Merge commit 'v2.6.30-rc1' into sched/urgent

Merge reason: update to latest upstream to queue up fix

Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 788 insertions, 353 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 6234d10c6a79..5724508c3b66 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -223,7 +223,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
 	ktime_t now;
 
-	if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF)
+	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
 		return;
 
 	if (hrtimer_active(&rt_b->rt_period_timer))
@@ -231,13 +231,20 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 
 	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);
-		hrtimer_start_expires(&rt_b->rt_period_timer,
-				HRTIMER_MODE_ABS);
+
+		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, 0);
 	}
 	spin_unlock(&rt_b->rt_runtime_lock);
 }
@@ -331,6 +338,13 @@ static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
  */
 static DEFINE_SPINLOCK(task_group_lock);
 
+#ifdef CONFIG_SMP
+static int root_task_group_empty(void)
+{
+	return list_empty(&root_task_group.children);
+}
+#endif
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
@@ -391,6 +405,13 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 
 #else
 
+#ifdef CONFIG_SMP
+static int root_task_group_empty(void)
+{
+	return 1;
+}
+#endif
+
 static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
 static inline struct task_group *task_group(struct task_struct *p)
 {
@@ -467,11 +488,17 @@ struct rt_rq {
 	struct rt_prio_array active;
 	unsigned long rt_nr_running;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
-	int highest_prio; /* highest queued rt task prio */
+	struct {
+		int curr; /* highest queued rt task prio */
+#ifdef CONFIG_SMP
+		int next; /* next highest */
+#endif
+	} highest_prio;
 #endif
 #ifdef CONFIG_SMP
 	unsigned long rt_nr_migratory;
 	int overloaded;
+	struct plist_head pushable_tasks;
 #endif
 	int rt_throttled;
 	u64 rt_time;
@@ -549,7 +576,6 @@ struct rq {
 	unsigned long nr_running;
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
-	unsigned char idle_at_tick;
 #ifdef CONFIG_NO_HZ
 	unsigned long last_tick_seen;
 	unsigned char in_nohz_recently;
@@ -590,6 +616,7 @@ struct rq {
 	struct root_domain *rd;
 	struct sched_domain *sd;
 
+	unsigned char idle_at_tick;
 	/* For active balancing */
 	int active_balance;
 	int push_cpu;
@@ -618,9 +645,6 @@ struct rq {
 	/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
 
 	/* sys_sched_yield() stats */
-	unsigned int yld_exp_empty;
-	unsigned int yld_act_empty;
-	unsigned int yld_both_empty;
 	unsigned int yld_count;
 
 	/* schedule() stats */
@@ -1093,7 +1117,7 @@ static void hrtick_start(struct rq *rq, u64 delay)
 	if (rq == this_rq()) {
 		hrtimer_restart(timer);
 	} else if (!rq->hrtick_csd_pending) {
-		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
+		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
 		rq->hrtick_csd_pending = 1;
 	}
 }
@@ -1129,7 +1153,8 @@ static __init void init_hrtick(void)
  */
 static void hrtick_start(struct rq *rq, u64 delay)
 {
-	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
+	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
+			HRTIMER_MODE_REL, 0);
 }
 
 static inline void init_hrtick(void)
@@ -1183,10 +1208,10 @@ static void resched_task(struct task_struct *p)
 
 	assert_spin_locked(&task_rq(p)->lock);
 
-	if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
+	if (test_tsk_need_resched(p))
 		return;
 
-	set_tsk_thread_flag(p, TIF_NEED_RESCHED);
+	set_tsk_need_resched(p);
 
 	cpu = task_cpu(p);
 	if (cpu == smp_processor_id())
@@ -1242,7 +1267,7 @@ void wake_up_idle_cpu(int cpu)
 	 * lockless. The worst case is that the other CPU runs the
 	 * idle task through an additional NOOP schedule()
 	 */
-	set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED);
+	set_tsk_need_resched(rq->idle);
 
 	/* NEED_RESCHED must be visible before we test polling */
 	smp_mb();
@@ -1622,21 +1647,42 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
 
 #endif
 
+#ifdef CONFIG_PREEMPT
+
 /*
- * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ * fair double_lock_balance: Safely acquires both rq->locks in a fair
+ * way at the expense of forcing extra atomic operations in all
+ * invocations.  This assures that the double_lock is acquired using the
+ * same underlying policy as the spinlock_t on this architecture, which
+ * reduces latency compared to the unfair variant below.  However, it
+ * also adds more overhead and therefore may reduce throughput.
  */
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
+	__releases(this_rq->lock)
+	__acquires(busiest->lock)
+	__acquires(this_rq->lock)
+{
+	spin_unlock(&this_rq->lock);
+	double_rq_lock(this_rq, busiest);
+
+	return 1;
+}
+
+#else
+/*
+ * Unfair double_lock_balance: Optimizes throughput at the expense of
+ * latency by eliminating extra atomic operations when the locks are
+ * already in proper order on entry.  This favors lower cpu-ids and will
+ * grant the double lock to lower cpus over higher ids under contention,
+ * regardless of entry order into the function.
+ */
+static int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	__releases(this_rq->lock)
 	__acquires(busiest->lock)
 	__acquires(this_rq->lock)
 {
 	int ret = 0;
 
-	if (unlikely(!irqs_disabled())) {
-		/* printk() doesn't work good under rq->lock */
-		spin_unlock(&this_rq->lock);
-		BUG_ON(1);
-	}
 	if (unlikely(!spin_trylock(&busiest->lock))) {
 		if (busiest < this_rq) {
 			spin_unlock(&this_rq->lock);
@@ -1649,6 +1695,22 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	return ret;
 }
 
+#endif /* CONFIG_PREEMPT */
+
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+{
+	if (unlikely(!irqs_disabled())) {
+		/* printk() doesn't work good under rq->lock */
+		spin_unlock(&this_rq->lock);
+		BUG_ON(1);
+	}
+
+	return _double_lock_balance(this_rq, busiest);
+}
+
 static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
 	__releases(busiest->lock)
 {
@@ -1717,6 +1779,9 @@ static void update_avg(u64 *avg, u64 sample)
 
 static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
 {
+	if (wakeup)
+		p->se.start_runtime = p->se.sum_exec_runtime;
+
 	sched_info_queued(p);
 	p->sched_class->enqueue_task(rq, p, wakeup);
 	p->se.on_rq = 1;
@@ -1724,10 +1789,15 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
 
 static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
 {
-	if (sleep && p->se.last_wakeup) {
-		update_avg(&p->se.avg_overlap,
-			   p->se.sum_exec_runtime - p->se.last_wakeup);
-		p->se.last_wakeup = 0;
+	if (sleep) {
+		if (p->se.last_wakeup) {
+			update_avg(&p->se.avg_overlap,
+				p->se.sum_exec_runtime - p->se.last_wakeup);
+			p->se.last_wakeup = 0;
+		} else {
+			update_avg(&p->se.avg_wakeup,
+				sysctl_sched_wakeup_granularity);
+		}
 	}
 
 	sched_info_dequeued(p);
@@ -2029,7 +2099,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * it must be off the runqueue _entirely_, and not
 		 * preempted!
 		 *
-		 * So if it wa still runnable (but just not actively
+		 * So if it was still runnable (but just not actively
 		 * running right now), it's preempted, and we should
 		 * yield - it could be a while.
 		 */
@@ -2278,18 +2348,8 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 	if (!sched_feat(SYNC_WAKEUPS))
 		sync = 0;
 
-	if (!sync) {
-		if (current->se.avg_overlap < sysctl_sched_migration_cost &&
-			  p->se.avg_overlap < sysctl_sched_migration_cost)
-			sync = 1;
-	} else {
-		if (current->se.avg_overlap >= sysctl_sched_migration_cost ||
-			  p->se.avg_overlap >= sysctl_sched_migration_cost)
-			sync = 0;
-	}
-
 #ifdef CONFIG_SMP
-	if (sched_feat(LB_WAKEUP_UPDATE)) {
+	if (sched_feat(LB_WAKEUP_UPDATE) && !root_task_group_empty()) {
 		struct sched_domain *sd;
 
 		this_cpu = raw_smp_processor_id();
@@ -2367,6 +2427,22 @@ out_activate:
 	activate_task(rq, p, 1);
 	success = 1;
 
+	/*
+	 * Only attribute actual wakeups done by this task.
+	 */
+	if (!in_interrupt()) {
+		struct sched_entity *se = &current->se;
+		u64 sample = se->sum_exec_runtime;
+
+		if (se->last_wakeup)
+			sample -= se->last_wakeup;
+		else
+			sample -= se->start_runtime;
+		update_avg(&se->avg_wakeup, sample);
+
+		se->last_wakeup = se->sum_exec_runtime;
+	}
+
 out_running:
 	trace_sched_wakeup(rq, p, success);
 	check_preempt_curr(rq, p, sync);
@@ -2377,8 +2453,6 @@ out_running:
 		p->sched_class->task_wake_up(rq, p);
 #endif
 out:
-	current->se.last_wakeup = current->se.sum_exec_runtime;
-
 	task_rq_unlock(rq, &flags);
 
 	return success;
@@ -2408,6 +2482,8 @@ static void __sched_fork(struct task_struct *p)
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.last_wakeup		= 0;
 	p->se.avg_overlap		= 0;
+	p->se.start_runtime		= 0;
+	p->se.avg_wakeup		= sysctl_sched_wakeup_granularity;
 
 #ifdef CONFIG_SCHEDSTATS
 	p->se.wait_start		= 0;
@@ -2470,6 +2546,8 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	/* Want to start with kernel preemption disabled. */
 	task_thread_info(p)->preempt_count = 1;
 #endif
+	plist_node_init(&p->pushable_tasks, MAX_PRIO);
+
 	put_cpu();
 }
 
@@ -2513,7 +2591,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
 /**
- * preempt_notifier_register - tell me when current is being being preempted & rescheduled
+ * preempt_notifier_register - tell me when current is being preempted & rescheduled
  * @notifier: notifier struct to register
  */
 void preempt_notifier_register(struct preempt_notifier *notifier)
@@ -2610,6 +2688,12 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 {
 	struct mm_struct *mm = rq->prev_mm;
 	long prev_state;
+#ifdef CONFIG_SMP
+	int post_schedule = 0;
+
+	if (current->sched_class->needs_post_schedule)
+		post_schedule = current->sched_class->needs_post_schedule(rq);
+#endif
 
 	rq->prev_mm = NULL;
 
@@ -2628,7 +2712,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	finish_arch_switch(prev);
 	finish_lock_switch(rq, prev);
 #ifdef CONFIG_SMP
-	if (current->sched_class->post_schedule)
+	if (post_schedule)
 		current->sched_class->post_schedule(rq);
 #endif
 
@@ -2935,6 +3019,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 		     struct sched_domain *sd, enum cpu_idle_type idle,
 		     int *all_pinned)
 {
+	int tsk_cache_hot = 0;
 	/*
 	 * We do not migrate tasks that are:
 	 * 1) running (obviously), or
@@ -2958,10 +3043,11 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 	 * 2) too many balance attempts have failed.
 	 */
 
-	if (!task_hot(p, rq->clock, sd) ||
-			sd->nr_balance_failed > sd->cache_nice_tries) {
+	tsk_cache_hot = task_hot(p, rq->clock, sd);
+	if (!tsk_cache_hot ||
+		sd->nr_balance_failed > sd->cache_nice_tries) {
 #ifdef CONFIG_SCHEDSTATS
-		if (task_hot(p, rq->clock, sd)) {
+		if (tsk_cache_hot) {
 			schedstat_inc(sd, lb_hot_gained[idle]);
 			schedstat_inc(p, se.nr_forced_migrations);
 		}
@@ -2969,7 +3055,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 		return 1;
 	}
 
-	if (task_hot(p, rq->clock, sd)) {
+	if (tsk_cache_hot) {
 		schedstat_inc(p, se.nr_failed_migrations_hot);
 		return 0;
 	}
@@ -3009,6 +3095,16 @@ next:
 	pulled++;
 	rem_load_move -= p->se.load.weight;
 
+#ifdef CONFIG_PREEMPT
+	/*
+	 * NEWIDLE balancing is a source of latency, so preemptible kernels
+	 * will stop after the first task is pulled to minimize the critical
+	 * section.
+	 */
+	if (idle == CPU_NEWLY_IDLE)
+		goto out;
+#endif
+
 	/*
 	 * We only want to steal up to the prescribed amount of weighted load.
 	 */
@@ -3055,9 +3151,15 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 				sd, idle, all_pinned, &this_best_prio);
 		class = class->next;
 
+#ifdef CONFIG_PREEMPT
+		/*
+		 * NEWIDLE balancing is a source of latency, so preemptible
+		 * kernels will stop after the first task is pulled to minimize
+		 * the critical section.
+		 */
 		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
 			break;
-
+#endif
 	} while (class && max_load_move > total_load_moved);
 
 	return total_load_moved > 0;
@@ -3107,246 +3209,480 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
 
 	return 0;
 }
-
+/********** Helpers for find_busiest_group ************************/
 /*
- * find_busiest_group finds and returns the busiest CPU group within the
- * domain. It calculates and returns the amount of weighted load which
- * should be moved to restore balance via the imbalance parameter.
+ * sd_lb_stats - Structure to store the statistics of a sched_domain
+ * 		during load balancing.
  */
-static struct sched_group *
-find_busiest_group(struct sched_domain *sd, int this_cpu,
-		   unsigned long *imbalance, enum cpu_idle_type idle,
-		   int *sd_idle, const struct cpumask *cpus, int *balance)
-{
-	struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
-	unsigned long max_load, avg_load, total_load, this_load, total_pwr;
-	unsigned long max_pull;
-	unsigned long busiest_load_per_task, busiest_nr_running;
-	unsigned long this_load_per_task, this_nr_running;
-	int load_idx, group_imb = 0;
+struct sd_lb_stats {
+	struct sched_group *busiest; /* Busiest group in this sd */
+	struct sched_group *this;  /* Local group in this sd */
+	unsigned long total_load;  /* Total load of all groups in sd */
+	unsigned long total_pwr;   /*	Total power of all groups in sd */
+	unsigned long avg_load;	   /* Average load across all groups in sd */
+
+	/** Statistics of this group */
+	unsigned long this_load;
+	unsigned long this_load_per_task;
+	unsigned long this_nr_running;
+
+	/* Statistics of the busiest group */
+	unsigned long max_load;
+	unsigned long busiest_load_per_task;
+	unsigned long busiest_nr_running;
+
+	int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-	int power_savings_balance = 1;
-	unsigned long leader_nr_running = 0, min_load_per_task = 0;
-	unsigned long min_nr_running = ULONG_MAX;
-	struct sched_group *group_min = NULL, *group_leader = NULL;
+	int power_savings_balance; /* Is powersave balance needed for this sd */
+	struct sched_group *group_min; /* Least loaded group in sd */
+	struct sched_group *group_leader; /* Group which relieves group_min */
+	unsigned long min_load_per_task; /* load_per_task in group_min */
+	unsigned long leader_nr_running; /* Nr running of group_leader */
+	unsigned long min_nr_running; /* Nr running of group_min */
 #endif
+};
 
-	max_load = this_load = total_load = total_pwr = 0;
-	busiest_load_per_task = busiest_nr_running = 0;
-	this_load_per_task = this_nr_running = 0;
+/*
+ * sg_lb_stats - stats of a sched_group required for load_balancing
+ */
+struct sg_lb_stats {
+	unsigned long avg_load; /*Avg load across the CPUs of the group */
+	unsigned long group_load; /* Total load over the CPUs of the group */
+	unsigned long sum_nr_running; /* Nr tasks running in the group */
+	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
+	unsigned long group_capacity;
+	int group_imb; /* Is there an imbalance in the group ? */
+};
 
-	if (idle == CPU_NOT_IDLE)
+/**
+ * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
+ * @group: The group whose first cpu is to be returned.
+ */
+static inline unsigned int group_first_cpu(struct sched_group *group)
+{
+	return cpumask_first(sched_group_cpus(group));
+}
+
+/**
+ * get_sd_load_idx - Obtain the load index for a given sched domain.
+ * @sd: The sched_domain whose load_idx is to be obtained.
+ * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
+ */
+static inline int get_sd_load_idx(struct sched_domain *sd,
+					enum cpu_idle_type idle)
+{
+	int load_idx;
+
+	switch (idle) {
+	case CPU_NOT_IDLE:
 		load_idx = sd->busy_idx;
-	else if (idle == CPU_NEWLY_IDLE)
+		break;
+
+	case CPU_NEWLY_IDLE:
 		load_idx = sd->newidle_idx;
-	else
+		break;
+	default:
 		load_idx = sd->idle_idx;
+		break;
+	}
 
-	do {
-		unsigned long load, group_capacity, max_cpu_load, min_cpu_load;
-		int local_group;
-		int i;
-		int __group_imb = 0;
-		unsigned int balance_cpu = -1, first_idle_cpu = 0;
-		unsigned long sum_nr_running, sum_weighted_load;
-		unsigned long sum_avg_load_per_task;
-		unsigned long avg_load_per_task;
+	return load_idx;
+}
 
-		local_group = cpumask_test_cpu(this_cpu,
-					       sched_group_cpus(group));
 
-		if (local_group)
-			balance_cpu = cpumask_first(sched_group_cpus(group));
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * init_sd_power_savings_stats - Initialize power savings statistics for
+ * the given sched_domain, during load balancing.
+ *
+ * @sd: Sched domain whose power-savings statistics are to be initialized.
+ * @sds: Variable containing the statistics for sd.
+ * @idle: Idle status of the CPU at which we're performing load-balancing.
+ */
+static inline void init_sd_power_savings_stats(struct sched_domain *sd,
+	struct sd_lb_stats *sds, enum cpu_idle_type idle)
+{
+	/*
+	 * Busy processors will not participate in power savings
+	 * balance.
+	 */
+	if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
+		sds->power_savings_balance = 0;
+	else {
+		sds->power_savings_balance = 1;
+		sds->min_nr_running = ULONG_MAX;
+		sds->leader_nr_running = 0;
+	}
+}
 
-		/* Tally up the load of all CPUs in the group */
-		sum_weighted_load = sum_nr_running = avg_load = 0;
-		sum_avg_load_per_task = avg_load_per_task = 0;
+/**
+ * update_sd_power_savings_stats - Update the power saving stats for a
+ * sched_domain while performing load balancing.
+ *
+ * @group: sched_group belonging to the sched_domain under consideration.
+ * @sds: Variable containing the statistics of the sched_domain
+ * @local_group: Does group contain the CPU for which we're performing
+ * 		load balancing ?
+ * @sgs: Variable containing the statistics of the group.
+ */
+static inline void update_sd_power_savings_stats(struct sched_group *group,
+	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
+{
 
-		max_cpu_load = 0;
-		min_cpu_load = ~0UL;
+	if (!sds->power_savings_balance)
+		return;
 
-		for_each_cpu_and(i, sched_group_cpus(group), cpus) {
-			struct rq *rq = cpu_rq(i);
+	/*
+	 * If the local group is idle or completely loaded
+	 * no need to do power savings balance at this domain
+	 */
+	if (local_group && (sds->this_nr_running >= sgs->group_capacity ||
+				!sds->this_nr_running))
+		sds->power_savings_balance = 0;
 
-			if (*sd_idle && rq->nr_running)
-				*sd_idle = 0;
+	/*
+	 * If a group is already running at full capacity or idle,
+	 * don't include that group in power savings calculations
+	 */
+	if (!sds->power_savings_balance ||
+		sgs->sum_nr_running >= sgs->group_capacity ||
+		!sgs->sum_nr_running)
+		return;
 
-			/* Bias balancing toward cpus of our domain */
-			if (local_group) {
-				if (idle_cpu(i) && !first_idle_cpu) {
-					first_idle_cpu = 1;
-					balance_cpu = i;
-				}
+	/*
+	 * Calculate the group which has the least non-idle load.
+	 * This is the group from where we need to pick up the load
+	 * for saving power
+	 */
+	if ((sgs->sum_nr_running < sds->min_nr_running) ||
+	    (sgs->sum_nr_running == sds->min_nr_running &&
+	     group_first_cpu(group) > group_first_cpu(sds->group_min))) {
+		sds->group_min = group;
+		sds->min_nr_running = sgs->sum_nr_running;
+		sds->min_load_per_task = sgs->sum_weighted_load /
+						sgs->sum_nr_running;
+	}
 
-				load = target_load(i, load_idx);
-			} else {
-				load = source_load(i, load_idx);
-				if (load > max_cpu_load)
-					max_cpu_load = load;
-				if (min_cpu_load > load)
-					min_cpu_load = load;
-			}
+	/*
+	 * Calculate the group which is almost near its
+	 * capacity but still has some space to pick up some load
+	 * from other group and save more power
+	 */
+	if (sgs->sum_nr_running > sgs->group_capacity - 1)
+		return;
 
-			avg_load += load;
-			sum_nr_running += rq->nr_running;
-			sum_weighted_load += weighted_cpuload(i);
+	if (sgs->sum_nr_running > sds->leader_nr_running ||
+	    (sgs->sum_nr_running == sds->leader_nr_running &&
+	     group_first_cpu(group) < group_first_cpu(sds->group_leader))) {
+		sds->group_leader = group;
+		sds->leader_nr_running = sgs->sum_nr_running;
+	}
+}
 
-			sum_avg_load_per_task += cpu_avg_load_per_task(i);
-		}
+/**
+ * check_power_save_busiest_group - see if there is potential for some power-savings balance
+ * @sds: Variable containing the statistics of the sched_domain
+ *	under consideration.
+ * @this_cpu: Cpu at which we're currently performing load-balancing.
+ * @imbalance: Variable to store the imbalance.
+ *
+ * Description:
+ * Check if we have potential to perform some power-savings balance.
+ * If yes, set the busiest group to be the least loaded group in the
+ * sched_domain, so that it's CPUs can be put to idle.
+ *
+ * Returns 1 if there is potential to perform power-savings balance.
+ * Else returns 0.
+ */
+static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
+					int this_cpu, unsigned long *imbalance)
+{
+	if (!sds->power_savings_balance)
+		return 0;
 
-		/*
-		 * First idle cpu or the first cpu(busiest) in this sched group
-		 * is eligible for doing load balancing at this and above
-		 * domains. In the newly idle case, we will allow all the cpu's
-		 * to do the newly idle load balance.
-		 */
-		if (idle != CPU_NEWLY_IDLE && local_group &&
-		    balance_cpu != this_cpu && balance) {
-			*balance = 0;
-			goto ret;
-		}
+	if (sds->this != sds->group_leader ||
+			sds->group_leader == sds->group_min)
+		return 0;
 
-		total_load += avg_load;
-		total_pwr += group->__cpu_power;
+	*imbalance = sds->min_load_per_task;
+	sds->busiest = sds->group_min;
 
-		/* Adjust by relative CPU power of the group */
-		avg_load = sg_div_cpu_power(group,
-				avg_load * SCHED_LOAD_SCALE);
+	if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
+		cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
+			group_first_cpu(sds->group_leader);
+	}
+
+	return 1;
 
+}
+#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+static inline void init_sd_power_savings_stats(struct sched_domain *sd,
+	struct sd_lb_stats *sds, enum cpu_idle_type idle)
+{
+	return;
+}
 
-		/*
-		 * Consider the group unbalanced when the imbalance is larger
-		 * than the average weight of two tasks.
-		 *
-		 * APZ: with cgroup the avg task weight can vary wildly and
-		 *      might not be a suitable number - should we keep a
-		 *      normalized nr_running number somewhere that negates
-		 *      the hierarchy?
-		 */
-		avg_load_per_task = sg_div_cpu_power(group,
-				sum_avg_load_per_task * SCHED_LOAD_SCALE);
+static inline void update_sd_power_savings_stats(struct sched_group *group,
+	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
+{
+	return;
+}
+
+static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
+					int this_cpu, unsigned long *imbalance)
+{
+	return 0;
+}
+#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+
+
+/**
+ * update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @group: sched_group whose statistics are to be updated.
+ * @this_cpu: Cpu for which load balance is currently performed.
+ * @idle: Idle status of this_cpu
+ * @load_idx: Load index of sched_domain of this_cpu for load calc.
+ * @sd_idle: Idle status of the sched_domain containing group.
+ * @local_group: Does group contain this_cpu.
+ * @cpus: Set of cpus considered for load balancing.
+ * @balance: Should we balance.
+ * @sgs: variable to hold the statistics for this group.
+ */
+static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
+			enum cpu_idle_type idle, int load_idx, int *sd_idle,
+			int local_group, const struct cpumask *cpus,
+			int *balance, struct sg_lb_stats *sgs)
+{
+	unsigned long load, max_cpu_load, min_cpu_load;
+	int i;
+	unsigned int balance_cpu = -1, first_idle_cpu = 0;
+	unsigned long sum_avg_load_per_task;
+	unsigned long avg_load_per_task;
+
+	if (local_group)
+		balance_cpu = group_first_cpu(group);
+
+	/* Tally up the load of all CPUs in the group */
+	sum_avg_load_per_task = avg_load_per_task = 0;
+	max_cpu_load = 0;
+	min_cpu_load = ~0UL;
 
-		if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
-			__group_imb = 1;
+	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
+		struct rq *rq = cpu_rq(i);
 
-		group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
+		if (*sd_idle && rq->nr_running)
+			*sd_idle = 0;
 
+		/* Bias balancing toward cpus of our domain */
 		if (local_group) {
-			this_load = avg_load;
-			this = group;
-			this_nr_running = sum_nr_running;
-			this_load_per_task = sum_weighted_load;
-		} else if (avg_load > max_load &&
-			   (sum_nr_running > group_capacity || __group_imb)) {
-			max_load = avg_load;
-			busiest = group;
-			busiest_nr_running = sum_nr_running;
-			busiest_load_per_task = sum_weighted_load;
-			group_imb = __group_imb;
+			if (idle_cpu(i) && !first_idle_cpu) {
+				first_idle_cpu = 1;
+				balance_cpu = i;
+			}
+
+			load = target_load(i, load_idx);
+		} else {
+			load = source_load(i, load_idx);
+			if (load > max_cpu_load)
+				max_cpu_load = load;
+			if (min_cpu_load > load)
+				min_cpu_load = load;
 		}
 
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-		/*
-		 * Busy processors will not participate in power savings
-		 * balance.
-		 */
-		if (idle == CPU_NOT_IDLE ||
-				!(sd->flags & SD_POWERSAVINGS_BALANCE))
-			goto group_next;
+		sgs->group_load += load;
+		sgs->sum_nr_running += rq->nr_running;
+		sgs->sum_weighted_load += weighted_cpuload(i);
 
-		/*
-		 * If the local group is idle or completely loaded
-		 * no need to do power savings balance at this domain
-		 */
-		if (local_group && (this_nr_running >= group_capacity ||
-				    !this_nr_running))
-			power_savings_balance = 0;
+		sum_avg_load_per_task += cpu_avg_load_per_task(i);
+	}
 
-		/*
-		 * If a group is already running at full capacity or idle,
-		 * don't include that group in power savings calculations
-		 */
-		if (!power_savings_balance || sum_nr_running >= group_capacity
-		    || !sum_nr_running)
-			goto group_next;
+	/*
+	 * First idle cpu or the first cpu(busiest) in this sched group
+	 * is eligible for doing load balancing at this and above
+	 * domains. In the newly idle case, we will allow all the cpu's
+	 * to do the newly idle load balance.
+	 */
+	if (idle != CPU_NEWLY_IDLE && local_group &&
+	    balance_cpu != this_cpu && balance) {
+		*balance = 0;
+		return;
+	}
 
-		/*
-		 * Calculate the group which has the least non-idle load.
-		 * This is the group from where we need to pick up the load
-		 * for saving power
-		 */
-		if ((sum_nr_running < min_nr_running) ||
-		    (sum_nr_running == min_nr_running &&
-		     cpumask_first(sched_group_cpus(group)) >
-		     cpumask_first(sched_group_cpus(group_min)))) {
-			group_min = group;
-			min_nr_running = sum_nr_running;
-			min_load_per_task = sum_weighted_load /
-						sum_nr_running;
-		}
+	/* Adjust by relative CPU power of the group */
+	sgs->avg_load = sg_div_cpu_power(group,
+			sgs->group_load * SCHED_LOAD_SCALE);
 
-		/*
-		 * Calculate the group which is almost near its
-		 * capacity but still has some space to pick up some load
-		 * from other group and save more power
-		 */
-		if (sum_nr_running <= group_capacity - 1) {
-			if (sum_nr_running > leader_nr_running ||
-			    (sum_nr_running == leader_nr_running &&
-			     cpumask_first(sched_group_cpus(group)) <
-			     cpumask_first(sched_group_cpus(group_leader)))) {
-				group_leader = group;
-				leader_nr_running = sum_nr_running;
-			}
+
+	/*
+	 * Consider the group unbalanced when the imbalance is larger
+	 * than the average weight of two tasks.
+	 *
+	 * APZ: with cgroup the avg task weight can vary wildly and
+	 *      might not be a suitable number - should we keep a
+	 *      normalized nr_running number somewhere that negates
+	 *      the hierarchy?
+	 */
+	avg_load_per_task = sg_div_cpu_power(group,
+			sum_avg_load_per_task * SCHED_LOAD_SCALE);
+
+	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+		sgs->group_imb = 1;
+
+	sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
+
+}
+
+/**
+ * update_sd_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: sched_domain whose statistics are to be updated.
+ * @this_cpu: Cpu for which load balance is currently performed.
+ * @idle: Idle status of this_cpu
+ * @sd_idle: Idle status of the sched_domain containing group.
+ * @cpus: Set of cpus considered for load balancing.
+ * @balance: Should we balance.
+ * @sds: variable to hold the statistics for this sched_domain.
+ */
+static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
+			enum cpu_idle_type idle, int *sd_idle,
+			const struct cpumask *cpus, int *balance,
+			struct sd_lb_stats *sds)
+{
+	struct sched_group *group = sd->groups;
+	struct sg_lb_stats sgs;
+	int load_idx;
+
+	init_sd_power_savings_stats(sd, sds, idle);
+	load_idx = get_sd_load_idx(sd, idle);
+
+	do {
+		int local_group;
+
+		local_group = cpumask_test_cpu(this_cpu,
+					       sched_group_cpus(group));
+		memset(&sgs, 0, sizeof(sgs));
+		update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
+				local_group, cpus, balance, &sgs);
+
+		if (local_group && balance && !(*balance))
+			return;
+
+		sds->total_load += sgs.group_load;
+		sds->total_pwr += group->__cpu_power;
+
+		if (local_group) {
+			sds->this_load = sgs.avg_load;
+			sds->this = group;
+			sds->this_nr_running = sgs.sum_nr_running;
+			sds->this_load_per_task = sgs.sum_weighted_load;
+		} else if (sgs.avg_load > sds->max_load &&
+			   (sgs.sum_nr_running > sgs.group_capacity ||
+				sgs.group_imb)) {
+			sds->max_load = sgs.avg_load;
+			sds->busiest = group;
+			sds->busiest_nr_running = sgs.sum_nr_running;
+			sds->busiest_load_per_task = sgs.sum_weighted_load;
+			sds->group_imb = sgs.group_imb;
 		}
-group_next:
-#endif
+
+		update_sd_power_savings_stats(group, sds, local_group, &sgs);
 		group = group->next;
 	} while (group != sd->groups);
 
-	if (!busiest || this_load >= max_load || busiest_nr_running == 0)
-		goto out_balanced;
-
-	avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;
+}
 
-	if (this_load >= avg_load ||
-			100*max_load <= sd->imbalance_pct*this_load)
-		goto out_balanced;
+/**
+ * fix_small_imbalance - Calculate the minor imbalance that exists
+ *			amongst the groups of a sched_domain, during
+ *			load balancing.
+ * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
+ * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
+ * @imbalance: Variable to store the imbalance.
+ */
+static inline void fix_small_imbalance(struct sd_lb_stats *sds,
+				int this_cpu, unsigned long *imbalance)
+{
+	unsigned long tmp, pwr_now = 0, pwr_move = 0;
+	unsigned int imbn = 2;
+
+	if (sds->this_nr_running) {
+		sds->this_load_per_task /= sds->this_nr_running;
+		if (sds->busiest_load_per_task >
+				sds->this_load_per_task)
+			imbn = 1;
+	} else
+		sds->this_load_per_task =
+			cpu_avg_load_per_task(this_cpu);
 
-	busiest_load_per_task /= busiest_nr_running;
-	if (group_imb)
-		busiest_load_per_task = min(busiest_load_per_task, avg_load);
+	if (sds->max_load - sds->this_load + sds->busiest_load_per_task >=
+			sds->busiest_load_per_task * imbn) {
+		*imbalance = sds->busiest_load_per_task;
+		return;
+	}
 
 	/*
-	 * We're trying to get all the cpus to the average_load, so we don't
-	 * want to push ourselves above the average load, nor do we wish to
-	 * reduce the max loaded cpu below the average load, as either of these
-	 * actions would just result in more rebalancing later, and ping-pong
-	 * tasks around. Thus we look for the minimum possible imbalance.
-	 * Negative imbalances (*we* are more loaded than anyone else) will
-	 * be counted as no imbalance for these purposes -- we can't fix that
-	 * by pulling tasks to us. Be careful of negative numbers as they'll
-	 * appear as very large values with unsigned longs.
+	 * OK, we don't have enough imbalance to justify moving tasks,
+	 * however we may be able to increase total CPU power used by
+	 * moving them.
 	 */
-	if (max_load <= busiest_load_per_task)
-		goto out_balanced;
 
+	pwr_now += sds->busiest->__cpu_power *
+			min(sds->busiest_load_per_task, sds->max_load);
+	pwr_now += sds->this->__cpu_power *
+			min(sds->this_load_per_task, sds->this_load);
+	pwr_now /= SCHED_LOAD_SCALE;
+
+	/* Amount of load we'd subtract */
+	tmp = sg_div_cpu_power(sds->busiest,
+			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+	if (sds->max_load > tmp)
+		pwr_move += sds->busiest->__cpu_power *
+			min(sds->busiest_load_per_task, sds->max_load - tmp);
+
+	/* Amount of load we'd add */
+	if (sds->max_load * sds->busiest->__cpu_power <
+		sds->busiest_load_per_task * SCHED_LOAD_SCALE)
+		tmp = sg_div_cpu_power(sds->this,
+			sds->max_load * sds->busiest->__cpu_power);
+	else
+		tmp = sg_div_cpu_power(sds->this,
+			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+	pwr_move += sds->this->__cpu_power *
+			min(sds->this_load_per_task, sds->this_load + tmp);
+	pwr_move /= SCHED_LOAD_SCALE;
+
+	/* Move if we gain throughput */
+	if (pwr_move > pwr_now)
+		*imbalance = sds->busiest_load_per_task;
+}
+
+/**
+ * calculate_imbalance - Calculate the amount of imbalance present within the
+ *			 groups of a given sched_domain during load balance.
+ * @sds: statistics of the sched_domain whose imbalance is to be calculated.
+ * @this_cpu: Cpu for which currently load balance is being performed.
+ * @imbalance: The variable to store the imbalance.
+ */
+static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
+		unsigned long *imbalance)
+{
+	unsigned long max_pull;
 	/*
 	 * In the presence of smp nice balancing, certain scenarios can have
 	 * max load less than avg load(as we skip the groups at or below
 	 * its cpu_power, while calculating max_load..)
 	 */
-	if (max_load < avg_load) {
+	if (sds->max_load < sds->avg_load) {
 		*imbalance = 0;
-		goto small_imbalance;
+		return fix_small_imbalance(sds, this_cpu, imbalance);
 	}
 
 	/* Don't want to pull so many tasks that a group would go idle */
-	max_pull = min(max_load - avg_load, max_load - busiest_load_per_task);
+	max_pull = min(sds->max_load - sds->avg_load,
+			sds->max_load - sds->busiest_load_per_task);
 
 	/* How much load to actually move to equalise the imbalance */
-	*imbalance = min(max_pull * busiest->__cpu_power,
-				(avg_load - this_load) * this->__cpu_power)
+	*imbalance = min(max_pull * sds->busiest->__cpu_power,
+		(sds->avg_load - sds->this_load) * sds->this->__cpu_power)
 			/ SCHED_LOAD_SCALE;
 
 	/*
@@ -3355,78 +3691,110 @@ group_next:
 	 * a think about bumping its value to force at least one task to be
 	 * moved
 	 */
-	if (*imbalance < busiest_load_per_task) {
-		unsigned long tmp, pwr_now, pwr_move;
-		unsigned int imbn;
-
-small_imbalance:
-		pwr_move = pwr_now = 0;
-		imbn = 2;
-		if (this_nr_running) {
-			this_load_per_task /= this_nr_running;
-			if (busiest_load_per_task > this_load_per_task)
-				imbn = 1;
-		} else
-			this_load_per_task = cpu_avg_load_per_task(this_cpu);
+	if (*imbalance < sds->busiest_load_per_task)
+		return fix_small_imbalance(sds, this_cpu, imbalance);
 
-		if (max_load - this_load + busiest_load_per_task >=
-					busiest_load_per_task * imbn) {
-			*imbalance = busiest_load_per_task;
-			return busiest;
-		}
+}
+/******* find_busiest_group() helpers end here *********************/
 
-		/*
-		 * OK, we don't have enough imbalance to justify moving tasks,
-		 * however we may be able to increase total CPU power used by
-		 * moving them.
-		 */
+/**
+ * find_busiest_group - Returns the busiest group within the sched_domain
+ * if there is an imbalance. If there isn't an imbalance, and
+ * the user has opted for power-savings, it returns a group whose
+ * CPUs can be put to idle by rebalancing those tasks elsewhere, if
+ * such a group exists.
+ *
+ * Also calculates the amount of weighted load which should be moved
+ * to restore balance.
+ *
+ * @sd: The sched_domain whose busiest group is to be returned.
+ * @this_cpu: The cpu for which load balancing is currently being performed.
+ * @imbalance: Variable which stores amount of weighted load which should
+ *		be moved to restore balance/put a group to idle.
+ * @idle: The idle status of this_cpu.
+ * @sd_idle: The idleness of sd
+ * @cpus: The set of CPUs under consideration for load-balancing.
+ * @balance: Pointer to a variable indicating if this_cpu
+ *	is the appropriate cpu to perform load balancing at this_level.
+ *
+ * Returns:	- the busiest group if imbalance exists.
+ *		- If no imbalance and user has opted for power-savings balance,
+ *		   return the least loaded group whose CPUs can be
+ *		   put to idle by rebalancing its tasks onto our group.
+ */
+static struct sched_group *
+find_busiest_group(struct sched_domain *sd, int this_cpu,
+		   unsigned long *imbalance, enum cpu_idle_type idle,
+		   int *sd_idle, const struct cpumask *cpus, int *balance)
+{
+	struct sd_lb_stats sds;
 
-		pwr_now += busiest->__cpu_power *
-				min(busiest_load_per_task, max_load);
-		pwr_now += this->__cpu_power *
-				min(this_load_per_task, this_load);
-		pwr_now /= SCHED_LOAD_SCALE;
-
-		/* Amount of load we'd subtract */
-		tmp = sg_div_cpu_power(busiest,
-				busiest_load_per_task * SCHED_LOAD_SCALE);
-		if (max_load > tmp)
-			pwr_move += busiest->__cpu_power *
-				min(busiest_load_per_task, max_load - tmp);
-
-		/* Amount of load we'd add */
-		if (max_load * busiest->__cpu_power <
-				busiest_load_per_task * SCHED_LOAD_SCALE)
-			tmp = sg_div_cpu_power(this,
-					max_load * busiest->__cpu_power);
-		else
-			tmp = sg_div_cpu_power(this,
-				busiest_load_per_task * SCHED_LOAD_SCALE);
-		pwr_move += this->__cpu_power *
-				min(this_load_per_task, this_load + tmp);
-		pwr_move /= SCHED_LOAD_SCALE;
+	memset(&sds, 0, sizeof(sds));
 
-		/* Move if we gain throughput */
-		if (pwr_move > pwr_now)
-			*imbalance = busiest_load_per_task;
-	}
+	/*
+	 * Compute the various statistics relavent for load balancing at
+	 * this level.
+	 */
+	update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
+					balance, &sds);
+
+	/* Cases where imbalance does not exist from POV of this_cpu */
+	/* 1) this_cpu is not the appropriate cpu to perform load balancing
+	 *    at this level.
+	 * 2) There is no busy sibling group to pull from.
+	 * 3) This group is the busiest group.
+	 * 4) This group is more busy than the avg busieness at this
+	 *    sched_domain.
+	 * 5) The imbalance is within the specified limit.
+	 * 6) Any rebalance would lead to ping-pong
+	 */
+	if (balance && !(*balance))
+		goto ret;
 
-	return busiest;
+	if (!sds.busiest || sds.busiest_nr_running == 0)
+		goto out_balanced;
 
-out_balanced:
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-	if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
-		goto ret;
+	if (sds.this_load >= sds.max_load)
+		goto out_balanced;
 
-	if (this == group_leader && group_leader != group_min) {
-		*imbalance = min_load_per_task;
-		if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
-			cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
-				cpumask_first(sched_group_cpus(group_leader));
-		}
-		return group_min;
-	}
-#endif
+	sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
+
+	if (sds.this_load >= sds.avg_load)
+		goto out_balanced;
+
+	if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+		goto out_balanced;
+
+	sds.busiest_load_per_task /= sds.busiest_nr_running;
+	if (sds.group_imb)
+		sds.busiest_load_per_task =
+			min(sds.busiest_load_per_task, sds.avg_load);
+
+	/*
+	 * We're trying to get all the cpus to the average_load, so we don't
+	 * want to push ourselves above the average load, nor do we wish to
+	 * reduce the max loaded cpu below the average load, as either of these
+	 * actions would just result in more rebalancing later, and ping-pong
+	 * tasks around. Thus we look for the minimum possible imbalance.
+	 * Negative imbalances (*we* are more loaded than anyone else) will
+	 * be counted as no imbalance for these purposes -- we can't fix that
+	 * by pulling tasks to us. Be careful of negative numbers as they'll
+	 * appear as very large values with unsigned longs.
+	 */
+	if (sds.max_load <= sds.busiest_load_per_task)
+		goto out_balanced;
+
+	/* Looks like there is an imbalance. Compute it */
+	calculate_imbalance(&sds, this_cpu, imbalance);
+	return sds.busiest;
+
+out_balanced:
+	/*
+	 * There is no obvious imbalance. But check if we can do some balancing
+	 * to save power.
+	 */
+	if (check_power_save_busiest_group(&sds, this_cpu, imbalance))
+		return sds.busiest;
 ret:
 	*imbalance = 0;
 	return NULL;
@@ -3470,19 +3838,23 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
  */
 #define MAX_PINNED_INTERVAL	512
 
+/* Working cpumask for load_balance and load_balance_newidle. */
+static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
  */
 static int load_balance(int this_cpu, struct rq *this_rq,
 			struct sched_domain *sd, enum cpu_idle_type idle,
-			int *balance, struct cpumask *cpus)
+			int *balance)
 {
 	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
 	struct sched_group *group;
 	unsigned long imbalance;
 	struct rq *busiest;
 	unsigned long flags;
+	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
 	cpumask_setall(cpus);
 
@@ -3637,8 +4009,7 @@ out:
  * this_rq is locked.
  */
 static int
-load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
-			struct cpumask *cpus)
+load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
 {
 	struct sched_group *group;
 	struct rq *busiest = NULL;
@@ -3646,6 +4017,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
 	int ld_moved = 0;
 	int sd_idle = 0;
 	int all_pinned = 0;
+	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
 	cpumask_setall(cpus);
 
@@ -3786,10 +4158,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 	struct sched_domain *sd;
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
-	cpumask_var_t tmpmask;
-
-	if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
-		return;
 
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
@@ -3800,7 +4168,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		if (sd->flags & SD_BALANCE_NEWIDLE)
 			/* If we've pulled tasks over stop searching: */
 			pulled_task = load_balance_newidle(this_cpu, this_rq,
-							   sd, tmpmask);
+							   sd);
 
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
@@ -3815,7 +4183,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		 */
 		this_rq->next_balance = next_balance;
 	}
-	free_cpumask_var(tmpmask);
 }
 
 /*
@@ -3902,19 +4269,24 @@ int select_nohz_load_balancer(int stop_tick)
 	int cpu = smp_processor_id();
 
 	if (stop_tick) {
-		cpumask_set_cpu(cpu, nohz.cpu_mask);
 		cpu_rq(cpu)->in_nohz_recently = 1;
 
-		/*
-		 * If we are going offline and still the leader, give up!
-		 */
-		if (!cpu_active(cpu) &&
-		    atomic_read(&nohz.load_balancer) == cpu) {
+		if (!cpu_active(cpu)) {
+			if (atomic_read(&nohz.load_balancer) != cpu)
+				return 0;
+
+			/*
+			 * If we are going offline and still the leader,
+			 * give up!
+			 */
 			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
 				BUG();
+
 			return 0;
 		}
 
+		cpumask_set_cpu(cpu, nohz.cpu_mask);
+
 		/* time for ilb owner also to sleep */
 		if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
 			if (atomic_read(&nohz.load_balancer) == cpu)
@@ -3960,11 +4332,6 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	unsigned long next_balance = jiffies + 60*HZ;
 	int update_next_balance = 0;
 	int need_serialize;
-	cpumask_var_t tmp;
-
-	/* Fails alloc?  Rebalancing probably not a priority right now. */
-	if (!alloc_cpumask_var(&tmp, GFP_ATOMIC))
-		return;
 
 	for_each_domain(cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
@@ -3989,7 +4356,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		}
 
 		if (time_after_eq(jiffies, sd->last_balance + interval)) {
-			if (load_balance(cpu, rq, sd, idle, &balance, tmp)) {
+			if (load_balance(cpu, rq, sd, idle, &balance)) {
 				/*
 				 * We've pulled tasks over so either we're no
 				 * longer idle, or one of our SMT siblings is
@@ -4023,8 +4390,6 @@ out:
 	 */
 	if (likely(update_next_balance))
 		rq->next_balance = next_balance;
-
-	free_cpumask_var(tmp);
 }
 
 /*
@@ -4074,6 +4439,11 @@ static void run_rebalance_domains(struct softirq_action *h)
 #endif
 }
 
+static inline int on_null_domain(int cpu)
+{
+	return !rcu_dereference(cpu_rq(cpu)->sd);
+}
+
 /*
  * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
  *
@@ -4131,7 +4501,9 @@ static inline void trigger_load_balance(struct rq *rq, int cpu)
 	    cpumask_test_cpu(cpu, nohz.cpu_mask))
 		return;
 #endif
-	if (time_after_eq(jiffies, rq->next_balance))
+	/* Don't need to rebalance while attached to NULL domain */
+	if (time_after_eq(jiffies, rq->next_balance) &&
+	    likely(!on_null_domain(cpu)))
 		raise_softirq(SCHED_SOFTIRQ);
 }
 
@@ -4474,10 +4846,7 @@ void scheduler_tick(void)
 #endif
 }
 
-#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
-				defined(CONFIG_PREEMPT_TRACER))
-
-static inline unsigned long get_parent_ip(unsigned long addr)
+unsigned long get_parent_ip(unsigned long addr)
 {
 	if (in_lock_functions(addr)) {
 		addr = CALLER_ADDR2;
@@ -4487,6 +4856,9 @@ static inline unsigned long get_parent_ip(unsigned long addr)
 	return addr;
 }
 
+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+				defined(CONFIG_PREEMPT_TRACER))
+
 void __kprobes add_preempt_count(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
@@ -4578,11 +4950,33 @@ static inline void schedule_debug(struct task_struct *prev)
 #endif
 }
 
+static void put_prev_task(struct rq *rq, struct task_struct *prev)
+{
+	if (prev->state == TASK_RUNNING) {
+		u64 runtime = prev->se.sum_exec_runtime;
+
+		runtime -= prev->se.prev_sum_exec_runtime;
+		runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
+
+		/*
+		 * In order to avoid avg_overlap growing stale when we are
+		 * indeed overlapping and hence not getting put to sleep, grow
+		 * the avg_overlap on preemption.
+		 *
+		 * We use the average preemption runtime because that
+		 * correlates to the amount of cache footprint a task can
+		 * build up.
+		 */
+		update_avg(&prev->se.avg_overlap, runtime);
+	}
+	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, struct task_struct *prev)
+pick_next_task(struct rq *rq)
 {
 	const struct sched_class *class;
 	struct task_struct *p;
@@ -4654,8 +5048,8 @@ need_resched_nonpreemptible:
 	if (unlikely(!rq->nr_running))
 		idle_balance(cpu, rq);
 
-	prev->sched_class->put_prev_task(rq, prev);
-	next = pick_next_task(rq, prev);
+	put_prev_task(rq, prev);
+	next = pick_next_task(rq);
 
 	if (likely(prev != next)) {
 		sched_info_switch(prev, next);
@@ -4777,7 +5171,7 @@ asmlinkage void __sched preempt_schedule(void)
 		 * between schedule and now.
 		 */
 		barrier();
-	} while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
+	} while (need_resched());
 }
 EXPORT_SYMBOL(preempt_schedule);
 
@@ -4806,7 +5200,7 @@ asmlinkage void __sched preempt_schedule_irq(void)
 		 * between schedule and now.
 		 */
 		barrier();
-	} while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
+	} while (need_resched());
 }
 
 #endif /* CONFIG_PREEMPT */
@@ -4867,11 +5261,17 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
 	__wake_up_common(q, mode, 1, 0, NULL);
 }
 
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+{
+	__wake_up_common(q, mode, 1, 0, key);
+}
+
 /**
- * __wake_up_sync - wake up threads blocked on a waitqueue.
+ * __wake_up_sync_key - wake up threads blocked on a waitqueue.
  * @q: the waitqueue
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: opaque value to be passed to wakeup targets
  *
  * The sync wakeup differs that the waker knows that it will schedule
  * away soon, so while the target thread will be woken up, it will not
@@ -4880,8 +5280,8 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
  *
  * On UP it can prevent extra preemption.
  */
-void
-__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
 {
 	unsigned long flags;
 	int sync = 1;
@@ -4893,9 +5293,18 @@ __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
 		sync = 0;
 
 	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive, sync, NULL);
+	__wake_up_common(q, mode, nr_exclusive, sync, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
+EXPORT_SYMBOL_GPL(__wake_up_sync_key);
+
+/*
+ * __wake_up_sync - see __wake_up_sync_key()
+ */
+void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+	__wake_up_sync_key(q, mode, nr_exclusive, NULL);
+}
 EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
 
 /**
@@ -5280,7 +5689,7 @@ SYSCALL_DEFINE1(nice, int, increment)
 	if (increment > 40)
 		increment = 40;
 
-	nice = PRIO_TO_NICE(current->static_prio) + increment;
+	nice = TASK_NICE(current) + increment;
 	if (nice < -20)
 		nice = -20;
 	if (nice > 19)
@@ -6079,12 +6488,7 @@ void sched_show_task(struct task_struct *p)
 		printk(KERN_CONT " %016lx ", thread_saved_pc(p));
 #endif
 #ifdef CONFIG_DEBUG_STACK_USAGE
-	{
-		unsigned long *n = end_of_stack(p);
-		while (!*n)
-			n++;
-		free = (unsigned long)n - (unsigned long)end_of_stack(p);
-	}
+	free = stack_not_used(p);
 #endif
 	printk(KERN_CONT "%5lu %5d %6d\n", free,
 		task_pid_nr(p), task_pid_nr(p->real_parent));
@@ -6558,7 +6962,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 		if (!rq->nr_running)
 			break;
 		update_rq_clock(rq);
-		next = pick_next_task(rq, rq->curr);
+		next = pick_next_task(rq);
 		if (!next)
 			break;
 		next->sched_class->put_prev_task(rq, next);
@@ -7080,20 +7484,26 @@ static void free_rootdomain(struct root_domain *rd)
 
 static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 {
+	struct root_domain *old_rd = NULL;
 	unsigned long flags;
 
 	spin_lock_irqsave(&rq->lock, flags);
 
 	if (rq->rd) {
-		struct root_domain *old_rd = rq->rd;
+		old_rd = rq->rd;
 
 		if (cpumask_test_cpu(rq->cpu, old_rd->online))
 			set_rq_offline(rq);
 
 		cpumask_clear_cpu(rq->cpu, old_rd->span);
 
-		if (atomic_dec_and_test(&old_rd->refcount))
-			free_rootdomain(old_rd);
+		/*
+		 * If we dont want to free the old_rt yet then
+		 * set old_rd to NULL to skip the freeing later
+		 * in this function:
+		 */
+		if (!atomic_dec_and_test(&old_rd->refcount))
+			old_rd = NULL;
 	}
 
 	atomic_inc(&rd->refcount);
@@ -7104,6 +7514,9 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 		set_rq_online(rq);
 
 	spin_unlock_irqrestore(&rq->lock, flags);
+
+	if (old_rd)
+		free_rootdomain(old_rd);
 }
 
 static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
@@ -7381,7 +7794,7 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 {
 	int group;
 
-	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
 	if (sg)
 		*sg = &per_cpu(sched_group_core, group).sg;
@@ -7410,7 +7823,7 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
 	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #else
 	group = cpu;
@@ -7753,7 +8166,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		SD_INIT(sd, SIBLING);
 		set_domain_attribute(sd, attr);
 		cpumask_and(sched_domain_span(sd),
-			    &per_cpu(cpu_sibling_map, i), cpu_map);
+			    topology_thread_cpumask(i), cpu_map);
 		sd->parent = p;
 		p->child = sd;
 		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
@@ -7764,7 +8177,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 	/* Set up CPU (sibling) groups */
 	for_each_cpu(i, cpu_map) {
 		cpumask_and(this_sibling_map,
-			    &per_cpu(cpu_sibling_map, i), cpu_map);
+			    topology_thread_cpumask(i), cpu_map);
 		if (i != cpumask_first(this_sibling_map))
 			continue;
 
@@ -8345,11 +8758,15 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 	__set_bit(MAX_RT_PRIO, array->bitmap);
 
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
-	rt_rq->highest_prio = MAX_RT_PRIO;
+	rt_rq->highest_prio.curr = MAX_RT_PRIO;
+#ifdef CONFIG_SMP
+	rt_rq->highest_prio.next = MAX_RT_PRIO;
+#endif
 #endif
 #ifdef CONFIG_SMP
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
+	plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
 #endif
 
 	rt_rq->rt_time = 0;
@@ -8436,6 +8853,9 @@ void __init sched_init(void)
 #ifdef CONFIG_USER_SCHED
 	alloc_size *= 2;
 #endif
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	alloc_size += num_possible_cpus() * cpumask_size();
+#endif
 	/*
 	 * As sched_init() is called before page_alloc is setup,
 	 * we use alloc_bootmem().
@@ -8473,6 +8893,12 @@ void __init sched_init(void)
 		ptr += nr_cpu_ids * sizeof(void **);
 #endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_RT_GROUP_SCHED */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+		for_each_possible_cpu(i) {
+			per_cpu(load_balance_tmpmask, i) = (void *)ptr;
+			ptr += cpumask_size();
+		}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
 	}
 
 #ifdef CONFIG_SMP
@@ -9351,6 +9777,16 @@ static int sched_rt_global_constraints(void)
 
 	return ret;
 }
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+	/* Don't accept realtime tasks when there is no way for them to run */
+	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+		return 0;
+
+	return 1;
+}
+
 #else /* !CONFIG_RT_GROUP_SCHED */
 static int sched_rt_global_constraints(void)
 {
@@ -9444,8 +9880,7 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 		      struct task_struct *tsk)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
-	/* Don't accept realtime tasks when there is no way for them to run */
-	if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0)
+	if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
 		return -EINVAL;
 #else
 	/* We don't support RT-tasks being in separate groups */
@@ -9624,7 +10059,7 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 
 static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
 {
-	u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 	u64 data;
 
 #ifndef CONFIG_64BIT
@@ -9643,7 +10078,7 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
 
 static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
 {
-	u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 
 #ifndef CONFIG_64BIT
 	/*
@@ -9754,7 +10189,7 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 	struct cpuacct *ca;
 	int cpu;
 
-	if (!cpuacct_subsys.active)
+	if (unlikely(!cpuacct_subsys.active))
 		return;
 
 	cpu = task_cpu(tsk);
@@ -9764,7 +10199,7 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 	ca = task_ca(tsk);
 
 	for (; ca; ca = ca->parent) {
-		u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 		*cpuusage += cputime;
 	}