diff --git a/include/linux/sched.h b/include/linux/sched.h
index 373bcc0598d1..12f633514ad2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -575,6 +575,7 @@ struct sched_statistics {
 struct sched_entity {
 	/* For load-balancing: */
 	struct load_weight		load;
+	struct load_weight		h_load;
 	struct rb_node			run_node;
 	u64				deadline;
 	u64				min_vruntime;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 96226707c2f6..2e7cde033a31 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5657,11 +5657,8 @@ EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
  */
 static inline void prefetch_curr_exec_start(struct task_struct *p)
 {
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	struct sched_entity *curr = p->se.cfs_rq->curr;
-#else
 	struct sched_entity *curr = task_rq(p)->cfs.curr;
-#endif
+
 	prefetch(curr);
 	prefetch(&curr->exec_start);
 }
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index f54e732e6d97..c15291cbcbb3 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -975,10 +975,11 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	else
 		SEQ_printf(m, " %c", task_state_to_char(p));
 
-	SEQ_printf(m, " %15s %5d %9Ld.%06ld   %c   %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld   %5d ",
+	SEQ_printf(m, " %15s %5d %10ld %9Ld.%06ld   %c   %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld   %5d ",
 		p->comm, task_pid_nr(p),
+		p->se.h_load.weight,
 		SPLIT_NS(p->se.vruntime),
-		entity_eligible(cfs_rq_of(&p->se), &p->se) ? 'E' : 'N',
+		entity_eligible(&rq->cfs, &p->se) ? 'E' : 'N',
 		SPLIT_NS(p->se.deadline),
 		p->se.custom_slice ? 'S' : ' ',
 		SPLIT_NS(p->se.slice),
@@ -1007,7 +1008,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "runnable tasks:\n");
-	SEQ_printf(m, " S            task   PID       vruntime   eligible    "
+	SEQ_printf(m, " S            task   PID     weight       vruntime   eligible    "
 		   "deadline             slice          sum-exec      switches  "
 		   "prio         wait-time        sum-sleep       sum-block"
 #ifdef CONFIG_NUMA_BALANCING
@@ -1115,6 +1116,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->tg_load_avg_contrib);
 	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_avg",
 			atomic_long_read(&cfs_rq->tg->load_avg));
+	SEQ_printf(m, "  .%-30s: %lu\n", "h_load",
+			cfs_rq->h_load);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_CFS_BANDWIDTH
 	SEQ_printf(m, "  .%-30s: %d\n", "throttled",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1608c01c36fb..cfaed2cb960e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -297,8 +297,8 @@ static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight
  */
 static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
 {
-	if (unlikely(se->load.weight != NICE_0_LOAD))
-		delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
+	if (se->h_load.weight != NICE_0_LOAD)
+		delta = __calc_delta(delta, NICE_0_LOAD, &se->h_load);
 
 	return delta;
 }
@@ -428,38 +428,6 @@ static inline struct sched_entity *parent_entity(const struct sched_entity *se)
 	return se->parent;
 }
 
-static void
-find_matching_se(struct sched_entity **se, struct sched_entity **pse)
-{
-	int se_depth, pse_depth;
-
-	/*
-	 * preemption test can be made between sibling entities who are in the
-	 * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
-	 * both tasks until we find their ancestors who are siblings of common
-	 * parent.
-	 */
-
-	/* First walk up until both entities are at same depth */
-	se_depth = (*se)->depth;
-	pse_depth = (*pse)->depth;
-
-	while (se_depth > pse_depth) {
-		se_depth--;
-		*se = parent_entity(*se);
-	}
-
-	while (pse_depth > se_depth) {
-		pse_depth--;
-		*pse = parent_entity(*pse);
-	}
-
-	while (!is_same_group(*se, *pse)) {
-		*se = parent_entity(*se);
-		*pse = parent_entity(*pse);
-	}
-}
-
 static int tg_is_idle(struct task_group *tg)
 {
 	return tg->idle > 0;
@@ -503,11 +471,6 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
 	return NULL;
 }
 
-static inline void
-find_matching_se(struct sched_entity **se, struct sched_entity **pse)
-{
-}
-
 static inline int tg_is_idle(struct task_group *tg)
 {
 	return 0;
@@ -686,7 +649,7 @@ static inline unsigned long avg_vruntime_weight(struct cfs_rq *cfs_rq, unsigned
 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);
+	unsigned long weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);
 	s64 w_vruntime, key = entity_key(cfs_rq, se);
 
 	w_vruntime = key * weight;
@@ -703,7 +666,7 @@ sum_w_vruntime_add_paranoid(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	s64 key, tmp;
 
 again:
-	weight = avg_vruntime_weight(cfs_rq, se->load.weight);
+	weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);
 	key = entity_key(cfs_rq, se);
 
 	if (check_mul_overflow(key, weight, &key))
@@ -749,7 +712,7 @@ sum_w_vruntime_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 sum_w_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	unsigned long weight = avg_vruntime_weight(cfs_rq, se->load.weight);
+	unsigned long weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);
 	s64 key = entity_key(cfs_rq, se);
 
 	cfs_rq->sum_w_vruntime -= key * weight;
@@ -791,7 +754,7 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
 		s64 runtime = cfs_rq->sum_w_vruntime;
 
 		if (curr) {
-			unsigned long w = avg_vruntime_weight(cfs_rq, curr->load.weight);
+			unsigned long w = avg_vruntime_weight(cfs_rq, curr->h_load.weight);
 
 			runtime += entity_key(cfs_rq, curr) * w;
 			weight += w;
@@ -862,8 +825,6 @@ bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	u64 avruntime = avg_vruntime(cfs_rq);
 	s64 vlag = entity_lag(cfs_rq, se, avruntime);
 
-	WARN_ON_ONCE(!se->on_rq);
-
 	if (se->sched_delayed) {
 		/* previous vlag < 0 otherwise se would not be delayed */
 		vlag = max(vlag, se->vlag);
@@ -899,7 +860,7 @@ 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 = avg_vruntime_weight(cfs_rq, curr->load.weight);
+		unsigned long weight = avg_vruntime_weight(cfs_rq, curr->h_load.weight);
 
 		avg += entity_key(cfs_rq, curr) * weight;
 		load += weight;
@@ -1040,6 +1001,9 @@ RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
  */
 static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	WARN_ON_ONCE(&rq_of(cfs_rq)->cfs != cfs_rq);
+	WARN_ON_ONCE(!entity_is_task(se));
+
 	sum_w_vruntime_add(cfs_rq, se);
 	se->min_vruntime = se->vruntime;
 	se->min_slice = se->slice;
@@ -1049,6 +1013,9 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	WARN_ON_ONCE(&rq_of(cfs_rq)->cfs != cfs_rq);
+	WARN_ON_ONCE(!entity_is_task(se));
+
 	rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
 				  &min_vruntime_cb);
 	sum_w_vruntime_sub(cfs_rq, se);
@@ -1145,7 +1112,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq, bool protect)
 	 * We can safely skip eligibility check if there is only one entity
 	 * in this cfs_rq, saving some cycles.
 	 */
-	if (cfs_rq->nr_queued == 1)
+	if (cfs_rq->h_nr_queued == 1)
 		return curr && curr->on_rq ? curr : se;
 
 	/*
@@ -1395,8 +1362,6 @@ static s64 update_se(struct rq *rq, struct sched_entity *se)
 	return delta_exec;
 }
 
-static void set_next_buddy(struct sched_entity *se);
-
 #ifdef CONFIG_SCHED_CACHE
 
 /*
@@ -1991,7 +1956,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	 * not necessarily be the actual task running
 	 * (rq->curr.se). This is easy to confuse!
 	 */
-	struct sched_entity *curr = cfs_rq->curr;
+	struct sched_entity *curr = cfs_rq->h_curr;
 	struct rq *rq = rq_of(cfs_rq);
 	s64 delta_exec;
 	bool resched;
@@ -2003,26 +1968,29 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	if (unlikely(delta_exec <= 0))
 		return;
 
+	account_cfs_rq_runtime(cfs_rq, delta_exec);
+
+	if (!entity_is_task(curr))
+		return;
+
+	cfs_rq = &rq->cfs;
+
 	curr->vruntime += calc_delta_fair(delta_exec, curr);
 	resched = update_deadline(cfs_rq, curr);
 
-	if (entity_is_task(curr)) {
-		/*
-		 * If the fair_server is active, we need to account for the
-		 * fair_server time whether or not the task is running on
-		 * behalf of fair_server or not:
-		 *  - If the task is running on behalf of fair_server, we need
-		 *    to limit its time based on the assigned runtime.
-		 *  - Fair task that runs outside of fair_server should account
-		 *    against fair_server such that it can account for this time
-		 *    and possibly avoid running this period.
-		 */
-		dl_server_update(&rq->fair_server, delta_exec);
-	}
+	/*
+	 * If the fair_server is active, we need to account for the
+	 * fair_server time whether or not the task is running on
+	 * behalf of fair_server or not:
+	 *  - If the task is running on behalf of fair_server, we need
+	 *    to limit its time based on the assigned runtime.
+	 *  - Fair task that runs outside of fair_server should account
+	 *    against fair_server such that it can account for this time
+	 *    and possibly avoid running this period.
+	 */
+	dl_server_update(&rq->fair_server, delta_exec);
 
-	account_cfs_rq_runtime(cfs_rq, delta_exec);
-
-	if (cfs_rq->nr_queued == 1)
+	if (cfs_rq->h_nr_queued == 1)
 		return;
 
 	if (resched || !protect_slice(curr)) {
@@ -2033,7 +2001,10 @@ static void update_curr(struct cfs_rq *cfs_rq)
 
 static void update_curr_fair(struct rq *rq)
 {
-	update_curr(cfs_rq_of(&rq->donor->se));
+	struct sched_entity *se = &rq->donor->se;
+
+	for_each_sched_entity(se)
+		update_curr(cfs_rq_of(se));
 }
 
 static inline void
@@ -2109,7 +2080,7 @@ update_stats_enqueue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int fl
 	 * Are we enqueueing a waiting task? (for current tasks
 	 * a dequeue/enqueue event is a NOP)
 	 */
-	if (se != cfs_rq->curr)
+	if (se != cfs_rq->h_curr)
 		update_stats_wait_start_fair(cfs_rq, se);
 
 	if (flags & ENQUEUE_WAKEUP)
@@ -2127,7 +2098,7 @@ update_stats_dequeue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int fl
 	 * Mark the end of the wait period if dequeueing a
 	 * waiting task:
 	 */
-	if (se != cfs_rq->curr)
+	if (se != cfs_rq->h_curr)
 		update_stats_wait_end_fair(cfs_rq, se);
 
 	if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) {
@@ -4468,6 +4439,7 @@ static inline void update_scan_period(struct task_struct *p, int new_cpu)
 static void
 account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	WARN_ON_ONCE(cfs_rq != cfs_rq_of(se));
 	update_load_add(&cfs_rq->load, se->load.weight);
 	if (entity_is_task(se)) {
 		struct task_struct *p = task_of(se);
@@ -4483,6 +4455,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	WARN_ON_ONCE(cfs_rq != cfs_rq_of(se));
 	update_load_sub(&cfs_rq->load, se->load.weight);
 	if (entity_is_task(se)) {
 		struct task_struct *p = task_of(se);
@@ -4564,7 +4537,7 @@ dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 rescale_entity(struct sched_entity *se, unsigned long weight, bool rel_vprot)
 {
-	unsigned long old_weight = se->load.weight;
+	long old_weight = se->h_load.weight;
 
 	/*
 	 * VRUNTIME
@@ -4664,16 +4637,17 @@ rescale_entity(struct sched_entity *se, unsigned long weight, bool 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)
+static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se,
+			   unsigned long weight, bool on_rq)
 {
 	bool curr = cfs_rq->curr == se;
 	bool rel_vprot = false;
 	u64 avruntime = 0;
 
-	if (se->on_rq) {
-		/* commit outstanding execution time */
-		update_curr(cfs_rq);
+	if (se->h_load.weight == weight)
+		return;
+
+	if (on_rq) {
 		avruntime = avg_vruntime(cfs_rq);
 		se->vlag = entity_lag(cfs_rq, se, avruntime);
 		se->deadline -= avruntime;
@@ -4683,15 +4657,40 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			rel_vprot = true;
 		}
 
-		cfs_rq->nr_queued--;
+		cfs_rq->h_nr_queued--;
 		if (!curr)
 			__dequeue_entity(cfs_rq, se);
+	}
+
+	rescale_entity(se, weight, rel_vprot);
+
+	update_load_set(&se->h_load, weight);
+
+	if (on_rq) {
+		if (rel_vprot)
+			se->vprot += avruntime;
+		se->deadline += avruntime;
+		se->rel_deadline = 0;
+		se->vruntime = avruntime - se->vlag;
+
+		if (!curr)
+			__enqueue_entity(cfs_rq, se);
+		cfs_rq->h_nr_queued++;
+	}
+}
+
+static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
+			    unsigned long weight)
+{
+	if (se->load.weight == weight)
+		return;
+
+	if (se->on_rq) {
+		WARN_ON_ONCE(cfs_rq != cfs_rq_of(se));
 		update_load_sub(&cfs_rq->load, se->load.weight);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
-	rescale_entity(se, weight, rel_vprot);
-
 	update_load_set(&se->load, weight);
 
 	do {
@@ -4700,29 +4699,48 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	} while (0);
 
 	enqueue_load_avg(cfs_rq, se);
-	if (se->on_rq) {
-		if (rel_vprot)
-			se->vprot += avruntime;
-		se->deadline += avruntime;
-		se->rel_deadline = 0;
-		se->vruntime = avruntime - se->vlag;
 
+	if (se->on_rq)
 		update_load_add(&cfs_rq->load, se->load.weight);
-		if (!curr)
-			__enqueue_entity(cfs_rq, se);
-		cfs_rq->nr_queued++;
-	}
+}
+
+/*
+ * weight = NICE_0_LOAD;
+ * for_each_entity_se(se)
+ *   weight = __calc_prop_weight(cfs_rq_of(se), se, weight);
+ */
+static __always_inline
+unsigned long __calc_prop_weight(struct cfs_rq *cfs_rq, struct sched_entity *se,
+				 unsigned long weight)
+{
+	weight *= se->load.weight;
+	if (parent_entity(se))
+		weight /= cfs_rq->load.weight;
+	else
+		weight /= NICE_0_LOAD;
+
+	return max(weight, MIN_SHARES);
 }
 
 static void reweight_task_fair(struct rq *rq, struct task_struct *p,
 			       const struct load_weight *lw)
 {
 	struct sched_entity *se = &p->se;
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	struct load_weight *load = &se->load;
+	unsigned long weight = NICE_0_LOAD;
 
-	reweight_entity(cfs_rq, se, lw->weight);
-	load->inv_weight = lw->inv_weight;
+	if (se->on_rq)
+		update_curr_fair(rq);
+
+	reweight_entity(cfs_rq_of(se), se, lw->weight);
+	se->load.inv_weight = lw->inv_weight;
+
+	if (!se->on_rq)
+		return;
+
+	for_each_sched_entity(se)
+		weight = __calc_prop_weight(cfs_rq_of(se), se, weight);
+
+	reweight_eevdf(&rq->cfs, &p->se, weight, p->se.on_rq);
 }
 
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
@@ -4958,8 +4976,7 @@ static void update_cfs_group(struct sched_entity *se)
 		return;
 
 	shares = static_call(calc_group_shares)(gcfs_rq);
-	if (unlikely(se->load.weight != shares))
-		reweight_entity(cfs_rq_of(se), se, shares);
+	reweight_entity(cfs_rq_of(se), se, shares);
 }
 
 #else /* !CONFIG_FAIR_GROUP_SCHED: */
@@ -5077,7 +5094,7 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
  * differential update where we store the last value we propagated. This in
  * turn allows skipping updates if the differential is 'small'.
  *
- * Updating tg's load_avg is necessary before update_cfs_share().
+ * Updating tg's load_avg is necessary before update_cfs_group().
  */
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
 {
@@ -5545,7 +5562,7 @@ static void migrate_se_pelt_lag(struct sched_entity *se) {}
  * The cfs_rq avg is the direct sum of all its entities (blocked and runnable)
  * avg. The immediate corollary is that all (fair) tasks must be attached.
  *
- * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example.
+ * cfs_rq->avg is used for task_h_load() and update_cfs_group() for example.
  *
  * Return: true if the load decayed or we removed load.
  *
@@ -6083,6 +6100,7 @@ static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	u64 vslice, vruntime = avg_vruntime(cfs_rq);
+	unsigned int nr_queued = cfs_rq->h_nr_queued;
 	bool update_zero = false;
 	s64 lag = 0;
 
@@ -6090,6 +6108,9 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		se->slice = sysctl_sched_base_slice;
 	vslice = calc_delta_fair(se->slice, se);
 
+	if (flags & ENQUEUE_QUEUED)
+		nr_queued -= 1;
+
 	/*
 	 * Due to how V is constructed as the weighted average of entities,
 	 * adding tasks with positive lag, or removing tasks with negative lag
@@ -6098,7 +6119,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 *
 	 * EEVDF: placement strategy #1 / #2
 	 */
-	if (sched_feat(PLACE_LAG) && cfs_rq->nr_queued && se->vlag) {
+	if (sched_feat(PLACE_LAG) && nr_queued && se->vlag) {
 		struct sched_entity *curr = cfs_rq->curr;
 		long load, weight;
 
@@ -6158,9 +6179,9 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		 */
 		load = cfs_rq->sum_weight;
 		if (curr && curr->on_rq)
-			load += avg_vruntime_weight(cfs_rq, curr->load.weight);
+			load += avg_vruntime_weight(cfs_rq, curr->h_load.weight);
 
-		weight = avg_vruntime_weight(cfs_rq, se->load.weight);
+		weight = avg_vruntime_weight(cfs_rq, se->h_load.weight);
 		lag *= load + weight;
 		if (WARN_ON_ONCE(!load))
 			load = 1;
@@ -6218,23 +6239,9 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
 static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq);
 
-static void
-requeue_delayed_entity(struct sched_entity *se);
-
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
-	bool curr = cfs_rq->curr == se;
-
-	/*
-	 * If we're the current task, we must renormalise before calling
-	 * update_curr().
-	 */
-	if (curr)
-		place_entity(cfs_rq, se, flags);
-
-	update_curr(cfs_rq);
-
 	/*
 	 * When enqueuing a sched_entity, we must:
 	 *   - Update loads to have both entity and cfs_rq synced with now.
@@ -6253,13 +6260,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	update_cfs_group(se);
 
-	/*
-	 * XXX now that the entity has been re-weighted, and it's lag adjusted,
-	 * we can place the entity.
-	 */
-	if (!curr)
-		place_entity(cfs_rq, se, flags);
-
 	account_entity_enqueue(cfs_rq, se);
 
 	/* Entity has migrated, no longer consider this task hot */
@@ -6268,8 +6268,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	check_schedstat_required();
 	update_stats_enqueue_fair(cfs_rq, se, flags);
-	if (!curr)
-		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
 
 	if (cfs_rq->nr_queued == 1) {
@@ -6287,21 +6285,19 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	}
 }
 
-static void __clear_buddies_next(struct sched_entity *se)
+static void set_next_buddy(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-		if (cfs_rq->next != se)
-			break;
-
-		cfs_rq->next = NULL;
-	}
+	if (WARN_ON_ONCE(!se->on_rq || se->sched_delayed))
+		return;
+	if (se_is_idle(se))
+		return;
+	cfs_rq->next = se;
 }
 
 static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (cfs_rq->next == se)
-		__clear_buddies_next(se);
+		cfs_rq->next = NULL;
 }
 
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
@@ -6312,7 +6308,7 @@ static void set_delayed(struct sched_entity *se)
 
 	/*
 	 * Delayed se of cfs_rq have no tasks queued on them.
-	 * Do not adjust h_nr_runnable since dequeue_entities()
+	 * Do not adjust h_nr_runnable since __dequeue_task()
 	 * will account it for blocked tasks.
 	 */
 	if (!entity_is_task(se))
@@ -6345,45 +6341,16 @@ static void clear_delayed(struct sched_entity *se)
 	}
 }
 
-static bool
+static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
-	bool sleep = flags & DEQUEUE_SLEEP;
-	int action = 0;
+	int action = UPDATE_TG;
 
-	update_curr(cfs_rq);
-	clear_buddies(cfs_rq, se);
-
-	if (flags & DEQUEUE_DELAYED) {
-		WARN_ON_ONCE(!se->sched_delayed);
-	} else {
-		bool delay = sleep;
-		/*
-		 * DELAY_DEQUEUE relies on spurious wakeups, special task
-		 * states must not suffer spurious wakeups, excempt them.
-		 */
-		if (flags & (DEQUEUE_SPECIAL | DEQUEUE_THROTTLE))
-			delay = false;
-
-		WARN_ON_ONCE(delay && se->sched_delayed);
-
-		if (sched_feat(DELAY_DEQUEUE) && delay &&
-		    !entity_eligible(cfs_rq, se)) {
-			if (entity_is_task(se))
-				action |= UPDATE_UTIL_EST;
-			update_load_avg(cfs_rq, se, action);
-			update_entity_lag(cfs_rq, se);
-			set_delayed(se);
-			return false;
-		}
-	}
-
-	action = UPDATE_TG;
 	if (entity_is_task(se)) {
 		if (task_on_rq_migrating(task_of(se)))
 			action |= DO_DETACH;
 
-		if (sleep && !(flags & DEQUEUE_DELAYED))
+		if ((flags & DEQUEUE_SLEEP) && !(flags & DEQUEUE_DELAYED))
 			action |= UPDATE_UTIL_EST;
 	}
 
@@ -6401,14 +6368,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	update_stats_dequeue_fair(cfs_rq, se, flags);
 
-	update_entity_lag(cfs_rq, se);
-	if (sched_feat(PLACE_REL_DEADLINE) && !sleep) {
-		se->deadline -= se->vruntime;
-		se->rel_deadline = 1;
-	}
-
-	if (se != cfs_rq->curr)
-		__dequeue_entity(cfs_rq, se);
 	se->on_rq = 0;
 	account_entity_dequeue(cfs_rq, se);
 
@@ -6417,9 +6376,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	update_cfs_group(se);
 
-	if (flags & DEQUEUE_DELAYED)
-		clear_delayed(se);
-
 	if (cfs_rq->nr_queued == 0) {
 		update_idle_cfs_rq_clock_pelt(cfs_rq);
 #ifdef CONFIG_CFS_BANDWIDTH
@@ -6432,15 +6388,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		}
 #endif
 	}
-
-	return true;
 }
 
 static void
-set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool first)
+set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	clear_buddies(cfs_rq, se);
-
 	/* 'current' is not kept within the tree. */
 	if (se->on_rq) {
 		/*
@@ -6449,16 +6401,12 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool first)
 		 * runqueue.
 		 */
 		update_stats_wait_end_fair(cfs_rq, se);
-		__dequeue_entity(cfs_rq, se);
 		update_load_avg(cfs_rq, se, UPDATE_TG);
-
-		if (first)
-			set_protect_slice(cfs_rq, se);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
-	WARN_ON_ONCE(cfs_rq->curr);
-	cfs_rq->curr = se;
+	WARN_ON_ONCE(cfs_rq->h_curr);
+	cfs_rq->h_curr = se;
 
 	/*
 	 * Track our maximum slice length, if the CPU's load is at
@@ -6478,23 +6426,17 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool first)
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
-static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags);
+static bool __dequeue_task(struct rq *rq, struct task_struct *p, int flags);
 
-/*
- * Pick the next process, keeping these things in mind, in this order:
- * 1) keep things fair between processes/task groups
- * 2) pick the "next" process, since someone really wants that to run
- * 3) pick the "last" process, for cache locality
- * 4) do not run the "skip" process, if something else is available
- */
 static struct sched_entity *
-pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq, bool protect)
+pick_next_entity(struct rq *rq, bool protect)
 {
+	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
 
 	se = pick_eevdf(cfs_rq, protect);
 	if (se->sched_delayed) {
-		dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
+		__dequeue_task(rq, task_of(se), DEQUEUE_SLEEP | DEQUEUE_DELAYED);
 		/*
 		 * Must not reference @se again, see __block_task().
 		 */
@@ -6514,13 +6456,11 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 
 	if (prev->on_rq) {
 		update_stats_wait_start_fair(cfs_rq, prev);
-		/* Put 'current' back into the tree. */
-		__enqueue_entity(cfs_rq, prev);
 		/* in !on_rq case, update occurred at dequeue */
 		update_load_avg(cfs_rq, prev, 0);
 	}
-	WARN_ON_ONCE(cfs_rq->curr != prev);
-	cfs_rq->curr = NULL;
+	WARN_ON_ONCE(cfs_rq->h_curr != prev);
+	cfs_rq->h_curr = NULL;
 }
 
 static void
@@ -7075,7 +7015,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	assert_list_leaf_cfs_rq(rq);
 
 	/* Determine whether we need to wake up potentially idle CPU: */
-	if (rq->curr == rq->idle && rq->cfs.nr_queued)
+	if (rq->curr == rq->idle && rq->cfs.h_nr_queued)
 		resched_curr(rq);
 }
 
@@ -7410,7 +7350,7 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 		return;
 
 	/* an active group must be handled by the update_curr() path */
-	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
+	if (!cfs_rq->runtime_enabled || cfs_rq->h_curr)
 		return;
 
 	/* ensure the group is not already throttled */
@@ -7782,7 +7722,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 			resched_curr(rq);
 		return;
 	}
-	delta = (se->load.weight * vdelta) / NICE_0_LOAD;
+	delta = (se->h_load.weight * vdelta) / NICE_0_LOAD;
 
 	/*
 	 * Correct for instantaneous load of other classes.
@@ -7882,10 +7822,8 @@ static int choose_idle_cpu(int cpu, struct task_struct *p)
 }
 
 static void
-requeue_delayed_entity(struct sched_entity *se)
+requeue_delayed_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-
 	/*
 	 * se->sched_delayed should imply: se->on_rq == 1.
 	 * Because a delayed entity is one that is still on
@@ -7895,19 +7833,58 @@ requeue_delayed_entity(struct sched_entity *se)
 	WARN_ON_ONCE(!se->on_rq);
 
 	if (update_entity_lag(cfs_rq, se)) {
-		cfs_rq->nr_queued--;
+		cfs_rq->h_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++;
+		cfs_rq->h_nr_queued++;
 	}
 
 	update_load_avg(cfs_rq, se, 0);
 	clear_delayed(se);
 }
 
+static unsigned long enqueue_hierarchy(struct task_struct *p, int flags)
+{
+	unsigned long weight = NICE_0_LOAD;
+	int task_new = !(flags & ENQUEUE_WAKEUP);
+	struct sched_entity *se = &p->se;
+	int h_nr_idle = task_has_idle_policy(p);
+	int h_nr_runnable = 1;
+
+	if (task_new && se->sched_delayed)
+		h_nr_runnable = 0;
+
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+		update_curr(cfs_rq);
+
+		if (!se->on_rq) {
+			enqueue_entity(cfs_rq, se, flags);
+		} else {
+			update_load_avg(cfs_rq, se, UPDATE_TG);
+			se_update_runnable(se);
+			update_cfs_group(se);
+		}
+
+		cfs_rq->h_nr_runnable += h_nr_runnable;
+		cfs_rq->h_nr_queued++;
+		cfs_rq->h_nr_idle += h_nr_idle;
+
+		if (cfs_rq_is_idle(cfs_rq))
+			h_nr_idle = 1;
+
+		weight = __calc_prop_weight(cfs_rq, se, weight);
+
+		flags = ENQUEUE_WAKEUP;
+	}
+
+	return weight;
+}
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -7916,13 +7893,12 @@ requeue_delayed_entity(struct sched_entity *se)
 static void
 enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
-	struct cfs_rq *cfs_rq;
-	struct sched_entity *se = &p->se;
-	int h_nr_idle = task_has_idle_policy(p);
-	int h_nr_runnable = 1;
-	int task_new = !(flags & ENQUEUE_WAKEUP);
 	int rq_h_nr_queued = rq->cfs.h_nr_queued;
-	u64 slice = 0;
+	int task_new = !(flags & ENQUEUE_WAKEUP);
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = &rq->cfs;
+	unsigned long weight;
+	bool curr;
 
 	if (task_is_throttled(p) && enqueue_throttled_task(p))
 		return;
@@ -7934,10 +7910,10 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * estimated utilization, before we update schedutil.
 	 */
 	if (!p->se.sched_delayed || (flags & ENQUEUE_DELAYED))
-		util_est_enqueue(&rq->cfs, p);
+		util_est_enqueue(cfs_rq, p);
 
 	if (flags & ENQUEUE_DELAYED) {
-		requeue_delayed_entity(se);
+		requeue_delayed_entity(cfs_rq, se);
 		return;
 	}
 
@@ -7949,57 +7925,22 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (p->in_iowait)
 		cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
 
-	if (task_new && se->sched_delayed)
-		h_nr_runnable = 0;
+	/*
+	 * XXX comment on the curr thing
+	 */
+	curr = (cfs_rq->curr == se);
+	if (curr)
+		place_entity(cfs_rq, se, flags);
 
-	for_each_sched_entity(se) {
-		if (se->on_rq) {
-			if (se->sched_delayed)
-				requeue_delayed_entity(se);
-			break;
-		}
-		cfs_rq = cfs_rq_of(se);
+	if (se->on_rq && se->sched_delayed)
+		requeue_delayed_entity(cfs_rq, se);
 
-		/*
-		 * Basically set the slice of group entries to the min_slice of
-		 * their respective cfs_rq. This ensures the group can service
-		 * its entities in the desired time-frame.
-		 */
-		if (slice) {
-			se->slice = slice;
-			se->custom_slice = 1;
-		}
-		enqueue_entity(cfs_rq, se, flags);
-		slice = cfs_rq_min_slice(cfs_rq);
+	weight = enqueue_hierarchy(p, flags);
 
-		cfs_rq->h_nr_runnable += h_nr_runnable;
-		cfs_rq->h_nr_queued++;
-		cfs_rq->h_nr_idle += h_nr_idle;
-
-		if (cfs_rq_is_idle(cfs_rq))
-			h_nr_idle = 1;
-
-		flags = ENQUEUE_WAKEUP;
-	}
-
-	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
-
-		update_load_avg(cfs_rq, se, UPDATE_TG);
-		se_update_runnable(se);
-		update_cfs_group(se);
-
-		se->slice = slice;
-		if (se != cfs_rq->curr)
-			min_vruntime_cb_propagate(&se->run_node, NULL);
-		slice = cfs_rq_min_slice(cfs_rq);
-
-		cfs_rq->h_nr_runnable += h_nr_runnable;
-		cfs_rq->h_nr_queued++;
-		cfs_rq->h_nr_idle += h_nr_idle;
-
-		if (cfs_rq_is_idle(cfs_rq))
-			h_nr_idle = 1;
+	if (!curr) {
+		reweight_eevdf(cfs_rq, se, weight, false);
+		place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
+		__enqueue_entity(cfs_rq, se);
 	}
 
 	if (!rq_h_nr_queued && rq->cfs.h_nr_queued)
@@ -8030,105 +7971,109 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	hrtick_update(rq);
 }
 
-/*
- * Basically dequeue_task_fair(), except it can deal with dequeue_entity()
- * failing half-way through and resume the dequeue later.
- *
- * Returns:
- * -1 - dequeue delayed
- *  0 - dequeue throttled
- *  1 - dequeue complete
- */
-static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
+static void dequeue_hierarchy(struct task_struct *p, int flags)
 {
-	bool was_sched_idle = sched_idle_rq(rq);
+	struct sched_entity *se = &p->se;
 	bool task_sleep = flags & DEQUEUE_SLEEP;
 	bool task_delayed = flags & DEQUEUE_DELAYED;
 	bool task_throttled = flags & DEQUEUE_THROTTLE;
-	struct task_struct *p = NULL;
-	int h_nr_idle = 0;
-	int h_nr_queued = 0;
 	int h_nr_runnable = 0;
-	struct cfs_rq *cfs_rq;
-	u64 slice = 0;
+	int h_nr_idle = task_has_idle_policy(p);
+	bool dequeue = true;
 
-	if (entity_is_task(se)) {
-		p = task_of(se);
-		h_nr_queued = 1;
-		h_nr_idle = task_has_idle_policy(p);
-		if (task_sleep || task_delayed || !se->sched_delayed)
-			h_nr_runnable = 1;
-	}
+	if (task_sleep || task_delayed || !se->sched_delayed)
+		h_nr_runnable = 1;
 
 	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
-		if (!dequeue_entity(cfs_rq, se, flags)) {
-			if (p && &p->se == se)
-				return -1;
+		update_curr(cfs_rq);
 
-			slice = cfs_rq_min_slice(cfs_rq);
-			break;
+		if (dequeue) {
+			dequeue_entity(cfs_rq, se, flags);
+			/* Don't dequeue parent if it has other entities besides us */
+			if (cfs_rq->load.weight)
+				dequeue = false;
+		} else {
+			update_load_avg(cfs_rq, se, UPDATE_TG);
+			se_update_runnable(se);
+			update_cfs_group(se);
 		}
 
 		cfs_rq->h_nr_runnable -= h_nr_runnable;
-		cfs_rq->h_nr_queued -= h_nr_queued;
+		cfs_rq->h_nr_queued--;
 		cfs_rq->h_nr_idle -= h_nr_idle;
 
 		if (cfs_rq_is_idle(cfs_rq))
-			h_nr_idle = h_nr_queued;
+			h_nr_idle = 1;
 
 		if (throttled_hierarchy(cfs_rq) && task_throttled)
 			record_throttle_clock(cfs_rq);
 
-		/* Don't dequeue parent if it has other entities besides us */
-		if (cfs_rq->load.weight) {
-			slice = cfs_rq_min_slice(cfs_rq);
-
-			/* Avoid re-evaluating load for this entity: */
-			se = parent_entity(se);
-			/*
-			 * Bias pick_next to pick a task from this cfs_rq, as
-			 * p is sleeping when it is within its sched_slice.
-			 */
-			if (task_sleep && se)
-				set_next_buddy(se);
-			break;
-		}
 		flags |= DEQUEUE_SLEEP;
 		flags &= ~(DEQUEUE_DELAYED | DEQUEUE_SPECIAL);
 	}
+}
 
-	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
+/*
+ * The part of dequeue_task_fair() that is needed to dequeue delayed tasks.
+ *
+ * Returns:
+ *   true  - dequeued
+ *   false - delayed
+ */
+static bool __dequeue_task(struct rq *rq, struct task_struct *p, int flags)
+{
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = &rq->cfs;
+	bool was_sched_idle = sched_idle_rq(rq);
+	bool task_sleep = flags & DEQUEUE_SLEEP;
+	bool task_delayed = flags & DEQUEUE_DELAYED;
 
-		update_load_avg(cfs_rq, se, UPDATE_TG);
-		se_update_runnable(se);
-		update_cfs_group(se);
+	clear_buddies(cfs_rq, se);
 
-		se->slice = slice;
-		if (se != cfs_rq->curr)
-			min_vruntime_cb_propagate(&se->run_node, NULL);
-		slice = cfs_rq_min_slice(cfs_rq);
+	update_curr(cfs_rq_of(se));
+	update_entity_lag(cfs_rq, se);
 
-		cfs_rq->h_nr_runnable -= h_nr_runnable;
-		cfs_rq->h_nr_queued -= h_nr_queued;
-		cfs_rq->h_nr_idle -= h_nr_idle;
+	if (flags & DEQUEUE_DELAYED) {
+		WARN_ON_ONCE(!se->sched_delayed);
+	} else {
+		bool delay = task_sleep;
+		/*
+		 * DELAY_DEQUEUE relies on spurious wakeups, special task
+		 * states must not suffer spurious wakeups, excempt them.
+		 */
+		if (flags & (DEQUEUE_SPECIAL | DEQUEUE_THROTTLE))
+			delay = false;
 
-		if (cfs_rq_is_idle(cfs_rq))
-			h_nr_idle = h_nr_queued;
+		WARN_ON_ONCE(delay && se->sched_delayed);
 
-		if (throttled_hierarchy(cfs_rq) && task_throttled)
-			record_throttle_clock(cfs_rq);
+		if (sched_feat(DELAY_DEQUEUE) && delay &&
+		    !entity_eligible(cfs_rq, se)) {
+			update_load_avg(cfs_rq_of(se), se, UPDATE_UTIL_EST);
+			set_delayed(se);
+			return false;
+		}
 	}
 
-	sub_nr_running(rq, h_nr_queued);
+	dequeue_hierarchy(p, flags);
+
+	if (sched_feat(PLACE_REL_DEADLINE) && !task_sleep) {
+		se->deadline -= se->vruntime;
+		se->rel_deadline = 1;
+	}
+	if (se != cfs_rq->curr)
+		__dequeue_entity(cfs_rq, se);
+
+	sub_nr_running(rq, 1);
 
 	/* balance early to pull high priority tasks */
 	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
 		rq->next_balance = jiffies;
 
-	if (p && task_delayed) {
+	if (task_delayed) {
+		clear_delayed(se);
+
 		WARN_ON_ONCE(!task_sleep);
 		WARN_ON_ONCE(p->on_rq != 1);
 
@@ -8140,7 +8085,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		__block_task(rq, p);
 	}
 
-	return 1;
+	return true;
 }
 
 /*
@@ -8158,11 +8103,11 @@ static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (!p->se.sched_delayed)
 		util_est_dequeue(&rq->cfs, p);
 
-	if (dequeue_entities(rq, &p->se, flags) < 0)
+	if (!__dequeue_task(rq, p, flags))
 		return false;
 
 	/*
-	 * Must not reference @p after dequeue_entities(DEQUEUE_DELAYED).
+	 * Must not reference @p after __dequeue_task(DEQUEUE_DELAYED).
 	 */
 	return true;
 }
@@ -9757,19 +9702,6 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 static void task_dead_fair(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
-
-	if (se->sched_delayed) {
-		struct rq_flags rf;
-		struct rq *rq;
-
-		rq = task_rq_lock(p, &rf);
-		if (se->sched_delayed) {
-			update_rq_clock(rq);
-			dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
-		}
-		task_rq_unlock(rq, p, &rf);
-	}
-
 	remove_entity_load_avg(se);
 }
 
@@ -9803,21 +9735,10 @@ static void set_cpus_allowed_fair(struct task_struct *p, struct affinity_context
 	set_task_max_allowed_capacity(p);
 }
 
-static void set_next_buddy(struct sched_entity *se)
-{
-	for_each_sched_entity(se) {
-		if (WARN_ON_ONCE(!se->on_rq))
-			return;
-		if (se_is_idle(se))
-			return;
-		cfs_rq_of(se)->next = se;
-	}
-}
-
 enum preempt_wakeup_action {
 	PREEMPT_WAKEUP_NONE,	/* No preemption. */
 	PREEMPT_WAKEUP_SHORT,	/* Ignore slice protection. */
-	PREEMPT_WAKEUP_PICK,	/* Let __pick_eevdf() decide. */
+	PREEMPT_WAKEUP_PICK,	/* Let pick_eevdf() decide. */
 	PREEMPT_WAKEUP_RESCHED,	/* Force reschedule. */
 };
 
@@ -9834,7 +9755,7 @@ set_preempt_buddy(struct cfs_rq *cfs_rq, int wake_flags,
 	if (cfs_rq->next && entity_before(cfs_rq->next, pse))
 		return false;
 
-	set_next_buddy(pse);
+	set_next_buddy(cfs_rq, pse);
 	return true;
 }
 
@@ -9887,7 +9808,7 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
 	enum preempt_wakeup_action preempt_action = PREEMPT_WAKEUP_PICK;
 	struct task_struct *donor = rq->donor;
 	struct sched_entity *nse, *se = &donor->se, *pse = &p->se;
-	struct cfs_rq *cfs_rq = task_cfs_rq(donor);
+	struct cfs_rq *cfs_rq = &rq->cfs;
 	int cse_is_idle, pse_is_idle;
 
 	/*
@@ -9925,7 +9846,6 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
 	if (!sched_feat(WAKEUP_PREEMPTION))
 		return;
 
-	find_matching_se(&se, &pse);
 	WARN_ON_ONCE(!pse);
 
 	cse_is_idle = se_is_idle(se);
@@ -9953,8 +9873,7 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
 	if (unlikely(!normal_policy(p->policy)))
 		return;
 
-	cfs_rq = cfs_rq_of(se);
-	update_curr(cfs_rq);
+	update_curr_fair(rq);
 	/*
 	 * If @p has a shorter slice than current and @p is eligible, override
 	 * current's slice protection in order to allow preemption.
@@ -9998,18 +9917,15 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
 	}
 
 pick:
-	nse = pick_next_entity(rq, cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT);
-	/* If @p has become the most eligible task, force preemption */
-	if (nse == pse)
-		goto preempt;
+	if (cfs_rq->h_nr_queued) {
+		nse = pick_next_entity(rq, preempt_action != PREEMPT_WAKEUP_SHORT);
+		if (unlikely(!nse))
+			goto pick;
 
-	/*
-	 * Because p is enqueued, nse being null can only mean that we
-	 * dequeued a delayed task. If there are still entities queued in
-	 * cfs, check if the next one will be p.
-	 */
-	if (!nse && cfs_rq->nr_queued)
-		goto pick;
+		/* If @p has become the most eligible task, force preemption */
+		if (nse == pse)
+			goto preempt;
+	}
 
 	if (sched_feat(RUN_TO_PARITY))
 		update_protect_slice(cfs_rq, se);
@@ -10028,33 +9944,24 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
 struct task_struct *pick_task_fair(struct rq *rq, struct rq_flags *rf)
 	__must_hold(__rq_lockp(rq))
 {
+	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
-	struct cfs_rq *cfs_rq;
 	struct task_struct *p;
-	bool throttled;
 	int new_tasks;
 
 again:
-	cfs_rq = &rq->cfs;
-	if (!cfs_rq->nr_queued)
+	if (!cfs_rq->h_nr_queued)
 		goto idle;
 
-	throttled = false;
+	/* Might not have done put_prev_entity() */
+	if (cfs_rq->curr && cfs_rq->curr->on_rq)
+		update_curr(cfs_rq);
 
-	do {
-		/* Might not have done put_prev_entity() */
-		if (cfs_rq->curr && cfs_rq->curr->on_rq)
-			update_curr(cfs_rq);
-
-		se = pick_next_entity(rq, cfs_rq, true);
-		if (!se)
-			goto again;
-		cfs_rq = group_cfs_rq(se);
-	} while (cfs_rq);
+	se = pick_next_entity(rq, true);
+	if (!se)
+		goto again;
 
 	p = task_of(se);
-	if (unlikely(throttled))
-		task_throttle_setup_work(p);
 	return p;
 
 idle:
@@ -10091,7 +9998,7 @@ void fair_server_init(struct rq *rq)
 static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct task_struct *next)
 {
 	struct sched_entity *se = &prev->se;
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *nse = NULL;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -10101,7 +10008,7 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct t
 
 	while (se) {
 		cfs_rq = cfs_rq_of(se);
-		if (!nse || cfs_rq->curr)
+		if (!nse || cfs_rq->h_curr)
 			put_prev_entity(cfs_rq, se);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		if (nse) {
@@ -10120,6 +10027,14 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct t
 #endif
 		se = parent_entity(se);
 	}
+
+	/* Put 'current' back into the tree. */
+	cfs_rq = &rq->cfs;
+	se = &prev->se;
+	WARN_ON_ONCE(cfs_rq->curr != se);
+	cfs_rq->curr = NULL;
+	if (se->on_rq)
+		__enqueue_entity(cfs_rq, se);
 }
 
 /*
@@ -10128,8 +10043,8 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct t
 static void yield_task_fair(struct rq *rq)
 {
 	struct task_struct *curr = rq->donor;
-	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	struct sched_entity *se = &curr->se;
+	struct cfs_rq *cfs_rq = &rq->cfs;
 
 	/*
 	 * Are we the only task in the tree?
@@ -10170,11 +10085,11 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p)
 	struct sched_entity *se = &p->se;
 
 	/* !se->on_rq also covers throttled task */
-	if (!se->on_rq)
+	if (!se->on_rq || se->sched_delayed)
 		return false;
 
 	/* Tell the scheduler that we'd really like se to run next. */
-	set_next_buddy(se);
+	set_next_buddy(&task_rq(p)->cfs, se);
 
 	yield_task_fair(rq);
 
@@ -10513,15 +10428,10 @@ static inline long migrate_degrades_locality(struct task_struct *p,
  */
 static inline int task_is_ineligible_on_dst_cpu(struct task_struct *p, int dest_cpu)
 {
-	struct cfs_rq *dst_cfs_rq;
+	struct cfs_rq *dst_cfs_rq = &cpu_rq(dest_cpu)->cfs;
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	dst_cfs_rq = tg_cfs_rq(task_group(p), dest_cpu);
-#else
-	dst_cfs_rq = &cpu_rq(dest_cpu)->cfs;
-#endif
-	if (sched_feat(PLACE_LAG) && dst_cfs_rq->nr_queued &&
-	    !entity_eligible(task_cfs_rq(p), &p->se))
+	if (sched_feat(PLACE_LAG) && dst_cfs_rq->h_nr_queued &&
+	    !entity_eligible(&task_rq(p)->cfs, &p->se))
 		return 1;
 
 	return 0;
@@ -11304,7 +11214,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 	while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) {
 		load = cfs_rq->h_load;
 		load = div64_ul(load * se->avg.load_avg,
-			cfs_rq_load_avg(cfs_rq) + 1);
+				cfs_rq_load_avg(cfs_rq) + 1);
 		cfs_rq = group_cfs_rq(se);
 		cfs_rq->h_load = load;
 		cfs_rq->last_h_load_update = now;
@@ -14696,7 +14606,7 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr)
 	 * MIN_NR_TASKS_DURING_FORCEIDLE - 1 tasks and use that to check
 	 * if we need to give up the CPU.
 	 */
-	if (rq->core->core_forceidle_count && rq->cfs.nr_queued == 1 &&
+	if (rq->core->core_forceidle_count && rq->cfs.h_nr_queued == 1 &&
 	    __entity_slice_used(&curr->se, MIN_NR_TASKS_DURING_FORCEIDLE))
 		resched_curr(rq);
 }
@@ -14905,30 +14815,8 @@ bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b,
 
 	WARN_ON_ONCE(task_rq(b)->core != rq->core);
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	/*
-	 * Find an se in the hierarchy for tasks a and b, such that the se's
-	 * are immediate siblings.
-	 */
-	while (sea->cfs_rq->tg != seb->cfs_rq->tg) {
-		int sea_depth = sea->depth;
-		int seb_depth = seb->depth;
-
-		if (sea_depth >= seb_depth)
-			sea = parent_entity(sea);
-		if (sea_depth <= seb_depth)
-			seb = parent_entity(seb);
-	}
-
-	se_fi_update(sea, rq->core->core_forceidle_seq, in_fi);
-	se_fi_update(seb, rq->core->core_forceidle_seq, in_fi);
-
-	cfs_rqa = sea->cfs_rq;
-	cfs_rqb = seb->cfs_rq;
-#else /* !CONFIG_FAIR_GROUP_SCHED: */
 	cfs_rqa = &task_rq(a)->cfs;
 	cfs_rqb = &task_rq(b)->cfs;
-#endif /* !CONFIG_FAIR_GROUP_SCHED */
 
 	/*
 	 * Find delta after normalizing se's vruntime with its cfs_rq's
@@ -14967,11 +14855,20 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) {}
 static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 {
 	struct sched_entity *se = &curr->se;
-	struct cfs_rq *cfs_rq;
 
-	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
-		entity_tick(cfs_rq, se, queued);
+	if (se->on_rq) {
+		unsigned long weight = NICE_0_LOAD;
+		struct cfs_rq *cfs_rq;
+
+		for_each_sched_entity(se) {
+			cfs_rq = cfs_rq_of(se);
+			entity_tick(cfs_rq, se, queued);
+
+			weight = __calc_prop_weight(cfs_rq, se, weight);
+		}
+
+		se = &curr->se;
+		reweight_eevdf(cfs_rq, se, weight, se->on_rq);
 	}
 
 	if (queued)
@@ -15011,7 +14908,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, u64 oldprio)
 	if (p->prio == oldprio)
 		return;
 
-	if (rq->cfs.nr_queued == 1)
+	if (rq->cfs.h_nr_queued == 1)
 		return;
 
 	/*
@@ -15140,33 +15037,44 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
 	}
 }
 
-/*
- * Account for a task changing its policy or group.
- *
- * This routine is mostly called to set cfs_rq->curr field when a task
- * migrates between groups/classes.
- */
 static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 {
 	struct sched_entity *se = &p->se;
 	bool throttled = false;
+	struct cfs_rq *cfs_rq = &rq->cfs;
+	unsigned long weight = NICE_0_LOAD;
+	bool on_rq = se->on_rq;
+
+	clear_buddies(cfs_rq, se);
+
+	if (on_rq)
+		__dequeue_entity(cfs_rq, se);
 
 	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		cfs_rq = cfs_rq_of(se);
 
-		if (IS_ENABLED(CONFIG_FAIR_GROUP_SCHED) &&
-		    first && cfs_rq->curr)
-			break;
+		if (!IS_ENABLED(CONFIG_FAIR_GROUP_SCHED) ||
+		    !first || !cfs_rq->h_curr)
+			set_next_entity(cfs_rq, se);
 
-		set_next_entity(cfs_rq, se, first);
 		/* ensure bandwidth has been allocated on our new cfs_rq */
 		throttled |= account_cfs_rq_runtime(cfs_rq, 0);
+
+		if (on_rq)
+			weight = __calc_prop_weight(cfs_rq, se, weight);
 	}
 
 	if (throttled)
 		task_throttle_setup_work(p);
 
 	se = &p->se;
+	cfs_rq->curr = se;
+
+	if (on_rq) {
+		reweight_eevdf(cfs_rq, se, weight, se->on_rq);
+		if (first)
+			set_protect_slice(cfs_rq, se);
+	}
 
 	if (task_on_rq_queued(p)) {
 		/*
@@ -15279,17 +15187,8 @@ void unregister_fair_sched_group(struct task_group *tg)
 		struct sched_entity *se = tg_se(tg, cpu);
 		struct rq *rq = cpu_rq(cpu);
 
-		if (se) {
-			if (se->sched_delayed) {
-				guard(rq_lock_irqsave)(rq);
-				if (se->sched_delayed) {
-					update_rq_clock(rq);
-					dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
-				}
-				list_del_leaf_cfs_rq(cfs_rq);
-			}
+		if (se)
 			remove_entity_load_avg(se);
-		}
 
 		/*
 		 * Only empty task groups can be destroyed; so we can speculatively
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index 897790889ba3..779eb58a4261 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -206,7 +206,7 @@ ___update_load_sum(u64 now, struct sched_avg *sa,
 	/*
 	 * running is a subset of runnable (weight) so running can't be set if
 	 * runnable is clear. But there are some corner cases where the current
-	 * se has been already dequeued but cfs_rq->curr still points to it.
+	 * se has been already dequeued but cfs_rq->h_curr still points to it.
 	 * This means that weight will be 0 but not running for a sched_entity
 	 * but also for a cfs_rq if the latter becomes idle. As an example,
 	 * this happens during sched_balance_newidle() which calls
@@ -307,7 +307,7 @@ int __update_load_avg_blocked_se(u64 now, struct sched_entity *se)
 int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (___update_load_sum(now, &se->avg, !!se->on_rq, se_runnable(se),
-				cfs_rq->curr == se)) {
+				cfs_rq->h_curr == se)) {
 
 		___update_load_avg(&se->avg, se_weight(se));
 		cfs_se_util_change(&se->avg);
@@ -323,7 +323,7 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq)
 	if (___update_load_sum(now, &cfs_rq->avg,
 				scale_load_down(cfs_rq->load.weight),
 				cfs_rq->h_nr_runnable,
-				cfs_rq->curr != NULL)) {
+				cfs_rq->h_curr != NULL)) {
 
 		___update_load_avg(&cfs_rq->avg, 1);
 		trace_pelt_cfs_tp(cfs_rq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fd267bfd51af..e20823fbd2b8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -530,21 +530,8 @@ struct task_group {
 
 };
 
-#ifdef CONFIG_GROUP_SCHED_WEIGHT
 #define ROOT_TASK_GROUP_LOAD	NICE_0_LOAD
 
-/*
- * A weight of 0 or 1 can cause arithmetics problems.
- * A weight of a cfs_rq is the sum of weights of which entities
- * are queued on this cfs_rq, so a weight of a entity should not be
- * too large, so as the shares value of a task group.
- * (The default weight is 1024 - so there's no practical
- *  limitation from this.)
- */
-#define MIN_SHARES		(1UL <<  1)
-#define MAX_SHARES		(1UL << 18)
-#endif
-
 typedef int (*tg_visitor)(struct task_group *, void *);
 
 extern int walk_tg_tree_from(struct task_group *from,
@@ -631,6 +618,17 @@ static inline bool cfs_task_bw_constrained(struct task_struct *p) { return false
 
 #endif /* !CONFIG_CGROUP_SCHED */
 
+/*
+ * A weight of 0 or 1 can cause arithmetics problems.
+ * A weight of a cfs_rq is the sum of weights of which entities
+ * are queued on this cfs_rq, so a weight of a entity should not be
+ * too large, so as the shares value of a task group.
+ * (The default weight is 1024 - so there's no practical
+ *  limitation from this.)
+ */
+#define MIN_SHARES		(1UL <<  1)
+#define MAX_SHARES		(1UL << 18)
+
 extern void unregister_rt_sched_group(struct task_group *tg);
 extern void free_rt_sched_group(struct task_group *tg);
 extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
@@ -709,6 +707,7 @@ struct cfs_rq {
 	/*
 	 * CFS load tracking
 	 */
+	struct sched_entity	*h_curr;
 	struct sched_avg	avg;
 #ifndef CONFIG_64BIT
 	u64			last_update_time_copy;
@@ -2575,6 +2574,7 @@ extern const u32		sched_prio_to_wmult[40];
 #define ENQUEUE_MIGRATED	0x00040000
 #define ENQUEUE_INITIAL		0x00080000
 #define ENQUEUE_RQ_SELECTED	0x00100000
+#define ENQUEUE_QUEUED		0x00200000
 
 #define RETRY_TASK		((void *)-1UL)