From d894837f23f491aa7ed167aae767fc07cfe6e6e6 Mon Sep 17 00:00:00 2001
From: Simon Kagstrom <simon.kagstrom@netinsight.net>
Date: Wed, 23 Dec 2009 11:08:18 +0100
Subject: [PATCH 01/25] sched: might_sleep(): Make file parameter const char *

Fixes a warning when building with g++:

 warning: deprecated conversion from string constant to 'char*'

And the file parameter use is constant, so mark it as such.

Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
Cc: peterz@infradead.org
LKML-Reference: <20091223110818.442d848e@marrow.netinsight.se>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/kernel.h | 5 +++--
 kernel/sched.c         | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3fc9f5aab5f8..785d7d1099d4 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -124,7 +124,7 @@ extern int _cond_resched(void);
 #endif
 
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-  void __might_sleep(char *file, int line, int preempt_offset);
+  void __might_sleep(const char *file, int line, int preempt_offset);
 /**
  * might_sleep - annotation for functions that can sleep
  *
@@ -138,7 +138,8 @@ extern int _cond_resched(void);
 # define might_sleep() \
 	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
 #else
-  static inline void __might_sleep(char *file, int line, int preempt_offset) { }
+  static inline void __might_sleep(const char *file, int line,
+				   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
 #endif
 
diff --git a/kernel/sched.c b/kernel/sched.c
index c535cc4f6428..64298a52eaa6 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -9694,7 +9694,7 @@ static inline int preempt_count_equals(int preempt_offset)
 	return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
 }
 
-void __might_sleep(char *file, int line, int preempt_offset)
+void __might_sleep(const char *file, int line, int preempt_offset)
 {
 #ifdef in_atomic
 	static unsigned long prev_jiffy;	/* ratelimiting */

From 6d686f4564f3fc7c6e678852919e48ad331d276b Mon Sep 17 00:00:00 2001
From: H Hartley Sweeten <hartleys@visionengravers.com>
Date: Wed, 13 Jan 2010 20:21:52 -0700
Subject: [PATCH 02/25] sched: Don't expose local functions

kernel/sched: don't expose local functions

The get_rr_interval_* functions are all class methods of
struct sched_class. They are not exported so make them
static.

Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <201001132021.53253.hartleys@visionengravers.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c     | 2 +-
 kernel/sched_idletask.c | 2 +-
 kernel/sched_rt.c       | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 42ac3c9f66f6..71778601c103 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2076,7 +2076,7 @@ static void moved_group_fair(struct task_struct *p, int on_rq)
 }
 #endif
 
-unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task)
+static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task)
 {
 	struct sched_entity *se = &task->se;
 	unsigned int rr_interval = 0;
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 5f93b570d383..01332bfc61a7 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -97,7 +97,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p,
 		check_preempt_curr(rq, p, 0);
 }
 
-unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
+static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
 {
 	return 0;
 }
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index f48328ac216f..072b3fcee8d8 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1721,7 +1721,7 @@ static void set_curr_task_rt(struct rq *rq)
 	dequeue_pushable_task(rq, p);
 }
 
-unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
+static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 {
 	/*
 	 * Time slice is 0 for SCHED_FIFO tasks

From 1e3c88bdeb1260edc341e45c9fb8efd182a5c511 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 17 Dec 2009 17:00:43 +0100
Subject: [PATCH 03/25] sched: Move load balance code into sched_fair.c

Straight fwd code movement.

Since non of the load-balance abstractions are used anymore, do away with
them and simplify the code some. In preparation move the code around.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c      | 1919 ++-----------------------------------------
 kernel/sched_fair.c | 1765 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 1844 insertions(+), 1840 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 64298a52eaa6..13a2acf18b2d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1805,6 +1805,51 @@ static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
 	raw_spin_unlock(&busiest->lock);
 	lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
 }
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+	__acquires(rq1->lock)
+	__acquires(rq2->lock)
+{
+	BUG_ON(!irqs_disabled());
+	if (rq1 == rq2) {
+		raw_spin_lock(&rq1->lock);
+		__acquire(rq2->lock);	/* Fake it out ;) */
+	} else {
+		if (rq1 < rq2) {
+			raw_spin_lock(&rq1->lock);
+			raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
+		} else {
+			raw_spin_lock(&rq2->lock);
+			raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
+		}
+	}
+	update_rq_clock(rq1);
+	update_rq_clock(rq2);
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+	__releases(rq1->lock)
+	__releases(rq2->lock)
+{
+	raw_spin_unlock(&rq1->lock);
+	if (rq1 != rq2)
+		raw_spin_unlock(&rq2->lock);
+	else
+		__release(rq2->lock);
+}
+
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1834,18 +1879,14 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 #endif
 }
 
-#include "sched_stats.h"
-#include "sched_idletask.c"
-#include "sched_fair.c"
-#include "sched_rt.c"
-#ifdef CONFIG_SCHED_DEBUG
-# include "sched_debug.c"
-#endif
+static const struct sched_class rt_sched_class;
 
 #define sched_class_highest (&rt_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
 
+#include "sched_stats.h"
+
 static void inc_nr_running(struct rq *rq)
 {
 	rq->nr_running++;
@@ -1911,6 +1952,37 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
 	p->se.on_rq = 0;
 }
 
+/*
+ * activate_task - move a task to the runqueue.
+ */
+static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
+{
+	if (task_contributes_to_load(p))
+		rq->nr_uninterruptible--;
+
+	enqueue_task(rq, p, wakeup);
+	inc_nr_running(rq);
+}
+
+/*
+ * deactivate_task - remove a task from the runqueue.
+ */
+static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
+{
+	if (task_contributes_to_load(p))
+		rq->nr_uninterruptible++;
+
+	dequeue_task(rq, p, sleep);
+	dec_nr_running(rq);
+}
+
+#include "sched_idletask.c"
+#include "sched_fair.c"
+#include "sched_rt.c"
+#ifdef CONFIG_SCHED_DEBUG
+# include "sched_debug.c"
+#endif
+
 /*
  * __normal_prio - return the priority that is based on the static prio
  */
@@ -1957,30 +2029,6 @@ static int effective_prio(struct task_struct *p)
 	return p->prio;
 }
 
-/*
- * activate_task - move a task to the runqueue.
- */
-static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
-{
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
-
-	enqueue_task(rq, p, wakeup);
-	inc_nr_running(rq);
-}
-
-/*
- * deactivate_task - remove a task from the runqueue.
- */
-static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
-{
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible++;
-
-	dequeue_task(rq, p, sleep);
-	dec_nr_running(rq);
-}
-
 /**
  * task_curr - is this task currently executing on a CPU?
  * @p: the task in question.
@@ -3087,50 +3135,6 @@ static void update_cpu_load(struct rq *this_rq)
 
 #ifdef CONFIG_SMP
 
-/*
- * double_rq_lock - safely lock two runqueues
- *
- * Note this does not disable interrupts like task_rq_lock,
- * you need to do so manually before calling.
- */
-static void double_rq_lock(struct rq *rq1, struct rq *rq2)
-	__acquires(rq1->lock)
-	__acquires(rq2->lock)
-{
-	BUG_ON(!irqs_disabled());
-	if (rq1 == rq2) {
-		raw_spin_lock(&rq1->lock);
-		__acquire(rq2->lock);	/* Fake it out ;) */
-	} else {
-		if (rq1 < rq2) {
-			raw_spin_lock(&rq1->lock);
-			raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
-		} else {
-			raw_spin_lock(&rq2->lock);
-			raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
-		}
-	}
-	update_rq_clock(rq1);
-	update_rq_clock(rq2);
-}
-
-/*
- * double_rq_unlock - safely unlock two runqueues
- *
- * Note this does not restore interrupts like task_rq_unlock,
- * you need to do so manually after calling.
- */
-static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
-	__releases(rq1->lock)
-	__releases(rq2->lock)
-{
-	raw_spin_unlock(&rq1->lock);
-	if (rq1 != rq2)
-		raw_spin_unlock(&rq2->lock);
-	else
-		__release(rq2->lock);
-}
-
 /*
  * sched_exec - execve() is a valuable balancing opportunity, because at
  * this point the task has the smallest effective memory and cache footprint.
@@ -3179,1771 +3183,6 @@ again:
 	task_rq_unlock(rq, &flags);
 }
 
-/*
- * pull_task - move a task from a remote runqueue to the local runqueue.
- * Both runqueues must be locked.
- */
-static void pull_task(struct rq *src_rq, struct task_struct *p,
-		      struct rq *this_rq, int this_cpu)
-{
-	deactivate_task(src_rq, p, 0);
-	set_task_cpu(p, this_cpu);
-	activate_task(this_rq, p, 0);
-	check_preempt_curr(this_rq, p, 0);
-}
-
-/*
- * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
- */
-static
-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
-	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
-	 * 3) are cache-hot on their current CPU.
-	 */
-	if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
-		schedstat_inc(p, se.nr_failed_migrations_affine);
-		return 0;
-	}
-	*all_pinned = 0;
-
-	if (task_running(rq, p)) {
-		schedstat_inc(p, se.nr_failed_migrations_running);
-		return 0;
-	}
-
-	/*
-	 * Aggressive migration if:
-	 * 1) task is cache cold, or
-	 * 2) too many balance attempts have failed.
-	 */
-
-	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 (tsk_cache_hot) {
-			schedstat_inc(sd, lb_hot_gained[idle]);
-			schedstat_inc(p, se.nr_forced_migrations);
-		}
-#endif
-		return 1;
-	}
-
-	if (tsk_cache_hot) {
-		schedstat_inc(p, se.nr_failed_migrations_hot);
-		return 0;
-	}
-	return 1;
-}
-
-static unsigned long
-balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
-	      unsigned long max_load_move, struct sched_domain *sd,
-	      enum cpu_idle_type idle, int *all_pinned,
-	      int *this_best_prio, struct rq_iterator *iterator)
-{
-	int loops = 0, pulled = 0, pinned = 0;
-	struct task_struct *p;
-	long rem_load_move = max_load_move;
-
-	if (max_load_move == 0)
-		goto out;
-
-	pinned = 1;
-
-	/*
-	 * Start the load-balancing iterator:
-	 */
-	p = iterator->start(iterator->arg);
-next:
-	if (!p || loops++ > sysctl_sched_nr_migrate)
-		goto out;
-
-	if ((p->se.load.weight >> 1) > rem_load_move ||
-	    !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
-		p = iterator->next(iterator->arg);
-		goto next;
-	}
-
-	pull_task(busiest, p, this_rq, this_cpu);
-	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.
-	 */
-	if (rem_load_move > 0) {
-		if (p->prio < *this_best_prio)
-			*this_best_prio = p->prio;
-		p = iterator->next(iterator->arg);
-		goto next;
-	}
-out:
-	/*
-	 * Right now, this is one of only two places pull_task() is called,
-	 * so we can safely collect pull_task() stats here rather than
-	 * inside pull_task().
-	 */
-	schedstat_add(sd, lb_gained[idle], pulled);
-
-	if (all_pinned)
-		*all_pinned = pinned;
-
-	return max_load_move - rem_load_move;
-}
-
-/*
- * move_tasks tries to move up to max_load_move weighted load from busiest to
- * this_rq, as part of a balancing operation within domain "sd".
- * Returns 1 if successful and 0 otherwise.
- *
- * Called with both runqueues locked.
- */
-static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		      unsigned long max_load_move,
-		      struct sched_domain *sd, enum cpu_idle_type idle,
-		      int *all_pinned)
-{
-	const struct sched_class *class = sched_class_highest;
-	unsigned long total_load_moved = 0;
-	int this_best_prio = this_rq->curr->prio;
-
-	do {
-		total_load_moved +=
-			class->load_balance(this_rq, this_cpu, busiest,
-				max_load_move - total_load_moved,
-				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;
-}
-
-static int
-iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		   struct sched_domain *sd, enum cpu_idle_type idle,
-		   struct rq_iterator *iterator)
-{
-	struct task_struct *p = iterator->start(iterator->arg);
-	int pinned = 0;
-
-	while (p) {
-		if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
-			pull_task(busiest, p, this_rq, this_cpu);
-			/*
-			 * Right now, this is only the second place pull_task()
-			 * is called, so we can safely collect pull_task()
-			 * stats here rather than inside pull_task().
-			 */
-			schedstat_inc(sd, lb_gained[idle]);
-
-			return 1;
-		}
-		p = iterator->next(iterator->arg);
-	}
-
-	return 0;
-}
-
-/*
- * move_one_task tries to move exactly one task from busiest to this_rq, as
- * part of active balancing operations within "domain".
- * Returns 1 if successful and 0 otherwise.
- *
- * Called with both runqueues locked.
- */
-static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-			 struct sched_domain *sd, enum cpu_idle_type idle)
-{
-	const struct sched_class *class;
-
-	for_each_class(class) {
-		if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
-			return 1;
-	}
-
-	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
-};
-
-/*
- * 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 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;
-		break;
-
-	case CPU_NEWLY_IDLE:
-		load_idx = sd->newidle_idx;
-		break;
-	default:
-		load_idx = sd->idle_idx;
-		break;
-	}
-
-	return load_idx;
-}
-
-
-#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;
-	}
-}
-
-/**
- * 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)
-{
-
-	if (!sds->power_savings_balance)
-		return;
-
-	/*
-	 * 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 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;
-
-	/*
-	 * 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;
-	}
-
-	/*
-	 * 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 + 1 > sgs->group_capacity)
-		return;
-
-	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;
-	}
-}
-
-/**
- * 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;
-
-	if (sds->this != sds->group_leader ||
-			sds->group_leader == sds->group_min)
-		return 0;
-
-	*imbalance = sds->min_load_per_task;
-	sds->busiest = sds->group_min;
-
-	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;
-}
-
-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 */
-
-
-unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
-{
-	return SCHED_LOAD_SCALE;
-}
-
-unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
-{
-	return default_scale_freq_power(sd, cpu);
-}
-
-unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
-{
-	unsigned long weight = cpumask_weight(sched_domain_span(sd));
-	unsigned long smt_gain = sd->smt_gain;
-
-	smt_gain /= weight;
-
-	return smt_gain;
-}
-
-unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
-{
-	return default_scale_smt_power(sd, cpu);
-}
-
-unsigned long scale_rt_power(int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-	u64 total, available;
-
-	sched_avg_update(rq);
-
-	total = sched_avg_period() + (rq->clock - rq->age_stamp);
-	available = total - rq->rt_avg;
-
-	if (unlikely((s64)total < SCHED_LOAD_SCALE))
-		total = SCHED_LOAD_SCALE;
-
-	total >>= SCHED_LOAD_SHIFT;
-
-	return div_u64(available, total);
-}
-
-static void update_cpu_power(struct sched_domain *sd, int cpu)
-{
-	unsigned long weight = cpumask_weight(sched_domain_span(sd));
-	unsigned long power = SCHED_LOAD_SCALE;
-	struct sched_group *sdg = sd->groups;
-
-	if (sched_feat(ARCH_POWER))
-		power *= arch_scale_freq_power(sd, cpu);
-	else
-		power *= default_scale_freq_power(sd, cpu);
-
-	power >>= SCHED_LOAD_SHIFT;
-
-	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
-		if (sched_feat(ARCH_POWER))
-			power *= arch_scale_smt_power(sd, cpu);
-		else
-			power *= default_scale_smt_power(sd, cpu);
-
-		power >>= SCHED_LOAD_SHIFT;
-	}
-
-	power *= scale_rt_power(cpu);
-	power >>= SCHED_LOAD_SHIFT;
-
-	if (!power)
-		power = 1;
-
-	sdg->cpu_power = power;
-}
-
-static void update_group_power(struct sched_domain *sd, int cpu)
-{
-	struct sched_domain *child = sd->child;
-	struct sched_group *group, *sdg = sd->groups;
-	unsigned long power;
-
-	if (!child) {
-		update_cpu_power(sd, cpu);
-		return;
-	}
-
-	power = 0;
-
-	group = child->groups;
-	do {
-		power += group->cpu_power;
-		group = group->next;
-	} while (group != child->groups);
-
-	sdg->cpu_power = power;
-}
-
-/**
- * update_sg_lb_stats - Update sched_group's statistics for load balancing.
- * @sd: The sched_domain whose statistics are to be updated.
- * @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_domain *sd,
-			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);
-		if (balance_cpu == this_cpu)
-			update_group_power(sd, this_cpu);
-	}
-
-	/* 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) {
-			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;
-		}
-
-		sgs->group_load += load;
-		sgs->sum_nr_running += rq->nr_running;
-		sgs->sum_weighted_load += weighted_cpuload(i);
-
-		sum_avg_load_per_task += cpu_avg_load_per_task(i);
-	}
-
-	/*
-	 * 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;
-	}
-
-	/* Adjust by relative CPU power of the group */
-	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
-
-
-	/*
-	 * 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 = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
-		group->cpu_power;
-
-	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
-		sgs->group_imb = 1;
-
-	sgs->group_capacity =
-		DIV_ROUND_CLOSEST(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_domain *child = sd->child;
-	struct sched_group *group = sd->groups;
-	struct sg_lb_stats sgs;
-	int load_idx, prefer_sibling = 0;
-
-	if (child && child->flags & SD_PREFER_SIBLING)
-		prefer_sibling = 1;
-
-	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(sd, 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;
-
-		/*
-		 * In case the child domain prefers tasks go to siblings
-		 * first, lower the group capacity to one so that we'll try
-		 * and move all the excess tasks away.
-		 */
-		if (prefer_sibling)
-			sgs.group_capacity = min(sgs.group_capacity, 1UL);
-
-		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;
-		}
-
-		update_sd_power_savings_stats(group, sds, local_group, &sgs);
-		group = group->next;
-	} while (group != sd->groups);
-}
-
-/**
- * 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);
-
-	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;
-	}
-
-	/*
-	 * 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.
-	 */
-
-	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 = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
-		sds->busiest->cpu_power;
-	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 = (sds->max_load * sds->busiest->cpu_power) /
-			sds->this->cpu_power;
-	else
-		tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
-			sds->this->cpu_power;
-	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 (sds->max_load < sds->avg_load) {
-		*imbalance = 0;
-		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(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 * sds->busiest->cpu_power,
-		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
-			/ SCHED_LOAD_SCALE;
-
-	/*
-	 * if *imbalance is less than the average load per runnable task
-	 * there is no gaurantee that any tasks will be moved so we'll have
-	 * a think about bumping its value to force at least one task to be
-	 * moved
-	 */
-	if (*imbalance < sds->busiest_load_per_task)
-		return fix_small_imbalance(sds, this_cpu, imbalance);
-
-}
-/******* find_busiest_group() helpers end here *********************/
-
-/**
- * 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;
-
-	memset(&sds, 0, sizeof(sds));
-
-	/*
-	 * 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;
-
-	if (!sds.busiest || sds.busiest_nr_running == 0)
-		goto out_balanced;
-
-	if (sds.this_load >= sds.max_load)
-		goto out_balanced;
-
-	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;
-}
-
-/*
- * find_busiest_queue - find the busiest runqueue among the cpus in group.
- */
-static struct rq *
-find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
-		   unsigned long imbalance, const struct cpumask *cpus)
-{
-	struct rq *busiest = NULL, *rq;
-	unsigned long max_load = 0;
-	int i;
-
-	for_each_cpu(i, sched_group_cpus(group)) {
-		unsigned long power = power_of(i);
-		unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
-		unsigned long wl;
-
-		if (!cpumask_test_cpu(i, cpus))
-			continue;
-
-		rq = cpu_rq(i);
-		wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
-		wl /= power;
-
-		if (capacity && rq->nr_running == 1 && wl > imbalance)
-			continue;
-
-		if (wl > max_load) {
-			max_load = wl;
-			busiest = rq;
-		}
-	}
-
-	return busiest;
-}
-
-/*
- * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
- * so long as it is large enough.
- */
-#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)
-{
-	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_copy(cpus, cpu_active_mask);
-
-	/*
-	 * When power savings policy is enabled for the parent domain, idle
-	 * sibling can pick up load irrespective of busy siblings. In this case,
-	 * let the state of idle sibling percolate up as CPU_IDLE, instead of
-	 * portraying it as CPU_NOT_IDLE.
-	 */
-	if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		sd_idle = 1;
-
-	schedstat_inc(sd, lb_count[idle]);
-
-redo:
-	update_shares(sd);
-	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
-				   cpus, balance);
-
-	if (*balance == 0)
-		goto out_balanced;
-
-	if (!group) {
-		schedstat_inc(sd, lb_nobusyg[idle]);
-		goto out_balanced;
-	}
-
-	busiest = find_busiest_queue(group, idle, imbalance, cpus);
-	if (!busiest) {
-		schedstat_inc(sd, lb_nobusyq[idle]);
-		goto out_balanced;
-	}
-
-	BUG_ON(busiest == this_rq);
-
-	schedstat_add(sd, lb_imbalance[idle], imbalance);
-
-	ld_moved = 0;
-	if (busiest->nr_running > 1) {
-		/*
-		 * Attempt to move tasks. If find_busiest_group has found
-		 * an imbalance but busiest->nr_running <= 1, the group is
-		 * still unbalanced. ld_moved simply stays zero, so it is
-		 * correctly treated as an imbalance.
-		 */
-		local_irq_save(flags);
-		double_rq_lock(this_rq, busiest);
-		ld_moved = move_tasks(this_rq, this_cpu, busiest,
-				      imbalance, sd, idle, &all_pinned);
-		double_rq_unlock(this_rq, busiest);
-		local_irq_restore(flags);
-
-		/*
-		 * some other cpu did the load balance for us.
-		 */
-		if (ld_moved && this_cpu != smp_processor_id())
-			resched_cpu(this_cpu);
-
-		/* All tasks on this runqueue were pinned by CPU affinity */
-		if (unlikely(all_pinned)) {
-			cpumask_clear_cpu(cpu_of(busiest), cpus);
-			if (!cpumask_empty(cpus))
-				goto redo;
-			goto out_balanced;
-		}
-	}
-
-	if (!ld_moved) {
-		schedstat_inc(sd, lb_failed[idle]);
-		sd->nr_balance_failed++;
-
-		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
-
-			raw_spin_lock_irqsave(&busiest->lock, flags);
-
-			/* don't kick the migration_thread, if the curr
-			 * task on busiest cpu can't be moved to this_cpu
-			 */
-			if (!cpumask_test_cpu(this_cpu,
-					      &busiest->curr->cpus_allowed)) {
-				raw_spin_unlock_irqrestore(&busiest->lock,
-							    flags);
-				all_pinned = 1;
-				goto out_one_pinned;
-			}
-
-			if (!busiest->active_balance) {
-				busiest->active_balance = 1;
-				busiest->push_cpu = this_cpu;
-				active_balance = 1;
-			}
-			raw_spin_unlock_irqrestore(&busiest->lock, flags);
-			if (active_balance)
-				wake_up_process(busiest->migration_thread);
-
-			/*
-			 * We've kicked active balancing, reset the failure
-			 * counter.
-			 */
-			sd->nr_balance_failed = sd->cache_nice_tries+1;
-		}
-	} else
-		sd->nr_balance_failed = 0;
-
-	if (likely(!active_balance)) {
-		/* We were unbalanced, so reset the balancing interval */
-		sd->balance_interval = sd->min_interval;
-	} else {
-		/*
-		 * If we've begun active balancing, start to back off. This
-		 * case may not be covered by the all_pinned logic if there
-		 * is only 1 task on the busy runqueue (because we don't call
-		 * move_tasks).
-		 */
-		if (sd->balance_interval < sd->max_interval)
-			sd->balance_interval *= 2;
-	}
-
-	if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		ld_moved = -1;
-
-	goto out;
-
-out_balanced:
-	schedstat_inc(sd, lb_balanced[idle]);
-
-	sd->nr_balance_failed = 0;
-
-out_one_pinned:
-	/* tune up the balancing interval */
-	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
-			(sd->balance_interval < sd->max_interval))
-		sd->balance_interval *= 2;
-
-	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		ld_moved = -1;
-	else
-		ld_moved = 0;
-out:
-	if (ld_moved)
-		update_shares(sd);
-	return ld_moved;
-}
-
-/*
- * Check this_cpu to ensure it is balanced within domain. Attempt to move
- * tasks if there is an imbalance.
- *
- * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE).
- * this_rq is locked.
- */
-static int
-load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
-{
-	struct sched_group *group;
-	struct rq *busiest = NULL;
-	unsigned long imbalance;
-	int ld_moved = 0;
-	int sd_idle = 0;
-	int all_pinned = 0;
-	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
-
-	cpumask_copy(cpus, cpu_active_mask);
-
-	/*
-	 * When power savings policy is enabled for the parent domain, idle
-	 * sibling can pick up load irrespective of busy siblings. In this case,
-	 * let the state of idle sibling percolate up as IDLE, instead of
-	 * portraying it as CPU_NOT_IDLE.
-	 */
-	if (sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		sd_idle = 1;
-
-	schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]);
-redo:
-	update_shares_locked(this_rq, sd);
-	group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
-				   &sd_idle, cpus, NULL);
-	if (!group) {
-		schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]);
-		goto out_balanced;
-	}
-
-	busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus);
-	if (!busiest) {
-		schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]);
-		goto out_balanced;
-	}
-
-	BUG_ON(busiest == this_rq);
-
-	schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance);
-
-	ld_moved = 0;
-	if (busiest->nr_running > 1) {
-		/* Attempt to move tasks */
-		double_lock_balance(this_rq, busiest);
-		/* this_rq->clock is already updated */
-		update_rq_clock(busiest);
-		ld_moved = move_tasks(this_rq, this_cpu, busiest,
-					imbalance, sd, CPU_NEWLY_IDLE,
-					&all_pinned);
-		double_unlock_balance(this_rq, busiest);
-
-		if (unlikely(all_pinned)) {
-			cpumask_clear_cpu(cpu_of(busiest), cpus);
-			if (!cpumask_empty(cpus))
-				goto redo;
-		}
-	}
-
-	if (!ld_moved) {
-		int active_balance = 0;
-
-		schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
-		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-			return -1;
-
-		if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
-			return -1;
-
-		if (sd->nr_balance_failed++ < 2)
-			return -1;
-
-		/*
-		 * The only task running in a non-idle cpu can be moved to this
-		 * cpu in an attempt to completely freeup the other CPU
-		 * package. The same method used to move task in load_balance()
-		 * have been extended for load_balance_newidle() to speedup
-		 * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2)
-		 *
-		 * The package power saving logic comes from
-		 * find_busiest_group().  If there are no imbalance, then
-		 * f_b_g() will return NULL.  However when sched_mc={1,2} then
-		 * f_b_g() will select a group from which a running task may be
-		 * pulled to this cpu in order to make the other package idle.
-		 * If there is no opportunity to make a package idle and if
-		 * there are no imbalance, then f_b_g() will return NULL and no
-		 * action will be taken in load_balance_newidle().
-		 *
-		 * Under normal task pull operation due to imbalance, there
-		 * will be more than one task in the source run queue and
-		 * move_tasks() will succeed.  ld_moved will be true and this
-		 * active balance code will not be triggered.
-		 */
-
-		/* Lock busiest in correct order while this_rq is held */
-		double_lock_balance(this_rq, busiest);
-
-		/*
-		 * don't kick the migration_thread, if the curr
-		 * task on busiest cpu can't be moved to this_cpu
-		 */
-		if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
-			double_unlock_balance(this_rq, busiest);
-			all_pinned = 1;
-			return ld_moved;
-		}
-
-		if (!busiest->active_balance) {
-			busiest->active_balance = 1;
-			busiest->push_cpu = this_cpu;
-			active_balance = 1;
-		}
-
-		double_unlock_balance(this_rq, busiest);
-		/*
-		 * Should not call ttwu while holding a rq->lock
-		 */
-		raw_spin_unlock(&this_rq->lock);
-		if (active_balance)
-			wake_up_process(busiest->migration_thread);
-		raw_spin_lock(&this_rq->lock);
-
-	} else
-		sd->nr_balance_failed = 0;
-
-	update_shares_locked(this_rq, sd);
-	return ld_moved;
-
-out_balanced:
-	schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]);
-	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		return -1;
-	sd->nr_balance_failed = 0;
-
-	return 0;
-}
-
-/*
- * idle_balance is called by schedule() if this_cpu is about to become
- * idle. Attempts to pull tasks from other CPUs.
- */
-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;
-
-	this_rq->idle_stamp = this_rq->clock;
-
-	if (this_rq->avg_idle < sysctl_sched_migration_cost)
-		return;
-
-	for_each_domain(this_cpu, sd) {
-		unsigned long interval;
-
-		if (!(sd->flags & SD_LOAD_BALANCE))
-			continue;
-
-		if (sd->flags & SD_BALANCE_NEWIDLE)
-			/* If we've pulled tasks over stop searching: */
-			pulled_task = load_balance_newidle(this_cpu, this_rq,
-							   sd);
-
-		interval = msecs_to_jiffies(sd->balance_interval);
-		if (time_after(next_balance, sd->last_balance + interval))
-			next_balance = sd->last_balance + interval;
-		if (pulled_task) {
-			this_rq->idle_stamp = 0;
-			break;
-		}
-	}
-	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
-		/*
-		 * We are going idle. next_balance may be set based on
-		 * a busy processor. So reset next_balance.
-		 */
-		this_rq->next_balance = next_balance;
-	}
-}
-
-/*
- * active_load_balance is run by migration threads. It pushes running tasks
- * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
- * running on each physical CPU where possible, and avoids physical /
- * logical imbalances.
- *
- * Called with busiest_rq locked.
- */
-static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
-{
-	int target_cpu = busiest_rq->push_cpu;
-	struct sched_domain *sd;
-	struct rq *target_rq;
-
-	/* Is there any task to move? */
-	if (busiest_rq->nr_running <= 1)
-		return;
-
-	target_rq = cpu_rq(target_cpu);
-
-	/*
-	 * This condition is "impossible", if it occurs
-	 * we need to fix it. Originally reported by
-	 * Bjorn Helgaas on a 128-cpu setup.
-	 */
-	BUG_ON(busiest_rq == target_rq);
-
-	/* move a task from busiest_rq to target_rq */
-	double_lock_balance(busiest_rq, target_rq);
-	update_rq_clock(busiest_rq);
-	update_rq_clock(target_rq);
-
-	/* Search for an sd spanning us and the target CPU. */
-	for_each_domain(target_cpu, sd) {
-		if ((sd->flags & SD_LOAD_BALANCE) &&
-		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
-				break;
-	}
-
-	if (likely(sd)) {
-		schedstat_inc(sd, alb_count);
-
-		if (move_one_task(target_rq, target_cpu, busiest_rq,
-				  sd, CPU_IDLE))
-			schedstat_inc(sd, alb_pushed);
-		else
-			schedstat_inc(sd, alb_failed);
-	}
-	double_unlock_balance(busiest_rq, target_rq);
-}
-
-#ifdef CONFIG_NO_HZ
-static struct {
-	atomic_t load_balancer;
-	cpumask_var_t cpu_mask;
-	cpumask_var_t ilb_grp_nohz_mask;
-} nohz ____cacheline_aligned = {
-	.load_balancer = ATOMIC_INIT(-1),
-};
-
-int get_nohz_load_balancer(void)
-{
-	return atomic_read(&nohz.load_balancer);
-}
-
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-/**
- * lowest_flag_domain - Return lowest sched_domain containing flag.
- * @cpu:	The cpu whose lowest level of sched domain is to
- *		be returned.
- * @flag:	The flag to check for the lowest sched_domain
- *		for the given cpu.
- *
- * Returns the lowest sched_domain of a cpu which contains the given flag.
- */
-static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
-{
-	struct sched_domain *sd;
-
-	for_each_domain(cpu, sd)
-		if (sd && (sd->flags & flag))
-			break;
-
-	return sd;
-}
-
-/**
- * for_each_flag_domain - Iterates over sched_domains containing the flag.
- * @cpu:	The cpu whose domains we're iterating over.
- * @sd:		variable holding the value of the power_savings_sd
- *		for cpu.
- * @flag:	The flag to filter the sched_domains to be iterated.
- *
- * Iterates over all the scheduler domains for a given cpu that has the 'flag'
- * set, starting from the lowest sched_domain to the highest.
- */
-#define for_each_flag_domain(cpu, sd, flag) \
-	for (sd = lowest_flag_domain(cpu, flag); \
-		(sd && (sd->flags & flag)); sd = sd->parent)
-
-/**
- * is_semi_idle_group - Checks if the given sched_group is semi-idle.
- * @ilb_group:	group to be checked for semi-idleness
- *
- * Returns:	1 if the group is semi-idle. 0 otherwise.
- *
- * We define a sched_group to be semi idle if it has atleast one idle-CPU
- * and atleast one non-idle CPU. This helper function checks if the given
- * sched_group is semi-idle or not.
- */
-static inline int is_semi_idle_group(struct sched_group *ilb_group)
-{
-	cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
-					sched_group_cpus(ilb_group));
-
-	/*
-	 * A sched_group is semi-idle when it has atleast one busy cpu
-	 * and atleast one idle cpu.
-	 */
-	if (cpumask_empty(nohz.ilb_grp_nohz_mask))
-		return 0;
-
-	if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
-		return 0;
-
-	return 1;
-}
-/**
- * find_new_ilb - Finds the optimum idle load balancer for nomination.
- * @cpu:	The cpu which is nominating a new idle_load_balancer.
- *
- * Returns:	Returns the id of the idle load balancer if it exists,
- *		Else, returns >= nr_cpu_ids.
- *
- * This algorithm picks the idle load balancer such that it belongs to a
- * semi-idle powersavings sched_domain. The idea is to try and avoid
- * completely idle packages/cores just for the purpose of idle load balancing
- * when there are other idle cpu's which are better suited for that job.
- */
-static int find_new_ilb(int cpu)
-{
-	struct sched_domain *sd;
-	struct sched_group *ilb_group;
-
-	/*
-	 * Have idle load balancer selection from semi-idle packages only
-	 * when power-aware load balancing is enabled
-	 */
-	if (!(sched_smt_power_savings || sched_mc_power_savings))
-		goto out_done;
-
-	/*
-	 * Optimize for the case when we have no idle CPUs or only one
-	 * idle CPU. Don't walk the sched_domain hierarchy in such cases
-	 */
-	if (cpumask_weight(nohz.cpu_mask) < 2)
-		goto out_done;
-
-	for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
-		ilb_group = sd->groups;
-
-		do {
-			if (is_semi_idle_group(ilb_group))
-				return cpumask_first(nohz.ilb_grp_nohz_mask);
-
-			ilb_group = ilb_group->next;
-
-		} while (ilb_group != sd->groups);
-	}
-
-out_done:
-	return cpumask_first(nohz.cpu_mask);
-}
-#else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
-static inline int find_new_ilb(int call_cpu)
-{
-	return cpumask_first(nohz.cpu_mask);
-}
-#endif
-
-/*
- * This routine will try to nominate the ilb (idle load balancing)
- * owner among the cpus whose ticks are stopped. ilb owner will do the idle
- * load balancing on behalf of all those cpus. If all the cpus in the system
- * go into this tickless mode, then there will be no ilb owner (as there is
- * no need for one) and all the cpus will sleep till the next wakeup event
- * arrives...
- *
- * For the ilb owner, tick is not stopped. And this tick will be used
- * for idle load balancing. ilb owner will still be part of
- * nohz.cpu_mask..
- *
- * While stopping the tick, this cpu will become the ilb owner if there
- * is no other owner. And will be the owner till that cpu becomes busy
- * or if all cpus in the system stop their ticks at which point
- * there is no need for ilb owner.
- *
- * When the ilb owner becomes busy, it nominates another owner, during the
- * next busy scheduler_tick()
- */
-int select_nohz_load_balancer(int stop_tick)
-{
-	int cpu = smp_processor_id();
-
-	if (stop_tick) {
-		cpu_rq(cpu)->in_nohz_recently = 1;
-
-		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_active_cpus()) {
-			if (atomic_read(&nohz.load_balancer) == cpu)
-				atomic_set(&nohz.load_balancer, -1);
-			return 0;
-		}
-
-		if (atomic_read(&nohz.load_balancer) == -1) {
-			/* make me the ilb owner */
-			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
-				return 1;
-		} else if (atomic_read(&nohz.load_balancer) == cpu) {
-			int new_ilb;
-
-			if (!(sched_smt_power_savings ||
-						sched_mc_power_savings))
-				return 1;
-			/*
-			 * Check to see if there is a more power-efficient
-			 * ilb.
-			 */
-			new_ilb = find_new_ilb(cpu);
-			if (new_ilb < nr_cpu_ids && new_ilb != cpu) {
-				atomic_set(&nohz.load_balancer, -1);
-				resched_cpu(new_ilb);
-				return 0;
-			}
-			return 1;
-		}
-	} else {
-		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
-			return 0;
-
-		cpumask_clear_cpu(cpu, nohz.cpu_mask);
-
-		if (atomic_read(&nohz.load_balancer) == cpu)
-			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
-				BUG();
-	}
-	return 0;
-}
-#endif
-
-static DEFINE_SPINLOCK(balancing);
-
-/*
- * It checks each scheduling domain to see if it is due to be balanced,
- * and initiates a balancing operation if so.
- *
- * Balancing parameters are set up in arch_init_sched_domains.
- */
-static void rebalance_domains(int cpu, enum cpu_idle_type idle)
-{
-	int balance = 1;
-	struct rq *rq = cpu_rq(cpu);
-	unsigned long interval;
-	struct sched_domain *sd;
-	/* Earliest time when we have to do rebalance again */
-	unsigned long next_balance = jiffies + 60*HZ;
-	int update_next_balance = 0;
-	int need_serialize;
-
-	for_each_domain(cpu, sd) {
-		if (!(sd->flags & SD_LOAD_BALANCE))
-			continue;
-
-		interval = sd->balance_interval;
-		if (idle != CPU_IDLE)
-			interval *= sd->busy_factor;
-
-		/* scale ms to jiffies */
-		interval = msecs_to_jiffies(interval);
-		if (unlikely(!interval))
-			interval = 1;
-		if (interval > HZ*NR_CPUS/10)
-			interval = HZ*NR_CPUS/10;
-
-		need_serialize = sd->flags & SD_SERIALIZE;
-
-		if (need_serialize) {
-			if (!spin_trylock(&balancing))
-				goto out;
-		}
-
-		if (time_after_eq(jiffies, sd->last_balance + interval)) {
-			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
-				 * not idle.
-				 */
-				idle = CPU_NOT_IDLE;
-			}
-			sd->last_balance = jiffies;
-		}
-		if (need_serialize)
-			spin_unlock(&balancing);
-out:
-		if (time_after(next_balance, sd->last_balance + interval)) {
-			next_balance = sd->last_balance + interval;
-			update_next_balance = 1;
-		}
-
-		/*
-		 * Stop the load balance at this level. There is another
-		 * CPU in our sched group which is doing load balancing more
-		 * actively.
-		 */
-		if (!balance)
-			break;
-	}
-
-	/*
-	 * next_balance will be updated only when there is a need.
-	 * When the cpu is attached to null domain for ex, it will not be
-	 * updated.
-	 */
-	if (likely(update_next_balance))
-		rq->next_balance = next_balance;
-}
-
-/*
- * run_rebalance_domains is triggered when needed from the scheduler tick.
- * In CONFIG_NO_HZ case, the idle load balance owner will do the
- * rebalancing for all the cpus for whom scheduler ticks are stopped.
- */
-static void run_rebalance_domains(struct softirq_action *h)
-{
-	int this_cpu = smp_processor_id();
-	struct rq *this_rq = cpu_rq(this_cpu);
-	enum cpu_idle_type idle = this_rq->idle_at_tick ?
-						CPU_IDLE : CPU_NOT_IDLE;
-
-	rebalance_domains(this_cpu, idle);
-
-#ifdef CONFIG_NO_HZ
-	/*
-	 * If this cpu is the owner for idle load balancing, then do the
-	 * balancing on behalf of the other idle cpus whose ticks are
-	 * stopped.
-	 */
-	if (this_rq->idle_at_tick &&
-	    atomic_read(&nohz.load_balancer) == this_cpu) {
-		struct rq *rq;
-		int balance_cpu;
-
-		for_each_cpu(balance_cpu, nohz.cpu_mask) {
-			if (balance_cpu == this_cpu)
-				continue;
-
-			/*
-			 * If this cpu gets work to do, stop the load balancing
-			 * work being done for other cpus. Next load
-			 * balancing owner will pick it up.
-			 */
-			if (need_resched())
-				break;
-
-			rebalance_domains(balance_cpu, CPU_IDLE);
-
-			rq = cpu_rq(balance_cpu);
-			if (time_after(this_rq->next_balance, rq->next_balance))
-				this_rq->next_balance = rq->next_balance;
-		}
-	}
-#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.
- *
- * In case of CONFIG_NO_HZ, this is the place where we nominate a new
- * idle load balancing owner or decide to stop the periodic load balancing,
- * if the whole system is idle.
- */
-static inline void trigger_load_balance(struct rq *rq, int cpu)
-{
-#ifdef CONFIG_NO_HZ
-	/*
-	 * If we were in the nohz mode recently and busy at the current
-	 * scheduler tick, then check if we need to nominate new idle
-	 * load balancer.
-	 */
-	if (rq->in_nohz_recently && !rq->idle_at_tick) {
-		rq->in_nohz_recently = 0;
-
-		if (atomic_read(&nohz.load_balancer) == cpu) {
-			cpumask_clear_cpu(cpu, nohz.cpu_mask);
-			atomic_set(&nohz.load_balancer, -1);
-		}
-
-		if (atomic_read(&nohz.load_balancer) == -1) {
-			int ilb = find_new_ilb(cpu);
-
-			if (ilb < nr_cpu_ids)
-				resched_cpu(ilb);
-		}
-	}
-
-	/*
-	 * If this cpu is idle and doing idle load balancing for all the
-	 * cpus with ticks stopped, is it time for that to stop?
-	 */
-	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu &&
-	    cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
-		resched_cpu(cpu);
-		return;
-	}
-
-	/*
-	 * If this cpu is idle and the idle load balancing is done by
-	 * someone else, then no need raise the SCHED_SOFTIRQ
-	 */
-	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu &&
-	    cpumask_test_cpu(cpu, nohz.cpu_mask))
-		return;
-#endif
-	/* 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);
-}
-
-#else	/* CONFIG_SMP */
-
-/*
- * on UP we do not need to balance between CPUs:
- */
-static inline void idle_balance(int cpu, struct rq *rq)
-{
-}
-
 #endif
 
 DEFINE_PER_CPU(struct kernel_stat, kstat);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 71778601c103..5116b81d7727 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1952,6 +1952,1762 @@ move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	return 0;
 }
 
+/*
+ * pull_task - move a task from a remote runqueue to the local runqueue.
+ * Both runqueues must be locked.
+ */
+static void pull_task(struct rq *src_rq, struct task_struct *p,
+		      struct rq *this_rq, int this_cpu)
+{
+	deactivate_task(src_rq, p, 0);
+	set_task_cpu(p, this_cpu);
+	activate_task(this_rq, p, 0);
+	check_preempt_curr(this_rq, p, 0);
+}
+
+/*
+ * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
+ */
+static
+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
+	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
+	 * 3) are cache-hot on their current CPU.
+	 */
+	if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
+		schedstat_inc(p, se.nr_failed_migrations_affine);
+		return 0;
+	}
+	*all_pinned = 0;
+
+	if (task_running(rq, p)) {
+		schedstat_inc(p, se.nr_failed_migrations_running);
+		return 0;
+	}
+
+	/*
+	 * Aggressive migration if:
+	 * 1) task is cache cold, or
+	 * 2) too many balance attempts have failed.
+	 */
+
+	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 (tsk_cache_hot) {
+			schedstat_inc(sd, lb_hot_gained[idle]);
+			schedstat_inc(p, se.nr_forced_migrations);
+		}
+#endif
+		return 1;
+	}
+
+	if (tsk_cache_hot) {
+		schedstat_inc(p, se.nr_failed_migrations_hot);
+		return 0;
+	}
+	return 1;
+}
+
+static unsigned long
+balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+	      unsigned long max_load_move, struct sched_domain *sd,
+	      enum cpu_idle_type idle, int *all_pinned,
+	      int *this_best_prio, struct rq_iterator *iterator)
+{
+	int loops = 0, pulled = 0, pinned = 0;
+	struct task_struct *p;
+	long rem_load_move = max_load_move;
+
+	if (max_load_move == 0)
+		goto out;
+
+	pinned = 1;
+
+	/*
+	 * Start the load-balancing iterator:
+	 */
+	p = iterator->start(iterator->arg);
+next:
+	if (!p || loops++ > sysctl_sched_nr_migrate)
+		goto out;
+
+	if ((p->se.load.weight >> 1) > rem_load_move ||
+	    !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
+		p = iterator->next(iterator->arg);
+		goto next;
+	}
+
+	pull_task(busiest, p, this_rq, this_cpu);
+	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.
+	 */
+	if (rem_load_move > 0) {
+		if (p->prio < *this_best_prio)
+			*this_best_prio = p->prio;
+		p = iterator->next(iterator->arg);
+		goto next;
+	}
+out:
+	/*
+	 * Right now, this is one of only two places pull_task() is called,
+	 * so we can safely collect pull_task() stats here rather than
+	 * inside pull_task().
+	 */
+	schedstat_add(sd, lb_gained[idle], pulled);
+
+	if (all_pinned)
+		*all_pinned = pinned;
+
+	return max_load_move - rem_load_move;
+}
+
+/*
+ * move_tasks tries to move up to max_load_move weighted load from busiest to
+ * this_rq, as part of a balancing operation within domain "sd".
+ * Returns 1 if successful and 0 otherwise.
+ *
+ * Called with both runqueues locked.
+ */
+static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		      unsigned long max_load_move,
+		      struct sched_domain *sd, enum cpu_idle_type idle,
+		      int *all_pinned)
+{
+	const struct sched_class *class = sched_class_highest;
+	unsigned long total_load_moved = 0;
+	int this_best_prio = this_rq->curr->prio;
+
+	do {
+		total_load_moved +=
+			class->load_balance(this_rq, this_cpu, busiest,
+				max_load_move - total_load_moved,
+				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;
+}
+
+static int
+iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		   struct sched_domain *sd, enum cpu_idle_type idle,
+		   struct rq_iterator *iterator)
+{
+	struct task_struct *p = iterator->start(iterator->arg);
+	int pinned = 0;
+
+	while (p) {
+		if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
+			pull_task(busiest, p, this_rq, this_cpu);
+			/*
+			 * Right now, this is only the second place pull_task()
+			 * is called, so we can safely collect pull_task()
+			 * stats here rather than inside pull_task().
+			 */
+			schedstat_inc(sd, lb_gained[idle]);
+
+			return 1;
+		}
+		p = iterator->next(iterator->arg);
+	}
+
+	return 0;
+}
+
+/*
+ * move_one_task tries to move exactly one task from busiest to this_rq, as
+ * part of active balancing operations within "domain".
+ * Returns 1 if successful and 0 otherwise.
+ *
+ * Called with both runqueues locked.
+ */
+static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+			 struct sched_domain *sd, enum cpu_idle_type idle)
+{
+	const struct sched_class *class;
+
+	for_each_class(class) {
+		if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
+			return 1;
+	}
+
+	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
+};
+
+/*
+ * 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 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;
+		break;
+
+	case CPU_NEWLY_IDLE:
+		load_idx = sd->newidle_idx;
+		break;
+	default:
+		load_idx = sd->idle_idx;
+		break;
+	}
+
+	return load_idx;
+}
+
+
+#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;
+	}
+}
+
+/**
+ * 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)
+{
+
+	if (!sds->power_savings_balance)
+		return;
+
+	/*
+	 * 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 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;
+
+	/*
+	 * 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;
+	}
+
+	/*
+	 * 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 + 1 > sgs->group_capacity)
+		return;
+
+	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;
+	}
+}
+
+/**
+ * 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;
+
+	if (sds->this != sds->group_leader ||
+			sds->group_leader == sds->group_min)
+		return 0;
+
+	*imbalance = sds->min_load_per_task;
+	sds->busiest = sds->group_min;
+
+	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;
+}
+
+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 */
+
+
+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return SCHED_LOAD_SCALE;
+}
+
+unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return default_scale_freq_power(sd, cpu);
+}
+
+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long smt_gain = sd->smt_gain;
+
+	smt_gain /= weight;
+
+	return smt_gain;
+}
+
+unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+	return default_scale_smt_power(sd, cpu);
+}
+
+unsigned long scale_rt_power(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	u64 total, available;
+
+	sched_avg_update(rq);
+
+	total = sched_avg_period() + (rq->clock - rq->age_stamp);
+	available = total - rq->rt_avg;
+
+	if (unlikely((s64)total < SCHED_LOAD_SCALE))
+		total = SCHED_LOAD_SCALE;
+
+	total >>= SCHED_LOAD_SHIFT;
+
+	return div_u64(available, total);
+}
+
+static void update_cpu_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long power = SCHED_LOAD_SCALE;
+	struct sched_group *sdg = sd->groups;
+
+	if (sched_feat(ARCH_POWER))
+		power *= arch_scale_freq_power(sd, cpu);
+	else
+		power *= default_scale_freq_power(sd, cpu);
+
+	power >>= SCHED_LOAD_SHIFT;
+
+	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+		if (sched_feat(ARCH_POWER))
+			power *= arch_scale_smt_power(sd, cpu);
+		else
+			power *= default_scale_smt_power(sd, cpu);
+
+		power >>= SCHED_LOAD_SHIFT;
+	}
+
+	power *= scale_rt_power(cpu);
+	power >>= SCHED_LOAD_SHIFT;
+
+	if (!power)
+		power = 1;
+
+	sdg->cpu_power = power;
+}
+
+static void update_group_power(struct sched_domain *sd, int cpu)
+{
+	struct sched_domain *child = sd->child;
+	struct sched_group *group, *sdg = sd->groups;
+	unsigned long power;
+
+	if (!child) {
+		update_cpu_power(sd, cpu);
+		return;
+	}
+
+	power = 0;
+
+	group = child->groups;
+	do {
+		power += group->cpu_power;
+		group = group->next;
+	} while (group != child->groups);
+
+	sdg->cpu_power = power;
+}
+
+/**
+ * update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: The sched_domain whose statistics are to be updated.
+ * @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_domain *sd,
+			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);
+		if (balance_cpu == this_cpu)
+			update_group_power(sd, this_cpu);
+	}
+
+	/* 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) {
+			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;
+		}
+
+		sgs->group_load += load;
+		sgs->sum_nr_running += rq->nr_running;
+		sgs->sum_weighted_load += weighted_cpuload(i);
+
+		sum_avg_load_per_task += cpu_avg_load_per_task(i);
+	}
+
+	/*
+	 * 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;
+	}
+
+	/* Adjust by relative CPU power of the group */
+	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
+
+
+	/*
+	 * 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 = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
+		group->cpu_power;
+
+	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+		sgs->group_imb = 1;
+
+	sgs->group_capacity =
+		DIV_ROUND_CLOSEST(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_domain *child = sd->child;
+	struct sched_group *group = sd->groups;
+	struct sg_lb_stats sgs;
+	int load_idx, prefer_sibling = 0;
+
+	if (child && child->flags & SD_PREFER_SIBLING)
+		prefer_sibling = 1;
+
+	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(sd, 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;
+
+		/*
+		 * In case the child domain prefers tasks go to siblings
+		 * first, lower the group capacity to one so that we'll try
+		 * and move all the excess tasks away.
+		 */
+		if (prefer_sibling)
+			sgs.group_capacity = min(sgs.group_capacity, 1UL);
+
+		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;
+		}
+
+		update_sd_power_savings_stats(group, sds, local_group, &sgs);
+		group = group->next;
+	} while (group != sd->groups);
+}
+
+/**
+ * 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);
+
+	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;
+	}
+
+	/*
+	 * 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.
+	 */
+
+	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 = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+		sds->busiest->cpu_power;
+	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 = (sds->max_load * sds->busiest->cpu_power) /
+			sds->this->cpu_power;
+	else
+		tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+			sds->this->cpu_power;
+	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 (sds->max_load < sds->avg_load) {
+		*imbalance = 0;
+		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(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 * sds->busiest->cpu_power,
+		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
+			/ SCHED_LOAD_SCALE;
+
+	/*
+	 * if *imbalance is less than the average load per runnable task
+	 * there is no gaurantee that any tasks will be moved so we'll have
+	 * a think about bumping its value to force at least one task to be
+	 * moved
+	 */
+	if (*imbalance < sds->busiest_load_per_task)
+		return fix_small_imbalance(sds, this_cpu, imbalance);
+
+}
+/******* find_busiest_group() helpers end here *********************/
+
+/**
+ * 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;
+
+	memset(&sds, 0, sizeof(sds));
+
+	/*
+	 * 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;
+
+	if (!sds.busiest || sds.busiest_nr_running == 0)
+		goto out_balanced;
+
+	if (sds.this_load >= sds.max_load)
+		goto out_balanced;
+
+	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;
+}
+
+/*
+ * find_busiest_queue - find the busiest runqueue among the cpus in group.
+ */
+static struct rq *
+find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
+		   unsigned long imbalance, const struct cpumask *cpus)
+{
+	struct rq *busiest = NULL, *rq;
+	unsigned long max_load = 0;
+	int i;
+
+	for_each_cpu(i, sched_group_cpus(group)) {
+		unsigned long power = power_of(i);
+		unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
+		unsigned long wl;
+
+		if (!cpumask_test_cpu(i, cpus))
+			continue;
+
+		rq = cpu_rq(i);
+		wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
+		wl /= power;
+
+		if (capacity && rq->nr_running == 1 && wl > imbalance)
+			continue;
+
+		if (wl > max_load) {
+			max_load = wl;
+			busiest = rq;
+		}
+	}
+
+	return busiest;
+}
+
+/*
+ * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
+ * so long as it is large enough.
+ */
+#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)
+{
+	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_copy(cpus, cpu_active_mask);
+
+	/*
+	 * When power savings policy is enabled for the parent domain, idle
+	 * sibling can pick up load irrespective of busy siblings. In this case,
+	 * let the state of idle sibling percolate up as CPU_IDLE, instead of
+	 * portraying it as CPU_NOT_IDLE.
+	 */
+	if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		sd_idle = 1;
+
+	schedstat_inc(sd, lb_count[idle]);
+
+redo:
+	update_shares(sd);
+	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+				   cpus, balance);
+
+	if (*balance == 0)
+		goto out_balanced;
+
+	if (!group) {
+		schedstat_inc(sd, lb_nobusyg[idle]);
+		goto out_balanced;
+	}
+
+	busiest = find_busiest_queue(group, idle, imbalance, cpus);
+	if (!busiest) {
+		schedstat_inc(sd, lb_nobusyq[idle]);
+		goto out_balanced;
+	}
+
+	BUG_ON(busiest == this_rq);
+
+	schedstat_add(sd, lb_imbalance[idle], imbalance);
+
+	ld_moved = 0;
+	if (busiest->nr_running > 1) {
+		/*
+		 * Attempt to move tasks. If find_busiest_group has found
+		 * an imbalance but busiest->nr_running <= 1, the group is
+		 * still unbalanced. ld_moved simply stays zero, so it is
+		 * correctly treated as an imbalance.
+		 */
+		local_irq_save(flags);
+		double_rq_lock(this_rq, busiest);
+		ld_moved = move_tasks(this_rq, this_cpu, busiest,
+				      imbalance, sd, idle, &all_pinned);
+		double_rq_unlock(this_rq, busiest);
+		local_irq_restore(flags);
+
+		/*
+		 * some other cpu did the load balance for us.
+		 */
+		if (ld_moved && this_cpu != smp_processor_id())
+			resched_cpu(this_cpu);
+
+		/* All tasks on this runqueue were pinned by CPU affinity */
+		if (unlikely(all_pinned)) {
+			cpumask_clear_cpu(cpu_of(busiest), cpus);
+			if (!cpumask_empty(cpus))
+				goto redo;
+			goto out_balanced;
+		}
+	}
+
+	if (!ld_moved) {
+		schedstat_inc(sd, lb_failed[idle]);
+		sd->nr_balance_failed++;
+
+		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
+
+			raw_spin_lock_irqsave(&busiest->lock, flags);
+
+			/* don't kick the migration_thread, if the curr
+			 * task on busiest cpu can't be moved to this_cpu
+			 */
+			if (!cpumask_test_cpu(this_cpu,
+					      &busiest->curr->cpus_allowed)) {
+				raw_spin_unlock_irqrestore(&busiest->lock,
+							    flags);
+				all_pinned = 1;
+				goto out_one_pinned;
+			}
+
+			if (!busiest->active_balance) {
+				busiest->active_balance = 1;
+				busiest->push_cpu = this_cpu;
+				active_balance = 1;
+			}
+			raw_spin_unlock_irqrestore(&busiest->lock, flags);
+			if (active_balance)
+				wake_up_process(busiest->migration_thread);
+
+			/*
+			 * We've kicked active balancing, reset the failure
+			 * counter.
+			 */
+			sd->nr_balance_failed = sd->cache_nice_tries+1;
+		}
+	} else
+		sd->nr_balance_failed = 0;
+
+	if (likely(!active_balance)) {
+		/* We were unbalanced, so reset the balancing interval */
+		sd->balance_interval = sd->min_interval;
+	} else {
+		/*
+		 * If we've begun active balancing, start to back off. This
+		 * case may not be covered by the all_pinned logic if there
+		 * is only 1 task on the busy runqueue (because we don't call
+		 * move_tasks).
+		 */
+		if (sd->balance_interval < sd->max_interval)
+			sd->balance_interval *= 2;
+	}
+
+	if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		ld_moved = -1;
+
+	goto out;
+
+out_balanced:
+	schedstat_inc(sd, lb_balanced[idle]);
+
+	sd->nr_balance_failed = 0;
+
+out_one_pinned:
+	/* tune up the balancing interval */
+	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
+			(sd->balance_interval < sd->max_interval))
+		sd->balance_interval *= 2;
+
+	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		ld_moved = -1;
+	else
+		ld_moved = 0;
+out:
+	if (ld_moved)
+		update_shares(sd);
+	return ld_moved;
+}
+
+/*
+ * Check this_cpu to ensure it is balanced within domain. Attempt to move
+ * tasks if there is an imbalance.
+ *
+ * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE).
+ * this_rq is locked.
+ */
+static int
+load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
+{
+	struct sched_group *group;
+	struct rq *busiest = NULL;
+	unsigned long imbalance;
+	int ld_moved = 0;
+	int sd_idle = 0;
+	int all_pinned = 0;
+	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
+
+	cpumask_copy(cpus, cpu_active_mask);
+
+	/*
+	 * When power savings policy is enabled for the parent domain, idle
+	 * sibling can pick up load irrespective of busy siblings. In this case,
+	 * let the state of idle sibling percolate up as IDLE, instead of
+	 * portraying it as CPU_NOT_IDLE.
+	 */
+	if (sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		sd_idle = 1;
+
+	schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]);
+redo:
+	update_shares_locked(this_rq, sd);
+	group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
+				   &sd_idle, cpus, NULL);
+	if (!group) {
+		schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]);
+		goto out_balanced;
+	}
+
+	busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus);
+	if (!busiest) {
+		schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]);
+		goto out_balanced;
+	}
+
+	BUG_ON(busiest == this_rq);
+
+	schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance);
+
+	ld_moved = 0;
+	if (busiest->nr_running > 1) {
+		/* Attempt to move tasks */
+		double_lock_balance(this_rq, busiest);
+		/* this_rq->clock is already updated */
+		update_rq_clock(busiest);
+		ld_moved = move_tasks(this_rq, this_cpu, busiest,
+					imbalance, sd, CPU_NEWLY_IDLE,
+					&all_pinned);
+		double_unlock_balance(this_rq, busiest);
+
+		if (unlikely(all_pinned)) {
+			cpumask_clear_cpu(cpu_of(busiest), cpus);
+			if (!cpumask_empty(cpus))
+				goto redo;
+		}
+	}
+
+	if (!ld_moved) {
+		int active_balance = 0;
+
+		schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
+		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+			return -1;
+
+		if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
+			return -1;
+
+		if (sd->nr_balance_failed++ < 2)
+			return -1;
+
+		/*
+		 * The only task running in a non-idle cpu can be moved to this
+		 * cpu in an attempt to completely freeup the other CPU
+		 * package. The same method used to move task in load_balance()
+		 * have been extended for load_balance_newidle() to speedup
+		 * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2)
+		 *
+		 * The package power saving logic comes from
+		 * find_busiest_group().  If there are no imbalance, then
+		 * f_b_g() will return NULL.  However when sched_mc={1,2} then
+		 * f_b_g() will select a group from which a running task may be
+		 * pulled to this cpu in order to make the other package idle.
+		 * If there is no opportunity to make a package idle and if
+		 * there are no imbalance, then f_b_g() will return NULL and no
+		 * action will be taken in load_balance_newidle().
+		 *
+		 * Under normal task pull operation due to imbalance, there
+		 * will be more than one task in the source run queue and
+		 * move_tasks() will succeed.  ld_moved will be true and this
+		 * active balance code will not be triggered.
+		 */
+
+		/* Lock busiest in correct order while this_rq is held */
+		double_lock_balance(this_rq, busiest);
+
+		/*
+		 * don't kick the migration_thread, if the curr
+		 * task on busiest cpu can't be moved to this_cpu
+		 */
+		if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
+			double_unlock_balance(this_rq, busiest);
+			all_pinned = 1;
+			return ld_moved;
+		}
+
+		if (!busiest->active_balance) {
+			busiest->active_balance = 1;
+			busiest->push_cpu = this_cpu;
+			active_balance = 1;
+		}
+
+		double_unlock_balance(this_rq, busiest);
+		/*
+		 * Should not call ttwu while holding a rq->lock
+		 */
+		raw_spin_unlock(&this_rq->lock);
+		if (active_balance)
+			wake_up_process(busiest->migration_thread);
+		raw_spin_lock(&this_rq->lock);
+
+	} else
+		sd->nr_balance_failed = 0;
+
+	update_shares_locked(this_rq, sd);
+	return ld_moved;
+
+out_balanced:
+	schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]);
+	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		return -1;
+	sd->nr_balance_failed = 0;
+
+	return 0;
+}
+
+/*
+ * idle_balance is called by schedule() if this_cpu is about to become
+ * idle. Attempts to pull tasks from other CPUs.
+ */
+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;
+
+	this_rq->idle_stamp = this_rq->clock;
+
+	if (this_rq->avg_idle < sysctl_sched_migration_cost)
+		return;
+
+	for_each_domain(this_cpu, sd) {
+		unsigned long interval;
+
+		if (!(sd->flags & SD_LOAD_BALANCE))
+			continue;
+
+		if (sd->flags & SD_BALANCE_NEWIDLE)
+			/* If we've pulled tasks over stop searching: */
+			pulled_task = load_balance_newidle(this_cpu, this_rq,
+							   sd);
+
+		interval = msecs_to_jiffies(sd->balance_interval);
+		if (time_after(next_balance, sd->last_balance + interval))
+			next_balance = sd->last_balance + interval;
+		if (pulled_task) {
+			this_rq->idle_stamp = 0;
+			break;
+		}
+	}
+	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
+		/*
+		 * We are going idle. next_balance may be set based on
+		 * a busy processor. So reset next_balance.
+		 */
+		this_rq->next_balance = next_balance;
+	}
+}
+
+/*
+ * active_load_balance is run by migration threads. It pushes running tasks
+ * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
+ * running on each physical CPU where possible, and avoids physical /
+ * logical imbalances.
+ *
+ * Called with busiest_rq locked.
+ */
+static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
+{
+	int target_cpu = busiest_rq->push_cpu;
+	struct sched_domain *sd;
+	struct rq *target_rq;
+
+	/* Is there any task to move? */
+	if (busiest_rq->nr_running <= 1)
+		return;
+
+	target_rq = cpu_rq(target_cpu);
+
+	/*
+	 * This condition is "impossible", if it occurs
+	 * we need to fix it. Originally reported by
+	 * Bjorn Helgaas on a 128-cpu setup.
+	 */
+	BUG_ON(busiest_rq == target_rq);
+
+	/* move a task from busiest_rq to target_rq */
+	double_lock_balance(busiest_rq, target_rq);
+	update_rq_clock(busiest_rq);
+	update_rq_clock(target_rq);
+
+	/* Search for an sd spanning us and the target CPU. */
+	for_each_domain(target_cpu, sd) {
+		if ((sd->flags & SD_LOAD_BALANCE) &&
+		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
+				break;
+	}
+
+	if (likely(sd)) {
+		schedstat_inc(sd, alb_count);
+
+		if (move_one_task(target_rq, target_cpu, busiest_rq,
+				  sd, CPU_IDLE))
+			schedstat_inc(sd, alb_pushed);
+		else
+			schedstat_inc(sd, alb_failed);
+	}
+	double_unlock_balance(busiest_rq, target_rq);
+}
+
+#ifdef CONFIG_NO_HZ
+static struct {
+	atomic_t load_balancer;
+	cpumask_var_t cpu_mask;
+	cpumask_var_t ilb_grp_nohz_mask;
+} nohz ____cacheline_aligned = {
+	.load_balancer = ATOMIC_INIT(-1),
+};
+
+int get_nohz_load_balancer(void)
+{
+	return atomic_read(&nohz.load_balancer);
+}
+
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * lowest_flag_domain - Return lowest sched_domain containing flag.
+ * @cpu:	The cpu whose lowest level of sched domain is to
+ *		be returned.
+ * @flag:	The flag to check for the lowest sched_domain
+ *		for the given cpu.
+ *
+ * Returns the lowest sched_domain of a cpu which contains the given flag.
+ */
+static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
+{
+	struct sched_domain *sd;
+
+	for_each_domain(cpu, sd)
+		if (sd && (sd->flags & flag))
+			break;
+
+	return sd;
+}
+
+/**
+ * for_each_flag_domain - Iterates over sched_domains containing the flag.
+ * @cpu:	The cpu whose domains we're iterating over.
+ * @sd:		variable holding the value of the power_savings_sd
+ *		for cpu.
+ * @flag:	The flag to filter the sched_domains to be iterated.
+ *
+ * Iterates over all the scheduler domains for a given cpu that has the 'flag'
+ * set, starting from the lowest sched_domain to the highest.
+ */
+#define for_each_flag_domain(cpu, sd, flag) \
+	for (sd = lowest_flag_domain(cpu, flag); \
+		(sd && (sd->flags & flag)); sd = sd->parent)
+
+/**
+ * is_semi_idle_group - Checks if the given sched_group is semi-idle.
+ * @ilb_group:	group to be checked for semi-idleness
+ *
+ * Returns:	1 if the group is semi-idle. 0 otherwise.
+ *
+ * We define a sched_group to be semi idle if it has atleast one idle-CPU
+ * and atleast one non-idle CPU. This helper function checks if the given
+ * sched_group is semi-idle or not.
+ */
+static inline int is_semi_idle_group(struct sched_group *ilb_group)
+{
+	cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
+					sched_group_cpus(ilb_group));
+
+	/*
+	 * A sched_group is semi-idle when it has atleast one busy cpu
+	 * and atleast one idle cpu.
+	 */
+	if (cpumask_empty(nohz.ilb_grp_nohz_mask))
+		return 0;
+
+	if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
+		return 0;
+
+	return 1;
+}
+/**
+ * find_new_ilb - Finds the optimum idle load balancer for nomination.
+ * @cpu:	The cpu which is nominating a new idle_load_balancer.
+ *
+ * Returns:	Returns the id of the idle load balancer if it exists,
+ *		Else, returns >= nr_cpu_ids.
+ *
+ * This algorithm picks the idle load balancer such that it belongs to a
+ * semi-idle powersavings sched_domain. The idea is to try and avoid
+ * completely idle packages/cores just for the purpose of idle load balancing
+ * when there are other idle cpu's which are better suited for that job.
+ */
+static int find_new_ilb(int cpu)
+{
+	struct sched_domain *sd;
+	struct sched_group *ilb_group;
+
+	/*
+	 * Have idle load balancer selection from semi-idle packages only
+	 * when power-aware load balancing is enabled
+	 */
+	if (!(sched_smt_power_savings || sched_mc_power_savings))
+		goto out_done;
+
+	/*
+	 * Optimize for the case when we have no idle CPUs or only one
+	 * idle CPU. Don't walk the sched_domain hierarchy in such cases
+	 */
+	if (cpumask_weight(nohz.cpu_mask) < 2)
+		goto out_done;
+
+	for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
+		ilb_group = sd->groups;
+
+		do {
+			if (is_semi_idle_group(ilb_group))
+				return cpumask_first(nohz.ilb_grp_nohz_mask);
+
+			ilb_group = ilb_group->next;
+
+		} while (ilb_group != sd->groups);
+	}
+
+out_done:
+	return cpumask_first(nohz.cpu_mask);
+}
+#else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
+static inline int find_new_ilb(int call_cpu)
+{
+	return cpumask_first(nohz.cpu_mask);
+}
+#endif
+
+/*
+ * This routine will try to nominate the ilb (idle load balancing)
+ * owner among the cpus whose ticks are stopped. ilb owner will do the idle
+ * load balancing on behalf of all those cpus. If all the cpus in the system
+ * go into this tickless mode, then there will be no ilb owner (as there is
+ * no need for one) and all the cpus will sleep till the next wakeup event
+ * arrives...
+ *
+ * For the ilb owner, tick is not stopped. And this tick will be used
+ * for idle load balancing. ilb owner will still be part of
+ * nohz.cpu_mask..
+ *
+ * While stopping the tick, this cpu will become the ilb owner if there
+ * is no other owner. And will be the owner till that cpu becomes busy
+ * or if all cpus in the system stop their ticks at which point
+ * there is no need for ilb owner.
+ *
+ * When the ilb owner becomes busy, it nominates another owner, during the
+ * next busy scheduler_tick()
+ */
+int select_nohz_load_balancer(int stop_tick)
+{
+	int cpu = smp_processor_id();
+
+	if (stop_tick) {
+		cpu_rq(cpu)->in_nohz_recently = 1;
+
+		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_active_cpus()) {
+			if (atomic_read(&nohz.load_balancer) == cpu)
+				atomic_set(&nohz.load_balancer, -1);
+			return 0;
+		}
+
+		if (atomic_read(&nohz.load_balancer) == -1) {
+			/* make me the ilb owner */
+			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
+				return 1;
+		} else if (atomic_read(&nohz.load_balancer) == cpu) {
+			int new_ilb;
+
+			if (!(sched_smt_power_savings ||
+						sched_mc_power_savings))
+				return 1;
+			/*
+			 * Check to see if there is a more power-efficient
+			 * ilb.
+			 */
+			new_ilb = find_new_ilb(cpu);
+			if (new_ilb < nr_cpu_ids && new_ilb != cpu) {
+				atomic_set(&nohz.load_balancer, -1);
+				resched_cpu(new_ilb);
+				return 0;
+			}
+			return 1;
+		}
+	} else {
+		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
+			return 0;
+
+		cpumask_clear_cpu(cpu, nohz.cpu_mask);
+
+		if (atomic_read(&nohz.load_balancer) == cpu)
+			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
+				BUG();
+	}
+	return 0;
+}
+#endif
+
+static DEFINE_SPINLOCK(balancing);
+
+/*
+ * It checks each scheduling domain to see if it is due to be balanced,
+ * and initiates a balancing operation if so.
+ *
+ * Balancing parameters are set up in arch_init_sched_domains.
+ */
+static void rebalance_domains(int cpu, enum cpu_idle_type idle)
+{
+	int balance = 1;
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long interval;
+	struct sched_domain *sd;
+	/* Earliest time when we have to do rebalance again */
+	unsigned long next_balance = jiffies + 60*HZ;
+	int update_next_balance = 0;
+	int need_serialize;
+
+	for_each_domain(cpu, sd) {
+		if (!(sd->flags & SD_LOAD_BALANCE))
+			continue;
+
+		interval = sd->balance_interval;
+		if (idle != CPU_IDLE)
+			interval *= sd->busy_factor;
+
+		/* scale ms to jiffies */
+		interval = msecs_to_jiffies(interval);
+		if (unlikely(!interval))
+			interval = 1;
+		if (interval > HZ*NR_CPUS/10)
+			interval = HZ*NR_CPUS/10;
+
+		need_serialize = sd->flags & SD_SERIALIZE;
+
+		if (need_serialize) {
+			if (!spin_trylock(&balancing))
+				goto out;
+		}
+
+		if (time_after_eq(jiffies, sd->last_balance + interval)) {
+			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
+				 * not idle.
+				 */
+				idle = CPU_NOT_IDLE;
+			}
+			sd->last_balance = jiffies;
+		}
+		if (need_serialize)
+			spin_unlock(&balancing);
+out:
+		if (time_after(next_balance, sd->last_balance + interval)) {
+			next_balance = sd->last_balance + interval;
+			update_next_balance = 1;
+		}
+
+		/*
+		 * Stop the load balance at this level. There is another
+		 * CPU in our sched group which is doing load balancing more
+		 * actively.
+		 */
+		if (!balance)
+			break;
+	}
+
+	/*
+	 * next_balance will be updated only when there is a need.
+	 * When the cpu is attached to null domain for ex, it will not be
+	 * updated.
+	 */
+	if (likely(update_next_balance))
+		rq->next_balance = next_balance;
+}
+
+/*
+ * run_rebalance_domains is triggered when needed from the scheduler tick.
+ * In CONFIG_NO_HZ case, the idle load balance owner will do the
+ * rebalancing for all the cpus for whom scheduler ticks are stopped.
+ */
+static void run_rebalance_domains(struct softirq_action *h)
+{
+	int this_cpu = smp_processor_id();
+	struct rq *this_rq = cpu_rq(this_cpu);
+	enum cpu_idle_type idle = this_rq->idle_at_tick ?
+						CPU_IDLE : CPU_NOT_IDLE;
+
+	rebalance_domains(this_cpu, idle);
+
+#ifdef CONFIG_NO_HZ
+	/*
+	 * If this cpu is the owner for idle load balancing, then do the
+	 * balancing on behalf of the other idle cpus whose ticks are
+	 * stopped.
+	 */
+	if (this_rq->idle_at_tick &&
+	    atomic_read(&nohz.load_balancer) == this_cpu) {
+		struct rq *rq;
+		int balance_cpu;
+
+		for_each_cpu(balance_cpu, nohz.cpu_mask) {
+			if (balance_cpu == this_cpu)
+				continue;
+
+			/*
+			 * If this cpu gets work to do, stop the load balancing
+			 * work being done for other cpus. Next load
+			 * balancing owner will pick it up.
+			 */
+			if (need_resched())
+				break;
+
+			rebalance_domains(balance_cpu, CPU_IDLE);
+
+			rq = cpu_rq(balance_cpu);
+			if (time_after(this_rq->next_balance, rq->next_balance))
+				this_rq->next_balance = rq->next_balance;
+		}
+	}
+#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.
+ *
+ * In case of CONFIG_NO_HZ, this is the place where we nominate a new
+ * idle load balancing owner or decide to stop the periodic load balancing,
+ * if the whole system is idle.
+ */
+static inline void trigger_load_balance(struct rq *rq, int cpu)
+{
+#ifdef CONFIG_NO_HZ
+	/*
+	 * If we were in the nohz mode recently and busy at the current
+	 * scheduler tick, then check if we need to nominate new idle
+	 * load balancer.
+	 */
+	if (rq->in_nohz_recently && !rq->idle_at_tick) {
+		rq->in_nohz_recently = 0;
+
+		if (atomic_read(&nohz.load_balancer) == cpu) {
+			cpumask_clear_cpu(cpu, nohz.cpu_mask);
+			atomic_set(&nohz.load_balancer, -1);
+		}
+
+		if (atomic_read(&nohz.load_balancer) == -1) {
+			int ilb = find_new_ilb(cpu);
+
+			if (ilb < nr_cpu_ids)
+				resched_cpu(ilb);
+		}
+	}
+
+	/*
+	 * If this cpu is idle and doing idle load balancing for all the
+	 * cpus with ticks stopped, is it time for that to stop?
+	 */
+	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu &&
+	    cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
+		resched_cpu(cpu);
+		return;
+	}
+
+	/*
+	 * If this cpu is idle and the idle load balancing is done by
+	 * someone else, then no need raise the SCHED_SOFTIRQ
+	 */
+	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu &&
+	    cpumask_test_cpu(cpu, nohz.cpu_mask))
+		return;
+#endif
+	/* 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);
+}
+
 static void rq_online_fair(struct rq *rq)
 {
 	update_sysctl();
@@ -1962,6 +3718,15 @@ static void rq_offline_fair(struct rq *rq)
 	update_sysctl();
 }
 
+#else	/* CONFIG_SMP */
+
+/*
+ * on UP we do not need to balance between CPUs:
+ */
+static inline void idle_balance(int cpu, struct rq *rq)
+{
+}
+
 #endif /* CONFIG_SMP */
 
 /*

From 3d45fd804a95055ecab5b3eed81f5ab2dbb047a2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 17 Dec 2009 17:12:46 +0100
Subject: [PATCH 04/25] sched: Remove the sched_class load_balance methods

Take out the sched_class methods for load-balancing.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/sched.h   |  8 -----
 kernel/sched.c          | 26 ----------------
 kernel/sched_fair.c     | 66 +++++++++++++++++++++++------------------
 kernel/sched_idletask.c | 21 -------------
 kernel/sched_rt.c       | 20 -------------
 5 files changed, 37 insertions(+), 104 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index f2f842db03ce..50d685cde70e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1087,14 +1087,6 @@ struct sched_class {
 #ifdef CONFIG_SMP
 	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
 
-	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
-			struct rq *busiest, unsigned long max_load_move,
-			struct sched_domain *sd, enum cpu_idle_type idle,
-			int *all_pinned, int *this_best_prio);
-
-	int (*move_one_task) (struct rq *this_rq, int this_cpu,
-			      struct rq *busiest, struct sched_domain *sd,
-			      enum cpu_idle_type idle);
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
 	void (*task_waking) (struct rq *this_rq, struct task_struct *task);
diff --git a/kernel/sched.c b/kernel/sched.c
index 13a2acf18b2d..c0be07932a8d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1390,32 +1390,6 @@ static const u32 prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-static void activate_task(struct rq *rq, struct task_struct *p, int wakeup);
-
-/*
- * runqueue iterator, to support SMP load-balancing between different
- * scheduling classes, without having to expose their internal data
- * structures to the load-balancing proper:
- */
-struct rq_iterator {
-	void *arg;
-	struct task_struct *(*start)(void *);
-	struct task_struct *(*next)(void *);
-};
-
-#ifdef CONFIG_SMP
-static unsigned long
-balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
-	      unsigned long max_load_move, struct sched_domain *sd,
-	      enum cpu_idle_type idle, int *all_pinned,
-	      int *this_best_prio, struct rq_iterator *iterator);
-
-static int
-iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		   struct sched_domain *sd, enum cpu_idle_type idle,
-		   struct rq_iterator *iterator);
-#endif
-
 /* Time spent by the tasks of the cpu accounting group executing in ... */
 enum cpuacct_stat_index {
 	CPUACCT_STAT_USER,	/* ... user mode */
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5116b81d7727..faf9a2f099ab 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1851,6 +1851,24 @@ static struct task_struct *load_balance_next_fair(void *arg)
 	return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
 }
 
+/*
+ * runqueue iterator, to support SMP load-balancing between different
+ * scheduling classes, without having to expose their internal data
+ * structures to the load-balancing proper:
+ */
+struct rq_iterator {
+	void *arg;
+	struct task_struct *(*start)(void *);
+	struct task_struct *(*next)(void *);
+};
+
+static unsigned long
+balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		unsigned long max_load_move, struct sched_domain *sd,
+		enum cpu_idle_type idle, int *all_pinned,
+		int *this_best_prio, struct rq_iterator *iterator);
+
+
 static unsigned long
 __load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		unsigned long max_load_move, struct sched_domain *sd,
@@ -1929,8 +1947,20 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 #endif
 
 static int
-move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		   struct sched_domain *sd, enum cpu_idle_type idle)
+iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		struct sched_domain *sd, enum cpu_idle_type idle,
+		struct rq_iterator *iterator);
+
+/*
+ * move_one_task tries to move exactly one task from busiest to this_rq, as
+ * part of active balancing operations within "domain".
+ * Returns 1 if successful and 0 otherwise.
+ *
+ * Called with both runqueues locked.
+ */
+static int
+move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+	      struct sched_domain *sd, enum cpu_idle_type idle)
 {
 	struct cfs_rq *busy_cfs_rq;
 	struct rq_iterator cfs_rq_iterator;
@@ -2094,16 +2124,15 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		      struct sched_domain *sd, enum cpu_idle_type idle,
 		      int *all_pinned)
 {
-	const struct sched_class *class = sched_class_highest;
-	unsigned long total_load_moved = 0;
+	unsigned long total_load_moved = 0, load_moved;
 	int this_best_prio = this_rq->curr->prio;
 
 	do {
-		total_load_moved +=
-			class->load_balance(this_rq, this_cpu, busiest,
+		load_moved = load_balance_fair(this_rq, this_cpu, busiest,
 				max_load_move - total_load_moved,
 				sd, idle, all_pinned, &this_best_prio);
-		class = class->next;
+
+		total_load_moved += load_moved;
 
 #ifdef CONFIG_PREEMPT
 		/*
@@ -2114,7 +2143,7 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
 			break;
 #endif
-	} while (class && max_load_move > total_load_moved);
+	} while (load_moved && max_load_move > total_load_moved);
 
 	return total_load_moved > 0;
 }
@@ -2145,25 +2174,6 @@ iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	return 0;
 }
 
-/*
- * move_one_task tries to move exactly one task from busiest to this_rq, as
- * part of active balancing operations within "domain".
- * Returns 1 if successful and 0 otherwise.
- *
- * Called with both runqueues locked.
- */
-static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-			 struct sched_domain *sd, enum cpu_idle_type idle)
-{
-	const struct sched_class *class;
-
-	for_each_class(class) {
-		if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
-			return 1;
-	}
-
-	return 0;
-}
 /********** Helpers for find_busiest_group ************************/
 /*
  * sd_lb_stats - Structure to store the statistics of a sched_domain
@@ -3873,8 +3883,6 @@ static const struct sched_class fair_sched_class = {
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_fair,
 
-	.load_balance		= load_balance_fair,
-	.move_one_task		= move_one_task_fair,
 	.rq_online		= rq_online_fair,
 	.rq_offline		= rq_offline_fair,
 
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 01332bfc61a7..a8a6d8a50947 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -44,24 +44,6 @@ static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
 }
 
-#ifdef CONFIG_SMP
-static unsigned long
-load_balance_idle(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_load_move,
-		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
-{
-	return 0;
-}
-
-static int
-move_one_task_idle(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		   struct sched_domain *sd, enum cpu_idle_type idle)
-{
-	return 0;
-}
-#endif
-
 static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
 {
 }
@@ -119,9 +101,6 @@ static const struct sched_class idle_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_idle,
-
-	.load_balance		= load_balance_idle,
-	.move_one_task		= move_one_task_idle,
 #endif
 
 	.set_curr_task          = set_curr_task_idle,
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 072b3fcee8d8..502bb614e40a 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1481,24 +1481,6 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 		push_rt_tasks(rq);
 }
 
-static unsigned long
-load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		unsigned long max_load_move,
-		struct sched_domain *sd, enum cpu_idle_type idle,
-		int *all_pinned, int *this_best_prio)
-{
-	/* don't touch RT tasks */
-	return 0;
-}
-
-static int
-move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		 struct sched_domain *sd, enum cpu_idle_type idle)
-{
-	/* don't touch RT tasks */
-	return 0;
-}
-
 static void set_cpus_allowed_rt(struct task_struct *p,
 				const struct cpumask *new_mask)
 {
@@ -1746,8 +1728,6 @@ static const struct sched_class rt_sched_class = {
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_rt,
 
-	.load_balance		= load_balance_rt,
-	.move_one_task		= move_one_task_rt,
 	.set_cpus_allowed       = set_cpus_allowed_rt,
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,

From ee00e66ffff250fb0d3a789e5565462f71c7c9a7 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 17 Dec 2009 17:25:20 +0100
Subject: [PATCH 05/25] sched: Remove rq_iterator usage from load_balance_fair

Since we only ever iterate the fair class, do away with this abstraction.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 80 ++++++++++++++++-----------------------------
 1 file changed, 29 insertions(+), 51 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index faf9a2f099ab..709deb33708a 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1866,26 +1866,9 @@ static unsigned long
 balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		unsigned long max_load_move, struct sched_domain *sd,
 		enum cpu_idle_type idle, int *all_pinned,
-		int *this_best_prio, struct rq_iterator *iterator);
+		int *this_best_prio, struct cfs_rq *busiest_cfs_rq);
 
 
-static unsigned long
-__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		unsigned long max_load_move, struct sched_domain *sd,
-		enum cpu_idle_type idle, int *all_pinned, int *this_best_prio,
-		struct cfs_rq *cfs_rq)
-{
-	struct rq_iterator cfs_rq_iterator;
-
-	cfs_rq_iterator.start = load_balance_start_fair;
-	cfs_rq_iterator.next = load_balance_next_fair;
-	cfs_rq_iterator.arg = cfs_rq;
-
-	return balance_tasks(this_rq, this_cpu, busiest,
-			max_load_move, sd, idle, all_pinned,
-			this_best_prio, &cfs_rq_iterator);
-}
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
@@ -1915,9 +1898,9 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		rem_load = (u64)rem_load_move * busiest_weight;
 		rem_load = div_u64(rem_load, busiest_h_load + 1);
 
-		moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
+		moved_load = balance_tasks(this_rq, this_cpu, busiest,
 				rem_load, sd, idle, all_pinned, this_best_prio,
-				tg->cfs_rq[busiest_cpu]);
+				busiest_cfs_rq);
 
 		if (!moved_load)
 			continue;
@@ -1940,7 +1923,7 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  struct sched_domain *sd, enum cpu_idle_type idle,
 		  int *all_pinned, int *this_best_prio)
 {
-	return __load_balance_fair(this_rq, this_cpu, busiest,
+	return balance_tasks(this_rq, this_cpu, busiest,
 			max_load_move, sd, idle, all_pinned,
 			this_best_prio, &busiest->cfs);
 }
@@ -2050,53 +2033,48 @@ static unsigned long
 balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	      unsigned long max_load_move, struct sched_domain *sd,
 	      enum cpu_idle_type idle, int *all_pinned,
-	      int *this_best_prio, struct rq_iterator *iterator)
+	      int *this_best_prio, struct cfs_rq *busiest_cfs_rq)
 {
 	int loops = 0, pulled = 0, pinned = 0;
-	struct task_struct *p;
 	long rem_load_move = max_load_move;
+	struct task_struct *p, *n;
 
 	if (max_load_move == 0)
 		goto out;
 
 	pinned = 1;
 
-	/*
-	 * Start the load-balancing iterator:
-	 */
-	p = iterator->start(iterator->arg);
-next:
-	if (!p || loops++ > sysctl_sched_nr_migrate)
-		goto out;
+	list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) {
+		if (loops++ > sysctl_sched_nr_migrate)
+			break;
 
-	if ((p->se.load.weight >> 1) > rem_load_move ||
-	    !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
-		p = iterator->next(iterator->arg);
-		goto next;
-	}
+		if ((p->se.load.weight >> 1) > rem_load_move ||
+		    !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned))
+			continue;
 
-	pull_task(busiest, p, this_rq, this_cpu);
-	pulled++;
-	rem_load_move -= p->se.load.weight;
+		pull_task(busiest, p, this_rq, this_cpu);
+		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;
+		/*
+		 * 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)
+			break;
 #endif
 
-	/*
-	 * We only want to steal up to the prescribed amount of weighted load.
-	 */
-	if (rem_load_move > 0) {
+		/*
+		 * We only want to steal up to the prescribed amount of
+		 * weighted load.
+		 */
+		if (rem_load_move <= 0)
+			break;
+
 		if (p->prio < *this_best_prio)
 			*this_best_prio = p->prio;
-		p = iterator->next(iterator->arg);
-		goto next;
 	}
 out:
 	/*

From 897c395f4c94ae19302f92393a0b8304e414ee06 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 17 Dec 2009 17:45:42 +0100
Subject: [PATCH 06/25] sched: Remove rq_iterator from move_one_task

Again, since we only iterate the fair class, remove the abstraction.

Since this is the last user of the rq_iterator, remove all that too.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 146 +++++++++++---------------------------------
 1 file changed, 36 insertions(+), 110 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 709deb33708a..e48e459da98d 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1814,54 +1814,6 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
  * Fair scheduling class load-balancing methods:
  */
 
-/*
- * Load-balancing iterator. Note: while the runqueue stays locked
- * during the whole iteration, the current task might be
- * dequeued so the iterator has to be dequeue-safe. Here we
- * achieve that by always pre-iterating before returning
- * the current task:
- */
-static struct task_struct *
-__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
-{
-	struct task_struct *p = NULL;
-	struct sched_entity *se;
-
-	if (next == &cfs_rq->tasks)
-		return NULL;
-
-	se = list_entry(next, struct sched_entity, group_node);
-	p = task_of(se);
-	cfs_rq->balance_iterator = next->next;
-
-	return p;
-}
-
-static struct task_struct *load_balance_start_fair(void *arg)
-{
-	struct cfs_rq *cfs_rq = arg;
-
-	return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next);
-}
-
-static struct task_struct *load_balance_next_fair(void *arg)
-{
-	struct cfs_rq *cfs_rq = arg;
-
-	return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
-}
-
-/*
- * runqueue iterator, to support SMP load-balancing between different
- * scheduling classes, without having to expose their internal data
- * structures to the load-balancing proper:
- */
-struct rq_iterator {
-	void *arg;
-	struct task_struct *(*start)(void *);
-	struct task_struct *(*next)(void *);
-};
-
 static unsigned long
 balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		unsigned long max_load_move, struct sched_domain *sd,
@@ -1929,42 +1881,6 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 }
 #endif
 
-static int
-iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		struct sched_domain *sd, enum cpu_idle_type idle,
-		struct rq_iterator *iterator);
-
-/*
- * move_one_task tries to move exactly one task from busiest to this_rq, as
- * part of active balancing operations within "domain".
- * Returns 1 if successful and 0 otherwise.
- *
- * Called with both runqueues locked.
- */
-static int
-move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-	      struct sched_domain *sd, enum cpu_idle_type idle)
-{
-	struct cfs_rq *busy_cfs_rq;
-	struct rq_iterator cfs_rq_iterator;
-
-	cfs_rq_iterator.start = load_balance_start_fair;
-	cfs_rq_iterator.next = load_balance_next_fair;
-
-	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
-		/*
-		 * pass busy_cfs_rq argument into
-		 * load_balance_[start|next]_fair iterators
-		 */
-		cfs_rq_iterator.arg = busy_cfs_rq;
-		if (iter_move_one_task(this_rq, this_cpu, busiest, sd, idle,
-				       &cfs_rq_iterator))
-		    return 1;
-	}
-
-	return 0;
-}
-
 /*
  * pull_task - move a task from a remote runqueue to the local runqueue.
  * Both runqueues must be locked.
@@ -2029,6 +1945,42 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 	return 1;
 }
 
+/*
+ * move_one_task tries to move exactly one task from busiest to this_rq, as
+ * part of active balancing operations within "domain".
+ * Returns 1 if successful and 0 otherwise.
+ *
+ * Called with both runqueues locked.
+ */
+static int
+move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+	      struct sched_domain *sd, enum cpu_idle_type idle)
+{
+	struct task_struct *p, *n;
+	struct cfs_rq *cfs_rq;
+	int pinned = 0;
+
+	for_each_leaf_cfs_rq(busiest, cfs_rq) {
+		list_for_each_entry_safe(p, n, &cfs_rq->tasks, se.group_node) {
+
+			if (!can_migrate_task(p, busiest, this_cpu,
+						sd, idle, &pinned))
+				continue;
+
+			pull_task(busiest, p, this_rq, this_cpu);
+			/*
+			 * Right now, this is only the second place pull_task()
+			 * is called, so we can safely collect pull_task()
+			 * stats here rather than inside pull_task().
+			 */
+			schedstat_inc(sd, lb_gained[idle]);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
 static unsigned long
 balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	      unsigned long max_load_move, struct sched_domain *sd,
@@ -2126,32 +2078,6 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	return total_load_moved > 0;
 }
 
-static int
-iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		   struct sched_domain *sd, enum cpu_idle_type idle,
-		   struct rq_iterator *iterator)
-{
-	struct task_struct *p = iterator->start(iterator->arg);
-	int pinned = 0;
-
-	while (p) {
-		if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
-			pull_task(busiest, p, this_rq, this_cpu);
-			/*
-			 * Right now, this is only the second place pull_task()
-			 * is called, so we can safely collect pull_task()
-			 * stats here rather than inside pull_task().
-			 */
-			schedstat_inc(sd, lb_gained[idle]);
-
-			return 1;
-		}
-		p = iterator->next(iterator->arg);
-	}
-
-	return 0;
-}
-
 /********** Helpers for find_busiest_group ************************/
 /*
  * sd_lb_stats - Structure to store the statistics of a sched_domain

From 230059de77a4e0f6afba98073e73bc9fd471506e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 17 Dec 2009 17:47:12 +0100
Subject: [PATCH 07/25] sched: Remove from fwd decls

Move code around to get rid of fwd declarations.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 127 +++++++++++++++++++++-----------------------
 1 file changed, 60 insertions(+), 67 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index e48e459da98d..93fccbadde23 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1814,73 +1814,6 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
  * Fair scheduling class load-balancing methods:
  */
 
-static unsigned long
-balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		unsigned long max_load_move, struct sched_domain *sd,
-		enum cpu_idle_type idle, int *all_pinned,
-		int *this_best_prio, struct cfs_rq *busiest_cfs_rq);
-
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static unsigned long
-load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_load_move,
-		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
-{
-	long rem_load_move = max_load_move;
-	int busiest_cpu = cpu_of(busiest);
-	struct task_group *tg;
-
-	rcu_read_lock();
-	update_h_load(busiest_cpu);
-
-	list_for_each_entry_rcu(tg, &task_groups, list) {
-		struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
-		unsigned long busiest_h_load = busiest_cfs_rq->h_load;
-		unsigned long busiest_weight = busiest_cfs_rq->load.weight;
-		u64 rem_load, moved_load;
-
-		/*
-		 * empty group
-		 */
-		if (!busiest_cfs_rq->task_weight)
-			continue;
-
-		rem_load = (u64)rem_load_move * busiest_weight;
-		rem_load = div_u64(rem_load, busiest_h_load + 1);
-
-		moved_load = balance_tasks(this_rq, this_cpu, busiest,
-				rem_load, sd, idle, all_pinned, this_best_prio,
-				busiest_cfs_rq);
-
-		if (!moved_load)
-			continue;
-
-		moved_load *= busiest_h_load;
-		moved_load = div_u64(moved_load, busiest_weight + 1);
-
-		rem_load_move -= moved_load;
-		if (rem_load_move < 0)
-			break;
-	}
-	rcu_read_unlock();
-
-	return max_load_move - rem_load_move;
-}
-#else
-static unsigned long
-load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_load_move,
-		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
-{
-	return balance_tasks(this_rq, this_cpu, busiest,
-			max_load_move, sd, idle, all_pinned,
-			this_best_prio, &busiest->cfs);
-}
-#endif
-
 /*
  * pull_task - move a task from a remote runqueue to the local runqueue.
  * Both runqueues must be locked.
@@ -2042,6 +1975,66 @@ out:
 	return max_load_move - rem_load_move;
 }
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static unsigned long
+load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		  unsigned long max_load_move,
+		  struct sched_domain *sd, enum cpu_idle_type idle,
+		  int *all_pinned, int *this_best_prio)
+{
+	long rem_load_move = max_load_move;
+	int busiest_cpu = cpu_of(busiest);
+	struct task_group *tg;
+
+	rcu_read_lock();
+	update_h_load(busiest_cpu);
+
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
+		unsigned long busiest_h_load = busiest_cfs_rq->h_load;
+		unsigned long busiest_weight = busiest_cfs_rq->load.weight;
+		u64 rem_load, moved_load;
+
+		/*
+		 * empty group
+		 */
+		if (!busiest_cfs_rq->task_weight)
+			continue;
+
+		rem_load = (u64)rem_load_move * busiest_weight;
+		rem_load = div_u64(rem_load, busiest_h_load + 1);
+
+		moved_load = balance_tasks(this_rq, this_cpu, busiest,
+				rem_load, sd, idle, all_pinned, this_best_prio,
+				busiest_cfs_rq);
+
+		if (!moved_load)
+			continue;
+
+		moved_load *= busiest_h_load;
+		moved_load = div_u64(moved_load, busiest_weight + 1);
+
+		rem_load_move -= moved_load;
+		if (rem_load_move < 0)
+			break;
+	}
+	rcu_read_unlock();
+
+	return max_load_move - rem_load_move;
+}
+#else
+static unsigned long
+load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		  unsigned long max_load_move,
+		  struct sched_domain *sd, enum cpu_idle_type idle,
+		  int *all_pinned, int *this_best_prio)
+{
+	return balance_tasks(this_rq, this_cpu, busiest,
+			max_load_move, sd, idle, all_pinned,
+			this_best_prio, &busiest->cfs);
+}
+#endif
+
 /*
  * move_tasks tries to move up to max_load_move weighted load from busiest to
  * this_rq, as part of a balancing operation within domain "sd".

From baa8c1102f0cd86e69c1497d61d2ee177e663663 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 17 Dec 2009 18:10:09 +0100
Subject: [PATCH 08/25] sched: Add a lock break for PREEMPT=y

Since load-balancing can hold rq->locks for quite a long while, allow
breaking out early when there is lock contention.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 93fccbadde23..65d08207e925 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2065,6 +2065,10 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		 */
 		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
 			break;
+
+		if (raw_spin_is_contended(&this_rq->lock) ||
+				raw_spin_is_contended(&busiest->lock))
+			break;
 #endif
 	} while (load_moved && max_load_move > total_load_moved);
 

From 1af3ed3ddf27499c3f57662c4c29871e2b95e5f9 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 23 Dec 2009 15:10:31 +0100
Subject: [PATCH 09/25] sched: Unify load_balance{,_newidle}()

load_balance() and load_balance_newidle() look remarkably similar, one
key point they differ in is the condition on when to active balance.

So split out that logic into a separate function.

One side effect is that previously load_balance_newidle() used to fail
and return -1 under these conditions, whereas now it doesn't. I've not
yet fully figured out the whole -1 return case for either
load_balance{,_newidle}().

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 115 +++++++++++++++++++++++---------------------
 1 file changed, 59 insertions(+), 56 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 65d08207e925..10408323794e 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2816,6 +2816,39 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
 /* Working cpumask for load_balance and load_balance_newidle. */
 static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
 
+static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle)
+{
+	if (idle == CPU_NEWLY_IDLE) {
+		/*
+		 * The only task running in a non-idle cpu can be moved to this
+		 * cpu in an attempt to completely freeup the other CPU
+		 * package.
+		 *
+		 * The package power saving logic comes from
+		 * find_busiest_group(). If there are no imbalance, then
+		 * f_b_g() will return NULL. However when sched_mc={1,2} then
+		 * f_b_g() will select a group from which a running task may be
+		 * pulled to this cpu in order to make the other package idle.
+		 * If there is no opportunity to make a package idle and if
+		 * there are no imbalance, then f_b_g() will return NULL and no
+		 * action will be taken in load_balance_newidle().
+		 *
+		 * Under normal task pull operation due to imbalance, there
+		 * will be more than one task in the source run queue and
+		 * move_tasks() will succeed.  ld_moved will be true and this
+		 * active balance code will not be triggered.
+		 */
+		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+			return 0;
+
+		if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
+			return 0;
+	}
+
+	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
+}
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
@@ -2902,8 +2935,7 @@ redo:
 		schedstat_inc(sd, lb_failed[idle]);
 		sd->nr_balance_failed++;
 
-		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
-
+		if (need_active_balance(sd, sd_idle, idle)) {
 			raw_spin_lock_irqsave(&busiest->lock, flags);
 
 			/* don't kick the migration_thread, if the curr
@@ -3049,66 +3081,37 @@ redo:
 		int active_balance = 0;
 
 		schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
-		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-			return -1;
+		sd->nr_balance_failed++;
 
-		if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
-			return -1;
+		if (need_active_balance(sd, sd_idle, CPU_NEWLY_IDLE)) {
+			double_lock_balance(this_rq, busiest);
 
-		if (sd->nr_balance_failed++ < 2)
-			return -1;
+			/*
+			 * don't kick the migration_thread, if the curr
+			 * task on busiest cpu can't be moved to this_cpu
+			 */
+			if (!cpumask_test_cpu(this_cpu,
+					      &busiest->curr->cpus_allowed)) {
+				double_unlock_balance(this_rq, busiest);
+				all_pinned = 1;
+				return ld_moved;
+			}
 
-		/*
-		 * The only task running in a non-idle cpu can be moved to this
-		 * cpu in an attempt to completely freeup the other CPU
-		 * package. The same method used to move task in load_balance()
-		 * have been extended for load_balance_newidle() to speedup
-		 * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2)
-		 *
-		 * The package power saving logic comes from
-		 * find_busiest_group().  If there are no imbalance, then
-		 * f_b_g() will return NULL.  However when sched_mc={1,2} then
-		 * f_b_g() will select a group from which a running task may be
-		 * pulled to this cpu in order to make the other package idle.
-		 * If there is no opportunity to make a package idle and if
-		 * there are no imbalance, then f_b_g() will return NULL and no
-		 * action will be taken in load_balance_newidle().
-		 *
-		 * Under normal task pull operation due to imbalance, there
-		 * will be more than one task in the source run queue and
-		 * move_tasks() will succeed.  ld_moved will be true and this
-		 * active balance code will not be triggered.
-		 */
+			if (!busiest->active_balance) {
+				busiest->active_balance = 1;
+				busiest->push_cpu = this_cpu;
+				active_balance = 1;
+			}
 
-		/* Lock busiest in correct order while this_rq is held */
-		double_lock_balance(this_rq, busiest);
-
-		/*
-		 * don't kick the migration_thread, if the curr
-		 * task on busiest cpu can't be moved to this_cpu
-		 */
-		if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
 			double_unlock_balance(this_rq, busiest);
-			all_pinned = 1;
-			return ld_moved;
+			/*
+			 * Should not call ttwu while holding a rq->lock
+			 */
+			raw_spin_unlock(&this_rq->lock);
+			if (active_balance)
+				wake_up_process(busiest->migration_thread);
+			raw_spin_lock(&this_rq->lock);
 		}
-
-		if (!busiest->active_balance) {
-			busiest->active_balance = 1;
-			busiest->push_cpu = this_cpu;
-			active_balance = 1;
-		}
-
-		double_unlock_balance(this_rq, busiest);
-		/*
-		 * Should not call ttwu while holding a rq->lock
-		 */
-		raw_spin_unlock(&this_rq->lock);
-		if (active_balance)
-			wake_up_process(busiest->migration_thread);
-		raw_spin_lock(&this_rq->lock);
-
 	} else
 		sd->nr_balance_failed = 0;
 

From f492e12ef050e02bf0185b6b57874992591b9be1 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 23 Dec 2009 15:29:42 +0100
Subject: [PATCH 10/25] sched: Remove load_balance_newidle()

The two functions: load_balance{,_newidle}() are very similar, with the
following differences:

 - rq->lock usage
 - sb->balance_interval updates
 - *balance check

So remove the load_balance_newidle() call with load_balance(.idle =
CPU_NEWLY_IDLE), explicitly unlock the rq->lock before calling (would be
done by double_lock_balance() anyway), and ignore the other differences
for now.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 135 +++++---------------------------------------
 1 file changed, 13 insertions(+), 122 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 10408323794e..de5ab1239e04 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3009,125 +3009,6 @@ out:
 	return ld_moved;
 }
 
-/*
- * Check this_cpu to ensure it is balanced within domain. Attempt to move
- * tasks if there is an imbalance.
- *
- * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE).
- * this_rq is locked.
- */
-static int
-load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
-{
-	struct sched_group *group;
-	struct rq *busiest = NULL;
-	unsigned long imbalance;
-	int ld_moved = 0;
-	int sd_idle = 0;
-	int all_pinned = 0;
-	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
-
-	cpumask_copy(cpus, cpu_active_mask);
-
-	/*
-	 * When power savings policy is enabled for the parent domain, idle
-	 * sibling can pick up load irrespective of busy siblings. In this case,
-	 * let the state of idle sibling percolate up as IDLE, instead of
-	 * portraying it as CPU_NOT_IDLE.
-	 */
-	if (sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		sd_idle = 1;
-
-	schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]);
-redo:
-	update_shares_locked(this_rq, sd);
-	group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
-				   &sd_idle, cpus, NULL);
-	if (!group) {
-		schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]);
-		goto out_balanced;
-	}
-
-	busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus);
-	if (!busiest) {
-		schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]);
-		goto out_balanced;
-	}
-
-	BUG_ON(busiest == this_rq);
-
-	schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance);
-
-	ld_moved = 0;
-	if (busiest->nr_running > 1) {
-		/* Attempt to move tasks */
-		double_lock_balance(this_rq, busiest);
-		/* this_rq->clock is already updated */
-		update_rq_clock(busiest);
-		ld_moved = move_tasks(this_rq, this_cpu, busiest,
-					imbalance, sd, CPU_NEWLY_IDLE,
-					&all_pinned);
-		double_unlock_balance(this_rq, busiest);
-
-		if (unlikely(all_pinned)) {
-			cpumask_clear_cpu(cpu_of(busiest), cpus);
-			if (!cpumask_empty(cpus))
-				goto redo;
-		}
-	}
-
-	if (!ld_moved) {
-		int active_balance = 0;
-
-		schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
-		sd->nr_balance_failed++;
-
-		if (need_active_balance(sd, sd_idle, CPU_NEWLY_IDLE)) {
-			double_lock_balance(this_rq, busiest);
-
-			/*
-			 * don't kick the migration_thread, if the curr
-			 * task on busiest cpu can't be moved to this_cpu
-			 */
-			if (!cpumask_test_cpu(this_cpu,
-					      &busiest->curr->cpus_allowed)) {
-				double_unlock_balance(this_rq, busiest);
-				all_pinned = 1;
-				return ld_moved;
-			}
-
-			if (!busiest->active_balance) {
-				busiest->active_balance = 1;
-				busiest->push_cpu = this_cpu;
-				active_balance = 1;
-			}
-
-			double_unlock_balance(this_rq, busiest);
-			/*
-			 * Should not call ttwu while holding a rq->lock
-			 */
-			raw_spin_unlock(&this_rq->lock);
-			if (active_balance)
-				wake_up_process(busiest->migration_thread);
-			raw_spin_lock(&this_rq->lock);
-		}
-	} else
-		sd->nr_balance_failed = 0;
-
-	update_shares_locked(this_rq, sd);
-	return ld_moved;
-
-out_balanced:
-	schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]);
-	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		return -1;
-	sd->nr_balance_failed = 0;
-
-	return 0;
-}
-
 /*
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
@@ -3143,16 +3024,23 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 	if (this_rq->avg_idle < sysctl_sched_migration_cost)
 		return;
 
+	/*
+	 * Drop the rq->lock, but keep IRQ/preempt disabled.
+	 */
+	raw_spin_unlock(&this_rq->lock);
+
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
+		int balance = 1;
 
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;
 
-		if (sd->flags & SD_BALANCE_NEWIDLE)
+		if (sd->flags & SD_BALANCE_NEWIDLE) {
 			/* If we've pulled tasks over stop searching: */
-			pulled_task = load_balance_newidle(this_cpu, this_rq,
-							   sd);
+			pulled_task = load_balance(this_cpu, this_rq,
+						   sd, CPU_NEWLY_IDLE, &balance);
+		}
 
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
@@ -3162,6 +3050,9 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 			break;
 		}
 	}
+
+	raw_spin_lock(&this_rq->lock);
+
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
 		/*
 		 * We are going idle. next_balance may be set based on

From 8f190fb3f7a405682666d3723f6ec370b5afe4da Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 24 Dec 2009 14:18:21 +0100
Subject: [PATCH 11/25] sched: Assume *balance is valid

Since all load_balance() callers will have !NULL balance parameters we
can now assume so and remove a few checks.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index de5ab1239e04..0b482f5b5b3b 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2465,7 +2465,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	 * to do the newly idle load balance.
 	 */
 	if (idle != CPU_NEWLY_IDLE && local_group &&
-	    balance_cpu != this_cpu && balance) {
+	    balance_cpu != this_cpu) {
 		*balance = 0;
 		return;
 	}
@@ -2528,7 +2528,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 		update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle,
 				local_group, cpus, balance, &sgs);
 
-		if (local_group && balance && !(*balance))
+		if (local_group && !(*balance))
 			return;
 
 		sds->total_load += sgs.group_load;
@@ -2720,7 +2720,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	 * 5) The imbalance is within the specified limit.
 	 * 6) Any rebalance would lead to ping-pong
 	 */
-	if (balance && !(*balance))
+	if (!(*balance))
 		goto ret;
 
 	if (!sds.busiest || sds.busiest_nr_running == 0)

From 871e35bc9733f273eaf5ceb69bbd0423b58e5285 Mon Sep 17 00:00:00 2001
From: Gautham R Shenoy <ego@in.ibm.com>
Date: Wed, 20 Jan 2010 14:02:44 -0600
Subject: [PATCH 12/25] sched: Fix the place where group powers are updated

We want to update the sched_group_powers when balance_cpu == this_cpu.

Currently the group powers are updated only if the balance_cpu is the
first CPU in the local group. But balance_cpu = this_cpu could also be
the first idle cpu in the group. Hence fix the place where the group
powers are updated.

Signed-off-by: Gautham R Shenoy <ego@in.ibm.com>
Signed-off-by: Joel Schopp <jschopp@austin.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1264017764.5717.127.camel@jschopp-laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 0b482f5b5b3b..22231ccb2f98 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2418,11 +2418,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	unsigned long sum_avg_load_per_task;
 	unsigned long avg_load_per_task;
 
-	if (local_group) {
+	if (local_group)
 		balance_cpu = group_first_cpu(group);
-		if (balance_cpu == this_cpu)
-			update_group_power(sd, this_cpu);
-	}
 
 	/* Tally up the load of all CPUs in the group */
 	sum_avg_load_per_task = avg_load_per_task = 0;
@@ -2470,6 +2467,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 		return;
 	}
 
+	update_group_power(sd, this_cpu);
+
 	/* Adjust by relative CPU power of the group */
 	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
 

From 7c9414385ebfdd87cc542d4e7e3bb0dbb2d3ce25 Mon Sep 17 00:00:00 2001
From: Dhaval Giani <dhaval.giani@gmail.com>
Date: Wed, 20 Jan 2010 13:26:18 +0100
Subject: [PATCH 13/25] sched: Remove USER_SCHED

Remove the USER_SCHED feature. It has been scheduled to be removed in
2.6.34 as per http://marc.info/?l=linux-kernel&m=125728479022976&w=2

Signed-off-by: Dhaval Giani <dhaval.giani@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1263990378.24844.3.camel@localhost>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 Documentation/feature-removal-schedule.txt |  15 -
 include/linux/sched.h                      |  14 +-
 init/Kconfig                               |  81 ++----
 kernel/ksysfs.c                            |   8 -
 kernel/sched.c                             | 114 +-------
 kernel/sys.c                               |   5 -
 kernel/user.c                              | 305 ---------------------
 7 files changed, 38 insertions(+), 504 deletions(-)

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 870d190fe617..04a3fc3d139b 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -6,21 +6,6 @@ be removed from this file.
 
 ---------------------------
 
-What:	USER_SCHED
-When:	2.6.34
-
-Why:	USER_SCHED was implemented as a proof of concept for group scheduling.
-	The effect of USER_SCHED can already be achieved from userspace with
-	the help of libcgroup. The removal of USER_SCHED will also simplify
-	the scheduler code with the removal of one major ifdef. There are also
-	issues USER_SCHED has with USER_NS. A decision was taken not to fix
-	those and instead remove USER_SCHED. Also new group scheduling
-	features will not be implemented for USER_SCHED.
-
-Who:	Dhaval Giani <dhaval@linux.vnet.ibm.com>
-
----------------------------
-
 What:	PRISM54
 When:	2.6.34
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 50d685cde70e..8b079735ae5f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -731,14 +731,6 @@ struct user_struct {
 	uid_t uid;
 	struct user_namespace *user_ns;
 
-#ifdef CONFIG_USER_SCHED
-	struct task_group *tg;
-#ifdef CONFIG_SYSFS
-	struct kobject kobj;
-	struct delayed_work work;
-#endif
-#endif
-
 #ifdef CONFIG_PERF_EVENTS
 	atomic_long_t locked_vm;
 #endif
@@ -2502,13 +2494,9 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
 extern void normalize_rt_tasks(void);
 
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
 
 extern struct task_group init_task_group;
-#ifdef CONFIG_USER_SCHED
-extern struct task_group root_task_group;
-extern void set_tg_uid(struct user_struct *user);
-#endif
 
 extern struct task_group *sched_create_group(struct task_group *parent);
 extern void sched_destroy_group(struct task_group *tg);
diff --git a/init/Kconfig b/init/Kconfig
index a23da9f01803..e9fa3007a6fc 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -435,57 +435,6 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
 	bool
 
-config GROUP_SCHED
-	bool "Group CPU scheduler"
-	depends on EXPERIMENTAL
-	default n
-	help
-	  This feature lets CPU scheduler recognize task groups and control CPU
-	  bandwidth allocation to such task groups.
-	  In order to create a group from arbitrary set of processes, use
-	  CONFIG_CGROUPS. (See Control Group support.)
-
-config FAIR_GROUP_SCHED
-	bool "Group scheduling for SCHED_OTHER"
-	depends on GROUP_SCHED
-	default GROUP_SCHED
-
-config RT_GROUP_SCHED
-	bool "Group scheduling for SCHED_RR/FIFO"
-	depends on EXPERIMENTAL
-	depends on GROUP_SCHED
-	default n
-	help
-	  This feature lets you explicitly allocate real CPU bandwidth
-	  to users or control groups (depending on the "Basis for grouping tasks"
-	  setting below. If enabled, it will also make it impossible to
-	  schedule realtime tasks for non-root users until you allocate
-	  realtime bandwidth for them.
-	  See Documentation/scheduler/sched-rt-group.txt for more information.
-
-choice
-	depends on GROUP_SCHED
-	prompt "Basis for grouping tasks"
-	default USER_SCHED
-
-config USER_SCHED
-	bool "user id"
-	help
-	  This option will choose userid as the basis for grouping
-	  tasks, thus providing equal CPU bandwidth to each user.
-
-config CGROUP_SCHED
-	bool "Control groups"
- 	depends on CGROUPS
- 	help
-	  This option allows you to create arbitrary task groups
-	  using the "cgroup" pseudo filesystem and control
-	  the cpu bandwidth allocated to each such task group.
-	  Refer to Documentation/cgroups/cgroups.txt for more
-	  information on "cgroup" pseudo filesystem.
-
-endchoice
-
 menuconfig CGROUPS
 	boolean "Control Group support"
 	help
@@ -606,6 +555,36 @@ config CGROUP_MEM_RES_CTLR_SWAP
 	  Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
 	  size is 4096bytes, 512k per 1Gbytes of swap.
 
+menuconfig CGROUP_SCHED
+	bool "Group CPU scheduler"
+	depends on EXPERIMENTAL && CGROUPS
+	default n
+	help
+	  This feature lets CPU scheduler recognize task groups and control CPU
+	  bandwidth allocation to such task groups. It uses cgroups to group
+	  tasks.
+
+if CGROUP_SCHED
+config FAIR_GROUP_SCHED
+	bool "Group scheduling for SCHED_OTHER"
+	depends on CGROUP_SCHED
+	default CGROUP_SCHED
+
+config RT_GROUP_SCHED
+	bool "Group scheduling for SCHED_RR/FIFO"
+	depends on EXPERIMENTAL
+	depends on CGROUP_SCHED
+	default n
+	help
+	  This feature lets you explicitly allocate real CPU bandwidth
+	  to users or control groups (depending on the "Basis for grouping tasks"
+	  setting below. If enabled, it will also make it impossible to
+	  schedule realtime tasks for non-root users until you allocate
+	  realtime bandwidth for them.
+	  See Documentation/scheduler/sched-rt-group.txt for more information.
+
+endif #CGROUP_SCHED
+
 endif # CGROUPS
 
 config MM_OWNER
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 3feaf5a74514..6b1ccc3f0205 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -197,16 +197,8 @@ static int __init ksysfs_init(void)
 			goto group_exit;
 	}
 
-	/* create the /sys/kernel/uids/ directory */
-	error = uids_sysfs_init();
-	if (error)
-		goto notes_exit;
-
 	return 0;
 
-notes_exit:
-	if (notes_size > 0)
-		sysfs_remove_bin_file(kernel_kobj, &notes_attr);
 group_exit:
 	sysfs_remove_group(kernel_kobj, &kernel_attr_group);
 kset_exit:
diff --git a/kernel/sched.c b/kernel/sched.c
index c0be07932a8d..41e76d325648 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -233,7 +233,7 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
  */
 static DEFINE_MUTEX(sched_domains_mutex);
 
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
 
 #include <linux/cgroup.h>
 
@@ -243,13 +243,7 @@ static LIST_HEAD(task_groups);
 
 /* task group related information */
 struct task_group {
-#ifdef CONFIG_CGROUP_SCHED
 	struct cgroup_subsys_state css;
-#endif
-
-#ifdef CONFIG_USER_SCHED
-	uid_t uid;
-#endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* schedulable entities of this group on each cpu */
@@ -274,35 +268,7 @@ struct task_group {
 	struct list_head children;
 };
 
-#ifdef CONFIG_USER_SCHED
-
-/* Helper function to pass uid information to create_sched_user() */
-void set_tg_uid(struct user_struct *user)
-{
-	user->tg->uid = user->uid;
-}
-
-/*
- * Root task group.
- *	Every UID task group (including init_task_group aka UID-0) will
- *	be a child to this group.
- */
-struct task_group root_task_group;
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-/* Default task group's sched entity on each cpu */
-static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
-/* Default task group's cfs_rq on each cpu */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq);
-#endif /* CONFIG_FAIR_GROUP_SCHED */
-
-#ifdef CONFIG_RT_GROUP_SCHED
-static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq_var);
-#endif /* CONFIG_RT_GROUP_SCHED */
-#else /* !CONFIG_USER_SCHED */
 #define root_task_group init_task_group
-#endif /* CONFIG_USER_SCHED */
 
 /* task_group_lock serializes add/remove of task groups and also changes to
  * a task group's cpu shares.
@@ -318,11 +284,7 @@ static int root_task_group_empty(void)
 }
 #endif
 
-#ifdef CONFIG_USER_SCHED
-# define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
-#else /* !CONFIG_USER_SCHED */
 # define INIT_TASK_GROUP_LOAD	NICE_0_LOAD
-#endif /* CONFIG_USER_SCHED */
 
 /*
  * A weight of 0 or 1 can cause arithmetics problems.
@@ -348,11 +310,7 @@ static inline struct task_group *task_group(struct task_struct *p)
 {
 	struct task_group *tg;
 
-#ifdef CONFIG_USER_SCHED
-	rcu_read_lock();
-	tg = __task_cred(p)->user->tg;
-	rcu_read_unlock();
-#elif defined(CONFIG_CGROUP_SCHED)
+#ifdef CONFIG_CGROUP_SCHED
 	tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
 				struct task_group, css);
 #else
@@ -383,7 +341,7 @@ static inline struct task_group *task_group(struct task_struct *p)
 	return NULL;
 }
 
-#endif	/* CONFIG_GROUP_SCHED */
+#endif	/* CONFIG_CGROUP_SCHED */
 
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
@@ -7678,9 +7636,6 @@ void __init sched_init(void)
 #ifdef CONFIG_RT_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
 #endif
-#ifdef CONFIG_USER_SCHED
-	alloc_size *= 2;
-#endif
 #ifdef CONFIG_CPUMASK_OFFSTACK
 	alloc_size += num_possible_cpus() * cpumask_size();
 #endif
@@ -7694,13 +7649,6 @@ void __init sched_init(void)
 		init_task_group.cfs_rq = (struct cfs_rq **)ptr;
 		ptr += nr_cpu_ids * sizeof(void **);
 
-#ifdef CONFIG_USER_SCHED
-		root_task_group.se = (struct sched_entity **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
-
-		root_task_group.cfs_rq = (struct cfs_rq **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
-#endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
 		init_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -7709,13 +7657,6 @@ void __init sched_init(void)
 		init_task_group.rt_rq = (struct rt_rq **)ptr;
 		ptr += nr_cpu_ids * sizeof(void **);
 
-#ifdef CONFIG_USER_SCHED
-		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
-
-		root_task_group.rt_rq = (struct rt_rq **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
-#endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_RT_GROUP_SCHED */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 		for_each_possible_cpu(i) {
@@ -7735,22 +7676,13 @@ void __init sched_init(void)
 #ifdef CONFIG_RT_GROUP_SCHED
 	init_rt_bandwidth(&init_task_group.rt_bandwidth,
 			global_rt_period(), global_rt_runtime());
-#ifdef CONFIG_USER_SCHED
-	init_rt_bandwidth(&root_task_group.rt_bandwidth,
-			global_rt_period(), RUNTIME_INF);
-#endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
 	list_add(&init_task_group.list, &task_groups);
 	INIT_LIST_HEAD(&init_task_group.children);
 
-#ifdef CONFIG_USER_SCHED
-	INIT_LIST_HEAD(&root_task_group.children);
-	init_task_group.parent = &root_task_group;
-	list_add(&init_task_group.siblings, &root_task_group.children);
-#endif /* CONFIG_USER_SCHED */
-#endif /* CONFIG_GROUP_SCHED */
+#endif /* CONFIG_CGROUP_SCHED */
 
 #if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
 	update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
@@ -7790,25 +7722,6 @@ void __init sched_init(void)
 		 * directly in rq->cfs (i.e init_task_group->se[] = NULL).
 		 */
 		init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL);
-#elif defined CONFIG_USER_SCHED
-		root_task_group.shares = NICE_0_LOAD;
-		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, 0, NULL);
-		/*
-		 * In case of task-groups formed thr' the user id of tasks,
-		 * init_task_group represents tasks belonging to root user.
-		 * Hence it forms a sibling of all subsequent groups formed.
-		 * In this case, init_task_group gets only a fraction of overall
-		 * system cpu resource, based on the weight assigned to root
-		 * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished
-		 * by letting tasks of init_task_group sit in a separate cfs_rq
-		 * (init_tg_cfs_rq) and having one entity represent this group of
-		 * tasks in rq->cfs (i.e init_task_group->se[] != NULL).
-		 */
-		init_tg_cfs_entry(&init_task_group,
-				&per_cpu(init_tg_cfs_rq, i),
-				&per_cpu(init_sched_entity, i), i, 1,
-				root_task_group.se[i]);
-
 #endif
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
@@ -7817,12 +7730,6 @@ void __init sched_init(void)
 		INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
 #ifdef CONFIG_CGROUP_SCHED
 		init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL);
-#elif defined CONFIG_USER_SCHED
-		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
-		init_tg_rt_entry(&init_task_group,
-				&per_cpu(init_rt_rq_var, i),
-				&per_cpu(init_sched_rt_entity, i), i, 1,
-				root_task_group.rt_se[i]);
 #endif
 #endif
 
@@ -8218,7 +8125,7 @@ static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
 static void free_sched_group(struct task_group *tg)
 {
 	free_fair_sched_group(tg);
@@ -8327,7 +8234,7 @@ void sched_move_task(struct task_struct *tsk)
 
 	task_rq_unlock(rq, &flags);
 }
-#endif /* CONFIG_GROUP_SCHED */
+#endif /* CONFIG_CGROUP_SCHED */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void __set_se_shares(struct sched_entity *se, unsigned long shares)
@@ -8469,13 +8376,6 @@ static int tg_schedulable(struct task_group *tg, void *data)
 		runtime = d->rt_runtime;
 	}
 
-#ifdef CONFIG_USER_SCHED
-	if (tg == &root_task_group) {
-		period = global_rt_period();
-		runtime = global_rt_runtime();
-	}
-#endif
-
 	/*
 	 * Cannot have more runtime than the period.
 	 */
diff --git a/kernel/sys.c b/kernel/sys.c
index 26a6b73a6b85..f75bf0936f47 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -569,11 +569,6 @@ static int set_user(struct cred *new)
 	if (!new_user)
 		return -EAGAIN;
 
-	if (!task_can_switch_user(new_user, current)) {
-		free_uid(new_user);
-		return -EINVAL;
-	}
-
 	if (atomic_read(&new_user->processes) >=
 				current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
 			new_user != INIT_USER) {
diff --git a/kernel/user.c b/kernel/user.c
index 46d0165ca70c..766467b3bcb7 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -56,9 +56,6 @@ struct user_struct root_user = {
 	.sigpending	= ATOMIC_INIT(0),
 	.locked_shm     = 0,
 	.user_ns	= &init_user_ns,
-#ifdef CONFIG_USER_SCHED
-	.tg		= &init_task_group,
-#endif
 };
 
 /*
@@ -75,268 +72,6 @@ static void uid_hash_remove(struct user_struct *up)
 	put_user_ns(up->user_ns);
 }
 
-#ifdef CONFIG_USER_SCHED
-
-static void sched_destroy_user(struct user_struct *up)
-{
-	sched_destroy_group(up->tg);
-}
-
-static int sched_create_user(struct user_struct *up)
-{
-	int rc = 0;
-
-	up->tg = sched_create_group(&root_task_group);
-	if (IS_ERR(up->tg))
-		rc = -ENOMEM;
-
-	set_tg_uid(up);
-
-	return rc;
-}
-
-#else	/* CONFIG_USER_SCHED */
-
-static void sched_destroy_user(struct user_struct *up) { }
-static int sched_create_user(struct user_struct *up) { return 0; }
-
-#endif	/* CONFIG_USER_SCHED */
-
-#if defined(CONFIG_USER_SCHED) && defined(CONFIG_SYSFS)
-
-static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
-{
-	struct user_struct *user;
-	struct hlist_node *h;
-
-	hlist_for_each_entry(user, h, hashent, uidhash_node) {
-		if (user->uid == uid) {
-			/* possibly resurrect an "almost deleted" object */
-			if (atomic_inc_return(&user->__count) == 1)
-				cancel_delayed_work(&user->work);
-			return user;
-		}
-	}
-
-	return NULL;
-}
-
-static struct kset *uids_kset; /* represents the /sys/kernel/uids/ directory */
-static DEFINE_MUTEX(uids_mutex);
-
-static inline void uids_mutex_lock(void)
-{
-	mutex_lock(&uids_mutex);
-}
-
-static inline void uids_mutex_unlock(void)
-{
-	mutex_unlock(&uids_mutex);
-}
-
-/* uid directory attributes */
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static ssize_t cpu_shares_show(struct kobject *kobj,
-			       struct kobj_attribute *attr,
-			       char *buf)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-
-	return sprintf(buf, "%lu\n", sched_group_shares(up->tg));
-}
-
-static ssize_t cpu_shares_store(struct kobject *kobj,
-				struct kobj_attribute *attr,
-				const char *buf, size_t size)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-	unsigned long shares;
-	int rc;
-
-	sscanf(buf, "%lu", &shares);
-
-	rc = sched_group_set_shares(up->tg, shares);
-
-	return (rc ? rc : size);
-}
-
-static struct kobj_attribute cpu_share_attr =
-	__ATTR(cpu_share, 0644, cpu_shares_show, cpu_shares_store);
-#endif
-
-#ifdef CONFIG_RT_GROUP_SCHED
-static ssize_t cpu_rt_runtime_show(struct kobject *kobj,
-				   struct kobj_attribute *attr,
-				   char *buf)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-
-	return sprintf(buf, "%ld\n", sched_group_rt_runtime(up->tg));
-}
-
-static ssize_t cpu_rt_runtime_store(struct kobject *kobj,
-				    struct kobj_attribute *attr,
-				    const char *buf, size_t size)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-	unsigned long rt_runtime;
-	int rc;
-
-	sscanf(buf, "%ld", &rt_runtime);
-
-	rc = sched_group_set_rt_runtime(up->tg, rt_runtime);
-
-	return (rc ? rc : size);
-}
-
-static struct kobj_attribute cpu_rt_runtime_attr =
-	__ATTR(cpu_rt_runtime, 0644, cpu_rt_runtime_show, cpu_rt_runtime_store);
-
-static ssize_t cpu_rt_period_show(struct kobject *kobj,
-				   struct kobj_attribute *attr,
-				   char *buf)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-
-	return sprintf(buf, "%lu\n", sched_group_rt_period(up->tg));
-}
-
-static ssize_t cpu_rt_period_store(struct kobject *kobj,
-				    struct kobj_attribute *attr,
-				    const char *buf, size_t size)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-	unsigned long rt_period;
-	int rc;
-
-	sscanf(buf, "%lu", &rt_period);
-
-	rc = sched_group_set_rt_period(up->tg, rt_period);
-
-	return (rc ? rc : size);
-}
-
-static struct kobj_attribute cpu_rt_period_attr =
-	__ATTR(cpu_rt_period, 0644, cpu_rt_period_show, cpu_rt_period_store);
-#endif
-
-/* default attributes per uid directory */
-static struct attribute *uids_attributes[] = {
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	&cpu_share_attr.attr,
-#endif
-#ifdef CONFIG_RT_GROUP_SCHED
-	&cpu_rt_runtime_attr.attr,
-	&cpu_rt_period_attr.attr,
-#endif
-	NULL
-};
-
-/* the lifetime of user_struct is not managed by the core (now) */
-static void uids_release(struct kobject *kobj)
-{
-	return;
-}
-
-static struct kobj_type uids_ktype = {
-	.sysfs_ops = &kobj_sysfs_ops,
-	.default_attrs = uids_attributes,
-	.release = uids_release,
-};
-
-/*
- * Create /sys/kernel/uids/<uid>/cpu_share file for this user
- * We do not create this file for users in a user namespace (until
- * sysfs tagging is implemented).
- *
- * See Documentation/scheduler/sched-design-CFS.txt for ramifications.
- */
-static int uids_user_create(struct user_struct *up)
-{
-	struct kobject *kobj = &up->kobj;
-	int error;
-
-	memset(kobj, 0, sizeof(struct kobject));
-	if (up->user_ns != &init_user_ns)
-		return 0;
-	kobj->kset = uids_kset;
-	error = kobject_init_and_add(kobj, &uids_ktype, NULL, "%d", up->uid);
-	if (error) {
-		kobject_put(kobj);
-		goto done;
-	}
-
-	kobject_uevent(kobj, KOBJ_ADD);
-done:
-	return error;
-}
-
-/* create these entries in sysfs:
- * 	"/sys/kernel/uids" directory
- * 	"/sys/kernel/uids/0" directory (for root user)
- * 	"/sys/kernel/uids/0/cpu_share" file (for root user)
- */
-int __init uids_sysfs_init(void)
-{
-	uids_kset = kset_create_and_add("uids", NULL, kernel_kobj);
-	if (!uids_kset)
-		return -ENOMEM;
-
-	return uids_user_create(&root_user);
-}
-
-/* delayed work function to remove sysfs directory for a user and free up
- * corresponding structures.
- */
-static void cleanup_user_struct(struct work_struct *w)
-{
-	struct user_struct *up = container_of(w, struct user_struct, work.work);
-	unsigned long flags;
-	int remove_user = 0;
-
-	/* Make uid_hash_remove() + sysfs_remove_file() + kobject_del()
-	 * atomic.
-	 */
-	uids_mutex_lock();
-
-	spin_lock_irqsave(&uidhash_lock, flags);
-	if (atomic_read(&up->__count) == 0) {
-		uid_hash_remove(up);
-		remove_user = 1;
-	}
-	spin_unlock_irqrestore(&uidhash_lock, flags);
-
-	if (!remove_user)
-		goto done;
-
-	if (up->user_ns == &init_user_ns) {
-		kobject_uevent(&up->kobj, KOBJ_REMOVE);
-		kobject_del(&up->kobj);
-		kobject_put(&up->kobj);
-	}
-
-	sched_destroy_user(up);
-	key_put(up->uid_keyring);
-	key_put(up->session_keyring);
-	kmem_cache_free(uid_cachep, up);
-
-done:
-	uids_mutex_unlock();
-}
-
-/* IRQs are disabled and uidhash_lock is held upon function entry.
- * IRQ state (as stored in flags) is restored and uidhash_lock released
- * upon function exit.
- */
-static void free_user(struct user_struct *up, unsigned long flags)
-{
-	INIT_DELAYED_WORK(&up->work, cleanup_user_struct);
-	schedule_delayed_work(&up->work, msecs_to_jiffies(1000));
-	spin_unlock_irqrestore(&uidhash_lock, flags);
-}
-
-#else	/* CONFIG_USER_SCHED && CONFIG_SYSFS */
-
 static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
 {
 	struct user_struct *user;
@@ -352,11 +87,6 @@ static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
 	return NULL;
 }
 
-int uids_sysfs_init(void) { return 0; }
-static inline int uids_user_create(struct user_struct *up) { return 0; }
-static inline void uids_mutex_lock(void) { }
-static inline void uids_mutex_unlock(void) { }
-
 /* IRQs are disabled and uidhash_lock is held upon function entry.
  * IRQ state (as stored in flags) is restored and uidhash_lock released
  * upon function exit.
@@ -365,32 +95,11 @@ static void free_user(struct user_struct *up, unsigned long flags)
 {
 	uid_hash_remove(up);
 	spin_unlock_irqrestore(&uidhash_lock, flags);
-	sched_destroy_user(up);
 	key_put(up->uid_keyring);
 	key_put(up->session_keyring);
 	kmem_cache_free(uid_cachep, up);
 }
 
-#endif
-
-#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED)
-/*
- * We need to check if a setuid can take place. This function should be called
- * before successfully completing the setuid.
- */
-int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
-{
-
-	return sched_rt_can_attach(up->tg, tsk);
-
-}
-#else
-int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
-{
-	return 1;
-}
-#endif
-
 /*
  * Locate the user_struct for the passed UID.  If found, take a ref on it.  The
  * caller must undo that ref with free_uid().
@@ -431,8 +140,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 	/* Make uid_hash_find() + uids_user_create() + uid_hash_insert()
 	 * atomic.
 	 */
-	uids_mutex_lock();
-
 	spin_lock_irq(&uidhash_lock);
 	up = uid_hash_find(uid, hashent);
 	spin_unlock_irq(&uidhash_lock);
@@ -445,14 +152,8 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		new->uid = uid;
 		atomic_set(&new->__count, 1);
 
-		if (sched_create_user(new) < 0)
-			goto out_free_user;
-
 		new->user_ns = get_user_ns(ns);
 
-		if (uids_user_create(new))
-			goto out_destoy_sched;
-
 		/*
 		 * Before adding this, check whether we raced
 		 * on adding the same user already..
@@ -475,17 +176,11 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		spin_unlock_irq(&uidhash_lock);
 	}
 
-	uids_mutex_unlock();
-
 	return up;
 
-out_destoy_sched:
-	sched_destroy_user(new);
 	put_user_ns(new->user_ns);
-out_free_user:
 	kmem_cache_free(uid_cachep, new);
 out_unlock:
-	uids_mutex_unlock();
 	return NULL;
 }
 

From ea87bb7853168434f4a82426dd1ea8421f9e604d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 20 Jan 2010 20:58:57 +0000
Subject: [PATCH 14/25] sched: Extend enqueue_task to allow head queueing

The ability of enqueueing a task to the head of a SCHED_FIFO priority
list is required to fix some violations of POSIX scheduling policy.

Extend the related functions with a "head" argument.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Tested-by: Carsten Emde <cbe@osadl.org>
Tested-by: Mathias Weber <mathias.weber.mw1@roche.com>
LKML-Reference: <20100120171629.734886007@linutronix.de>
---
 include/linux/sched.h |  3 ++-
 kernel/sched.c        | 13 +++++++------
 kernel/sched_fair.c   |  3 ++-
 kernel/sched_rt.c     |  3 ++-
 4 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8b079735ae5f..b35c0c7130c8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1067,7 +1067,8 @@ struct sched_domain;
 struct sched_class {
 	const struct sched_class *next;
 
-	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
+	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup,
+			      bool head);
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
 	void (*yield_task) (struct rq *rq);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 41e76d325648..f47560ff3346 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1856,13 +1856,14 @@ static void update_avg(u64 *avg, u64 sample)
 	*avg += diff >> 3;
 }
 
-static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
+static void
+enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head)
 {
 	if (wakeup)
 		p->se.start_runtime = p->se.sum_exec_runtime;
 
 	sched_info_queued(p);
-	p->sched_class->enqueue_task(rq, p, wakeup);
+	p->sched_class->enqueue_task(rq, p, wakeup, head);
 	p->se.on_rq = 1;
 }
 
@@ -1892,7 +1893,7 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible--;
 
-	enqueue_task(rq, p, wakeup);
+	enqueue_task(rq, p, wakeup, false);
 	inc_nr_running(rq);
 }
 
@@ -4236,7 +4237,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		enqueue_task(rq, p, 0);
+		enqueue_task(rq, p, 0, false);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
 	}
@@ -4280,7 +4281,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	delta = p->prio - old_prio;
 
 	if (on_rq) {
-		enqueue_task(rq, p, 0);
+		enqueue_task(rq, p, 0, false);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
@@ -8230,7 +8231,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
 	if (on_rq)
-		enqueue_task(rq, tsk, 0);
+		enqueue_task(rq, tsk, 0, false);
 
 	task_rq_unlock(rq, &flags);
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 22231ccb2f98..0e7a7af9cf8b 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1053,7 +1053,8 @@ static inline void hrtick_update(struct rq *rq)
  * increased. Here we update the fair scheduling stats and
  * then put the task into the rbtree:
  */
-static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
+static void
+enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 502bb614e40a..38076dabb44a 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -878,7 +878,8 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
 /*
  * Adding/removing a task to/from a priority array:
  */
-static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
+static void
+enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, bool head)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 

From 37dad3fce97f01e5149d69de0833d8452c0e862e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 20 Jan 2010 20:59:01 +0000
Subject: [PATCH 15/25] sched: Implement head queueing for sched_rt

The ability of enqueueing a task to the head of a SCHED_FIFO priority
list is required to fix some violations of POSIX scheduling policy.

Implement the functionality in sched_rt.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Tested-by: Carsten Emde <cbe@osadl.org>
Tested-by: Mathias Weber <mathias.weber.mw1@roche.com>
LKML-Reference: <20100120171629.772169931@linutronix.de>
---
 kernel/sched_rt.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 38076dabb44a..ca49ceb01201 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -194,7 +194,7 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
 	return rt_se->my_q;
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se);
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head);
 static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
@@ -204,7 +204,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 
 	if (rt_rq->rt_nr_running) {
 		if (rt_se && !on_rt_rq(rt_se))
-			enqueue_rt_entity(rt_se);
+			enqueue_rt_entity(rt_se, false);
 		if (rt_rq->highest_prio.curr < curr->prio)
 			resched_task(curr);
 	}
@@ -803,7 +803,7 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	dec_rt_group(rt_se, rt_rq);
 }
 
-static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
+static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
@@ -819,7 +819,10 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
 	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
 		return;
 
-	list_add_tail(&rt_se->run_list, queue);
+	if (head)
+		list_add(&rt_se->run_list, queue);
+	else
+		list_add_tail(&rt_se->run_list, queue);
 	__set_bit(rt_se_prio(rt_se), array->bitmap);
 
 	inc_rt_tasks(rt_se, rt_rq);
@@ -856,11 +859,11 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
 	}
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 {
 	dequeue_rt_stack(rt_se);
 	for_each_sched_rt_entity(rt_se)
-		__enqueue_rt_entity(rt_se);
+		__enqueue_rt_entity(rt_se, head);
 }
 
 static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
@@ -871,7 +874,7 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
 		struct rt_rq *rt_rq = group_rt_rq(rt_se);
 
 		if (rt_rq && rt_rq->rt_nr_running)
-			__enqueue_rt_entity(rt_se);
+			__enqueue_rt_entity(rt_se, false);
 	}
 }
 
@@ -886,7 +889,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, bool head)
 	if (wakeup)
 		rt_se->timeout = 0;
 
-	enqueue_rt_entity(rt_se);
+	enqueue_rt_entity(rt_se, head);
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);

From 60db48cacb9b253d5607a5ff206112a59cd09e34 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 20 Jan 2010 20:59:06 +0000
Subject: [PATCH 16/25] sched: Queue a deboosted task to the head of the RT
 prio queue

rtmutex_set_prio() is used to implement priority inheritance for
futexes. When a task is deboosted it gets enqueued at the tail of its
RT priority list. This is violating the POSIX scheduling semantics:

rt priority list X contains two runnable tasks A and B

task A	 runs with priority X and holds mutex M
task C	 preempts A and is blocked on mutex M
     	 -> task A is boosted to priority of task C (Y)
task A	 unlocks the mutex M and deboosts itself
     	 -> A is dequeued from rt priority list Y
	 -> A is enqueued to the tail of rt priority list X
task C	 schedules away
task B	 runs

This is wrong as task A did not schedule away and therefor violates
the POSIX scheduling semantics.

Enqueue the task to the head of the priority list instead.

Reported-by: Mathias Weber <mathias.weber.mw1@roche.com>
Reported-by: Carsten Emde <cbe@osadl.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Tested-by: Carsten Emde <cbe@osadl.org>
Tested-by: Mathias Weber <mathias.weber.mw1@roche.com>
LKML-Reference: <20100120171629.809074113@linutronix.de>
---
 kernel/sched.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index f47560ff3346..a56ead42d651 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4237,7 +4237,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		enqueue_task(rq, p, 0, false);
+		enqueue_task(rq, p, 0, oldprio < prio);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
 	}

From 90fdbdb48442a03c72cae5463e6edb64cb3a3a7d Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 31 Jan 2010 20:53:24 +0900
Subject: [PATCH 17/25] sched: Use for_each_bit

No change in functionality.

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <1264938810-4173-1-git-send-email-akinobu.mita@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_cpupri.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index 597b33099dfa..eeb3506c4834 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -47,9 +47,7 @@ static int convert_prio(int prio)
 }
 
 #define for_each_cpupri_active(array, idx)                    \
-  for (idx = find_first_bit(array, CPUPRI_NR_PRIORITIES);     \
-       idx < CPUPRI_NR_PRIORITIES;                            \
-       idx = find_next_bit(array, CPUPRI_NR_PRIORITIES, idx+1))
+	for_each_bit(idx, array, CPUPRI_NR_PRIORITIES)
 
 /**
  * cpupri_find - find the best (lowest-pri) CPU in the system

From 4a461c85b643258e305eb5a3aced34009db2f818 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 1 Feb 2010 11:13:39 +0100
Subject: [PATCH 18/25] sched: Remove unused update_shares_locked()

Commit f492e12ef050e02bf0185b6b57874992591b9be1 ("sched: Remove
load_balance_newidle()") removed the only user of this function,
so remove it too.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1265019219.24455.128.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index a56ead42d651..2386f5440002 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1633,16 +1633,6 @@ static void update_shares(struct sched_domain *sd)
 	}
 }
 
-static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
-{
-	if (root_task_group_empty())
-		return;
-
-	raw_spin_unlock(&rq->lock);
-	update_shares(sd);
-	raw_spin_lock(&rq->lock);
-}
-
 static void update_h_load(long cpu)
 {
 	if (root_task_group_empty())
@@ -1657,10 +1647,6 @@ static inline void update_shares(struct sched_domain *sd)
 {
 }
 
-static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
-{
-}
-
 #endif
 
 #ifdef CONFIG_PREEMPT

From 74b7eb5885415ed41d012f432398d1b697115b5f Mon Sep 17 00:00:00 2001
From: Yong Zhang <yong.zhang0@gmail.com>
Date: Fri, 29 Jan 2010 14:57:52 +0800
Subject: [PATCH 19/25] sched: Change usage of rt_rq->rt_se to
 rt_rq->tg->rt_se[cpu]

This is the first step to remove rt_rq member rt_se because it have the
same meaning with tg->rt_se[cpu]. And the latter style is also used by
the fair scheduling class.

Signed-off-by: Yong Zhang <yong.zhang0@gmail.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <2674af741001282257r28c97a92o9f90cf16fe8d3d84@mail.gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_rt.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index ca49ceb01201..bf3e38fdbe6d 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -199,8 +199,11 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
+	int this_cpu = smp_processor_id();
 	struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
-	struct sched_rt_entity *rt_se = rt_rq->rt_se;
+	struct sched_rt_entity *rt_se;
+
+	rt_se = rt_rq->tg->rt_se[this_cpu];
 
 	if (rt_rq->rt_nr_running) {
 		if (rt_se && !on_rt_rq(rt_se))
@@ -212,7 +215,10 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 
 static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
-	struct sched_rt_entity *rt_se = rt_rq->rt_se;
+	int this_cpu = smp_processor_id();
+	struct sched_rt_entity *rt_se;
+
+	rt_se = rt_rq->tg->rt_se[this_cpu];
 
 	if (rt_se && on_rt_rq(rt_se))
 		dequeue_rt_entity(rt_se);

From 23577256953c870de9b724c3a2611ce7be6a1e4e Mon Sep 17 00:00:00 2001
From: Yong Zhang <yong.zhang0@gmail.com>
Date: Fri, 29 Jan 2010 14:58:47 +0800
Subject: [PATCH 20/25] sched: Remove member rt_se from struct rt_rq

It's a duplicate of tg->rt_se[cpu] and the only usage is
sched_rt_rq_dequeue() and sched_rt_rq_enqueue(). After the
first patch to those two function. rt_se can be removed.

Signed-off-by: Yong Zhang <yong.zhang0@gmail.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <2674af741001282258q38781619u653ca4a7dd267347@mail.gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 2386f5440002..6cee227b1459 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -436,7 +436,6 @@ struct rt_rq {
 	struct rq *rq;
 	struct list_head leaf_rt_rq_list;
 	struct task_group *tg;
-	struct sched_rt_entity *rt_se;
 #endif
 };
 
@@ -7592,7 +7591,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 	tg->rt_rq[cpu] = rt_rq;
 	init_rt_rq(rt_rq, rq);
 	rt_rq->tg = tg;
-	rt_rq->rt_se = rt_se;
 	rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
 	if (add)
 		list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);

From 0c9cf2efd74dbc90354e2ccc7dbd6bad68ec6c4d Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 2 Feb 2010 14:46:10 -0800
Subject: [PATCH 21/25] percpu_counter: Make __percpu_counter_add an inline
 function on UP

Even though batch isn't used on UP, we may want to pass one in
to keep the SMP and UP code paths similar. Convert
__percpu_counter_add to an inline function so we wont get
variable unused warnings if we do.

Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/percpu_counter.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index a7684a513994..794662b2be5d 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -98,9 +98,6 @@ static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
 	fbc->count = amount;
 }
 
-#define __percpu_counter_add(fbc, amount, batch) \
-	percpu_counter_add(fbc, amount)
-
 static inline void
 percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
@@ -109,6 +106,12 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 	preempt_enable();
 }
 
+static inline void
+__percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
+{
+	percpu_counter_add(fbc, amount);
+}
+
 static inline s64 percpu_counter_read(struct percpu_counter *fbc)
 {
 	return fbc->count;

From fa535a77bd3fa32b9215ba375d6a202fe73e1dd6 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 2 Feb 2010 14:46:13 -0800
Subject: [PATCH 22/25] sched: cpuacct: Use bigger percpu counter batch values
 for stats counters

When CONFIG_VIRT_CPU_ACCOUNTING and CONFIG_CGROUP_CPUACCT are
enabled we can call cpuacct_update_stats with values much larger
than percpu_counter_batch.  This means the call to
percpu_counter_add will always add to the global count which is
protected by a spinlock and we end up with a global spinlock in
the scheduler.

Based on an idea by KOSAKI Motohiro, this patch scales the batch
value by cputime_one_jiffy such that we have the same batch
limit as we would if CONFIG_VIRT_CPU_ACCOUNTING was disabled.
His patch did this once at boot but that initialisation happened
too early on PowerPC (before time_init) and it was never updated
at runtime as a result of a hotplug cpu add/remove.

This patch instead scales percpu_counter_batch by
cputime_one_jiffy at runtime, which keeps the batch correct even
after cpu hotplug operations.  We cap it at INT_MAX in case of
overflow.

For architectures that do not support
CONFIG_VIRT_CPU_ACCOUNTING, cputime_one_jiffy is the constant 1
and gcc is smart enough to optimise min(s32
percpu_counter_batch, INT_MAX) to just percpu_counter_batch at
least on x86 and PowerPC.  So there is no need to add an #ifdef.

On a 64 thread PowerPC box with CONFIG_VIRT_CPU_ACCOUNTING and
CONFIG_CGROUP_CPUACCT enabled, a context switch microbenchmark
is 234x faster and almost matches a CONFIG_CGROUP_CPUACCT
disabled kernel:

 CONFIG_CGROUP_CPUACCT disabled:   16906698 ctx switches/sec
 CONFIG_CGROUP_CPUACCT enabled:       61720 ctx switches/sec
 CONFIG_CGROUP_CPUACCT + patch:	   16663217 ctx switches/sec

Tested with:

 wget http://ozlabs.org/~anton/junkcode/context_switch.c
 make context_switch
 for i in `seq 0 63`; do taskset -c $i ./context_switch & done
 vmstat 1

Signed-off-by: Anton Blanchard <anton@samba.org>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index f96be9370b75..bae6fcfe6d75 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8997,6 +8997,23 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 	rcu_read_unlock();
 }
 
+/*
+ * When CONFIG_VIRT_CPU_ACCOUNTING is enabled one jiffy can be very large
+ * in cputime_t units. As a result, cpuacct_update_stats calls
+ * percpu_counter_add with values large enough to always overflow the
+ * per cpu batch limit causing bad SMP scalability.
+ *
+ * To fix this we scale percpu_counter_batch by cputime_one_jiffy so we
+ * batch the same amount of time with CONFIG_VIRT_CPU_ACCOUNTING disabled
+ * and enabled. We cap it at INT_MAX which is the largest allowed batch value.
+ */
+#ifdef CONFIG_SMP
+#define CPUACCT_BATCH	\
+	min_t(long, percpu_counter_batch * cputime_one_jiffy, INT_MAX)
+#else
+#define CPUACCT_BATCH	0
+#endif
+
 /*
  * Charge the system/user time to the task's accounting group.
  */
@@ -9004,6 +9021,7 @@ static void cpuacct_update_stats(struct task_struct *tsk,
 		enum cpuacct_stat_index idx, cputime_t val)
 {
 	struct cpuacct *ca;
+	int batch = CPUACCT_BATCH;
 
 	if (unlikely(!cpuacct_subsys.active))
 		return;
@@ -9012,7 +9030,7 @@ static void cpuacct_update_stats(struct task_struct *tsk,
 	ca = task_ca(tsk);
 
 	do {
-		percpu_counter_add(&ca->cpustat[idx], val);
+		__percpu_counter_add(&ca->cpustat[idx], val, batch);
 		ca = ca->parent;
 	} while (ca);
 	rcu_read_unlock();

From 301ba0457f1ed853fc08e57785f8c87fe7e49c68 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 9 Feb 2010 15:07:40 +1100
Subject: [PATCH 23/25] kthread, sched: Remove reference to
 kthread_create_on_cpu

kthread_create_on_cpu doesn't exist so update a comment in
kthread.c to reflect this.

Signed-off-by: Anton Blanchard <anton@samba.org>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100209040740.GB3702@kryten>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/kthread.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/kthread.c b/kernel/kthread.c
index fbb6222fe7e0..82ed0ea15194 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -101,7 +101,7 @@ static void create_kthread(struct kthread_create_info *create)
  *
  * Description: This helper function creates and names a kernel
  * thread.  The thread will be stopped: use wake_up_process() to start
- * it.  See also kthread_run(), kthread_create_on_cpu().
+ * it.  See also kthread_run().
  *
  * When woken, the thread will run @threadfn() with @data as its
  * argument. @threadfn() can either call do_exit() directly if it is a

From 83ab0aa0d5623d823444db82c3b3c34d7ec364ae Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 17 Feb 2010 09:05:48 +0100
Subject: [PATCH 24/25] sched: Don't use possibly stale sched_class

setscheduler() saves task->sched_class outside of the rq->lock held
region for a check after the setscheduler changes have become
effective. That might result in checking a stale value.

rtmutex_setprio() has the same problem, though it is protected by
p->pi_lock against setscheduler(), but for correctness sake (and to
avoid bad examples) it needs to be fixed as well.

Retrieve task->sched_class inside of the rq->lock held region.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: stable@kernel.org
---
 kernel/sched.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index af5fa239804d..0b914fc90a55 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4249,7 +4249,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	unsigned long flags;
 	int oldprio, on_rq, running;
 	struct rq *rq;
-	const struct sched_class *prev_class = p->sched_class;
+	const struct sched_class *prev_class;
 
 	BUG_ON(prio < 0 || prio > MAX_PRIO);
 
@@ -4257,6 +4257,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	update_rq_clock(rq);
 
 	oldprio = p->prio;
+	prev_class = p->sched_class;
 	on_rq = p->se.on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
@@ -4476,7 +4477,7 @@ static int __sched_setscheduler(struct task_struct *p, int policy,
 {
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
 	unsigned long flags;
-	const struct sched_class *prev_class = p->sched_class;
+	const struct sched_class *prev_class;
 	struct rq *rq;
 	int reset_on_fork;
 
@@ -4590,6 +4591,7 @@ recheck:
 	p->sched_reset_on_fork = reset_on_fork;
 
 	oldprio = p->prio;
+	prev_class = p->sched_class;
 	__setscheduler(rq, p, policy, param->sched_priority);
 
 	if (running)

From dd5feea14a7de4edbd9f36db1a2db785de91b88d Mon Sep 17 00:00:00 2001
From: Suresh Siddha <suresh.b.siddha@intel.com>
Date: Tue, 23 Feb 2010 16:13:52 -0800
Subject: [PATCH 25/25] sched: Fix SCHED_MC regression caused by change in
 sched cpu_power

On platforms like dual socket quad-core platform, the scheduler load
balancer is not detecting the load imbalances in certain scenarios. This
is leading to scenarios like where one socket is completely busy (with
all the 4 cores running with 4 tasks) and leaving another socket
completely idle. This causes performance issues as those 4 tasks share
the memory controller, last-level cache bandwidth etc. Also we won't be
taking advantage of turbo-mode as much as we would like, etc.

Some of the comparisons in the scheduler load balancing code are
comparing the "weighted cpu load that is scaled wrt sched_group's
cpu_power" with the "weighted average load per task that is not scaled
wrt sched_group's cpu_power". While this has probably been broken for a
longer time (for multi socket numa nodes etc), the problem got aggrevated
via this recent change:

 |
 |  commit f93e65c186ab3c05ce2068733ca10e34fd00125e
 |  Author: Peter Zijlstra <a.p.zijlstra@chello.nl>
 |  Date:   Tue Sep 1 10:34:32 2009 +0200
 |
 |	sched: Restore __cpu_power to a straight sum of power
 |

Also with this change, the sched group cpu power alone no longer reflects
the group capacity that is needed to implement MC, MT performance
(default) and power-savings (user-selectable) policies.

We need to use the computed group capacity (sgs.group_capacity, that is
computed using the SD_PREFER_SIBLING logic in update_sd_lb_stats()) to
find out if the group with the max load is above its capacity and how
much load to move etc.

Reported-by: Ma Ling <ling.ma@intel.com>
Initial-Analysis-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
[ -v2: build fix ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <stable@kernel.org> # [2.6.32.x, 2.6.33.x]
LKML-Reference: <1266970432.11588.22.camel@sbs-t61.sc.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c | 76 +++++++++++++++++++++++++--------------------
 1 file changed, 43 insertions(+), 33 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ff7692ccda89..3e1fd96c6cf9 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2097,6 +2097,7 @@ struct sd_lb_stats {
 	unsigned long max_load;
 	unsigned long busiest_load_per_task;
 	unsigned long busiest_nr_running;
+	unsigned long busiest_group_capacity;
 
 	int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2416,14 +2417,12 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	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;
+	unsigned long avg_load_per_task = 0;
 
 	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;
 
@@ -2453,7 +2452,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 		sgs->sum_nr_running += rq->nr_running;
 		sgs->sum_weighted_load += weighted_cpuload(i);
 
-		sum_avg_load_per_task += cpu_avg_load_per_task(i);
 	}
 
 	/*
@@ -2473,7 +2471,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	/* Adjust by relative CPU power of the group */
 	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
-
 	/*
 	 * Consider the group unbalanced when the imbalance is larger
 	 * than the average weight of two tasks.
@@ -2483,8 +2480,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	 *      normalized nr_running number somewhere that negates
 	 *      the hierarchy?
 	 */
-	avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
-		group->cpu_power;
+	if (sgs->sum_nr_running)
+		avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
 	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
 		sgs->group_imb = 1;
@@ -2553,6 +2550,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			sds->max_load = sgs.avg_load;
 			sds->busiest = group;
 			sds->busiest_nr_running = sgs.sum_nr_running;
+			sds->busiest_group_capacity = sgs.group_capacity;
 			sds->busiest_load_per_task = sgs.sum_weighted_load;
 			sds->group_imb = sgs.group_imb;
 		}
@@ -2575,6 +2573,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 {
 	unsigned long tmp, pwr_now = 0, pwr_move = 0;
 	unsigned int imbn = 2;
+	unsigned long scaled_busy_load_per_task;
 
 	if (sds->this_nr_running) {
 		sds->this_load_per_task /= sds->this_nr_running;
@@ -2585,8 +2584,12 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 		sds->this_load_per_task =
 			cpu_avg_load_per_task(this_cpu);
 
-	if (sds->max_load - sds->this_load + sds->busiest_load_per_task >=
-			sds->busiest_load_per_task * imbn) {
+	scaled_busy_load_per_task = sds->busiest_load_per_task
+						 * SCHED_LOAD_SCALE;
+	scaled_busy_load_per_task /= sds->busiest->cpu_power;
+
+	if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
+			(scaled_busy_load_per_task * imbn)) {
 		*imbalance = sds->busiest_load_per_task;
 		return;
 	}
@@ -2637,7 +2640,14 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 		unsigned long *imbalance)
 {
-	unsigned long max_pull;
+	unsigned long max_pull, load_above_capacity = ~0UL;
+
+	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);
+	}
+
 	/*
 	 * 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
@@ -2648,9 +2658,29 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 		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(sds->max_load - sds->avg_load,
-			sds->max_load - sds->busiest_load_per_task);
+	if (!sds->group_imb) {
+		/*
+		 * Don't want to pull so many tasks that a group would go idle.
+		 */
+		load_above_capacity = (sds->busiest_nr_running -
+						sds->busiest_group_capacity);
+
+		load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_LOAD_SCALE);
+
+		load_above_capacity /= sds->busiest->cpu_power;
+	}
+
+	/*
+	 * 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. At the same time,
+	 * we also don't want to reduce the group load below the group capacity
+	 * (so that we can implement power-savings policies etc). Thus we look
+	 * for the minimum possible imbalance.
+	 * Be careful of negative numbers as they'll appear as very large values
+	 * with unsigned longs.
+	 */
+	max_pull = min(sds->max_load - sds->avg_load, load_above_capacity);
 
 	/* How much load to actually move to equalise the imbalance */
 	*imbalance = min(max_pull * sds->busiest->cpu_power,
@@ -2718,7 +2748,6 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	 * 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))
 		goto ret;
@@ -2737,25 +2766,6 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	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;