X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fsched_fair.c;h=08ae848b71d4643429f67ef312a7bfd78a32aa0a;hb=1b7558e457ed0de61023cfc913d2c342c7c3d9f2;hp=e2a530515619ee8f3b42b1ca246cd18ae05f5544;hpb=bed04a4413376265746053be2a9cfbfc80c98ec9;p=linux-2.6

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index e2a5305156..08ae848b71 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -61,16 +61,6 @@ const_debug unsigned int sysctl_sched_child_runs_first = 1;
  */
 unsigned int __read_mostly sysctl_sched_compat_yield;
 
-/*
- * SCHED_BATCH wake-up granularity.
- * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
- *
- * This option delays the preemption effects of decoupled workloads
- * and reduces their over-scheduling. Synchronous workloads will still
- * have immediate wakeup/sleep latencies.
- */
-unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL;
-
 /*
  * SCHED_OTHER wake-up granularity.
  * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
@@ -87,6 +77,11 @@ const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
  * CFS operations on generic schedulable entities:
  */
 
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+	return container_of(se, struct task_struct, se);
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 /* cpu runqueue to which this cfs_rq is attached */
@@ -98,6 +93,54 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 /* An entity is a task if it doesn't "own" a runqueue */
 #define entity_is_task(se)	(!se->my_q)
 
+/* Walk up scheduling entities hierarchy */
+#define for_each_sched_entity(se) \
+		for (; se; se = se->parent)
+
+static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
+{
+	return p->se.cfs_rq;
+}
+
+/* runqueue on which this entity is (to be) queued */
+static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
+{
+	return se->cfs_rq;
+}
+
+/* runqueue "owned" by this group */
+static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
+{
+	return grp->my_q;
+}
+
+/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
+ * another cpu ('this_cpu')
+ */
+static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
+{
+	return cfs_rq->tg->cfs_rq[this_cpu];
+}
+
+/* Iterate thr' all leaf cfs_rq's on a runqueue */
+#define for_each_leaf_cfs_rq(rq, cfs_rq) \
+	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
+
+/* Do the two (enqueued) entities belong to the same group ? */
+static inline int
+is_same_group(struct sched_entity *se, struct sched_entity *pse)
+{
+	if (se->cfs_rq == pse->cfs_rq)
+		return 1;
+
+	return 0;
+}
+
+static inline struct sched_entity *parent_entity(struct sched_entity *se)
+{
+	return se->parent;
+}
+
 #else	/* CONFIG_FAIR_GROUP_SCHED */
 
 static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
@@ -107,13 +150,49 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 
 #define entity_is_task(se)	1
 
-#endif	/* CONFIG_FAIR_GROUP_SCHED */
+#define for_each_sched_entity(se) \
+		for (; se; se = NULL)
 
-static inline struct task_struct *task_of(struct sched_entity *se)
+static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
 {
-	return container_of(se, struct task_struct, se);
+	return &task_rq(p)->cfs;
 }
 
+static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
+{
+	struct task_struct *p = task_of(se);
+	struct rq *rq = task_rq(p);
+
+	return &rq->cfs;
+}
+
+/* runqueue "owned" by this group */
+static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
+{
+	return NULL;
+}
+
+static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
+{
+	return &cpu_rq(this_cpu)->cfs;
+}
+
+#define for_each_leaf_cfs_rq(rq, cfs_rq) \
+		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
+
+static inline int
+is_same_group(struct sched_entity *se, struct sched_entity *pse)
+{
+	return 1;
+}
+
+static inline struct sched_entity *parent_entity(struct sched_entity *se)
+{
+	return NULL;
+}
+
+#endif	/* CONFIG_FAIR_GROUP_SCHED */
+
 
 /**************************************************************
  * Scheduling class tree data structure manipulation methods:
@@ -175,8 +254,15 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * Maintain a cache of leftmost tree entries (it is frequently
 	 * used):
 	 */
-	if (leftmost)
+	if (leftmost) {
 		cfs_rq->rb_leftmost = &se->run_node;
+		/*
+		 * maintain cfs_rq->min_vruntime to be a monotonic increasing
+		 * value tracking the leftmost vruntime in the tree.
+		 */
+		cfs_rq->min_vruntime =
+			max_vruntime(cfs_rq->min_vruntime, se->vruntime);
+	}
 
 	rb_link_node(&se->run_node, parent, link);
 	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
@@ -184,8 +270,24 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	if (cfs_rq->rb_leftmost == &se->run_node)
-		cfs_rq->rb_leftmost = rb_next(&se->run_node);
+	if (cfs_rq->rb_leftmost == &se->run_node) {
+		struct rb_node *next_node;
+		struct sched_entity *next;
+
+		next_node = rb_next(&se->run_node);
+		cfs_rq->rb_leftmost = next_node;
+
+		if (next_node) {
+			next = rb_entry(next_node,
+					struct sched_entity, run_node);
+			cfs_rq->min_vruntime =
+				max_vruntime(cfs_rq->min_vruntime,
+					     next->vruntime);
+		}
+	}
+
+	if (cfs_rq->next == se)
+		cfs_rq->next = NULL;
 
 	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
 }
@@ -262,36 +364,45 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	u64 slice = __sched_period(cfs_rq->nr_running);
 
-	slice *= se->load.weight;
-	do_div(slice, cfs_rq->load.weight);
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		slice *= se->load.weight;
+		do_div(slice, cfs_rq->load.weight);
+	}
+
 
 	return slice;
 }
 
 /*
- * We calculate the vruntime slice.
+ * We calculate the vruntime slice of a to be inserted task
  *
  * vs = s/w = p/rw
  */
-static u64 __sched_vslice(unsigned long rq_weight, unsigned long nr_running)
+static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 vslice = __sched_period(nr_running);
+	unsigned long nr_running = cfs_rq->nr_running;
+	unsigned long weight;
+	u64 vslice;
 
-	vslice *= NICE_0_LOAD;
-	do_div(vslice, rq_weight);
+	if (!se->on_rq)
+		nr_running++;
 
-	return vslice;
-}
+	vslice = __sched_period(nr_running);
 
-static u64 sched_vslice(struct cfs_rq *cfs_rq)
-{
-	return __sched_vslice(cfs_rq->load.weight, cfs_rq->nr_running);
-}
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
 
-static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	return __sched_vslice(cfs_rq->load.weight + se->load.weight,
-			cfs_rq->nr_running + 1);
+		weight = cfs_rq->load.weight;
+		if (!se->on_rq)
+			weight += se->load.weight;
+
+		vslice *= NICE_0_LOAD;
+		do_div(vslice, weight);
+	}
+
+	return vslice;
 }
 
 /*
@@ -303,7 +414,6 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 	      unsigned long delta_exec)
 {
 	unsigned long delta_exec_weighted;
-	u64 vruntime;
 
 	schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
 
@@ -315,19 +425,6 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 							&curr->load);
 	}
 	curr->vruntime += delta_exec_weighted;
-
-	/*
-	 * maintain cfs_rq->min_vruntime to be a monotonic increasing
-	 * value tracking the leftmost vruntime in the tree.
-	 */
-	if (first_fair(cfs_rq)) {
-		vruntime = min_vruntime(curr->vruntime,
-				__pick_next_entity(cfs_rq)->vruntime);
-	} else
-		vruntime = curr->vruntime;
-
-	cfs_rq->min_vruntime =
-		max_vruntime(cfs_rq->min_vruntime, vruntime);
 }
 
 static void update_curr(struct cfs_rq *cfs_rq)
@@ -419,6 +516,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	update_load_add(&cfs_rq->load, se->load.weight);
 	cfs_rq->nr_running++;
 	se->on_rq = 1;
+	list_add(&se->group_node, &cfs_rq->tasks);
 }
 
 static void
@@ -427,6 +525,7 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	update_load_sub(&cfs_rq->load, se->load.weight);
 	cfs_rq->nr_running--;
 	se->on_rq = 0;
+	list_del_init(&se->group_node);
 }
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -493,16 +592,11 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
 	u64 vruntime;
 
-	vruntime = cfs_rq->min_vruntime;
-
-	if (sched_feat(TREE_AVG)) {
-		struct sched_entity *last = __pick_last_entity(cfs_rq);
-		if (last) {
-			vruntime += last->vruntime;
-			vruntime >>= 1;
-		}
-	} else if (sched_feat(APPROX_AVG) && cfs_rq->nr_running)
-		vruntime += sched_vslice(cfs_rq)/2;
+	if (first_fair(cfs_rq)) {
+		vruntime = min_vruntime(cfs_rq->min_vruntime,
+				__pick_next_entity(cfs_rq)->vruntime);
+	} else
+		vruntime = cfs_rq->min_vruntime;
 
 	/*
 	 * The 'current' period is already promised to the current tasks,
@@ -532,6 +626,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
+	account_entity_enqueue(cfs_rq, se);
 
 	if (wakeup) {
 		place_entity(cfs_rq, se, 0);
@@ -542,7 +637,21 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 	check_spread(cfs_rq, se);
 	if (se != cfs_rq->curr)
 		__enqueue_entity(cfs_rq, se);
-	account_entity_enqueue(cfs_rq, se);
+}
+
+static void update_avg(u64 *avg, u64 sample)
+{
+	s64 diff = sample - *avg;
+	*avg += diff >> 3;
+}
+
+static void update_avg_stats(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	if (!se->last_wakeup)
+		return;
+
+	update_avg(&se->avg_overlap, se->sum_exec_runtime - se->last_wakeup);
+	se->last_wakeup = 0;
 }
 
 static void
@@ -555,6 +664,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 
 	update_stats_dequeue(cfs_rq, se);
 	if (sleep) {
+		update_avg_stats(cfs_rq, se);
 #ifdef CONFIG_SCHEDSTATS
 		if (entity_is_task(se)) {
 			struct task_struct *tsk = task_of(se);
@@ -616,12 +726,28 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
+
+static struct sched_entity *
+pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	if (!cfs_rq->next)
+		return se;
+
+	if (wakeup_preempt_entity(cfs_rq->next, se) != 0)
+		return se;
+
+	return cfs_rq->next;
+}
+
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *se = NULL;
 
 	if (first_fair(cfs_rq)) {
 		se = __pick_next_entity(cfs_rq);
+		se = pick_next(cfs_rq, se);
 		set_next_entity(cfs_rq, se);
 	}
 
@@ -659,8 +785,10 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	 * queued ticks are scheduled to match the slice, so don't bother
 	 * validating it and just reschedule.
 	 */
-	if (queued)
-		return resched_task(rq_of(cfs_rq)->curr);
+	if (queued) {
+		resched_task(rq_of(cfs_rq)->curr);
+		return;
+	}
 	/*
 	 * don't let the period tick interfere with the hrtick preemption
 	 */
@@ -677,101 +805,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
  * CFS operations on tasks:
  */
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-
-/* Walk up scheduling entities hierarchy */
-#define for_each_sched_entity(se) \
-		for (; se; se = se->parent)
-
-static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
-{
-	return p->se.cfs_rq;
-}
-
-/* runqueue on which this entity is (to be) queued */
-static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
-{
-	return se->cfs_rq;
-}
-
-/* runqueue "owned" by this group */
-static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
-{
-	return grp->my_q;
-}
-
-/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
- * another cpu ('this_cpu')
- */
-static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
-{
-	return cfs_rq->tg->cfs_rq[this_cpu];
-}
-
-/* Iterate thr' all leaf cfs_rq's on a runqueue */
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
-
-/* Do the two (enqueued) entities belong to the same group ? */
-static inline int
-is_same_group(struct sched_entity *se, struct sched_entity *pse)
-{
-	if (se->cfs_rq == pse->cfs_rq)
-		return 1;
-
-	return 0;
-}
-
-static inline struct sched_entity *parent_entity(struct sched_entity *se)
-{
-	return se->parent;
-}
-
-#else	/* CONFIG_FAIR_GROUP_SCHED */
-
-#define for_each_sched_entity(se) \
-		for (; se; se = NULL)
-
-static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
-{
-	return &task_rq(p)->cfs;
-}
-
-static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
-{
-	struct task_struct *p = task_of(se);
-	struct rq *rq = task_rq(p);
-
-	return &rq->cfs;
-}
-
-/* runqueue "owned" by this group */
-static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
-{
-	return NULL;
-}
-
-static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
-{
-	return &cpu_rq(this_cpu)->cfs;
-}
-
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
-
-static inline int
-is_same_group(struct sched_entity *se, struct sched_entity *pse)
-{
-	return 1;
-}
-
-static inline struct sched_entity *parent_entity(struct sched_entity *se)
-{
-	return NULL;
-}
-
-#endif	/* CONFIG_FAIR_GROUP_SCHED */
-
 #ifdef CONFIG_SCHED_HRTICK
 static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
@@ -870,7 +903,7 @@ static void yield_task_fair(struct rq *rq)
 		return;
 
 	if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
-		__update_rq_clock(rq);
+		update_rq_clock(rq);
 		/*
 		 * Update run-time statistics of the 'current'.
 		 */
@@ -885,7 +918,7 @@ static void yield_task_fair(struct rq *rq)
 	/*
 	 * Already in the rightmost position?
 	 */
-	if (unlikely(rightmost->vruntime < se->vruntime))
+	if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
 		return;
 
 	/*
@@ -920,11 +953,13 @@ static int wake_idle(int cpu, struct task_struct *p)
 	 * sibling runqueue info. This will avoid the checks and cache miss
 	 * penalities associated with that.
 	 */
-	if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
+	if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1)
 		return cpu;
 
 	for_each_domain(cpu, sd) {
-		if (sd->flags & SD_WAKE_IDLE) {
+		if ((sd->flags & SD_WAKE_IDLE)
+		    || ((sd->flags & SD_WAKE_IDLE_FAR)
+			&& !task_hot(p, task_rq(p)->clock, sd))) {
 			cpus_and(tmp, sd->span, p->cpus_allowed);
 			for_each_cpu_mask(i, tmp) {
 				if (idle_cpu(i)) {
@@ -949,100 +984,181 @@ static inline int wake_idle(int cpu, struct task_struct *p)
 #endif
 
 #ifdef CONFIG_SMP
-static int select_task_rq_fair(struct task_struct *p, int sync)
+
+static const struct sched_class fair_sched_class;
+
+static int
+wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
+	    struct task_struct *p, int prev_cpu, int this_cpu, int sync,
+	    int idx, unsigned long load, unsigned long this_load,
+	    unsigned int imbalance)
 {
-	int cpu, this_cpu;
-	struct rq *rq;
-	struct sched_domain *sd, *this_sd = NULL;
-	int new_cpu;
+	struct task_struct *curr = this_rq->curr;
+	unsigned long tl = this_load;
+	unsigned long tl_per_task;
+	int balanced;
 
-	cpu      = task_cpu(p);
-	rq       = task_rq(p);
-	this_cpu = smp_processor_id();
-	new_cpu  = cpu;
+	if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
+		return 0;
 
-	if (cpu == this_cpu)
-		goto out_set_cpu;
+	/*
+	 * If sync wakeup then subtract the (maximum possible)
+	 * effect of the currently running task from the load
+	 * of the current CPU:
+	 */
+	if (sync)
+		tl -= current->se.load.weight;
+
+	balanced = 100*(tl + p->se.load.weight) <= imbalance*load;
 
+	/*
+	 * If the currently running task will sleep within
+	 * a reasonable amount of time then attract this newly
+	 * woken task:
+	 */
+	if (sync && balanced && curr->sched_class == &fair_sched_class) {
+		if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
+				p->se.avg_overlap < sysctl_sched_migration_cost)
+			return 1;
+	}
+
+	schedstat_inc(p, se.nr_wakeups_affine_attempts);
+	tl_per_task = cpu_avg_load_per_task(this_cpu);
+
+	if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
+			balanced) {
+		/*
+		 * This domain has SD_WAKE_AFFINE and
+		 * p is cache cold in this domain, and
+		 * there is no bad imbalance.
+		 */
+		schedstat_inc(this_sd, ttwu_move_affine);
+		schedstat_inc(p, se.nr_wakeups_affine);
+
+		return 1;
+	}
+	return 0;
+}
+
+static int select_task_rq_fair(struct task_struct *p, int sync)
+{
+	struct sched_domain *sd, *this_sd = NULL;
+	int prev_cpu, this_cpu, new_cpu;
+	unsigned long load, this_load;
+	struct rq *rq, *this_rq;
+	unsigned int imbalance;
+	int idx;
+
+	prev_cpu	= task_cpu(p);
+	rq		= task_rq(p);
+	this_cpu	= smp_processor_id();
+	this_rq		= cpu_rq(this_cpu);
+	new_cpu		= prev_cpu;
+
+	/*
+	 * 'this_sd' is the first domain that both
+	 * this_cpu and prev_cpu are present in:
+	 */
 	for_each_domain(this_cpu, sd) {
-		if (cpu_isset(cpu, sd->span)) {
+		if (cpu_isset(prev_cpu, sd->span)) {
 			this_sd = sd;
 			break;
 		}
 	}
 
 	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
-		goto out_set_cpu;
+		goto out;
 
 	/*
 	 * Check for affine wakeup and passive balancing possibilities.
 	 */
-	if (this_sd) {
-		int idx = this_sd->wake_idx;
-		unsigned int imbalance;
-		unsigned long load, this_load;
-
-		imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
-
-		load = source_load(cpu, idx);
-		this_load = target_load(this_cpu, idx);
-
-		new_cpu = this_cpu; /* Wake to this CPU if we can */
-
-		if (this_sd->flags & SD_WAKE_AFFINE) {
-			unsigned long tl = this_load;
-			unsigned long tl_per_task;
-
-			/*
-			 * Attract cache-cold tasks on sync wakeups:
-			 */
-			if (sync && !task_hot(p, rq->clock, this_sd))
-				goto out_set_cpu;
-
-			schedstat_inc(p, se.nr_wakeups_affine_attempts);
-			tl_per_task = cpu_avg_load_per_task(this_cpu);
-
-			/*
-			 * If sync wakeup then subtract the (maximum possible)
-			 * effect of the currently running task from the load
-			 * of the current CPU:
-			 */
-			if (sync)
-				tl -= current->se.load.weight;
-
-			if ((tl <= load &&
-				tl + target_load(cpu, idx) <= tl_per_task) ||
-			       100*(tl + p->se.load.weight) <= imbalance*load) {
-				/*
-				 * This domain has SD_WAKE_AFFINE and
-				 * p is cache cold in this domain, and
-				 * there is no bad imbalance.
-				 */
-				schedstat_inc(this_sd, ttwu_move_affine);
-				schedstat_inc(p, se.nr_wakeups_affine);
-				goto out_set_cpu;
-			}
-		}
+	if (!this_sd)
+		goto out;
 
-		/*
-		 * Start passive balancing when half the imbalance_pct
-		 * limit is reached.
-		 */
-		if (this_sd->flags & SD_WAKE_BALANCE) {
-			if (imbalance*this_load <= 100*load) {
-				schedstat_inc(this_sd, ttwu_move_balance);
-				schedstat_inc(p, se.nr_wakeups_passive);
-				goto out_set_cpu;
-			}
+	idx = this_sd->wake_idx;
+
+	imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+
+	load = source_load(prev_cpu, idx);
+	this_load = target_load(this_cpu, idx);
+
+	if (wake_affine(rq, this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
+				     load, this_load, imbalance))
+		return this_cpu;
+
+	if (prev_cpu == this_cpu)
+		goto out;
+
+	/*
+	 * Start passive balancing when half the imbalance_pct
+	 * limit is reached.
+	 */
+	if (this_sd->flags & SD_WAKE_BALANCE) {
+		if (imbalance*this_load <= 100*load) {
+			schedstat_inc(this_sd, ttwu_move_balance);
+			schedstat_inc(p, se.nr_wakeups_passive);
+			return this_cpu;
 		}
 	}
 
-	new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
-out_set_cpu:
+out:
 	return wake_idle(new_cpu, p);
 }
 #endif /* CONFIG_SMP */
 
+static unsigned long wakeup_gran(struct sched_entity *se)
+{
+	unsigned long gran = sysctl_sched_wakeup_granularity;
+
+	/*
+	 * More easily preempt - nice tasks, while not making
+	 * it harder for + nice tasks.
+	 */
+	if (unlikely(se->load.weight > NICE_0_LOAD))
+		gran = calc_delta_fair(gran, &se->load);
+
+	return gran;
+}
+
+/*
+ * Should 'se' preempt 'curr'.
+ *
+ *             |s1
+ *        |s2
+ *   |s3
+ *         g
+ *      |<--->|c
+ *
+ *  w(c, s1) = -1
+ *  w(c, s2) =  0
+ *  w(c, s3) =  1
+ *
+ */
+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
+{
+	s64 gran, vdiff = curr->vruntime - se->vruntime;
+
+	if (vdiff < 0)
+		return -1;
+
+	gran = wakeup_gran(curr);
+	if (vdiff > gran)
+		return 1;
+
+	return 0;
+}
+
+/* return depth at which a sched entity is present in the hierarchy */
+static inline int depth_se(struct sched_entity *se)
+{
+	int depth = 0;
+
+	for_each_sched_entity(se)
+		depth++;
+
+	return depth;
+}
 
 /*
  * Preempt the current task with a newly woken task if needed:
@@ -1052,7 +1168,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 	struct task_struct *curr = rq->curr;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	struct sched_entity *se = &curr->se, *pse = &p->se;
-	unsigned long gran;
+	int se_depth, pse_depth;
 
 	if (unlikely(rt_prio(p->prio))) {
 		update_rq_clock(rq);
@@ -1060,6 +1176,13 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 		resched_task(curr);
 		return;
 	}
+
+	se->last_wakeup = se->sum_exec_runtime;
+	if (unlikely(se == pse))
+		return;
+
+	cfs_rq_of(pse)->next = pse;
+
 	/*
 	 * Batch tasks do not preempt (their preemption is driven by
 	 * the tick):
@@ -1070,20 +1193,33 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
 
-	while (!is_same_group(se, pse)) {
+	/*
+	 * preemption test can be made between sibling entities who are in the
+	 * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
+	 * both tasks until we find their ancestors who are siblings of common
+	 * parent.
+	 */
+
+	/* First walk up until both entities are at same depth */
+	se_depth = depth_se(se);
+	pse_depth = depth_se(pse);
+
+	while (se_depth > pse_depth) {
+		se_depth--;
 		se = parent_entity(se);
+	}
+
+	while (pse_depth > se_depth) {
+		pse_depth--;
 		pse = parent_entity(pse);
 	}
 
-	gran = sysctl_sched_wakeup_granularity;
-	/*
-	 * More easily preempt - nice tasks, while not making
-	 * it harder for + nice tasks.
-	 */
-	if (unlikely(se->load.weight > NICE_0_LOAD))
-		gran = calc_delta_fair(gran, &se->load);
+	while (!is_same_group(se, pse)) {
+		se = parent_entity(se);
+		pse = parent_entity(pse);
+	}
 
-	if (pse->vruntime + gran < se->vruntime)
+	if (wakeup_preempt_entity(se, pse) == 1)
 		resched_task(curr);
 }
 
@@ -1134,15 +1270,27 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
  * the current task:
  */
 static struct task_struct *
-__load_balance_iterator(struct cfs_rq *cfs_rq, struct rb_node *curr)
+__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
 {
-	struct task_struct *p;
+	struct task_struct *p = NULL;
+	struct sched_entity *se;
 
-	if (!curr)
+	if (next == &cfs_rq->tasks)
 		return NULL;
 
-	p = rb_entry(curr, struct task_struct, se.run_node);
-	cfs_rq->rb_load_balance_curr = rb_next(curr);
+	/* Skip over entities that are not tasks */
+	do {
+		se = list_entry(next, struct sched_entity, group_node);
+		next = next->next;
+	} while (next != &cfs_rq->tasks && !entity_is_task(se));
+
+	if (next == &cfs_rq->tasks)
+		return NULL;
+
+	cfs_rq->balance_iterator = next;
+
+	if (entity_is_task(se))
+		p = task_of(se);
 
 	return p;
 }
@@ -1151,14 +1299,14 @@ static struct task_struct *load_balance_start_fair(void *arg)
 {
 	struct cfs_rq *cfs_rq = arg;
 
-	return __load_balance_iterator(cfs_rq, first_fair(cfs_rq));
+	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->rb_load_balance_curr);
+	return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1402,9 +1550,6 @@ static void print_cfs_stats(struct seq_file *m, int cpu)
 {
 	struct cfs_rq *cfs_rq;
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	print_cfs_rq(m, cpu, &cpu_rq(cpu)->cfs);
-#endif
 	rcu_read_lock();
 	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
 		print_cfs_rq(m, cpu, cfs_rq);