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

Pull scheduler changes from Ingo Molnar:
 "Bigger changes:

   - sched/idle restructuring: they are WIP preparation for deeper
     integration between the scheduler and idle state selection, by
     Nicolas Pitre.

   - add NUMA scheduling pseudo-interleaving, by Rik van Riel.

   - optimize cgroup context switches, by Peter Zijlstra.

   - RT scheduling enhancements, by Thomas Gleixner.

  The rest is smaller changes, non-urgnt fixes and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (68 commits)
  sched: Clean up the task_hot() function
  sched: Remove double calculation in fix_small_imbalance()
  sched: Fix broken setscheduler()
  sparc64, sched: Remove unused sparc64_multi_core
  sched: Remove unused mc_capable() and smt_capable()
  sched/numa: Move task_numa_free() to __put_task_struct()
  sched/fair: Fix endless loop in idle_balance()
  sched/core: Fix endless loop in pick_next_task()
  sched/fair: Push down check for high priority class task into idle_balance()
  sched/rt: Fix picking RT and DL tasks from empty queue
  trace: Replace hardcoding of 19 with MAX_NICE
  sched: Guarantee task priority in pick_next_task()
  sched/idle: Remove stale old file
  sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED
  cpuidle/arm64: Remove redundant cpuidle_idle_call()
  cpuidle/powernv: Remove redundant cpuidle_idle_call()
  sched, nohz: Exclude isolated cores from load balancing
  sched: Fix select_task_rq_fair() description comments
  workqueue: Replace hardcoding of -20 and 19 with MIN_NICE and MAX_NICE
  sys: Replace hardcoding of -20 and 19 with MIN_NICE and MAX_NICE
  ...

21 files changed, 788 insertions, 350 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 5c0e7666811d..4fd847488b76 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -22,7 +22,6 @@ obj-y += sched/
 obj-y += locking/
 obj-y += power/
 obj-y += printk/
-obj-y += cpu/
 obj-y += irq/
 obj-y += rcu/
 
diff --git a/kernel/cpu/Makefile b/kernel/cpu/Makefile
deleted file mode 100644
index 59ab052ef7a0..000000000000
--- a/kernel/cpu/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-y	= idle.o
diff --git a/kernel/fork.c b/kernel/fork.c
index a17621c6cd42..332688e5e7b4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -237,6 +237,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(atomic_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	task_numa_free(tsk);
 	security_task_free(tsk);
 	exit_creds(tsk);
 	delayacct_tsk_free(tsk);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2e960a2bab81..aa4dff04b594 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -213,6 +213,18 @@ struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 }
 
 /*
+ * Called by sched_setscheduler() to check whether the priority change
+ * is overruled by a possible priority boosting.
+ */
+int rt_mutex_check_prio(struct task_struct *task, int newprio)
+{
+	if (!task_has_pi_waiters(task))
+		return 0;
+
+	return task_top_pi_waiter(task)->task->prio <= newprio;
+}
+
+/*
  * Adjust the priority of a task, after its pi_waiters got modified.
  *
  * This can be both boosting and unboosting. task->pi_lock must be held.
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index f59d48597dde..bd30bc61bc05 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -696,7 +696,7 @@ rcu_torture_writer(void *arg)
 	static DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
-	set_user_nice(current, 19);
+	set_user_nice(current, MAX_NICE);
 
 	do {
 		schedule_timeout_uninterruptible(1);
@@ -759,7 +759,7 @@ rcu_torture_fakewriter(void *arg)
 	DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("rcu_torture_fakewriter task started");
-	set_user_nice(current, 19);
+	set_user_nice(current, MAX_NICE);
 
 	do {
 		schedule_timeout_uninterruptible(1 + torture_random(&rand)%10);
@@ -872,7 +872,7 @@ rcu_torture_reader(void *arg)
 	unsigned long long ts;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_reader task started");
-	set_user_nice(current, 19);
+	set_user_nice(current, MAX_NICE);
 	if (irqreader && cur_ops->irq_capable)
 		setup_timer_on_stack(&t, rcu_torture_timer, 0);
 
@@ -1161,7 +1161,7 @@ static int rcu_torture_barrier_cbs(void *arg)
 
 	init_rcu_head_on_stack(&rcu);
 	VERBOSE_TOROUT_STRING("rcu_torture_barrier_cbs task started");
-	set_user_nice(current, 19);
+	set_user_nice(current, MAX_NICE);
 	do {
 		wait_event(barrier_cbs_wq[myid],
 			   (newphase =
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 9a95c8c2af2a..ab32b7b0db5c 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -13,7 +13,7 @@ endif
 
 obj-y += core.o proc.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
-obj-y += wait.o completion.o
+obj-y += wait.o completion.o idle.o
 obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 4a073539c58e..e73efba98301 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -203,7 +203,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 	struct autogroup *ag;
 	int err;
 
-	if (nice < -20 || nice > 19)
+	if (nice < MIN_NICE || nice > MAX_NICE)
 		return -EINVAL;
 
 	err = security_task_setnice(current, nice);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f5c6635b806c..ae365aaa8181 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1745,8 +1745,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 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;
+	p->numa_faults_memory = NULL;
+	p->numa_faults_buffer_memory = NULL;
+	p->last_task_numa_placement = 0;
+	p->last_sum_exec_runtime = 0;
 
 	INIT_LIST_HEAD(&p->numa_entry);
 	p->numa_group = NULL;
@@ -2149,8 +2151,6 @@ 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);
-
 		if (prev->sched_class->task_dead)
 			prev->sched_class->task_dead(prev);
 
@@ -2167,13 +2167,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 
 #ifdef CONFIG_SMP
 
-/* assumes rq->lock is held */
-static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
-{
-	if (prev->sched_class->pre_schedule)
-		prev->sched_class->pre_schedule(rq, prev);
-}
-
 /* rq->lock is NOT held, but preemption is disabled */
 static inline void post_schedule(struct rq *rq)
 {
@@ -2191,10 +2184,6 @@ static inline void post_schedule(struct rq *rq)
 
 #else
 
-static inline void pre_schedule(struct rq *rq, struct task_struct *p)
-{
-}
-
 static inline void post_schedule(struct rq *rq)
 {
 }
@@ -2510,8 +2499,13 @@ void __kprobes preempt_count_add(int val)
 	DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
 				PREEMPT_MASK - 10);
 #endif
-	if (preempt_count() == val)
-		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+	if (preempt_count() == val) {
+		unsigned long ip = get_parent_ip(CALLER_ADDR1);
+#ifdef CONFIG_DEBUG_PREEMPT
+		current->preempt_disable_ip = ip;
+#endif
+		trace_preempt_off(CALLER_ADDR0, ip);
+	}
 }
 EXPORT_SYMBOL(preempt_count_add);
 
@@ -2554,6 +2548,13 @@ static noinline void __schedule_bug(struct task_struct *prev)
 	print_modules();
 	if (irqs_disabled())
 		print_irqtrace_events(prev);
+#ifdef CONFIG_DEBUG_PREEMPT
+	if (in_atomic_preempt_off()) {
+		pr_err("Preemption disabled at:");
+		print_ip_sym(current->preempt_disable_ip);
+		pr_cont("\n");
+	}
+#endif
 	dump_stack();
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
@@ -2577,36 +2578,34 @@ static inline void schedule_debug(struct task_struct *prev)
 	schedstat_inc(this_rq(), sched_count);
 }
 
-static void put_prev_task(struct rq *rq, struct task_struct *prev)
-{
-	if (prev->on_rq || rq->skip_clock_update < 0)
-		update_rq_clock(rq);
-	prev->sched_class->put_prev_task(rq, prev);
-}
-
 /*
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-pick_next_task(struct rq *rq)
+pick_next_task(struct rq *rq, struct task_struct *prev)
 {
-	const struct sched_class *class;
+	const struct sched_class *class = &fair_sched_class;
 	struct task_struct *p;
 
 	/*
 	 * Optimization: we know that if all tasks are in
 	 * the fair class we can call that function directly:
 	 */
-	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
-		p = fair_sched_class.pick_next_task(rq);
-		if (likely(p))
+	if (likely(prev->sched_class == class &&
+		   rq->nr_running == rq->cfs.h_nr_running)) {
+		p = fair_sched_class.pick_next_task(rq, prev);
+		if (likely(p && p != RETRY_TASK))
 			return p;
 	}
 
+again:
 	for_each_class(class) {
-		p = class->pick_next_task(rq);
-		if (p)
+		p = class->pick_next_task(rq, prev);
+		if (p) {
+			if (unlikely(p == RETRY_TASK))
+				goto again;
 			return p;
+		}
 	}
 
 	BUG(); /* the idle class will always have a runnable task */
@@ -2700,13 +2699,10 @@ need_resched:
 		switch_count = &prev->nvcsw;
 	}
 
-	pre_schedule(rq, prev);
-
-	if (unlikely(!rq->nr_running))
-		idle_balance(cpu, rq);
+	if (prev->on_rq || rq->skip_clock_update < 0)
+		update_rq_clock(rq);
 
-	put_prev_task(rq, prev);
-	next = pick_next_task(rq);
+	next = pick_next_task(rq, prev);
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
 	rq->skip_clock_update = 0;
@@ -2908,7 +2904,8 @@ EXPORT_SYMBOL(sleep_on_timeout);
  * This function changes the 'effective' priority of a task. It does
  * not touch ->normal_prio like __setscheduler().
  *
- * Used by the rt_mutex code to implement priority inheritance logic.
+ * Used by the rt_mutex code to implement priority inheritance
+ * logic. Call site only calls if the priority of the task changed.
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
@@ -2998,7 +2995,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	unsigned long flags;
 	struct rq *rq;
 
-	if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
+	if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
 		return;
 	/*
 	 * We have to be careful, if called from sys_setpriority(),
@@ -3076,11 +3073,11 @@ SYSCALL_DEFINE1(nice, int, increment)
 	if (increment > 40)
 		increment = 40;
 
-	nice = TASK_NICE(current) + increment;
-	if (nice < -20)
-		nice = -20;
-	if (nice > 19)
-		nice = 19;
+	nice = task_nice(current) + increment;
+	if (nice < MIN_NICE)
+		nice = MIN_NICE;
+	if (nice > MAX_NICE)
+		nice = MAX_NICE;
 
 	if (increment < 0 && !can_nice(current, nice))
 		return -EPERM;
@@ -3109,18 +3106,6 @@ int task_prio(const struct task_struct *p)
 }
 
 /**
- * task_nice - return the nice value of a given task.
- * @p: the task in question.
- *
- * Return: The nice value [ -20 ... 0 ... 19 ].
- */
-int task_nice(const struct task_struct *p)
-{
-	return TASK_NICE(p);
-}
-EXPORT_SYMBOL(task_nice);
-
-/**
  * idle_cpu - is a given cpu idle currently?
  * @cpu: the processor in question.
  *
@@ -3189,9 +3174,8 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	dl_se->dl_new = 1;
 }
 
-/* Actually do priority change: must hold pi & rq lock. */
-static void __setscheduler(struct rq *rq, struct task_struct *p,
-			   const struct sched_attr *attr)
+static void __setscheduler_params(struct task_struct *p,
+		const struct sched_attr *attr)
 {
 	int policy = attr->sched_policy;
 
@@ -3211,9 +3195,21 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
 	 * getparam()/getattr() don't report silly values for !rt tasks.
 	 */
 	p->rt_priority = attr->sched_priority;
-
 	p->normal_prio = normal_prio(p);
-	p->prio = rt_mutex_getprio(p);
+	set_load_weight(p);
+}
+
+/* Actually do priority change: must hold pi & rq lock. */
+static void __setscheduler(struct rq *rq, struct task_struct *p,
+			   const struct sched_attr *attr)
+{
+	__setscheduler_params(p, attr);
+
+	/*
+	 * If we get here, there was no pi waiters boosting the
+	 * task. It is safe to use the normal prio.
+	 */
+	p->prio = normal_prio(p);
 
 	if (dl_prio(p->prio))
 		p->sched_class = &dl_sched_class;
@@ -3221,8 +3217,6 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
 		p->sched_class = &rt_sched_class;
 	else
 		p->sched_class = &fair_sched_class;
-
-	set_load_weight(p);
 }
 
 static void
@@ -3275,6 +3269,8 @@ static int __sched_setscheduler(struct task_struct *p,
 				const struct sched_attr *attr,
 				bool user)
 {
+	int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
+		      MAX_RT_PRIO - 1 - attr->sched_priority;
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
 	int policy = attr->sched_policy;
 	unsigned long flags;
@@ -3319,7 +3315,7 @@ recheck:
 	 */
 	if (user && !capable(CAP_SYS_NICE)) {
 		if (fair_policy(policy)) {
-			if (attr->sched_nice < TASK_NICE(p) &&
+			if (attr->sched_nice < task_nice(p) &&
 			    !can_nice(p, attr->sched_nice))
 				return -EPERM;
 		}
@@ -3352,7 +3348,7 @@ recheck:
 		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
 		 */
 		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
-			if (!can_nice(p, TASK_NICE(p)))
+			if (!can_nice(p, task_nice(p)))
 				return -EPERM;
 		}
 
@@ -3389,16 +3385,18 @@ recheck:
 	}
 
 	/*
-	 * If not changing anything there's no need to proceed further:
+	 * If not changing anything there's no need to proceed further,
+	 * but store a possible modification of reset_on_fork.
 	 */
 	if (unlikely(policy == p->policy)) {
-		if (fair_policy(policy) && attr->sched_nice != TASK_NICE(p))
+		if (fair_policy(policy) && attr->sched_nice != task_nice(p))
 			goto change;
 		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
 			goto change;
 		if (dl_policy(policy))
 			goto change;
 
+		p->sched_reset_on_fork = reset_on_fork;
 		task_rq_unlock(rq, p, &flags);
 		return 0;
 	}
@@ -3452,6 +3450,24 @@ change:
 		return -EBUSY;
 	}
 
+	p->sched_reset_on_fork = reset_on_fork;
+	oldprio = p->prio;
+
+	/*
+	 * Special case for priority boosted tasks.
+	 *
+	 * If the new priority is lower or equal (user space view)
+	 * than the current (boosted) priority, we just store the new
+	 * normal parameters and do not touch the scheduler class and
+	 * the runqueue. This will be done when the task deboost
+	 * itself.
+	 */
+	if (rt_mutex_check_prio(p, newprio)) {
+		__setscheduler_params(p, attr);
+		task_rq_unlock(rq, p, &flags);
+		return 0;
+	}
+
 	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
@@ -3459,16 +3475,18 @@ change:
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
-	p->sched_reset_on_fork = reset_on_fork;
-
-	oldprio = p->prio;
 	prev_class = p->sched_class;
 	__setscheduler(rq, p, attr);
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq)
-		enqueue_task(rq, p, 0);
+	if (on_rq) {
+		/*
+		 * We enqueue to tail when the priority of a task is
+		 * increased (user space view).
+		 */
+		enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0);
+	}
 
 	check_class_changed(rq, p, prev_class, oldprio);
 	task_rq_unlock(rq, p, &flags);
@@ -3624,7 +3642,7 @@ static int sched_copy_attr(struct sched_attr __user *uattr,
 	 * XXX: do we want to be lenient like existing syscalls; or do we want
 	 * to be strict and return an error on out-of-bounds values?
 	 */
-	attr->sched_nice = clamp(attr->sched_nice, -20, 19);
+	attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);
 
 out:
 	return ret;
@@ -3845,7 +3863,7 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	else if (task_has_rt_policy(p))
 		attr.sched_priority = p->rt_priority;
 	else
-		attr.sched_nice = TASK_NICE(p);
+		attr.sched_nice = task_nice(p);
 
 	rcu_read_unlock();
 
@@ -4483,6 +4501,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	rcu_read_unlock();
 
 	rq->curr = rq->idle = idle;
+	idle->on_rq = 1;
 #if defined(CONFIG_SMP)
 	idle->on_cpu = 1;
 #endif
@@ -4721,6 +4740,22 @@ static void calc_load_migrate(struct rq *rq)
 		atomic_long_add(delta, &calc_load_tasks);
 }
 
+static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
+{
+}
+
+static const struct sched_class fake_sched_class = {
+	.put_prev_task = put_prev_task_fake,
+};
+
+static struct task_struct fake_task = {
+	/*
+	 * Avoid pull_{rt,dl}_task()
+	 */
+	.prio = MAX_PRIO + 1,
+	.sched_class = &fake_sched_class,
+};
+
 /*
  * Migrate all tasks from the rq, sleeping tasks will be migrated by
  * try_to_wake_up()->select_task_rq().
@@ -4761,7 +4796,7 @@ static void migrate_tasks(unsigned int dead_cpu)
 		if (rq->nr_running == 1)
 			break;
 
-		next = pick_next_task(rq);
+		next = pick_next_task(rq, &fake_task);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 
@@ -4851,7 +4886,7 @@ set_table_entry(struct ctl_table *entry,
 static struct ctl_table *
 sd_alloc_ctl_domain_table(struct sched_domain *sd)
 {
-	struct ctl_table *table = sd_alloc_ctl_entry(13);
+	struct ctl_table *table = sd_alloc_ctl_entry(14);
 
 	if (table == NULL)
 		return NULL;
@@ -4879,9 +4914,12 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
 		sizeof(int), 0644, proc_dointvec_minmax, false);
 	set_table_entry(&table[10], "flags", &sd->flags,
 		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[11], "name", sd->name,
+	set_table_entry(&table[11], "max_newidle_lb_cost",
+		&sd->max_newidle_lb_cost,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[12], "name", sd->name,
 		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
-	/* &table[12] is terminator */
+	/* &table[13] is terminator */
 
 	return table;
 }
@@ -6858,7 +6896,6 @@ void __init sched_init(void)
 
 		rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
 #ifdef CONFIG_RT_GROUP_SCHED
-		INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
 		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
 #endif
 
@@ -6947,7 +6984,8 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 	static unsigned long prev_jiffy;	/* ratelimiting */
 
 	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
-	if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
+	     !is_idle_task(current)) ||
 	    system_state != SYSTEM_RUNNING || oops_in_progress)
 		return;
 	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
@@ -6965,6 +7003,13 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 	debug_show_held_locks(current);
 	if (irqs_disabled())
 		print_irqtrace_events(current);
+#ifdef CONFIG_DEBUG_PREEMPT
+	if (!preempt_count_equals(preempt_offset)) {
+		pr_err("Preemption disabled at:");
+		print_ip_sym(current->preempt_disable_ip);
+		pr_cont("\n");
+	}
+#endif
 	dump_stack();
 }
 EXPORT_SYMBOL(__might_sleep);
@@ -7018,7 +7063,7 @@ void normalize_rt_tasks(void)
 			 * Renice negative nice level userspace
 			 * tasks back to 0:
 			 */
-			if (TASK_NICE(p) < 0 && p->mm)
+			if (task_nice(p) < 0 && p->mm)
 				set_user_nice(p, 0);
 			continue;
 		}
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 99947919e30b..58624a65f124 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -142,7 +142,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
 	p->utimescaled += cputime_scaled;
 	account_group_user_time(p, cputime);
 
-	index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
+	index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
 
 	/* Add user time to cpustat. */
 	task_group_account_field(p, index, (__force u64) cputime);
@@ -169,7 +169,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
 	p->gtime += cputime;
 
 	/* Add guest time to cpustat. */
-	if (TASK_NICE(p) > 0) {
+	if (task_nice(p) > 0) {
 		cpustat[CPUTIME_NICE] += (__force u64) cputime;
 		cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
 	} else {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6e79b3faa4cd..27ef40925525 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -210,6 +210,16 @@ static inline int has_pushable_dl_tasks(struct rq *rq)
 
 static int push_dl_task(struct rq *rq);
 
+static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
+{
+	return dl_task(prev);
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+	rq->post_schedule = has_pushable_dl_tasks(rq);
+}
+
 #else
 
 static inline
@@ -232,6 +242,19 @@ void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 }
 
+static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
+{
+	return false;
+}
+
+static inline int pull_dl_task(struct rq *rq)
+{
+	return 0;
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+}
 #endif /* CONFIG_SMP */
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
@@ -586,8 +609,8 @@ static void update_curr_dl(struct rq *rq)
 	 * approach need further study.
 	 */
 	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
-	if (unlikely((s64)delta_exec < 0))
-		delta_exec = 0;
+	if (unlikely((s64)delta_exec <= 0))
+		return;
 
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
@@ -942,6 +965,8 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
 	resched_task(rq->curr);
 }
 
+static int pull_dl_task(struct rq *this_rq);
+
 #endif /* CONFIG_SMP */
 
 /*
@@ -988,7 +1013,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
 	return rb_entry(left, struct sched_dl_entity, rb_node);
 }
 
-struct task_struct *pick_next_task_dl(struct rq *rq)
+struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
 {
 	struct sched_dl_entity *dl_se;
 	struct task_struct *p;
@@ -996,9 +1021,20 @@ struct task_struct *pick_next_task_dl(struct rq *rq)
 
 	dl_rq = &rq->dl;
 
+	if (need_pull_dl_task(rq, prev))
+		pull_dl_task(rq);
+	/*
+	 * When prev is DL, we may throttle it in put_prev_task().
+	 * So, we update time before we check for dl_nr_running.
+	 */
+	if (prev->sched_class == &dl_sched_class)
+		update_curr_dl(rq);
+
 	if (unlikely(!dl_rq->dl_nr_running))
 		return NULL;
 
+	put_prev_task(rq, prev);
+
 	dl_se = pick_next_dl_entity(rq, dl_rq);
 	BUG_ON(!dl_se);
 
@@ -1013,9 +1049,7 @@ struct task_struct *pick_next_task_dl(struct rq *rq)
 		start_hrtick_dl(rq, p);
 #endif
 
-#ifdef CONFIG_SMP
-	rq->post_schedule = has_pushable_dl_tasks(rq);
-#endif /* CONFIG_SMP */
+	set_post_schedule(rq);
 
 	return p;
 }
@@ -1424,13 +1458,6 @@ skip:
 	return ret;
 }
 
-static void pre_schedule_dl(struct rq *rq, struct task_struct *prev)
-{
-	/* Try to pull other tasks here */
-	if (dl_task(prev))
-		pull_dl_task(rq);
-}
-
 static void post_schedule_dl(struct rq *rq)
 {
 	push_dl_tasks(rq);
@@ -1558,7 +1585,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 	if (unlikely(p->dl.dl_throttled))
 		return;
 
-	if (p->on_rq || rq->curr != p) {
+	if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
 			/* Only reschedule if pushing failed */
@@ -1623,7 +1650,6 @@ const struct sched_class dl_sched_class = {
 	.set_cpus_allowed       = set_cpus_allowed_dl,
 	.rq_online              = rq_online_dl,
 	.rq_offline             = rq_offline_dl,
-	.pre_schedule		= pre_schedule_dl,
 	.post_schedule		= post_schedule_dl,
 	.task_woken		= task_woken_dl,
 #endif
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index dd52e7ffb10e..f3344c31632a 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -321,6 +321,7 @@ do {									\
 	P(sched_goidle);
 #ifdef CONFIG_SMP
 	P64(avg_idle);
+	P64(max_idle_balance_cost);
 #endif
 
 	P(ttwu_count);
@@ -533,15 +534,15 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
 			unsigned long nr_faults = -1;
 			int cpu_current, home_node;
 
-			if (p->numa_faults)
-				nr_faults = p->numa_faults[2*node + i];
+			if (p->numa_faults_memory)
+				nr_faults = p->numa_faults_memory[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",
+			SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n",
 				i, node, cpu_current, home_node, nr_faults);
 		}
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9b4c4f320130..7e9bd0b1fa9e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -322,13 +322,13 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
-static inline int
+static inline struct cfs_rq *
 is_same_group(struct sched_entity *se, struct sched_entity *pse)
 {
 	if (se->cfs_rq == pse->cfs_rq)
-		return 1;
+		return se->cfs_rq;
 
-	return 0;
+	return NULL;
 }
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
@@ -336,17 +336,6 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
 	return se->parent;
 }
 
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
-{
-	int depth = 0;
-
-	for_each_sched_entity(se)
-		depth++;
-
-	return depth;
-}
-
 static void
 find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 {
@@ -360,8 +349,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 	 */
 
 	/* First walk up until both entities are at same depth */
-	se_depth = depth_se(*se);
-	pse_depth = depth_se(*pse);
+	se_depth = (*se)->depth;
+	pse_depth = (*pse)->depth;
 
 	while (se_depth > pse_depth) {
 		se_depth--;
@@ -426,12 +415,6 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 #define for_each_leaf_cfs_rq(rq, cfs_rq) \
 		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
 
-static inline int
-is_same_group(struct sched_entity *se, struct sched_entity *pse)
-{
-	return 1;
-}
-
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
 {
 	return NULL;
@@ -819,14 +802,6 @@ 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;
 
-/*
- * 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;
@@ -893,10 +868,26 @@ struct numa_group {
 	struct list_head task_list;
 
 	struct rcu_head rcu;
+	nodemask_t active_nodes;
 	unsigned long total_faults;
+	/*
+	 * Faults_cpu is used to decide whether memory should move
+	 * towards the CPU. As a consequence, these stats are weighted
+	 * more by CPU use than by memory faults.
+	 */
+	unsigned long *faults_cpu;
 	unsigned long faults[0];
 };
 
+/* Shared or private faults. */
+#define NR_NUMA_HINT_FAULT_TYPES 2
+
+/* Memory and CPU locality */
+#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2)
+
+/* Averaged statistics, and temporary buffers. */
+#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2)
+
 pid_t task_numa_group_id(struct task_struct *p)
 {
 	return p->numa_group ? p->numa_group->gid : 0;
@@ -904,16 +895,16 @@ pid_t task_numa_group_id(struct task_struct *p)
 
 static inline int task_faults_idx(int nid, int priv)
 {
-	return 2 * nid + priv;
+	return NR_NUMA_HINT_FAULT_TYPES * nid + priv;
 }
 
 static inline unsigned long task_faults(struct task_struct *p, int nid)
 {
-	if (!p->numa_faults)
+	if (!p->numa_faults_memory)
 		return 0;
 
-	return p->numa_faults[task_faults_idx(nid, 0)] +
-		p->numa_faults[task_faults_idx(nid, 1)];
+	return p->numa_faults_memory[task_faults_idx(nid, 0)] +
+		p->numa_faults_memory[task_faults_idx(nid, 1)];
 }
 
 static inline unsigned long group_faults(struct task_struct *p, int nid)
@@ -925,6 +916,12 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
 		p->numa_group->faults[task_faults_idx(nid, 1)];
 }
 
+static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
+{
+	return group->faults_cpu[task_faults_idx(nid, 0)] +
+		group->faults_cpu[task_faults_idx(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
@@ -935,7 +932,7 @@ static inline unsigned long task_weight(struct task_struct *p, int nid)
 {
 	unsigned long total_faults;
 
-	if (!p->numa_faults)
+	if (!p->numa_faults_memory)
 		return 0;
 
 	total_faults = p->total_numa_faults;
@@ -954,6 +951,69 @@ static inline unsigned long group_weight(struct task_struct *p, int nid)
 	return 1000 * group_faults(p, nid) / p->numa_group->total_faults;
 }
 
+bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
+				int src_nid, int dst_cpu)
+{
+	struct numa_group *ng = p->numa_group;
+	int dst_nid = cpu_to_node(dst_cpu);
+	int last_cpupid, this_cpupid;
+
+	this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
+
+	/*
+	 * Multi-stage node selection is used in conjunction with a periodic
+	 * migration fault to build a temporal task<->page relation. By using
+	 * a two-stage filter we remove short/unlikely relations.
+	 *
+	 * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate
+	 * a task's usage of a particular page (n_p) per total usage of this
+	 * page (n_t) (in a given time-span) to a probability.
+	 *
+	 * Our periodic faults will sample this probability and getting the
+	 * same result twice in a row, given these samples are fully
+	 * independent, is then given by P(n)^2, provided our sample period
+	 * is sufficiently short compared to the usage pattern.
+	 *
+	 * This quadric squishes small probabilities, making it less likely we
+	 * act on an unlikely task<->page relation.
+	 */
+	last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+	if (!cpupid_pid_unset(last_cpupid) &&
+				cpupid_to_nid(last_cpupid) != dst_nid)
+		return false;
+
+	/* Always allow migrate on private faults */
+	if (cpupid_match_pid(p, last_cpupid))
+		return true;
+
+	/* A shared fault, but p->numa_group has not been set up yet. */
+	if (!ng)
+		return true;
+
+	/*
+	 * Do not migrate if the destination is not a node that
+	 * is actively used by this numa group.
+	 */
+	if (!node_isset(dst_nid, ng->active_nodes))
+		return false;
+
+	/*
+	 * Source is a node that is not actively used by this
+	 * numa group, while the destination is. Migrate.
+	 */
+	if (!node_isset(src_nid, ng->active_nodes))
+		return true;
+
+	/*
+	 * Both source and destination are nodes in active
+	 * use by this numa group. Maximize memory bandwidth
+	 * by migrating from more heavily used groups, to less
+	 * heavily used ones, spreading the load around.
+	 * Use a 1/4 hysteresis to avoid spurious page movement.
+	 */
+	return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4);
+}
+
 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);
@@ -1267,7 +1327,7 @@ static int task_numa_migrate(struct task_struct *p)
 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))
+	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory))
 		return;
 
 	/* Periodically retry migrating the task to the preferred node */
@@ -1282,6 +1342,38 @@ static void numa_migrate_preferred(struct task_struct *p)
 }
 
 /*
+ * Find the nodes on which the workload is actively running. We do this by
+ * tracking the nodes from which NUMA hinting faults are triggered. This can
+ * be different from the set of nodes where the workload's memory is currently
+ * located.
+ *
+ * The bitmask is used to make smarter decisions on when to do NUMA page
+ * migrations, To prevent flip-flopping, and excessive page migrations, nodes
+ * are added when they cause over 6/16 of the maximum number of faults, but
+ * only removed when they drop below 3/16.
+ */
+static void update_numa_active_node_mask(struct numa_group *numa_group)
+{
+	unsigned long faults, max_faults = 0;
+	int nid;
+
+	for_each_online_node(nid) {
+		faults = group_faults_cpu(numa_group, nid);
+		if (faults > max_faults)
+			max_faults = faults;
+	}
+
+	for_each_online_node(nid) {
+		faults = group_faults_cpu(numa_group, nid);
+		if (!node_isset(nid, numa_group->active_nodes)) {
+			if (faults > max_faults * 6 / 16)
+				node_set(nid, numa_group->active_nodes);
+		} else if (faults < max_faults * 3 / 16)
+			node_clear(nid, numa_group->active_nodes);
+	}
+}
+
+/*
  * 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
@@ -1355,11 +1447,41 @@ static void update_task_scan_period(struct task_struct *p,
 	memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 }
 
+/*
+ * Get the fraction of time the task has been running since the last
+ * NUMA placement cycle. The scheduler keeps similar statistics, but
+ * decays those on a 32ms period, which is orders of magnitude off
+ * from the dozens-of-seconds NUMA balancing period. Use the scheduler
+ * stats only if the task is so new there are no NUMA statistics yet.
+ */
+static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
+{
+	u64 runtime, delta, now;
+	/* Use the start of this time slice to avoid calculations. */
+	now = p->se.exec_start;
+	runtime = p->se.sum_exec_runtime;
+
+	if (p->last_task_numa_placement) {
+		delta = runtime - p->last_sum_exec_runtime;
+		*period = now - p->last_task_numa_placement;
+	} else {
+		delta = p->se.avg.runnable_avg_sum;
+		*period = p->se.avg.runnable_avg_period;
+	}
+
+	p->last_sum_exec_runtime = runtime;
+	p->last_task_numa_placement = now;
+
+	return delta;
+}
+
 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 };
+	unsigned long total_faults;
+	u64 runtime, period;
 	spinlock_t *group_lock = NULL;
 
 	seq = ACCESS_ONCE(p->mm->numa_scan_seq);
@@ -1368,6 +1490,10 @@ static void task_numa_placement(struct task_struct *p)
 	p->numa_scan_seq = seq;
 	p->numa_scan_period_max = task_scan_max(p);
 
+	total_faults = p->numa_faults_locality[0] +
+		       p->numa_faults_locality[1];
+	runtime = numa_get_avg_runtime(p, &period);
+
 	/* If the task is part of a group prevent parallel updates to group stats */
 	if (p->numa_group) {
 		group_lock = &p->numa_group->lock;
@@ -1379,24 +1505,37 @@ static void task_numa_placement(struct task_struct *p)
 		unsigned long faults = 0, group_faults = 0;
 		int priv, i;
 
-		for (priv = 0; priv < 2; priv++) {
-			long diff;
+		for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
+			long diff, f_diff, f_weight;
 
 			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;
+			diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2;
+			fault_types[priv] += p->numa_faults_buffer_memory[i];
+			p->numa_faults_buffer_memory[i] = 0;
 
-			faults += p->numa_faults[i];
-			diff += p->numa_faults[i];
+			/*
+			 * Normalize the faults_from, so all tasks in a group
+			 * count according to CPU use, instead of by the raw
+			 * number of faults. Tasks with little runtime have
+			 * little over-all impact on throughput, and thus their
+			 * faults are less important.
+			 */
+			f_weight = div64_u64(runtime << 16, period + 1);
+			f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) /
+				   (total_faults + 1);
+			f_diff = f_weight - p->numa_faults_cpu[i] / 2;
+			p->numa_faults_buffer_cpu[i] = 0;
+
+			p->numa_faults_memory[i] += diff;
+			p->numa_faults_cpu[i] += f_diff;
+			faults += p->numa_faults_memory[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->faults_cpu[i] += f_diff;
 				p->numa_group->total_faults += diff;
 				group_faults += p->numa_group->faults[i];
 			}
@@ -1416,6 +1555,7 @@ static void task_numa_placement(struct task_struct *p)
 	update_task_scan_period(p, fault_types[0], fault_types[1]);
 
 	if (p->numa_group) {
+		update_numa_active_node_mask(p->numa_group);
 		/*
 		 * If the preferred task and group nids are different,
 		 * iterate over the nodes again to find the best place.
@@ -1465,7 +1605,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 
 	if (unlikely(!p->numa_group)) {
 		unsigned int size = sizeof(struct numa_group) +
-				    2*nr_node_ids*sizeof(unsigned long);
+				    4*nr_node_ids*sizeof(unsigned long);
 
 		grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
 		if (!grp)
@@ -1475,9 +1615,14 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 		spin_lock_init(&grp->lock);
 		INIT_LIST_HEAD(&grp->task_list);
 		grp->gid = p->pid;
+		/* Second half of the array tracks nids where faults happen */
+		grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
+						nr_node_ids;
+
+		node_set(task_node(current), grp->active_nodes);
 
-		for (i = 0; i < 2*nr_node_ids; i++)
-			grp->faults[i] = p->numa_faults[i];
+		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+			grp->faults[i] = p->numa_faults_memory[i];
 
 		grp->total_faults = p->total_numa_faults;
 
@@ -1534,9 +1679,9 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 
 	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];
+	for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
+		my_grp->faults[i] -= p->numa_faults_memory[i];
+		grp->faults[i] += p->numa_faults_memory[i];
 	}
 	my_grp->total_faults -= p->total_numa_faults;
 	grp->total_faults += p->total_numa_faults;
@@ -1562,12 +1707,12 @@ void task_numa_free(struct task_struct *p)
 {
 	struct numa_group *grp = p->numa_group;
 	int i;
-	void *numa_faults = p->numa_faults;
+	void *numa_faults = p->numa_faults_memory;
 
 	if (grp) {
 		spin_lock(&grp->lock);
-		for (i = 0; i < 2*nr_node_ids; i++)
-			grp->faults[i] -= p->numa_faults[i];
+		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+			grp->faults[i] -= p->numa_faults_memory[i];
 		grp->total_faults -= p->total_numa_faults;
 
 		list_del(&p->numa_entry);
@@ -1577,18 +1722,21 @@ void task_numa_free(struct task_struct *p)
 		put_numa_group(grp);
 	}
 
-	p->numa_faults = NULL;
-	p->numa_faults_buffer = NULL;
+	p->numa_faults_memory = NULL;
+	p->numa_faults_buffer_memory = NULL;
+	p->numa_faults_cpu= NULL;
+	p->numa_faults_buffer_cpu = NULL;
 	kfree(numa_faults);
 }
 
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
-void task_numa_fault(int last_cpupid, int node, int pages, int flags)
+void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 {
 	struct task_struct *p = current;
 	bool migrated = flags & TNF_MIGRATED;
+	int cpu_node = task_node(current);
 	int priv;
 
 	if (!numabalancing_enabled)
@@ -1603,16 +1751,24 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 		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;
+	if (unlikely(!p->numa_faults_memory)) {
+		int size = sizeof(*p->numa_faults_memory) *
+			   NR_NUMA_HINT_FAULT_BUCKETS * 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)
+		p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
+		if (!p->numa_faults_memory)
 			return;
 
-		BUG_ON(p->numa_faults_buffer);
-		p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
+		BUG_ON(p->numa_faults_buffer_memory);
+		/*
+		 * The averaged statistics, shared & private, memory & cpu,
+		 * occupy the first half of the array. The second half of the
+		 * array is for current counters, which are averaged into the
+		 * first set by task_numa_placement.
+		 */
+		p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids);
+		p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids);
+		p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids);
 		p->total_numa_faults = 0;
 		memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 	}
@@ -1641,7 +1797,8 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 	if (migrated)
 		p->numa_pages_migrated += pages;
 
-	p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
+	p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages;
+	p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages;
 	p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
 }
 
@@ -2219,13 +2376,20 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 		se->avg.load_avg_contrib >>= NICE_0_SHIFT;
 	}
 }
-#else
+
+static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
+{
+	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
+	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
+}
+#else /* CONFIG_FAIR_GROUP_SCHED */
 static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
 						 int force_update) {}
 static inline void __update_tg_runnable_avg(struct sched_avg *sa,
 						  struct cfs_rq *cfs_rq) {}
 static inline void __update_group_entity_contrib(struct sched_entity *se) {}
-#endif
+static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 static inline void __update_task_entity_contrib(struct sched_entity *se)
 {
@@ -2323,12 +2487,6 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
 	__update_cfs_rq_tg_load_contrib(cfs_rq, force_update);
 }
 
-static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
-{
-	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
-	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
-}
-
 /* Add the load generated by se into cfs_rq's child load-average */
 static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 						  struct sched_entity *se,
@@ -2416,7 +2574,10 @@ void idle_exit_fair(struct rq *this_rq)
 	update_rq_runnable_avg(this_rq, 0);
 }
 
-#else
+static int idle_balance(struct rq *this_rq);
+
+#else /* CONFIG_SMP */
+
 static inline void update_entity_load_avg(struct sched_entity *se,
 					  int update_cfs_rq) {}
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {}
@@ -2428,7 +2589,13 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
 					   int sleep) {}
 static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
 					      int force_update) {}
-#endif
+
+static inline int idle_balance(struct rq *rq)
+{
+	return 0;
+}
+
+#endif /* CONFIG_SMP */
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -2578,10 +2745,10 @@ static void __clear_buddies_last(struct sched_entity *se)
 {
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-		if (cfs_rq->last == se)
-			cfs_rq->last = NULL;
-		else
+		if (cfs_rq->last != se)
 			break;
+
+		cfs_rq->last = NULL;
 	}
 }
 
@@ -2589,10 +2756,10 @@ static void __clear_buddies_next(struct sched_entity *se)
 {
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-		if (cfs_rq->next == se)
-			cfs_rq->next = NULL;
-		else
+		if (cfs_rq->next != se)
 			break;
+
+		cfs_rq->next = NULL;
 	}
 }
 
@@ -2600,10 +2767,10 @@ static void __clear_buddies_skip(struct sched_entity *se)
 {
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-		if (cfs_rq->skip == se)
-			cfs_rq->skip = NULL;
-		else
+		if (cfs_rq->skip != se)
 			break;
+
+		cfs_rq->skip = NULL;
 	}
 }
 
@@ -2746,17 +2913,36 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
  * 3) pick the "last" process, for cache locality
  * 4) do not run the "skip" process, if something else is available
  */
-static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *
+pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 {
-	struct sched_entity *se = __pick_first_entity(cfs_rq);
-	struct sched_entity *left = se;
+	struct sched_entity *left = __pick_first_entity(cfs_rq);
+	struct sched_entity *se;
+
+	/*
+	 * If curr is set we have to see if its left of the leftmost entity
+	 * still in the tree, provided there was anything in the tree at all.
+	 */
+	if (!left || (curr && entity_before(curr, left)))
+		left = curr;
+
+	se = left; /* ideally we run the leftmost entity */
 
 	/*
 	 * Avoid running the skip buddy, if running something else can
 	 * be done without getting too unfair.
 	 */
 	if (cfs_rq->skip == se) {
-		struct sched_entity *second = __pick_next_entity(se);
+		struct sched_entity *second;
+
+		if (se == curr) {
+			second = __pick_first_entity(cfs_rq);
+		} else {
+			second = __pick_next_entity(se);
+			if (!second || (curr && entity_before(curr, second)))
+				second = curr;
+		}
+
 		if (second && wakeup_preempt_entity(second, left) < 1)
 			se = second;
 	}
@@ -2778,7 +2964,7 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 	return se;
 }
 
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 
 static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 {
@@ -3433,22 +3619,23 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 }
 
 /* conditionally throttle active cfs_rq's from put_prev_entity() */
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
 	if (!cfs_bandwidth_used())
-		return;
+		return false;
 
 	if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0))
-		return;
+		return false;
 
 	/*
 	 * it's possible for a throttled entity to be forced into a running
 	 * state (e.g. set_curr_task), in this case we're finished.
 	 */
 	if (cfs_rq_throttled(cfs_rq))
-		return;
+		return true;
 
 	throttle_cfs_rq(cfs_rq);
+	return true;
 }
 
 static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
@@ -3558,7 +3745,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 }
 
 static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
-static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
+static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 
@@ -4213,13 +4400,14 @@ done:
 }
 
 /*
- * sched_balance_self: balance the current task (running on cpu) in domains
- * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
- * SD_BALANCE_EXEC.
+ * select_task_rq_fair: Select target runqueue for the waking task in domains
+ * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
+ * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
  *
- * Balance, ie. select the least loaded group.
+ * Balances load by selecting the idlest cpu in the idlest group, or under
+ * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set.
  *
- * Returns the target CPU number, or the same CPU if no balancing is needed.
+ * Returns the target cpu number.
  *
  * preempt must be disabled.
  */
@@ -4494,26 +4682,124 @@ preempt:
 		set_last_buddy(se);
 }
 
-static struct task_struct *pick_next_task_fair(struct rq *rq)
+static struct task_struct *
+pick_next_task_fair(struct rq *rq, struct task_struct *prev)
 {
-	struct task_struct *p;
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
+	struct task_struct *p;
+	int new_tasks;
 
+again:
+#ifdef CONFIG_FAIR_GROUP_SCHED
 	if (!cfs_rq->nr_running)
-		return NULL;
+		goto idle;
+
+	if (prev->sched_class != &fair_sched_class)
+		goto simple;
+
+	/*
+	 * Because of the set_next_buddy() in dequeue_task_fair() it is rather
+	 * likely that a next task is from the same cgroup as the current.
+	 *
+	 * Therefore attempt to avoid putting and setting the entire cgroup
+	 * hierarchy, only change the part that actually changes.
+	 */
+
+	do {
+		struct sched_entity *curr = cfs_rq->curr;
+
+		/*
+		 * Since we got here without doing put_prev_entity() we also
+		 * have to consider cfs_rq->curr. If it is still a runnable
+		 * entity, update_curr() will update its vruntime, otherwise
+		 * forget we've ever seen it.
+		 */
+		if (curr && curr->on_rq)
+			update_curr(cfs_rq);
+		else
+			curr = NULL;
+
+		/*
+		 * This call to check_cfs_rq_runtime() will do the throttle and
+		 * dequeue its entity in the parent(s). Therefore the 'simple'
+		 * nr_running test will indeed be correct.
+		 */
+		if (unlikely(check_cfs_rq_runtime(cfs_rq)))
+			goto simple;
+
+		se = pick_next_entity(cfs_rq, curr);
+		cfs_rq = group_cfs_rq(se);
+	} while (cfs_rq);
+
+	p = task_of(se);
+
+	/*
+	 * Since we haven't yet done put_prev_entity and if the selected task
+	 * is a different task than we started out with, try and touch the
+	 * least amount of cfs_rqs.
+	 */
+	if (prev != p) {
+		struct sched_entity *pse = &prev->se;
+
+		while (!(cfs_rq = is_same_group(se, pse))) {
+			int se_depth = se->depth;
+			int pse_depth = pse->depth;
+
+			if (se_depth <= pse_depth) {
+				put_prev_entity(cfs_rq_of(pse), pse);
+				pse = parent_entity(pse);
+			}
+			if (se_depth >= pse_depth) {
+				set_next_entity(cfs_rq_of(se), se);
+				se = parent_entity(se);
+			}
+		}
+
+		put_prev_entity(cfs_rq, pse);
+		set_next_entity(cfs_rq, se);
+	}
+
+	if (hrtick_enabled(rq))
+		hrtick_start_fair(rq, p);
+
+	return p;
+simple:
+	cfs_rq = &rq->cfs;
+#endif
+
+	if (!cfs_rq->nr_running)
+		goto idle;
+
+	put_prev_task(rq, prev);
 
 	do {
-		se = pick_next_entity(cfs_rq);
+		se = pick_next_entity(cfs_rq, NULL);
 		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
 
 	p = task_of(se);
+
 	if (hrtick_enabled(rq))
 		hrtick_start_fair(rq, p);
 
 	return p;
+
+idle:
+	new_tasks = idle_balance(rq);
+	/*
+	 * Because idle_balance() releases (and re-acquires) rq->lock, it is
+	 * possible for any higher priority task to appear. In that case we
+	 * must re-start the pick_next_entity() loop.
+	 */
+	if (new_tasks < 0)
+		return RETRY_TASK;
+
+	if (new_tasks > 0)
+		goto again;
+
+	return NULL;
 }
 
 /*
@@ -4751,7 +5037,7 @@ static void move_task(struct task_struct *p, struct lb_env *env)
  * Is this task likely cache-hot:
  */
 static int
-task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
+task_hot(struct task_struct *p, u64 now)
 {
 	s64 delta;
 
@@ -4785,7 +5071,7 @@ 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 ||
+	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory ||
 	    !(env->sd->flags & SD_NUMA)) {
 		return false;
 	}
@@ -4816,7 +5102,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
 		return false;
 
-	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
+	if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA))
 		return false;
 
 	src_nid = cpu_to_node(env->src_cpu);
@@ -4912,7 +5198,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	 * 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);
+	tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq));
 	if (!tsk_cache_hot)
 		tsk_cache_hot = migrate_degrades_locality(p, env);
 
@@ -5775,12 +6061,10 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 	pwr_now /= SCHED_POWER_SCALE;
 
 	/* Amount of load we'd subtract */
-	tmp = (busiest->load_per_task * SCHED_POWER_SCALE) /
-		busiest->group_power;
-	if (busiest->avg_load > tmp) {
+	if (busiest->avg_load > scaled_busy_load_per_task) {
 		pwr_move += busiest->group_power *
 			    min(busiest->load_per_task,
-				busiest->avg_load - tmp);
+				busiest->avg_load - scaled_busy_load_per_task);
 	}
 
 	/* Amount of load we'd add */
@@ -6359,17 +6643,23 @@ out:
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
-void idle_balance(int this_cpu, struct rq *this_rq)
+static int idle_balance(struct rq *this_rq)
 {
 	struct sched_domain *sd;
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
 	u64 curr_cost = 0;
+	int this_cpu = this_rq->cpu;
 
+	idle_enter_fair(this_rq);
+	/*
+	 * We must set idle_stamp _before_ calling idle_balance(), such that we
+	 * measure the duration of idle_balance() as idle time.
+	 */
 	this_rq->idle_stamp = rq_clock(this_rq);
 
 	if (this_rq->avg_idle < sysctl_sched_migration_cost)
-		return;
+		goto out;
 
 	/*
 	 * Drop the rq->lock, but keep IRQ/preempt disabled.
@@ -6407,15 +6697,22 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
 			next_balance = sd->last_balance + interval;
-		if (pulled_task) {
-			this_rq->idle_stamp = 0;
+		if (pulled_task)
 			break;
-		}
 	}
 	rcu_read_unlock();
 
 	raw_spin_lock(&this_rq->lock);
 
+	/*
+	 * While browsing the domains, we released the rq lock.
+	 * A task could have be enqueued in the meantime
+	 */
+	if (this_rq->cfs.h_nr_running && !pulled_task) {
+		pulled_task = 1;
+		goto out;
+	}
+
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
 		/*
 		 * We are going idle. next_balance may be set based on
@@ -6426,6 +6723,20 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 
 	if (curr_cost > this_rq->max_idle_balance_cost)
 		this_rq->max_idle_balance_cost = curr_cost;
+
+out:
+	/* Is there a task of a high priority class? */
+	if (this_rq->nr_running != this_rq->cfs.h_nr_running &&
+	    (this_rq->dl.dl_nr_running ||
+	     (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt))))
+		pulled_task = -1;
+
+	if (pulled_task) {
+		idle_exit_fair(this_rq);
+		this_rq->idle_stamp = 0;
+	}
+
+	return pulled_task;
 }
 
 /*
@@ -6496,6 +6807,11 @@ out_unlock:
 	return 0;
 }
 
+static inline int on_null_domain(struct rq *rq)
+{
+	return unlikely(!rcu_dereference_sched(rq->sd));
+}
+
 #ifdef CONFIG_NO_HZ_COMMON
 /*
  * idle load balancing details
@@ -6550,8 +6866,13 @@ static void nohz_balancer_kick(void)
 static inline void nohz_balance_exit_idle(int cpu)
 {
 	if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
-		cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
-		atomic_dec(&nohz.nr_cpus);
+		/*
+		 * Completely isolated CPUs don't ever set, so we must test.
+		 */
+		if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) {
+			cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
+			atomic_dec(&nohz.nr_cpus);
+		}
 		clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
 	}
 }
@@ -6605,6 +6926,12 @@ void nohz_balance_enter_idle(int cpu)
 	if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
 		return;
 
+	/*
+	 * If we're a completely isolated CPU, we don't play.
+	 */
+	if (on_null_domain(cpu_rq(cpu)))
+		return;
+
 	cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
 	atomic_inc(&nohz.nr_cpus);
 	set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
@@ -6867,11 +7194,6 @@ static void run_rebalance_domains(struct softirq_action *h)
 	nohz_idle_balance(this_rq, idle);
 }
 
-static inline int on_null_domain(struct rq *rq)
-{
-	return !rcu_dereference_sched(rq->sd);
-}
-
 /*
  * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
  */
@@ -7036,7 +7358,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
  */
 static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
-	if (!p->se.on_rq)
+	struct sched_entity *se = &p->se;
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	/*
+	 * Since the real-depth could have been changed (only FAIR
+	 * class maintain depth value), reset depth properly.
+	 */
+	se->depth = se->parent ? se->parent->depth + 1 : 0;
+#endif
+	if (!se->on_rq)
 		return;
 
 	/*
@@ -7084,7 +7414,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void task_move_group_fair(struct task_struct *p, int on_rq)
 {
+	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq;
+
 	/*
 	 * If the task was not on the rq at the time of this cgroup movement
 	 * it must have been asleep, sleeping tasks keep their ->vruntime
@@ -7110,23 +7442,24 @@ static void task_move_group_fair(struct task_struct *p, int on_rq)
 	 * To prevent boost or penalty in the new cfs_rq caused by delta
 	 * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
 	 */
-	if (!on_rq && (!p->se.sum_exec_runtime || p->state == TASK_WAKING))
+	if (!on_rq && (!se->sum_exec_runtime || p->state == TASK_WAKING))
 		on_rq = 1;
 
 	if (!on_rq)
-		p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
+		se->vruntime -= cfs_rq_of(se)->min_vruntime;
 	set_task_rq(p, task_cpu(p));
+	se->depth = se->parent ? se->parent->depth + 1 : 0;
 	if (!on_rq) {
-		cfs_rq = cfs_rq_of(&p->se);
-		p->se.vruntime += cfs_rq->min_vruntime;
+		cfs_rq = cfs_rq_of(se);
+		se->vruntime += cfs_rq->min_vruntime;
 #ifdef CONFIG_SMP
 		/*
 		 * migrate_task_rq_fair() will have removed our previous
 		 * contribution, but we must synchronize for ongoing future
 		 * decay.
 		 */
-		p->se.avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
-		cfs_rq->blocked_load_avg += p->se.avg.load_avg_contrib;
+		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
+		cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
 #endif
 	}
 }
@@ -7222,10 +7555,13 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 	if (!se)
 		return;
 
-	if (!parent)
+	if (!parent) {
 		se->cfs_rq = &rq->cfs;
-	else
+		se->depth = 0;
+	} else {
 		se->cfs_rq = parent->my_q;
+		se->depth = parent->depth + 1;
+	}
 
 	se->my_q = cfs_rq;
 	/* guarantee group entities always have weight */
diff --git a/kernel/cpu/idle.c b/kernel/sched/idle.c
index 277f494c2a9a..b7976a127178 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/sched/idle.c
@@ -3,6 +3,7 @@
  */
 #include <linux/sched.h>
 #include <linux/cpu.h>
+#include <linux/cpuidle.h>
 #include <linux/tick.h>
 #include <linux/mm.h>
 #include <linux/stackprotector.h>
@@ -95,8 +96,10 @@ static void cpu_idle_loop(void)
 				if (!current_clr_polling_and_test()) {
 					stop_critical_timings();
 					rcu_idle_enter();
-					arch_cpu_idle();
-					WARN_ON_ONCE(irqs_disabled());
+					if (cpuidle_idle_call())
+						arch_cpu_idle();
+					if (WARN_ON_ONCE(irqs_disabled()))
+						local_irq_enable();
 					rcu_idle_exit();
 					start_critical_timings();
 				} else {
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 516c3d9ceea1..879f2b75266a 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -13,18 +13,8 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
-
-static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
-{
-	idle_exit_fair(rq);
-	rq_last_tick_reset(rq);
-}
-
-static void post_schedule_idle(struct rq *rq)
-{
-	idle_enter_fair(rq);
-}
 #endif /* CONFIG_SMP */
+
 /*
  * Idle tasks are unconditionally rescheduled:
  */
@@ -33,13 +23,12 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 	resched_task(rq->idle);
 }
 
-static struct task_struct *pick_next_task_idle(struct rq *rq)
+static struct task_struct *
+pick_next_task_idle(struct rq *rq, struct task_struct *prev)
 {
+	put_prev_task(rq, prev);
+
 	schedstat_inc(rq, sched_goidle);
-#ifdef CONFIG_SMP
-	/* Trigger the post schedule to do an idle_enter for CFS */
-	rq->post_schedule = 1;
-#endif
 	return rq->idle;
 }
 
@@ -58,6 +47,8 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
+	idle_exit_fair(rq);
+	rq_last_tick_reset(rq);
 }
 
 static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
@@ -101,8 +92,6 @@ const struct sched_class idle_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_idle,
-	.pre_schedule		= pre_schedule_idle,
-	.post_schedule		= post_schedule_idle,
 #endif
 
 	.set_curr_task          = set_curr_task_idle,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 1999021042c7..d8cdf1618551 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -229,6 +229,14 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 
 #ifdef CONFIG_SMP
 
+static int pull_rt_task(struct rq *this_rq);
+
+static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
+{
+	/* Try to pull RT tasks here if we lower this rq's prio */
+	return rq->rt.highest_prio.curr > prev->prio;
+}
+
 static inline int rt_overloaded(struct rq *rq)
 {
 	return atomic_read(&rq->rd->rto_count);
@@ -315,6 +323,15 @@ static inline int has_pushable_tasks(struct rq *rq)
 	return !plist_head_empty(&rq->rt.pushable_tasks);
 }
 
+static inline void set_post_schedule(struct rq *rq)
+{
+	/*
+	 * We detect this state here so that we can avoid taking the RQ
+	 * lock again later if there is no need to push
+	 */
+	rq->post_schedule = has_pushable_tasks(rq);
+}
+
 static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
 {
 	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
@@ -359,6 +376,19 @@ void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
 }
 
+static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
+{
+	return false;
+}
+
+static inline int pull_rt_task(struct rq *this_rq)
+{
+	return 0;
+}
+
+static inline void set_post_schedule(struct rq *rq)
+{
+}
 #endif /* CONFIG_SMP */
 
 static inline int on_rt_rq(struct sched_rt_entity *rt_se)
@@ -440,11 +470,6 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 		dequeue_rt_entity(rt_se);
 }
 
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
-}
-
 static int rt_se_boosted(struct sched_rt_entity *rt_se)
 {
 	struct rt_rq *rt_rq = group_rt_rq(rt_se);
@@ -515,11 +540,6 @@ static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
 }
 
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
-	return rt_rq->rt_throttled;
-}
-
 static inline const struct cpumask *sched_rt_period_mask(void)
 {
 	return cpu_online_mask;
@@ -1318,15 +1338,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 {
 	struct sched_rt_entity *rt_se;
 	struct task_struct *p;
-	struct rt_rq *rt_rq;
-
-	rt_rq = &rq->rt;
-
-	if (!rt_rq->rt_nr_running)
-		return NULL;
-
-	if (rt_rq_throttled(rt_rq))
-		return NULL;
+	struct rt_rq *rt_rq  = &rq->rt;
 
 	do {
 		rt_se = pick_next_rt_entity(rq, rt_rq);
@@ -1340,21 +1352,45 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 	return p;
 }
 
-static struct task_struct *pick_next_task_rt(struct rq *rq)
+static struct task_struct *
+pick_next_task_rt(struct rq *rq, struct task_struct *prev)
 {
-	struct task_struct *p = _pick_next_task_rt(rq);
+	struct task_struct *p;
+	struct rt_rq *rt_rq = &rq->rt;
+
+	if (need_pull_rt_task(rq, prev)) {
+		pull_rt_task(rq);
+		/*
+		 * pull_rt_task() can drop (and re-acquire) rq->lock; this
+		 * means a dl task can slip in, in which case we need to
+		 * re-start task selection.
+		 */
+		if (unlikely(rq->dl.dl_nr_running))
+			return RETRY_TASK;
+	}
+
+	/*
+	 * We may dequeue prev's rt_rq in put_prev_task().
+	 * So, we update time before rt_nr_running check.
+	 */
+	if (prev->sched_class == &rt_sched_class)
+		update_curr_rt(rq);
+
+	if (!rt_rq->rt_nr_running)
+		return NULL;
+
+	if (rt_rq_throttled(rt_rq))
+		return NULL;
+
+	put_prev_task(rq, prev);
+
+	p = _pick_next_task_rt(rq);
 
 	/* The running task is never eligible for pushing */
 	if (p)
 		dequeue_pushable_task(rq, p);
 
-#ifdef CONFIG_SMP
-	/*
-	 * We detect this state here so that we can avoid taking the RQ
-	 * lock again later if there is no need to push
-	 */
-	rq->post_schedule = has_pushable_tasks(rq);
-#endif
+	set_post_schedule(rq);
 
 	return p;
 }
@@ -1724,13 +1760,6 @@ skip:
 	return ret;
 }
 
-static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
-{
-	/* Try to pull RT tasks here if we lower this rq's prio */
-	if (rq->rt.highest_prio.curr > prev->prio)
-		pull_rt_task(rq);
-}
-
 static void post_schedule_rt(struct rq *rq)
 {
 	push_rt_tasks(rq);
@@ -1833,7 +1862,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
 		resched_task(rq->curr);
 }
 
-void init_sched_rt_class(void)
+void __init init_sched_rt_class(void)
 {
 	unsigned int i;
 
@@ -2007,7 +2036,6 @@ const struct sched_class rt_sched_class = {
 	.set_cpus_allowed       = set_cpus_allowed_rt,
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,
-	.pre_schedule		= pre_schedule_rt,
 	.post_schedule		= post_schedule_rt,
 	.task_woken		= task_woken_rt,
 	.switched_from		= switched_from_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f964add50f38..f2de7a175620 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -24,24 +24,6 @@ extern long calc_load_fold_active(struct rq *this_rq);
 extern void update_cpu_load_active(struct rq *this_rq);
 
 /*
- * Convert user-nice values [ -20 ... 0 ... 19 ]
- * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
- * and back.
- */
-#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
-#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
-#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)
-
-/*
- * 'User priority' is the nice value converted to something we
- * can work with better when scaling various scheduler parameters,
- * it's a [ 0 ... 39 ] range.
- */
-#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
-#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
-#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
-
-/*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
 #define NS_TO_JIFFIES(TIME)	((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
@@ -441,6 +423,18 @@ struct rt_rq {
 #endif
 };
 
+#ifdef CONFIG_RT_GROUP_SCHED
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+	return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
+}
+#else
+static inline int rt_rq_throttled(struct rt_rq *rt_rq)
+{
+	return rt_rq->rt_throttled;
+}
+#endif
+
 /* Deadline class' related fields in a runqueue */
 struct dl_rq {
 	/* runqueue is an rbtree, ordered by deadline */
@@ -558,11 +552,9 @@ struct rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this cpu: */
 	struct list_head leaf_cfs_rq_list;
-#endif /* CONFIG_FAIR_GROUP_SCHED */
 
-#ifdef CONFIG_RT_GROUP_SCHED
-	struct list_head leaf_rt_rq_list;
-#endif
+	struct sched_avg avg;
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 	/*
 	 * This is part of a global counter where only the total sum
@@ -651,8 +643,6 @@ struct rq {
 #ifdef CONFIG_SMP
 	struct llist_head wake_list;
 #endif
-
-	struct sched_avg avg;
 };
 
 static inline int cpu_of(struct rq *rq)
@@ -1112,6 +1102,8 @@ static const u32 prio_to_wmult[40] = {
 
 #define DEQUEUE_SLEEP		1
 
+#define RETRY_TASK		((void *)-1UL)
+
 struct sched_class {
 	const struct sched_class *next;
 
@@ -1122,14 +1114,22 @@ struct sched_class {
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
-	struct task_struct * (*pick_next_task) (struct rq *rq);
+	/*
+	 * It is the responsibility of the pick_next_task() method that will
+	 * return the next task to call put_prev_task() on the @prev task or
+	 * something equivalent.
+	 *
+	 * May return RETRY_TASK when it finds a higher prio class has runnable
+	 * tasks.
+	 */
+	struct task_struct * (*pick_next_task) (struct rq *rq,
+						struct task_struct *prev);
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
 	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);
 	void (*post_schedule) (struct rq *this_rq);
 	void (*task_waking) (struct task_struct *task);
 	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
@@ -1159,6 +1159,11 @@ struct sched_class {
 #endif
 };
 
+static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
+{
+	prev->sched_class->put_prev_task(rq, prev);
+}
+
 #define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
@@ -1175,16 +1180,14 @@ extern const struct sched_class idle_sched_class;
 extern void update_group_power(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
-extern void idle_balance(int this_cpu, struct rq *this_rq);
 
 extern void idle_enter_fair(struct rq *this_rq);
 extern void idle_exit_fair(struct rq *this_rq);
 
-#else	/* CONFIG_SMP */
+#else
 
-static inline void idle_balance(int cpu, struct rq *rq)
-{
-}
+static inline void idle_enter_fair(struct rq *rq) { }
+static inline void idle_exit_fair(struct rq *rq) { }
 
 #endif
 
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index fdb6bb0b3356..d6ce65dde541 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -23,16 +23,19 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
 	/* we're never preempted */
 }
 
-static struct task_struct *pick_next_task_stop(struct rq *rq)
+static struct task_struct *
+pick_next_task_stop(struct rq *rq, struct task_struct *prev)
 {
 	struct task_struct *stop = rq->stop;
 
-	if (stop && stop->on_rq) {
-		stop->se.exec_start = rq_clock_task(rq);
-		return stop;
-	}
+	if (!stop || !stop->on_rq)
+		return NULL;
 
-	return NULL;
+	put_prev_task(rq, prev);
+
+	stop->se.exec_start = rq_clock_task(rq);
+
+	return stop;
 }
 
 static void
diff --git a/kernel/sys.c b/kernel/sys.c
index c0a58be780a4..adaeab6f7a87 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -174,10 +174,10 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 
 	/* normalize: avoid signed division (rounding problems) */
 	error = -ESRCH;
-	if (niceval < -20)
-		niceval = -20;
-	if (niceval > 19)
-		niceval = 19;
+	if (niceval < MIN_NICE)
+		niceval = MIN_NICE;
+	if (niceval > MAX_NICE)
+		niceval = MAX_NICE;
 
 	rcu_read_lock();
 	read_lock(&tasklist_lock);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 49e13e1f8fe6..7754ff16f334 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -386,13 +386,6 @@ static struct ctl_table kern_table[] = {
 		.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,
-	},
-	{
 		.procname	= "numa_balancing",
 		.data		= NULL, /* filled in by handler */
 		.maxlen		= sizeof(unsigned int),
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index a5457d577b98..0434ff1b808e 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -40,8 +40,8 @@ static int write_iteration = 50;
 module_param(write_iteration, uint, 0644);
 MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
 
-static int producer_nice = 19;
-static int consumer_nice = 19;
+static int producer_nice = MAX_NICE;
+static int consumer_nice = MAX_NICE;
 
 static int producer_fifo = -1;
 static int consumer_fifo = -1;
@@ -308,7 +308,7 @@ static void ring_buffer_producer(void)
 
 	/* Let the user know that the test is running at low priority */
 	if (producer_fifo < 0 && consumer_fifo < 0 &&
-	    producer_nice == 19 && consumer_nice == 19)
+	    producer_nice == MAX_NICE && consumer_nice == MAX_NICE)
 		trace_printk("WARNING!!! This test is running at lowest priority.\n");
 
 	trace_printk("Time:     %lld (usecs)\n", time);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 193e977a10ea..3fa5b8f3aae3 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3225,7 +3225,7 @@ static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr,
 		return -ENOMEM;
 
 	if (sscanf(buf, "%d", &attrs->nice) == 1 &&
-	    attrs->nice >= -20 && attrs->nice <= 19)
+	    attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE)
 		ret = apply_workqueue_attrs(wq, attrs);
 	else
 		ret = -EINVAL;