Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - massive CPU hotplug rework (Thomas Gleixner)

 - improve migration fairness (Peter Zijlstra)

 - CPU load calculation updates/cleanups (Yuyang Du)

 - cpufreq updates (Steve Muckle)

 - nohz optimizations (Frederic Weisbecker)

 - switch_mm() micro-optimization on x86 (Andy Lutomirski)

 - ... lots of other enhancements, fixes and cleanups.

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (66 commits)
  ARM: Hide finish_arch_post_lock_switch() from modules
  sched/core: Provide a tsk_nr_cpus_allowed() helper
  sched/core: Use tsk_cpus_allowed() instead of accessing ->cpus_allowed
  sched/loadavg: Fix loadavg artifacts on fully idle and on fully loaded systems
  sched/fair: Correct unit of load_above_capacity
  sched/fair: Clean up scale confusion
  sched/nohz: Fix affine unpinned timers mess
  sched/fair: Fix fairness issue on migration
  sched/core: Kill sched_class::task_waking to clean up the migration logic
  sched/fair: Prepare to fix fairness problems on migration
  sched/fair: Move record_wakee()
  sched/core: Fix comment typo in wake_q_add()
  sched/core: Remove unused variable
  sched: Make hrtick_notifier an explicit call
  sched/fair: Make ilb_notifier an explicit call
  sched/hotplug: Make activate() the last hotplug step
  sched/hotplug: Move migration CPU_DYING to sched_cpu_dying()
  sched/migration: Move CPU_ONLINE into scheduler state
  sched/migration: Move calc_load_migrate() into CPU_DYING
  sched/migration: Move prepare transition to SCHED_STARTING state
  ...

16 files changed, 1059 insertions, 776 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 3e3f6e49eabb..d948e44c471e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -703,21 +703,6 @@ static int takedown_cpu(unsigned int cpu)
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	int err;
 
-	/*
-	 * By now we've cleared cpu_active_mask, wait for all preempt-disabled
-	 * and RCU users of this state to go away such that all new such users
-	 * will observe it.
-	 *
-	 * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might
-	 * not imply sync_sched(), so wait for both.
-	 *
-	 * Do sync before park smpboot threads to take care the rcu boost case.
-	 */
-	if (IS_ENABLED(CONFIG_PREEMPT))
-		synchronize_rcu_mult(call_rcu, call_rcu_sched);
-	else
-		synchronize_rcu();
-
 	/* Park the smpboot threads */
 	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
 	smpboot_park_threads(cpu);
@@ -923,8 +908,6 @@ void cpuhp_online_idle(enum cpuhp_state state)
 
 	st->state = CPUHP_AP_ONLINE_IDLE;
 
-	/* The cpu is marked online, set it active now */
-	set_cpu_active(cpu, true);
 	/* Unpark the stopper thread and the hotplug thread of this cpu */
 	stop_machine_unpark(cpu);
 	kthread_unpark(st->thread);
@@ -1236,6 +1219,12 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 		.name			= "ap:offline",
 		.cant_stop		= true,
 	},
+	/* First state is scheduler control. Interrupts are disabled */
+	[CPUHP_AP_SCHED_STARTING] = {
+		.name			= "sched:starting",
+		.startup		= sched_cpu_starting,
+		.teardown		= sched_cpu_dying,
+	},
 	/*
 	 * Low level startup/teardown notifiers. Run with interrupts
 	 * disabled. Will be removed once the notifiers are converted to
@@ -1274,6 +1263,15 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 	 * The dynamically registered state space is here
 	 */
 
+#ifdef CONFIG_SMP
+	/* Last state is scheduler control setting the cpu active */
+	[CPUHP_AP_ACTIVE] = {
+		.name			= "sched:active",
+		.startup		= sched_cpu_activate,
+		.teardown		= sched_cpu_deactivate,
+	},
+#endif
+
 	/* CPU is fully up and running. */
 	[CPUHP_ONLINE] = {
 		.name			= "online",
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 874d53eaf389..81f1a7107c0e 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -45,6 +45,7 @@
 #include <linux/bitops.h>
 #include <linux/gfp.h>
 #include <linux/kmemcheck.h>
+#include <linux/random.h>
 
 #include <asm/sections.h>
 
@@ -3585,7 +3586,35 @@ static int __lock_is_held(struct lockdep_map *lock)
 	return 0;
 }
 
-static void __lock_pin_lock(struct lockdep_map *lock)
+static struct pin_cookie __lock_pin_lock(struct lockdep_map *lock)
+{
+	struct pin_cookie cookie = NIL_COOKIE;
+	struct task_struct *curr = current;
+	int i;
+
+	if (unlikely(!debug_locks))
+		return cookie;
+
+	for (i = 0; i < curr->lockdep_depth; i++) {
+		struct held_lock *hlock = curr->held_locks + i;
+
+		if (match_held_lock(hlock, lock)) {
+			/*
+			 * Grab 16bits of randomness; this is sufficient to not
+			 * be guessable and still allows some pin nesting in
+			 * our u32 pin_count.
+			 */
+			cookie.val = 1 + (prandom_u32() >> 16);
+			hlock->pin_count += cookie.val;
+			return cookie;
+		}
+	}
+
+	WARN(1, "pinning an unheld lock\n");
+	return cookie;
+}
+
+static void __lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 {
 	struct task_struct *curr = current;
 	int i;
@@ -3597,7 +3626,7 @@ static void __lock_pin_lock(struct lockdep_map *lock)
 		struct held_lock *hlock = curr->held_locks + i;
 
 		if (match_held_lock(hlock, lock)) {
-			hlock->pin_count++;
+			hlock->pin_count += cookie.val;
 			return;
 		}
 	}
@@ -3605,7 +3634,7 @@ static void __lock_pin_lock(struct lockdep_map *lock)
 	WARN(1, "pinning an unheld lock\n");
 }
 
-static void __lock_unpin_lock(struct lockdep_map *lock)
+static void __lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 {
 	struct task_struct *curr = current;
 	int i;
@@ -3620,7 +3649,11 @@ static void __lock_unpin_lock(struct lockdep_map *lock)
 			if (WARN(!hlock->pin_count, "unpinning an unpinned lock\n"))
 				return;
 
-			hlock->pin_count--;
+			hlock->pin_count -= cookie.val;
+
+			if (WARN((int)hlock->pin_count < 0, "pin count corrupted\n"))
+				hlock->pin_count = 0;
+
 			return;
 		}
 	}
@@ -3751,24 +3784,44 @@ int lock_is_held(struct lockdep_map *lock)
 }
 EXPORT_SYMBOL_GPL(lock_is_held);
 
-void lock_pin_lock(struct lockdep_map *lock)
+struct pin_cookie lock_pin_lock(struct lockdep_map *lock)
 {
+	struct pin_cookie cookie = NIL_COOKIE;
 	unsigned long flags;
 
 	if (unlikely(current->lockdep_recursion))
-		return;
+		return cookie;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
 	current->lockdep_recursion = 1;
-	__lock_pin_lock(lock);
+	cookie = __lock_pin_lock(lock);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
+
+	return cookie;
 }
 EXPORT_SYMBOL_GPL(lock_pin_lock);
 
-void lock_unpin_lock(struct lockdep_map *lock)
+void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
+{
+	unsigned long flags;
+
+	if (unlikely(current->lockdep_recursion))
+		return;
+
+	raw_local_irq_save(flags);
+	check_flags(flags);
+
+	current->lockdep_recursion = 1;
+	__lock_repin_lock(lock, cookie);
+	current->lockdep_recursion = 0;
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(lock_repin_lock);
+
+void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 {
 	unsigned long flags;
 
@@ -3779,7 +3832,7 @@ void lock_unpin_lock(struct lockdep_map *lock)
 	check_flags(flags);
 
 	current->lockdep_recursion = 1;
-	__lock_unpin_lock(lock);
+	__lock_unpin_lock(lock, cookie);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index fedb967a9841..e85a725e5c34 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -318,6 +318,7 @@ u64 sched_clock_cpu(int cpu)
 
 	return clock;
 }
+EXPORT_SYMBOL_GPL(sched_clock_cpu);
 
 void sched_clock_tick(void)
 {
@@ -363,39 +364,6 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
-/*
- * As outlined at the top, provides a fast, high resolution, nanosecond
- * time source that is monotonic per cpu argument and has bounded drift
- * between cpus.
- *
- * ######################### BIG FAT WARNING ##########################
- * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can #
- * # go backwards !!                                                  #
- * ####################################################################
- */
-u64 cpu_clock(int cpu)
-{
-	if (!sched_clock_stable())
-		return sched_clock_cpu(cpu);
-
-	return sched_clock();
-}
-
-/*
- * Similar to cpu_clock() for the current cpu. Time will only be observed
- * to be monotonic if care is taken to only compare timestampt taken on the
- * same CPU.
- *
- * See cpu_clock().
- */
-u64 local_clock(void)
-{
-	if (!sched_clock_stable())
-		return sched_clock_cpu(raw_smp_processor_id());
-
-	return sched_clock();
-}
-
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
 void sched_clock_init(void)
@@ -410,22 +378,8 @@ u64 sched_clock_cpu(int cpu)
 
 	return sched_clock();
 }
-
-u64 cpu_clock(int cpu)
-{
-	return sched_clock();
-}
-
-u64 local_clock(void)
-{
-	return sched_clock();
-}
-
 #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
-EXPORT_SYMBOL_GPL(cpu_clock);
-EXPORT_SYMBOL_GPL(local_clock);
-
 /*
  * Running clock - returns the time that has elapsed while a guest has been
  * running.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d1f7149f8704..404c0784b1fc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -33,7 +33,7 @@
 #include <linux/init.h>
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
-#include <asm/mmu_context.h>
+#include <linux/mmu_context.h>
 #include <linux/interrupt.h>
 #include <linux/capability.h>
 #include <linux/completion.h>
@@ -170,6 +170,71 @@ static struct rq *this_rq_lock(void)
 	return rq;
 }
 
+/*
+ * __task_rq_lock - lock the rq @p resides on.
+ */
+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+	__acquires(rq->lock)
+{
+	struct rq *rq;
+
+	lockdep_assert_held(&p->pi_lock);
+
+	for (;;) {
+		rq = task_rq(p);
+		raw_spin_lock(&rq->lock);
+		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
+			rf->cookie = lockdep_pin_lock(&rq->lock);
+			return rq;
+		}
+		raw_spin_unlock(&rq->lock);
+
+		while (unlikely(task_on_rq_migrating(p)))
+			cpu_relax();
+	}
+}
+
+/*
+ * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
+ */
+struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+	__acquires(p->pi_lock)
+	__acquires(rq->lock)
+{
+	struct rq *rq;
+
+	for (;;) {
+		raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
+		rq = task_rq(p);
+		raw_spin_lock(&rq->lock);
+		/*
+		 *	move_queued_task()		task_rq_lock()
+		 *
+		 *	ACQUIRE (rq->lock)
+		 *	[S] ->on_rq = MIGRATING		[L] rq = task_rq()
+		 *	WMB (__set_task_cpu())		ACQUIRE (rq->lock);
+		 *	[S] ->cpu = new_cpu		[L] task_rq()
+		 *					[L] ->on_rq
+		 *	RELEASE (rq->lock)
+		 *
+		 * If we observe the old cpu in task_rq_lock, the acquire of
+		 * the old rq->lock will fully serialize against the stores.
+		 *
+		 * If we observe the new cpu in task_rq_lock, the acquire will
+		 * pair with the WMB to ensure we must then also see migrating.
+		 */
+		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
+			rf->cookie = lockdep_pin_lock(&rq->lock);
+			return rq;
+		}
+		raw_spin_unlock(&rq->lock);
+		raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
+
+		while (unlikely(task_on_rq_migrating(p)))
+			cpu_relax();
+	}
+}
+
 #ifdef CONFIG_SCHED_HRTICK
 /*
  * Use HR-timers to deliver accurate preemption points.
@@ -249,29 +314,6 @@ void hrtick_start(struct rq *rq, u64 delay)
 	}
 }
 
-static int
-hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
-{
-	int cpu = (int)(long)hcpu;
-
-	switch (action) {
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		hrtick_clear(cpu_rq(cpu));
-		return NOTIFY_OK;
-	}
-
-	return NOTIFY_DONE;
-}
-
-static __init void init_hrtick(void)
-{
-	hotcpu_notifier(hotplug_hrtick, 0);
-}
 #else
 /*
  * Called to set the hrtick timer state.
@@ -288,10 +330,6 @@ void hrtick_start(struct rq *rq, u64 delay)
 	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
 		      HRTIMER_MODE_REL_PINNED);
 }
-
-static inline void init_hrtick(void)
-{
-}
 #endif /* CONFIG_SMP */
 
 static void init_rq_hrtick(struct rq *rq)
@@ -315,10 +353,6 @@ static inline void hrtick_clear(struct rq *rq)
 static inline void init_rq_hrtick(struct rq *rq)
 {
 }
-
-static inline void init_hrtick(void)
-{
-}
 #endif	/* CONFIG_SCHED_HRTICK */
 
 /*
@@ -400,7 +434,7 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * wakeup due to that.
 	 *
 	 * This cmpxchg() implies a full barrier, which pairs with the write
-	 * barrier implied by the wakeup in wake_up_list().
+	 * barrier implied by the wakeup in wake_up_q().
 	 */
 	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
 		return;
@@ -499,7 +533,10 @@ int get_nohz_timer_target(void)
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
 		for_each_cpu(i, sched_domain_span(sd)) {
-			if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) {
+			if (cpu == i)
+				continue;
+
+			if (!idle_cpu(i) && is_housekeeping_cpu(i)) {
 				cpu = i;
 				goto unlock;
 			}
@@ -1085,12 +1122,20 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 static int __set_cpus_allowed_ptr(struct task_struct *p,
 				  const struct cpumask *new_mask, bool check)
 {
-	unsigned long flags;
-	struct rq *rq;
+	const struct cpumask *cpu_valid_mask = cpu_active_mask;
 	unsigned int dest_cpu;
+	struct rq_flags rf;
+	struct rq *rq;
 	int ret = 0;
 
-	rq = task_rq_lock(p, &flags);
+	rq = task_rq_lock(p, &rf);
+
+	if (p->flags & PF_KTHREAD) {
+		/*
+		 * Kernel threads are allowed on online && !active CPUs
+		 */
+		cpu_valid_mask = cpu_online_mask;
+	}
 
 	/*
 	 * Must re-check here, to close a race against __kthread_bind(),
@@ -1104,22 +1149,32 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	if (cpumask_equal(&p->cpus_allowed, new_mask))
 		goto out;
 
-	if (!cpumask_intersects(new_mask, cpu_active_mask)) {
+	if (!cpumask_intersects(new_mask, cpu_valid_mask)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
 	do_set_cpus_allowed(p, new_mask);
 
+	if (p->flags & PF_KTHREAD) {
+		/*
+		 * For kernel threads that do indeed end up on online &&
+		 * !active we want to ensure they are strict per-cpu threads.
+		 */
+		WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) &&
+			!cpumask_intersects(new_mask, cpu_active_mask) &&
+			p->nr_cpus_allowed != 1);
+	}
+
 	/* Can the task run on the task's current CPU? If so, we're done */
 	if (cpumask_test_cpu(task_cpu(p), new_mask))
 		goto out;
 
-	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
+	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
 	if (task_running(rq, p) || p->state == TASK_WAKING) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
-		task_rq_unlock(rq, p, &flags);
+		task_rq_unlock(rq, p, &rf);
 		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
 		tlb_migrate_finish(p->mm);
 		return 0;
@@ -1128,12 +1183,12 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		 * OK, since we're going to drop the lock immediately
 		 * afterwards anyway.
 		 */
-		lockdep_unpin_lock(&rq->lock);
+		lockdep_unpin_lock(&rq->lock, rf.cookie);
 		rq = move_queued_task(rq, p, dest_cpu);
-		lockdep_pin_lock(&rq->lock);
+		lockdep_repin_lock(&rq->lock, rf.cookie);
 	}
 out:
-	task_rq_unlock(rq, p, &flags);
+	task_rq_unlock(rq, p, &rf);
 
 	return ret;
 }
@@ -1317,8 +1372,8 @@ out:
  */
 unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 {
-	unsigned long flags;
 	int running, queued;
+	struct rq_flags rf;
 	unsigned long ncsw;
 	struct rq *rq;
 
@@ -1353,14 +1408,14 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * lock now, to be *sure*. If we're wrong, we'll
 		 * just go back and repeat.
 		 */
-		rq = task_rq_lock(p, &flags);
+		rq = task_rq_lock(p, &rf);
 		trace_sched_wait_task(p);
 		running = task_running(rq, p);
 		queued = task_on_rq_queued(p);
 		ncsw = 0;
 		if (!match_state || p->state == match_state)
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
-		task_rq_unlock(rq, p, &flags);
+		task_rq_unlock(rq, p, &rf);
 
 		/*
 		 * If it changed from the expected state, bail out now.
@@ -1434,6 +1489,25 @@ EXPORT_SYMBOL_GPL(kick_process);
 
 /*
  * ->cpus_allowed is protected by both rq->lock and p->pi_lock
+ *
+ * A few notes on cpu_active vs cpu_online:
+ *
+ *  - cpu_active must be a subset of cpu_online
+ *
+ *  - on cpu-up we allow per-cpu kthreads on the online && !active cpu,
+ *    see __set_cpus_allowed_ptr(). At this point the newly online
+ *    cpu isn't yet part of the sched domains, and balancing will not
+ *    see it.
+ *
+ *  - on cpu-down we clear cpu_active() to mask the sched domains and
+ *    avoid the load balancer to place new tasks on the to be removed
+ *    cpu. Existing tasks will remain running there and will be taken
+ *    off.
+ *
+ * This means that fallback selection must not select !active CPUs.
+ * And can assume that any active CPU must be online. Conversely
+ * select_task_rq() below may allow selection of !active CPUs in order
+ * to satisfy the above rules.
  */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
@@ -1452,8 +1526,6 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 
 		/* Look for allowed, online CPU in same node. */
 		for_each_cpu(dest_cpu, nodemask) {
-			if (!cpu_online(dest_cpu))
-				continue;
 			if (!cpu_active(dest_cpu))
 				continue;
 			if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
@@ -1464,8 +1536,6 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	for (;;) {
 		/* Any allowed, online CPU? */
 		for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
-			if (!cpu_online(dest_cpu))
-				continue;
 			if (!cpu_active(dest_cpu))
 				continue;
 			goto out;
@@ -1515,8 +1585,10 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 {
 	lockdep_assert_held(&p->pi_lock);
 
-	if (p->nr_cpus_allowed > 1)
+	if (tsk_nr_cpus_allowed(p) > 1)
 		cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
+	else
+		cpu = cpumask_any(tsk_cpus_allowed(p));
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -1604,8 +1676,8 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl
 /*
  * Mark the task runnable and perform wakeup-preemption.
  */
-static void
-ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
+static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
+			   struct pin_cookie cookie)
 {
 	check_preempt_curr(rq, p, wake_flags);
 	p->state = TASK_RUNNING;
@@ -1617,9 +1689,9 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 		 * Our task @p is fully woken up and running; so its safe to
 		 * drop the rq->lock, hereafter rq is only used for statistics.
 		 */
-		lockdep_unpin_lock(&rq->lock);
+		lockdep_unpin_lock(&rq->lock, cookie);
 		p->sched_class->task_woken(rq, p);
-		lockdep_pin_lock(&rq->lock);
+		lockdep_repin_lock(&rq->lock, cookie);
 	}
 
 	if (rq->idle_stamp) {
@@ -1637,17 +1709,23 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 }
 
 static void
-ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
+ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
+		 struct pin_cookie cookie)
 {
+	int en_flags = ENQUEUE_WAKEUP;
+
 	lockdep_assert_held(&rq->lock);
 
 #ifdef CONFIG_SMP
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
+
+	if (wake_flags & WF_MIGRATED)
+		en_flags |= ENQUEUE_MIGRATED;
 #endif
 
-	ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING);
-	ttwu_do_wakeup(rq, p, wake_flags);
+	ttwu_activate(rq, p, en_flags);
+	ttwu_do_wakeup(rq, p, wake_flags, cookie);
 }
 
 /*
@@ -1658,17 +1736,18 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
  */
 static int ttwu_remote(struct task_struct *p, int wake_flags)
 {
+	struct rq_flags rf;
 	struct rq *rq;
 	int ret = 0;
 
-	rq = __task_rq_lock(p);
+	rq = __task_rq_lock(p, &rf);
 	if (task_on_rq_queued(p)) {
 		/* check_preempt_curr() may use rq clock */
 		update_rq_clock(rq);
-		ttwu_do_wakeup(rq, p, wake_flags);
+		ttwu_do_wakeup(rq, p, wake_flags, rf.cookie);
 		ret = 1;
 	}
-	__task_rq_unlock(rq);
+	__task_rq_unlock(rq, &rf);
 
 	return ret;
 }
@@ -1678,6 +1757,7 @@ void sched_ttwu_pending(void)
 {
 	struct rq *rq = this_rq();
 	struct llist_node *llist = llist_del_all(&rq->wake_list);
+	struct pin_cookie cookie;
 	struct task_struct *p;
 	unsigned long flags;
 
@@ -1685,15 +1765,19 @@ void sched_ttwu_pending(void)
 		return;
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
-	lockdep_pin_lock(&rq->lock);
+	cookie = lockdep_pin_lock(&rq->lock);
 
 	while (llist) {
 		p = llist_entry(llist, struct task_struct, wake_entry);
 		llist = llist_next(llist);
-		ttwu_do_activate(rq, p, 0);
+		/*
+		 * See ttwu_queue(); we only call ttwu_queue_remote() when
+		 * its a x-cpu wakeup.
+		 */
+		ttwu_do_activate(rq, p, WF_MIGRATED, cookie);
 	}
 
-	lockdep_unpin_lock(&rq->lock);
+	lockdep_unpin_lock(&rq->lock, cookie);
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
@@ -1777,9 +1861,10 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 }
 #endif /* CONFIG_SMP */
 
-static void ttwu_queue(struct task_struct *p, int cpu)
+static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 {
 	struct rq *rq = cpu_rq(cpu);
+	struct pin_cookie cookie;
 
 #if defined(CONFIG_SMP)
 	if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
@@ -1790,9 +1875,9 @@ static void ttwu_queue(struct task_struct *p, int cpu)
 #endif
 
 	raw_spin_lock(&rq->lock);
-	lockdep_pin_lock(&rq->lock);
-	ttwu_do_activate(rq, p, 0);
-	lockdep_unpin_lock(&rq->lock);
+	cookie = lockdep_pin_lock(&rq->lock);
+	ttwu_do_activate(rq, p, wake_flags, cookie);
+	lockdep_unpin_lock(&rq->lock, cookie);
 	raw_spin_unlock(&rq->lock);
 }
 
@@ -1961,9 +2046,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	p->sched_contributes_to_load = !!task_contributes_to_load(p);
 	p->state = TASK_WAKING;
 
-	if (p->sched_class->task_waking)
-		p->sched_class->task_waking(p);
-
 	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
@@ -1971,7 +2053,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	}
 #endif /* CONFIG_SMP */
 
-	ttwu_queue(p, cpu);
+	ttwu_queue(p, cpu, wake_flags);
 stat:
 	if (schedstat_enabled())
 		ttwu_stat(p, cpu, wake_flags);
@@ -1989,7 +2071,7 @@ out:
  * ensure that this_rq() is locked, @p is bound to this_rq() and not
  * the current task.
  */
-static void try_to_wake_up_local(struct task_struct *p)
+static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie)
 {
 	struct rq *rq = task_rq(p);
 
@@ -2006,11 +2088,11 @@ static void try_to_wake_up_local(struct task_struct *p)
 		 * disabled avoiding further scheduler activity on it and we've
 		 * not yet picked a replacement task.
 		 */
-		lockdep_unpin_lock(&rq->lock);
+		lockdep_unpin_lock(&rq->lock, cookie);
 		raw_spin_unlock(&rq->lock);
 		raw_spin_lock(&p->pi_lock);
 		raw_spin_lock(&rq->lock);
-		lockdep_pin_lock(&rq->lock);
+		lockdep_repin_lock(&rq->lock, cookie);
 	}
 
 	if (!(p->state & TASK_NORMAL))
@@ -2021,7 +2103,7 @@ static void try_to_wake_up_local(struct task_struct *p)
 	if (!task_on_rq_queued(p))
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
-	ttwu_do_wakeup(rq, p, 0);
+	ttwu_do_wakeup(rq, p, 0, cookie);
 	if (schedstat_enabled())
 		ttwu_stat(p, smp_processor_id(), 0);
 out:
@@ -2381,7 +2463,8 @@ static int dl_overflow(struct task_struct *p, int policy,
 	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
 	int cpus, err = -1;
 
-	if (new_bw == p->dl.dl_bw)
+	/* !deadline task may carry old deadline bandwidth */
+	if (new_bw == p->dl.dl_bw && task_has_dl_policy(p))
 		return 0;
 
 	/*
@@ -2420,12 +2503,12 @@ extern void init_dl_bw(struct dl_bw *dl_b);
  */
 void wake_up_new_task(struct task_struct *p)
 {
-	unsigned long flags;
+	struct rq_flags rf;
 	struct rq *rq;
 
-	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	/* Initialize new task's runnable average */
 	init_entity_runnable_average(&p->se);
+	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
 #ifdef CONFIG_SMP
 	/*
 	 * Fork balancing, do it here and not earlier because:
@@ -2434,8 +2517,10 @@ void wake_up_new_task(struct task_struct *p)
 	 */
 	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
+	/* Post initialize new task's util average when its cfs_rq is set */
+	post_init_entity_util_avg(&p->se);
 
-	rq = __task_rq_lock(p);
+	rq = __task_rq_lock(p, &rf);
 	activate_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
@@ -2446,12 +2531,12 @@ void wake_up_new_task(struct task_struct *p)
 		 * Nothing relies on rq->lock after this, so its fine to
 		 * drop it.
 		 */
-		lockdep_unpin_lock(&rq->lock);
+		lockdep_unpin_lock(&rq->lock, rf.cookie);
 		p->sched_class->task_woken(rq, p);
-		lockdep_pin_lock(&rq->lock);
+		lockdep_repin_lock(&rq->lock, rf.cookie);
 	}
 #endif
-	task_rq_unlock(rq, p, &flags);
+	task_rq_unlock(rq, p, &rf);
 }
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -2713,7 +2798,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
  */
 static __always_inline struct rq *
 context_switch(struct rq *rq, struct task_struct *prev,
-	       struct task_struct *next)
+	       struct task_struct *next, struct pin_cookie cookie)
 {
 	struct mm_struct *mm, *oldmm;
 
@@ -2733,7 +2818,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 		atomic_inc(&oldmm->mm_count);
 		enter_lazy_tlb(oldmm, next);
 	} else
-		switch_mm(oldmm, mm, next);
+		switch_mm_irqs_off(oldmm, mm, next);
 
 	if (!prev->mm) {
 		prev->active_mm = NULL;
@@ -2745,7 +2830,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 * of the scheduler it's an obvious special-case), so we
 	 * do an early lockdep release here:
 	 */
-	lockdep_unpin_lock(&rq->lock);
+	lockdep_unpin_lock(&rq->lock, cookie);
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 
 	/* Here we just switch the register state and the stack. */
@@ -2867,7 +2952,7 @@ EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
  */
 unsigned long long task_sched_runtime(struct task_struct *p)
 {
-	unsigned long flags;
+	struct rq_flags rf;
 	struct rq *rq;
 	u64 ns;
 
@@ -2887,7 +2972,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 		return p->se.sum_exec_runtime;
 #endif
 
-	rq = task_rq_lock(p, &flags);
+	rq = task_rq_lock(p, &rf);
 	/*
 	 * Must be ->curr _and_ ->on_rq.  If dequeued, we would
 	 * project cycles that may never be accounted to this
@@ -2898,7 +2983,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 		p->sched_class->update_curr(rq);
 	}
 	ns = p->se.sum_exec_runtime;
-	task_rq_unlock(rq, p, &flags);
+	task_rq_unlock(rq, p, &rf);
 
 	return ns;
 }
@@ -2918,7 +3003,7 @@ void scheduler_tick(void)
 	raw_spin_lock(&rq->lock);
 	update_rq_clock(rq);
 	curr->sched_class->task_tick(rq, curr, 0);
-	update_cpu_load_active(rq);
+	cpu_load_update_active(rq);
 	calc_global_load_tick(rq);
 	raw_spin_unlock(&rq->lock);
 
@@ -2961,6 +3046,20 @@ u64 scheduler_tick_max_deferment(void)
 
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
 				defined(CONFIG_PREEMPT_TRACER))
+/*
+ * If the value passed in is equal to the current preempt count
+ * then we just disabled preemption. Start timing the latency.
+ */
+static inline void preempt_latency_start(int val)
+{
+	if (preempt_count() == val) {
+		unsigned long ip = get_lock_parent_ip();
+#ifdef CONFIG_DEBUG_PREEMPT
+		current->preempt_disable_ip = ip;
+#endif
+		trace_preempt_off(CALLER_ADDR0, ip);
+	}
+}
 
 void preempt_count_add(int val)
 {
@@ -2979,17 +3078,21 @@ void preempt_count_add(int val)
 	DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
 				PREEMPT_MASK - 10);
 #endif
-	if (preempt_count() == val) {
-		unsigned long ip = get_lock_parent_ip();
-#ifdef CONFIG_DEBUG_PREEMPT
-		current->preempt_disable_ip = ip;
-#endif
-		trace_preempt_off(CALLER_ADDR0, ip);
-	}
+	preempt_latency_start(val);
 }
 EXPORT_SYMBOL(preempt_count_add);
 NOKPROBE_SYMBOL(preempt_count_add);
 
+/*
+ * If the value passed in equals to the current preempt count
+ * then we just enabled preemption. Stop timing the latency.
+ */
+static inline void preempt_latency_stop(int val)
+{
+	if (preempt_count() == val)
+		trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
+}
+
 void preempt_count_sub(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
@@ -3006,13 +3109,15 @@ void preempt_count_sub(int val)
 		return;
 #endif
 
-	if (preempt_count() == val)
-		trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
+	preempt_latency_stop(val);
 	__preempt_count_sub(val);
 }
 EXPORT_SYMBOL(preempt_count_sub);
 NOKPROBE_SYMBOL(preempt_count_sub);
 
+#else
+static inline void preempt_latency_start(int val) { }
+static inline void preempt_latency_stop(int val) { }
 #endif
 
 /*
@@ -3065,7 +3170,7 @@ static inline void schedule_debug(struct task_struct *prev)
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev)
+pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
 {
 	const struct sched_class *class = &fair_sched_class;
 	struct task_struct *p;
@@ -3076,20 +3181,20 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
 	 */
 	if (likely(prev->sched_class == class &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
-		p = fair_sched_class.pick_next_task(rq, prev);
+		p = fair_sched_class.pick_next_task(rq, prev, cookie);
 		if (unlikely(p == RETRY_TASK))
 			goto again;
 
 		/* assumes fair_sched_class->next == idle_sched_class */
 		if (unlikely(!p))
-			p = idle_sched_class.pick_next_task(rq, prev);