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

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

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

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

   - wait.h fixes and code reorganization from Peter Zijlstra

   - cfs_bandwidth fixes from Ben Segall

   - SMP load-balancer cleanups from Peter Zijstra

   - idle balancer improvements from Jason Low

   - other fixes and cleanups"

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

26 files changed, 2325 insertions, 827 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 8531609b6a82..f6d11fc67f72 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..1deccd78be98 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -513,12 +513,11 @@ static inline void init_hrtick(void)
  * might also involve a cross-CPU call to trigger the scheduler on
  * the target CPU.
  */
-#ifdef CONFIG_SMP
 void resched_task(struct task_struct *p)
 {
 	int cpu;
 
-	assert_raw_spin_locked(&task_rq(p)->lock);
+	lockdep_assert_held(&task_rq(p)->lock);
 
 	if (test_tsk_need_resched(p))
 		return;
@@ -526,8 +525,10 @@ void resched_task(struct task_struct *p)
 	set_tsk_need_resched(p);
 
 	cpu = task_cpu(p);
-	if (cpu == smp_processor_id())
+	if (cpu == smp_processor_id()) {
+		set_preempt_need_resched();
 		return;
+	}
 
 	/* NEED_RESCHED must be visible before we test polling */
 	smp_mb();
@@ -546,6 +547,7 @@ void resched_cpu(int cpu)
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
+#ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ_COMMON
 /*
  * In the semi idle case, use the nearest busy cpu for migrating timers
@@ -693,12 +695,6 @@ void sched_avg_update(struct rq *rq)
 	}
 }
 
-#else /* !CONFIG_SMP */
-void resched_task(struct task_struct *p)
-{
-	assert_raw_spin_locked(&task_rq(p)->lock);
-	set_tsk_need_resched(p);
-}
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
@@ -767,14 +763,14 @@ static void set_load_weight(struct task_struct *p)
 static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_rq_clock(rq);
-	sched_info_queued(p);
+	sched_info_queued(rq, p);
 	p->sched_class->enqueue_task(rq, p, flags);
 }
 
 static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_rq_clock(rq);
-	sched_info_dequeued(p);
+	sched_info_dequeued(rq, p);
 	p->sched_class->dequeue_task(rq, p, flags);
 }
 
@@ -987,7 +983,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * ttwu() will sort out the placement.
 	 */
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
-			!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
+			!(task_preempt_count(p) & PREEMPT_ACTIVE));
 
 #ifdef CONFIG_LOCKDEP
 	/*
@@ -1017,6 +1013,107 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	__set_task_cpu(p, new_cpu);
 }
 
+static void __migrate_swap_task(struct task_struct *p, int cpu)
+{
+	if (p->on_rq) {
+		struct rq *src_rq, *dst_rq;
+
+		src_rq = task_rq(p);
+		dst_rq = cpu_rq(cpu);
+
+		deactivate_task(src_rq, p, 0);
+		set_task_cpu(p, cpu);
+		activate_task(dst_rq, p, 0);
+		check_preempt_curr(dst_rq, p, 0);
+	} else {
+		/*
+		 * Task isn't running anymore; make it appear like we migrated
+		 * it before it went to sleep. This means on wakeup we make the
+		 * previous cpu our targer instead of where it really is.
+		 */
+		p->wake_cpu = cpu;
+	}
+}
+
+struct migration_swap_arg {
+	struct task_struct *src_task, *dst_task;
+	int src_cpu, dst_cpu;
+};
+
+static int migrate_swap_stop(void *data)
+{
+	struct migration_swap_arg *arg = data;
+	struct rq *src_rq, *dst_rq;
+	int ret = -EAGAIN;
+
+	src_rq = cpu_rq(arg->src_cpu);
+	dst_rq = cpu_rq(arg->dst_cpu);
+
+	double_raw_lock(&arg->src_task->pi_lock,
+			&arg->dst_task->pi_lock);
+	double_rq_lock(src_rq, dst_rq);
+	if (task_cpu(arg->dst_task) != arg->dst_cpu)
+		goto unlock;
+
+	if (task_cpu(arg->src_task) != arg->src_cpu)
+		goto unlock;
+
+	if (!cpumask_test_cpu(arg->dst_cpu, tsk_cpus_allowed(arg->src_task)))
+		goto unlock;
+
+	if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task)))
+		goto unlock;
+
+	__migrate_swap_task(arg->src_task, arg->dst_cpu);
+	__migrate_swap_task(arg->dst_task, arg->src_cpu);
+
+	ret = 0;
+
+unlock:
+	double_rq_unlock(src_rq, dst_rq);
+	raw_spin_unlock(&arg->dst_task->pi_lock);
+	raw_spin_unlock(&arg->src_task->pi_lock);
+
+	return ret;
+}
+
+/*
+ * Cross migrate two tasks
+ */
+int migrate_swap(struct task_struct *cur, struct task_struct *p)
+{
+	struct migration_swap_arg arg;
+	int ret = -EINVAL;
+
+	arg = (struct migration_swap_arg){
+		.src_task = cur,
+		.src_cpu = task_cpu(cur),
+		.dst_task = p,
+		.dst_cpu = task_cpu(p),
+	};
+
+	if (arg.src_cpu == arg.dst_cpu)
+		goto out;
+
+	/*
+	 * These three tests are all lockless; this is OK since all of them
+	 * will be re-checked with proper locks held further down the line.
+	 */
+	if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
+		goto out;
+
+	if (!cpumask_test_cpu(arg.dst_cpu, tsk_cpus_allowed(arg.src_task)))
+		goto out;
+
+	if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task)))
+		goto out;
+
+	ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg);
+
+out:
+	return ret;
+}
+
 struct migration_arg {
 	struct task_struct *task;
 	int dest_cpu;
@@ -1236,9 +1333,9 @@ out:
  * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 {
-	int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+	cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -1330,12 +1427,13 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 
 	if (rq->idle_stamp) {
 		u64 delta = rq_clock(rq) - rq->idle_stamp;
-		u64 max = 2*sysctl_sched_migration_cost;
+		u64 max = 2*rq->max_idle_balance_cost;
+
+		update_avg(&rq->avg_idle, delta);
 
-		if (delta > max)
+		if (rq->avg_idle > max)
 			rq->avg_idle = max;
-		else
-			update_avg(&rq->avg_idle, delta);
+
 		rq->idle_stamp = 0;
 	}
 #endif
@@ -1396,6 +1494,14 @@ static void sched_ttwu_pending(void)
 
 void scheduler_ipi(void)
 {
+	/*
+	 * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
+	 * TIF_NEED_RESCHED remotely (for the first time) will also send
+	 * this IPI.
+	 */
+	if (tif_need_resched())
+		set_preempt_need_resched();
+
 	if (llist_empty(&this_rq()->wake_list)
 			&& !tick_nohz_full_cpu(smp_processor_id())
 			&& !got_nohz_idle_kick())
@@ -1513,7 +1619,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	if (p->sched_class->task_waking)
 		p->sched_class->task_waking(p);
 
-	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
 		set_task_cpu(p, cpu);
@@ -1595,7 +1701,7 @@ int wake_up_state(struct task_struct *p, unsigned int state)
  *
  * __sched_fork() is basic setup used by init_idle() too:
  */
-static void __sched_fork(struct task_struct *p)
+static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	p->on_rq			= 0;
 
@@ -1619,16 +1725,24 @@ static void __sched_fork(struct task_struct *p)
 
 #ifdef CONFIG_NUMA_BALANCING
 	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
-		p->mm->numa_next_scan = jiffies;
-		p->mm->numa_next_reset = jiffies;
+		p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
 		p->mm->numa_scan_seq = 0;
 	}
 
+	if (clone_flags & CLONE_VM)
+		p->numa_preferred_nid = current->numa_preferred_nid;
+	else
+		p->numa_preferred_nid = -1;
+
 	p->node_stamp = 0ULL;
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
-	p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
+	p->numa_faults = NULL;
+	p->numa_faults_buffer = NULL;
+
+	INIT_LIST_HEAD(&p->numa_entry);
+	p->numa_group = NULL;
 #endif /* CONFIG_NUMA_BALANCING */
 }
 
@@ -1654,12 +1768,12 @@ void set_numabalancing_state(bool enabled)
 /*
  * fork()/clone()-time setup:
  */
-void sched_fork(struct task_struct *p)
+void sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long flags;
 	int cpu = get_cpu();
 
-	__sched_fork(p);
+	__sched_fork(clone_flags, p);
 	/*
 	 * We mark the process as running here. This guarantees that
 	 * nobody will actually run it, and a signal or other external
@@ -1717,10 +1831,7 @@ void sched_fork(struct task_struct *p)
 #if defined(CONFIG_SMP)
 	p->on_cpu = 0;
 #endif
-#ifdef CONFIG_PREEMPT_COUNT
-	/* Want to start with kernel preemption disabled. */
-	task_thread_info(p)->preempt_count = 1;
-#endif
+	init_task_preempt_count(p);
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 #endif
@@ -1747,7 +1858,7 @@ void wake_up_new_task(struct task_struct *p)
 	 *  - cpus_allowed can change in the fork path
 	 *  - any previously selected cpu might disappear through hotplug
 	 */
-	set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0));
+	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 
 	/* Initialize new task's runnable average */
@@ -1838,7 +1949,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next)
 {
 	trace_sched_switch(prev, next);
-	sched_info_switch(prev, next);
+	sched_info_switch(rq, prev, next);
 	perf_event_task_sched_out(prev, next);
 	fire_sched_out_preempt_notifiers(prev, next);
 	prepare_lock_switch(rq, next);
@@ -1890,6 +2001,8 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	if (mm)
 		mmdrop(mm);
 	if (unlikely(prev_state == TASK_DEAD)) {
+		task_numa_free(prev);
+
 		/*
 		 * Remove function-return probe instances associated with this
 		 * task and put them back on the free list.
@@ -2073,7 +2186,7 @@ void sched_exec(void)
 	int dest_cpu;
 
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
+	dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0);
 	if (dest_cpu == smp_processor_id())
 		goto unlock;
 
@@ -2215,7 +2328,7 @@ notrace unsigned long get_parent_ip(unsigned long addr)
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
 				defined(CONFIG_PREEMPT_TRACER))
 
-void __kprobes add_preempt_count(int val)
+void __kprobes preempt_count_add(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
@@ -2224,7 +2337,7 @@ void __kprobes add_preempt_count(int val)
 	if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
 		return;
 #endif
-	preempt_count() += val;
+	__preempt_count_add(val);
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
 	 * Spinlock count overflowing soon?
@@ -2235,9 +2348,9 @@ void __kprobes add_preempt_count(int val)
 	if (preempt_count() == val)
 		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
-EXPORT_SYMBOL(add_preempt_count);
+EXPORT_SYMBOL(preempt_count_add);
 
-void __kprobes sub_preempt_count(int val)