Merge branch 'sched-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (46 commits)
  sched: Add comments to find_busiest_group() function
  sched: Refactor the power savings balance code
  sched: Optimize the !power_savings_balance during fbg()
  sched: Create a helper function to calculate imbalance
  sched: Create helper to calculate small_imbalance in fbg()
  sched: Create a helper function to calculate sched_domain stats for fbg()
  sched: Define structure to store the sched_domain statistics for fbg()
  sched: Create a helper function to calculate sched_group stats for fbg()
  sched: Define structure to store the sched_group statistics for fbg()
  sched: Fix indentations in find_busiest_group() using gotos
  sched: Simple helper functions for find_busiest_group()
  sched: remove unused fields from struct rq
  sched: jiffies not printed per CPU
  sched: small optimisation of can_migrate_task()
  sched: fix typos in documentation
  sched: add avg_overlap decay
  x86, sched_clock(): mark variables read-mostly
  sched: optimize ttwu vs group scheduling
  sched: TIF_NEED_RESCHED -> need_reshed() cleanup
  sched: don't rebalance if attached on NULL domain
  ...

8 files changed, 1215 insertions, 494 deletions

diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 449db466bdbc..ca07c5c0c914 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -9,6 +9,44 @@
  * as published by the Free Software Foundation; version 2
  * of the License.
  */
+
+/*
+ * CONFIG_LATENCYTOP enables a kernel latency tracking infrastructure that is
+ * used by the "latencytop" userspace tool. The latency that is tracked is not
+ * the 'traditional' interrupt latency (which is primarily caused by something
+ * else consuming CPU), but instead, it is the latency an application encounters
+ * because the kernel sleeps on its behalf for various reasons.
+ *
+ * This code tracks 2 levels of statistics:
+ * 1) System level latency
+ * 2) Per process latency
+ *
+ * The latency is stored in fixed sized data structures in an accumulated form;
+ * if the "same" latency cause is hit twice, this will be tracked as one entry
+ * in the data structure. Both the count, total accumulated latency and maximum
+ * latency are tracked in this data structure. When the fixed size structure is
+ * full, no new causes are tracked until the buffer is flushed by writing to
+ * the /proc file; the userspace tool does this on a regular basis.
+ *
+ * A latency cause is identified by a stringified backtrace at the point that
+ * the scheduler gets invoked. The userland tool will use this string to
+ * identify the cause of the latency in human readable form.
+ *
+ * The information is exported via /proc/latency_stats and /proc/<pid>/latency.
+ * These files look like this:
+ *
+ * Latency Top version : v0.1
+ * 70 59433 4897 i915_irq_wait drm_ioctl vfs_ioctl do_vfs_ioctl sys_ioctl
+ * |    |    |    |
+ * |    |    |    +----> the stringified backtrace
+ * |    |    +---------> The maximum latency for this entry in microseconds
+ * |    +--------------> The accumulated latency for this entry (microseconds)
+ * +-------------------> The number of times this entry is hit
+ *
+ * (note: the average latency is the accumulated latency divided by the number
+ * of times)
+ */
+
 #include <linux/latencytop.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
@@ -72,7 +110,7 @@ account_global_scheduler_latency(struct task_struct *tsk, struct latency_record
 				firstnonnull = i;
 			continue;
 		}
-		for (q = 0 ; q < LT_BACKTRACEDEPTH ; q++) {
+		for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
 			unsigned long record = lat->backtrace[q];
 
 			if (latency_record[i].backtrace[q] != record) {
@@ -101,31 +139,52 @@ account_global_scheduler_latency(struct task_struct *tsk, struct latency_record
 	memcpy(&latency_record[i], lat, sizeof(struct latency_record));
 }
 
-static inline void store_stacktrace(struct task_struct *tsk, struct latency_record *lat)
+/*
+ * Iterator to store a backtrace into a latency record entry
+ */
+static inline void store_stacktrace(struct task_struct *tsk,
+					struct latency_record *lat)
 {
 	struct stack_trace trace;
 
 	memset(&trace, 0, sizeof(trace));
 	trace.max_entries = LT_BACKTRACEDEPTH;
 	trace.entries = &lat->backtrace[0];
-	trace.skip = 0;
 	save_stack_trace_tsk(tsk, &trace);
 }
 
+/**
+ * __account_scheduler_latency - record an occured latency
+ * @tsk - the task struct of the task hitting the latency
+ * @usecs - the duration of the latency in microseconds
+ * @inter - 1 if the sleep was interruptible, 0 if uninterruptible
+ *
+ * This function is the main entry point for recording latency entries
+ * as called by the scheduler.
+ *
+ * This function has a few special cases to deal with normal 'non-latency'
+ * sleeps: specifically, interruptible sleep longer than 5 msec is skipped
+ * since this usually is caused by waiting for events via select() and co.
+ *
+ * Negative latencies (caused by time going backwards) are also explicitly
+ * skipped.
+ */
 void __sched
-account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
+__account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
 {
 	unsigned long flags;
 	int i, q;
 	struct latency_record lat;
 
-	if (!latencytop_enabled)
-		return;
-
 	/* Long interruptible waits are generally user requested... */
 	if (inter && usecs > 5000)
 		return;
 
+	/* Negative sleeps are time going backwards */
+	/* Zero-time sleeps are non-interesting */
+	if (usecs <= 0)
+		return;
+
 	memset(&lat, 0, sizeof(lat));
 	lat.count = 1;
 	lat.time = usecs;
@@ -143,12 +202,12 @@ account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
 	if (tsk->latency_record_count >= LT_SAVECOUNT)
 		goto out_unlock;
 
-	for (i = 0; i < LT_SAVECOUNT ; i++) {
+	for (i = 0; i < LT_SAVECOUNT; i++) {
 		struct latency_record *mylat;
 		int same = 1;
 
 		mylat = &tsk->latency_record[i];
-		for (q = 0 ; q < LT_BACKTRACEDEPTH ; q++) {
+		for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
 			unsigned long record = lat.backtrace[q];
 
 			if (mylat->backtrace[q] != record) {
@@ -186,7 +245,7 @@ static int lstats_show(struct seq_file *m, void *v)
 	for (i = 0; i < MAXLR; i++) {
 		if (latency_record[i].backtrace[0]) {
 			int q;
-			seq_printf(m, "%i %li %li ",
+			seq_printf(m, "%i %lu %lu ",
 				latency_record[i].count,
 				latency_record[i].time,
 				latency_record[i].max);
@@ -223,7 +282,7 @@ static int lstats_open(struct inode *inode, struct file *filp)
 	return single_open(filp, lstats_show, NULL);
 }
 
-static struct file_operations lstats_fops = {
+static const struct file_operations lstats_fops = {
 	.open		= lstats_open,
 	.read		= seq_read,
 	.write		= lstats_write,
@@ -236,4 +295,4 @@ static int __init init_lstats_procfs(void)
 	proc_create("latency_stats", 0644, NULL, &lstats_fops);
 	return 0;
 }
-__initcall(init_lstats_procfs);
+device_initcall(init_lstats_procfs);
diff --git a/kernel/sched.c b/kernel/sched.c
index 8e2558c2ba67..9f8506d68fdc 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -331,6 +331,13 @@ 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 +398,13 @@ 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 +481,17 @@ 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 +569,6 @@ 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 +609,7 @@ 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 +638,6 @@ 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 */
@@ -1183,10 +1200,10 @@ 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 +1259,7 @@ 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();
@@ -1610,21 +1627,42 @@ 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);
@@ -1637,6 +1675,22 @@ 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)
 {
@@ -1705,6 +1759,9 @@ 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;
@@ -1712,10 +1769,15 @@ 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);
@@ -2017,7 +2079,7 @@ 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.
 		 */
@@ -2267,7 +2329,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 		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();
@@ -2345,6 +2407,22 @@ 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);
@@ -2355,8 +2433,6 @@ 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;
@@ -2386,6 +2462,8 @@ 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;
@@ -2448,6 +2526,8 @@ 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();
 }
 
@@ -2491,7 +2571,7 @@ 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)
@@ -2588,6 +2668,12 @@ 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;
 
@@ -2606,7 +2692,7 @@ 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
 
@@ -2913,6 +2999,7 @@ 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
@@ -2936,10 +3023,11 @@ 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);
 		}
@@ -2947,7 +3035,7 @@ 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;
 	}
@@ -2987,6 +3075,16 @@ 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.
 	 */
@@ -3033,9 +3131,15 @@ 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;
@@ -3085,246 +3189,479 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
 
 	return 0;
 }
+/********** Helpers for find_busiest_group ************************/
+/**
+ * sd_lb_stats - Structure to store the statistics of a sched_domain
+ * 		during load balancing.
+ */
+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; /* 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
+};
 
-/*
- * 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.
+/**
+ * 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 ? */
+};
+
+/**
+ * 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 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)
+static inline unsigned int group_first_cpu(struct sched_group *group)
 {
-	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;
-#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;
-#endif
+	return cpumask_first(sched_group_cpus(group));
+}
 
-	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;
+/**
+ * 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;
 
-	if (idle == CPU_NOT_IDLE)
+	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 - 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.
+ *
+ * @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.
+ *
+ * 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;
 
-		/*
-		 * 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);
+}
+#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;
+}
 
-		if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
-			__group_imb = 1;
+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 */
 
-		group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
 
+/**
+ * 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;
+
+	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
+		struct rq *rq = cpu_rq(i);
+
+		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 = g