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

Pull scheduler changes from Ingo Molnar:
 "The main changes in this cycle are:

   - (much) improved CONFIG_NUMA_BALANCING support from Mel Gorman, Rik
     van Riel, Peter Zijlstra et al.  Yay!

   - optimize preemption counter handling: merge the NEED_RESCHED flag
     into the preempt_count variable, by Peter Zijlstra.

   - wait.h fixes and code reorganization from Peter Zijlstra

   - cfs_bandwidth fixes from Ben Segall

   - SMP load-balancer cleanups from Peter Zijstra

   - idle balancer improvements from Jason Low

   - other fixes and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (129 commits)
  ftrace, sched: Add TRACE_FLAG_PREEMPT_RESCHED
  stop_machine: Fix race between stop_two_cpus() and stop_cpus()
  sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus
  sched: Fix asymmetric scheduling for POWER7
  sched: Move completion code from core.c to completion.c
  sched: Move wait code from core.c to wait.c
  sched: Move wait.c into kernel/sched/
  sched/wait: Fix __wait_event_interruptible_lock_irq_timeout()
  sched: Avoid throttle_cfs_rq() racing with period_timer stopping
  sched: Guarantee new group-entities always have weight
  sched: Fix hrtimer_cancel()/rq->lock deadlock
  sched: Fix cfs_bandwidth misuse of hrtimer_expires_remaining
  sched: Fix race on toggling cfs_bandwidth_used
  sched: Remove extra put_online_cpus() inside sched_setaffinity()
  sched/rt: Fix task_tick_rt() comment
  sched/wait: Fix build breakage
  sched/wait: Introduce prepare_to_wait_event()
  sched/wait: Add ___wait_cond_timeout() to wait_event*_timeout() too
  sched: Remove get_online_cpus() usage
  sched: Fix race in migrate_swap_stop()
  ...

1 files changed, 234 insertions, 449 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5ac63c9a995a..1deccd78be98 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -513,12 +513,11 @@ static inline void init_hrtick(void)
  * might also involve a cross-CPU call to trigger the scheduler on
  * the target CPU.
  */
-#ifdef CONFIG_SMP
 void resched_task(struct task_struct *p)
 {
 	int cpu;
 
-	assert_raw_spin_locked(&task_rq(p)->lock);
+	lockdep_assert_held(&task_rq(p)->lock);
 
 	if (test_tsk_need_resched(p))
 		return;
@@ -526,8 +525,10 @@ void resched_task(struct task_struct *p)
 	set_tsk_need_resched(p);
 
 	cpu = task_cpu(p);
-	if (cpu == smp_processor_id())
+	if (cpu == smp_processor_id()) {
+		set_preempt_need_resched();
 		return;
+	}
 
 	/* NEED_RESCHED must be visible before we test polling */
 	smp_mb();
@@ -546,6 +547,7 @@ void resched_cpu(int cpu)
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
+#ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ_COMMON
 /*
  * In the semi idle case, use the nearest busy cpu for migrating timers
@@ -693,12 +695,6 @@ void sched_avg_update(struct rq *rq)
 	}
 }
 
-#else /* !CONFIG_SMP */
-void resched_task(struct task_struct *p)
-{
-	assert_raw_spin_locked(&task_rq(p)->lock);
-	set_tsk_need_resched(p);
-}
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
@@ -767,14 +763,14 @@ static void set_load_weight(struct task_struct *p)
 static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_rq_clock(rq);
-	sched_info_queued(p);
+	sched_info_queued(rq, p);
 	p->sched_class->enqueue_task(rq, p, flags);
 }
 
 static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_rq_clock(rq);
-	sched_info_dequeued(p);
+	sched_info_dequeued(rq, p);
 	p->sched_class->dequeue_task(rq, p, flags);
 }
 
@@ -987,7 +983,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * ttwu() will sort out the placement.
 	 */
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
-			!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
+			!(task_preempt_count(p) & PREEMPT_ACTIVE));
 
 #ifdef CONFIG_LOCKDEP
 	/*
@@ -1017,6 +1013,107 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	__set_task_cpu(p, new_cpu);
 }
 
+static void __migrate_swap_task(struct task_struct *p, int cpu)
+{
+	if (p->on_rq) {
+		struct rq *src_rq, *dst_rq;
+
+		src_rq = task_rq(p);
+		dst_rq = cpu_rq(cpu);
+
+		deactivate_task(src_rq, p, 0);
+		set_task_cpu(p, cpu);
+		activate_task(dst_rq, p, 0);
+		check_preempt_curr(dst_rq, p, 0);
+	} else {
+		/*
+		 * Task isn't running anymore; make it appear like we migrated
+		 * it before it went to sleep. This means on wakeup we make the
+		 * previous cpu our targer instead of where it really is.
+		 */
+		p->wake_cpu = cpu;
+	}
+}
+
+struct migration_swap_arg {
+	struct task_struct *src_task, *dst_task;
+	int src_cpu, dst_cpu;
+};
+
+static int migrate_swap_stop(void *data)
+{
+	struct migration_swap_arg *arg = data;
+	struct rq *src_rq, *dst_rq;
+	int ret = -EAGAIN;
+
+	src_rq = cpu_rq(arg->src_cpu);
+	dst_rq = cpu_rq(arg->dst_cpu);
+
+	double_raw_lock(&arg->src_task->pi_lock,
+			&arg->dst_task->pi_lock);
+	double_rq_lock(src_rq, dst_rq);
+	if (task_cpu(arg->dst_task) != arg->dst_cpu)
+		goto unlock;
+
+	if (task_cpu(arg->src_task) != arg->src_cpu)
+		goto unlock;
+
+	if (!cpumask_test_cpu(arg->dst_cpu, tsk_cpus_allowed(arg->src_task)))
+		goto unlock;
+
+	if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task)))
+		goto unlock;
+
+	__migrate_swap_task(arg->src_task, arg->dst_cpu);
+	__migrate_swap_task(arg->dst_task, arg->src_cpu);
+
+	ret = 0;
+
+unlock:
+	double_rq_unlock(src_rq, dst_rq);
+	raw_spin_unlock(&arg->dst_task->pi_lock);
+	raw_spin_unlock(&arg->src_task->pi_lock);
+
+	return ret;
+}
+
+/*
+ * Cross migrate two tasks
+ */
+int migrate_swap(struct task_struct *cur, struct task_struct *p)
+{
+	struct migration_swap_arg arg;
+	int ret = -EINVAL;
+
+	arg = (struct migration_swap_arg){
+		.src_task = cur,
+		.src_cpu = task_cpu(cur),
+		.dst_task = p,
+		.dst_cpu = task_cpu(p),
+	};
+
+	if (arg.src_cpu == arg.dst_cpu)
+		goto out;
+
+	/*
+	 * These three tests are all lockless; this is OK since all of them
+	 * will be re-checked with proper locks held further down the line.
+	 */
+	if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
+		goto out;
+
+	if (!cpumask_test_cpu(arg.dst_cpu, tsk_cpus_allowed(arg.src_task)))
+		goto out;
+
+	if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task)))
+		goto out;
+
+	ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg);
+
+out:
+	return ret;
+}
+
 struct migration_arg {
 	struct task_struct *task;
 	int dest_cpu;
@@ -1236,9 +1333,9 @@ out:
  * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 {
-	int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+	cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -1330,12 +1427,13 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 
 	if (rq->idle_stamp) {
 		u64 delta = rq_clock(rq) - rq->idle_stamp;
-		u64 max = 2*sysctl_sched_migration_cost;
+		u64 max = 2*rq->max_idle_balance_cost;
+
+		update_avg(&rq->avg_idle, delta);
 
-		if (delta > max)
+		if (rq->avg_idle > max)
 			rq->avg_idle = max;
-		else
-			update_avg(&rq->avg_idle, delta);
+
 		rq->idle_stamp = 0;
 	}
 #endif
@@ -1396,6 +1494,14 @@ static void sched_ttwu_pending(void)
 
 void scheduler_ipi(void)
 {
+	/*
+	 * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
+	 * TIF_NEED_RESCHED remotely (for the first time) will also send
+	 * this IPI.
+	 */
+	if (tif_need_resched())
+		set_preempt_need_resched();
+
 	if (llist_empty(&this_rq()->wake_list)
 			&& !tick_nohz_full_cpu(smp_processor_id())
 			&& !got_nohz_idle_kick())
@@ -1513,7 +1619,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	if (p->sched_class->task_waking)
 		p->sched_class->task_waking(p);
 
-	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
 		set_task_cpu(p, cpu);
@@ -1595,7 +1701,7 @@ int wake_up_state(struct task_struct *p, unsigned int state)
  *
  * __sched_fork() is basic setup used by init_idle() too:
  */
-static void __sched_fork(struct task_struct *p)
+static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	p->on_rq			= 0;
 
@@ -1619,16 +1725,24 @@ static void __sched_fork(struct task_struct *p)
 
 #ifdef CONFIG_NUMA_BALANCING
 	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
-		p->mm->numa_next_scan = jiffies;
-		p->mm->numa_next_reset = jiffies;
+		p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
 		p->mm->numa_scan_seq = 0;
 	}
 
+	if (clone_flags & CLONE_VM)
+		p->numa_preferred_nid = current->numa_preferred_nid;
+	else
+		p->numa_preferred_nid = -1;
+
 	p->node_stamp = 0ULL;
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
-	p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
+	p->numa_faults = NULL;
+	p->numa_faults_buffer = NULL;
+
+	INIT_LIST_HEAD(&p->numa_entry);
+	p->numa_group = NULL;
 #endif /* CONFIG_NUMA_BALANCING */
 }
 
@@ -1654,12 +1768,12 @@ void set_numabalancing_state(bool enabled)
 /*
  * fork()/clone()-time setup:
  */
-void sched_fork(struct task_struct *p)
+void sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long flags;
 	int cpu = get_cpu();
 
-	__sched_fork(p);
+	__sched_fork(clone_flags, p);
 	/*
 	 * We mark the process as running here. This guarantees that
 	 * nobody will actually run it, and a signal or other external
@@ -1717,10 +1831,7 @@ void sched_fork(struct task_struct *p)
 #if defined(CONFIG_SMP)
 	p->on_cpu = 0;
 #endif
-#ifdef CONFIG_PREEMPT_COUNT
-	/* Want to start with kernel preemption disabled. */
-	task_thread_info(p)->preempt_count = 1;
-#endif
+	init_task_preempt_count(p);
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 #endif
@@ -1747,7 +1858,7 @@ void wake_up_new_task(struct task_struct *p)
 	 *  - cpus_allowed can change in the fork path
 	 *  - any previously selected cpu might disappear through hotplug
 	 */
-	set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0));
+	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 
 	/* Initialize new task's runnable average */
@@ -1838,7 +1949,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next)
 {
 	trace_sched_switch(prev, next);
-	sched_info_switch(prev, next);
+	sched_info_switch(rq, prev, next);
 	perf_event_task_sched_out(prev, next);
 	fire_sched_out_preempt_notifiers(prev, next);
 	prepare_lock_switch(rq, next);
@@ -1890,6 +2001,8 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	if (mm)
 		mmdrop(mm);
 	if (unlikely(prev_state == TASK_DEAD)) {
+		task_numa_free(prev);
+
 		/*
 		 * Remove function-return probe instances associated with this
 		 * task and put them back on the free list.
@@ -2073,7 +2186,7 @@ void sched_exec(void)
 	int dest_cpu;
 
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
+	dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0);
 	if (dest_cpu == smp_processor_id())
 		goto unlock;
 
@@ -2215,7 +2328,7 @@ notrace unsigned long get_parent_ip(unsigned long addr)
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
 				defined(CONFIG_PREEMPT_TRACER))
 
-void __kprobes add_preempt_count(int val)
+void __kprobes preempt_count_add(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
@@ -2224,7 +2337,7 @@ void __kprobes add_preempt_count(int val)
 	if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
 		return;
 #endif
-	preempt_count() += val;
+	__preempt_count_add(val);
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
 	 * Spinlock count overflowing soon?
@@ -2235,9 +2348,9 @@ void __kprobes add_preempt_count(int val)
 	if (preempt_count() == val)
 		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
-EXPORT_SYMBOL(add_preempt_count);
+EXPORT_SYMBOL(preempt_count_add);
 
-void __kprobes sub_preempt_count(int val)
+void __kprobes preempt_count_sub(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
@@ -2255,9 +2368,9 @@ void __kprobes sub_preempt_count(int val)
 
 	if (preempt_count() == val)
 		trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
-	preempt_count() -= val;
+	__preempt_count_sub(val);
 }
-EXPORT_SYMBOL(sub_preempt_count);
+EXPORT_SYMBOL(preempt_count_sub);
 
 #endif
 
@@ -2430,6 +2543,7 @@ need_resched:
 	put_prev_task(rq, prev);
 	next = pick_next_task(rq);
 	clear_tsk_need_resched(prev);
+	clear_preempt_need_resched();
 	rq->skip_clock_update = 0;
 
 	if (likely(prev != next)) {
@@ -2520,9 +2634,9 @@ asmlinkage void __sched notrace preempt_schedule(void)
 		return;
 
 	do {
-		add_preempt_count_notrace(PREEMPT_ACTIVE);
+		__preempt_count_add(PREEMPT_ACTIVE);
 		__schedule();
-		sub_preempt_count_notrace(PREEMPT_ACTIVE);
+		__preempt_count_sub(PREEMPT_ACTIVE);
 
 		/*
 		 * Check again in case we missed a preemption opportunity
@@ -2541,20 +2655,19 @@ EXPORT_SYMBOL(preempt_schedule);
  */
 asmlinkage void __sched preempt_schedule_irq(void)
 {
-	struct thread_info *ti = current_thread_info();
 	enum ctx_state prev_state;
 
 	/* Catch callers which need to be fixed */
-	BUG_ON(ti->preempt_count || !irqs_disabled());
+	BUG_ON(preempt_count() || !irqs_disabled());
 
 	prev_state = exception_enter();
 
 	do {
-		add_preempt_count(PREEMPT_ACTIVE);
+		__preempt_count_add(PREEMPT_ACTIVE);
 		local_irq_enable();
 		__schedule();
 		local_irq_disable();
-		sub_preempt_count(PREEMPT_ACTIVE);
+		__preempt_count_sub(PREEMPT_ACTIVE);
 
 		/*
 		 * Check again in case we missed a preemption opportunity
@@ -2575,393 +2688,6 @@ int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
 }
 EXPORT_SYMBOL(default_wake_function);
 
-/*
- * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
- * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
- * number) then we wake all the non-exclusive tasks and one exclusive task.
- *
- * There are circumstances in which we can try to wake a task which has already
- * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
- * zero in this (rare) case, and we handle it by continuing to scan the queue.
- */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-			int nr_exclusive, int wake_flags, void *key)
-{
-	wait_queue_t *curr, *next;
-
-	list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
-		unsigned flags = curr->flags;
-
-		if (curr->func(curr, mode, wake_flags, key) &&
-				(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
-			break;
-	}
-}
-
-/**
- * __wake_up - wake up threads blocked on a waitqueue.
- * @q: the waitqueue
- * @mode: which threads
- * @nr_exclusive: how many wake-one or wake-many threads to wake up
- * @key: is directly passed to the wakeup function
- *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
- */
-void __wake_up(wait_queue_head_t *q, unsigned int mode,
-			int nr_exclusive, void *key)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive, 0, key);
-	spin_unlock_irqrestore(&q->lock, flags);
-}
-EXPORT_SYMBOL(__wake_up);
-
-/*
- * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
- */
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
-{
-	__wake_up_common(q, mode, nr, 0, NULL);
-}
-EXPORT_SYMBOL_GPL(__wake_up_locked);
-
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
-{
-	__wake_up_common(q, mode, 1, 0, key);
-}
-EXPORT_SYMBOL_GPL(__wake_up_locked_key);
-
-/**
- * __wake_up_sync_key - wake up threads blocked on a waitqueue.
- * @q: the waitqueue
- * @mode: which threads
- * @nr_exclusive: how many wake-one or wake-many threads to wake up
- * @key: opaque value to be passed to wakeup targets
- *
- * The sync wakeup differs that the waker knows that it will schedule
- * away soon, so while the target thread will be woken up, it will not
- * be migrated to another CPU - ie. the two threads are 'synchronized'
- * with each other. This can prevent needless bouncing between CPUs.
- *
- * On UP it can prevent extra preemption.
- *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
- */
-void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
-			int nr_exclusive, void *key)
-{
-	unsigned long flags;
-	int wake_flags = WF_SYNC;
-
-	if (unlikely(!q))
-		return;
-
-	if (unlikely(nr_exclusive != 1))
-		wake_flags = 0;
-
-	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive, wake_flags, key);
-	spin_unlock_irqrestore(&q->lock, flags);
-}
-EXPORT_SYMBOL_GPL(__wake_up_sync_key);
-
-/*
- * __wake_up_sync - see __wake_up_sync_key()
- */
-void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
-{
-	__wake_up_sync_key(q, mode, nr_exclusive, NULL);
-}
-EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
-
-/**
- * complete: - signals a single thread waiting on this completion
- * @x:  holds the state of this particular completion
- *
- * This will wake up a single thread waiting on this completion. Threads will be
- * awakened in the same order in which they were queued.
- *
- * See also complete_all(), wait_for_completion() and related routines.
- *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
- */
-void complete(struct completion *x)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&x->wait.lock, flags);
-	x->done++;
-	__wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
-	spin_unlock_irqrestore(&x->wait.lock, flags);
-}
-EXPORT_SYMBOL(complete);
-
-/**
- * complete_all: - signals all threads waiting on this completion
- * @x:  holds the state of this particular completion
- *
- * This will wake up all threads waiting on this particular completion event.
- *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
- */
-void complete_all(struct completion *x)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&x->wait.lock, flags);
-	x->done += UINT_MAX/2;
-	__wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
-	spin_unlock_irqrestore(&x->wait.lock, flags);
-}
-EXPORT_SYMBOL(complete_all);
-
-static inline long __sched
-do_wait_for_common(struct completion *x,
-		   long (*action)(long), long timeout, int state)
-{
-	if (!x->done) {
-		DECLARE_WAITQUEUE(wait, current);
-
-		__add_wait_queue_tail_exclusive(&x->wait, &wait);
-		do {
-			if (signal_pending_state(state, current)) {
-				timeout = -ERESTARTSYS;
-				break;
-			}
-			__set_current_state(state);
-			spin_unlock_irq(&x->wait.lock);
-			timeout = action(timeout);
-			spin_lock_irq(&x->wait.lock);
-		} while (!x->done && timeout);
-		__remove_wait_queue(&x->wait, &wait);
-		if (!x->done)
-			return timeout;
-	}
-	x->done--;
-	return timeout ?: 1;
-}
-
-static inline long __sched
-__wait_for_common(struct completion *x,
-		  long (*action)(long), long timeout, int state)
-{
-	might_sleep();
-
-	spin_lock_irq(&x->wait.lock);
-	timeout = do_wait_for_common(x, action, timeout, state);
-	spin_unlock_irq(&x->wait.lock);
-	return timeout;
-}
-
-static long __sched
-wait_for_common(struct completion *x, long timeout, int state)
-{
-	return __wait_for_common(x, schedule_timeout, timeout, state);
-}
-
-static long __sched
-wait_for_common_io(struct completion *x, long timeout, int state)
-{
-	return __wait_for_common(x, io_schedule_timeout, timeout, state);
-}
-
-/**
- * wait_for_completion: - waits for completion of a task
- * @x:  holds the state of this particular completion
- *
- * This waits to be signaled for completion of a specific task. It is NOT
- * interruptible and there is no timeout.
- *
- * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
- * and interrupt capability. Also see complete().
- */
-void __sched wait_for_completion(struct completion *x)
-{
-	wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion);
-
-/**
- * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
- * @x:  holds the state of this particular completion
- * @timeout:  timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be signaled or for a
- * specified timeout to expire. The timeout is in jiffies. It is not
- * interruptible.
- *
- * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
- * till timeout) if completed.
- */
-unsigned long __sched
-wait_for_completion_timeout(struct completion *x, unsigned long timeout)
-{
-	return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_timeout);
-
-/**
- * wait_for_completion_io: - waits for completion of a task
- * @x:  holds the state of this particular completion
- *
- * This waits to be signaled for completion of a specific task. It is NOT
- * interruptible and there is no timeout. The caller is accounted as waiting
- * for IO.
- */
-void __sched wait_for_completion_io(struct completion *x)
-{
-	wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_io);
-
-/**
- * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
- * @x:  holds the state of this particular completion
- * @timeout:  timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be signaled or for a
- * specified timeout to expire. The timeout is in jiffies. It is not
- * interruptible. The caller is accounted as waiting for IO.
- *
- * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
- * till timeout) if completed.
- */
-unsigned long __sched
-wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
-{
-	return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_io_timeout);
-
-/**
- * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
- * @x:  holds the state of this particular completion
- *
- * This waits for completion of a specific task to be signaled. It is
- * interruptible.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if completed.
- */
-int __sched wait_for_completion_interruptible(struct completion *x)
-{
-	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
-	if (t == -ERESTARTSYS)
-		return t;
-	return 0;
-}
-EXPORT_SYMBOL(wait_for_completion_interruptible);
-
-/**
- * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
- * @x:  holds the state of this particular completion
- * @timeout:  timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be signaled or for a
- * specified timeout to expire. It is interruptible. The timeout is in jiffies.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
- * or number of jiffies left till timeout) if completed.
- */
-long __sched
-wait_for_completion_interruptible_timeout(struct completion *x,
-					  unsigned long timeout)
-{
-	return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
-
-/**
- * wait_for_completion_killable: - waits for completion of a task (killable)
- * @x:  holds the state of this particular completion
- *
- * This waits to be signaled for completion of a specific task. It can be
- * interrupted by a kill signal.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if completed.
- */
-int __sched wait_for_completion_killable(struct completion *x)
-{
-	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
-	if (t == -ERESTARTSYS)
-		return t;
-	return 0;
-}
-EXPORT_SYMBOL(wait_for_completion_killable);
-
-/**
- * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
- * @x:  holds the state of this particular completion
- * @timeout:  timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be
- * signaled or for a specified timeout to expire. It can be
- * interrupted by a kill signal. The timeout is in jiffies.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
- * or number of jiffies left till timeout) if completed.
- */
-long __sched
-wait_for_completion_killable_timeout(struct completion *x,
-				     unsigned long timeout)
-{
-	return wait_for_common(x, timeout, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(wait_for_completion_killable_timeout);
-
-/**
- *	try_wait_for_completion - try to decrement a completion without blocking
- *	@x:	completion structure
- *
- *	Return: 0 if a decrement cannot be done without blocking
- *		 1 if a decrement succeeded.
- *
- *	If a completion is being used as a counting completion,
- *	attempt to decrement the counter without blocking. This
- *	enables us to avoid waiting if the resource the completion
- *	is protecting is not available.
- */
-bool try_wait_for_completion(struct completion *x)
-{
-	unsigned long flags;
-	int ret = 1;
-
-	spin_lock_irqsave(&x->wait.lock, flags);
-	if (!x->done)
-		ret = 0;
-	else
-		x->done--;
-	spin_unlock_irqrestore(&x->wait.lock, flags);
-	return ret;
-}
-EXPORT_SYMBOL(try_wait_for_completion);
-
-/**
- *	completion_done - Test to see if a completion has any waiters
- *	@x:	completion structure
- *
- *	Return: 0 if there are waiters (wait_for_completion() in progress)
- *		 1 if there are no waiters.
- *
- */
-bool completion_done(struct completion *x)
-{
-	unsigned long flags;
-	int ret = 1;
-
-	spin_lock_irqsave(&x->wait.lock, flags);
-	if (!x->done)
-		ret = 0;
-	spin_unlock_irqrestore(&x->wait.lock, flags);
-	return ret;
-}
-EXPORT_SYMBOL(completion_done);
-
 static long __sched
 sleep_on_common(wait_queue_head_t *q, int state, long timeout)
 {
@@ -3598,13 +3324,11 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	struct task_struct *p;
 	int retval;
 
-	get_online_cpus();
 	rcu_read_lock();
 
 	p = find_process_by_pid(pid);
 	if (!p) {
 		rcu_read_unlock();
-		put_online_cpus();
 		return -ESRCH;
 	}
 
@@ -3661,7 +3385,6 @@ out_free_cpus_allowed:
 	free_cpumask_var(cpus_allowed);
 out_put_task:
 	put_task_struct(p);
-	put_online_cpus();
 	return retval;
 }
 
@@ -3706,7 +3429,6 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
 	unsigned long flags;
 	int retval;
 
-	get_online_cpus();
 	rcu_read_lock();
 
 	retval = -ESRCH;
@@ -3719,12 +3441,11 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
 		goto out_unlock;
 
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
+	cpumask_and(mask, &p->cpus_allowed, cpu_active_mask);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 out_unlock:
 	rcu_read_unlock();
-	put_online_cpus();
 
 	return retval;
 }
@@ -3794,16 +3515,11 @@ SYSCALL_DEFINE0(sched_yield)
 	return 0;
 }
 
-static inline int should_resched(void)
-{
-	return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
-}
-
 static void __cond_resched(void)
 {
-	add_preempt_count(PREEMPT_ACTIVE);
+	__preempt_count_add(PREEMPT_ACTIVE);
 	__schedule();
-	sub_preempt_count(PREEMPT_ACTIVE);
+	__preempt_count_sub(PREEMPT_ACTIVE);
 }
 
 int __sched _cond_resched(void)
@@ -4186,7 +3902,7 @@ void init_idle(struct task_struct *idle, int cpu)
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
 
-	__sched_fork(idle);
+	__sched_fork(0, idle);
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
 
@@ -4212,7 +3928,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
 	/* Set the preempt count _outside_ the spinlocks! */
-	task_thread_info(idle)->preempt_count = 0;
+	init_idle_preempt_count(idle, cpu);
 
 	/*
 	 * The idle tasks have their own, simple scheduling class:
@@ -4346,6 +4062,53 @@ fail:
 	return ret;
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+/* Migrate current task p to target_cpu */
+int migrate_task_to(struct task_struct *p, int target_cpu)
+{
+	struct migration_arg arg = { p, target_cpu };
+	int curr_cpu = task_cpu(p);
+
+	if (curr_cpu == target_cpu)
+		return 0;
+
+	if (!cpumask_test_cpu(target_cpu, tsk_cpus_allowed(p)))
+		return -EINVAL;
+
+	/* TODO: This is not properly updating schedstats */
+
+	return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
+}
+
+/*
+ * Requeue a task on a given node and accurately track the number of NUMA
+ * tasks on the runqueues
+ */
+void sched_setnuma(struct task_struct *p, int nid)
+{
+	struct rq *rq;
+	unsigned long flags;
+	bool on_rq, running;
+
+	rq = task_rq_lock(p, &flags);
+	on_rq = p->on_rq;
+	running = task_current(rq, p);
+
+	if (on_rq)
+		dequeue_task(rq, p, 0);
+	if (running)
+		p->sched_class->put_prev_task(rq, p);
+
+	p->numa_preferred_nid = nid;
+
+	if (running)
+		p->sched_class->set_curr_task(rq);
+	if (on_rq)
+		enqueue_task(rq, p, 0);
+	task_rq_unlock(rq, p, &flags);
+}
+#endif
+
 /*
  * migration_cpu_stop - this will be executed by a highprio stopper thread
  * and performs thread migration by bumping thread off CPU then
@@ -5119,6 +4882,9 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu)
 DEFINE_PER_CPU(struct sched_domain *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
+DEFINE_PER_CPU(struct sched_domain *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain *, sd_busy);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym);
 
 static void update_top_cache_domain(int cpu)
 {
@@ -5130,11 +4896,18 @@ static void update_top_cache_domain(int cpu)
 	if (sd) {
 		id = cpumask_first(sched_domain_span(sd));
 		size = cpumask_weight(sched_domain_span(sd));
+		rcu_assign_pointer(per_cpu(sd_busy, cpu), sd->parent);
 	}
 
 	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
 	per_cpu(sd_llc_size, cpu) = size;
 	per_cpu(sd_llc_id, cpu) = id;
+
+	sd = lowest_flag_domain(cpu, SD_NUMA);
+	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
+
+	sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
+	rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
 }
 
 /*
@@ -5654,6 +5427,7 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
 					| 0*SD_SHARE_PKG_RESOURCES
 					| 1*SD_SERIALIZE
 					| 0*SD_PREFER_SIBLING
+					| 1*SD_NUMA
 					| sd_local_flags(level)
 					,
 		.last_balance		= jiffies,
@@ -6335,14 +6109,17 @@ void __init sched_init_smp(void)
 
 	sched_init_numa();
 
-	get_online_cpus();
+	/*
+	 * There's no userspace yet to cause hotplug operations; hence all the
+	 * cpu masks are stable and all blatant races in the below code cannot
+	 * happen.
+	 */
 	mutex_lock(&sched_domains_mutex);
 	init_sched_domains(cpu_active_mask);
 	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
 	if (cpumask_empty(non_isolated_cpus))
 		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
 	mutex_unlock(&sched_domains_mutex);
-	put_online_cpus();
 
 	hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE);
 	hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
@@ -6505,6 +6282,7 @@ void __init sched_init(void)
 		rq->online = 0;
 		rq->idle_stamp = 0;
 		rq->avg_idle = 2*sysctl_sched_migration_cost;
+		rq->max_idle_balance_cost = sysctl_sched_migration_cost;
 
 		INIT_LIST_HEAD(&rq->cfs_tasks);
 
@@ -7277,7 +7055,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 
 	runtime_enabled = quota != RUNTIME_INF;
 	runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
-	account_cfs_bandwidth_used(runtime_enabled, runtime_was_enabled);
+	/*
+	 * If we need to toggle cfs_bandwidth_used, off->on must occur
+	 * before making related changes, and on->off must occur afterwards
+	 */
+	if (runtime_enabled && !runtime_was_enabled)
+		cfs_bandwidth_usage_inc();
 	raw_spin_lock_irq(&cfs_b->lock);
 	cfs_b->period = ns_to_ktime(period);
 	cfs_b->quota = quota;
@@ -7303,6 +7086,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 			unthrottle_cfs_rq(cfs_rq);
 		raw_spin_unlock_irq(&rq->lock);
 	}
+	if (runtime_was_enabled && !runtime_enabled)
+		cfs_bandwidth_usage_dec();
 out_unlock:
 	mutex_unlock(&cfs_constraints_mutex);