Merge branch 'tip/sched/core' into for-6.12

To receive 863ccdbb91 ("sched: Allow sched_class::dequeue_task() to fail")
which makes sched_class.dequeue_task() return bool instead of void. This
leads to compile breakage and will be fixed by a follow-up patch.

Signed-off-by: Tejun Heo <tj@kernel.org>

fs/bcachefs/six.c

@@ -335,7 +335,7 @@ static inline bool six_owner_running(struct six_lock *lock)
 	 */
 	rcu_read_lock();
 	struct task_struct *owner = READ_ONCE(lock->owner);
-	bool ret = owner ? owner_on_cpu(owner) : !rt_task(current);
+	bool ret = owner ? owner_on_cpu(owner) : !rt_or_dl_task(current);
 	rcu_read_unlock();
 
 	return ret;

fs/select.c

@@ -82,7 +82,7 @@ u64 select_estimate_accuracy(struct timespec64 *tv)
 	 * Realtime tasks get a slack of 0 for obvious reasons.
 	 */
 
-	if (rt_task(current))
+	if (rt_or_dl_task(current))
 		return 0;
 
 	ktime_get_ts64(&now);

include/linux/ioprio.h

@@ -40,7 +40,7 @@ static inline int task_nice_ioclass(struct task_struct *task)
 {
 	if (task->policy == SCHED_IDLE)
 		return IOPRIO_CLASS_IDLE;
-	else if (task_is_realtime(task))
+	else if (rt_or_dl_task_policy(task))
 		return IOPRIO_CLASS_RT;
 	else
 		return IOPRIO_CLASS_BE;

include/linux/sched.h

@@ -151,8 +151,9 @@ struct user_event_mm;
  * Special states are those that do not use the normal wait-loop pattern. See
  * the comment with set_special_state().
  */
-#define is_special_task_state(state)				\
+#define is_special_task_state(state)					\
-	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD))
+	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED |	\
+		    TASK_DEAD | TASK_FROZEN))
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 # define debug_normal_state_change(state_value)				\
@@ -543,9 +544,14 @@ struct sched_entity {
 	struct rb_node			run_node;
 	u64				deadline;
 	u64				min_vruntime;
+	u64				min_slice;
 
 	struct list_head		group_node;
-	unsigned int			on_rq;
+	unsigned char			on_rq;
+	unsigned char			sched_delayed;
+	unsigned char			rel_deadline;
+	unsigned char			custom_slice;
+					/* hole */
 
 	u64				exec_start;
 	u64				sum_exec_runtime;

include/linux/sched/deadline.h

@@ -10,16 +10,16 @@
 
 #include <linux/sched.h>
 
-#define MAX_DL_PRIO		0
+static inline bool dl_prio(int prio)
-
-static inline int dl_prio(int prio)
 {
-	if (unlikely(prio < MAX_DL_PRIO))
+	return unlikely(prio < MAX_DL_PRIO);
-		return 1;
-	return 0;
 }
 
-static inline int dl_task(struct task_struct *p)
+/*
+ * Returns true if a task has a priority that belongs to DL class. PI-boosted
+ * tasks will return true. Use dl_policy() to ignore PI-boosted tasks.
+ */
+static inline bool dl_task(struct task_struct *p)
 {
 	return dl_prio(p->prio);
 }

include/linux/sched/prio.h

@@ -14,6 +14,7 @@
  */
 
 #define MAX_RT_PRIO		100
+#define MAX_DL_PRIO		0
 
 #define MAX_PRIO		(MAX_RT_PRIO + NICE_WIDTH)
 #define DEFAULT_PRIO		(MAX_RT_PRIO + NICE_WIDTH / 2)

include/linux/sched/rt.h

@@ -6,19 +6,40 @@
 
 struct task_struct;
 
-static inline int rt_prio(int prio)
+static inline bool rt_prio(int prio)
 {
-	if (unlikely(prio < MAX_RT_PRIO))
+	return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO);
-		return 1;
-	return 0;
 }
 
-static inline int rt_task(struct task_struct *p)
+static inline bool rt_or_dl_prio(int prio)
+{
+	return unlikely(prio < MAX_RT_PRIO);
+}
+
+/*
+ * Returns true if a task has a priority that belongs to RT class. PI-boosted
+ * tasks will return true. Use rt_policy() to ignore PI-boosted tasks.
+ */
+static inline bool rt_task(struct task_struct *p)
 {
 	return rt_prio(p->prio);
 }
 
-static inline bool task_is_realtime(struct task_struct *tsk)
+/*
+ * Returns true if a task has a priority that belongs to RT or DL classes.
+ * PI-boosted tasks will return true. Use rt_or_dl_task_policy() to ignore
+ * PI-boosted tasks.
+ */
+static inline bool rt_or_dl_task(struct task_struct *p)
+{
+	return rt_or_dl_prio(p->prio);
+}
+
+/*
+ * Returns true if a task has a policy that belongs to RT or DL classes.
+ * PI-boosted tasks will return false.
+ */
+static inline bool rt_or_dl_task_policy(struct task_struct *tsk)
 {
 	int policy = tsk->policy;
 

kernel/freezer.c

@@ -72,7 +72,7 @@ bool __refrigerator(bool check_kthr_stop)
 		bool freeze;
 
 		raw_spin_lock_irq(&current->pi_lock);
-		set_current_state(TASK_FROZEN);
+		WRITE_ONCE(current->__state, TASK_FROZEN);
 		/* unstale saved_state so that __thaw_task() will wake us up */
 		current->saved_state = TASK_RUNNING;
 		raw_spin_unlock_irq(&current->pi_lock);

kernel/locking/rtmutex.c

@@ -347,7 +347,7 @@ static __always_inline int __waiter_prio(struct task_struct *task)
 {
 	int prio = task->prio;
 
-	if (!rt_prio(prio))
+	if (!rt_or_dl_prio(prio))
 		return DEFAULT_PRIO;
 
 	return prio;
@@ -435,7 +435,7 @@ static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
 	 * Note that RT tasks are excluded from same priority (lateral)
 	 * steals to prevent the introduction of an unbounded latency.
 	 */
-	if (rt_prio(waiter->tree.prio) || dl_prio(waiter->tree.prio))
+	if (rt_or_dl_prio(waiter->tree.prio))
 		return false;
 
 	return rt_waiter_node_equal(&waiter->tree, &top_waiter->tree);

kernel/locking/rwsem.c

@@ -631,7 +631,7 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 			 * if it is an RT task or wait in the wait queue
 			 * for too long.
 			 */
-			if (has_handoff || (!rt_task(waiter->task) &&
+			if (has_handoff || (!rt_or_dl_task(waiter->task) &&
 					    !time_after(jiffies, waiter->timeout)))
 				return false;
 
@@ -914,7 +914,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 		if (owner_state != OWNER_WRITER) {
 			if (need_resched())
 				break;
-			if (rt_task(current) &&
+			if (rt_or_dl_task(current) &&
 			   (prev_owner_state != OWNER_WRITER))
 				break;
 		}

kernel/locking/ww_mutex.h

@@ -237,7 +237,7 @@ __ww_ctx_less(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b)
 	int a_prio = a->task->prio;
 	int b_prio = b->task->prio;
 
-	if (rt_prio(a_prio) || rt_prio(b_prio)) {
+	if (rt_or_dl_prio(a_prio) || rt_or_dl_prio(b_prio)) {
 
 		if (a_prio > b_prio)
 			return true;

kernel/sched/core.c

@@ -166,7 +166,7 @@ static inline int __task_prio(const struct task_struct *p)
 	if (p->dl_server)
 		return -1; /* deadline */
 
-	if (rt_prio(p->prio)) /* includes deadline */
+	if (rt_or_dl_prio(p->prio))
 		return p->prio; /* [-1, 99] */
 
 	if (p->sched_class == &idle_sched_class)
@@ -1702,6 +1702,9 @@ 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);
 
@@ -1726,6 +1729,9 @@ 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);
 }
@@ -2005,14 +2011,21 @@ 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);
@@ -2025,8 +2038,12 @@ 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)
@@ -2044,12 +2061,25 @@ 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.
@@ -3697,12 +3727,14 @@ 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);
@@ -4091,11 +4123,16 @@ 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;
 
@@ -4384,9 +4421,11 @@ 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
@@ -4638,6 +4677,8 @@ 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
@@ -6562,13 +6603,15 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		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)
+			if (unlikely(is_special_task_state(prev_state)))
-				rq->nr_uninterruptible++;
+				flags |= DEQUEUE_SPECIAL;
 
 			/*
 			 * __schedule()			ttwu()
@@ -6581,12 +6624,7 @@ 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);
+			block_task(rq, prev, flags);
-
-			if (prev->in_iowait) {
-				atomic_inc(&rq->nr_iowait);
-				delayacct_blkio_start();
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -8461,6 +8499,7 @@ 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:
@@ -8677,7 +8716,7 @@ 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:

kernel/sched/deadline.c

@@ -2162,7 +2162,7 @@ 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);
 
@@ -2172,6 +2172,8 @@ 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;
 }
 
 /*
@@ -2426,7 +2428,6 @@ static struct task_struct *__pick_next_task_dl(struct rq *rq, bool peek)
 		else
 			p = dl_se->server_pick_next(dl_se);
 		if (!p) {
-			WARN_ON_ONCE(1);
 			dl_se->dl_yielded = 1;
 			update_curr_dl_se(rq, dl_se, 0);
 			goto again;

kernel/sched/debug.c

@@ -338,7 +338,7 @@ enum dl_param {
 	DL_PERIOD,
 };
 
-static unsigned long fair_server_period_max = (1 << 22) * NSEC_PER_USEC; /* ~4 seconds */
+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,
@@ -739,11 +739,12 @@ 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),

kernel/sched/fair.c

@@ -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,
+	cfs_rq->min_vruntime = __update_min_vruntime(cfs_rq, 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) {
+	return true;
-		resched_curr(rq_of(cfs_rq));
-		clear_buddies(cfs_rq, se);
-	}
 }
 
 #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.
  */
@@ -1158,6 +1218,7 @@ 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;
@@ -1167,7 +1228,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 		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)) {
@@ -1185,6 +1246,14 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	}
 
 	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)
@@ -5191,7 +5260,8 @@ 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);
 
 	/*
@@ -5272,6 +5342,12 @@ 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
@@ -5291,6 +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)
 {
@@ -5378,19 +5457,40 @@ 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 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.
@@ -5408,6 +5508,11 @@ 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;
@@ -5427,8 +5532,16 @@ 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) {
+		se->sched_delayed = 0;
+		if (sched_feat(DELAY_ZERO) && se->vlag > 0)
+			se->vlag = 0;
+	}
+
 	if (cfs_rq->nr_running == 0)
 		update_idle_cfs_rq_clock_pelt(cfs_rq);
+
+	return true;
 }
 
 static void
@@ -5454,6 +5567,7 @@ 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;
 
 	/*
@@ -5474,6 +5588,8 @@ 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
@@ -5482,16 +5598,26 @@ 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);
@@ -5515,6 +5641,7 @@ 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;
 }
 
@@ -5812,11 +5939,21 @@ 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;
@@ -5909,8 +6046,10 @@ 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)))
@@ -6760,6 +6899,37 @@ 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
@@ -6773,6 +6943,12 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	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;
+
+	if (flags & ENQUEUE_DELAYED) {
+		requeue_delayed_entity(se);
+		return;
+	}
 
 	/*
 	 * The code below (indirectly) updates schedutil which looks at
@@ -6791,10 +6967,24 @@ 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;
@@ -6816,6 +7006,9 @@ 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;
 
@@ -6863,37 +7056,59 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 static void set_next_buddy(struct sched_entity *se);
 
 /*
- * The dequeue_task method is called before nr_running is
+ * Basically dequeue_task_fair(), except it can deal with dequeue_entity()
- * decreased. We remove the task from the rbtree and
+ * failing half-way through and resume the dequeue later.
- * update the fair scheduling stats:
+ *
+ * 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);
 			/*
@@ -6905,6 +7120,7 @@ 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) {
@@ -6914,20 +7130,21 @@ 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, h_nr_running);
-	sub_nr_running(rq, 1);
 
 	if (rq_h_nr_running && !rq->cfs.h_nr_running)
 		dl_server_stop(&rq->fair_server);
@@ -6936,9 +7153,37 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
 		rq->next_balance = jiffies;
 
-dequeue_throttle:
+	if (p && task_delayed) {
-	util_est_update(&rq->cfs, p, task_sleep);
+		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)
+{
+	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
@@ -8320,7 +8565,21 @@ 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);
 }
 
 /*
@@ -8356,7 +8615,7 @@ 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;
@@ -8442,7 +8701,17 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	cfs_rq = cfs_rq_of(se);
 	update_curr(cfs_rq);
 	/*
-	 * XXX pick_eevdf(cfs_rq) != se ?
+	 * 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;
+
+	/*
+	 * If @p has become the most eligible task, force preemption.
 	 */
 	if (pick_eevdf(cfs_rq) == pse)
 		goto preempt;
@@ -8453,7 +8722,6 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	resched_curr(rq);
 }
 
-#ifdef CONFIG_SMP
 static struct task_struct *pick_task_fair(struct rq *rq)
 {
 	struct sched_entity *se;
@@ -8465,20 +8733,16 @@ static struct task_struct *pick_task_fair(struct rq *rq)
 		return NULL;
 
 	do {
-		struct sched_entity *curr = cfs_rq->curr;
+		/* Might not have done put_prev_entity() */
+		if (cfs_rq->curr && cfs_rq->curr->on_rq)
+			update_curr(cfs_rq);
 
-		/* When we pick for a remote RQ, we'll not have done put_prev_entity() */
+		if (unlikely(check_cfs_rq_runtime(cfs_rq)))
-		if (curr) {
+			goto again;
-			if (curr->on_rq)
-				update_curr(cfs_rq);
-			else
-				curr = NULL;
 
-			if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+		se = pick_next_entity(rq, cfs_rq);
-				goto again;
+		if (!se)
-		}
+			goto again;
-
-		se = pick_next_entity(cfs_rq);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
 
@@ -8492,19 +8756,19 @@ static struct task_struct *pick_task_fair(struct rq *rq)
 
 	return task_of(se);
 }
-#endif
 
 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)
@@ -8516,52 +8780,14 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 	 *
 	 * 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;
@@ -8587,13 +8813,8 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 	if (prev)
 		put_prev_task(rq, prev);
 
-	do {
+	for_each_sched_entity(se)
-		se = pick_next_entity(cfs_rq);
+		set_next_entity(cfs_rq_of(se), se);
-		set_next_entity(cfs_rq, se);
-		cfs_rq = group_cfs_rq(se);
-	} while (cfs_rq);
-
-	p = task_of(se);
 
 done: __maybe_unused;
 #ifdef CONFIG_SMP
@@ -12872,10 +13093,23 @@ 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) {
+		dequeue_task(rq, p, DEQUEUE_NOCLOCK | DEQUEUE_SLEEP);
+		p->se.sched_delayed = 0;
+		p->se.rel_deadline = 0;
+		if (sched_feat(DELAY_ZERO) && p->se.vlag > 0)
+			p->se.vlag = 0;
+	}
 }
 
 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);
@@ -12919,12 +13153,17 @@ 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);
 	}
+
+	if (!first)
+		return;
+
+	SCHED_WARN_ON(se->sched_delayed);
 }
 
 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
@@ -13026,28 +13265,35 @@ 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])
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu];
-			remove_entity_load_avg(tg->se[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)
+		if (cfs_rq->on_list) {
-			continue;
+			guard(rq_lock_irqsave)(rq);
-
+			list_del_leaf_cfs_rq(cfs_rq);
-		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);
 	}
 }
 

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
@@ -21,6 +37,18 @@ 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:
  */

kernel/sched/idle.c

@@ -484,13 +484,14 @@ struct task_struct *pick_next_task_idle(struct rq *rq)
  * 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;
 }
 
 /*

kernel/sched/rt.c

@@ -1483,7 +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;
 
@@ -1491,6 +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;
 }
 
 /*

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>
@@ -645,10 +646,6 @@ struct cfs_rq {
 	u64			min_vruntime_fi;
 #endif
 
-#ifndef CONFIG_64BIT
-	u64			min_vruntime_copy;
-#endif
-
 	struct rb_root_cached	tasks_timeline;
 
 	/*
@@ -891,6 +888,9 @@ 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
@@ -905,6 +905,9 @@ 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;
 }
 
@@ -2317,11 +2320,13 @@ 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
@@ -2337,6 +2342,7 @@ 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)
 
@@ -2355,7 +2361,7 @@ 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);
 
@@ -2711,6 +2717,19 @@ 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);
 
@@ -3736,7 +3755,7 @@ 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_changing(struct rq *rq, struct task_struct *p,
 				 const struct sched_class *prev_class);

kernel/sched/stop_task.c

@@ -57,10 +57,11 @@ 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)

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;
 }
@@ -420,10 +420,20 @@ 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;
+		}
+	}
 
 	/*
 	 * __sched_setscheduler() ensures attr->sched_priority == 0 when
@@ -723,7 +733,9 @@ int __sched_setscheduler(struct task_struct *p,
 	 * 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;
@@ -870,6 +882,9 @@ 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;
@@ -1036,12 +1051,14 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 
 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;
+	}
 }
 
 /**

kernel/time/hrtimer.c

@@ -1975,7 +1975,7 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
 	 * expiry.
 	 */
 	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
-		if (task_is_realtime(current) && !(mode & HRTIMER_MODE_SOFT))
+		if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT))
 			mode |= HRTIMER_MODE_HARD;
 	}
 
@@ -2075,7 +2075,7 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
 	u64 slack;
 
 	slack = current->timer_slack_ns;
-	if (rt_task(current))
+	if (rt_or_dl_task(current))
 		slack = 0;
 
 	hrtimer_init_sleeper_on_stack(&t, clockid, mode);
@@ -2280,7 +2280,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
 	 * Override any slack passed by the user if under
 	 * rt contraints.
 	 */
-	if (rt_task(current))
+	if (rt_or_dl_task(current))
 		delta = 0;
 
 	hrtimer_init_sleeper_on_stack(&t, clock_id, mode);

kernel/trace/trace_sched_wakeup.c

@@ -547,7 +547,7 @@ probe_wakeup(void *ignore, struct task_struct *p)
 	 *  - wakeup_dl handles tasks belonging to sched_dl class only.
 	 */
 	if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
-	    (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+	    (wakeup_rt && !rt_or_dl_task(p)) ||
 	    (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
 		return;
 

mm/page-writeback.c

@@ -418,7 +418,7 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 		bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
 
 	tsk = current;
-	if (rt_task(tsk)) {
+	if (rt_or_dl_task(tsk)) {
 		bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32;
 		thresh += thresh / 4 + global_wb_domain.dirty_limit / 32;
 	}
@@ -477,7 +477,7 @@ static unsigned long node_dirty_limit(struct pglist_data *pgdat)
 	else
 		dirty = vm_dirty_ratio * node_memory / 100;
 
-	if (rt_task(tsk))
+	if (rt_or_dl_task(tsk))
 		dirty += dirty / 4;
 
 	/*

mm/page_alloc.c

@@ -4002,7 +4002,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order)
 		 */
 		if (alloc_flags & ALLOC_MIN_RESERVE)
 			alloc_flags &= ~ALLOC_CPUSET;
-	} else if (unlikely(rt_task(current)) && in_task())
+	} else if (unlikely(rt_or_dl_task(current)) && in_task())
 		alloc_flags |= ALLOC_MIN_RESERVE;
 
 	alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags);