Merge tag 'sched-core-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Implement the SCHED_DEADLINE server infrastructure - Daniel Bristot
   de Oliveira's last major contribution to the kernel:

     "SCHED_DEADLINE servers can help fixing starvation issues of low
      priority tasks (e.g., SCHED_OTHER) when higher priority tasks
      monopolize CPU cycles. Today we have RT Throttling; DEADLINE
      servers should be able to replace and improve that."

   (Daniel Bristot de Oliveira, Peter Zijlstra, Joel Fernandes, Youssef
   Esmat, Huang Shijie)

 - Preparatory changes for sched_ext integration:
     - Use set_next_task(.first) where required
     - Fix up set_next_task() implementations
     - Clean up DL server vs. core sched
     - Split up put_prev_task_balance()
     - Rework pick_next_task()
     - Combine the last put_prev_task() and the first set_next_task()
     - Rework dl_server
     - Add put_prev_task(.next)

   (Peter Zijlstra, with a fix by Tejun Heo)

 - Complete the EEVDF transition and refine EEVDF scheduling:
     - Implement delayed dequeue
     - Allow shorter slices to wakeup-preempt
     - Use sched_attr::sched_runtime to set request/slice suggestion
     - Document the new feature flags
     - Remove unused and duplicate-functionality fields
     - Simplify & unify pick_next_task_fair()
     - Misc debuggability enhancements

   (Peter Zijlstra, with fixes/cleanups by Dietmar Eggemann, Valentin
   Schneider and Chuyi Zhou)

 - Initialize the vruntime of a new task when it is first enqueued,
   resulting in significant decrease in latency of newly woken tasks
   (Zhang Qiao)

 - Introduce SM_IDLE and an idle re-entry fast-path in __schedule()
   (K Prateek Nayak, Peter Zijlstra)

 - Clean up and clarify the usage of Clean up usage of rt_task()
   (Qais Yousef)

 - Preempt SCHED_IDLE entities in strict cgroup hierarchies
   (Tianchen Ding)

 - Clarify the documentation of time units for deadline scheduler
   parameters (Christian Loehle)

 - Remove the HZ_BW chicken-bit feature flag introduced a year ago,
   the original change seems to be working fine (Phil Auld)

 - Misc fixes and cleanups (Chen Yu, Dan Carpenter, Huang Shijie,
   Peilin He, Qais Yousefm and Vincent Guittot)

* tag 'sched-core-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  sched/cpufreq: Use NSEC_PER_MSEC for deadline task
  cpufreq/cppc: Use NSEC_PER_MSEC for deadline task
  sched/deadline: Clarify nanoseconds in uapi
  sched/deadline: Convert schedtool example to chrt
  sched/debug: Fix the runnable tasks output
  sched: Fix sched_delayed vs sched_core
  kernel/sched: Fix util_est accounting for DELAY_DEQUEUE
  kthread: Fix task state in kthread worker if being frozen
  sched/pelt: Use rq_clock_task() for hw_pressure
  sched/fair: Move effective_cpu_util() and effective_cpu_util() in fair.c
  sched/core: Introduce SM_IDLE and an idle re-entry fast-path in __schedule()
  sched: Add put_prev_task(.next)
  sched: Rework dl_server
  sched: Combine the last put_prev_task() and the first set_next_task()
  sched: Rework pick_next_task()
  sched: Split up put_prev_task_balance()
  sched: Clean up DL server vs core sched
  sched: Fixup set_next_task() implementations
  sched: Use set_next_task(.first) where required
  sched/fair: Properly deactivate sched_delayed task upon class change
  ...

12 files changed, 1600 insertions, 700 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1d7f5941bcdc..a7af49b3a337 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -163,7 +163,10 @@ static inline int __task_prio(const struct task_struct *p)
 	if (p->sched_class == &stop_sched_class) /* trumps deadline */
 		return -2;
 
-	if (rt_prio(p->prio)) /* includes deadline */
+	if (p->dl_server)
+		return -1; /* deadline */
+
+	if (rt_or_dl_prio(p->prio))
 		return p->prio; /* [-1, 99] */
 
 	if (p->sched_class == &idle_sched_class)
@@ -192,8 +195,24 @@ static inline bool prio_less(const struct task_struct *a,
 	if (-pb < -pa)
 		return false;
 
-	if (pa == -1) /* dl_prio() doesn't work because of stop_class above */
-		return !dl_time_before(a->dl.deadline, b->dl.deadline);
+	if (pa == -1) { /* dl_prio() doesn't work because of stop_class above */
+		const struct sched_dl_entity *a_dl, *b_dl;
+
+		a_dl = &a->dl;
+		/*
+		 * Since,'a' and 'b' can be CFS tasks served by DL server,
+		 * __task_prio() can return -1 (for DL) even for those. In that
+		 * case, get to the dl_server's DL entity.
+		 */
+		if (a->dl_server)
+			a_dl = a->dl_server;
+
+		b_dl = &b->dl;
+		if (b->dl_server)
+			b_dl = b->dl_server;
+
+		return !dl_time_before(a_dl->deadline, b_dl->deadline);
+	}
 
 	if (pa == MAX_RT_PRIO + MAX_NICE)	/* fair */
 		return cfs_prio_less(a, b, in_fi);
@@ -240,6 +259,9 @@ static inline int rb_sched_core_cmp(const void *key, const struct rb_node *node)
 
 void sched_core_enqueue(struct rq *rq, struct task_struct *p)
 {
+	if (p->se.sched_delayed)
+		return;
+
 	rq->core->core_task_seq++;
 
 	if (!p->core_cookie)
@@ -250,6 +272,9 @@ void sched_core_enqueue(struct rq *rq, struct task_struct *p)
 
 void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags)
 {
+	if (p->se.sched_delayed)
+		return;
+
 	rq->core->core_task_seq++;
 
 	if (sched_core_enqueued(p)) {
@@ -1269,7 +1294,7 @@ bool sched_can_stop_tick(struct rq *rq)
 	 * dequeued by migrating while the constrained task continues to run.
 	 * E.g. going from 2->1 without going through pick_next_task().
 	 */
-	if (sched_feat(HZ_BW) && __need_bw_check(rq, rq->curr)) {
+	if (__need_bw_check(rq, rq->curr)) {
 		if (cfs_task_bw_constrained(rq->curr))
 			return false;
 	}
@@ -1672,6 +1697,9 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
+	if (p->se.sched_delayed)
+		return;
+
 	for_each_clamp_id(clamp_id)
 		uclamp_rq_inc_id(rq, p, clamp_id);
 
@@ -1696,6 +1724,9 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
+	if (p->se.sched_delayed)
+		return;
+
 	for_each_clamp_id(clamp_id)
 		uclamp_rq_dec_id(rq, p, clamp_id);
 }
@@ -1975,14 +2006,21 @@ void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 		psi_enqueue(p, (flags & ENQUEUE_WAKEUP) && !(flags & ENQUEUE_MIGRATED));
 	}
 
-	uclamp_rq_inc(rq, p);
 	p->sched_class->enqueue_task(rq, p, flags);
+	/*
+	 * Must be after ->enqueue_task() because ENQUEUE_DELAYED can clear
+	 * ->sched_delayed.
+	 */
+	uclamp_rq_inc(rq, p);
 
 	if (sched_core_enabled(rq))
 		sched_core_enqueue(rq, p);
 }
 
-void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
+/*
+ * Must only return false when DEQUEUE_SLEEP.
+ */
+inline bool dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (sched_core_enabled(rq))
 		sched_core_dequeue(rq, p, flags);
@@ -1995,8 +2033,12 @@ void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 		psi_dequeue(p, flags & DEQUEUE_SLEEP);
 	}
 
+	/*
+	 * Must be before ->dequeue_task() because ->dequeue_task() can 'fail'
+	 * and mark the task ->sched_delayed.
+	 */
 	uclamp_rq_dec(rq, p);
-	p->sched_class->dequeue_task(rq, p, flags);
+	return p->sched_class->dequeue_task(rq, p, flags);
 }
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
@@ -2014,12 +2056,25 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	WRITE_ONCE(p->on_rq, (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING);
+	SCHED_WARN_ON(flags & DEQUEUE_SLEEP);
+
+	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
 	ASSERT_EXCLUSIVE_WRITER(p->on_rq);
 
+	/*
+	 * Code explicitly relies on TASK_ON_RQ_MIGRATING begin set *before*
+	 * dequeue_task() and cleared *after* enqueue_task().
+	 */
+
 	dequeue_task(rq, p, flags);
 }
 
+static void block_task(struct rq *rq, struct task_struct *p, int flags)
+{
+	if (dequeue_task(rq, p, DEQUEUE_SLEEP | flags))
+		__block_task(rq, p);
+}
+
 /**
  * task_curr - is this task currently executing on a CPU?
  * @p: the task in question.
@@ -2233,6 +2288,12 @@ void migrate_disable(void)
 	struct task_struct *p = current;
 
 	if (p->migration_disabled) {
+#ifdef CONFIG_DEBUG_PREEMPT
+		/*
+		 *Warn about overflow half-way through the range.
+		 */
+		WARN_ON_ONCE((s16)p->migration_disabled < 0);
+#endif
 		p->migration_disabled++;
 		return;
 	}
@@ -2251,14 +2312,20 @@ void migrate_enable(void)
 		.flags     = SCA_MIGRATE_ENABLE,
 	};
 
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Check both overflow from migrate_disable() and superfluous
+	 * migrate_enable().
+	 */
+	if (WARN_ON_ONCE((s16)p->migration_disabled <= 0))
+		return;
+#endif
+
 	if (p->migration_disabled > 1) {
 		p->migration_disabled--;
 		return;
 	}
 
-	if (WARN_ON_ONCE(!p->migration_disabled))
-		return;
-
 	/*
 	 * Ensure stop_task runs either before or after this, and that
 	 * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
@@ -3607,8 +3674,6 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		rq->idle_stamp = 0;
 	}
 #endif
-
-	p->dl_server = NULL;
 }
 
 /*
@@ -3644,12 +3709,14 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
 
 	rq = __task_rq_lock(p, &rf);
 	if (task_on_rq_queued(p)) {
+		update_rq_clock(rq);
+		if (p->se.sched_delayed)
+			enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED);
 		if (!task_on_cpu(rq, p)) {
 			/*
 			 * When on_rq && !on_cpu the task is preempted, see if
 			 * it should preempt the task that is current now.
 			 */
-			update_rq_clock(rq);
 			wakeup_preempt(rq, p, wake_flags);
 		}
 		ttwu_do_wakeup(p);
@@ -4029,11 +4096,16 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 * case the whole 'p->on_rq && ttwu_runnable()' case below
 		 * without taking any locks.
 		 *
+		 * Specifically, given current runs ttwu() we must be before
+		 * schedule()'s block_task(), as such this must not observe
+		 * sched_delayed.
+		 *
 		 * In particular:
 		 *  - we rely on Program-Order guarantees for all the ordering,
 		 *  - we're serialized against set_special_state() by virtue of
 		 *    it disabling IRQs (this allows not taking ->pi_lock).
 		 */
+		SCHED_WARN_ON(p->se.sched_delayed);
 		if (!ttwu_state_match(p, state, &success))
 			goto out;
 
@@ -4322,9 +4394,11 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.nr_migrations		= 0;
 	p->se.vruntime			= 0;
 	p->se.vlag			= 0;
-	p->se.slice			= sysctl_sched_base_slice;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+	/* A delayed task cannot be in clone(). */
+	SCHED_WARN_ON(p->se.sched_delayed);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	p->se.cfs_rq			= NULL;
 #endif
@@ -4572,6 +4646,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 		p->prio = p->normal_prio = p->static_prio;
 		set_load_weight(p, false);
+		p->se.custom_slice = 0;
+		p->se.slice = sysctl_sched_base_slice;
 
 		/*
 		 * We don't need the reset flag anymore after the fork. It has
@@ -4686,7 +4762,7 @@ void wake_up_new_task(struct task_struct *p)
 	update_rq_clock(rq);
 	post_init_entity_util_avg(p);
 
-	activate_task(rq, p, ENQUEUE_NOCLOCK);
+	activate_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_INITIAL);
 	trace_sched_wakeup_new(p);
 	wakeup_preempt(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
@@ -5769,8 +5845,8 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
 	schedstat_inc(this_rq()->sched_count);
 }
 
-static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
-				  struct rq_flags *rf)
+static void prev_balance(struct rq *rq, struct task_struct *prev,
+			 struct rq_flags *rf)
 {
 #ifdef CONFIG_SMP
 	const struct sched_class *class;
@@ -5787,8 +5863,6 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
 			break;
 	}
 #endif
-
-	put_prev_task(rq, prev);
 }
 
 /*
@@ -5800,6 +5874,8 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	const struct sched_class *class;
 	struct task_struct *p;
 
+	rq->dl_server = NULL;
+
 	/*
 	 * Optimization: we know that if all tasks are in the fair class we can
 	 * call that function directly, but only if the @prev task wasn't of a
@@ -5815,35 +5891,28 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		/* Assume the next prioritized class is idle_sched_class */
 		if (!p) {
-			put_prev_task(rq, prev);
-			p = pick_next_task_idle(rq);
+			p = pick_task_idle(rq);
+			put_prev_set_next_task(rq, prev, p);
 		}
 
-		/*
-		 * This is the fast path; it cannot be a DL server pick;
-		 * therefore even if @p == @prev, ->dl_server must be NULL.
-		 */
-		if (p->dl_server)
-			p->dl_server = NULL;
-
 		return p;
 	}
 
 restart:
-	put_prev_task_balance(rq, prev, rf);
-
-	/*
-	 * We've updated @prev and no longer need the server link, clear it.
-	 * Must be done before ->pick_next_task() because that can (re)set
-	 * ->dl_server.
-	 */
-	if (prev->dl_server)
-		prev->dl_server = NULL;
+	prev_balance(rq, prev, rf);
 
 	for_each_class(class) {
-		p = class->pick_next_task(rq);
-		if (p)
-			return p;
+		if (class->pick_next_task) {
+			p = class->pick_next_task(rq, prev);
+			if (p)
+				return p;
+		} else {
+			p = class->pick_task(rq);
+			if (p) {
+				put_prev_set_next_task(rq, prev, p);
+				return p;
+			}
+		}
 	}
 
 	BUG(); /* The idle class should always have a runnable task. */
@@ -5873,6 +5942,8 @@ static inline struct task_struct *pick_task(struct rq *rq)
 	const struct sched_class *class;
 	struct task_struct *p;
 
+	rq->dl_server = NULL;
+
 	for_each_class(class) {
 		p = class->pick_task(rq);
 		if (p)
@@ -5911,6 +5982,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		 * another cpu during offline.
 		 */
 		rq->core_pick = NULL;
+		rq->core_dl_server = NULL;
 		return __pick_next_task(rq, prev, rf);
 	}
 
@@ -5929,16 +6001,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		WRITE_ONCE(rq->core_sched_seq, rq->core->core_pick_seq);
 
 		next = rq->core_pick;
-		if (next != prev) {
-			put_prev_task(rq, prev);
-			set_next_task(rq, next);
-		}
-
+		rq->dl_server = rq->core_dl_server;
 		rq->core_pick = NULL;
-		goto out;
+		rq->core_dl_server = NULL;
+		goto out_set_next;
 	}
 
-	put_prev_task_balance(rq, prev, rf);
+	prev_balance(rq, prev, rf);
 
 	smt_mask = cpu_smt_mask(cpu);
 	need_sync = !!rq->core->core_cookie;
@@ -5979,6 +6048,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		next = pick_task(rq);
 		if (!next->core_cookie) {
 			rq->core_pick = NULL;
+			rq->core_dl_server = NULL;
 			/*
 			 * For robustness, update the min_vruntime_fi for
 			 * unconstrained picks as well.
@@ -6006,7 +6076,9 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		if (i != cpu && (rq_i != rq->core || !core_clock_updated))
 			update_rq_clock(rq_i);
 
-		p = rq_i->core_pick = pick_task(rq_i);
+		rq_i->core_pick = p = pick_task(rq_i);
+		rq_i->core_dl_server = rq_i->dl_server;
+
 		if (!max || prio_less(max, p, fi_before))
 			max = p;
 	}
@@ -6030,6 +6102,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		}
 
 		rq_i->core_pick = p;
+		rq_i->core_dl_server = NULL;
 
 		if (p == rq_i->idle) {
 			if (rq_i->nr_running) {
@@ -6090,6 +6163,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		if (i == cpu) {
 			rq_i->core_pick = NULL;
+			rq_i->core_dl_server = NULL;
 			continue;
 		}
 
@@ -6098,6 +6172,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		if (rq_i->curr == rq_i->core_pick) {
 			rq_i->core_pick = NULL;
+			rq_i->core_dl_server = NULL;
 			continue;
 		}
 
@@ -6105,8 +6180,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	}
 
 out_set_next:
-	set_next_task(rq, next);
-out:
+	put_prev_set_next_task(rq, prev, next);
 	if (rq->core->core_forceidle_count && next == rq->idle)
 		queue_core_balance(rq);
 
@@ -6342,19 +6416,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  * Constants for the sched_mode argument of __schedule().
  *
  * The mode argument allows RT enabled kernels to differentiate a
- * preemption from blocking on an 'sleeping' spin/rwlock. Note that
- * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
- * optimize the AND operation out and just check for zero.
+ * preemption from blocking on an 'sleeping' spin/rwlock.
  */
-#define SM_NONE			0x0
-#define SM_PREEMPT		0x1
-#define SM_RTLOCK_WAIT		0x2
-
-#ifndef CONFIG_PREEMPT_RT
-# define SM_MASK_PREEMPT	(~0U)
-#else
-# define SM_MASK_PREEMPT	SM_PREEMPT
-#endif
+#define SM_IDLE			(-1)
+#define SM_NONE			0
+#define SM_PREEMPT		1
+#define SM_RTLOCK_WAIT		2
 
 /*
  * __schedule() is the main scheduler function.
@@ -6395,9 +6462,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  *
  * WARNING: must be called with preemption disabled!
  */
-static void __sched notrace __schedule(unsigned int sched_mode)
+static void __sched notrace __schedule(int sched_mode)
 {
 	struct task_struct *prev, *next;
+	/*
+	 * On PREEMPT_RT kernel, SM_RTLOCK_WAIT is noted
+	 * as a preemption by schedule_debug() and RCU.
+	 */
+	bool preempt = sched_mode > SM_NONE;
 	unsigned long *switch_count;
 	unsigned long prev_state;
 	struct rq_flags rf;
@@ -6408,13 +6480,13 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	schedule_debug(prev, !!sched_mode);
+	schedule_debug(prev, preempt);
 
 	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
 	local_irq_disable();
-	rcu_note_context_switch(!!sched_mode);
+	rcu_note_context_switch(preempt);
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
@@ -6443,22 +6515,32 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 
 	switch_count = &prev->nivcsw;
 
+	/* Task state changes only considers SM_PREEMPT as preemption */
+	preempt = sched_mode == SM_PREEMPT;
+
 	/*
 	 * We must load prev->state once (task_struct::state is volatile), such
 	 * that we form a control dependency vs deactivate_task() below.
 	 */
 	prev_state = READ_ONCE(prev->__state);
-	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
+	if (sched_mode == SM_IDLE) {
+		if (!rq->nr_running) {
+			next = prev;
+			goto picked;
+		}
+	} else if (!preempt && prev_state) {
 		if (signal_pending_state(prev_state, prev)) {
 			WRITE_ONCE(prev->__state, TASK_RUNNING);
 		} else {
+			int flags = DEQUEUE_NOCLOCK;
+
 			prev->sched_contributes_to_load =
 				(prev_state & TASK_UNINTERRUPTIBLE) &&
 				!(prev_state & TASK_NOLOAD) &&
 				!(prev_state & TASK_FROZEN);
 
-			if (prev->sched_contributes_to_load)
-				rq->nr_uninterruptible++;
+			if (unlikely(is_special_task_state(prev_state)))
+				flags |= DEQUEUE_SPECIAL;
 
 			/*
 			 * __schedule()			ttwu()
@@ -6471,17 +6553,13 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 			 *
 			 * After this, schedule() must not care about p->state any more.
 			 */
-			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
-
-			if (prev->in_iowait) {
-				atomic_inc(&rq->nr_iowait);
-				delayacct_blkio_start();
-			}
+			block_task(rq, prev, flags);
 		}
 		switch_count = &prev->nvcsw;
 	}
 
 	next = pick_next_task(rq, prev, &rf);
+picked:
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
 #ifdef CONFIG_SCHED_DEBUG
@@ -6523,7 +6601,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		psi_account_irqtime(rq, prev, next);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
+		trace_sched_switch(preempt, prev, next, prev_state);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
@@ -6599,7 +6677,7 @@ static void sched_update_worker(struct task_struct *tsk)
 	}
 }
 
-static __always_inline void __schedule_loop(unsigned int sched_mode)
+static __always_inline void __schedule_loop(int sched_mode)
 {
 	do {
 		preempt_disable();
@@ -6644,7 +6722,7 @@ void __sched schedule_idle(void)
 	 */
 	WARN_ON_ONCE(current->__state);
 	do {
-		__schedule(SM_NONE);
+		__schedule(SM_IDLE);
 	} while (need_resched());
 }
 
@@ -8228,8 +8306,6 @@ void __init sched_init(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 	}
 
-	init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
-
 #ifdef CONFIG_SMP
 	init_defrootdomain();
 #endif
@@ -8284,8 +8360,13 @@ void __init sched_init(void)
 		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-		rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
 #ifdef CONFIG_RT_GROUP_SCHED
+		/*
+		 * This is required for init cpu because rt.c:__enable_runtime()
+		 * starts working after scheduler_running, which is not the case
+		 * yet.
+		 */
+		rq->rt.rt_runtime = global_rt_runtime();
 		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
 #endif
 #ifdef CONFIG_SMP
@@ -8317,10 +8398,12 @@ void __init sched_init(void)
 #endif /* CONFIG_SMP */
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
+		fair_server_init(rq);
 
 #ifdef CONFIG_SCHED_CORE
 		rq->core = rq;
 		rq->core_pick = NULL;
+		rq->core_dl_server = NULL;
 		rq->core_enabled = 0;
 		rq->core_tree = RB_ROOT;
 		rq->core_forceidle_count = 0;
@@ -8333,6 +8416,7 @@ void __init sched_init(void)
 	}
 
 	set_load_weight(&init_task, false);
+	init_task.se.slice = sysctl_sched_base_slice,
 
 	/*
 	 * The boot idle thread does lazy MMU switching as well:
@@ -8548,7 +8632,7 @@ void normalize_rt_tasks(void)
 		schedstat_set(p->stats.sleep_start, 0);
 		schedstat_set(p->stats.block_start, 0);
 
-		if (!dl_task(p) && !rt_task(p)) {
+		if (!rt_or_dl_task(p)) {
 			/*
 			 * Renice negative nice level userspace
 			 * tasks back to 0:
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index eece6244f9d2..43111a515a28 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -654,9 +654,9 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy)
 		 * Fake (unused) bandwidth; workaround to "fix"
 		 * priority inheritance.
 		 */
-		.sched_runtime	=  1000000,
-		.sched_deadline = 10000000,
-		.sched_period	= 10000000,
+		.sched_runtime	= NSEC_PER_MSEC,
+		.sched_deadline = 10 * NSEC_PER_MSEC,
+		.sched_period	= 10 * NSEC_PER_MSEC,
 	};
 	struct cpufreq_policy *policy = sg_policy->policy;
 	int ret;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f59e5c19d944..9ce93d0bf452 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -320,19 +320,12 @@ void sub_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 		__sub_running_bw(dl_se->dl_bw, dl_rq);
 }
 
-static void dl_change_utilization(struct task_struct *p, u64 new_bw)
+static void dl_rq_change_utilization(struct rq *rq, struct sched_dl_entity *dl_se, u64 new_bw)
 {
-	struct rq *rq;
-
-	WARN_ON_ONCE(p->dl.flags & SCHED_FLAG_SUGOV);
-
-	if (task_on_rq_queued(p))
-		return;
+	if (dl_se->dl_non_contending) {
+		sub_running_bw(dl_se, &rq->dl);
+		dl_se->dl_non_contending = 0;
 
-	rq = task_rq(p);
-	if (p->dl.dl_non_contending) {
-		sub_running_bw(&p->dl, &rq->dl);
-		p->dl.dl_non_contending = 0;
 		/*
 		 * If the timer handler is currently running and the
 		 * timer cannot be canceled, inactive_task_timer()
@@ -340,13 +333,25 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
 		 * will not touch the rq's active utilization,
 		 * so we are still safe.
 		 */
-		if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
-			put_task_struct(p);
+		if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1) {
+			if (!dl_server(dl_se))
+				put_task_struct(dl_task_of(dl_se));
+		}
 	}
-	__sub_rq_bw(p->dl.dl_bw, &rq->dl);
+	__sub_rq_bw(dl_se->dl_bw, &rq->dl);
 	__add_rq_bw(new_bw, &rq->dl);
 }
 
+static void dl_change_utilization(struct task_struct *p, u64 new_bw)
+{
+	WARN_ON_ONCE(p->dl.flags & SCHED_FLAG_SUGOV);
+
+	if (task_on_rq_queued(p))
+		return;
+
+	dl_rq_change_utilization(task_rq(p), &p->dl, new_bw);
+}
+
 static void __dl_clear_params(struct sched_dl_entity *dl_se);
 
 /*
@@ -771,6 +776,15 @@ static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
 	/* for non-boosted task, pi_of(dl_se) == dl_se */
 	dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
 	dl_se->runtime = pi_of(dl_se)->dl_runtime;
+
+	/*
+	 * If it is a deferred reservation, and the server
+	 * is not handling an starvation case, defer it.
+	 */
+	if (dl_se->dl_defer & !dl_se->dl_defer_running) {
+		dl_se->dl_throttled = 1;
+		dl_se->dl_defer_armed = 1;
+	}
 }
 
 /*
@@ -809,6 +823,9 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
 	replenish_dl_new_period(dl_se, rq);
 }
 
+static int start_dl_timer(struct sched_dl_entity *dl_se);
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t);
+
 /*
  * Pure Earliest Deadline First (EDF) scheduling does not deal with the
  * possibility of a entity lasting more than what it declared, and thus
@@ -837,9 +854,18 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 	/*
 	 * This could be the case for a !-dl task that is boosted.
 	 * Just go with full inherited parameters.
+	 *
+	 * Or, it could be the case of a deferred reservation that
+	 * was not able to consume its runtime in background and
+	 * reached this point with current u > U.
+	 *
+	 * In both cases, set a new period.
 	 */
-	if (dl_se->dl_deadline == 0)
-		replenish_dl_new_period(dl_se, rq);
+	if (dl_se->dl_deadline == 0 ||
+	    (dl_se->dl_defer_armed && dl_entity_overflow(dl_se, rq_clock(rq)))) {
+		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+		dl_se->runtime = pi_of(dl_se)->dl_runtime;
+	}
 
 	if (dl_se->dl_yielded && dl_se->runtime > 0)
 		dl_se->runtime = 0;
@@ -873,6 +899,44 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 		dl_se->dl_yielded = 0;
 	if (dl_se->dl_throttled)
 		dl_se->dl_throttled = 0;
+
+	/*
+	 * If this is the replenishment of a deferred reservation,
+	 * clear the flag and return.
+	 */
+	if (dl_se->dl_defer_armed) {
+		dl_se->dl_defer_armed = 0;
+		return;
+	}
+
+	/*
+	 * A this point, if the deferred server is not armed, and the deadline
+	 * is in the future, if it is not running already, throttle the server
+	 * and arm the defer timer.
+	 */
+	if (dl_se->dl_defer && !dl_se->dl_defer_running &&
+	    dl_time_before(rq_clock(dl_se->rq), dl_se->deadline - dl_se->runtime)) {
+		if (!is_dl_boosted(dl_se) && dl_se->server_has_tasks(dl_se)) {
+
+			/*
+			 * Set dl_se->dl_defer_armed and dl_throttled variables to
+			 * inform the start_dl_timer() that this is a deferred
+			 * activation.
+			 */
+			dl_se->dl_defer_armed = 1;
+			dl_se->dl_throttled = 1;
+			if (!start_dl_timer(dl_se)) {
+				/*
+				 * If for whatever reason (delays), a previous timer was
+				 * queued but not serviced, cancel it and clean the
+				 * deferrable server variables intended for start_dl_timer().
+				 */
+				hrtimer_try_to_cancel(&dl_se->dl_timer);
+				dl_se->dl_defer_armed = 0;
+				dl_se->dl_throttled = 0;
+			}
+		}
+	}
 }
 
 /*
@@ -1023,6 +1087,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se)
 		}
 
 		replenish_dl_new_period(dl_se, rq);
+	} else if (dl_server(dl_se) && dl_se->dl_defer) {
+		/*
+		 * The server can still use its previous deadline, so check if
+		 * it left the dl_defer_running state.
+		 */
+		if (!dl_se->dl_defer_running) {
+			dl_se->dl_defer_armed = 1;
+			dl_se->dl_throttled = 1;
+		}
 	}
 }
 
@@ -1055,8 +1128,21 @@ static int start_dl_timer(struct sched_dl_entity *dl_se)
 	 * We want the timer to fire at the deadline, but considering
 	 * that it is actually coming from rq->clock and not from
 	 * hrtimer's time base reading.
+	 *
+	 * The deferred reservation will have its timer set to
+	 * (deadline - runtime). At that point, the CBS rule will decide
+	 * if the current deadline can be used, or if a replenishment is
+	 * required to avoid add too much pressure on the system
+	 * (current u > U).
 	 */
-	act = ns_to_ktime(dl_next_period(dl_se));
+	if (dl_se->dl_defer_armed) {
+		WARN_ON_ONCE(!dl_se->dl_throttled);
+		act = ns_to_ktime(dl_se->deadline - dl_se->runtime);
+	} else {
+		/* act = deadline - rel-deadline + period */
+		act = ns_to_ktime(dl_next_period(dl_se));
+	}
+
 	now = hrtimer_cb_get_time(timer);
 	delta = ktime_to_ns(now) - rq_clock(rq);
 	act = ktime_add_ns(act, delta);
@@ -1106,6 +1192,62 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
 #endif
 }
 
+/* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */
+static const u64 dl_server_min_res = 1 * NSEC_PER_MSEC;
+
+static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_dl_entity *dl_se)
+{
+	struct rq *rq = rq_of_dl_se(dl_se);
+	u64 fw;
+
+	scoped_guard (rq_lock, rq) {
+		struct rq_flags *rf = &scope.rf;
+
+		if (!dl_se->dl_throttled || !dl_se->dl_runtime)
+			return HRTIMER_NORESTART;
+
+		sched_clock_tick();
+		update_rq_clock(rq);
+
+		if (!dl_se->dl_runtime)
+			return HRTIMER_NORESTART;
+
+		if (!dl_se->server_has_tasks(dl_se)) {
+			replenish_dl_entity(dl_se);
+			return HRTIMER_NORESTART;
+		}
+
+		if (dl_se->dl_defer_armed) {
+			/*
+			 * First check if the server could consume runtime in background.
+			 * If so, it is possible to push the defer timer for this amount
+			 * of time. The dl_server_min_res serves as a limit to avoid
+			 * forwarding the timer for a too small amount of time.
+			 */
+			if (dl_time_before(rq_clock(dl_se->rq),
+					   (dl_se->deadline - dl_se->runtime - dl_server_min_res))) {
+
+				/* reset the defer timer */
+				fw = dl_se->deadline - rq_clock(dl_se->rq) - dl_se->runtime;
+
+				hrtimer_forward_now(timer, ns_to_ktime(fw));
+				return HRTIMER_RESTART;
+			}
+
+			dl_se->dl_defer_running = 1;
+		}
+
+		enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
+
+		if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &dl_se->rq->curr->dl))
+			resched_curr(rq);
+
+		__push_dl_task(rq, rf);
+	}
+
+	return HRTIMER_NORESTART;
+}
+
 /*
  * This is the bandwidth enforcement timer callback. If here, we know
  * a task is not on its dl_rq, since the fact that the timer was running
@@ -1128,28 +1270,8 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	struct rq_flags rf;
 	struct rq *rq;
 
-	if (dl_server(dl_se)) {
-		struct rq *rq = rq_of_dl_se(dl_se);
-		struct rq_flags rf;
-
-		rq_lock(rq, &rf);
-		if (dl_se->dl_throttled) {
-			sched_clock_tick();
-			update_rq_clock(rq);
-
-			if (dl_se->server_has_tasks(dl_se)) {
-				enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
-				resched_curr(rq);
-				__push_dl_task(rq, &rf);
-			} else {
-				replenish_dl_entity(dl_se);
-			}
-
-		}
-		rq_unlock(rq, &rf);
-
-		return HRTIMER_NORESTART;
-	}
+	if (dl_server(dl_se))
+		return dl_server_timer(timer, dl_se);
 
 	p = dl_task_of(dl_se);
 	rq = task_rq_lock(p, &rf);
@@ -1319,22 +1441,10 @@ static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
 	return (delta * u_act) >> BW_SHIFT;
 }
 
-static inline void
-update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
-                        int flags);
-static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
+s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
 {
 	s64 scaled_delta_exec;
 
-	if (unlikely(delta_exec <= 0)) {
-		if (unlikely(dl_se->dl_yielded))
-			goto throttle;
-		return;
-	}
-
-	if (dl_entity_is_special(dl_se))
-		return;
-
 	/*
 	 * For tasks that participate in GRUB, we implement GRUB-PA: the
 	 * spare reclaimed bandwidth is used to clock down frequency.
@@ -1353,8 +1463,64 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 		scaled_delta_exec = cap_scale(scaled_delta_exec, scale_cpu);
 	}
 
+	return scaled_delta_exec;
+}
+
+static inline void
+update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
+			int flags);
+static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
+{
+	s64 scaled_delta_exec;
+
+	if (unlikely(delta_exec <= 0)) {
+		if (unlikely(dl_se->dl_yielded))
+			goto throttle;
+		return;
+	}
+
+	if (dl_server(dl_se) && dl_se->dl_throttled && !dl_se->dl_defer)
+		return;
+
+	if (dl_entity_is_special(dl_se))
+		return;
+
+	scaled_delta_exec = dl_scaled_delta_exec(rq, dl_se, delta_exec);
+
 	dl_se->runtime -= scaled_delta_exec;
 
+	/*
+	 * The fair server can consume its runtime while throttled (not queued/
+	 * running as regular CFS).
+	 *
+	 * If the server consumes its entire runtime in this state. The server
+	 * is not required for the current period. Thus, reset the server by
+	 * starting a new period, pushing the activation.
+	 */
+	if (dl_se->dl_defer && dl_se->dl_throttled && dl_runtime_exceeded(dl_se)) {
+		/*
+		 * If the server was previously activated - the starving condition
+		 * took place, it this point it went away because the fair scheduler
+		 * was able to get runtime in background. So return to the initial
+		 * state.
+		 */
+		dl_se->dl_defer_running = 0;
+
+		hrtimer_try_to_cancel(&dl_se->dl_timer);
+
+		replenish_dl_new_period(dl_se, dl_se->rq);
+
+		/*
+		 * Not being able to start the timer seems problematic. If it could not
+		 * be started for whatever reason, we need to "unthrottle" the DL server
+		 * and queue right away. Otherwise nothing might queue it. That's similar
+		 * to what enqueue_dl_entity() does on start_dl_timer==0. For now, just warn.
+		 */
+		WARN_ON_ONCE(!start_dl_timer(dl_se));
+
+		return;
+	}
+
 throttle:
 	if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) {
 		dl_se->dl_throttled = 1;
@@ -1382,6 +1548,14 @@ throttle:
 	}
 
 	/*
+	 * The fair server (sole dl_server) does not account for real-time
+	 * workload because it is running fair work.
+	 */
+	if (dl_se == &rq->fair_server)
+		return;
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	/*
 	 * Because -- for now -- we share the rt bandwidth, we need to
 	 * account our runtime there too, otherwise actual rt tasks
 	 * would be able to exceed the shared quota.
@@ -1405,34 +1579,155 @@ throttle:
 			rt_rq->rt_time += delta_exec;
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 	}
+#endif
+}
+
+/*
+ * In the non-defer mode, the idle time is not accounted, as the
+ * server provides a guarantee.
+ *
+ * If the dl_server is in defer mode, the idle time is also considered
+ * as time available for the fair server, avoiding a penalty for the
+ * rt scheduler that did not consumed that time.
+ */
+void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
+{
+	s64 delta_exec, scaled_delta_exec;
+
+	if (!rq->fair_server.dl_defer)
+		return;
+
+	/* no need to discount more */
+	if (rq->fair_server.runtime < 0)
+		return;
+
+	delta_exec = rq_clock_task(rq) - p->se.exec_start;
+	if (delta_exec < 0)
+		return;
+
+	scaled_delta_exec = dl_scaled_delta_exec(rq, &rq->fair_server, delta_exec);
+
+	rq->fair_server.runtime -= scaled_delta_exec;
+
+	if (rq->fair_server.runtime < 0) {
+		rq->fair_server.dl_defer_running = 0;
+		rq->fair_server.runtime = 0;
+	}
+
+	p->se.exec_start = rq_clock_task(rq);
 }
 
 void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
 {
-	update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
+	/* 0 runtime = fair server disabled */
+	if (dl_se->dl_runtime)
+		update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
 }
 
 void dl_server_start(struct sched_dl_entity *dl_se)
 {
+	struct rq *rq = dl_se->rq;
+
+	/*
+	 * XXX: the apply do not work fine at the init phase for the
+	 * fair server because things are not yet set. We need to improve
+	 * this before getting generic.
+	 */
 	if (!dl_server(dl_se)) {
+		u64 runtime =  50 * NSEC_PER_MSEC;
+		u64 period = 1000 * NSEC_PER_MSEC;
+
+		dl_server_apply_params(dl_se, runtime, period, 1);
+
 		dl_se->dl_server = 1;
+		dl_se->dl_defer = 1;
 		setup_new_dl_entity(dl_se);
 	}
+
+	if (!dl_se->dl_runtime)
+		return;
+
 	enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
+	if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
+		resched_curr(dl_se->rq);
 }
 
 void dl_server_stop(struct sched_dl_entity *dl_se)
 {
+	if (!dl_se->dl_runtime)
+		return;
+
 	dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
+	hrtimer_try_to_cancel(&dl_se->dl_timer);
+	dl_se->dl_defer_armed = 0;
+	dl_se->dl_throttled = 0;
 }
 
 void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 		    dl_server_has_tasks_f has_tasks,
-		    dl_server_pick_f pick)
+		    dl_server_pick_f pick_task)
 {
 	dl_se->rq = rq;
 	dl_se->server_has_tasks = has_tasks;
-	dl_se->server_pick = pick;
+	dl_se->server_pick_task = pick_task;
+}
+
+void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq)
+{
+	u64 new_bw = dl_se->dl_bw;
+	int cpu = cpu_of(rq);
+	struct dl_bw *dl_b;
+
+	dl_b = dl_bw_of(cpu_of(rq));
+	guard(raw_spinlock)(&dl_b->lock);
+
+	if (!dl_bw_cpus(cpu))
+		return;
+
+	__dl_add(dl_b, new_bw, dl_bw_cpus(cpu));
+}
+
+int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 period, bool init)
+{
+	u64 old_bw = init ? 0 : to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+	u64 new_bw = to_ratio(period, runtime);
+	struct rq *rq = dl_se->rq;
+	int cpu = cpu_of(rq);
+	struct dl_bw *dl_b;
+	unsigned long cap;
+	int retval = 0;
+	int cpus;
+
+	dl_b = dl_bw_of(cpu);
+	guard(raw_spinlock)(&dl_b->lock);
+
+	cpus = dl_bw_cpus(cpu);
+	cap = dl_bw_capacity(cpu);
+
+	if (__dl_overflow(dl_b, cap, old_bw, new_bw))
+		return -EBUSY;
+
+	if (init) {
+		__add_rq_bw(new_bw, &rq->dl);
+		__dl_add(dl_b, new_bw, cpus);
+	} else {
+		__dl_sub(dl_b, dl_se->dl_bw, cpus);
+		__dl_add(dl_b, new_bw, cpus);
+
+		dl_rq_change_utilization(rq, dl_se, new_bw);
+	}
+
+	dl_se->dl_runtime = runtime;
+	dl_se->dl_deadline = period;
+	dl_se->dl_period = period;
+
+	dl_se->runtime = 0;
+	dl_se->deadline = 0;
+
+	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+	dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
+
+	return retval;
 }
 
 /*
@@ -1599,46 +1894,40 @@ static inline bool __dl_less(struct rb_node *a, const struct rb_node *b)
 	return dl_time_before(__node_2_dle(a)->deadline, __node_2_dle(b)->deadline);
 }
 
-static inline struct sched_statistics *
+static __always_inline struct sched_statistics *
 __schedstats_from_dl_se(struct sched_dl_entity *dl_se)
 {
+	if (!schedstat_enabled())
+		return NULL;
+
+	if (dl_server(dl_se))
+		return NULL;
+
 	return &dl_task_of(dl_se)->stats;
 }
 
 static inline void
 update_stats_wait_start_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
 {
-	struct sched_statistics *stats;
-
-	if (!schedstat_enabled())
-		return;
-
-	stats = __schedstats_from_dl_se(dl_se);
-	__update_stats_wait_start(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+	struct sched_statistics *stats = __schedstats_from_dl_se(dl_se);
+	if (stats)
+		__update_stats_wait_start(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
 }
 
 static inline void
 update_stats_wait_end_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
 {
-	struct sched_statistics *stats;
-
-	if (!schedstat_enabled())
-		return;
-
-	stats = __schedstats_from_dl_se(dl_se);
-	__update_stats_wait_end(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+	struct sched_statistics *stats = __schedstats_from_dl_se(dl_se);
+	if (stats)
+		__update_stats_wait_end(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
 }
 
 static inline void
 update_stats_enqueue_sleeper_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
 {
-	struct sched_statistics *stats;
-
-	if (!schedstat_enabled())
-		return;
-
-	stats = __schedstats_from_dl_se(dl_se);
-	__update_stats_enqueue_sleeper(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+	struct sched_statistics *stats = __schedstats_from_dl_se(dl_se);
+	if (stats)
+		__update_stats_enqueue_sleeper(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
 }
 
 static inline void
@@ -1735,7 +2024,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 	 * be counted in the active utilization; hence, we need to call
 	 * add_running_bw().
 	 */
-	if (dl_se->dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
+	if (!dl_se->dl_defer && dl_se->dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
 		if (flags & ENQUEUE_WAKEUP)
 			task_contending(dl_se, flags);
 
@@ -1757,6 +2046,25 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 		setup_new_dl_entity(dl_se);
 	}
 
+	/*
+	 * If the reservation is still throttled, e.g., it got replenished but is a
+	 * deferred task and still got to wait, don't enqueue.
+	 */
+	if (dl_se->dl_throttled && start_dl_timer(dl_se))
+		return;
+
+	/*
+	 * We're about to enqueue, make sure we're not ->dl_throttled!
+	 * In case the timer was not started, say because the defer time
+	 * has passed, mark as not throttled and mark unarmed.
+	 * Also cancel earlier timers, since letting those run is pointless.
+	 */
+	if (dl_se->dl_throttled) {
+		hrtimer_try_to_cancel(&dl_se->dl_timer);
+		dl_se->dl_defer_armed = 0;
+		dl_se->dl_throttled = 0;
+	}
+
 	__enqueue_dl_entity(dl_se);
 }
 
@@ -1846,7 +2154,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		enqueue_pushable_dl_task(rq, p);
 }
 
-static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+static bool dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_curr_dl(rq);
 
@@ -1856,6 +2164,8 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_dl_entity(&p->dl, flags);
 	if (!p->dl.dl_throttled && !dl_server(&p->dl))
 		dequeue_pushable_dl_task(rq, p);
+
+	return true;
 }
 
 /*
@@ -2074,6 +2384,9 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 		update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
 
 	deadline_queue_push_tasks(rq);
+
+	if (hrtick_enabled(rq))
+		start_hrtick_dl(rq, &p->dl);
 }
 
 static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
@@ -2086,7 +2399,11 @@ static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
 	return __node_2_dle(left);
 }
 
-static struct task_struct *pick_task_dl(struct rq *rq)
+/*
+ * __pick_next_task_dl - Helper to pick the next -deadline task to run.
+ * @rq: The runqueue to pick the next task from.
+ */
+static struct task_struct *__pick_task_dl(struct rq *rq)
 {
 	struct sched_dl_entity *dl_se;
 	struct dl_rq *dl_rq = &rq->dl;
@@ -2100,14 +2417,13 @@ again:
 	WARN_ON_ONCE(!dl_se);
 
 	if (dl_server(dl_se)) {
-		p = dl_se->server_pick(dl_se);
+		p = dl_se->server_pick_task(dl_se);
 		if (!p) {
-			WARN_ON_ONCE(1);
 			dl_se->dl_yielded = 1;
 			update_curr_dl_se(rq, dl_se, 0);
 			goto again;
 		}
-		p->dl_server = dl_se;
+		rq->dl_server = dl_se;
 	} else {
 		p = dl_task_of(dl_se);
 	}
@@ -2115,24 +2431,12 @@ again:
 	return p;
 }
 
-static struct task_struct *pick_next_task_dl(struct rq *rq)
+static struct task_struct *pick_task_dl(struct rq *rq)
 {
-	struct task_struct *p;
-
-	p = pick_task_dl(rq);
-	if (!p)
-		return p;
-
-	if (!p->dl_server)
-		set_next_task_dl(rq, p, true);
-
-	if (hrtick_enabled(rq))
-		start_hrtick_dl(rq, &p->dl);
-
-	return p;
+	return __pick_task_dl(rq);
 }
 
-static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct task_struct *next)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
 	struct dl_rq *dl_rq = &rq->dl;
@@ -2824,13 +3128,12 @@ DEFINE_SCHED_CLASS(dl) = {
 
 	.wakeup_preempt		= wakeup_preempt_dl,
 
-	.pick_next_task		= pick_next_task_dl,
+	.pick_task		= pick_task_dl,
 	.put_prev_task		= put_prev_task_dl,
 	.set_next_task		= set_next_task_dl,
 
 #ifdef CONFIG_SMP
 	.balance		= balance_dl,
-	.pick_task		= pick_task_dl,
 	.select_task_rq		= select_task_rq_dl,
 	.migrate_task_rq	= migrate_task_rq_dl,
 	.set_cpus_allowed       = set_cpus_allowed_dl,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index c1eb9a1afd13..de1dc5264b3f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -333,8 +333,165 @@ static const struct file_operations sched_debug_fops = {
 	.release	= seq_release,
 };
 
+enum dl_param {
+	DL_RUNTIME = 0,
+	DL_PERIOD,
+};
+
+static unsigned long fair_server_period_max = (1UL << 22) * NSEC_PER_USEC; /* ~4 seconds */
+static unsigned long fair_server_period_min = (100) * NSEC_PER_USEC;     /* 100 us */
+
+static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubuf,
+				       size_t cnt, loff_t *ppos, enum dl_param param)
+{
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+	u64 runtime, period;
+	size_t err;
+	int retval;
+	u64 value;
+
+	err = kstrtoull_from_user(ubuf, cnt, 10, &value);
+	if (err)
+		return err;
+
+	scoped_guard (rq_lock_irqsave, rq) {
+		runtime  = rq->fair_server.dl_runtime;
+		period = rq->fair_server.dl_period;
+
+		switch (param) {
+		case DL_RUNTIME:
+			if (runtime == value)
+				break;
+			runtime = value;
+			break;
+		case DL_PERIOD:
+			if (value == period)
+				break;
+			period = value;
+			break;
+		}
+
+		if (runtime > period ||
+		    period > fair_server_period_max ||
+		    period < fair_server_period_min) {
+			return  -EINVAL;
+		}
+
+		if (rq->cfs.h_nr_running) {
+			update_rq_clock(rq);
+			dl_server_stop(&rq->fair_server);
+		}
+
+		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
+		if (retval)
+			cnt = retval;
+
+		if (!runtime)
+			printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n",
+					cpu_of(rq));
+
+		if (rq->cfs.h_nr_running)
+			dl_server_start(&rq->fair_server);
+	}
+
+	*ppos += cnt;
+	return cnt;
+}
+
+static size_t sched_fair_server_show(struct seq_file *m, void *v, enum dl_param param)
+{
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+	u64 value;
+
+	switch (param) {
+	case DL_RUNTIME:
+		value = rq->fair_server.dl_runtime;
+		break;
+	case DL_PERIOD:
+		value = rq->fair_server.dl_period;
+		break;
+	}
+
+	seq_printf(m, "%llu\n", value);
+	return 0;
+
+}
+
+static ssize_t
+sched_fair_server_runtime_write(struct file *filp, const char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	return sched_fair_server_write(filp, ubuf, cnt, ppos, DL_RUNTIME);
+}
+
+static int sched_fair_server_runtime_show(struct seq_file *m, void *v)
+{
+	return sched_fair_server_show(m, v, DL_RUNTIME);
+}
+
+static int sched_fair_server_runtime_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_fair_server_runtime_show, inode->i_private);
+}
+
+static const struct file_operations fair_server_runtime_fops = {
+	.open		= sched_fair_server_runtime_open,
+	.write		= sched_fair_server_runtime_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static ssize_t
+sched_fair_server_period_write(struct file *filp, const char __user *ubuf,
+			       size_t cnt, loff_t *ppos)
+{
+	return sched_fair_server_write(filp, ubuf, cnt, ppos, DL_PERIOD);
+}
+
+static int sched_fair_server_period_show(struct seq_file *m, void *v)
+{
+	return sched_fair_server_show(m, v, DL_PERIOD);
+}
+
+static int sched_fair_server_period_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_fair_server_period_show, inode->i_private);
+}
+
+static const struct file_operations fair_server_period_fops = {
+	.open		= sched_fair_server_period_open,
+	.write		= sched_fair_server_period_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static struct dentry *debugfs_sched;
 
+static void debugfs_fair_server_init(void)
+{
+	struct dentry *d_fair;
+	unsigned long cpu;
+
+	d_fair = debugfs_create_dir("fair_server", debugfs_sched);
+	if (!d_fair)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct dentry *d_cpu;
+		char buf[32];
+
+		snprintf(buf, sizeof(buf), "cpu%lu", cpu);
+		d_cpu = debugfs_create_dir(buf, d_fair);
+
+		debugfs_create_file("runtime", 0644, d_cpu, (void *) cpu, &fair_server_runtime_fops);
+		debugfs_create_file("period", 0644, d_cpu, (void *) cpu, &fair_server_period_fops);
+	}
+}
+
 static __init int sched_init_debug(void)
 {
 	struct dentry __maybe_unused *numa;
@@ -374,6 +531,8 @@ static __init int sched_init_debug(void)
 
 	debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
 
+	debugfs_fair_server_init();
+
 	return 0;
 }
 late_initcall(sched_init_debug);
@@ -580,27 +739,27 @@ 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 %9Ld.%06ld %9Ld.%06ld %9Ld %5d ",
+	SEQ_printf(m, " %15s %5d %9Ld.%06ld   %c   %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld   %5d ",
 		p->comm, task_pid_nr(p),
 		SPLIT_NS(p->se.vruntime),
 		entity_eligible(cfs_rq_of(&p->se), &p->se) ? 'E' : 'N',
 		SPLIT_NS(p->se.deadline),
+		p->se.custom_slice ? 'S' : ' ',
 		SPLIT_NS(p->se.slice),
 		SPLIT_NS(p->se.sum_exec_runtime),
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
 
-	SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld %9lld.%06ld",
+	SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld",
 		SPLIT_NS(schedstat_val_or_zero(p->stats.wait_sum)),
-		SPLIT_NS(p->se.sum_exec_runtime),
 		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)),
 		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_block_runtime)));
 
 #ifdef CONFIG_NUMA_BALANCING
-	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
+	SEQ_printf(m, "   %d      %d", task_node(p), task_numa_group_id(p));
 #endif
 #ifdef CONFIG_CGROUP_SCHED
-	SEQ_printf_task_group_path(m, task_group(p), " %s")
+	SEQ_printf_task_group_path(m, task_group(p), "        %s")
 #endif
 
 	SEQ_printf(m, "\n");
@@ -612,10 +771,26 @@ 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         tree-key  switches  prio"
-		   "     wait-time             sum-exec        sum-sleep\n");
+	SEQ_printf(m, " S            task   PID       vruntime   eligible    "
+		   "deadline             slice          sum-exec      switches  "
+		   "prio         wait-time        sum-sleep       sum-block"
+#ifdef CONFIG_NUMA_BALANCING
+		   "  node   group-id"
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+		   "  group-path"
+#endif
+		   "\n");
 	SEQ_printf(m, "-------------------------------------------------------"
-		   "------------------------------------------------------\n");
+		   "------------------------------------------------------"
+		   "------------------------------------------------------"
+#ifdef CONFIG_NUMA_BALANCING
+		   "--------------"
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+		   "--------------"
+#endif
+		   "\n");
 
 	rcu_read_lock();
 	for_each_process_thread(g, p) {
@@ -641,8 +816,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "cfs_rq[%d]:\n", cpu);
 #endif
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
-			SPLIT_NS(cfs_rq->exec_clock));
 
 	raw_spin_rq_lock_irqsave(rq, flags);
 	root = __pick_root_entity(cfs_rq);
@@ -669,8 +842,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			SPLIT_NS(right_vruntime));
 	spread = right_vruntime - left_vruntime;
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread));
-	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
-			cfs_rq->nr_spread_over);
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "idle_nr_running",
@@ -730,9 +901,12 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
 
 	PU(rt_nr_running);
+
+#ifdef CONFIG_RT_GROUP_SCHED
 	P(rt_throttled);
 	PN(rt_time);
 	PN(rt_runtime);
+#endif
 
 #undef PN
 #undef PU
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8dc9385f6da4..b9784e13e6b6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -511,7 +511,7 @@ static int cfs_rq_is_idle(struct cfs_rq *cfs_rq)
 
 static int se_is_idle(struct sched_entity *se)
 {
-	return 0;
+	return task_has_idle_policy(task_of(se));
 }
 
 #endif	/* CONFIG_FAIR_GROUP_SCHED */
@@ -779,8 +779,22 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 	}
 
 	/* ensure we never gain time by being placed backwards. */
-	u64_u32_store(cfs_rq->min_vruntime,
-		      __update_min_vruntime(cfs_rq, vruntime));
+	cfs_rq->min_vruntime = __update_min_vruntime(cfs_rq, vruntime);
+}
+
+static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq)
+{
+	struct sched_entity *root = __pick_root_entity(cfs_rq);
+	struct sched_entity *curr = cfs_rq->curr;
+	u64 min_slice = ~0ULL;
+
+	if (curr && curr->on_rq)
+		min_slice = curr->slice;
+
+	if (root)
+		min_slice = min(min_slice, root->min_slice);
+
+	return min_slice;
 }
 
 static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
@@ -799,19 +813,34 @@ static inline void __min_vruntime_update(struct sched_entity *se, struct rb_node
 	}
 }
 
+static inline void __min_slice_update(struct sched_entity *se, struct rb_node *node)
+{
+	if (node) {
+		struct sched_entity *rse = __node_2_se(node);
+		if (rse->min_slice < se->min_slice)
+			se->min_slice = rse->min_slice;
+	}
+}
+
 /*
  * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
  */
 static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
 {
 	u64 old_min_vruntime = se->min_vruntime;
+	u64 old_min_slice = se->min_slice;
 	struct rb_node *node = &se->run_node;
 
 	se->min_vruntime = se->vruntime;
 	__min_vruntime_update(se, node->rb_right);
 	__min_vruntime_update(se, node->rb_left);
 
-	return se->min_vruntime == old_min_vruntime;
+	se->min_slice = se->slice;
+	__min_slice_update(se, node->rb_right);
+	__min_slice_update(se, node->rb_left);
+
+	return se->min_vruntime == old_min_vruntime &&
+	       se->min_slice == old_min_slice;
 }
 
 RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
@@ -824,6 +853,7 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	avg_vruntime_add(cfs_rq, se);
 	se->min_vruntime = se->vruntime;
+	se->min_slice = se->slice;
 	rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
 				__entity_less, &min_vruntime_cb);
 }
@@ -974,17 +1004,18 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se);
  * XXX: strictly: vd_i += N*r_i/w_i such that: vd_i > ve_i
  * this is probably good enough.
  */
-static void update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static bool update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if ((s64)(se->vruntime - se->deadline) < 0)
-		return;
+		return false;
 
 	/*
 	 * For EEVDF the virtual time slope is determined by w_i (iow.
 	 * nice) while the request time r_i is determined by
 	 * sysctl_sched_base_slice.
 	 */
-	se->slice = sysctl_sched_base_slice;
+	if (!se->custom_slice)
+		se->slice = sysctl_sched_base_slice;
 
 	/*
 	 * EEVDF: vd_i = ve_i + r_i / w_i
@@ -994,10 +1025,7 @@ static void update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	/*
 	 * The task has consumed its request, reschedule.
 	 */
-	if (cfs_rq->nr_running > 1) {
-		resched_curr(rq_of(cfs_rq));
-		clear_buddies(cfs_rq, se);
-	}
+	return true;
 }
 
 #include "pelt.h"
@@ -1135,6 +1163,38 @@ static inline void update_curr_task(struct task_struct *p, s64 delta_exec)
 		dl_server_update(p->dl_server, delta_exec);
 }
 
+static inline bool did_preempt_short(struct cfs_rq *cfs_rq, struct sched_entity *curr)
+{
+	if (!sched_feat(PREEMPT_SHORT))
+		return false;
+
+	if (curr->vlag == curr->deadline)
+		return false;
+
+	return !entity_eligible(cfs_rq, curr);
+}
+
+static inline bool do_preempt_short(struct cfs_rq *cfs_rq,
+				    struct sched_entity *pse, struct sched_entity *se)
+{
+	if (!sched_feat(PREEMPT_SHORT))
+		return false;
+
+	if (pse->slice >= se->slice)
+		return false;
+
+	if (!entity_eligible(cfs_rq, pse))
+		return false;
+
+	if (entity_before(pse, se))
+		return true;
+
+	if (!entity_eligible(cfs_rq, se))
+		return true;
+
+	return false;
+}
+
 /*
  * Used by other classes to account runtime.
  */
@@ -1156,23 +1216,44 @@ s64 update_curr_common(struct rq *rq)
 static void update_curr(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
+	struct rq *rq = rq_of(cfs_rq);
 	s64 delta_exec;
+	bool resched;
 
 	if (unlikely(!curr))
 		return;
 
-	delta_exec = update_curr_se(rq_of(cfs_rq), curr);
+	delta_exec = update_curr_se(rq, curr);
 	if (unlikely(delta_exec <= 0))
 		return;
 
 	curr->vruntime += calc_delta_fair(delta_exec, curr);
-	update_deadline(cfs_rq, curr);
+	resched = update_deadline(cfs_rq, curr);
 	update_min_vruntime(cfs_rq);
 
-	if (entity_is_task(curr))
-		update_curr_task(task_of(curr), delta_exec);
+	if (entity_is_task(curr)) {
+		struct task_struct *p = task_of(curr);
+
+		update_curr_task(p, delta_exec);
+
+		/*
+		 * Any 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.
+		 */
+		if (p->dl_server != &rq->fair_server)
+			dl_server_update(&rq->fair_server, delta_exec);
+	}
 
 	account_cfs_rq_runtime(cfs_rq, delta_exec);
+
+	if (rq->nr_running == 1)
+		return;
+
+	if (resched || did_preempt_short(cfs_rq, curr)) {
+		resched_curr(rq);
+		clear_buddies(cfs_rq, curr);
+	}
 }
 
 static void update_curr_fair(struct rq *rq)
@@ -5178,7 +5259,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	u64 vslice, vruntime = avg_vruntime(cfs_rq);
 	s64 lag = 0;
 
-	se->slice = sysctl_sched_base_slice;
+	if (!se->custom_slice)
+		se->slice = sysctl_sched_base_slice;
 	vslice = calc_delta_fair(se->slice, se);
 
 	/*
@@ -5259,6 +5341,12 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	se->vruntime = vruntime - lag;
 
+	if (sched_feat(PLACE_REL_DEADLINE) && se->rel_deadline) {
+		se->deadline += se->vruntime;
+		se->rel_deadline = 0;
+		return;
+	}
+
 	/*
 	 * When joining the competition; the existing tasks will be,
 	 * on average, halfway through their slice, as such start tasks
@@ -5279,6 +5367,9 @@ static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq);
 static inline bool cfs_bandwidth_used(void);
 
 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;
@@ -5365,20 +5456,48 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 
-static void
+static inline void finish_delayed_dequeue_entity(struct sched_entity *se)
+{
+	se->sched_delayed = 0;
+	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)
 {
-	int action = UPDATE_TG;
+	bool sleep = flags & DEQUEUE_SLEEP;
 
+	update_curr(cfs_rq);
+
+	if (flags & DEQUEUE_DELAYED) {
+		SCHED_WARN_ON(!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)
+			delay = false;
+
+		SCHED_WARN_ON(delay && se->sched_delayed);
+
+		if (sched_feat(DELAY_DEQUEUE) && delay &&
+		    !entity_eligible(cfs_rq, se)) {
+			if (cfs_rq->next == se)
+				cfs_rq->next = NULL;
+			update_load_avg(cfs_rq, se, 0);
+			se->sched_delayed = 1;
+			return false;
+		}
+	}
+
+	int action = UPDATE_TG;
 	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)))
 		action |= DO_DETACH;
 
 	/*
-	 * Update run-time statistics of the 'current'.
-	 */
-	update_curr(cfs_rq);
-
-	/*
 	 * When dequeuing a sched_entity, we must:
 	 *   - Update loads to have both entity and cfs_rq synced with now.
 	 *   - For group_entity, update its runnable_weight to reflect the new
@@ -5395,6 +5514,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	clear_buddies(cfs_rq, se);
 
 	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;
@@ -5414,8 +5538,13 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
 		update_min_vruntime(cfs_rq);
 
+	if (flags & DEQUEUE_DELAYED)
+		finish_delayed_dequeue_entity(se);
+
 	if (cfs_rq->nr_running == 0)
 		update_idle_cfs_rq_clock_pelt(cfs_rq);
+
+	return true;
 }
 
 static void
@@ -5441,6 +5570,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	}
 
 	update_stats_curr_start(cfs_rq, se);
+	SCHED_WARN_ON(cfs_rq->curr);
 	cfs_rq->curr = se;
 
 	/*
@@ -5461,6 +5591,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
+static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags);
+
 /*
  * Pick the next process, keeping these things in mind, in this order:
  * 1) keep things fair between processes/task groups
@@ -5469,16 +5601,26 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * 4) do not run the "skip" process, if something else is available
  */
 static struct sched_entity *
-pick_next_entity(struct cfs_rq *cfs_rq)
+pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
 {
 	/*
 	 * Enabling NEXT_BUDDY will affect latency but not fairness.
 	 */
 	if (sched_feat(NEXT_BUDDY) &&
-	    cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next))
+	    cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next)) {
+		/* ->next will never be delayed */
+		SCHED_WARN_ON(cfs_rq->next->sched_delayed);
 		return cfs_rq->next;
+	}
 
-	return pick_eevdf(cfs_rq);
+	struct sched_entity *se = pick_eevdf(cfs_rq);
+	if (se->sched_delayed) {
+		dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
+		SCHED_WARN_ON(se->sched_delayed);
+		SCHED_WARN_ON(se->on_rq);
+		return NULL;
+	}
+	return se;
 }
 
 static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
@@ -5502,6 +5644,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 		/* in !on_rq case, update occurred at dequeue */
 		update_load_avg(cfs_rq, prev, 0);
 	}
+	SCHED_WARN_ON(cfs_rq->curr != prev);
 	cfs_rq->curr = NULL;
 }
 
@@ -5765,6 +5908,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long task_delta, idle_task_delta, dequeue = 1;
+	long rq_h_nr_running = rq->cfs.h_nr_running;
 
 	raw_spin_lock(&cfs_b->lock);
 	/* This will start the period timer if necessary */
@@ -5798,11 +5942,21 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
+		int flags;
+
 		/* throttled entity or throttle-on-deactivate */
 		if (!se->on_rq)
 			goto done;
 
-		dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
+		/*
+		 * Abuse SPECIAL to avoid delayed dequeue in this instance.
+		 * This avoids teaching dequeue_entities() about throttled
+		 * entities and keeps things relatively simple.
+		 */
+		flags = DEQUEUE_SLEEP | DEQUEUE_SPECIAL;
+		if (se->sched_delayed)
+			flags |= DEQUEUE_DELAYED;
+		dequeue_entity(qcfs_rq, se, flags);
 
 		if (cfs_rq_is_idle(group_cfs_rq(se)))
 			idle_task_delta = cfs_rq->h_nr_running;
@@ -5836,6 +5990,9 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	/* At this point se is NULL and we are at root level*/
 	sub_nr_running(rq, task_delta);
 
+	/* Stop the fair server if throttling resulted in no runnable tasks */
+	if (rq_h_nr_running && !rq->cfs.h_nr_running)
+		dl_server_stop(&rq->fair_server);
 done:
 	/*
 	 * Note: distribution will already see us throttled via the
@@ -5854,6 +6011,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long task_delta, idle_task_delta;
+	long rq_h_nr_running = rq->cfs.h_nr_running;
 
 	se = cfs_rq->tg->se[cpu_of(rq)];
 
@@ -5891,8 +6049,10 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 
-		if (se->on_rq)
+		if (se->on_rq) {
+			SCHED_WARN_ON(se->sched_delayed);
 			break;
+		}
 		enqueue_entity(qcfs_rq, se, ENQUEUE_WAKEUP);
 
 		if (cfs_rq_is_idle(group_cfs_rq(se)))
@@ -5923,6 +6083,10 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 			goto unthrottle_throttle;
 	}
 
+	/* Start the fair server if un-throttling resulted in new runnable tasks */
+	if (!rq_h_nr_running && rq->cfs.h_nr_running)
+		dl_server_start(&rq->fair_server);
+
 	/* At this point se is NULL and we are at root level*/
 	add_nr_running(rq, task_delta);
 
@@ -6555,7 +6719,7 @@ static void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p)
 {
 	int cpu = cpu_of(rq);
 
-	if (!sched_feat(HZ_BW) || !cfs_bandwidth_used())
+	if (!cfs_bandwidth_used())
 		return;
 
 	if (!tick_nohz_full_cpu(cpu))
@@ -6738,6 +6902,37 @@ static int sched_idle_cpu(int cpu)
 }
 #endif
 
+static void
+requeue_delayed_entity(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
+	 * the runqueue competing until elegibility.
+	 */
+	SCHED_WARN_ON(!se->sched_delayed);
+	SCHED_WARN_ON(!se->on_rq);
+
+	if (sched_feat(DELAY_ZERO)) {
+		update_entity_lag(cfs_rq, se);
+		if (se->vlag > 0) {
+			cfs_rq->nr_running--;
+			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_running++;
+		}
+	}
+
+	update_load_avg(cfs_rq, se, 0);
+	se->sched_delayed = 0;
+}
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -6750,6 +6945,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_entity *se = &p->se;
 	int idle_h_nr_running = task_has_idle_policy(p);
 	int task_new = !(flags & ENQUEUE_WAKEUP);
+	int rq_h_nr_running = rq->cfs.h_nr_running;
+	u64 slice = 0;
 
 	/*
 	 * The code below (indirectly) updates schedutil which looks at
@@ -6757,7 +6954,13 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * Let's add the task's estimated utilization to the cfs_rq's
 	 * estimated utilization, before we update schedutil.
 	 */
-	util_est_enqueue(&rq->cfs, p);
+	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & ENQUEUE_RESTORE))))
+		util_est_enqueue(&rq->cfs, p);
+
+	if (flags & ENQUEUE_DELAYED) {
+		requeue_delayed_entity(se);
+		return;
+	}
 
 	/*
 	 * If in_iowait is set, the code below may not trigger any cpufreq
@@ -6768,10 +6971,24 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
 
 	for_each_sched_entity(se) {
-		if (se->on_rq)
+		if (se->on_rq) {
+			if (se->sched_delayed)
+				requeue_delayed_entity(se);
 			break;
+		}
 		cfs_rq = cfs_rq_of(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);
 
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
@@ -6793,6 +7010,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		se_update_runnable(se);
 		update_cfs_group(se);
 
+		se->slice = slice;
+		slice = cfs_rq_min_slice(cfs_rq);
+
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
@@ -6804,6 +7024,13 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 			goto enqueue_throttle;
 	}
 
+	if (!rq_h_nr_running && rq->cfs.h_nr_running) {
+		/* Account for idle runtime */
+		if (!rq->nr_running)
+			dl_server_update_idle_time(rq, rq->curr);
+		dl_server_start(&rq->fair_server);
+	}
+
 	/* At this point se is NULL and we are at root level*/
 	add_nr_running(rq, 1);
 
@@ -6833,36 +7060,59 @@ enqueue_throttle:
 static void set_next_buddy(struct sched_entity *se);
 
 /*
- * The dequeue_task method is called before nr_running is
- * decreased. We remove the task from the rbtree and
- * update the fair scheduling stats:
+ * 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 void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
+static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 {
-	struct cfs_rq *cfs_rq;
-	struct sched_entity *se = &p->se;
-	int task_sleep = flags & DEQUEUE_SLEEP;
-	int idle_h_nr_running = task_has_idle_policy(p);
 	bool was_sched_idle = sched_idle_rq(rq);
+	int rq_h_nr_running = rq->cfs.h_nr_running;
+	bool task_sleep = flags & DEQUEUE_SLEEP;
+	bool task_delayed = flags & DEQUEUE_DELAYED;
+	struct task_struct *p = NULL;
+	int idle_h_nr_running = 0;
+	int h_nr_running = 0;
+	struct cfs_rq *cfs_rq;
+	u64 slice = 0;
 
-	util_est_dequeue(&rq->cfs, p);
+	if (entity_is_task(se)) {
+		p = task_of(se);
+		h_nr_running = 1;
+		idle_h_nr_running = task_has_idle_policy(p);
+	} else {
+		cfs_rq = group_cfs_rq(se);
+		slice = cfs_rq_min_slice(cfs_rq);
+	}
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		dequeue_entity(cfs_rq, se, flags);
 
-		cfs_rq->h_nr_running--;
+		if (!dequeue_entity(cfs_rq, se, flags)) {
+			if (p && &p->se == se)
+				return -1;
+
+			break;
+		}
+
+		cfs_rq->h_nr_running -= h_nr_running;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
 		if (cfs_rq_is_idle(cfs_rq))
-			idle_h_nr_running = 1;
+			idle_h_nr_running = h_nr_running;
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			goto dequeue_throttle;
+			return 0;
 
 		/* 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);
 			/*
@@ -6874,6 +7124,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 			break;
 		}
 		flags |= DEQUEUE_SLEEP;
+		flags &= ~(DEQUEUE_DELAYED | DEQUEUE_SPECIAL);
 	}
 
 	for_each_sched_entity(se) {
@@ -6883,28 +7134,61 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		se_update_runnable(se);
 		update_cfs_group(se);
 
-		cfs_rq->h_nr_running--;
+		se->slice = slice;
+		slice = cfs_rq_min_slice(cfs_rq);
+
+		cfs_rq->h_nr_running -= h_nr_running;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
 
 		if (cfs_rq_is_idle(cfs_rq))
-			idle_h_nr_running = 1;
+			idle_h_nr_running = h_nr_running;
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
-			goto dequeue_throttle;
-
+			return 0;
 	}
 
-	/* At this point se is NULL and we are at root level*/
-	sub_nr_running(rq, 1);
+	sub_nr_running(rq, h_nr_running);
+
+	if (rq_h_nr_running && !rq->cfs.h_nr_running)
+		dl_server_stop(&rq->fair_server);
 
 	/* balance early to pull high priority tasks */
 	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
 		rq->next_balance = jiffies;
 
-dequeue_throttle:
-	util_est_update(&rq->cfs, p, task_sleep);
+	if (p && task_delayed) {
+		SCHED_WARN_ON(!task_sleep);
+		SCHED_WARN_ON(p->on_rq != 1);
+
+		/* Fix-up what dequeue_task_fair() skipped */
+		hrtick_update(rq);
+
+		/* Fix-up what block_task() skipped. */
+		__block_task(rq, p);
+	}
+
+	return 1;
+}
+
+/*
+ * The dequeue_task method is called before nr_running is
+ * decreased. We remove the task from the rbtree and
+ * update the fair scheduling stats:
+ */
+static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
+{
+	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & DEQUEUE_SAVE))))
+		util_est_dequeue(&rq->cfs, p);
+
+	if (dequeue_entities(rq, &p->se, flags) < 0) {
+		util_est_update(&rq->cfs, p, DEQUEUE_SLEEP);
+		return false;
+	}
+
+	util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP);
 	hrtick_update(rq);
+	return true;
 }
 
 #ifdef CONFIG_SMP
@@ -7803,6 +8087,105 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p)
 }
 
 /*
+ * This function computes an effective utilization for the given CPU, to be
+ * used for frequency selection given the linear relation: f = u * f_max.
+ *
+ * The scheduler tracks the following metrics:
+ *
+ *   cpu_util_{cfs,rt,dl,irq}()
+ *   cpu_bw_dl()
+ *
+ * Where the cfs,rt and dl util numbers are tracked with the same metric and
+ * synchronized windows and are thus directly comparable.
+ *
+ * The cfs,rt,dl utilization are the running times measured with rq->clock_task
+ * which excludes things like IRQ and steal-time. These latter are then accrued
+ * in the IRQ utilization.
+ *
+ * The DL bandwidth number OTOH is not a measured metric but a value computed
+ * based on the task model parameters and gives the minimal utilization
+ * required to meet deadlines.
+ */
+unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
+				 unsigned long *min,
+				 unsigned long *max)
+{
+	unsigned long util, irq, scale;
+	struct rq *rq = cpu_rq(cpu);
+
+	scale = arch_scale_cpu_capacity(cpu);
+
+	/*
+	 * Early check to see if IRQ/steal time saturates the CPU, can be
+	 * because of inaccuracies in how we track these -- see
+	 * update_irq_load_avg().
+	 */
+	irq = cpu_util_irq(rq);
+	if (unlikely(irq >= scale)) {
+		if (min)
+			*min = scale;
+		if (max)
+			*max = scale;
+		return scale;
+	}
+
+	if (min) {
+		/*
+		 * The minimum utilization returns the highest level between:
+		 * - the computed DL bandwidth needed with the IRQ pressure which
+		 *   steals time to the deadline task.
+		 * - The minimum performance requirement for CFS and/or RT.
+		 */
+		*min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN));
+
+		/*
+		 * When an RT task is runnable and uclamp is not used, we must
+		 * ensure that the task will run at maximum compute capacity.
+		 */
+		if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt))
+			*min = max(*min, scale);
+	}
+
+	/*
+	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
+	 * CFS tasks and we use the same metric to track the effective
+	 * utilization (PELT windows are synchronized) we can directly add them
+	 * to obtain the CPU's actual utilization.
+	 */
+	util = util_cfs + cpu_util_rt(rq);
+	util += cpu_util_dl(rq);
+
+	/*
+	 * The maximum hint is a soft bandwidth requirement, which can be lower
+	 * than the actual utilization because of uclamp_max requirements.
+	 */
+	if (max)
+		*max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX));
+
+	if (util >= scale)
+		return scale;
+
+	/*
+	 * There is still idle time; further improve the number by using the
+	 * IRQ metric. Because IRQ/steal time is hidden from the task clock we
+	 * need to scale the task numbers:
+	 *
+	 *              max - irq
+	 *   U' = irq + --------- * U
+	 *                 max
+	 */
+	util = scale_irq_capacity(util, irq, scale);
+	util += irq;
+
+	return min(scale, util);
+}
+
+unsigned long sched_cpu_util(int cpu)
+{
+	return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL);
+}
+
+/*
  * energy_env - Utilization landscape for energy estimation.
  * @task_busy_time: Utilization contribution by the task for which we test the
  *                  placement. Given by eenv_task_busy_time().
@@ -8286,7 +8669,21 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 
 static void task_dead_fair(struct task_struct *p)
 {
-	remove_entity_load_avg(&p->se);
+	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);
 }
 
 /*
@@ -8322,7 +8719,7 @@ static void set_cpus_allowed_fair(struct task_struct *p, struct affinity_context
 static int
 balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	if (rq->nr_running)
+	if (sched_fair_runnable(rq))
 		return 1;
 
 	return sched_balance_newidle(rq, rf) != 0;
@@ -8381,16 +8778,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	if (test_tsk_need_resched(curr))
 		return;
 
-	/* Idle tasks are by definition preempted by non-idle tasks. */
-	if (unlikely(task_has_idle_policy(curr)) &&
-	    likely(!task_has_idle_policy(p)))
-		goto preempt;
-
-	/*
-	 * Batch and idle tasks do not preempt non-idle tasks (their preemption
-	 * is driven by the tick):
-	 */
-	if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION))
+	if (!sched_feat(WAKEUP_PREEMPTION))
 		return;
 
 	find_matching_se(&se, &pse);
@@ -8400,7 +8788,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	pse_is_idle = se_is_idle(pse);
 
 	/*
-	 * Preempt an idle group in favor of a non-idle group (and don't preempt
+	 * Preempt an idle entity in favor of a non-idle entity (and don't preempt
 	 * in the inverse case).
 	 */
 	if (cse_is_idle && !pse_is_idle)
@@ -8408,11 +8796,26 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	if (cse_is_idle != pse_is_idle)
 		return;
 
+	/*
+	 * BATCH and IDLE tasks do not preempt others.
+	 */
+	if (unlikely(p->policy != SCHED_NORMAL))
+		return;
+
 	cfs_rq = cfs_rq_of(se);
 	update_curr(cfs_rq);
+	/*
+	 * If @p has a shorter slice than current and @p is eligible, override
+	 * current's slice protection in order to allow preemption.
+	 *
+	 * Note that even if @p does not turn out to be the most eligible
+	 * task at this moment, current's slice protection will be lost.
+	 */
+	if (do_preempt_short(cfs_rq, pse, se) && se->vlag == se->deadline)
+		se->vlag = se->deadline + 1;
 
 	/*
-	 * XXX pick_eevdf(cfs_rq) != se ?
+	 * If @p has become the most eligible task, force preemption.
 	 */
 	if (pick_eevdf(cfs_rq) == pse)
 		goto preempt;
@@ -8423,7 +8826,6 @@ preempt:
 	resched_curr(rq);
 }
 
-#ifdef CONFIG_SMP
 static struct task_struct *pick_task_fair(struct rq *rq)
 {
 	struct sched_entity *se;
@@ -8435,95 +8837,58 @@ again:
 		return NULL;
 
 	do {
-		struct sched_entity *curr = cfs_rq->curr;
-
-		/* When we pick for a remote RQ, we'll not have done put_prev_entity() */
-		if (curr) {
-			if (curr->on_rq)
-				update_curr(cfs_rq);
-			else
-				curr = NULL;
+		/* Might not have done put_prev_entity() */
+		if (cfs_rq->curr && cfs_rq->curr->on_rq)
+			update_curr(cfs_rq);
 
-			if (unlikely(check_cfs_rq_runtime(cfs_rq)))
-				goto again;
-		}
+		if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+			goto again;
 
-		se = pick_next_entity(cfs_rq);
+		se = pick_next_entity(rq, cfs_rq);
+		if (!se)
+			goto again;
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
 
 	return task_of(se);
 }
-#endif
+
+static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool first);
+static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first);
 
 struct task_struct *
 pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
 	struct task_struct *p;
 	int new_tasks;
 
 again:
-	if (!sched_fair_runnable(rq))
+	p = pick_task_fair(rq);
+	if (!p)
 		goto idle;
+	se = &p->se;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	if (!prev || prev->sched_class != &fair_sched_class)
+	if (prev->sched_class != &fair_sched_class)
 		goto simple;
 
+	__put_prev_set_next_dl_server(rq, prev, p);
+
 	/*
 	 * Because of the set_next_buddy() in dequeue_task_fair() it is rather
 	 * likely that a next task is from the same cgroup as the current.
 	 *
 	 * Therefore attempt to avoid putting and setting the entire cgroup
 	 * hierarchy, only change the part that actually changes.
-	 */
-
-	do {
-		struct sched_entity *curr = cfs_rq->curr;
-
-		/*
-		 * Since we got here without doing put_prev_entity() we also
-		 * have to consider cfs_rq->curr. If it is still a runnable
-		 * entity, update_curr() will update its vruntime, otherwise
-		 * forget we've ever seen it.
-		 */
-		if (curr) {
-			if (curr->on_rq)
-				update_curr(cfs_rq);
-			else
-				curr = NULL;
-
-			/*
-			 * This call to check_cfs_rq_runtime() will do the
-			 * throttle and dequeue its entity in the parent(s).
-			 * Therefore the nr_running test will indeed
-			 * be correct.
-			 */
-			if (unlikely(check_cfs_rq_runtime(cfs_rq))) {
-				cfs_rq = &rq->cfs;
-
-				if (!cfs_rq->nr_running)
-					goto idle;
-
-				goto simple;
-			}
-		}
-
-		se = pick_next_entity(cfs_rq);
-		cfs_rq = group_cfs_rq(se);
-	} while (cfs_rq);
-
-	p = task_of(se);
-
-	/*
+	 *
 	 * Since we haven't yet done put_prev_entity and if the selected task
 	 * is a different task than we started out with, try and touch the
 	 * least amount of cfs_rqs.
 	 */
 	if (prev != p) {
 		struct sched_entity *pse = &prev->se;
+		struct cfs_rq *cfs_rq;
 
 		while (!(cfs_rq = is_same_group(se, pse))) {
 			int se_depth = se->depth;
@@ -8541,38 +8906,15 @@ again:
 
 		put_prev_entity(cfs_rq, pse);
 		set_next_entity(cfs_rq, se);
-	}
-
-	goto done;
-simple:
-#endif
-	if (prev)
-		put_prev_task(rq, prev);
 
-	do {
-		se = pick_next_entity(cfs_rq);
-		set_next_entity(cfs_rq, se);
-		cfs_rq = group_cfs_rq(se);
-	} while (cfs_rq);
+		__set_next_task_fair(rq, p, true);
+	}
 
-	p = task_of(se);
+	return p;
 
-done: __maybe_unused;
-#ifdef CONFIG_SMP
-	/*
-	 * Move the next running task to the front of
-	 * the list, so our cfs_tasks list becomes MRU
-	 * one.
-	 */
-	list_move(&p->se.group_node, &rq->cfs_tasks);
+simple:
 #endif
-
-	if (hrtick_enabled_fair(rq))
-		hrtick_start_fair(rq, p);
-
-	update_misfit_status(p, rq);
-	sched_fair_update_stop_tick(rq, p);
-
+	put_prev_set_next_task(rq, prev, p);
 	return p;
 
 idle:
@@ -8601,15 +8943,34 @@ idle:
 	return NULL;
 }
 
-static struct task_struct *__pick_next_task_fair(struct rq *rq)
+static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_struct *prev)
 {
-	return pick_next_task_fair(rq, NULL, NULL);
+	return pick_next_task_fair(rq, prev, NULL);
+}
+
+static bool fair_server_has_tasks(struct sched_dl_entity *dl_se)
+{
+	return !!dl_se->rq->cfs.nr_running;
+}
+
+static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se)
+{
+	return pick_task_fair(dl_se->rq);
+}
+
+void fair_server_init(struct rq *rq)
+{
+	struct sched_dl_entity *dl_se = &rq->fair_server;
+
+	init_dl_entity(dl_se);
+
+	dl_server_init(dl_se, rq, fair_server_has_tasks, fair_server_pick_task);
 }
 
 /*
  * Account for a descheduled task:
  */
-static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
+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;
@@ -9360,9 +9721,10 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 
 	hw_pressure = arch_scale_hw_pressure(cpu_of(rq));
 
+	/* hw_pressure doesn't care about invariance */
 	decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
 		  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
-		  update_hw_load_avg(now, rq, hw_pressure) |
+		  update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure) |
 		  update_irq_load_avg(rq, 0);
 
 	if (others_have_blocked(rq))
@@ -12702,22 +13064,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
  */
 static void task_fork_fair(struct task_struct *p)
 {
-	struct sched_entity *se = &p->se, *curr;
-	struct cfs_rq *cfs_rq;
-	struct rq *rq = this_rq();
-	struct rq_flags rf;
-
-	rq_lock(rq, &rf);
-	update_rq_clock(rq);
-
 	set_task_max_allowed_capacity(p);
-
-	cfs_rq = task_cfs_rq(current);
-	curr = cfs_rq->curr;
-	if (curr)
-		update_curr(cfs_rq);
-	place_entity(cfs_rq, se, ENQUEUE_INITIAL);
-	rq_unlock(rq, &rf);
 }
 
 /*
@@ -12829,10 +13176,28 @@ static void attach_task_cfs_rq(struct task_struct *p)
 static void switched_from_fair(struct rq *rq, struct task_struct *p)
 {
 	detach_task_cfs_rq(p);
+	/*
+	 * Since this is called after changing class, this is a little weird
+	 * and we cannot use DEQUEUE_DELAYED.
+	 */
+	if (p->se.sched_delayed) {
+		/* First, dequeue it from its new class' structures */
+		dequeue_task(rq, p, DEQUEUE_NOCLOCK | DEQUEUE_SLEEP);
+		/*
+		 * Now, clean up the fair_sched_class side of things
+		 * related to sched_delayed being true and that wasn't done
+		 * due to the generic dequeue not using DEQUEUE_DELAYED.
+		 */
+		finish_delayed_dequeue_entity(&p->se);
+		p->se.rel_deadline = 0;
+		__block_task(rq, p);
+	}
 }
 
 static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
+	SCHED_WARN_ON(p->se.sched_delayed);
+
 	attach_task_cfs_rq(p);
 
 	set_task_max_allowed_capacity(p);
@@ -12850,12 +13215,7 @@ 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)
+static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 {
 	struct sched_entity *se = &p->se;
 
@@ -12868,6 +13228,27 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 		list_move(&se->group_node, &rq->cfs_tasks);
 	}
 #endif
+	if (!first)
+		return;
+
+	SCHED_WARN_ON(se->sched_delayed);
+
+	if (hrtick_enabled_fair(rq))
+		hrtick_start_fair(rq, p);
+
+	update_misfit_status(p, rq);
+	sched_fair_update_stop_tick(rq, 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;
 
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
@@ -12876,12 +13257,14 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 		/* ensure bandwidth has been allocated on our new cfs_rq */
 		account_cfs_rq_runtime(cfs_rq, 0);
 	}
+
+	__set_next_task_fair(rq, p, first);
 }
 
 void init_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	cfs_rq->tasks_timeline = RB_ROOT_CACHED;
-	u64_u32_store(cfs_rq->min_vruntime, (u64)(-(1LL << 20)));
+	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
 #ifdef CONFIG_SMP
 	raw_spin_lock_init(&cfs_rq->removed.lock);
 #endif
@@ -12983,28 +13366,35 @@ void online_fair_sched_group(struct task_group *tg)
 
 void unregister_fair_sched_group(struct task_group *tg)
 {
-	unsigned long flags;
-	struct rq *rq;
 	int cpu;
 
 	destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
 	for_each_possible_cpu(cpu) {
-		if (tg->se[cpu])
-			remove_entity_load_avg(tg->se[cpu]);
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu];
+		struct sched_entity *se = tg->se[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);
+			}
+			remove_entity_load_avg(se);
+		}
 
 		/*
 		 * Only empty task groups can be destroyed; so we can speculatively
 		 * check on_list without danger of it being re-added.
 		 */
-		if (!tg->cfs_rq[cpu]->on_list)
-			continue;
-
-		rq = cpu_rq(cpu);
-
-		raw_spin_rq_lock_irqsave(rq, flags);
-		list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
-		raw_spin_rq_unlock_irqrestore(rq, flags);
+		if (cfs_rq->on_list) {
+			guard(rq_lock_irqsave)(rq);
+			list_del_leaf_cfs_rq(cfs_rq);
+		}
 	}
 }
 
@@ -13194,13 +13584,13 @@ DEFINE_SCHED_CLASS(fair) = {
 
 	.wakeup_preempt		= check_preempt_wakeup_fair,
 
+	.pick_task		= pick_task_fair,
 	.pick_next_task		= __pick_next_task_fair,
 	.put_prev_task		= put_prev_task_fair,
 	.set_next_task          = set_next_task_fair,
 
 #ifdef CONFIG_SMP
 	.balance		= balance_fair,
-	.pick_task		= pick_task_fair,
 	.select_task_rq		= select_task_rq_fair,
 	.migrate_task_rq	= migrate_task_rq_fair,
 
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 143f55df890b..290874079f60 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -5,8 +5,24 @@
  * sleep+wake cycles. EEVDF placement strategy #1, #2 if disabled.
  */
 SCHED_FEAT(PLACE_LAG, true)
+/*
+ * Give new tasks half a slice to ease into the competition.
+ */
 SCHED_FEAT(PLACE_DEADLINE_INITIAL, true)
+/*
+ * Preserve relative virtual deadline on 'migration'.
+ */
+SCHED_FEAT(PLACE_REL_DEADLINE, true)
+/*
+ * Inhibit (wakeup) preemption until the current task has either matched the
+ * 0-lag point or until is has exhausted it's slice.
+ */
 SCHED_FEAT(RUN_TO_PARITY, true)
+/*
+ * Allow wakeup of tasks with a shorter slice to cancel RESPECT_SLICE for
+ * current.
+ */
+SCHED_FEAT(PREEMPT_SHORT, true)
 
 /*
  * Prefer to schedule the task we woke last (assuming it failed
@@ -22,6 +38,18 @@ SCHED_FEAT(NEXT_BUDDY, false)
 SCHED_FEAT(CACHE_HOT_BUDDY, true)
 
 /*
+ * Delay dequeueing tasks until they get selected or woken.
+ *
+ * By delaying the dequeue for non-eligible tasks, they remain in the
+ * competition and can burn off their negative lag. When they get selected
+ * they'll have positive lag by definition.
+ *
+ * DELAY_ZERO clips the lag on dequeue (or wakeup) to 0.
+ */
+SCHED_FEAT(DELAY_DEQUEUE, true)
+SCHED_FEAT(DELAY_ZERO, true)
+
+/*
  * Allow wakeup-time preemption of the current task:
  */
 SCHED_FEAT(WAKEUP_PREEMPTION, true)
@@ -85,5 +113,3 @@ SCHED_FEAT(WA_BIAS, true)
 SCHED_FEAT(UTIL_EST, true)
 
 SCHED_FEAT(LATENCY_WARN, false)
-
-SCHED_FEAT(HZ_BW, true)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 6e78d071beb5..7a105a0123aa 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -450,43 +450,35 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
 	resched_curr(rq);
 }
 
-static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next)
 {
+	dl_server_update_idle_time(rq, prev);
 }
 
 static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
 {
 	update_idle_core(rq);
 	schedstat_inc(rq->sched_goidle);
+	next->se.exec_start = rq_clock_task(rq);
 }
 
-#ifdef CONFIG_SMP
-static struct task_struct *pick_task_idle(struct rq *rq)
+struct task_struct *pick_task_idle(struct rq *rq)
 {
 	return rq->idle;
 }
-#endif
-
-struct task_struct *pick_next_task_idle(struct rq *rq)
-{
-	struct task_struct *next = rq->idle;
-
-	set_next_task_idle(rq, next, true);
-
-	return next;
-}
 
 /*
  * It is not legal to sleep in the idle task - print a warning
  * message if some code attempts to do it:
  */
-static void
+static bool
 dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 {
 	raw_spin_rq_unlock_irq(rq);
 	printk(KERN_ERR "bad: scheduling from the idle thread!\n");
 	dump_stack();
 	raw_spin_rq_lock_irq(rq);
+	return true;
 }
 
 /*
@@ -528,13 +520,12 @@ DEFINE_SCHED_CLASS(idle) = {
 
 	.wakeup_preempt		= wakeup_preempt_idle,
 
-	.pick_next_task		= pick_next_task_idle,
+	.pick_task		= pick_task_idle,
 	.put_prev_task		= put_prev_task_idle,
 	.set_next_task          = set_next_task_idle,
 
 #ifdef CONFIG_SMP
 	.balance		= balance_idle,
-	.pick_task		= pick_task_idle,
 	.select_task_rq		= select_task_rq_idle,
 	.set_cpus_allowed	= set_cpus_allowed_common,
 #endif
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 310523c1b9e3..172c588de542 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -8,10 +8,6 @@ int sched_rr_timeslice = RR_TIMESLICE;
 /* More than 4 hours if BW_SHIFT equals 20. */
 static const u64 max_rt_runtime = MAX_BW;
 
-static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
-
-struct rt_bandwidth def_rt_bandwidth;
-
 /*
  * period over which we measure -rt task CPU usage in us.
  * default: 1s
@@ -66,6 +62,40 @@ static int __init sched_rt_sysctl_init(void)
 late_initcall(sched_rt_sysctl_init);
 #endif
 
+void init_rt_rq(struct rt_rq *rt_rq)
+{
+	struct rt_prio_array *array;
+	int i;
+
+	array = &rt_rq->active;
+	for (i = 0; i < MAX_RT_PRIO; i++) {
+		INIT_LIST_HEAD(array->queue + i);
+		__clear_bit(i, array->bitmap);
+	}
+	/* delimiter for bitsearch: */
+	__set_bit(MAX_RT_PRIO, array->bitmap);
+
+#if defined CONFIG_SMP
+	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
+	rt_rq->highest_prio.next = MAX_RT_PRIO-1;
+	rt_rq->overloaded = 0;
+	plist_head_init(&rt_rq->pushable_tasks);
+#endif /* CONFIG_SMP */
+	/* We start is dequeued state, because no RT tasks are queued */
+	rt_rq->rt_queued = 0;
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	rt_rq->rt_time = 0;
+	rt_rq->rt_throttled = 0;
+	rt_rq->rt_runtime = 0;
+	raw_spin_lock_init(&rt_rq->rt_runtime_lock);
+#endif
+}
+
+#ifdef CONFIG_RT_GROUP_SCHED
+
+static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
+
 static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
 {
 	struct rt_bandwidth *rt_b =
@@ -130,35 +160,6 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	do_start_rt_bandwidth(rt_b);
 }
 
-void init_rt_rq(struct rt_rq *rt_rq)
-{
-	struct rt_prio_array *array;
-	int i;
-
-	array = &rt_rq->active;
-	for (i = 0; i < MAX_RT_PRIO; i++) {
-		INIT_LIST_HEAD(array->queue + i);
-		__clear_bit(i, array->bitmap);
-	}
-	/* delimiter for bit-search: */
-	__set_bit(MAX_RT_PRIO, array->bitmap);
-
-#if defined CONFIG_SMP
-	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
-	rt_rq->highest_prio.next = MAX_RT_PRIO-1;
-	rt_rq->overloaded = 0;
-	plist_head_init(&rt_rq->pushable_tasks);
-#endif /* CONFIG_SMP */
-	/* We start is dequeued state, because no RT tasks are queued */
-	rt_rq->rt_queued = 0;
-
-	rt_rq->rt_time = 0;
-	rt_rq->rt_throttled = 0;
-	rt_rq->rt_runtime = 0;
-	raw_spin_lock_init(&rt_rq->rt_runtime_lock);
-}
-
-#ifdef CONFIG_RT_GROUP_SCHED
 static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
 	hrtimer_cancel(&rt_b->rt_period_timer);
@@ -195,7 +196,6 @@ void unregister_rt_sched_group(struct task_group *tg)
 {
 	if (tg->rt_se)
 		destroy_rt_bandwidth(&tg->rt_bandwidth);
-
 }
 
 void free_rt_sched_group(struct task_group *tg)
@@ -253,8 +253,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 	if (!tg->rt_se)
 		goto err;
 
-	init_rt_bandwidth(&tg->rt_bandwidth,
-			ktime_to_ns(def_rt_bandwidth.rt_period), 0);
+	init_rt_bandwidth(&tg->rt_bandwidth, ktime_to_ns(global_rt_period()), 0);
 
 	for_each_possible_cpu(i) {
 		rt_rq = kzalloc_node(sizeof(struct rt_rq),
@@ -604,70 +603,6 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 	return &rt_rq->tg->rt_bandwidth;
 }
 
-#else /* !CONFIG_RT_GROUP_SCHED */
-
-static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_runtime;
-}
-
-static inline u64 sched_rt_period(struct rt_rq *rt_rq)
-{
-	return ktime_to_ns(def_rt_bandwidth.rt_period);
-}
-
-typedef struct rt_rq *rt_rq_iter_t;
-
-#define for_each_rt_rq(rt_rq, iter, rq) \
-	for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
-
-#define for_each_sched_rt_entity(rt_se) \
-	for (; rt_se; rt_se = NULL)
-
-static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
-{
-	return NULL;
-}
-
-static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
-{
-	struct rq *rq = rq_of_rt_rq(rt_rq);
-
-	if (!rt_rq->rt_nr_running)
-		return;
-
-	enqueue_top_rt_rq(rt_rq);
-	resched_curr(rq);
-}
-
-static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
-{
-	dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
-}
-
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_throttled;
-}
-
-static inline const struct cpumask *sched_rt_period_mask(void)
-{
-	return cpu_online_mask;
-}
-
-static inline
-struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
-{
-	return &cpu_rq(cpu)->rt;
-}
-
-static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
-{
-	return &def_rt_bandwidth;
-}
-
-#endif /* CONFIG_RT_GROUP_SCHED */
-
 bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
 {
 	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
@@ -859,7 +794,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	const struct cpumask *span;
 
 	span = sched_rt_period_mask();
-#ifdef CONFIG_RT_GROUP_SCHED
+
 	/*
 	 * FIXME: isolated CPUs should really leave the root task group,
 	 * whether they are isolcpus or were isolated via cpusets, lest
@@ -871,7 +806,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	 */
 	if (rt_b == &root_task_group.rt_bandwidth)
 		span = cpu_online_mask;
-#endif
+
 	for_each_cpu(i, span) {
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
@@ -938,18 +873,6 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	return idle;
 }
 
-static inline int rt_se_prio(struct sched_rt_entity *rt_se)
-{
-#ifdef CONFIG_RT_GROUP_SCHED
-	struct rt_rq *rt_rq = group_rt_rq(rt_se);
-
-	if (rt_rq)
-		return rt_rq->highest_prio.curr;
-#endif
-
-	return rt_task_of(rt_se)->prio;
-}
-
 static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 {
 	u64 runtime = sched_rt_runtime(rt_rq);
@@ -993,6 +916,72 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 	return 0;
 }
 
+#else /* !CONFIG_RT_GROUP_SCHED */
+
+typedef struct rt_rq *rt_rq_iter_t;
+
+#define for_each_rt_rq(rt_rq, iter, rq) \
+	for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
+
+#define for_each_sched_rt_entity(rt_se) \
+	for (; rt_se; rt_se = NULL)
+
+static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
+{
+	return NULL;
+}
+
+static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
+{
+	struct rq *rq = rq_of_rt_rq(rt_rq);
+
+	if (!rt_rq->rt_nr_running)
+		return;
+
+	enqueue_top_rt_rq(rt_rq);
+	resched_curr(rq);
+}
+
+static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
+{
+	dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
+}
+
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+	return false;
+}
+
+static inline const struct cpumask *sched_rt_period_mask(void)
+{
+	return cpu_online_mask;
+}
+
+static inline
+struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
+{
+	return &cpu_rq(cpu)->rt;
+}
+
+#ifdef CONFIG_SMP
+static void __enable_runtime(struct rq *rq) { }
+static void __disable_runtime(struct rq *rq) { }
+#endif
+
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+static inline int rt_se_prio(struct sched_rt_entity *rt_se)
+{
+#ifdef CONFIG_RT_GROUP_SCHED
+	struct rt_rq *rt_rq = group_rt_rq(rt_se);
+
+	if (rt_rq)
+		return rt_rq->highest_prio.curr;
+#endif
+
+	return rt_task_of(rt_se)->prio;
+}
+
 /*
  * Update the current task's runtime statistics. Skip current tasks that
  * are not in our scheduling class.
@@ -1000,7 +989,6 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 static void update_curr_rt(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
-	struct sched_rt_entity *rt_se = &curr->rt;
 	s64 delta_exec;
 
 	if (curr->sched_class != &rt_sched_class)
@@ -1010,6 +998,9 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely(delta_exec <= 0))
 		return;
 
+#ifdef CONFIG_RT_GROUP_SCHED
+	struct sched_rt_entity *rt_se = &curr->rt;
+
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -1028,6 +1019,7 @@ static void update_curr_rt(struct rq *rq)
 				do_start_rt_bandwidth(sched_rt_bandwidth(rt_rq));
 		}
 	}
+#endif
 }
 
 static void
@@ -1184,7 +1176,6 @@ dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 static void
 inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
-	start_rt_bandwidth(&def_rt_bandwidth);
 }
 
 static inline
@@ -1492,7 +1483,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 		enqueue_pushable_task(rq, p);
 }
 
-static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
+static bool dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 
@@ -1500,6 +1491,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_rt_entity(rt_se, flags);
 
 	dequeue_pushable_task(rq, p);
+
+	return true;
 }
 
 /*
@@ -1755,17 +1748,7 @@ static struct task_struct *pick_task_rt(struct rq *rq)
 	return p;
 }
 
-static struct task_struct *pick_next_task_rt(struct rq *rq)
-{
-	struct task_struct *p = pick_task_rt(rq);
-
-	if (p)
-		set_next_task_rt(rq, p, true);
-
-	return p;
-}
-
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_struct *next)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 	struct rt_rq *rt_rq = &rq->rt;
@@ -2652,13 +2635,12 @@ DEFINE_SCHED_CLASS(rt) = {
 
 	.wakeup_preempt		= wakeup_preempt_rt,
 
-	.pick_next_task		= pick_next_task_rt,
+	.pick_task		= pick_task_rt,
 	.put_prev_task		= put_prev_task_rt,
 	.set_next_task          = set_next_task_rt,
 
 #ifdef CONFIG_SMP
 	.balance		= balance_rt,
-	.pick_task		= pick_task_rt,
 	.select_task_rq		= select_task_rq_rt,
 	.set_cpus_allowed       = set_cpus_allowed_common,
 	.rq_online              = rq_online_rt,
@@ -2912,19 +2894,6 @@ int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 #ifdef CONFIG_SYSCTL
 static int sched_rt_global_constraints(void)
 {
-	unsigned long flags;
-	int i;
-
-	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
-	for_each_possible_cpu(i) {
-		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
-
-		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_runtime = global_rt_runtime();
-		raw_spin_unlock(&rt_rq->rt_runtime_lock);
-	}
-	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
-
 	return 0;
 }
 #endif /* CONFIG_SYSCTL */
@@ -2944,12 +2913,6 @@ static int sched_rt_global_validate(void)
 
 static void sched_rt_do_global(void)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
-	def_rt_bandwidth.rt_runtime = global_rt_runtime();
-	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
-	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 }
 
 static int sched_rt_handler(const struct ctl_table *table, int write, void *buffer,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4c36cc680361..3744f16a1293 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -68,6 +68,7 @@
 #include <linux/wait_api.h>
 #include <linux/wait_bit.h>
 #include <linux/workqueue_api.h>
+#include <linux/delayacct.h>
 
 #include <trace/events/power.h>
 #include <trace/events/sched.h>
@@ -335,7 +336,7 @@ extern bool __checkparam_dl(const struct sched_attr *attr);
 extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
 extern int  dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
 extern int  dl_bw_check_overflow(int cpu);
-
+extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec);
 /*
  * SCHED_DEADLINE supports servers (nested scheduling) with the following
  * interface:
@@ -361,7 +362,14 @@ extern void dl_server_start(struct sched_dl_entity *dl_se);
 extern void dl_server_stop(struct sched_dl_entity *dl_se);
 extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 		    dl_server_has_tasks_f has_tasks,
-		    dl_server_pick_f pick);
+		    dl_server_pick_f pick_task);
+
+extern void dl_server_update_idle_time(struct rq *rq,
+		    struct task_struct *p);
+extern void fair_server_init(struct rq *rq);
+extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq);
+extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
+		    u64 runtime, u64 period, bool init);
 
 #ifdef CONFIG_CGROUP_SCHED
 
@@ -599,17 +607,12 @@ struct cfs_rq {
 	s64			avg_vruntime;
 	u64			avg_load;
 
-	u64			exec_clock;
 	u64			min_vruntime;
 #ifdef CONFIG_SCHED_CORE
 	unsigned int		forceidle_seq;
 	u64			min_vruntime_fi;
 #endif
 
-#ifndef CONFIG_64BIT
-	u64			min_vruntime_copy;
-#endif
-
 	struct rb_root_cached	tasks_timeline;
 
 	/*
@@ -619,10 +622,6 @@ struct cfs_rq {
 	struct sched_entity	*curr;
 	struct sched_entity	*next;
 
-#ifdef	CONFIG_SCHED_DEBUG
-	unsigned int		nr_spread_over;
-#endif
-
 #ifdef CONFIG_SMP
 	/*
 	 * CFS load tracking
@@ -726,13 +725,13 @@ struct rt_rq {
 #endif /* CONFIG_SMP */
 	int			rt_queued;
 
+#ifdef CONFIG_RT_GROUP_SCHED
 	int			rt_throttled;
 	u64			rt_time;
 	u64			rt_runtime;
 	/* Nests inside the rq lock: */
 	raw_spinlock_t		rt_runtime_lock;
 
-#ifdef CONFIG_RT_GROUP_SCHED
 	unsigned int		rt_nr_boosted;
 
 	struct rq		*rq;
@@ -820,6 +819,9 @@ static inline void se_update_runnable(struct sched_entity *se)
 
 static inline long se_runnable(struct sched_entity *se)
 {
+	if (se->sched_delayed)
+		return false;
+
 	if (entity_is_task(se))
 		return !!se->on_rq;
 	else
@@ -834,6 +836,9 @@ static inline void se_update_runnable(struct sched_entity *se) { }
 
 static inline long se_runnable(struct sched_entity *se)
 {
+	if (se->sched_delayed)
+		return false;
+
 	return !!se->on_rq;
 }
 
@@ -1044,6 +1049,8 @@ struct rq {
 	struct rt_rq		rt;
 	struct dl_rq		dl;
 
+	struct sched_dl_entity	fair_server;
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this CPU: */
 	struct list_head	leaf_cfs_rq_list;
@@ -1059,6 +1066,7 @@ struct rq {
 	unsigned int		nr_uninterruptible;
 
 	struct task_struct __rcu	*curr;
+	struct sched_dl_entity	*dl_server;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
 	unsigned long		next_balance;
@@ -1158,7 +1166,6 @@ struct rq {
 	/* latency stats */
 	struct sched_info	rq_sched_info;
 	unsigned long long	rq_cpu_time;
-	/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
 
 	/* sys_sched_yield() stats */
 	unsigned int		yld_count;
@@ -1187,6 +1194,7 @@ struct rq {
 	/* per rq */
 	struct rq		*core;
 	struct task_struct	*core_pick;
+	struct sched_dl_entity	*core_dl_server;
 	unsigned int		core_enabled;
 	unsigned int		core_sched_seq;
 	struct rb_root		core_tree;
@@ -2247,11 +2255,13 @@ extern const u32		sched_prio_to_wmult[40];
  *
  */
 
-#define DEQUEUE_SLEEP		0x01
+#define DEQUEUE_SLEEP		0x01 /* Matches ENQUEUE_WAKEUP */
 #define DEQUEUE_SAVE		0x02 /* Matches ENQUEUE_RESTORE */
 #define DEQUEUE_MOVE		0x04 /* Matches ENQUEUE_MOVE */
 #define DEQUEUE_NOCLOCK		0x08 /* Matches ENQUEUE_NOCLOCK */
+#define DEQUEUE_SPECIAL		0x10
 #define DEQUEUE_MIGRATING	0x100 /* Matches ENQUEUE_MIGRATING */
+#define DEQUEUE_DELAYED		0x200 /* Matches ENQUEUE_DELAYED */
 
 #define ENQUEUE_WAKEUP		0x01
 #define ENQUEUE_RESTORE		0x02
@@ -2267,6 +2277,7 @@ extern const u32		sched_prio_to_wmult[40];
 #endif
 #define ENQUEUE_INITIAL		0x80
 #define ENQUEUE_MIGRATING	0x100
+#define ENQUEUE_DELAYED		0x200
 
 #define RETRY_TASK		((void *)-1UL)
 
@@ -2285,23 +2296,31 @@ struct sched_class {
 #endif
 
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
-	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
+	bool (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*yield_task)   (struct rq *rq);
 	bool (*yield_to_task)(struct rq *rq, struct task_struct *p);
 
 	void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags);
 
-	struct task_struct *(*pick_next_task)(struct rq *rq);
+	struct task_struct *(*pick_task)(struct rq *rq);
+	/*
+	 * Optional! When implemented pick_next_task() should be equivalent to:
+	 *
+	 *   next = pick_task();
+	 *   if (next) {
+	 *       put_prev_task(prev);
+	 *       set_next_task_first(next);
+	 *   }
+	 */
+	struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev);
 
-	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
+	void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct task_struct *next);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
 
 #ifdef CONFIG_SMP
 	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
 
-	struct task_struct * (*pick_task)(struct rq *rq);
-
 	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
 
 	void (*task_woken)(struct rq *this_rq, struct task_struct *task);
@@ -2345,7 +2364,7 @@ struct sched_class {
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	WARN_ON_ONCE(rq->curr != prev);
-	prev->sched_class->put_prev_task(rq, prev);
+	prev->sched_class->put_prev_task(rq, prev, NULL);
 }
 
 static inline void set_next_task(struct rq *rq, struct task_struct *next)
@@ -2353,6 +2372,30 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next)
 	next->sched_class->set_next_task(rq, next, false);
 }
 
+static inline void
+__put_prev_set_next_dl_server(struct rq *rq,
+			      struct task_struct *prev,
+			      struct task_struct *next)
+{
+	prev->dl_server = NULL;
+	next->dl_server = rq->dl_server;
+	rq->dl_server = NULL;
+}
+
+static inline void put_prev_set_next_task(struct rq *rq,
+					  struct task_struct *prev,
+					  struct task_struct *next)
+{
+	WARN_ON_ONCE(rq->curr != prev);
+
+	__put_prev_set_next_dl_server(rq, prev, next);
+
+	if (next == prev)
+		return;
+
+	prev->sched_class->put_prev_task(rq, prev, next);
+	next->sched_class->set_next_task(rq, next, true);
+}
 
 /*
  * Helper to define a sched_class instance; each one is placed in a separate
@@ -2408,7 +2451,7 @@ static inline bool sched_fair_runnable(struct rq *rq)
 }
 
 extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
-extern struct task_struct *pick_next_task_idle(struct rq *rq);
+extern struct task_struct *pick_task_idle(struct rq *rq);
 
 #define SCA_CHECK		0x01
 #define SCA_MIGRATE_DISABLE	0x02
@@ -2515,7 +2558,6 @@ extern void reweight_task(struct task_struct *p, const struct load_weight *lw);
 extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);
 
-extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
 
@@ -2586,6 +2628,19 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)
 	sched_update_tick_dependency(rq);
 }
 
+static inline void __block_task(struct rq *rq, struct task_struct *p)
+{
+	WRITE_ONCE(p->on_rq, 0);
+	ASSERT_EXCLUSIVE_WRITER(p->on_rq);
+	if (p->sched_contributes_to_load)
+		rq->nr_uninterruptible++;
+
+	if (p->in_iowait) {
+		atomic_inc(&rq->nr_iowait);
+		delayacct_blkio_start();
+	}
+}
+
 extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
 extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
@@ -3607,7 +3662,7 @@ extern int __sched_setaffinity(struct task_struct *p, struct affinity_context *c
 extern void __setscheduler_prio(struct task_struct *p, int prio);
 extern void set_load_weight(struct task_struct *p, bool update_load);
 extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags);
-extern void dequeue_task(struct rq *rq, struct task_struct *p, int flags);
+extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags);
 
 extern void check_class_changed(struct rq *rq, struct task_struct *p,
 				const struct sched_class *prev_class,
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index b1b8fe61c532..058dd42e3d9b 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -41,26 +41,17 @@ static struct task_struct *pick_task_stop(struct rq *rq)
 	return rq->stop;
 }
 
-static struct task_struct *pick_next_task_stop(struct rq *rq)
-{
-	struct task_struct *p = pick_task_stop(rq);
-
-	if (p)
-		set_next_task_stop(rq, p, true);
-
-	return p;
-}
-
 static void
 enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
 	add_nr_running(rq, 1);
 }
 
-static void
+static bool
 dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
 	sub_nr_running(rq, 1);
+	return true;
 }
 
 static void yield_task_stop(struct rq *rq)
@@ -68,7 +59,7 @@ static void yield_task_stop(struct rq *rq)
 	BUG(); /* the stop task should never yield, its pointless. */
 }
 
-static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct task_struct *next)
 {
 	update_curr_common(rq);
 }
@@ -111,13 +102,12 @@ DEFINE_SCHED_CLASS(stop) = {
 
 	.wakeup_preempt		= wakeup_preempt_stop,
 
-	.pick_next_task		= pick_next_task_stop,
+	.pick_task		= pick_task_stop,
 	.put_prev_task		= put_prev_task_stop,
 	.set_next_task          = set_next_task_stop,
 
 #ifdef CONFIG_SMP
 	.balance		= balance_stop,
-	.pick_task		= pick_task_stop,
 	.select_task_rq		= select_task_rq_stop,
 	.set_cpus_allowed	= set_cpus_allowed_common,
 #endif
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 195d2f2834a9..cb03c790c27a 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -57,7 +57,7 @@ static int effective_prio(struct task_struct *p)
 	 * keep the priority unchanged. Otherwise, update priority
 	 * to the normal priority:
 	 */
-	if (!rt_prio(p->prio))
+	if (!rt_or_dl_prio(p->prio))
 		return p->normal_prio;
 	return p->prio;
 }
@@ -258,107 +258,6 @@ int sched_core_idle_cpu(int cpu)
 
 #endif
 
-#ifdef CONFIG_SMP
-/*
- * This function computes an effective utilization for the given CPU, to be
- * used for frequency selection given the linear relation: f = u * f_max.
- *
- * The scheduler tracks the following metrics:
- *
- *   cpu_util_{cfs,rt,dl,irq}()
- *   cpu_bw_dl()
- *
- * Where the cfs,rt and dl util numbers are tracked with the same metric and
- * synchronized windows and are thus directly comparable.
- *
- * The cfs,rt,dl utilization are the running times measured with rq->clock_task
- * which excludes things like IRQ and steal-time. These latter are then accrued
- * in the IRQ utilization.
- *
- * The DL bandwidth number OTOH is not a measured metric but a value computed
- * based on the task model parameters and gives the minimal utilization
- * required to meet deadlines.
- */
-unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
-				 unsigned long *min,
-				 unsigned long *max)
-{
-	unsigned long util, irq, scale;
-	struct rq *rq = cpu_rq(cpu);
-
-	scale = arch_scale_cpu_capacity(cpu);
-
-	/*
-	 * Early check to see if IRQ/steal time saturates the CPU, can be
-	 * because of inaccuracies in how we track these -- see
-	 * update_irq_load_avg().
-	 */
-	irq = cpu_util_irq(rq);
-	if (unlikely(irq >= scale)) {
-		if (min)
-			*min = scale;
-		if (max)
-			*max = scale;
-		return scale;
-	}
-
-	if (min) {
-		/*
-		 * The minimum utilization returns the highest level between:
-		 * - the computed DL bandwidth needed with the IRQ pressure which
-		 *   steals time to the deadline task.
-		 * - The minimum performance requirement for CFS and/or RT.
-		 */
-		*min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN));
-
-		/*
-		 * When an RT task is runnable and uclamp is not used, we must
-		 * ensure that the task will run at maximum compute capacity.
-		 */
-		if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt))
-			*min = max(*min, scale);
-	}
-
-	/*
-	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
-	 * CFS tasks and we use the same metric to track the effective
-	 * utilization (PELT windows are synchronized) we can directly add them
-	 * to obtain the CPU's actual utilization.
-	 */
-	util = util_cfs + cpu_util_rt(rq);
-	util += cpu_util_dl(rq);
-
-	/*
-	 * The maximum hint is a soft bandwidth requirement, which can be lower
-	 * than the actual utilization because of uclamp_max requirements.
-	 */
-	if (max)
-		*max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX));
-
-	if (util >= scale)
-		return scale;
-
-	/*
-	 * There is still idle time; further improve the number by using the
-	 * IRQ metric. Because IRQ/steal time is hidden from the task clock we
-	 * need to scale the task numbers:
-	 *
-	 *              max - irq
-	 *   U' = irq + --------- * U
-	 *                 max
-	 */
-	util = scale_irq_capacity(util, irq, scale);
-	util += irq;
-
-	return min(scale, util);
-}
-
-unsigned long sched_cpu_util(int cpu)
-{
-	return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL);
-}
-#endif /* CONFIG_SMP */
-
 /**
  * find_process_by_pid - find a process with a matching PID value.
  * @pid: the pid in question.
@@ -401,13 +300,23 @@ static void __setscheduler_params(struct task_struct *p,
 
 	p->policy = policy;
 
-	if (dl_policy(policy))
+	if (dl_policy(policy)) {
 		__setparam_dl(p, attr);
-	else if (fair_policy(policy))
+	} else if (fair_policy(policy)) {
 		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+		if (attr->sched_runtime) {
+			p->se.custom_slice = 1;
+			p->se.slice = clamp_t(u64, attr->sched_runtime,
+					      NSEC_PER_MSEC/10,   /* HZ=1000 * 10 */
+					      NSEC_PER_MSEC*100); /* HZ=100  / 10 */
+		} else {
+			p->se.custom_slice = 0;
+			p->se.slice = sysctl_sched_base_slice;
+		}
+	}
 
 	/* rt-policy tasks do not have a timerslack */
-	if (task_is_realtime(p)) {
+	if (rt_or_dl_task_policy(p)) {
 		p->timer_slack_ns = 0;
 	} else if (p->timer_slack_ns == 0) {
 		/* when switching back to non-rt policy, restore timerslack */
@@ -708,7 +617,9 @@ recheck:
 	 * but store a possible modification of reset_on_fork.
 	 */
 	if (unlikely(policy == p->policy)) {
-		if (fair_policy(policy) && attr->sched_nice != task_nice(p))
+		if (fair_policy(policy) &&
+		    (attr->sched_nice != task_nice(p) ||
+		     (attr->sched_runtime != p->se.slice)))
 			goto change;
 		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
 			goto change;
@@ -854,6 +765,9 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
 		.sched_nice	= PRIO_TO_NICE(p->static_prio),
 	};
 
+	if (p->se.custom_slice)
+		attr.sched_runtime = p->se.slice;
+
 	/* Fixup the legacy SCHED_RESET_ON_FORK hack. */
 	if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
 		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
@@ -1020,12 +934,14 @@ err_size:
 
 static void get_params(struct task_struct *p, struct sched_attr *attr)
 {
-	if (task_has_dl_policy(p))
+	if (task_has_dl_policy(p)) {
 		__getparam_dl(p, attr);
-	else if (task_has_rt_policy(p))
+	} else if (task_has_rt_policy(p)) {
 		attr->sched_priority = p->rt_priority;
-	else
+	} else {
 		attr->sched_nice = task_nice(p);
+		attr->sched_runtime = p->se.slice;
+	}
 }
 
 /**
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 76504b776d03..9748a4c8d668 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -516,6 +516,14 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
 		set_rq_online(rq);
 
+	/*
+	 * Because the rq is not a task, dl_add_task_root_domain() did not
+	 * move the fair server bw to the rd if it already started.
+	 * Add it now.
+	 */
+	if (rq->fair_server.dl_server)
+		__dl_server_attach_root(&rq->fair_server, rq);
+
 	rq_unlock_irqrestore(rq, &rf);
 
 	if (old_rd)