1 files changed, 579 insertions, 171 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index ccacdbdecf45..0e9344a71be3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -196,10 +196,28 @@ static inline int rt_bandwidth_enabled(void)
 	return sysctl_sched_rt_runtime >= 0;
 }
 
-static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
+static void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
 {
-	ktime_t now;
+	unsigned long delta;
+	ktime_t soft, hard, now;
+
+	for (;;) {
+		if (hrtimer_active(period_timer))
+			break;
+
+		now = hrtimer_cb_get_time(period_timer);
+		hrtimer_forward(period_timer, now, period);
 
+		soft = hrtimer_get_softexpires(period_timer);
+		hard = hrtimer_get_expires(period_timer);
+		delta = ktime_to_ns(ktime_sub(hard, soft));
+		__hrtimer_start_range_ns(period_timer, soft, delta,
+					 HRTIMER_MODE_ABS_PINNED, 0);
+	}
+}
+
+static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
+{
 	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
 		return;
 
@@ -207,22 +225,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 		return;
 
 	raw_spin_lock(&rt_b->rt_runtime_lock);
-	for (;;) {
-		unsigned long delta;
-		ktime_t soft, hard;
-
-		if (hrtimer_active(&rt_b->rt_period_timer))
-			break;
-
-		now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
-		hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
-
-		soft = hrtimer_get_softexpires(&rt_b->rt_period_timer);
-		hard = hrtimer_get_expires(&rt_b->rt_period_timer);
-		delta = ktime_to_ns(ktime_sub(hard, soft));
-		__hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
-				HRTIMER_MODE_ABS_PINNED, 0);
-	}
+	start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period);
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
@@ -247,6 +250,24 @@ struct cfs_rq;
 
 static LIST_HEAD(task_groups);
 
+struct cfs_bandwidth {
+#ifdef CONFIG_CFS_BANDWIDTH
+	raw_spinlock_t lock;
+	ktime_t period;
+	u64 quota, runtime;
+	s64 hierarchal_quota;
+	u64 runtime_expires;
+
+	int idle, timer_active;
+	struct hrtimer period_timer, slack_timer;
+	struct list_head throttled_cfs_rq;
+
+	/* statistics */
+	int nr_periods, nr_throttled;
+	u64 throttled_time;
+#endif
+};
+
 /* task group related information */
 struct task_group {
 	struct cgroup_subsys_state css;
@@ -278,6 +299,8 @@ struct task_group {
 #ifdef CONFIG_SCHED_AUTOGROUP
 	struct autogroup *autogroup;
 #endif
+
+	struct cfs_bandwidth cfs_bandwidth;
 };
 
 /* task_group_lock serializes the addition/removal of task groups */
@@ -311,7 +334,7 @@ struct task_group root_task_group;
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
 	struct load_weight load;
-	unsigned long nr_running;
+	unsigned long nr_running, h_nr_running;
 
 	u64 exec_clock;
 	u64 min_vruntime;
@@ -377,9 +400,120 @@ struct cfs_rq {
 
 	unsigned long load_contribution;
 #endif
+#ifdef CONFIG_CFS_BANDWIDTH
+	int runtime_enabled;
+	u64 runtime_expires;
+	s64 runtime_remaining;
+
+	u64 throttled_timestamp;
+	int throttled, throttle_count;
+	struct list_head throttled_list;
+#endif
 #endif
 };
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_CFS_BANDWIDTH
+static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
+{
+	return &tg->cfs_bandwidth;
+}
+
+static inline u64 default_cfs_period(void);
+static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun);
+static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b);
+
+static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
+{
+	struct cfs_bandwidth *cfs_b =
+		container_of(timer, struct cfs_bandwidth, slack_timer);
+	do_sched_cfs_slack_timer(cfs_b);
+
+	return HRTIMER_NORESTART;
+}
+
+static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
+{
+	struct cfs_bandwidth *cfs_b =
+		container_of(timer, struct cfs_bandwidth, period_timer);
+	ktime_t now;
+	int overrun;
+	int idle = 0;
+
+	for (;;) {
+		now = hrtimer_cb_get_time(timer);
+		overrun = hrtimer_forward(timer, now, cfs_b->period);
+
+		if (!overrun)
+			break;
+
+		idle = do_sched_cfs_period_timer(cfs_b, overrun);
+	}
+
+	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
+}
+
+static void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
+{
+	raw_spin_lock_init(&cfs_b->lock);
+	cfs_b->runtime = 0;
+	cfs_b->quota = RUNTIME_INF;
+	cfs_b->period = ns_to_ktime(default_cfs_period());
+
+	INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
+	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	cfs_b->period_timer.function = sched_cfs_period_timer;
+	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	cfs_b->slack_timer.function = sched_cfs_slack_timer;
+}
+
+static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+{
+	cfs_rq->runtime_enabled = 0;
+	INIT_LIST_HEAD(&cfs_rq->throttled_list);
+}
+
+/* requires cfs_b->lock, may release to reprogram timer */
+static void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
+{
+	/*
+	 * The timer may be active because we're trying to set a new bandwidth
+	 * period or because we're racing with the tear-down path
+	 * (timer_active==0 becomes visible before the hrtimer call-back
+	 * terminates).  In either case we ensure that it's re-programmed
+	 */
+	while (unlikely(hrtimer_active(&cfs_b->period_timer))) {
+		raw_spin_unlock(&cfs_b->lock);
+		/* ensure cfs_b->lock is available while we wait */
+		hrtimer_cancel(&cfs_b->period_timer);
+
+		raw_spin_lock(&cfs_b->lock);
+		/* if someone else restarted the timer then we're done */
+		if (cfs_b->timer_active)
+			return;
+	}
+
+	cfs_b->timer_active = 1;
+	start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period);
+}
+
+static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
+{
+	hrtimer_cancel(&cfs_b->period_timer);
+	hrtimer_cancel(&cfs_b->slack_timer);
+}
+#else
+static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
+static void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
+static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
+
+static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
+{
+	return NULL;
+}
+#endif /* CONFIG_CFS_BANDWIDTH */
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
 /* Real-Time classes' related field in a runqueue: */
 struct rt_rq {
 	struct rt_prio_array active;
@@ -510,7 +644,7 @@ struct rq {
 
 	unsigned long cpu_power;
 
-	unsigned char idle_at_tick;
+	unsigned char idle_balance;
 	/* For active balancing */
 	int post_schedule;
 	int active_balance;
@@ -520,8 +654,6 @@ struct rq {
 	int cpu;
 	int online;
 
-	unsigned long avg_load_per_task;
-
 	u64 rt_avg;
 	u64 age_stamp;
 	u64 idle_stamp;
@@ -570,7 +702,7 @@ struct rq {
 #endif
 
 #ifdef CONFIG_SMP
-	struct task_struct *wake_list;
+	struct llist_head wake_list;
 #endif
 };
 
@@ -1272,6 +1404,18 @@ void wake_up_idle_cpu(int cpu)
 		smp_send_reschedule(cpu);
 }
 
+static inline bool got_nohz_idle_kick(void)
+{
+	return idle_cpu(smp_processor_id()) && this_rq()->nohz_balance_kick;
+}
+
+#else /* CONFIG_NO_HZ */
+
+static inline bool got_nohz_idle_kick(void)
+{
+	return false;
+}
+
 #endif /* CONFIG_NO_HZ */
 
 static u64 sched_avg_period(void)
@@ -1471,24 +1615,28 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load)
 	update_load_sub(&rq->load, load);
 }
 
-#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED)
+#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
+			(defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH)))
 typedef int (*tg_visitor)(struct task_group *, void *);
 
 /*
- * Iterate the full tree, calling @down when first entering a node and @up when
- * leaving it for the final time.
+ * Iterate task_group tree rooted at *from, calling @down when first entering a
+ * node and @up when leaving it for the final time.
+ *
+ * Caller must hold rcu_lock or sufficient equivalent.
  */
-static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
+static int walk_tg_tree_from(struct task_group *from,
+			     tg_visitor down, tg_visitor up, void *data)
 {
 	struct task_group *parent, *child;
 	int ret;
 
-	rcu_read_lock();
-	parent = &root_task_group;
+	parent = from;
+
 down:
 	ret = (*down)(parent, data);
 	if (ret)
-		goto out_unlock;
+		goto out;
 	list_for_each_entry_rcu(child, &parent->children, siblings) {
 		parent = child;
 		goto down;
@@ -1497,19 +1645,29 @@ up:
 		continue;
 	}
 	ret = (*up)(parent, data);
-	if (ret)
-		goto out_unlock;
+	if (ret || parent == from)
+		goto out;
 
 	child = parent;
 	parent = parent->parent;
 	if (parent)
 		goto up;
-out_unlock:
-	rcu_read_unlock();
-
+out:
 	return ret;
 }
 
+/*
+ * Iterate the full tree, calling @down when first entering a node and @up when
+ * leaving it for the final time.
+ *
+ * Caller must hold rcu_lock or sufficient equivalent.
+ */
+
+static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
+{
+	return walk_tg_tree_from(&root_task_group, down, up, data);
+}
+
 static int tg_nop(struct task_group *tg, void *data)
 {
 	return 0;
@@ -1569,11 +1727,9 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 	unsigned long nr_running = ACCESS_ONCE(rq->nr_running);
 
 	if (nr_running)
-		rq->avg_load_per_task = rq->load.weight / nr_running;
-	else
-		rq->avg_load_per_task = 0;
+		return rq->load.weight / nr_running;
 
-	return rq->avg_load_per_task;
+	return 0;
 }
 
 #ifdef CONFIG_PREEMPT
@@ -1739,7 +1895,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 #ifdef CONFIG_SMP
 	/*
 	 * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
-	 * successfuly executed on another CPU. We must ensure that updates of
+	 * successfully executed on another CPU. We must ensure that updates of
 	 * per-task data have been completed by this moment.
 	 */
 	smp_wmb();
@@ -1806,7 +1962,6 @@ static void activate_task(struct rq *rq, struct task_struct *p, int flags)
 		rq->nr_uninterruptible--;
 
 	enqueue_task(rq, p, flags);
-	inc_nr_running(rq);
 }
 
 /*
@@ -1818,7 +1973,6 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 		rq->nr_uninterruptible++;
 
 	dequeue_task(rq, p, flags);
-	dec_nr_running(rq);
 }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -2390,11 +2544,11 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 
 	/* Look for allowed, online CPU in same node. */
 	for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
-		if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+		if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
 			return dest_cpu;
 
 	/* Any allowed, online CPU? */
-	dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask);
+	dest_cpu = cpumask_any_and(tsk_cpus_allowed(p), cpu_active_mask);
 	if (dest_cpu < nr_cpu_ids)
 		return dest_cpu;
 
@@ -2431,7 +2585,7 @@ int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
 	 * [ this allows ->select_task() to simply return task_cpu(p) and
 	 *   not worry about this generic constraint ]
 	 */
-	if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
+	if (unlikely(!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)) ||
 		     !cpu_online(cpu)))
 		cpu = select_fallback_rq(task_cpu(p), p);
 
@@ -2556,42 +2710,26 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 }
 
 #ifdef CONFIG_SMP
-static void sched_ttwu_do_pending(struct task_struct *list)
+static void sched_ttwu_pending(void)
 {
 	struct rq *rq = this_rq();
+	struct llist_node *llist = llist_del_all(&rq->wake_list);
+	struct task_struct *p;
 
 	raw_spin_lock(&rq->lock);
 
-	while (list) {
-		struct task_struct *p = list;
-		list = list->wake_entry;
+	while (llist) {
+		p = llist_entry(llist, struct task_struct, wake_entry);
+		llist = llist_next(llist);
 		ttwu_do_activate(rq, p, 0);
 	}
 
 	raw_spin_unlock(&rq->lock);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
-static void sched_ttwu_pending(void)
-{
-	struct rq *rq = this_rq();
-	struct task_struct *list = xchg(&rq->wake_list, NULL);
-
-	if (!list)
-		return;
-
-	sched_ttwu_do_pending(list);
-}
-
-#endif /* CONFIG_HOTPLUG_CPU */
-
 void scheduler_ipi(void)
 {
-	struct rq *rq = this_rq();
-	struct task_struct *list = xchg(&rq->wake_list, NULL);
-
-	if (!list)
+	if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
 		return;
 
 	/*
@@ -2608,25 +2746,21 @@ void scheduler_ipi(void)
 	 * somewhat pessimize the simple resched case.
 	 */
 	irq_enter();
-	sched_ttwu_do_pending(list);
+	sched_ttwu_pending();
+
+	/*
+	 * Check if someone kicked us for doing the nohz idle load balance.
+	 */
+	if (unlikely(got_nohz_idle_kick() && !need_resched())) {
+		this_rq()->idle_balance = 1;
+		raise_softirq_irqoff(SCHED_SOFTIRQ);
+	}
 	irq_exit();
 }
 
 static void ttwu_queue_remote(struct task_struct *p, int cpu)
 {
-	struct rq *rq = cpu_rq(cpu);
-	struct task_struct *next = rq->wake_list;
-
-	for (;;) {
-		struct task_struct *old = next;
-
-		p->wake_entry = next;
-		next = cmpxchg(&rq->wake_list, old, p);
-		if (next == old)
-			break;
-	}
-
-	if (!next)
+	if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list))
 		smp_send_reschedule(cpu);
 }
 
@@ -2848,19 +2982,23 @@ void sched_fork(struct task_struct *p)
 	p->state = TASK_RUNNING;
 
 	/*
+	 * Make sure we do not leak PI boosting priority to the child.
+	 */
+	p->prio = current->normal_prio;
+
+	/*
 	 * Revert to default priority/policy on fork if requested.
 	 */
 	if (unlikely(p->sched_reset_on_fork)) {
-		if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
+		if (task_has_rt_policy(p)) {
 			p->policy = SCHED_NORMAL;
-			p->normal_prio = p->static_prio;
-		}
-
-		if (PRIO_TO_NICE(p->static_prio) < 0) {
 			p->static_prio = NICE_TO_PRIO(0);
-			p->normal_prio = p->static_prio;
-			set_load_weight(p);
-		}
+			p->rt_priority = 0;
+		} else if (PRIO_TO_NICE(p->static_prio) < 0)
+			p->static_prio = NICE_TO_PRIO(0);
+
+		p->prio = p->normal_prio = __normal_prio(p);
+		set_load_weight(p);
 
 		/*
 		 * We don't need the reset flag anymore after the fork. It has
@@ -2869,11 +3007,6 @@ void sched_fork(struct task_struct *p)
 		p->sched_reset_on_fork = 0;
 	}
 
-	/*
-	 * Make sure we do not leak PI boosting priority to the child.
-	 */
-	p->prio = current->normal_prio;
-
 	if (!rt_prio(p->prio))
 		p->sched_class = &fair_sched_class;
 
@@ -3065,7 +3198,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	local_irq_disable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
-	perf_event_task_sched_in(current);
+	perf_event_task_sched_in(prev, current);
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	local_irq_enable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
@@ -3725,30 +3858,6 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 }
 
 /*
- * Return sum_exec_runtime for the thread group.
- * In case the task is currently running, return the sum plus current's
- * pending runtime that have not been accounted yet.
- *
- * Note that the thread group might have other running tasks as well,
- * so the return value not includes other pending runtime that other
- * running tasks might have.
- */
-unsigned long long thread_group_sched_runtime(struct task_struct *p)
-{
-	struct task_cputime totals;
-	unsigned long flags;
-	struct rq *rq;
-	u64 ns;
-
-	rq = task_rq_lock(p, &flags);
-	thread_group_cputime(p, &totals);
-	ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, p, &flags);
-
-	return ns;
-}
-
-/*
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in user space since the last update
@@ -4140,7 +4249,7 @@ void scheduler_tick(void)
 	perf_event_task_tick();
 
 #ifdef CONFIG_SMP
-	rq->idle_at_tick = idle_cpu(cpu);
+	rq->idle_balance = idle_cpu(cpu);
 	trigger_load_balance(rq, cpu);
 #endif
 }
@@ -4237,6 +4346,7 @@ static inline void schedule_debug(struct task_struct *prev)
 	 */
 	if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
 		__schedule_bug(prev);
+	rcu_sleep_check();
 
 	profile_hit(SCHED_PROFILING, __builtin_return_address(0));
 
@@ -4263,7 +4373,7 @@ pick_next_task(struct rq *rq)
 	 * 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.nr_running)) {
+	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
 		p = fair_sched_class.pick_next_task(rq);
 		if (likely(p))
 			return p;
@@ -4279,9 +4389,9 @@ pick_next_task(struct rq *rq)
 }
 
 /*
- * schedule() is the main scheduler function.
+ * __schedule() is the main scheduler function.
  */
-asmlinkage void __sched schedule(void)
+static void __sched __schedule(void)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
@@ -4322,16 +4432,6 @@ need_resched:
 				if (to_wakeup)
 					try_to_wake_up_local(to_wakeup);
 			}
-
-			/*
-			 * If we are going to sleep and we have plugged IO
-			 * queued, make sure to submit it to avoid deadlocks.
-			 */
-			if (blk_needs_flush_plug(prev)) {
-				raw_spin_unlock(&rq->lock);
-				blk_schedule_flush_plug(prev);
-				raw_spin_lock(&rq->lock);
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -4369,6 +4469,26 @@ need_resched:
 	if (need_resched())
 		goto need_resched;
 }
+
+static inline void sched_submit_work(struct task_struct *tsk)
+{
+	if (!tsk->state)
+		return;
+	/*
+	 * If we are going to sleep and we have plugged IO queued,
+	 * make sure to submit it to avoid deadlocks.
+	 */
+	if (blk_needs_flush_plug(tsk))
+		blk_schedule_flush_plug(tsk);
+}
+
+asmlinkage void __sched schedule(void)
+{
+	struct task_struct *tsk = current;
+
+	sched_submit_work(tsk);
+	__schedule();
+}
 EXPORT_SYMBOL(schedule);
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
@@ -4435,7 +4555,7 @@ asmlinkage void __sched notrace preempt_schedule(void)
 
 	do {
 		add_preempt_count_notrace(PREEMPT_ACTIVE);
-		schedule();
+		__schedule();
 		sub_preempt_count_notrace(PREEMPT_ACTIVE);
 
 		/*
@@ -4463,7 +4583,7 @@ asmlinkage void __sched preempt_schedule_irq(void)
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		local_irq_enable();
-		schedule();
+		__schedule();
 		local_irq_disable();
 		sub_preempt_count(PREEMPT_ACTIVE);
 
@@ -5039,7 +5159,20 @@ EXPORT_SYMBOL(task_nice);
  */
 int idle_cpu(int cpu)
 {
-	return cpu_curr(cpu) == cpu_rq(cpu)->idle;
+	struct rq *rq = cpu_rq(cpu);
+
+	if (rq->curr != rq->idle)
+		return 0;
+
+	if (rq->nr_running)
+		return 0;
+
+#ifdef CONFIG_SMP
+	if (!llist_empty(&rq->wake_list))
+		return 0;
+#endif
+
+	return 1;
 }
 
 /**
@@ -5588,7 +5721,7 @@ static inline int should_resched(void)
 static void __cond_resched(void)
 {
 	add_preempt_count(PREEMPT_ACTIVE);
-	schedule();
+	__schedule();
 	sub_preempt_count(PREEMPT_ACTIVE);
 }
 
@@ -5889,7 +6022,7 @@ void show_state_filter(unsigned long state_filter)
 	printk(KERN_INFO
 		"  task                        PC stack   pid father\n");
 #endif
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	do_each_thread(g, p) {
 		/*
 		 * reset the NMI-timeout, listing all files on a slow
@@ -5905,7 +6038,7 @@ void show_state_filter(unsigned long state_filter)
 #ifdef CONFIG_SCHED_DEBUG
 	sysrq_sched_debug_show();
 #endif
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 	/*
 	 * Only show locks if all tasks are dumped:
 	 */
@@ -5969,15 +6102,6 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 }
 
 /*
- * In a system that switches off the HZ timer nohz_cpu_mask
- * indicates which cpus entered this state. This is used
- * in the rcu update to wait only for active cpus. For system
- * which do not switch off the HZ timer nohz_cpu_mask should
- * always be CPU_BITS_NONE.
- */
-cpumask_var_t nohz_cpu_mask;
-
-/*
  * Increase the granularity value when there are more CPUs,
  * because with more CPUs the 'effective latency' as visible
  * to users decreases. But the relationship is not linear,
@@ -6029,10 +6153,9 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
 	if (p->sched_class && p->sched_class->set_cpus_allowed)
 		p->sched_class->set_cpus_allowed(p, new_mask);
-	else {
-		cpumask_copy(&p->cpus_allowed, new_mask);
-		p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
-	}
+
+	cpumask_copy(&p->cpus_allowed, new_mask);
+	p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
 /*
@@ -6130,7 +6253,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 	if (task_cpu(p) != src_cpu)
 		goto done;
 	/* Affinity changed (again). */
-	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+	if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
 		goto fail;
 
 	/*
@@ -6211,6 +6334,30 @@ static void calc_global_load_remove(struct rq *rq)
 	rq->calc_load_active = 0;
 }
 
+#ifdef CONFIG_CFS_BANDWIDTH
+static void unthrottle_offline_cfs_rqs(struct rq *rq)
+{
+	struct cfs_rq *cfs_rq;
+
+	for_each_leaf_cfs_rq(rq, cfs_rq) {
+		struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
+
+		if (!cfs_rq->runtime_enabled)
+			continue;
+
+		/*
+		 * clock_task is not advancing so we just need to make sure
+		 * there's some valid quota amount
+		 */
+		cfs_rq->runtime_remaining = cfs_b->quota;
+		if (cfs_rq_throttled(cfs_rq))
+			unthrottle_cfs_rq(cfs_rq);
+	}
+}
+#else
+static void unthrottle_offline_cfs_rqs(struct rq *rq) {}
+#endif
+
 /*
  * Migrate all tasks from the rq, sleeping tasks will be migrated by
  * try_to_wake_up()->select_task_rq().
@@ -6236,6 +6383,9 @@ static void migrate_tasks(unsigned int dead_cpu)
 	 */
 	rq->stop = NULL;
 
+	/* Ensure any throttled groups are reachable by pick_next_task */
+	unthrottle_offline_cfs_rqs(rq);
+
 	for ( ; ; ) {
 		/*
 		 * There's this thread running, bail when that's the only
@@ -6937,8 +7087,6 @@ static int __init isolated_cpu_setup(char *str)
 
 __setup("isolcpus=", isolated_cpu_setup);
 
-#define SD_NODES_PER_DOMAIN 16
-
 #ifdef CONFIG_NUMA
 
 /**
@@ -7443,6 +7591,7 @@ static void __sdt_free(const struct cpumask *cpu_map)
 			struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
 			if (sd && (sd->flags & SD_OVERLAP))
 				free_sched_groups(sd->groups, 0);
+			kfree(*per_cpu_ptr(sdd->sd, j));
 			kfree(*per_cpu_ptr(sdd->sg, j));
 			kfree(*per_cpu_ptr(sdd->sgp, j));
 		}
@@ -7978,6 +8127,7 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 	/* allow initial update_cfs_load() to truncate */
 	cfs_rq->load_stamp = 1;
 #endif
+	init_cfs_rq_runtime(cfs_rq);
 
 	tg->cfs_rq[cpu] = cfs_rq;
 	tg->se[cpu] = se;
@@ -8117,6 +8267,7 @@ void __init sched_init(void)
 		 * We achieve this by letting root_task_group's tasks sit
 		 * directly in rq->cfs (i.e root_task_group->se[] = NULL).
 		 */
+		init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
 		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
@@ -8146,7 +8297,6 @@ void __init sched_init(void)
 		rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ
 		rq->nohz_balance_kick = 0;
-		init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i));
 #endif
 #endif
 		init_rq_hrtick(rq);
@@ -8188,8 +8338,6 @@ void __init sched_init(void)
 	 */
 	current->sched_class = &fair_sched_class;
 
-	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
-	zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
 #ifdef CONFIG_SMP
 	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
 #ifdef CONFIG_NO_HZ
@@ -8219,6 +8367,7 @@ 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()) ||
 	    system_state != SYSTEM_RUNNING || oops_in_progress)
 		return;
@@ -8358,6 +8507,8 @@ static void free_fair_sched_group(struct task_group *tg)
 {
 	int i;
 
+	destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
+
 	for_each_possible_cpu(i) {
 		if (tg->cfs_rq)
 			kfree(tg->cfs_rq[i]);
@@ -8385,6 +8536,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 
 	tg->shares = NICE_0_LOAD;
 
+	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
+
 	for_each_possible_cpu(i) {
 		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
 				      GFP_KERNEL, cpu_to_node(i));
@@ -8660,12 +8813,7 @@ unsigned long sched_group_shares(struct task_group *tg)
 }
 #endif
 
-#ifdef CONFIG_RT_GROUP_SCHED
-/*
- * Ensure that the real time constraints are schedulable.
- */
-static DEFINE_MUTEX(rt_constraints_mutex);
-
+#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_CFS_BANDWIDTH)
 static unsigned long to_ratio(u64 period, u64 runtime)
 {
 	if (runtime == RUNTIME_INF)
@@ -8673,6 +8821,13 @@ static unsigned long to_ratio(u64 period, u64 runtime)
 
 	return div64_u64(runtime << 20, period);
 }
+#endif
+
+#ifdef CONFIG_RT_GROUP_SCHED
+/*
+ * Ensure that the real time constraints are schedulable.
+ */
+static DEFINE_MUTEX(rt_constraints_mutex);
 
 /* Must be called with tasklist_lock held */
 static inline int tg_has_rt_tasks(struct task_group *tg)
@@ -8693,7 +8848,7 @@ struct rt_schedulable_data {
 	u64 rt_runtime;
 };
 
-static int tg_schedulable(struct task_group *tg, void *data)
+static int tg_rt_schedulable(struct task_group *tg, void *data)
 {
 	struct rt_schedulable_data *d = data;
 	struct task_group *child;
@@ -8751,16 +8906,22 @@ static int tg_schedulable(struct task_group *tg, void *data)
 
 static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 {
+	int ret;
+
 	struct rt_schedulable_data data = {
 		.tg = tg,
 		.rt_period = period,
 		.rt_runtime = runtime,
 	};
 
-	return walk_tg_tree(tg_schedulable, tg_nop, &data);
+	rcu_read_lock();
+	ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
+	rcu_read_unlock();
+
+	return ret;
 }
 
-static int tg_set_bandwidth(struct task_group *tg,
+static int tg_set_rt_bandwidth(struct task_group *tg,
 		u64 rt_period, u64 rt_runtime)
 {
 	int i, err = 0;
@@ -8799,7 +8960,7 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
 	if (rt_runtime_us < 0)
 		rt_runtime = RUNTIME_INF;
 
-	return tg_set_bandwidth(tg, rt_period, rt_runtime);
+	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
 }
 
 long sched_group_rt_runtime(struct task_group *tg)
@@ -8824,7 +8985,7 @@ int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
 	if (rt_period == 0)
 		return -EINVAL;
 
-	return tg_set_bandwidth(tg, rt_period, rt_runtime);
+	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
 }
 
 long sched_group_rt_period(struct task_group *tg)
@@ -9014,6 +9175,238 @@ static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft)
 
 	return (u64) scale_load_down(tg->shares);
 }
+
+#ifdef CONFIG_CFS_BANDWIDTH
+static DEFINE_MUTEX(cfs_constraints_mutex);
+
+const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
+const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+
+static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
+
+static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
+{
+	int i, ret = 0, runtime_enabled;
+	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
+
+	if (tg == &root_task_group)
+		return -EINVAL;
+
+	/*
+	 * Ensure we have at some amount of bandwidth every period.  This is
+	 * to prevent reaching a state of large arrears when throttled via
+	 * entity_tick() resulting in prolonged exit starvation.
+	 */
+	if (quota < min_cfs_quota_period || period < min_cfs_quota_period)
+		return -EINVAL;
+
+	/*
+	 * Likewise, bound things on the otherside by preventing insane quota
+	 * periods.  This also allows us to normalize in computing quota
+	 * feasibility.
+	 */
+	if (period > max_cfs_quota_period)
+		return -EINVAL;
+
+	mutex_lock(&cfs_constraints_mutex);
+	ret = __cfs_schedulable(tg, period, quota);
+	if (ret)
+		goto out_unlock;
+
+	runtime_enabled = quota != RUNTIME_INF;
+	raw_spin_lock_irq(&cfs_b->lock);
+	cfs_b->period = ns_to_ktime(period);
+	cfs_b->quota = quota;
+
+	__refill_cfs_bandwidth_runtime(cfs_b);
+	/* restart the period timer (if active) to handle new period expiry */
+	if (runtime_enabled && cfs_b->timer_active) {
+		/* force a reprogram */
+		cfs_b->timer_active = 0;
+		__start_cfs_bandwidth(cfs_b);
+	}
+	raw_spin_unlock_irq(&cfs_b->lock);
+
+	for_each_possible_cpu(i) {
+		struct cfs_rq *cfs_rq = tg->cfs_rq[i];
+		struct rq *rq = rq_of(cfs_rq);
+
+		raw_spin_lock_irq(&rq->lock);
+		cfs_rq->runtime_enabled = runtime_enabled;
+		cfs_rq->runtime_remaining = 0;
+
+		if (cfs_rq_throttled(cfs_rq))
+			unthrottle_cfs_rq(cfs_rq);
+		raw_spin_unlock_irq(&rq->lock);
+	}
+out_unlock:
+	mutex_unlock(&cfs_constraints_mutex);
+
+	return ret;
+}
+
+int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
+{
+	u64 quota, period;
+
+	period = ktime_to_ns(tg_cfs_bandwidth(tg)->period);
+	if (cfs_quota_us < 0)
+		quota = RUNTIME_INF;
+	else
+		quota = (u64)cfs_quota_us * NSEC_PER_USEC;
+
+	return tg_set_cfs_bandwidth(tg, period, quota);
+}
+
+long tg_get_cfs_quota(struct task_group *tg)
+{
+	u64 quota_us;
+
+	if (tg_cfs_bandwidth(tg)->quota == RUNTIME_INF)
+		return -1;
+
+	quota_us = tg_cfs_bandwidth(tg)->quota;
+	do_div(quota_us, NSEC_PER_USEC);
+
+	return quota_us;
+}
+
+int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
+{
+	u64 quota, period;
+
+	period = (u64)cfs_period_us * NSEC_PER_USEC;
+	quota = tg_cfs_bandwidth(tg)->quota;
+
+	if (period <= 0)
+		return -EINVAL;
+
+	return tg_set_cfs_bandwidth(tg, period, quota);
+}
+
+long tg_get_cfs_period(struct task_group *tg)
+{
+	u64 cfs_period_us;
+
+	cfs_period_us = ktime_to_ns(tg_cfs_bandwidth(tg)->period);
+	do_div(cfs_period_us, NSEC_PER_USEC);
+
+	return cfs_period_us;
+}
+
+static s64 cpu_cfs_quota_read_s64(struct cgroup *cgrp, struct cftype *cft)
+{
+	return tg_get_cfs_quota(cgroup_tg(cgrp));
+}
+
+static int cpu_cfs_quota_write_s64(struct cgroup *cgrp, struct cftype *cftype,
+				s64 cfs_quota_us)
+{
+	return tg_set_cfs_quota(cgroup_tg(cgrp), cfs_quota_us);
+}
+
+static u64 cpu_cfs_period_read_u64(struct cgroup *cgrp, struct cftype *cft)
+{
+	return tg_get_cfs_period(cgroup_tg(cgrp));
+}
+
+static int cpu_cfs_period_write_u64(struct cgroup *cgrp, struct cftype *cftype,
+				u64 cfs_period_us)
+{
+	return tg_set_cfs_period(cgroup_tg(cgrp), cfs_period_us);
+}
+
+struct cfs_schedulable_data {
+	struct task_group *tg;
+	u64 period, quota;
+};
+
+/*
+ * normalize group quota/period to be quota/max_period
+ * note: units are usecs
+ */
+static u64 normalize_cfs_quota(struct task_group *tg,
+			       struct cfs_schedulable_data *d)
+{
+	u64 quota, period;
+
+	if (tg == d->tg) {
+		period = d->period;
+		quota = d->quota;
+	} else {
+		period = tg_get_cfs_period(tg);
+		quota = tg_get_cfs_quota(tg);
+	}
+
+	/* note: these should typically be equivalent */
+	if (quota == RUNTIME_INF || quota == -1)
+		return RUNTIME_INF;
+
+	return to_ratio(period, quota);
+}
+
+static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
+{
+	struct cfs_schedulable_data *d = data;
+	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
+	s64 quota = 0, parent_quota = -1;
+
+	if (!tg->parent) {
+		quota = RUNTIME_INF;
+	} else {
+		struct cfs_bandwidth *parent_b = tg_cfs_bandwidth(tg->parent);
+
+		quota = normalize_cfs_quota(tg, d);
+		parent_quota = parent_b->hierarchal_quota;
+
+		/*
+		 * ensure max(child_quota) <= parent_quota, inherit when no
+		 * limit is set
+		 */
+		if (quota == RUNTIME_INF)
+			quota = parent_quota;
+		else if (parent_quota != RUNTIME_INF && quota > parent_quota)
+			return -EINVAL;
+	}
+	cfs_b->hierarchal_quota = quota;
+
+	return 0;
+}
+
+static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
+{
+	int ret;
+	struct cfs_schedulable_data data = {
+		.tg = tg,
+		.period = period,
+		.quota = quota,
+	};
+
+	if (quota != RUNTIME_INF) {
+		do_div(data.period, NSEC_PER_USEC);
+		do_div(data.quota, NSEC_PER_USEC);
+	}
+
+	rcu_read_lock();
+	ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int cpu_stats_show(struct cgroup *cgrp, struct cftype *cft,
+		struct cgroup_map_cb *cb)
+{
+	struct task_group *tg = cgroup_tg(cgrp);
+	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
+
+	cb->fill(cb, "nr_periods", cfs_b->nr_periods);
+	cb->fill(cb, "nr_throttled", cfs_b->nr_throttled);
+	cb->fill(cb, "throttled_time", cfs_b->throttled_time);
+
+	return 0;
+}
+#endif /* CONFIG_CFS_BANDWIDTH */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -9048,6 +9441,22 @@ static struct cftype cpu_files[] = {
 		.write_u64 = cpu_shares_write_u64,
 	},
 #endif
+#ifdef CONFIG_CFS_BANDWIDTH
+	{
+		.name = "cfs_quota_us",
+		.read_s64 = cpu_cfs_quota_read_s64,
+		.write_s64 = cpu_cfs_quota_write_s64,
+	},
+	{
+		.name = "cfs_period_us",
+		.read_u64 = cpu_cfs_period_read_u64,
+		.write_u64 = cpu_cfs_period_write_u64,
+	},
+	{
+		.name = "stat",
+		.read_map = cpu_stats_show,
+	},
+#endif
 #ifdef CONFIG_RT_GROUP_SCHED
 	{
 		.name = "rt_runtime_us",
@@ -9357,4 +9766,3 @@ struct cgroup_subsys cpuacct_subsys = {
 	.subsys_id = cpuacct_subsys_id,
 };
 #endif	/* CONFIG_CGROUP_CPUACCT */
-