1 files changed, 179 insertions, 157 deletions

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index d2c072b0ef01..9ae8f41e3372 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -15,10 +15,42 @@
  *                    Michael Trimarchi <michael@amarulasolutions.com>,
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
-#include "sched.h"
-#include "pelt.h"
 
-struct dl_bandwidth def_dl_bandwidth;
+/*
+ * Default limits for DL period; on the top end we guard against small util
+ * tasks still getting ridiculously long effective runtimes, on the bottom end we
+ * guard against timer DoS.
+ */
+static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
+static unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_dl_sysctls[] = {
+	{
+		.procname       = "sched_deadline_period_max_us",
+		.data           = &sysctl_sched_dl_period_max,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_douintvec_minmax,
+		.extra1         = (void *)&sysctl_sched_dl_period_min,
+	},
+	{
+		.procname       = "sched_deadline_period_min_us",
+		.data           = &sysctl_sched_dl_period_min,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_douintvec_minmax,
+		.extra2         = (void *)&sysctl_sched_dl_period_max,
+	},
+	{}
+};
+
+static int __init sched_dl_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_dl_sysctls);
+	return 0;
+}
+late_initcall(sched_dl_sysctl_init);
+#endif
 
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
@@ -92,15 +124,12 @@ static inline int dl_bw_cpus(int i)
 	return cpus;
 }
 
-static inline unsigned long __dl_bw_capacity(int i)
+static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
 {
-	struct root_domain *rd = cpu_rq(i)->rd;
 	unsigned long cap = 0;
+	int i;
 
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
-			 "sched RCU must be held");
-
-	for_each_cpu_and(i, rd->span, cpu_active_mask)
+	for_each_cpu_and(i, mask, cpu_active_mask)
 		cap += capacity_orig_of(i);
 
 	return cap;
@@ -112,11 +141,14 @@ static inline unsigned long __dl_bw_capacity(int i)
  */
 static inline unsigned long dl_bw_capacity(int i)
 {
-	if (!static_branch_unlikely(&sched_asym_cpucapacity) &&
+	if (!sched_asym_cpucap_active() &&
 	    capacity_orig_of(i) == SCHED_CAPACITY_SCALE) {
 		return dl_bw_cpus(i) << SCHED_CAPACITY_SHIFT;
 	} else {
-		return __dl_bw_capacity(i);
+		RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+				 "sched RCU must be held");
+
+		return __dl_bw_capacity(cpu_rq(i)->rd->span);
 	}
 }
 
@@ -130,6 +162,21 @@ static inline bool dl_bw_visited(int cpu, u64 gen)
 	rd->visit_gen = gen;
 	return false;
 }
+
+static inline
+void __dl_update(struct dl_bw *dl_b, s64 bw)
+{
+	struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw);
+	int i;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	for_each_cpu_and(i, rd->span, cpu_active_mask) {
+		struct rq *rq = cpu_rq(i);
+
+		rq->dl.extra_bw += bw;
+	}
+}
 #else
 static inline struct dl_bw *dl_bw_of(int i)
 {
@@ -150,9 +197,38 @@ static inline bool dl_bw_visited(int cpu, u64 gen)
 {
 	return false;
 }
+
+static inline
+void __dl_update(struct dl_bw *dl_b, s64 bw)
+{
+	struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw);
+
+	dl->extra_bw += bw;
+}
 #endif
 
 static inline
+void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
+{
+	dl_b->total_bw -= tsk_bw;
+	__dl_update(dl_b, (s32)tsk_bw / cpus);
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
+{
+	dl_b->total_bw += tsk_bw;
+	__dl_update(dl_b, -((s32)tsk_bw / cpus));
+}
+
+static inline bool
+__dl_overflow(struct dl_bw *dl_b, unsigned long cap, u64 old_bw, u64 new_bw)
+{
+	return dl_b->bw != -1 &&
+	       cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw;
+}
+
+static inline
 void __add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
 {
 	u64 old = dl_rq->running_bw;
@@ -234,7 +310,7 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
 {
 	struct rq *rq;
 
-	BUG_ON(p->dl.flags & SCHED_FLAG_SUGOV);
+	WARN_ON_ONCE(p->dl.flags & SCHED_FLAG_SUGOV);
 
 	if (task_on_rq_queued(p))
 		return;
@@ -355,8 +431,8 @@ static void task_non_contending(struct task_struct *p)
 				sub_rq_bw(&p->dl, &rq->dl);
 			raw_spin_lock(&dl_b->lock);
 			__dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
-			__dl_clear_params(p);
 			raw_spin_unlock(&dl_b->lock);
+			__dl_clear_params(p);
 		}
 
 		return;
@@ -408,7 +484,7 @@ static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
 
-	return dl_rq->root.rb_leftmost == &dl_se->rb_node;
+	return rb_first_cached(&dl_rq->root) == &dl_se->rb_node;
 }
 
 static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
@@ -423,12 +499,10 @@ void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
 void init_dl_bw(struct dl_bw *dl_b)
 {
 	raw_spin_lock_init(&dl_b->lock);
-	raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock);
 	if (global_rt_runtime() == RUNTIME_INF)
 		dl_b->bw = -1;
 	else
 		dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
-	raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock);
 	dl_b->total_bw = 0;
 }
 
@@ -533,7 +607,7 @@ static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
 {
 	struct rb_node *leftmost;
 
-	BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
+	WARN_ON_ONCE(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
 
 	leftmost = rb_add_cached(&p->pushable_dl_tasks,
 				 &rq->dl.pushable_dl_tasks_root,
@@ -570,8 +644,8 @@ static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
 	return rq->online && dl_task(prev);
 }
 
-static DEFINE_PER_CPU(struct callback_head, dl_push_head);
-static DEFINE_PER_CPU(struct callback_head, dl_pull_head);
+static DEFINE_PER_CPU(struct balance_callback, dl_push_head);
+static DEFINE_PER_CPU(struct balance_callback, dl_pull_head);
 
 static void push_dl_tasks(struct rq *);
 static void pull_dl_task(struct rq *);
@@ -610,7 +684,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
 			 * Failed to find any suitable CPU.
 			 * The task will never come back!
 			 */
-			BUG_ON(dl_bandwidth_enabled());
+			WARN_ON_ONCE(dl_bandwidth_enabled());
 
 			/*
 			 * If admission control is disabled we
@@ -683,15 +757,6 @@ void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 }
 
-static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
-{
-	return false;
-}
-
-static inline void pull_dl_task(struct rq *rq)
-{
-}
-
 static inline void deadline_queue_push_tasks(struct rq *rq)
 {
 }
@@ -705,6 +770,14 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
 static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, int flags);
 
+static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
+					    struct rq *rq)
+{
+	/* 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;
+}
+
 /*
  * We are being explicitly informed that a new instance is starting,
  * and this means that:
@@ -738,8 +811,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
 	 * future; in fact, we must consider execution overheads (time
 	 * spent on hardirq context, etc.).
 	 */
-	dl_se->deadline = rq_clock(rq) + dl_se->dl_deadline;
-	dl_se->runtime = dl_se->dl_runtime;
+	replenish_dl_new_period(dl_se, rq);
 }
 
 /*
@@ -765,16 +837,14 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	BUG_ON(pi_of(dl_se)->dl_runtime <= 0);
+	WARN_ON_ONCE(pi_of(dl_se)->dl_runtime <= 0);
 
 	/*
 	 * This could be the case for a !-dl task that is boosted.
 	 * Just go with full inherited parameters.
 	 */
-	if (dl_se->dl_deadline == 0) {
-		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_deadline == 0)
+		replenish_dl_new_period(dl_se, rq);
 
 	if (dl_se->dl_yielded && dl_se->runtime > 0)
 		dl_se->runtime = 0;
@@ -801,8 +871,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 	 */
 	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
 		printk_deferred_once("sched: DL replenish lagged too much\n");
-		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
-		dl_se->runtime = pi_of(dl_se)->dl_runtime;
+		replenish_dl_new_period(dl_se, rq);
 	}
 
 	if (dl_se->dl_yielded)
@@ -959,8 +1028,7 @@ static void update_dl_entity(struct sched_dl_entity *dl_se)
 			return;
 		}
 
-		dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
-		dl_se->runtime = pi_of(dl_se)->dl_runtime;
+		replenish_dl_new_period(dl_se, rq);
 	}
 }
 
@@ -1191,8 +1259,6 @@ int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
 	return (dl_se->runtime <= 0);
 }
 
-extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
-
 /*
  * This function implements the GRUB accounting rule:
  * according to the GRUB reclaiming algorithm, the runtime is
@@ -1270,11 +1336,7 @@ static void update_curr_dl(struct rq *rq)
 
 	trace_sched_stat_runtime(curr, delta_exec, 0);
 
-	curr->se.sum_exec_runtime += delta_exec;
-	account_group_exec_runtime(curr, delta_exec);
-
-	curr->se.exec_start = now;
-	cgroup_account_cputime(curr, delta_exec);
+	update_current_exec_runtime(curr, now, delta_exec);
 
 	if (dl_entity_is_special(dl_se))
 		return;
@@ -1393,6 +1455,9 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
 	timer->function = inactive_task_timer;
 }
 
+#define __node_2_dle(node) \
+	rb_entry((node), struct sched_dl_entity, rb_node)
+
 #ifdef CONFIG_SMP
 
 static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
@@ -1422,10 +1487,9 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 		cpudl_clear(&rq->rd->cpudl, rq->cpu);
 		cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
 	} else {
-		struct rb_node *leftmost = dl_rq->root.rb_leftmost;
-		struct sched_dl_entity *entry;
+		struct rb_node *leftmost = rb_first_cached(&dl_rq->root);
+		struct sched_dl_entity *entry = __node_2_dle(leftmost);
 
-		entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
 		dl_rq->earliest_dl.curr = entry->deadline;
 		cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline);
 	}
@@ -1466,9 +1530,6 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	dec_dl_migration(dl_se, dl_rq);
 }
 
-#define __node_2_dle(node) \
-	rb_entry((node), struct sched_dl_entity, rb_node)
-
 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);
@@ -1554,7 +1615,7 @@ static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 
-	BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node));
+	WARN_ON_ONCE(!RB_EMPTY_NODE(&dl_se->rb_node));
 
 	rb_add_cached(&dl_se->rb_node, &dl_rq->root, __dl_less);
 
@@ -1578,7 +1639,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
 static void
 enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 {
-	BUG_ON(on_dl_rq(dl_se));
+	WARN_ON_ONCE(on_dl_rq(dl_se));
 
 	update_stats_enqueue_dl(dl_rq_of_se(dl_se), dl_se, flags);
 
@@ -1641,7 +1702,10 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		 * the throttle.
 		 */
 		p->dl.dl_throttled = 0;
-		BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH);
+		if (!(flags & ENQUEUE_REPLENISH))
+			printk_deferred_once("sched: DL de-boosted task PID %d: REPLENISH flag missing\n",
+					     task_pid_nr(p));
+
 		return;
 	}
 
@@ -1749,6 +1813,14 @@ static void yield_task_dl(struct rq *rq)
 
 #ifdef CONFIG_SMP
 
+static inline bool dl_task_is_earliest_deadline(struct task_struct *p,
+						 struct rq *rq)
+{
+	return (!rq->dl.dl_nr_running ||
+		dl_time_before(p->dl.deadline,
+			       rq->dl.earliest_dl.curr));
+}
+
 static int find_later_rq(struct task_struct *task);
 
 static int
@@ -1784,16 +1856,14 @@ select_task_rq_dl(struct task_struct *p, int cpu, int flags)
 	 * Take the capacity of the CPU into account to
 	 * ensure it fits the requirement of the task.
 	 */
-	if (static_branch_unlikely(&sched_asym_cpucapacity))
+	if (sched_asym_cpucap_active())
 		select_rq |= !dl_task_fits_capacity(p, cpu);
 
 	if (select_rq) {
 		int target = find_later_rq(p);
 
 		if (target != -1 &&
-				(dl_time_before(p->dl.deadline,
-					cpu_rq(target)->dl.earliest_dl.curr) ||
-				(cpu_rq(target)->dl.dl_nr_running == 0)))
+		    dl_task_is_earliest_deadline(p, cpu_rq(target)))
 			cpu = target;
 	}
 	rcu_read_unlock();
@@ -1804,6 +1874,7 @@ out:
 
 static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused)
 {
+	struct rq_flags rf;
 	struct rq *rq;
 
 	if (READ_ONCE(p->__state) != TASK_WAKING)
@@ -1815,7 +1886,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
 	 * from try_to_wake_up(). Hence, p->pi_lock is locked, but
 	 * rq->lock is not... So, lock it
 	 */
-	raw_spin_rq_lock(rq);
+	rq_lock(rq, &rf);
 	if (p->dl.dl_non_contending) {
 		update_rq_clock(rq);
 		sub_running_bw(&p->dl, &rq->dl);
@@ -1831,7 +1902,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
 			put_task_struct(p);
 	}
 	sub_rq_bw(&p->dl, &rq->dl);
-	raw_spin_rq_unlock(rq);
+	rq_unlock(rq, &rf);
 }
 
 static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
@@ -1931,15 +2002,14 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 	deadline_queue_push_tasks(rq);
 }
 
-static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
-						   struct dl_rq *dl_rq)
+static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
 {
 	struct rb_node *left = rb_first_cached(&dl_rq->root);
 
 	if (!left)
 		return NULL;
 
-	return rb_entry(left, struct sched_dl_entity, rb_node);
+	return __node_2_dle(left);
 }
 
 static struct task_struct *pick_task_dl(struct rq *rq)
@@ -1951,8 +2021,8 @@ static struct task_struct *pick_task_dl(struct rq *rq)
 	if (!sched_dl_runnable(rq))
 		return NULL;
 
-	dl_se = pick_next_dl_entity(rq, dl_rq);
-	BUG_ON(!dl_se);
+	dl_se = pick_next_dl_entity(dl_rq);
+	WARN_ON_ONCE(!dl_se);
 	p = dl_task_of(dl_se);
 
 	return p;
@@ -2022,7 +2092,7 @@ static void task_fork_dl(struct task_struct *p)
 
 static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 {
-	if (!task_running(rq, p) &&
+	if (!task_on_cpu(rq, p) &&
 	    cpumask_test_cpu(cpu, &p->cpus_mask))
 		return 1;
 	return 0;
@@ -2034,15 +2104,17 @@ static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
  */
 static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu)
 {
-	struct rb_node *next_node = rq->dl.pushable_dl_tasks_root.rb_leftmost;
 	struct task_struct *p = NULL;
+	struct rb_node *next_node;
 
 	if (!has_pushable_dl_tasks(rq))
 		return NULL;
 
+	next_node = rb_first_cached(&rq->dl.pushable_dl_tasks_root);
+
 next_node:
 	if (next_node) {
-		p = rb_entry(next_node, struct task_struct, pushable_dl_tasks);
+		p = __node_2_pdl(next_node);
 
 		if (pick_dl_task(rq, p, cpu))
 			return p;
@@ -2158,9 +2230,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 
 		later_rq = cpu_rq(cpu);
 
-		if (later_rq->dl.dl_nr_running &&
-		    !dl_time_before(task->dl.deadline,
-					later_rq->dl.earliest_dl.curr)) {
+		if (!dl_task_is_earliest_deadline(task, later_rq)) {
 			/*
 			 * Target rq has tasks of equal or earlier deadline,
 			 * retrying does not release any lock and is unlikely
@@ -2174,7 +2244,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 		if (double_lock_balance(rq, later_rq)) {
 			if (unlikely(task_rq(task) != rq ||
 				     !cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) ||
-				     task_running(rq, task) ||
+				     task_on_cpu(rq, task) ||
 				     !dl_task(task) ||
 				     !task_on_rq_queued(task))) {
 				double_unlock_balance(rq, later_rq);
@@ -2188,9 +2258,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 		 * its earliest one has a later deadline than our
 		 * task, the rq is a good one.
 		 */
-		if (!later_rq->dl.dl_nr_running ||
-		    dl_time_before(task->dl.deadline,
-				   later_rq->dl.earliest_dl.curr))
+		if (dl_task_is_earliest_deadline(task, later_rq))
 			break;
 
 		/* Otherwise we try again. */
@@ -2208,15 +2276,14 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
 	if (!has_pushable_dl_tasks(rq))
 		return NULL;
 
-	p = rb_entry(rq->dl.pushable_dl_tasks_root.rb_leftmost,
-		     struct task_struct, pushable_dl_tasks);
+	p = __node_2_pdl(rb_first_cached(&rq->dl.pushable_dl_tasks_root));
 
-	BUG_ON(rq->cpu != task_cpu(p));
-	BUG_ON(task_current(rq, p));
-	BUG_ON(p->nr_cpus_allowed <= 1);
+	WARN_ON_ONCE(rq->cpu != task_cpu(p));
+	WARN_ON_ONCE(task_current(rq, p));
+	WARN_ON_ONCE(p->nr_cpus_allowed <= 1);
 
-	BUG_ON(!task_on_rq_queued(p));
-	BUG_ON(!dl_task(p));
+	WARN_ON_ONCE(!task_on_rq_queued(p));
+	WARN_ON_ONCE(!dl_task(p));
 
 	return p;
 }
@@ -2240,12 +2307,6 @@ static int push_dl_task(struct rq *rq)
 		return 0;
 
 retry:
-	if (is_migration_disabled(next_task))
-		return 0;
-
-	if (WARN_ON(next_task == rq->curr))
-		return 0;
-
 	/*
 	 * If next_task preempts rq->curr, and rq->curr
 	 * can move away, it makes sense to just reschedule
@@ -2258,6 +2319,12 @@ retry:
 		return 0;
 	}
 
+	if (is_migration_disabled(next_task))
+		return 0;
+
+	if (WARN_ON(next_task == rq->curr))
+		return 0;
+
 	/* We might release rq lock */
 	get_task_struct(next_task);
 
@@ -2291,13 +2358,7 @@ retry:
 
 	deactivate_task(rq, next_task, 0);
 	set_task_cpu(next_task, later_rq->cpu);
-
-	/*
-	 * Update the later_rq clock here, because the clock is used
-	 * by the cpufreq_update_util() inside __add_running_bw().
-	 */
-	update_rq_clock(later_rq);
-	activate_task(later_rq, next_task, ENQUEUE_NOCLOCK);
+	activate_task(later_rq, next_task, 0);
 	ret = 1;
 
 	resched_curr(later_rq);
@@ -2368,9 +2429,7 @@ static void pull_dl_task(struct rq *this_rq)
 		 *  - it will preempt the last one we pulled (if any).
 		 */
 		if (p && dl_time_before(p->dl.deadline, dmin) &&
-		    (!this_rq->dl.dl_nr_running ||
-		     dl_time_before(p->dl.deadline,
-				    this_rq->dl.earliest_dl.curr))) {
+		    dl_task_is_earliest_deadline(p, this_rq)) {
 			WARN_ON(p == src_rq->curr);
 			WARN_ON(!task_on_rq_queued(p));
 
@@ -2415,7 +2474,7 @@ skip:
  */
 static void task_woken_dl(struct rq *rq, struct task_struct *p)
 {
-	if (!task_running(rq, p) &&
+	if (!task_on_cpu(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
 	    p->nr_cpus_allowed > 1 &&
 	    dl_task(rq->curr) &&
@@ -2432,7 +2491,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 	struct root_domain *src_rd;
 	struct rq *rq;
 
-	BUG_ON(!dl_task(p));
+	WARN_ON_ONCE(!dl_task(p));
 
 	rq = task_rq(p);
 	src_rd = rq->rd;
@@ -2731,9 +2790,6 @@ void sched_dl_do_global(void)
 	int cpu;
 	unsigned long flags;
 
-	def_dl_bandwidth.dl_period = global_rt_period();
-	def_dl_bandwidth.dl_runtime = global_rt_runtime();
-
 	if (global_rt_runtime() != RUNTIME_INF)
 		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
 
@@ -2855,14 +2911,6 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 }
 
 /*
- * Default limits for DL period; on the top end we guard against small util
- * tasks still getting ridiculously long effective runtimes, on the bottom end we
- * guard against timer DoS.
- */
-unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
-unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
-
-/*
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
  * than the runtime, as well as the period of being zero or
@@ -2955,55 +3003,18 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 }
 
 #ifdef CONFIG_SMP
-int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
-{
-	unsigned long flags, cap;
-	unsigned int dest_cpu;
-	struct dl_bw *dl_b;
-	bool overflow;
-	int ret;
-
-	dest_cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
-
-	rcu_read_lock_sched();
-	dl_b = dl_bw_of(dest_cpu);
-	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cap = dl_bw_capacity(dest_cpu);
-	overflow = __dl_overflow(dl_b, cap, 0, p->dl.dl_bw);
-	if (overflow) {
-		ret = -EBUSY;
-	} else {
-		/*
-		 * We reserve space for this task in the destination
-		 * root_domain, as we can't fail after this point.
-		 * We will free resources in the source root_domain
-		 * later on (see set_cpus_allowed_dl()).
-		 */
-		int cpus = dl_bw_cpus(dest_cpu);
-
-		__dl_add(dl_b, p->dl.dl_bw, cpus);
-		ret = 0;
-	}
-	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-	rcu_read_unlock_sched();
-
-	return ret;
-}
-
 int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 				 const struct cpumask *trial)
 {
-	int ret = 1, trial_cpus;
+	unsigned long flags, cap;
 	struct dl_bw *cur_dl_b;
-	unsigned long flags;
+	int ret = 1;
 
 	rcu_read_lock_sched();
 	cur_dl_b = dl_bw_of(cpumask_any(cur));
-	trial_cpus = cpumask_weight(trial);
-
+	cap = __dl_bw_capacity(trial);
 	raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
-	if (cur_dl_b->bw != -1 &&
-	    cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
+	if (__dl_overflow(cur_dl_b, cap, 0, 0))
 		ret = 0;
 	raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
 	rcu_read_unlock_sched();
@@ -3011,7 +3022,7 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 	return ret;
 }
 
-bool dl_cpu_busy(unsigned int cpu)
+int dl_cpu_busy(int cpu, struct task_struct *p)
 {
 	unsigned long flags, cap;
 	struct dl_bw *dl_b;
@@ -3021,11 +3032,22 @@ bool dl_cpu_busy(unsigned int cpu)
 	dl_b = dl_bw_of(cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
 	cap = dl_bw_capacity(cpu);
-	overflow = __dl_overflow(dl_b, cap, 0, 0);
+	overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0);
+
+	if (!overflow && p) {
+		/*
+		 * We reserve space for this task in the destination
+		 * root_domain, as we can't fail after this point.
+		 * We will free resources in the source root_domain
+		 * later on (see set_cpus_allowed_dl()).
+		 */
+		__dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu));
+	}
+
 	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	rcu_read_unlock_sched();
 
-	return overflow;
+	return overflow ? -EBUSY : 0;
 }
 #endif