Merge branch 'sched/core' into core/locking, to prepare the kernel/locking/ file move

Conflicts:
	kernel/Makefile

There are conflicts in kernel/Makefile due to file moving in the
scheduler tree - resolve them.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

23 files changed, 2264 insertions, 804 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index f99d908b5550..a4d1aa8da9bc 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -7,7 +7,7 @@ obj-y     = fork.o exec_domain.o panic.o \
 	    sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o task_work.o \
 	    extable.o params.o posix-timers.o \
-	    kthread.o wait.o sys_ni.o posix-cpu-timers.o mutex.o \
+	    kthread.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o semaphore.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
 	    async.o range.o groups.o lglock.o smpboot.o
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 0c9b862292b2..e8ca97b5c386 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -10,6 +10,7 @@
 #include <linux/mmzone.h>
 #include <linux/kbuild.h>
 #include <linux/page_cgroup.h>
+#include <linux/log2.h>
 
 void foo(void)
 {
@@ -17,5 +18,8 @@ void foo(void)
 	DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
 	DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
 	DEFINE(NR_PCG_FLAGS, __NR_PCG_FLAGS);
+#ifdef CONFIG_SMP
+	DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
+#endif
 	/* End of constants */
 }
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 859c8dfd78a1..e5f3917aa05b 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -120,7 +120,7 @@ void context_tracking_user_enter(void)
  * instead of preempt_schedule() to exit user context if needed before
  * calling the scheduler.
  */
-void __sched notrace preempt_schedule_context(void)
+asmlinkage void __sched notrace preempt_schedule_context(void)
 {
 	enum ctx_state prev_ctx;
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index d7f07a2da5a6..63aa50d7ce1e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -308,6 +308,23 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	}
 	smpboot_park_threads(cpu);
 
+	/*
+	 * 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 explicitly call both.
+	 */
+#ifdef CONFIG_PREEMPT
+	synchronize_sched();
+#endif
+	synchronize_rcu();
+
+	/*
+	 * So now all preempt/rcu users must observe !cpu_active().
+	 */
+
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index e695c0a0bcb5..988573a9a387 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -44,7 +44,7 @@ static inline int cpu_idle_poll(void)
 	rcu_idle_enter();
 	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
-	while (!need_resched())
+	while (!tif_need_resched())
 		cpu_relax();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	rcu_idle_exit();
@@ -92,8 +92,7 @@ static void cpu_idle_loop(void)
 			if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
 				cpu_idle_poll();
 			} else {
-				current_clr_polling();
-				if (!need_resched()) {
+				if (!current_clr_polling_and_test()) {
 					stop_critical_timings();
 					rcu_idle_enter();
 					arch_cpu_idle();
@@ -103,9 +102,16 @@ static void cpu_idle_loop(void)
 				} else {
 					local_irq_enable();
 				}
-				current_set_polling();
+				__current_set_polling();
 			}
 			arch_cpu_idle_exit();
+			/*
+			 * We need to test and propagate the TIF_NEED_RESCHED
+			 * bit here because we might not have send the
+			 * reschedule IPI to idle tasks.
+			 */
+			if (tif_need_resched())
+				set_preempt_need_resched();
 		}
 		tick_nohz_idle_exit();
 		schedule_preempt_disabled();
@@ -129,7 +135,7 @@ void cpu_startup_entry(enum cpuhp_state state)
 	 */
 	boot_init_stack_canary();
 #endif
-	current_set_polling();
+	__current_set_polling();
 	arch_cpu_idle_prepare();
 	cpu_idle_loop();
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 086fe73ad6bd..c93be06dee87 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -817,9 +817,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	mm->pmd_huge_pte = NULL;
 #endif
-#ifdef CONFIG_NUMA_BALANCING
-	mm->first_nid = NUMA_PTE_SCAN_INIT;
-#endif
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
@@ -1313,7 +1310,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(p);
+	sched_fork(clone_flags, p);
 
 	retval = perf_event_init_task(p);
 	if (retval)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8a2c81e86dda..4c06ddfea7cd 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -916,6 +916,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	force_quiescent_state(rsp);  /* Kick them all. */
 }
 
+/*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
 static void print_cpu_stall(struct rcu_state *rsp)
 {
 	int cpu;
@@ -945,7 +951,14 @@ static void print_cpu_stall(struct rcu_state *rsp)
 				     3 * rcu_jiffies_till_stall_check() + 3;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
-	set_need_resched();  /* kick ourselves to get things going. */
+	/*
+	 * Attempt to revive the RCU machinery by forcing a context switch.
+	 *
+	 * A context switch would normally allow the RCU state machine to make
+	 * progress and it could be we're stuck in kernel space without context
+	 * switches for an entirely unreasonable amount of time.
+	 */
+	resched_cpu(smp_processor_id());
 }
 
 static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 54adcf35f495..7b621409cf15 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -12,6 +12,7 @@ CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
 obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
+obj-y += wait.o completion.o
 obj-$(CONFIG_SMP) += cpupri.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
new file mode 100644
index 000000000000..a63f4dc27909
--- /dev/null
+++ b/kernel/sched/completion.c
@@ -0,0 +1,299 @@
+/*
+ * Generic wait-for-completion handler;
+ *
+ * It differs from semaphores in that their default case is the opposite,
+ * wait_for_completion default blocks whereas semaphore default non-block. The
+ * interface also makes it easy to 'complete' multiple waiting threads,
+ * something which isn't entirely natural for semaphores.
+ *
+ * But more importantly, the primitive documents the usage. Semaphores would
+ * typically be used for exclusion which gives rise to priority inversion.
+ * Waiting for completion is a typically sync point, but not an exclusion point.
+ */
+
+#include <linux/sched.h>
+#include <linux/completion.h>
+
+/**
+ * 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_locked(&x->wait, TASK_NORMAL, 1);
+	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_locked(&x->wait, TASK_NORMAL, 0);
+	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);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5ac63c9a995a..aa066f306be2 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;
 
-		if (delta > max)
+		update_avg(&rq->avg_idle, delta);
+
+		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 +4882,7 @@ 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);
 
 static void update_top_cache_domain(int cpu)
 {
@@ -5135,6 +4899,9 @@ static void update_top_cache_domain(int cpu)
 	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);
 }
 
 /*
@@ -5654,6 +5421,7 @@ 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 +6103,17 @@ 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 +6276,7 @@ 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 +7049,12 @@ 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 +7080,8 @@ 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);
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 196559994f7c..5c34d1817e8f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -15,6 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
+#include <linux/mempolicy.h>
 
 #include "sched.h"
 
@@ -137,6 +138,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	SEQ_printf(m, " %d", cpu_to_node(task_cpu(p)));
+#endif
 #ifdef CONFIG_CGROUP_SCHED
 	SEQ_printf(m, " %s", task_group_path(task_group(p)));
 #endif
@@ -159,7 +163,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	read_lock_irqsave(&tasklist_lock, flags);
 
 	do_each_thread(g, p) {
-		if (!p->on_rq || task_cpu(p) != rq_cpu)
+		if (task_cpu(p) != rq_cpu)
 			continue;
 
 		print_task(m, rq, p);
@@ -225,6 +229,14 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			atomic_read(&cfs_rq->tg->runnable_avg));
 #endif
 #endif
+#ifdef CONFIG_CFS_BANDWIDTH
+	SEQ_printf(m, "  .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
+			cfs_rq->tg->cfs_bandwidth.timer_active);
+	SEQ_printf(m, "  .%-30s: %d\n", "throttled",
+			cfs_rq->throttled);
+	SEQ_printf(m, "  .%-30s: %d\n", "throttle_count",
+			cfs_rq->throttle_count);
+#endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	print_cfs_group_stats(m, cpu, cfs_rq->tg);
@@ -345,7 +357,7 @@ static void sched_debug_header(struct seq_file *m)
 	cpu_clk = local_clock();
 	local_irq_restore(flags);
 
-	SEQ_printf(m, "Sched Debug Version: v0.10, %s %.*s\n",
+	SEQ_printf(m, "Sched Debug Version: v0.11, %s %.*s\n",
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
@@ -488,6 +500,56 @@ static int __init init_sched_debug_procfs(void)
 
 __initcall(init_sched_debug_procfs);
 
+#define __P(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
+#define P(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
+#define __PN(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
+#define PN(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+
+
+static void sched_show_numa(struct task_struct *p, struct seq_file *m)
+{
+#ifdef CONFIG_NUMA_BALANCING
+	struct mempolicy *pol;
+	int node, i;
+
+	if (p->mm)
+		P(mm->numa_scan_seq);
+
+	task_lock(p);
+	pol = p->mempolicy;
+	if (pol && !(pol->flags & MPOL_F_MORON))
+		pol = NULL;
+	mpol_get(pol);
+	task_unlock(p);
+
+	SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0));
+
+	for_each_online_node(node) {
+		for (i = 0; i < 2; i++) {
+			unsigned long nr_faults = -1;
+			int cpu_current, home_node;
+
+			if (p->numa_faults)
+				nr_faults = p->numa_faults[2*node + i];
+
+			cpu_current = !i ? (task_node(p) == node) :
+				(pol && node_isset(node, pol->v.nodes));
+
+			home_node = (p->numa_preferred_nid == node);
+
+			SEQ_printf(m, "numa_faults, %d, %d, %d, %d, %ld\n",
+				i, node, cpu_current, home_node, nr_faults);
+		}
+	}
+
+	mpol_put(pol);
+#endif
+}
+
 void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 {
 	unsigned long nr_switches;
@@ -591,6 +653,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 		SEQ_printf(m, "%-45s:%21Ld\n",
 			   "clock-delta", (long long)(t1-t0));
 	}
+
+	sched_show_numa(p, m);
 }
 
 void proc_sched_set_task(struct task_struct *p)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7c70201fbc61..41c02b6b090e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -681,6 +681,8 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 #ifdef CONFIG_SMP
+static unsigned long task_h_load(struct task_struct *p);
+
 static inline void __update_task_entity_contrib(struct sched_entity *se);
 
 /* Give new task start runnable values to heavy its load in infant time */
@@ -818,11 +820,12 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 #ifdef CONFIG_NUMA_BALANCING
 /*
- * numa task sample period in ms
+ * Approximate time to scan a full NUMA task in ms. The task scan period is
+ * calculated based on the tasks virtual memory size and
+ * numa_balancing_scan_size.
  */
-unsigned int sysctl_numa_balancing_scan_period_min = 100;
-unsigned int sysctl_numa_balancing_scan_period_max = 100*50;
-unsigned int sysctl_numa_balancing_scan_period_reset = 100*600;
+unsigned int sysctl_numa_balancing_scan_period_min = 1000;
+unsigned int sysctl_numa_balancing_scan_period_max = 60000;
 
 /* Portion of address space to scan in MB */
 unsigned int sysctl_numa_balancing_scan_size = 256;
@@ -830,41 +833,810 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
 /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
 unsigned int sysctl_numa_balancing_scan_delay = 1000;
 
-static void task_numa_placement(struct task_struct *p)
+/*
+ * After skipping a page migration on a shared page, skip N more numa page
+ * migrations unconditionally. This reduces the number of NUMA migrations
+ * in shared memory workloads, and has the effect of pulling tasks towards
+ * where their memory lives, over pulling the memory towards the task.
+ */
+unsigned int sysctl_numa_balancing_migrate_deferred = 16;
+
+static unsigned int task_nr_scan_windows(struct task_struct *p)
+{
+	unsigned long rss = 0;
+	unsigned long nr_scan_pages;
+
+	/*
+	 * Calculations based on RSS as non-present and empty pages are skipped
+	 * by the PTE scanner and NUMA hinting faults should be trapped based
+	 * on resident pages
+	 */
+	nr_scan_pages = sysctl_numa_balancing_scan_size << (20 - PAGE_SHIFT);
+	rss = get_mm_rss(p->mm);
+	if (!rss)
+		rss = nr_scan_pages;
+
+	rss = round_up(rss, nr_scan_pages);
+	return rss / nr_scan_pages;
+}
+
+/* For sanitys sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */
+#define MAX_SCAN_WINDOW 2560
+
+static unsigned int task_scan_min(struct task_struct *p)
+{
+	unsigned int scan, floor;
+	unsigned int windows = 1;
+
+	if (sysctl_numa_balancing_scan_size < MAX_SCAN_WINDOW)
+		windows = MAX_SCAN_WINDOW / sysctl_numa_balancing_scan_size;
+	floor = 1000 / windows;
+
+	scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p);
+	return max_t(unsigned int, floor, scan);
+}
+
+static unsigned int task_scan_max(struct task_struct *p)
+{
+	unsigned int smin = task_scan_min(p);
+	unsigned int smax;
+
+	/* Watch for min being lower than max due to floor calculations */
+	smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p);
+	return max(smin, smax);
+}
+
+/*
+ * Once a preferred node is selected the scheduler balancer will prefer moving
+ * a task to that node for sysctl_numa_balancing_settle_count number of PTE
+ * scans. This will give the process the chance to accumulate more faults on
+ * the preferred node but still allow the scheduler to move the task again if
+ * the nodes CPUs are overloaded.
+ */
+unsigned int sysctl_numa_balancing_settle_count __read_mostly = 4;
+
+static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
+{
+	rq->nr_numa_running += (p->numa_preferred_nid != -1);
+	rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p));
+}
+
+static void account_numa_dequeue(struct rq *rq, struct task_struct *p)
+{
+	rq->nr_numa_running -= (p->numa_preferred_nid != -1);
+	rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p));
+}
+
+struct numa_group {
+	atomic_t refcount;
+
+	spinlock_t lock; /* nr_tasks, tasks */
+	int nr_tasks;
+	pid_t gid;
+	struct list_head task_list;
+
+	struct rcu_head rcu;
+	unsigned long total_faults;
+	unsigned long faults[0];
+};
+
+pid_t task_numa_group_id(struct task_struct *p)
+{
+	return p->numa_group ? p->numa_group->gid : 0;
+}
+
+static inline int task_faults_idx(int nid, int priv)
+{
+	return 2 * nid + priv;
+}
+
+static inline unsigned long task_faults(struct task_struct *p, int nid)
+{
+	if (!p->numa_faults)
+		return 0;
+
+	return p->numa_faults[task_faults_idx(nid, 0)] +
+		p->numa_faults[task_faults_idx(nid, 1)];
+}
+
+static inline unsigned long group_faults(struct task_struct *p, int nid)
+{
+	if (!p->numa_group)
+		return 0;
+
+	return p->numa_group->faults[2*nid] + p->numa_group->faults[2*nid+1];
+}
+
+/*
+ * These return the fraction of accesses done by a particular task, or
+ * task group, on a particular numa node.  The group weight is given a
+ * larger multiplier, in order to group tasks together that are almost
+ * evenly spread out between numa nodes.
+ */
+static inline unsigned long task_weight(struct task_struct *p, int nid)
+{
+	unsigned long total_faults;
+
+	if (!p->numa_faults)
+		return 0;
+
+	total_faults = p->total_numa_faults;
+
+	if (!total_faults)
+		return 0;
+
+	return 1000 * task_faults(p, nid) / total_faults;
+}
+
+static inline unsigned long group_weight(struct task_struct *p, int nid)
 {
-	int seq;
+	if (!p->numa_group || !p->numa_group->total_faults)
+		return 0;
+
+	return 1000 * group_faults(p, nid) / p->numa_group->total_faults;
+}
+
+static unsigned long weighted_cpuload(const int cpu);
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static unsigned long power_of(int cpu);
+static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
+
+/* Cached statistics for all CPUs within a node */
+struct numa_stats {
+	unsigned long nr_running;
+	unsigned long load;
+
+	/* Total compute capacity of CPUs on a node */
+	unsigned long power;
+
+	/* Approximate capacity in terms of runnable tasks on a node */
+	unsigned long capacity;
+	int has_capacity;
+};
+
+/*
+ * XXX borrowed from update_sg_lb_stats
+ */
+static void update_numa_stats(struct numa_stats *ns, int nid)
+{
+	int cpu;
+
+	memset(ns, 0, sizeof(*ns));
+	for_each_cpu(cpu, cpumask_of_node(nid)) {
+		struct rq *rq = cpu_rq(cpu);
+
+		ns->nr_running += rq->nr_running;
+		ns->load += weighted_cpuload(cpu);
+		ns->power += power_of(cpu);
+	}
+
+	ns->load = (ns->load * SCHED_POWER_SCALE) / ns->power;
+	ns->capacity = DIV_ROUND_CLOSEST(ns->power, SCHED_POWER_SCALE);
+	ns->has_capacity = (ns->nr_running < ns->capacity);
+}
+
+struct task_numa_env {
+	struct task_struct *p;
+
+	int src_cpu, src_nid;
+	int dst_cpu, dst_nid;
+
+	struct numa_stats src_stats, dst_stats;
+
+	int imbalance_pct, idx;
+
+	struct task_struct *best_task;
+	long best_imp;
+	int best_cpu;
+};
+
+static void task_numa_assign(struct task_numa_env *env,
+			     struct task_struct *p, long imp)
+{
+	if (env->best_task)
+		put_task_struct(env->best_task);
+	if (p)
+		get_task_struct(p);
+
+	env->best_task = p;
+	env->best_imp = imp;
+	env->best_cpu = env->dst_cpu;
+}
+
+/*
+ * This checks if the overall compute and NUMA accesses of the system would
+ * be improved if the source tasks was migrated to the target dst_cpu taking
+ * into account that it might be best if task running on the dst_cpu should
+ * be exchanged with the source task
+ */
+static void task_numa_compare(struct task_numa_env *env,
+			      long taskimp, long groupimp)
+{
+	struct rq *src_rq = cpu_rq(env->src_cpu);
+	struct rq *dst_rq = cpu_rq(env->dst_cpu);
+	struct task_struct *cur;
+	long dst_load, src_load;
+	long load;
+	long imp = (groupimp > 0) ? groupimp : taskimp;
+
+	rcu_read_lock();
+	cur = ACCESS_ONCE(dst_rq->curr);
+	if (cur->pid == 0) /* idle */
+		cur = NULL;
+
+	/*
+	 * "imp" is the fault differential for the source task between the
+	 * source and destination node. Calculate the total differential for
+	 * the source task and potential destination task. The more negative
+	 * the value is, the more rmeote accesses that would be expected to
+	 * be incurred if the tasks were swapped.
+	 */
+	if (cur) {
+		/* Skip this swap candidate if cannot move to the source cpu */
+		if (!cpumask_test_cpu(env->src_cpu, tsk_cpus_allowed(cur)))
+			goto unlock;
+
+		/*
+		 * If dst and source tasks are in the same NUMA group, or not
+		 * in any group then look only at task weights.
+		 */
+		if (cur->numa_group == env->p->numa_group) {
+			imp = taskimp + task_weight(cur, env->src_nid) -
+			      task_weight(cur, env->dst_nid);
+			/*
+			 * Add some hysteresis to prevent swapping the
+			 * tasks within a group over tiny differences.
+			 */
+			if (cur->numa_group)
+				imp -= imp/16;
+		} else {
+			/*
+			 * Compare the group weights. If a task is all by
+			 * itself (not part of a group), use the task weight
+			 * instead.
+			 */
+			if (env->p->numa_group)
+				imp = groupimp;
+			else
+				imp = taskimp;
+
+			if (cur->numa_group)
+				imp += group_weight(cur, env->src_nid) -
+				       group_weight(cur, env->dst_nid);
+			else
+				imp += task_weight(cur, env->src_nid) -
+				       task_weight(cur, env->dst_nid);
+		}
+	}
+
+	if (imp < env->best_imp)
+		goto unlock;
+
+	if (!cur) {
+		/* Is there capacity at our destination? */
+		if (env->src_stats.has_capacity &&
+		    !env->dst_stats.has_capacity)
+			goto unlock;
+
+		goto balance;
+	}
+
+	/* Balance doesn't matter much if we're running a task per cpu */
+	if (src_rq->nr_running == 1 && dst_rq->nr_running == 1)
+		goto assign;
+
+	/*
+	 * In the overloaded case, try and keep the load balanced.
+	 */
+balance:
+	dst_load = env->dst_stats.load;
+	src_load = env->src_stats.load;
+
+	/* XXX missing power terms */
+	load = task_h_load(env->p);
+	dst_load += load;
+	src_load -= load;
+
+	if (cur) {
+		load = task_h_load(cur);
+		dst_load -= load;
+		src_load += load;
+	}
+
+	/* make src_load the smaller */
+	if (dst_load < src_load)
+		swap(dst_load, src_load);
+
+	if (src_load * env->imbalance_pct < dst_load * 100)
+		goto unlock;
+
+assign:
+	task_numa_assign(env, cur, imp);
+unlock:
+	rcu_read_unlock();
+}
+
+static void task_numa_find_cpu(struct task_numa_env *env,
+				long taskimp, long groupimp)
+{
+	int cpu;
+
+	for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
+		/* Skip this CPU if the source task cannot migrate */
+		if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(env->p)))
+			continue;
+
+		env->dst_cpu = cpu;
+		task_numa_compare(env, taskimp, groupimp);
+	}
+}
+
+static int task_numa_migrate(struct task_struct *p)
+{
+	struct task_numa_env env = {
+		.p = p,
+
+		.src_cpu = task_cpu(p),
+		.src_nid = task_node(p),
+
+		.imbalance_pct = 112,
+
+		.best_task = NULL,
+		.best_imp = 0,
+		.best_cpu = -1
+	};
+	struct sched_domain *sd;
+	unsigned long taskweight, groupweight;
+	int nid, ret;
+	long taskimp, groupimp;
+
+	/*
+	 * Pick the lowest SD_NUMA domain, as that would have the smallest
+	 * imbalance and would be the first to start moving tasks about.
+	 *
+	 * And we want to avoid any moving of tasks about, as that would create
+	 * random movement of tasks -- counter the numa conditions we're trying
+	 * to satisfy here.
+	 */
+	rcu_read_lock();
+	sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu));
+	env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2;
+	rcu_read_unlock();
+
+	taskweight = task_weight(p, env.src_nid);
+	groupweight = group_weight(p, env.src_nid);
+	update_numa_stats(&env.src_stats, env.src_nid);
+	env.dst_nid = p->numa_preferred_nid;
+	taskimp = task_weight(p, env.dst_nid) - taskweight;
+	groupimp = group_weight(p, env.dst_nid) - groupweight;
+	update_numa_stats(&env.dst_stats, env.dst_nid);
+
+	/* If the preferred nid has capacity, try to use it. */
+	if (env.dst_stats.has_capacity)
+		task_numa_find_cpu(&env, taskimp, groupimp);
+
+	/* No space available on the preferred nid. Look elsewhere. */
+	if (env.best_cpu == -1) {
+		for_each_online_node(nid) {
+			if (nid == env.src_nid || nid == p->numa_preferred_nid)
+				continue;
+
+			/* Only consider nodes where both task and groups benefit */
+			taskimp = task_weight(p, nid) - taskweight;
+			groupimp = group_weight(p, nid) - groupweight;
+			if (taskimp < 0 && groupimp < 0)
+				continue;
+
+			env.dst_nid = nid;
+			update_numa_stats(&env.dst_stats, env.dst_nid);
+			task_numa_find_cpu(&env, taskimp, groupimp);
+		}
+	}
+
+	/* No better CPU than the current one was found. */
+	if (env.best_cpu == -1)
+		return -EAGAIN;
+
+	sched_setnuma(p, env.dst_nid);
+
+	/*
+	 * Reset the scan period if the task is being rescheduled on an
+	 * alternative node to recheck if the tasks is now properly placed.
+	 */
+	p->numa_scan_period = task_scan_min(p);
+
+	if (env.best_task == NULL) {
+		int ret = migrate_task_to(p, env.best_cpu);
+		return ret;
+	}
+
+	ret = migrate_swap(p, env.best_task);
+	put_task_struct(env.best_task);
+	return ret;
+}
+
+/* Attempt to migrate a task to a CPU on the preferred node. */
+static void numa_migrate_preferred(struct task_struct *p)
+{
+	/* This task has no NUMA fault statistics yet */
+	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
+		return;
+
+	/* Periodically retry migrating the task to the preferred node */
+	p->numa_migrate_retry = jiffies + HZ;
+
+	/* Success if task is already running on preferred CPU */
+	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
+		return;
+
+	/* Otherwise, try migrate to a CPU on the preferred node */
+	task_numa_migrate(p);
+}
+
+/*
+ * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
+ * increments. The more local the fault statistics are, the higher the scan
+ * period will be for the next scan window. If local/remote ratio is below
+ * NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) the
+ * scan period will decrease
+ */
+#define NUMA_PERIOD_SLOTS 10
+#define NUMA_PERIOD_THRESHOLD 3
+
+/*
+ * Increase the scan period (slow down scanning) if the majority of
+ * our memory is already on our local node, or if the majority of
+ * the page accesses are shared with other processes.
+ * Otherwise, decrease the scan period.
+ */
+static void update_task_scan_period(struct task_struct *p,
+			unsigned long shared, unsigned long private)
+{
+	unsigned int period_slot;
+	int ratio;
+	int diff;
+
+	unsigned long remote = p->numa_faults_locality[0];
+	unsigned long local = p->numa_faults_locality[1];
+
+	/*
+	 * If there were no record hinting faults then either the task is
+	 * completely idle or all activity is areas that are not of interest
+	 * to automatic numa balancing. Scan slower
+	 */
+	if (local + shared == 0) {
+		p->numa_scan_period = min(p->numa_scan_period_max,
+			p->numa_scan_period << 1);
+
+		p->mm->numa_next_scan = jiffies +
+			msecs_to_jiffies(p->numa_scan_period);
 
-	if (!p->mm)	/* for example, ksmd faulting in a user's mm */
 		return;
+	}
+
+	/*
+	 * Prepare to scale scan period relative to the current period.
+	 *	 == NUMA_PERIOD_THRESHOLD scan period stays the same
+	 *       <  NUMA_PERIOD_THRESHOLD scan period decreases (scan faster)
+	 *	 >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower)
+	 */
+	period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS);
+	ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote);
+	if (ratio >= NUMA_PERIOD_THRESHOLD) {
+		int slot = ratio - NUMA_PERIOD_THRESHOLD;
+		if (!slot)
+			slot = 1;
+		diff = slot * period_slot;
+	} else {
+		diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
+
+		/*
+		 * Scale scan rate increases based on sharing. There is an
+		 * inverse relationship between the degree of sharing and
+		 * the adjustment made to the scanning period. Broadly
+		 * speaking the intent is that there is little point
+		 * scanning faster if shared accesses dominate as it may
+		 * simply bounce migrations uselessly
+		 */
+		period_slot = DIV_ROUND_UP(diff, NUMA_PERIOD_SLOTS);
+		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
+		diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
+	}
+
+	p->numa_scan_period = clamp(p->numa_scan_period + diff,
+			task_scan_min(p), task_scan_max(p));
+	memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
+}
+
+static void task_numa_placement(struct task_struct *p)
+{
+	int seq, nid, max_nid = -1, max_group_nid = -1;
+	unsigned long max_faults = 0, max_group_faults = 0;
+	unsigned long fault_types[2] = { 0, 0 };
+	spinlock_t *group_lock = NULL;
+
 	seq = ACCESS_ONCE(p->mm->numa_scan_seq);
 	if (p->numa_scan_seq == seq)
 		return;
 	p->numa_scan_seq = seq;
+	p->numa_scan_period_max = task_scan_max(p);
+
+	/* If the task is part of a group prevent parallel updates to group stats */
+	if (p->numa_group) {
+		group_lock = &p->numa_group->lock;
+		spin_lock(group_lock);
+	}
+
+	/* Find the node with the highest number of faults */
+	for_each_online_node(nid) {
+		unsigned long faults = 0, group_faults = 0;
+		int priv, i;
+
+		for (priv = 0; priv < 2; priv++) {
+			long diff;
+
+			i = task_faults_idx(nid, priv);
+			diff = -p->numa_faults[i];
+
+			/* Decay existing window, copy faults since last scan */
+			p->numa_faults[i] >>= 1;
+			p->numa_faults[i] += p->numa_faults_buffer[i];
+			fault_types[priv] += p->numa_faults_buffer[i];
+			p->numa_faults_buffer[i] = 0;
+
+			faults += p->numa_faults[i];
+			diff += p->numa_faults[i];
+			p->total_numa_faults += diff;
+			if (p->numa_group) {
+				/* safe because we can only change our own group */
+				p->numa_group->faults[i] += diff;
+				p->numa_group->total_faults += diff;
+				group_faults += p->numa_group->faults[i];
+			}
+		}
+
+		if (faults > max_faults) {
+			max_faults = faults;
+			max_nid = nid;
+		}
+
+		if (group_faults > max_group_faults) {
+			max_group_faults = group_faults;
+			max_group_nid = nid;
+		}
+	}
+
+	update_task_scan_period(p, fault_types[0], fault_types[1]);
+
+	if (p->numa_group) {
+		/*
+		 * If the preferred task and group nids are different,
+		 * iterate over the nodes again to find the best place.
+		 */
+		if (max_nid != max_group_nid) {
+			unsigned long weight, max_weight = 0;
+
+			for_each_online_node(nid) {
+				weight = task_weight(p, nid) + group_weight(p, nid);
+				if (weight > max_weight) {
+					max_weight = weight;
+					max_nid = nid;
+				}
+			}
+		}
+
+		spin_unlock(group_lock);
+	}
 
-	/* FIXME: Scheduling placement policy hints go here */
+	/* Preferred node as the node with the most faults */
+	if (max_faults && max_nid != p->numa_preferred_nid) {
+		/* Update the preferred nid and migrate task if possible */
+		sched_setnuma(p, max_nid);
+		numa_migrate_preferred(p);
+	}
+}
+
+static inline int get_numa_group(struct numa_group *grp)
+{
+	return atomic_inc_not_zero(&grp->refcount);
+}
+
+static inline void put_numa_group(struct numa_group *grp)
+{
+	if (atomic_dec_and_test(&grp->refcount))
+		kfree_rcu(grp, rcu);
+}
+
+static void task_numa_group(struct task_struct *p, int cpupid, int flags,
+			int *priv)
+{
+	struct numa_group *grp, *my_grp;
+	struct task_struct *tsk;
+	bool join = false;
+	int cpu = cpupid_to_cpu(cpupid);
+	int i;
+
+	if (unlikely(!p->numa_group)) {
+		unsigned int size = sizeof(struct numa_group) +
+				    2*nr_node_ids*sizeof(unsigned long);
+
+		grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
+		if (!grp)
+			return;
+
+		atomic_set(&grp->refcount, 1);
+		spin_lock_init(&grp->lock);
+		INIT_LIST_HEAD(&grp->task_list);
+		grp->gid = p->pid;
+
+		for (i = 0; i < 2*nr_node_ids; i++)
+			grp->faults[i] = p->numa_faults[i];
+
+		grp->total_faults = p->total_numa_faults;
+
+		list_add(&p->numa_entry, &grp->task_list);
+		grp->nr_tasks++;
+		rcu_assign_pointer(p->numa_group, grp);
+	}
+
+	rcu_read_lock();
+	tsk = ACCESS_ONCE(cpu_rq(cpu)->curr);
+
+	if (!cpupid_match_pid(tsk, cpupid))
+		goto no_join;
+
+	grp = rcu_dereference(tsk->numa_group);
+	if (!grp)
+		goto no_join;
+
+	my_grp = p->numa_group;
+	if (grp == my_grp)
+		goto no_join;
+
+	/*
+	 * Only join the other group if its bigger; if we're the bigger group,
+	 * the other task will join us.
+	 */
+	if (my_grp->nr_tasks > grp->nr_tasks)
+		goto no_join;
+
+	/*
+	 * Tie-break on the grp address.
+	 */
+	if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp)
+		goto no_join;
+
+	/* Always join threads in the same process. */
+	if (tsk->mm == current->mm)
+		join = true;
+
+	/* Simple filter to avoid false positives due to PID collisions */
+	if (flags & TNF_SHARED)
+		join = true;
+
+	/* Update priv based on whether false sharing was detected */
+	*priv = !join;
+
+	if (join && !get_numa_group(grp))
+		goto no_join;
+
+	rcu_read_unlock();
+
+	if (!join)
+		return;
+
+	double_lock(&my_grp->lock, &grp->lock);
+
+	for (i = 0; i < 2*nr_node_ids; i++) {
+		my_grp->faults[i] -= p->numa_faults[i];
+		grp->faults[i] += p->numa_faults[i];
+	}
+	my_grp->total_faults -= p->total_numa_faults;
+	grp->total_faults += p->total_numa_faults;
+
+	list_move(&p->numa_entry, &grp->task_list);
+	my_grp->nr_tasks--;
+	grp->nr_tasks++;
+
+	spin_unlock(&my_grp->lock);
+	spin_unlock(&grp->lock);
+
+	rcu_assign_pointer(p->numa_group, grp);
+
+	put_numa_group(my_grp);
+	return;
+
+no_join:
+	rcu_read_unlock();
+	return;
+}
+
+void task_numa_free(struct task_struct *p)
+{
+	struct numa_group *grp = p->numa_group;
+	int i;
+	void *numa_faults = p->numa_faults;
+
+	if (grp) {
+		spin_lock(&grp->lock);
+		for (i = 0; i < 2*nr_node_ids; i++)
+			grp->faults[i] -= p->numa_faults[i];
+		grp->total_faults -= p->total_numa_faults;
+
+		list_del(&p->numa_entry);
+		grp->nr_tasks--;
+		spin_unlock(&grp->lock);
+		rcu_assign_pointer(p->numa_group, NULL);
+		put_numa_group(grp);
+	}
+
+	p->numa_faults = NULL;
+	p->numa_faults_buffer = NULL;
+	kfree(numa_faults);
 }
 
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
-void task_numa_fault(int node, int pages, bool migrated)
+void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 {
 	struct task_struct *p = current;
+	bool migrated = flags & TNF_MIGRATED;
+	int priv;
 
 	if (!numabalancing_enabled)
 		return;
 
-	/* FIXME: Allocate task-specific structure for placement policy here */
+	/* for example, ksmd faulting in a user's mm */
+	if (!p->mm)
+		return;
+
+	/* Do not worry about placement if exiting */
+	if (p->state == TASK_DEAD)
+		return;
+
+	/* Allocate buffer to track faults on a per-node basis */
+	if (unlikely(!p->numa_faults)) {
+		int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
+
+		/* numa_faults and numa_faults_buffer share the allocation */
+		p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
+		if (!p->numa_faults)
+			return;
+
+		BUG_ON(p->numa_faults_buffer);
+		p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
+		p->total_numa_faults = 0;
+		memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
+	}
 
 	/*
-	 * If pages are properly placed (did not migrate) then scan slower.
-	 * This is reset periodically in case of phase changes
+	 * First accesses are treated as private, otherwise consider accesses
+	 * to be private if the accessing pid has not changed
 	 */
-        if (!migrated)
-		p->numa_scan_period = min(sysctl_numa_balancing_scan_period_max,
-			p->numa_scan_period + jiffies_to_msecs(10));
+	if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) {
+		priv = 1;
+	} else {
+		priv = cpupid_match_pid(p, last_cpupid);
+		if (!priv && !(flags & TNF_NO_GROUP))
+			task_numa_group(p, last_cpupid, flags, &priv);
+	}
 
 	task_numa_placement(p);
+
+	/*
+	 * Retry task to preferred node migration periodically, in case it
+	 * case it previously failed, or the scheduler moved us.
+	 */
+	if (time_after(jiffies, p->numa_migrate_retry))
+		numa_migrate_preferred(p);
+
+	if (migrated)
+		p->numa_pages_migrated += pages;
+
+	p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
+	p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
 }
 
 static void reset_ptenuma_scan(struct task_struct *p)
@@ -884,6 +1656,7 @@ void task_numa_work(struct callback_head *work)
 	struct mm_struct *mm = p->mm;
 	struct vm_area_struct *vma;
 	unsigned long start, end;
+	unsigned long nr_pte_updates = 0;
 	long pages;
 
 	WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
@@ -900,35 +1673,9 @@ void task_numa_work(struct callback_head *work)
 	if (p->flags & PF_EXITING)
 		return;
 
-	/*
-	 * We do not care about task placement until a task runs on a node
-	 * other than the first one used by the address space. This is
-	 * largely because migrations are driven by what CPU the task
-	 * is running on. If it's never scheduled on another node, it'll
-	 * not migrate so why bother trapping the fault.
-	 */
-	if (mm->first_nid == NUMA_PTE_SCAN_INIT)
-		mm->first_nid = numa_node_id();
-	if (mm->first_nid != NUMA_PTE_SCAN_ACTIVE) {
-		/* Are we running on a new node yet? */
-		if (numa_node_id() == mm->first_nid &&
-		    !sched_feat_numa(NUMA_FORCE))
-			return;
-
-		mm->first_nid = NUMA_PTE_SCAN_ACTIVE;
-	}
-
-	/*
-	 * Reset the scan period if enough time has gone by. Objective is that
-	 * scanning will be reduced if pages are properly placed. As tasks
-	 * can enter different phases this needs to be re-examined. Lacking
-	 * proper tracking of reference behaviour, this blunt hammer is used.
-	 */
-	migrate = mm->numa_next_reset;
-	if (time_after(now, migrate)) {
-		p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
-		next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);
-		xchg(&mm->numa_next_reset, next_scan);
+	if (!mm->numa_next_scan) {
+		mm->numa_next_scan = now +
+			msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
 	}
 
 	/*
@@ -938,20 +1685,20 @@ void task_numa_work(struct callback_head *work)
 	if (time_before(now, migrate))
 		return;
 
-	if (p->numa_scan_period == 0)
-		p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+	if (p->numa_scan_period == 0) {
+		p->numa_scan_period_max = task_scan_max(p);
+		p->numa_scan_period = task_scan_min(p);
+	}
 
 	next_scan = now + msecs_to_jiffies(p->numa_scan_period);
 	if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
 		return;
 
 	/*
-	 * Do not set pte_numa if the current running node is rate-limited.
-	 * This loses statistics on the fault but if we are unwilling to
-	 * migrate to this node, it is less likely we can do useful work
+	 * Delay this task enough that another task of this mm will likely win
+	 * the next time around.
 	 */
-	if (migrate_ratelimited(numa_node_id()))
-		return;
+	p->node_stamp += 2 * TICK_NSEC;
 
 	start = mm->numa_scan_offset;
 	pages = sysctl_numa_balancing_scan_size;
@@ -967,18 +1714,32 @@ void task_numa_work(struct callback_head *work)
 		vma = mm->mmap;
 	}
 	for (; vma; vma = vma->vm_next) {
-		if (!vma_migratable(vma))
+		if (!vma_migratable(vma) || !vma_policy_mof(p, vma))
 			continue;
 
-		/* Skip small VMAs. They are not likely to be of relevance */
-		if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
+		/*
+		 * Shared library pages mapped by multiple processes are not
+		 * migrated as it is expected they are cache replicated. Avoid
+		 * hinting faults in read-only file-backed mappings or the vdso
+		 * as migrating the pages will be of marginal benefit.
+		 */
+		if (!vma->vm_mm ||
+		    (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
 			continue;
 
 		do {
 			start = max(start, vma->vm_start);
 			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
 			end = min(end, vma->vm_end);
-			pages -= change_prot_numa(vma, start, end);
+			nr_pte_updates += change_prot_numa(vma, start, end);
+
+			/*
+			 * Scan sysctl_numa_balancing_scan_size but ensure that
+			 * at least one PTE is updated so that unused virtual
+			 * address space is quickly skipped.
+			 */
+			if (nr_pte_updates)
+				pages -= (end - start) >> PAGE_SHIFT;
 
 			start = end;
 			if (pages <= 0)
@@ -988,10 +1749,10 @@ void task_numa_work(struct callback_head *work)
 
 out:
 	/*
-	 * It is possible to reach the end of the VMA list but the last few VMAs are
-	 * not guaranteed to the vma_migratable. If they are not, we would find the
-	 * !migratable VMA on the next scan but not reset the scanner to the start
-	 * so check it now.
+	 * It is possible to reach the end of the VMA list but the last few
+	 * VMAs are not guaranteed to the vma_migratable. If they are not, we
+	 * would find the !migratable VMA on the next scan but not reset the
+	 * scanner to the start so check it now.
 	 */
 	if (vma)
 		mm->numa_scan_offset = start;
@@ -1025,8 +1786,8 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
 
 	if (now - curr->node_stamp > period) {
 		if (!curr->node_stamp)
-			curr->numa_scan_period = sysctl_numa_balancing_scan_period_min;
-		curr->node_stamp = now;
+			curr->numa_scan_period = task_scan_min(curr);
+		curr->node_stamp += period;
 
 		if (!time_before(jiffies, curr->mm->numa_next_scan)) {
 			init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */
@@ -1038,6 +1799,14 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
 static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 {
 }
+
+static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
+{
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 static void
@@ -1047,8 +1816,12 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	if (!parent_entity(se))
 		update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
 #ifdef CONFIG_SMP
-	if (entity_is_task(se))
-		list_add(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
+	if (entity_is_task(se)) {
+		struct rq *rq = rq_of(cfs_rq);
+
+		account_numa_enqueue(rq, task_of(se));
+		list_add(&se->group_node, &rq->cfs_tasks);
+	}
 #endif
 	cfs_rq->nr_running++;
 }
@@ -1059,8 +1832,10 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	update_load_sub(&cfs_rq->load, se->load.weight);
 	if (!parent_entity(se))
 		update_load_sub(&rq_of(cfs_rq)->load, se->load.weight);
-	if (entity_is_task(se))
+	if (entity_is_task(se)) {
+		account_numa_dequeue(rq_of(cfs_rq), task_of(se));
 		list_del_init(&se->group_node);
+	}
 	cfs_rq->nr_running--;
 }
 
@@ -2070,13 +2845,14 @@ static inline bool cfs_bandwidth_used(void)
 	return static_key_false(&__cfs_bandwidth_used);
 }
 
-void account_cfs_bandwidth_used(int enabled, int was_enabled)
+void cfs_bandwidth_usage_inc(void)
 {
-	/* only need to count groups transitioning between enabled/!enabled */
-	if (enabled && !was_enabled)
-		static_key_slow_inc(&__cfs_bandwidth_used);
-	else if (!enabled && was_enabled)
-		static_key_slow_dec(&__cfs_bandwidth_used);
+	static_key_slow_inc(&__cfs_bandwidth_used);
+}
+
+void cfs_bandwidth_usage_dec(void)
+{
+	static_key_slow_dec(&__cfs_bandwidth_used);
 }
 #else /* HAVE_JUMP_LABEL */
 static bool cfs_bandwidth_used(void)
@@ -2084,7 +2860,8 @@ static bool cfs_bandwidth_used(void)
 	return true;
 }
 
-void account_cfs_bandwidth_used(int enabled, int was_enabled) {}
+void cfs_bandwidth_usage_inc(void) {}
+void cfs_bandwidth_usage_dec(void) {}
 #endif /* HAVE_JUMP_LABEL */
 
 /*
@@ -2335,6 +3112,8 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->throttled_clock = rq_clock(rq);
 	raw_spin_lock(&cfs_b->lock);
 	list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+	if (!cfs_b->timer_active)
+		__start_cfs_bandwidth(cfs_b);
 	raw_spin_unlock(&cfs_b->lock);
 }
 
@@ -2448,6 +3227,13 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	if (idle)
 		goto out_unlock;
 
+	/*
+	 * if we have relooped after returning idle once, we need to update our
+	 * status as actually running, so that other cpus doing
+	 * __start_cfs_bandwidth will stop trying to cancel us.
+	 */
+	cfs_b->timer_active = 1;
+
 	__refill_cfs_bandwidth_runtime(cfs_b);
 
 	if (!throttled) {
@@ -2508,7 +3294,13 @@ static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC;
 /* how long we wait to gather additional slack before distributing */
 static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
 
-/* are we near the end of the current quota period? */
+/*
+ * Are we near the end of the current quota period?
+ *
+ * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
+ * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * migrate_hrtimers, base is never cleared, so we are fine.
+ */
 static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
 {
 	struct hrtimer *refresh_timer = &cfs_b->period_timer;
@@ -2584,10 +3376,12 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 	u64 expires;
 
 	/* confirm we're still not at a refresh boundary */
-	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration))
+	raw_spin_lock(&cfs_b->lock);
+	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
+		raw_spin_unlock(&cfs_b->lock);
 		return;
+	}
 
-	raw_spin_lock(&cfs_b->lock);
 	if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) {
 		runtime = cfs_b->runtime;
 		cfs_b->runtime = 0;
@@ -2708,11 +3502,11 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	 * (timer_active==0 becomes visible before the hrtimer call-back
 	 * terminates).  In either case we ensure that it's re-programmed
 	 */
-	while (unlikely(hrtimer_active(&cfs_b->period_timer))) {
+	while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
+	       hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
+		/* bounce the lock to allow do_sched_cfs_period_timer to run */
 		raw_spin_unlock(&cfs_b->lock);
-		/* ensure cfs_b->lock is available while we wait */
-		hrtimer_cancel(&cfs_b->period_timer);
-
+		cpu_relax();
 		raw_spin_lock(&cfs_b->lock);
 		/* if someone else restarted the timer then we're done */
 		if (cfs_b->timer_active)
@@ -3113,7 +3907,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 {
 	struct sched_entity *se = tg->se[cpu];
 
-	if (!tg->parent)	/* the trivial, non-cgroup case */
+	if (!tg->parent || !wl)	/* the trivial, non-cgroup case */
 		return wl;
 
 	for_each_sched_entity(se) {
@@ -3166,8 +3960,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 }
 #else
 
-static inline unsigned long effective_load(struct task_group *tg, int cpu,
-		unsigned long wl, unsigned long wg)
+static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 {
 	return wl;
 }
@@ -3420,11 +4213,10 @@ done:
  * preempt must be disabled.
  */
 static int
-select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
 {
 	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
 	int cpu = smp_processor_id();
-	int prev_cpu = task_cpu(p);
 	int new_cpu = cpu;
 	int want_affine = 0;
 	int sync = wake_flags & WF_SYNC;
@@ -3904,9 +4696,12 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp
 
 static unsigned long __read_mostly max_load_balance_interval = HZ/10;
 
+enum fbq_type { regular, remote, all };
+
 #define LBF_ALL_PINNED	0x01
 #define LBF_NEED_BREAK	0x02
-#define LBF_SOME_PINNED 0x04
+#define LBF_DST_PINNED  0x04
+#define LBF_SOME_PINNED	0x08
 
 struct lb_env {
 	struct sched_domain	*sd;
@@ -3929,6 +4724,8 @@ struct lb_env {
 	unsigned int		loop;
 	unsigned int		loop_break;
 	unsigned int		loop_max;
+
+	enum fbq_type		fbq_type;
 };
 
 /*
@@ -3975,6 +4772,78 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 	return delta < (s64)sysctl_sched_migration_cost;
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+/* Returns true if the destination node has incurred more faults */
+static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
+{
+	int src_nid, dst_nid;
+
+	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
+	    !(env->sd->flags & SD_NUMA)) {
+		return false;
+	}
+
+	src_nid = cpu_to_node(env->src_cpu);
+	dst_nid = cpu_to_node(env->dst_cpu);
+
+	if (src_nid == dst_nid)
+		return false;
+
+	/* Always encourage migration to the preferred node. */
+	if (dst_nid == p->numa_preferred_nid)
+		return true;
+
+	/* If both task and group weight improve, this move is a winner. */
+	if (task_weight(p, dst_nid) > task_weight(p, src_nid) &&
+	    group_weight(p, dst_nid) > group_weight(p, src_nid))
+		return true;
+
+	return false;
+}
+
+
+static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
+{
+	int src_nid, dst_nid;
+
+	if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
+		return false;
+
+	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+		return false;
+
+	src_nid = cpu_to_node(env->src_cpu);
+	dst_nid = cpu_to_node(env->dst_cpu);
+
+	if (src_nid == dst_nid)
+		return false;
+
+	/* Migrating away from the preferred node is always bad. */
+	if (src_nid == p->numa_preferred_nid)
+		return true;
+
+	/* If either task or group weight get worse, don't do it. */
+	if (task_weight(p, dst_nid) < task_weight(p, src_nid) ||
+	    group_weight(p, dst_nid) < group_weight(p, src_nid))
+		return true;
+
+	return false;
+}
+
+#else
+static inline bool migrate_improves_locality(struct task_struct *p,
+					     struct lb_env *env)
+{
+	return false;
+}
+
+static inline bool migrate_degrades_locality(struct task_struct *p,
+					     struct lb_env *env)
+{
+	return false;
+}
+#endif
+
 /*
  * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
  */
@@ -3997,6 +4866,8 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 
 		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
 
+		env->flags |= LBF_SOME_PINNED;
+
 		/*
 		 * Remember if this task can be migrated to any other cpu in
 		 * our sched_group. We may want to revisit it if we couldn't
@@ -4005,13 +4876,13 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 		 * Also avoid computing new_dst_cpu if we have already computed
 		 * one in current iteration.
 		 */
-		if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED))
+		if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED))
 			return 0;
 
 		/* Prevent to re-select dst_cpu via env's cpus */
 		for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
 			if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) {
-				env->flags |= LBF_SOME_PINNED;
+				env->flags |= LBF_DST_PINNED;
 				env->new_dst_cpu = cpu;
 				break;
 			}
@@ -4030,11 +4901,24 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 
 	/*
 	 * Aggressive migration if:
-	 * 1) task is cache cold, or
-	 * 2) too many balance attempts have failed.
+	 * 1) destination numa is preferred
+	 * 2) task is cache cold, or
+	 * 3) too many balance attempts have failed.
 	 */
-
 	tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
+	if (!tsk_cache_hot)
+		tsk_cache_hot = migrate_degrades_locality(p, env);
+
+	if (migrate_improves_locality(p, env)) {
+#ifdef CONFIG_SCHEDSTATS
+		if (tsk_cache_hot) {
+			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
+			schedstat_inc(p, se.statistics.nr_forced_migrations);
+		}
+#endif
+		return 1;
+	}
+
 	if (!tsk_cache_hot ||
 		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
 
@@ -4077,8 +4961,6 @@ static int move_one_task(struct lb_env *env)
 	return 0;
 }
 
-static unsigned long task_h_load(struct task_struct *p);
-
 static const unsigned int sched_nr_migrate_break = 32;
 
 /*
@@ -4291,6 +5173,10 @@ struct sg_lb_stats {
 	unsigned int group_weight;
 	int group_imb; /* Is there an imbalance in the group ? */
 	int group_has_capacity; /* Is there extra capacity in the group? */
+#ifdef CONFIG_NUMA_BALANCING
+	unsigned int nr_numa_running;
+	unsigned int nr_preferred_running;
+#endif
 };
 
 /*
@@ -4330,7 +5216,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
 /**
  * get_sd_load_idx - Obtain the load index for a given sched domain.
  * @sd: The sched_domain whose load_idx is to be obtained.
- * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
+ * @idle: The idle status of the CPU for whose sd load_idx is obtained.
  *
  * Return: The load index.
  */
@@ -4447,7 +5333,7 @@ void update_group_power(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
-	unsigned long power;
+	unsigned long power, power_orig;
 	unsigned long interval;
 
 	interval = msecs_to_jiffies(sd->balance_interval);
@@ -4459,7 +5345,7 @@ void update_group_power(struct sched_domain *sd, int cpu)
 		return;
 	}
 
-	power = 0;
+	power_orig = power = 0;
 
 	if (child->flags & SD_OVERLAP) {
 		/*
@@ -4467,8 +5353,12 @@ void update_group_power(struct sched_domain *sd, int cpu)
 		 * span the current group.
 		 */
 
-		for_each_cpu(cpu, sched_group_cpus(sdg))
-			power += power_of(cpu);
+		for_each_cpu(cpu, sched_group_cpus(sdg)) {
+			struct sched_group *sg = cpu_rq(cpu)->sd->groups;
+
+			power_orig += sg->sgp->power_orig;
+			power += sg->sgp->power;
+		}
 	} else  {
 		/*
 		 * !SD_OVERLAP domains can assume that child groups
@@ -4477,12 +5367,14 @@ void update_group_power(struct sched_domain *sd, int cpu)
 
 		group = child->groups;
 		do {
+			power_orig += group->sgp->power_orig;
 			power += group->sgp->power;
 			group = group->next;
 		} while (group != child->groups);
 	}
 
-	sdg->sgp->power_orig = sdg->sgp->power = power;
+	sdg->sgp->power_orig = power_orig;
+	sdg->sgp->power = power;
 }
 
 /*
@@ -4526,13 +5418,12 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  * cpu 3 and leave one of the cpus in the second group unused.
  *
  * The current solution to this issue is detecting the skew in the first group
- * by noticing it has a cpu that is overloaded while the remaining cpus are
- * idle -- or rather, there's a distinct imbalance in the cpus; see
- * sg_imbalanced().
+ * by noticing the lower domain failed to reach balance and had difficulty
+ * moving tasks due to affinity constraints.
  *
  * When this is so detected; this group becomes a candidate for busiest; see
- * update_sd_pick_busiest(). And calculcate_imbalance() and
- * find_busiest_group() avoid some of the usual balance conditional to allow it
+ * update_sd_pick_busiest(). And calculate_imbalance() and
+ * find_busiest_group() avoid some of the usual balance conditions to allow it
  * to create an effective group imbalance.
  *
  * This is a somewhat tricky proposition since the next run might not find the
@@ -4540,49 +5431,36 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  * subtle and fragile situation.
  */
 
-struct sg_imb_stats {
-	unsigned long max_nr_running, min_nr_running;
-	unsigned long max_cpu_load, min_cpu_load;
-};
-
-static inline void init_sg_imb_stats(struct sg_imb_stats *sgi)
+static inline int sg_imbalanced(struct sched_group *group)
 {
-	sgi->max_cpu_load = sgi->max_nr_running = 0UL;
-	sgi->min_cpu_load = sgi->min_nr_running = ~0UL;
+	return group->sgp->imbalance;
 }
 
-static inline void
-update_sg_imb_stats(struct sg_imb_stats *sgi,
-		    unsigned long load, unsigned long nr_running)
+/*
+ * Compute the group capacity.
+ *
+ * Avoid the issue where N*frac(smt_power) >= 1 creates 'phantom' cores by
+ * first dividing out the smt factor and computing the actual number of cores
+ * and limit power unit capacity with that.
+ */
+static inline int sg_capacity(struct lb_env *env, struct sched_group *group)
 {
-	if (load > sgi->max_cpu_load)
-		sgi->max_cpu_load = load;
-	if (sgi->min_cpu_load > load)
-		sgi->min_cpu_load = load;
+	unsigned int capacity, smt, cpus;
+	unsigned int power, power_orig;
 
-	if (nr_running > sgi->max_nr_running)
-		sgi->max_nr_running = nr_running;
-	if (sgi->min_nr_running > nr_running)
-		sgi->min_nr_running = nr_running;
-}
+	power = group->sgp->power;
+	power_orig = group->sgp->power_orig;
+	cpus = group->group_weight;
 
-static inline int
-sg_imbalanced(struct sg_lb_stats *sgs, struct sg_imb_stats *sgi)
-{
-	/*
-	 * Consider the group unbalanced when the imbalance is larger
-	 * than the average weight of a task.
-	 *
-	 * APZ: with cgroup the avg task weight can vary wildly and
-	 *      might not be a suitable number - should we keep a
-	 *      normalized nr_running number somewhere that negates
-	 *      the hierarchy?
-	 */
-	if ((sgi->max_cpu_load - sgi->min_cpu_load) >= sgs->load_per_task &&
-	    (sgi->max_nr_running - sgi->min_nr_running) > 1)
-		return 1;
+	/* smt := ceil(cpus / power), assumes: 1 < smt_power < 2 */
+	smt = DIV_ROUND_UP(SCHED_POWER_SCALE * cpus, power_orig);
+	capacity = cpus / smt; /* cores */
 
-	return 0;
+	capacity = min_t(unsigned, capacity, DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE));
+	if (!capacity)
+		capacity = fix_small_capacity(env->sd, group);
+
+	return capacity;
 }
 
 /**
@@ -4597,12 +5475,11 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			struct sched_group *group, int load_idx,
 			int local_group, struct sg_lb_stats *sgs)
 {
-	struct sg_imb_stats sgi;
 	unsigned long nr_running;
 	unsigned long load;
 	int i;
 
-	init_sg_imb_stats(&sgi);
+	memset(sgs, 0, sizeof(*sgs));
 
 	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
@@ -4610,24 +5487,22 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		nr_running = rq->nr_running;
 
 		/* Bias balancing toward cpus of our domain */
-		if (local_group) {
+		if (local_group)
 			load = target_load(i, load_idx);
-		} else {
+		else
 			load = source_load(i, load_idx);
-			update_sg_imb_stats(&sgi, load, nr_running);
-		}
 
 		sgs->group_load += load;
 		sgs->sum_nr_running += nr_running;
+#ifdef CONFIG_NUMA_BALANCING
+		sgs->nr_numa_running += rq->nr_numa_running;
+		sgs->nr_preferred_running += rq->nr_preferred_running;
+#endif
 		sgs->sum_weighted_load += weighted_cpuload(i);
 		if (idle_cpu(i))
 			sgs->idle_cpus++;
 	}
 
-	if (local_group && (env->idle != CPU_NEWLY_IDLE ||
-			time_after_eq(jiffies, group->sgp->next_update)))
-		update_group_power(env->sd, env->dst_cpu);
-
 	/* Adjust by relative CPU power of the group */
 	sgs->group_power = group->sgp->power;
 	sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / sgs->group_power;
@@ -4635,16 +5510,11 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	if (sgs->sum_nr_running)
 		sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
-	sgs->group_imb = sg_imbalanced(sgs, &sgi);
-
-	sgs->group_capacity =
-		DIV_ROUND_CLOSEST(sgs->group_power, SCHED_POWER_SCALE);
-
-	if (!sgs->group_capacity)
-		sgs->group_capacity = fix_small_capacity(env->sd, group);
-
 	sgs->group_weight = group->group_weight;
 
+	sgs->group_imb = sg_imbalanced(group);
+	sgs->group_capacity = sg_capacity(env, group);
+
 	if (sgs->group_capacity > sgs->sum_nr_running)
 		sgs->group_has_capacity = 1;
 }
@@ -4693,14 +5563,42 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	return false;
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
+{
+	if (sgs->sum_nr_running > sgs->nr_numa_running)
+		return regular;
+	if (sgs->sum_nr_running > sgs->nr_preferred_running)
+		return remote;
+	return all;
+}
+
+static inline enum fbq_type fbq_classify_rq(struct rq *rq)
+{
+	if (rq->nr_running > rq->nr_numa_running)
+		return regular;
+	if (rq->nr_running > rq->nr_preferred_running)
+		return remote;
+	return all;
+}
+#else
+static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs)
+{
+	return all;
+}
+
+static inline enum fbq_type fbq_classify_rq(struct rq *rq)
+{
+	return regular;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /**
  * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
  * @env: The load balancing environment.
- * @balance: Should we balance.
  * @sds: variable to hold the statistics for this sched_domain.
  */
-static inline void update_sd_lb_stats(struct lb_env *env,
-					struct sd_lb_stats *sds)
+static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
 {
 	struct sched_domain *child = env->sd->child;
 	struct sched_group *sg = env->sd->groups;
@@ -4720,11 +5618,17 @@ static inline void update_sd_lb_stats(struct lb_env *env,
 		if (local_group) {
 			sds->local = sg;
 			sgs = &sds->local_stat;
+
+			if (env->idle != CPU_NEWLY_IDLE ||
+			    time_after_eq(jiffies, sg->sgp->next_update))
+				update_group_power(env->sd, env->dst_cpu);
 		}
 
-		memset(sgs, 0, sizeof(*sgs));
 		update_sg_lb_stats(env, sg, load_idx, local_group, sgs);
 
+		if (local_group)
+			goto next_group;
+
 		/*
 		 * In case the child domain prefers tasks go to siblings
 		 * first, lower the sg capacity to one so that we'll try
@@ -4735,21 +5639,25 @@ static inline void update_sd_lb_stats(struct lb_env *env,
 		 * heaviest group when it is already under-utilized (possible
 		 * with a large weight task outweighs the tasks on the system).
 		 */
-		if (prefer_sibling && !local_group &&
-				sds->local && sds->local_stat.group_has_capacity)
+		if (prefer_sibling && sds->local &&
+		    sds->local_stat.group_has_capacity)
 			sgs->group_capacity = min(sgs->group_capacity, 1U);
 
-		/* Now, start updating sd_lb_stats */
-		sds->total_load += sgs->group_load;
-		sds->total_pwr += sgs->group_power;
-
-		if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) {
+		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
 			sds->busiest_stat = *sgs;
 		}
 
+next_group:
+		/* Now, start updating sd_lb_stats */
+		sds->total_load += sgs->group_load;
+		sds->total_pwr += sgs->group_power;
+
 		sg = sg->next;
 	} while (sg != env->sd->groups);
+
+	if (env->sd->flags & SD_NUMA)
+		env->fbq_type = fbq_classify_group(&sds->busiest_stat);
 }
 
 /**
@@ -5053,15 +5961,39 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 	int i;
 
 	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
-		unsigned long power = power_of(i);
-		unsigned long capacity = DIV_ROUND_CLOSEST(power,
-							   SCHED_POWER_SCALE);
-		unsigned long wl;
+		unsigned long power, capacity, wl;
+		enum fbq_type rt;
 
+		rq = cpu_rq(i);
+		rt = fbq_classify_rq(rq);
+
+		/*
+		 * We classify groups/runqueues into three groups:
+		 *  - regular: there are !numa tasks
+		 *  - remote:  there are numa tasks that run on the 'wrong' node
+		 *  - all:     there is no distinction
+		 *
+		 * In order to avoid migrating ideally placed numa tasks,
+		 * ignore those when there's better options.
+		 *
+		 * If we ignore the actual busiest queue to migrate another
+		 * task, the next balance pass can still reduce the busiest
+		 * queue by moving tasks around inside the node.
+		 *
+		 * If we cannot move enough load due to this classification
+		 * the next pass will adjust the group classification and
+		 * allow migration of more tasks.
+		 *
+		 * Both cases only affect the total convergence complexity.
+		 */
+		if (rt > env->fbq_type)
+			continue;
+
+		power = power_of(i);
+		capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE);
 		if (!capacity)
 			capacity = fix_small_capacity(env->sd, group);
 
-		rq = cpu_rq(i);
 		wl = weighted_cpuload(i);
 
 		/*
@@ -5164,6 +6096,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			int *continue_balancing)
 {
 	int ld_moved, cur_ld_moved, active_balance = 0;
+	struct sched_domain *sd_parent = sd->parent;
 	struct sched_group *group;
 	struct rq *busiest;
 	unsigned long flags;
@@ -5177,6 +6110,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.idle		= idle,
 		.loop_break	= sched_nr_migrate_break,
 		.cpus		= cpus,
+		.fbq_type	= all,
 	};
 
 	/*
@@ -5268,17 +6202,17 @@ more_balance:
 		 * moreover subsequent load balance cycles should correct the
 		 * excess load moved.
 		 */
-		if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) {
+		if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) {
+
+			/* Prevent to re-select dst_cpu via env's cpus */
+			cpumask_clear_cpu(env.dst_cpu, env.cpus);
 
 			env.dst_rq	 = cpu_rq(env.new_dst_cpu);
 			env.dst_cpu	 = env.new_dst_cpu;
-			env.flags	&= ~LBF_SOME_PINNED;
+			env.flags	&= ~LBF_DST_PINNED;
 			env.loop	 = 0;
 			env.loop_break	 = sched_nr_migrate_break;
 
-			/* Prevent to re-select dst_cpu via env's cpus */
-			cpumask_clear_cpu(env.dst_cpu, env.cpus);
-
 			/*
 			 * Go back to "more_balance" rather than "redo" since we
 			 * need to continue with same src_cpu.
@@ -5286,6 +6220,18 @@ more_balance:
 			goto more_balance;
 		}
 
+		/*
+		 * We failed to reach balance because of affinity.
+		 */
+		if (sd_parent) {
+			int *group_imbalance = &sd_parent->groups->sgp->imbalance;
+
+			if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) {
+				*group_imbalance = 1;
+			} else if (*group_imbalance)
+				*group_imbalance = 0;
+		}
+
 		/* All tasks on this runqueue were pinned by CPU affinity */
 		if (unlikely(env.flags & LBF_ALL_PINNED)) {
 			cpumask_clear_cpu(cpu_of(busiest), cpus);
@@ -5393,6 +6339,7 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 	struct sched_domain *sd;
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
+	u64 curr_cost = 0;
 
 	this_rq->idle_stamp = rq_clock(this_rq);
 
@@ -5409,15 +6356,27 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
 		int continue_balancing = 1;
+		u64 t0, domain_cost;
 
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;
 
+		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost)
+			break;
+
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
+			t0 = sched_clock_cpu(this_cpu);
+
 			/* If we've pulled tasks over stop searching: */
 			pulled_task = load_balance(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
 						   &continue_balancing);
+
+			domain_cost = sched_clock_cpu(this_cpu) - t0;
+			if (domain_cost > sd->max_newidle_lb_cost)
+				sd->max_newidle_lb_cost = domain_cost;
+
+			curr_cost += domain_cost;
 		}
 
 		interval = msecs_to_jiffies(sd->balance_interval);
@@ -5439,6 +6398,9 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 		 */
 		this_rq->next_balance = next_balance;
 	}
+
+	if (curr_cost > this_rq->max_idle_balance_cost)
+		this_rq->max_idle_balance_cost = curr_cost;
 }
 
 /*
@@ -5662,15 +6624,39 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	/* Earliest time when we have to do rebalance again */
 	unsigned long next_balance = jiffies + 60*HZ;
 	int update_next_balance = 0;
-	int need_serialize;
+	int need_serialize, need_decay = 0;
+	u64 max_cost = 0;
 
 	update_blocked_averages(cpu);
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
+		/*
+		 * Decay the newidle max times here because this is a regular
+		 * visit to all the domains. Decay ~1% per second.
+		 */
+		if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
+			sd->max_newidle_lb_cost =
+				(sd->max_newidle_lb_cost * 253) / 256;
+			sd->next_decay_max_lb_cost = jiffies + HZ;
+			need_decay = 1;
+		}
+		max_cost += sd->max_newidle_lb_cost;
+
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;
 
+		/*
+		 * Stop the load balance at this level. There is another
+		 * CPU in our sched group which is doing load balancing more
+		 * actively.
+		 */
+		if (!continue_balancing) {
+			if (need_decay)
+				continue;
+			break;
+		}
+
 		interval = sd->balance_interval;
 		if (idle != CPU_IDLE)
 			interval *= sd->busy_factor;
@@ -5689,7 +6675,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		if (time_after_eq(jiffies, sd->last_balance + interval)) {
 			if (load_balance(cpu, rq, sd, idle, &continue_balancing)) {
 				/*
-				 * The LBF_SOME_PINNED logic could have changed
+				 * The LBF_DST_PINNED logic could have changed
 				 * env->dst_cpu, so we can't know our idle
 				 * state even if we migrated tasks. Update it.
 				 */
@@ -5704,14 +6690,14 @@ out:
 			next_balance = sd->last_balance + interval;
 			update_next_balance = 1;
 		}
-
+	}
+	if (need_decay) {
 		/*
-		 * Stop the load balance at this level. There is another
-		 * CPU in our sched group which is doing load balancing more
-		 * actively.
+		 * Ensure the rq-wide value also decays but keep it at a
+		 * reasonable floor to avoid funnies with rq->avg_idle.
 		 */
-		if (!continue_balancing)
-			break;
+		rq->max_idle_balance_cost =
+			max((u64)sysctl_sched_migration_cost, max_cost);
 	}
 	rcu_read_unlock();
 
@@ -6214,7 +7200,8 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 		se->cfs_rq = parent->my_q;
 
 	se->my_q = cfs_rq;
-	update_load_set(&se->load, 0);
+	/* guarantee group entities always have weight */
+	update_load_set(&se->load, NICE_0_LOAD);
 	se->parent = parent;
 }
 
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 99399f8e4799..5716929a2e3a 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -63,10 +63,23 @@ SCHED_FEAT(LB_MIN, false)
 /*
  * Apply the automatic NUMA scheduling policy. Enabled automatically
  * at runtime if running on a NUMA machine. Can be controlled via
- * numa_balancing=. Allow PTE scanning to be forced on UMA machines
- * for debugging the core machinery.
+ * numa_balancing=
  */
 #ifdef CONFIG_NUMA_BALANCING
 SCHED_FEAT(NUMA,	false)
-SCHED_FEAT(NUMA_FORCE,	false)
+
+/*
+ * NUMA_FAVOUR_HIGHER will favor moving tasks towards nodes where a
+ * higher number of hinting faults are recorded during active load
+ * balancing.
+ */
+SCHED_FEAT(NUMA_FAVOUR_HIGHER, true)
+
+/*
+ * NUMA_RESIST_LOWER will resist moving tasks towards nodes where a
+ * lower number of hinting faults have been recorded. As this has
+ * the potential to prevent a task ever migrating to a new node
+ * due to CPU overload it is disabled by default.
+ */
+SCHED_FEAT(NUMA_RESIST_LOWER, false)
 #endif
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index d8da01008d39..516c3d9ceea1 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -9,7 +9,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
+select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 01970c8e64df..7d57275fc396 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -246,8 +246,10 @@ static inline void rt_set_overload(struct rq *rq)
 	 * if we should look at the mask. It would be a shame
 	 * if we looked at the mask, but the mask was not
 	 * updated yet.
+	 *
+	 * Matched by the barrier in pull_rt_task().
 	 */
-	wmb();
+	smp_wmb();
 	atomic_inc(&rq->rd->rto_count);
 }
 
@@ -1169,13 +1171,10 @@ static void yield_task_rt(struct rq *rq)
 static int find_lowest_rq(struct task_struct *task);
 
 static int
-select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
+select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	struct task_struct *curr;
 	struct rq *rq;
-	int cpu;
-
-	cpu = task_cpu(p);
 
 	if (p->nr_cpus_allowed == 1)
 		goto out;
@@ -1213,8 +1212,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 	 */
 	if (curr && unlikely(rt_task(curr)) &&
 	    (curr->nr_cpus_allowed < 2 ||
-	     curr->prio <= p->prio) &&
-	    (p->nr_cpus_allowed > 1)) {
+	     curr->prio <= p->prio)) {
 		int target = find_lowest_rq(p);
 
 		if (target != -1)
@@ -1630,6 +1628,12 @@ static int pull_rt_task(struct rq *this_rq)
 	if (likely(!rt_overloaded(this_rq)))
 		return 0;
 
+	/*
+	 * Match the barrier from rt_set_overloaded; this guarantees that if we
+	 * see overloaded we must also see the rto_mask bit.
+	 */
+	smp_rmb();
+
 	for_each_cpu(cpu, this_rq->rd->rto_mask) {
 		if (this_cpu == cpu)
 			continue;
@@ -1931,8 +1935,8 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	p->rt.time_slice = sched_rr_timeslice;
 
 	/*
-	 * Requeue to the end of queue if we (and all of our ancestors) are the
-	 * only element on the queue
+	 * Requeue to the end of queue if we (and all of our ancestors) are not
+	 * the only element on the queue
 	 */
 	for_each_sched_rt_entity(rt_se) {
 		if (rt_se->run_list.prev != rt_se->run_list.next) {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b3c5653e1dca..4e650acffed7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -6,6 +6,7 @@
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>
 #include <linux/tick.h>
+#include <linux/slab.h>
 
 #include "cpupri.h"
 #include "cpuacct.h"
@@ -408,6 +409,10 @@ struct rq {
 	 * remote CPUs use both these fields when doing load calculation.
 	 */
 	unsigned int nr_running;
+#ifdef CONFIG_NUMA_BALANCING
+	unsigned int nr_numa_running;
+	unsigned int nr_preferred_running;
+#endif
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
 	unsigned long last_load_update_tick;
@@ -476,6 +481,9 @@ struct rq {
 	u64 age_stamp;
 	u64 idle_stamp;
 	u64 avg_idle;
+
+	/* This is used to determine avg_idle's max value */
+	u64 max_idle_balance_cost;
 #endif
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -552,6 +560,12 @@ static inline u64 rq_clock_task(struct rq *rq)
 	return rq->clock_task;
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+extern void sched_setnuma(struct task_struct *p, int node);
+extern int migrate_task_to(struct task_struct *p, int cpu);
+extern int migrate_swap(struct task_struct *, struct task_struct *);
+#endif /* CONFIG_NUMA_BALANCING */
+
 #ifdef CONFIG_SMP
 
 #define rcu_dereference_check_sched_domain(p) \
@@ -593,9 +607,22 @@ static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
 	return hsd;
 }
 
+static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
+{
+	struct sched_domain *sd;
+
+	for_each_domain(cpu, sd) {
+		if (sd->flags & flag)
+			break;
+	}
+
+	return sd;
+}
+
 DECLARE_PER_CPU(struct sched_domain *, sd_llc);
 DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
+DECLARE_PER_CPU(struct sched_domain *, sd_numa);
 
 struct sched_group_power {
 	atomic_t ref;
@@ -605,6 +632,7 @@ struct sched_group_power {
 	 */
 	unsigned int power, power_orig;
 	unsigned long next_update;
+	int imbalance; /* XXX unrelated to power but shared group state */
 	/*
 	 * Number of busy cpus in this group.
 	 */
@@ -719,6 +747,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 	 */
 	smp_wmb();
 	task_thread_info(p)->cpu = cpu;
+	p->wake_cpu = cpu;
 #endif
 }
 
@@ -974,7 +1003,7 @@ struct sched_class {
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
+	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
 	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
 
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
@@ -1220,6 +1249,24 @@ static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
 	lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
 }
 
+static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
+{
+	if (l1 > l2)
+		swap(l1, l2);
+
+	spin_lock(l1);
+	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
+static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
+{
+	if (l1 > l2)
+		swap(l1, l2);
+
+	raw_spin_lock(l1);
+	raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
 /*
  * double_rq_lock - safely lock two runqueues
  *
@@ -1305,7 +1352,8 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
 extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
 
-extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
+extern void cfs_bandwidth_usage_inc(void);
+extern void cfs_bandwidth_usage_dec(void);
 
 #ifdef CONFIG_NO_HZ_COMMON
 enum rq_nohz_flag_bits {
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index c7edee71bce8..4ab704339656 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -59,9 +59,9 @@ static inline void sched_info_reset_dequeued(struct task_struct *t)
  * from dequeue_task() to account for possible rq->clock skew across cpus. The
  * delta taken on each cpu would annul the skew.
  */
-static inline void sched_info_dequeued(struct task_struct *t)
+static inline void sched_info_dequeued(struct rq *rq, struct task_struct *t)
 {
-	unsigned long long now = rq_clock(task_rq(t)), delta = 0;
+	unsigned long long now = rq_clock(rq), delta = 0;
 
 	if (unlikely(sched_info_on()))
 		if (t->sched_info.last_queued)
@@ -69,7 +69,7 @@ static inline void sched_info_dequeued(struct task_struct *t)
 	sched_info_reset_dequeued(t);
 	t->sched_info.run_delay += delta;
 
-	rq_sched_info_dequeued(task_rq(t), delta);
+	rq_sched_info_dequeued(rq, delta);
 }
 
 /*
@@ -77,9 +77,9 @@ static inline void sched_info_dequeued(struct task_struct *t)
  * long it was waiting to run.  We also note when it began so that we
  * can keep stats on how long its timeslice is.
  */
-static void sched_info_arrive(struct task_struct *t)
+static void sched_info_arrive(struct rq *rq, struct task_struct *t)
 {
-	unsigned long long now = rq_clock(task_rq(t)), delta = 0;
+	unsigned long long now = rq_clock(rq), delta = 0;
 
 	if (t->sched_info.last_queued)
 		delta = now - t->sched_info.last_queued;
@@ -88,7 +88,7 @@ static void sched_info_arrive(struct task_struct *t)
 	t->sched_info.last_arrival = now;
 	t->sched_info.pcount++;
 
-	rq_sched_info_arrive(task_rq(t), delta);
+	rq_sched_info_arrive(rq, delta);
 }
 
 /*
@@ -96,11 +96,11 @@ static void sched_info_arrive(struct task_struct *t)
  * the timestamp if it is already not set.  It's assumed that
  * sched_info_dequeued() will clear that stamp when appropriate.
  */
-static inline void sched_info_queued(struct task_struct *t)
+static inline void sched_info_queued(struct rq *rq, struct task_struct *t)
 {
 	if (unlikely(sched_info_on()))
 		if (!t->sched_info.last_queued)
-			t->sched_info.last_queued = rq_clock(task_rq(t));
+			t->sched_info.last_queued = rq_clock(rq);
 }
 
 /*
@@ -111,15 +111,15 @@ static inline void sched_info_queued(struct task_struct *t)
  * sched_info_queued() to mark that it has now again started waiting on
  * the runqueue.
  */
-static inline void sched_info_depart(struct task_struct *t)
+static inline void sched_info_depart(struct rq *rq, struct task_struct *t)
 {
-	unsigned long long delta = rq_clock(task_rq(t)) -
+	unsigned long long delta = rq_clock(rq) -
 					t->sched_info.last_arrival;
 
-	rq_sched_info_depart(task_rq(t), delta);
+	rq_sched_info_depart(rq, delta);
 
 	if (t->state == TASK_RUNNING)
-		sched_info_queued(t);
+		sched_info_queued(rq, t);
 }
 
 /*
@@ -128,32 +128,34 @@ static inline void sched_info_depart(struct task_struct *t)
  * the idle task.)  We are only called when prev != next.
  */
 static inline void
-__sched_info_switch(struct task_struct *prev, struct task_struct *next)
+__sched_info_switch(struct rq *rq,
+		    struct task_struct *prev, struct task_struct *next)
 {
-	struct rq *rq = task_rq(prev);
-
 	/*
 	 * prev now departs the cpu.  It's not interesting to record
 	 * stats about how efficient we were at scheduling the idle
 	 * process, however.
 	 */
 	if (prev != rq->idle)
-		sched_info_depart(prev);
+		sched_info_depart(rq, prev);
 
 	if (next != rq->idle)
-		sched_info_arrive(next);
+		sched_info_arrive(rq, next);
 }
 static inline void
-sched_info_switch(struct task_struct *prev, struct task_struct *next)
+sched_info_switch(struct rq *rq,
+		  struct task_struct *prev, struct task_struct *next)
 {
 	if (unlikely(sched_info_on()))
-		__sched_info_switch(prev, next);
+		__sched_info_switch(rq, prev, next);
 }
 #else
-#define sched_info_queued(t)			do { } while (0)
+#define sched_info_queued(rq, t)		do { } while (0)
 #define sched_info_reset_dequeued(t)	do { } while (0)
-#define sched_info_dequeued(t)			do { } while (0)
-#define sched_info_switch(t, next)		do { } while (0)
+#define sched_info_dequeued(rq, t)		do { } while (0)
+#define sched_info_depart(rq, t)		do { } while (0)
+#define sched_info_arrive(rq, next)		do { } while (0)
+#define sched_info_switch(rq, t, next)		do { } while (0)
 #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
 
 /*
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index e08fbeeb54b9..47197de8abd9 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -11,7 +11,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_stop(struct task_struct *p, int sd_flag, int flags)
+select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	return task_cpu(p); /* stop tasks as never migrate */
 }
diff --git a/kernel/wait.c b/kernel/sched/wait.c
index d550920e040c..7d50f794e248 100644
--- a/kernel/wait.c
+++ b/kernel/sched/wait.c
@@ -53,6 +53,109 @@ EXPORT_SYMBOL(remove_wait_queue);
 
 
 /*
+ * 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 = 1; /* XXX 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 */
+
+/*
  * Note: we use "set_current_state()" _after_ the wait-queue add,
  * because we need a memory barrier there on SMP, so that any
  * wake-function that tests for the wait-queue being active
@@ -92,6 +195,30 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
 
+long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
+{
+	unsigned long flags;
+
+	if (signal_pending_state(state, current))
+		return -ERESTARTSYS;
+
+	wait->private = current;
+	wait->func = autoremove_wake_function;
+
+	spin_lock_irqsave(&q->lock, flags);
+	if (list_empty(&wait->task_list)) {
+		if (wait->flags & WQ_FLAG_EXCLUSIVE)
+			__add_wait_queue_tail(q, wait);
+		else
+			__add_wait_queue(q, wait);
+	}
+	set_current_state(state);
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(prepare_to_wait_event);
+
 /**
  * finish_wait - clean up after waiting in a queue
  * @q: waitqueue waited on
diff --git a/kernel/softirq.c b/kernel/softirq.c
index d7d498d8cc4f..dcab1d3fb53d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -100,13 +100,13 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 
 	raw_local_irq_save(flags);
 	/*
-	 * The preempt tracer hooks into add_preempt_count and will break
+	 * The preempt tracer hooks into preempt_count_add and will break
 	 * lockdep because it calls back into lockdep after SOFTIRQ_OFFSET
 	 * is set and before current->softirq_enabled is cleared.
 	 * We must manually increment preempt_count here and manually
 	 * call the trace_preempt_off later.
 	 */
-	preempt_count() += cnt;
+	__preempt_count_add(cnt);
 	/*
 	 * Were softirqs turned off above:
 	 */
@@ -120,7 +120,7 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 #else /* !CONFIG_TRACE_IRQFLAGS */
 static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
 {
-	add_preempt_count(cnt);
+	preempt_count_add(cnt);
 	barrier();
 }
 #endif /* CONFIG_TRACE_IRQFLAGS */
@@ -139,7 +139,7 @@ static void __local_bh_enable(unsigned int cnt)
 
 	if (softirq_count() == cnt)
 		trace_softirqs_on(_RET_IP_);
-	sub_preempt_count(cnt);
+	preempt_count_sub(cnt);
 }
 
 /*
@@ -169,12 +169,12 @@ static inline void _local_bh_enable_ip(unsigned long ip)
 	 * Keep preemption disabled until we are done with
 	 * softirq processing:
  	 */
-	sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1);
+	preempt_count_sub(SOFTIRQ_DISABLE_OFFSET - 1);
 
 	if (unlikely(!in_interrupt() && local_softirq_pending()))
 		do_softirq();
 
-	dec_preempt_count();
+	preempt_count_dec();
 #ifdef CONFIG_TRACE_IRQFLAGS
 	local_irq_enable();
 #endif
@@ -256,7 +256,7 @@ restart:
 				       " exited with %08x?\n", vec_nr,
 				       softirq_to_name[vec_nr], h->action,
 				       prev_count, preempt_count());
-				preempt_count() = prev_count;
+				preempt_count_set(prev_count);
 			}
 
 			rcu_bh_qs(cpu);
@@ -369,7 +369,7 @@ void irq_exit(void)
 
 	account_irq_exit_time(current);
 	trace_hardirq_exit();
-	sub_preempt_count(HARDIRQ_OFFSET);
+	preempt_count_sub(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index c09f2955ae30..c530bc5be7cf 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -115,6 +115,182 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
 	return done.executed ? done.ret : -ENOENT;
 }
 
+/* This controls the threads on each CPU. */
+enum multi_stop_state {
+	/* Dummy starting state for thread. */
+	MULTI_STOP_NONE,
+	/* Awaiting everyone to be scheduled. */
+	MULTI_STOP_PREPARE,
+	/* Disable interrupts. */
+	MULTI_STOP_DISABLE_IRQ,
+	/* Run the function */
+	MULTI_STOP_RUN,
+	/* Exit */
+	MULTI_STOP_EXIT,
+};
+
+struct multi_stop_data {
+	int			(*fn)(void *);
+	void			*data;
+	/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+	unsigned int		num_threads;
+	const struct cpumask	*active_cpus;
+
+	enum multi_stop_state	state;
+	atomic_t		thread_ack;
+};
+
+static void set_state(struct multi_stop_data *msdata,
+		      enum multi_stop_state newstate)
+{
+	/* Reset ack counter. */
+	atomic_set(&msdata->thread_ack, msdata->num_threads);
+	smp_wmb();
+	msdata->state = newstate;
+}
+
+/* Last one to ack a state moves to the next state. */
+static void ack_state(struct multi_stop_data *msdata)
+{
+	if (atomic_dec_and_test(&msdata->thread_ack))
+		set_state(msdata, msdata->state + 1);
+}
+
+/* This is the cpu_stop function which stops the CPU. */
+static int multi_cpu_stop(void *data)
+{
+	struct multi_stop_data *msdata = data;
+	enum multi_stop_state curstate = MULTI_STOP_NONE;
+	int cpu = smp_processor_id(), err = 0;
+	unsigned long flags;
+	bool is_active;
+
+	/*
+	 * When called from stop_machine_from_inactive_cpu(), irq might
+	 * already be disabled.  Save the state and restore it on exit.
+	 */
+	local_save_flags(flags);
+
+	if (!msdata->active_cpus)
+		is_active = cpu == cpumask_first(cpu_online_mask);
+	else
+		is_active = cpumask_test_cpu(cpu, msdata->active_cpus);
+
+	/* Simple state machine */
+	do {
+		/* Chill out and ensure we re-read multi_stop_state. */
+		cpu_relax();
+		if (msdata->state != curstate) {
+			curstate = msdata->state;
+			switch (curstate) {
+			case MULTI_STOP_DISABLE_IRQ:
+				local_irq_disable();
+				hard_irq_disable();
+				break;
+			case MULTI_STOP_RUN:
+				if (is_active)
+					err = msdata->fn(msdata->data);
+				break;
+			default:
+				break;
+			}
+			ack_state(msdata);
+		}
+	} while (curstate != MULTI_STOP_EXIT);
+
+	local_irq_restore(flags);
+	return err;
+}
+
+struct irq_cpu_stop_queue_work_info {
+	int cpu1;
+	int cpu2;
+	struct cpu_stop_work *work1;
+	struct cpu_stop_work *work2;
+};
+
+/*
+ * This function is always run with irqs and preemption disabled.
+ * This guarantees that both work1 and work2 get queued, before
+ * our local migrate thread gets the chance to preempt us.
+ */
+static void irq_cpu_stop_queue_work(void *arg)
+{
+	struct irq_cpu_stop_queue_work_info *info = arg;
+	cpu_stop_queue_work(info->cpu1, info->work1);
+	cpu_stop_queue_work(info->cpu2, info->work2);
+}
+
+/**
+ * stop_two_cpus - stops two cpus
+ * @cpu1: the cpu to stop
+ * @cpu2: the other cpu to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Stops both the current and specified CPU and runs @fn on one of them.
+ *
+ * returns when both are completed.
+ */
+int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg)
+{
+	struct cpu_stop_done done;
+	struct cpu_stop_work work1, work2;
+	struct irq_cpu_stop_queue_work_info call_args;
+	struct multi_stop_data msdata;
+
+	preempt_disable();
+	msdata = (struct multi_stop_data){
+		.fn = fn,
+		.data = arg,
+		.num_threads = 2,
+		.active_cpus = cpumask_of(cpu1),
+	};
+
+	work1 = work2 = (struct cpu_stop_work){
+		.fn = multi_cpu_stop,
+		.arg = &msdata,
+		.done = &done
+	};
+
+	call_args = (struct irq_cpu_stop_queue_work_info){
+		.cpu1 = cpu1,
+		.cpu2 = cpu2,
+		.work1 = &work1,
+		.work2 = &work2,
+	};
+
+	cpu_stop_init_done(&done, 2);
+	set_state(&msdata, MULTI_STOP_PREPARE);
+
+	/*
+	 * If we observe both CPUs active we know _cpu_down() cannot yet have
+	 * queued its stop_machine works and therefore ours will get executed
+	 * first. Or its not either one of our CPUs that's getting unplugged,
+	 * in which case we don't care.
+	 *
+	 * This relies on the stopper workqueues to be FIFO.
+	 */
+	if (!cpu_active(cpu1) || !cpu_active(cpu2)) {
+		preempt_enable();
+		return -ENOENT;
+	}
+
+	/*
+	 * Queuing needs to be done by the lowest numbered CPU, to ensure
+	 * that works are always queued in the same order on every CPU.
+	 * This prevents deadlocks.
+	 */
+	smp_call_function_single(min(cpu1, cpu2),
+				 &irq_cpu_stop_queue_work,
+				 &call_args, 0);
+	preempt_enable();
+
+	wait_for_completion(&done.completion);
+
+	return done.executed ? done.ret : -ENOENT;
+}
+
 /**
  * stop_one_cpu_nowait - stop a cpu but don't wait for completion
  * @cpu: cpu to stop
@@ -359,98 +535,14 @@ early_initcall(cpu_stop_init);
 
 #ifdef CONFIG_STOP_MACHINE
 
-/* This controls the threads on each CPU. */
-enum stopmachine_state {
-	/* Dummy starting state for thread. */
-	STOPMACHINE_NONE,
-	/* Awaiting everyone to be scheduled. */
-	STOPMACHINE_PREPARE,
-	/* Disable interrupts. */
-	STOPMACHINE_DISABLE_IRQ,
-	/* Run the function */
-	STOPMACHINE_RUN,
-	/* Exit */
-	STOPMACHINE_EXIT,
-};
-
-struct stop_machine_data {
-	int			(*fn)(void *);
-	void			*data;
-	/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
-	unsigned int		num_threads;
-	const struct cpumask	*active_cpus;
-
-	enum stopmachine_state	state;
-	atomic_t		thread_ack;
-};
-
-static void set_state(struct stop_machine_data *smdata,
-		      enum stopmachine_state newstate)
-{
-	/* Reset ack counter. */
-	atomic_set(&smdata->thread_ack, smdata->num_threads);
-	smp_wmb();
-	smdata->state = newstate;
-}
-
-/* Last one to ack a state moves to the next state. */
-static void ack_state(struct stop_machine_data *smdata)
-{
-	if (atomic_dec_and_test(&smdata->thread_ack))
-		set_state(smdata, smdata->state + 1);
-}
-
-/* This is the cpu_stop function which stops the CPU. */
-static int stop_machine_cpu_stop(void *data)
-{
-	struct stop_machine_data *smdata = data;
-	enum stopmachine_state curstate = STOPMACHINE_NONE;
-	int cpu = smp_processor_id(), err = 0;
-	unsigned long flags;
-	bool is_active;
-
-	/*
-	 * When called from stop_machine_from_inactive_cpu(), irq might
-	 * already be disabled.  Save the state and restore it on exit.
-	 */
-	local_save_flags(flags);
-
-	if (!smdata->active_cpus)
-		is_active = cpu == cpumask_first(cpu_online_mask);
-	else
-		is_active = cpumask_test_cpu(cpu, smdata->active_cpus);
-
-	/* Simple state machine */
-	do {
-		/* Chill out and ensure we re-read stopmachine_state. */
-		cpu_relax();
-		if (smdata->state != curstate) {
-			curstate = smdata->state;
-			switch (curstate) {
-			case STOPMACHINE_DISABLE_IRQ:
-				local_irq_disable();
-				hard_irq_disable();
-				break;
-			case STOPMACHINE_RUN:
-				if (is_active)
-					err = smdata->fn(smdata->data);
-				break;
-			default:
-				break;
-			}
-			ack_state(smdata);
-		}
-	} while (curstate != STOPMACHINE_EXIT);
-
-	local_irq_restore(flags);
-	return err;
-}
-
 int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
-	struct stop_machine_data smdata = { .fn = fn, .data = data,
-					    .num_threads = num_online_cpus(),
-					    .active_cpus = cpus };
+	struct multi_stop_data msdata = {
+		.fn = fn,
+		.data = data,
+		.num_threads = num_online_cpus(),
+		.active_cpus = cpus,
+	};
 
 	if (!stop_machine_initialized) {
 		/*
@@ -461,7 +553,7 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 		unsigned long flags;
 		int ret;
 
-		WARN_ON_ONCE(smdata.num_threads != 1);
+		WARN_ON_ONCE(msdata.num_threads != 1);
 
 		local_irq_save(flags);
 		hard_irq_disable();
@@ -472,8 +564,8 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 	}
 
 	/* Set the initial state and stop all online cpus. */
-	set_state(&smdata, STOPMACHINE_PREPARE);
-	return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata);
+	set_state(&msdata, MULTI_STOP_PREPARE);
+	return stop_cpus(cpu_online_mask, multi_cpu_stop, &msdata);
 }
 
 int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
@@ -513,25 +605,25 @@ EXPORT_SYMBOL_GPL(stop_machine);
 int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
 				  const struct cpumask *cpus)
 {
-	struct stop_machine_data smdata = { .fn = fn, .data = data,
+	struct multi_stop_data msdata = { .fn = fn, .data = data,
 					    .active_cpus = cpus };
 	struct cpu_stop_done done;
 	int ret;
 
 	/* Local CPU must be inactive and CPU hotplug in progress. */
 	BUG_ON(cpu_active(raw_smp_processor_id()));
-	smdata.num_threads = num_active_cpus() + 1;	/* +1 for local */
+	msdata.num_threads = num_active_cpus() + 1;	/* +1 for local */
 
 	/* No proper task established and can't sleep - busy wait for lock. */
 	while (!mutex_trylock(&stop_cpus_mutex))
 		cpu_relax();
 
 	/* Schedule work on other CPUs and execute directly for local CPU */
-	set_state(&smdata, STOPMACHINE_PREPARE);
+	set_state(&msdata, MULTI_STOP_PREPARE);
 	cpu_stop_init_done(&done, num_active_cpus());
-	queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata,
+	queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata,
 			     &done);
-	ret = stop_machine_cpu_stop(&smdata);
+	ret = multi_cpu_stop(&msdata);
 
 	/* Busy wait for completion. */
 	while (!completion_done(&done.completion))
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b24ed7f87a14..339c003314f4 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -371,13 +371,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
-		.procname	= "numa_balancing_scan_period_reset",
-		.data		= &sysctl_numa_balancing_scan_period_reset,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
 		.procname	= "numa_balancing_scan_period_max_ms",
 		.data		= &sysctl_numa_balancing_scan_period_max,
 		.maxlen		= sizeof(unsigned int),
@@ -391,6 +384,20 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname       = "numa_balancing_settle_count",
+		.data           = &sysctl_numa_balancing_settle_count,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{
+		.procname       = "numa_balancing_migrate_deferred",
+		.data           = &sysctl_numa_balancing_migrate_deferred,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_SCHED_DEBUG */
 	{
diff --git a/kernel/timer.c b/kernel/timer.c
index 4296d13db3d1..6582b82fa966 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1092,7 +1092,7 @@ static int cascade(struct tvec_base *base, struct tvec *tv, int index)
 static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
 			  unsigned long data)
 {
-	int preempt_count = preempt_count();
+	int count = preempt_count();
 
 #ifdef CONFIG_LOCKDEP
 	/*
@@ -1119,16 +1119,16 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
 
 	lock_map_release(&lockdep_map);
 
-	if (preempt_count != preempt_count()) {
+	if (count != preempt_count()) {
 		WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n",
-			  fn, preempt_count, preempt_count());
+			  fn, count, preempt_count());
 		/*
 		 * Restore the preempt count. That gives us a decent
 		 * chance to survive and extract information. If the
 		 * callback kept a lock held, bad luck, but not worse
 		 * than the BUG() we had.
 		 */
-		preempt_count() = preempt_count;
+		preempt_count_set(count);
 	}
 }