!pd)
-		goto unlock;
+		return target;
 
 	/*
 	 * Energy-aware wake-up happens on the lowest sched_domain starting
@@ -8421,13 +8635,13 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 	while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
 		sd = sd->parent;
 	if (!sd)
-		goto unlock;
+		return target;
 
 	target = prev_cpu;
 
 	sync_entity_load_avg(&p->se);
 	if (!task_util_est(p) && p_util_min == 0)
-		goto unlock;
+		return target;
 
 	eenv_task_busy_time(&eenv, p, prev_cpu);
 
@@ -8522,7 +8736,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 						    prev_cpu);
 			/* CPU utilization has changed */
 			if (prev_delta < base_energy)
-				goto unlock;
+				return target;
 			prev_delta -= base_energy;
 			prev_actual_cap = cpu_actual_cap;
 			best_delta = min(best_delta, prev_delta);
@@ -8546,7 +8760,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 						   max_spare_cap_cpu);
 			/* CPU utilization has changed */
 			if (cur_delta < base_energy)
-				goto unlock;
+				return target;
 			cur_delta -= base_energy;
 
 			/*
@@ -8563,7 +8777,6 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 			best_actual_cap = cpu_actual_cap;
 		}
 	}
-	rcu_read_unlock();
 
 	if ((best_fits > prev_fits) ||
 	    ((best_fits > 0) && (best_delta < prev_delta)) ||
@@ -8571,11 +8784,6 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 		target = best_energy_cpu;
 
 	return target;
-
-unlock:
-	rcu_read_unlock();
-
-	return target;
 }
 
 /*
@@ -8620,7 +8828,6 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 		want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, p->cpus_ptr);
 	}
 
-	rcu_read_lock();
 	for_each_domain(cpu, tmp) {
 		/*
 		 * If both 'cpu' and 'prev_cpu' are part of this domain,
@@ -8646,14 +8853,13 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 			break;
 	}
 
-	if (unlikely(sd)) {
-		/* Slow path */
-		new_cpu = sched_balance_find_dst_cpu(sd, p, cpu, prev_cpu, sd_flag);
-	} else if (wake_flags & WF_TTWU) { /* XXX always ? */
-		/* Fast path */
-		new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
-	}
-	rcu_read_unlock();
+	/* Slow path */
+	if (unlikely(sd))
+		return sched_balance_find_dst_cpu(sd, p, cpu, prev_cpu, sd_flag);
+
+	/* Fast path */
+	if (wake_flags & WF_TTWU)
+		return select_idle_sibling(p, prev_cpu, new_cpu);
 
 	return new_cpu;
 }
@@ -8944,8 +9150,10 @@ pick:
 	return;
 
 preempt:
-	if (preempt_action == PREEMPT_WAKEUP_SHORT)
+	if (preempt_action == PREEMPT_WAKEUP_SHORT) {
 		cancel_protect_slice(se);
+		clear_buddies(cfs_rq, se);
+	}
 
 	resched_curr_lazy(rq);
 }
@@ -9793,32 +10001,6 @@ next:
 }
 
 /*
- * attach_task() -- attach the task detached by detach_task() to its new rq.
- */
-static void attach_task(struct rq *rq, struct task_struct *p)
-{
-	lockdep_assert_rq_held(rq);
-
-	WARN_ON_ONCE(task_rq(p) != rq);
-	activate_task(rq, p, ENQUEUE_NOCLOCK);
-	wakeup_preempt(rq, p, 0);
-}
-
-/*
- * attach_one_task() -- attaches the task returned from detach_one_task() to
- * its new rq.
- */
-static void attach_one_task(struct rq *rq, struct task_struct *p)
-{
-	struct rq_flags rf;
-
-	rq_lock(rq, &rf);
-	update_rq_clock(rq);
-	attach_task(rq, p);
-	rq_unlock(rq, &rf);
-}
-
-/*
  * attach_tasks() -- attaches all tasks detached by detach_tasks() to their
  * new rq.
  */
@@ -10055,6 +10237,7 @@ struct sg_lb_stats {
 	unsigned int group_asym_packing;	/* Tasks should be moved to preferred CPU */
 	unsigned int group_smt_balance;		/* Task on busy SMT be moved */
 	unsigned long group_misfit_task_load;	/* A CPU has a task too big for its capacity */
+	unsigned int group_overutilized;	/* At least one CPU is overutilized in the group */
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
 	unsigned int nr_preferred_running;
@@ -10287,6 +10470,13 @@ group_has_capacity(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 static inline bool
 group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 {
+	/*
+	 * With EAS and uclamp, 1 CPU in the group must be overutilized to
+	 * consider the group overloaded.
+	 */
+	if (sched_energy_enabled() && !sgs->group_overutilized)
+		return false;
+
 	if (sgs->sum_nr_running <= sgs->group_weight)
 		return false;
 
@@ -10470,14 +10660,12 @@ sched_reduced_capacity(struct rq *rq, struct sched_domain *sd)
  * @group: sched_group whose statistics are to be updated.
  * @sgs: variable to hold the statistics for this group.
  * @sg_overloaded: sched_group is overloaded
- * @sg_overutilized: sched_group is overutilized
  */
 static inline void update_sg_lb_stats(struct lb_env *env,
 				      struct sd_lb_stats *sds,
 				      struct sched_group *group,
 				      struct sg_lb_stats *sgs,
-				      bool *sg_overloaded,
-				      bool *sg_overutilized)
+				      bool *sg_overloaded)
 {
 	int i, nr_running, local_group, sd_flags = env->sd->flags;
 	bool balancing_at_rd = !env->sd->parent;
@@ -10499,7 +10687,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->sum_nr_running += nr_running;
 
 		if (cpu_overutilized(i))
-			*sg_overutilized = 1;
+			sgs->group_overutilized = 1;
 
 		/*
 		 * No need to call idle_cpu() if nr_running is not 0
@@ -11075,6 +11263,7 @@ static void update_idle_cpu_scan(struct lb_env *env,
 				 unsigned long sum_util)
 {
 	struct sched_domain_shared *sd_share;
+	struct sched_domain *sd = env->sd;
 	int llc_weight, pct;
 	u64 x, y, tmp;
 	/*
@@ -11088,11 +11277,7 @@ static void update_idle_cpu_scan(struct lb_env *env,
 	if (!sched_feat(SIS_UTIL) || env->idle == CPU_NEWLY_IDLE)
 		return;
 
-	llc_weight = per_cpu(sd_llc_size, env->dst_cpu);
-	if (env->sd->span_weight != llc_weight)
-		return;
-
-	sd_share = rcu_dereference_all(per_cpu(sd_llc_shared, env->dst_cpu));
+	sd_share = sd->shared;
 	if (!sd_share)
 		return;
 
@@ -11126,10 +11311,11 @@ static void update_idle_cpu_scan(struct lb_env *env,
 	 */
 	/* equation [3] */
 	x = sum_util;
+	llc_weight = sd->span_weight;
 	do_div(x, llc_weight);
 
 	/* equation [4] */
-	pct = env->sd->imbalance_pct;
+	pct = sd->imbalance_pct;
 	tmp = x * x * pct * pct;
 	do_div(tmp, 10000 * SCHED_CAPACITY_SCALE);
 	tmp = min_t(long, tmp, SCHED_CAPACITY_SCALE);
@@ -11170,13 +11356,15 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 				update_group_capacity(env->sd, env->dst_cpu);
 		}
 
-		update_sg_lb_stats(env, sds, sg, sgs, &sg_overloaded, &sg_overutilized);
+		update_sg_lb_stats(env, sds, sg, sgs, &sg_overloaded);
 
 		if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
 			sds->busiest_stat = *sgs;
 		}
 
+		sg_overutilized |= sgs->group_overutilized;
+
 		/* Now, start updating sd_lb_stats */
 		sds->total_load += sgs->group_load;
 		sds->total_capacity += sgs->group_capacity;
@@ -12297,7 +12485,30 @@ static inline void update_newidle_stats(struct sched_domain *sd, unsigned int su
 	sd->newidle_success += success;
 
 	if (sd->newidle_call >= 1024) {
-		sd->newidle_ratio = sd->newidle_success;
+		u64 now = sched_clock();
+		s64 delta = now - sd->newidle_stamp;
+		sd->newidle_stamp = now;
+		int ratio = 0;
+
+		if (delta < 0)
+			delta = 0;
+
+		if (sched_feat(NI_RATE)) {
+			/*
+			 * ratio  delta   freq
+			 *
+			 * 1024 -  4  s -  128 Hz
+			 *  512 -  2  s -  256 Hz
+			 *  256 -  1  s -  512 Hz
+			 *  128 - .5  s - 1024 Hz
+			 *   64 - .25 s - 2048 Hz
+			 */
+			ratio = delta >> 22;
+		}
+
+		ratio += sd->newidle_success;
+
+		sd->newidle_ratio = min(1024, ratio);
 		sd->newidle_call /= 2;
 		sd->newidle_success /= 2;
 	}
@@ -12344,7 +12555,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
 {
 	int continue_balancing = 1;
 	int cpu = rq->cpu;
-	int busy = idle != CPU_IDLE && !sched_idle_cpu(cpu);
+	int busy = idle != CPU_IDLE && !sched_idle_rq(rq);
 	unsigned long interval;
 	struct sched_domain *sd;
 	/* Earliest time when we have to do rebalance again */
@@ -12382,7 +12593,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
 				 * state even if we migrated tasks. Update it.
 				 */
 				idle = idle_cpu(cpu);
-				busy = !idle && !sched_idle_cpu(cpu);
+				busy = !idle && !sched_idle_rq(rq);
 			}
 			sd->last_balance = jiffies;
 			interval = get_sd_balance_interval(sd, busy);
@@ -12427,14 +12638,14 @@ static inline int on_null_domain(struct rq *rq)
  */
 static inline int find_new_ilb(void)
 {
+	int this_cpu = smp_processor_id();
 	const struct cpumask *hk_mask;
 	int ilb_cpu;
 
 	hk_mask = housekeeping_cpumask(HK_TYPE_KERNEL_NOISE);
 
 	for_each_cpu_and(ilb_cpu, nohz.idle_cpus_mask, hk_mask) {
-
-		if (ilb_cpu == smp_processor_id())
+		if (ilb_cpu == this_cpu)
 			continue;
 
 		if (idle_cpu(ilb_cpu))
@@ -13004,7 +13215,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
 			unsigned int weight = 1;
 
-			if (sched_feat(NI_RANDOM)) {
+			if (sched_feat(NI_RANDOM) && sd->newidle_ratio < 1024) {
 				/*
 				 * Throw a 1k sided dice; and only run
 				 * newidle_balance according to the success
@@ -14030,7 +14241,7 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m)
 			tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)];
 		}
 		if (ng) {
-			gsf = ng->faults[task_faults_idx(NUMA_MEM, node, 0)],
+			gsf = ng->faults[task_faults_idx(NUMA_MEM, node, 0)];
 			gpf = ng->faults[task_faults_idx(NUMA_MEM, node, 1)];
 		}
 		print_numa_stats(m, node, tsf, tpf, gsf, gpf);