1 files changed, 275 insertions, 219 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 08ae848..18fd171 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -63,13 +63,13 @@ unsigned int __read_mostly sysctl_sched_compat_yield;
 
 /*
  * SCHED_OTHER wake-up granularity.
- * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 5 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_wakeup_granularity = 10000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
@@ -334,6 +334,34 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
 #endif
 
 /*
+ * delta *= w / rw
+ */
+static inline unsigned long
+calc_delta_weight(unsigned long delta, struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		delta = calc_delta_mine(delta,
+				se->load.weight, &cfs_rq_of(se)->load);
+	}
+
+	return delta;
+}
+
+/*
+ * delta *= rw / w
+ */
+static inline unsigned long
+calc_delta_fair(unsigned long delta, struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		delta = calc_delta_mine(delta,
+				cfs_rq_of(se)->load.weight, &se->load);
+	}
+
+	return delta;
+}
+
+/*
  * The idea is to set a period in which each task runs once.
  *
  * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch
@@ -362,47 +390,22 @@ static u64 __sched_period(unsigned long nr_running)
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 slice = __sched_period(cfs_rq->nr_running);
-
-	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
-
-		slice *= se->load.weight;
-		do_div(slice, cfs_rq->load.weight);
-	}
-
-
-	return slice;
+	return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
 }
 
 /*
  * We calculate the vruntime slice of a to be inserted task
  *
- * vs = s/w = p/rw
+ * vs = s*rw/w = p
  */
 static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	unsigned long nr_running = cfs_rq->nr_running;
-	unsigned long weight;
-	u64 vslice;
 
 	if (!se->on_rq)
 		nr_running++;
 
-	vslice = __sched_period(nr_running);
-
-	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
-
-		weight = cfs_rq->load.weight;
-		if (!se->on_rq)
-			weight += se->load.weight;
-
-		vslice *= NICE_0_LOAD;
-		do_div(vslice, weight);
-	}
-
-	return vslice;
+	return __sched_period(nr_running);
 }
 
 /*
@@ -419,11 +422,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 
 	curr->sum_exec_runtime += delta_exec;
 	schedstat_add(cfs_rq, exec_clock, delta_exec);
-	delta_exec_weighted = delta_exec;
-	if (unlikely(curr->load.weight != NICE_0_LOAD)) {
-		delta_exec_weighted = calc_delta_fair(delta_exec_weighted,
-							&curr->load);
-	}
+	delta_exec_weighted = calc_delta_fair(delta_exec, curr);
 	curr->vruntime += delta_exec_weighted;
 }
 
@@ -510,22 +509,45 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
+#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
+static void
+add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
+{
+	cfs_rq->task_weight += weight;
+}
+#else
+static inline void
+add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
+{
+}
+#endif
+
 static void
 account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_add(&cfs_rq->load, se->load.weight);
+	if (!parent_entity(se))
+		inc_cpu_load(rq_of(cfs_rq), se->load.weight);
+	if (entity_is_task(se)) {
+		add_cfs_task_weight(cfs_rq, se->load.weight);
+		list_add(&se->group_node, &cfs_rq->tasks);
+	}
 	cfs_rq->nr_running++;
 	se->on_rq = 1;
-	list_add(&se->group_node, &cfs_rq->tasks);
 }
 
 static void
 account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_sub(&cfs_rq->load, se->load.weight);
+	if (!parent_entity(se))
+		dec_cpu_load(rq_of(cfs_rq), se->load.weight);
+	if (entity_is_task(se)) {
+		add_cfs_task_weight(cfs_rq, -se->load.weight);
+		list_del_init(&se->group_node);
+	}
 	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)
@@ -609,8 +631,17 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 	if (!initial) {
 		/* sleeps upto a single latency don't count. */
-		if (sched_feat(NEW_FAIR_SLEEPERS))
-			vruntime -= sysctl_sched_latency;
+		if (sched_feat(NEW_FAIR_SLEEPERS)) {
+			unsigned long thresh = sysctl_sched_latency;
+
+			/*
+			 * convert the sleeper threshold into virtual time
+			 */
+			if (sched_feat(NORMALIZED_SLEEPER))
+				thresh = calc_delta_fair(thresh, se);
+
+			vruntime -= thresh;
+		}
 
 		/* ensure we never gain time by being placed backwards. */
 		vruntime = max_vruntime(se->vruntime, vruntime);
@@ -639,21 +670,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 		__enqueue_entity(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
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -664,7 +680,6 @@ 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);
@@ -726,17 +741,16 @@ 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;
+	struct rq *rq = rq_of(cfs_rq);
+	u64 pair_slice = rq->clock - cfs_rq->pair_start;
 
-	if (wakeup_preempt_entity(cfs_rq->next, se) != 0)
+	if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) {
+		cfs_rq->pair_start = rq->clock;
 		return se;
+	}
 
 	return cfs_rq->next;
 }
@@ -808,7 +822,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 #ifdef CONFIG_SCHED_HRTICK
 static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
-	int requeue = rq->curr == p;
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
@@ -829,13 +842,13 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 		 * Don't schedule slices shorter than 10000ns, that just
 		 * doesn't make sense. Rely on vruntime for fairness.
 		 */
-		if (!requeue)
-			delta = max(10000LL, delta);
+		if (rq->curr != p)
+			delta = max_t(s64, 10000LL, delta);
 
-		hrtick_start(rq, delta, requeue);
+		hrtick_start(rq, delta);
 	}
 }
-#else
+#else /* !CONFIG_SCHED_HRTICK */
 static inline void
 hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
@@ -934,6 +947,8 @@ static void yield_task_fair(struct rq *rq)
  * not idle and an idle cpu is available.  The span of cpus to
  * search starts with cpus closest then further out as needed,
  * so we always favor a closer, idle cpu.
+ * Domains may include CPUs that are not usable for migration,
+ * hence we need to mask them out (cpu_active_map)
  *
  * Returns the CPU we should wake onto.
  */
@@ -961,7 +976,8 @@ static int wake_idle(int cpu, struct task_struct *p)
 		    || ((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) {
+			cpus_and(tmp, tmp, cpu_active_map);
+			for_each_cpu_mask_nr(i, tmp) {
 				if (idle_cpu(i)) {
 					if (i != task_cpu(p)) {
 						schedstat_inc(p,
@@ -976,7 +992,7 @@ static int wake_idle(int cpu, struct task_struct *p)
 	}
 	return cpu;
 }
-#else
+#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
 static inline int wake_idle(int cpu, struct task_struct *p)
 {
 	return cpu;
@@ -987,46 +1003,143 @@ static inline int wake_idle(int cpu, struct task_struct *p)
 
 static const struct sched_class fair_sched_class;
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * effective_load() calculates the load change as seen from the root_task_group
+ *
+ * Adding load to a group doesn't make a group heavier, but can cause movement
+ * of group shares between cpus. Assuming the shares were perfectly aligned one
+ * can calculate the shift in shares.
+ *
+ * The problem is that perfectly aligning the shares is rather expensive, hence
+ * we try to avoid doing that too often - see update_shares(), which ratelimits
+ * this change.
+ *
+ * We compensate this by not only taking the current delta into account, but
+ * also considering the delta between when the shares were last adjusted and
+ * now.
+ *
+ * We still saw a performance dip, some tracing learned us that between
+ * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
+ * significantly. Therefore try to bias the error in direction of failing
+ * the affine wakeup.
+ *
+ */
+static long effective_load(struct task_group *tg, int cpu,
+		long wl, long wg)
+{
+	struct sched_entity *se = tg->se[cpu];
+
+	if (!tg->parent)
+		return wl;
+
+	/*
+	 * By not taking the decrease of shares on the other cpu into
+	 * account our error leans towards reducing the affine wakeups.
+	 */
+	if (!wl && sched_feat(ASYM_EFF_LOAD))
+		return wl;
+
+	for_each_sched_entity(se) {
+		long S, rw, s, a, b;
+		long more_w;
+
+		/*
+		 * Instead of using this increment, also add the difference
+		 * between when the shares were last updated and now.
+		 */
+		more_w = se->my_q->load.weight - se->my_q->rq_weight;
+		wl += more_w;
+		wg += more_w;
+
+		S = se->my_q->tg->shares;
+		s = se->my_q->shares;
+		rw = se->my_q->rq_weight;
+
+		a = S*(rw + wl);
+		b = S*rw + s*wg;
+
+		wl = s*(a-b);
+
+		if (likely(b))
+			wl /= b;
+
+		/*
+		 * Assume the group is already running and will
+		 * thus already be accounted for in the weight.
+		 *
+		 * That is, moving shares between CPUs, does not
+		 * alter the group weight.
+		 */
+		wg = 0;
+	}
+
+	return wl;
+}
+
+#else
+
+static inline unsigned long effective_load(struct task_group *tg, int cpu,
+		unsigned long wl, unsigned long wg)
+{
+	return wl;
+}
+
+#endif
+
 static int
-wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
+wake_affine(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)
 {
 	struct task_struct *curr = this_rq->curr;
+	struct task_group *tg;
 	unsigned long tl = this_load;
 	unsigned long tl_per_task;
+	unsigned long weight;
 	int balanced;
 
 	if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
 		return 0;
 
+	if (!sync && sched_feat(SYNC_WAKEUPS) &&
+	    curr->se.avg_overlap < sysctl_sched_migration_cost &&
+	    p->se.avg_overlap < sysctl_sched_migration_cost)
+		sync = 1;
+
 	/*
 	 * 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 (sync) {
+		tg = task_group(current);
+		weight = current->se.load.weight;
+
+		tl += effective_load(tg, this_cpu, -weight, -weight);
+		load += effective_load(tg, prev_cpu, 0, -weight);
+	}
+
+	tg = task_group(p);
+	weight = p->se.load.weight;
 
-	balanced = 100*(tl + p->se.load.weight) <= imbalance*load;
+	balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
+		imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
 
 	/*
 	 * 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;
-	}
+	if (sync && balanced)
+		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) {
+	if (balanced || (tl <= load && tl + target_load(prev_cpu, idx) <=
+			tl_per_task)) {
 		/*
 		 * This domain has SD_WAKE_AFFINE and
 		 * p is cache cold in this domain, and
@@ -1045,16 +1158,17 @@ 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;
+	struct 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;
 
+	if (prev_cpu == this_cpu)
+		goto out;
 	/*
 	 * 'this_sd' is the first domain that both
 	 * this_cpu and prev_cpu are present in:
@@ -1082,13 +1196,10 @@ static int select_task_rq_fair(struct task_struct *p, int sync)
 	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,
+	if (wake_affine(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.
@@ -1111,64 +1222,24 @@ 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.
+	 * 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);
+	if (sched_feat(ASYM_GRAN))
+		gran = calc_delta_mine(gran, NICE_0_LOAD, &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:
  */
-static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
+static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 {
 	struct task_struct *curr = rq->curr;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	struct sched_entity *se = &curr->se, *pse = &p->se;
-	int se_depth, pse_depth;
+	s64 delta_exec;
 
 	if (unlikely(rt_prio(p->prio))) {
 		update_rq_clock(rq);
@@ -1177,13 +1248,19 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 		return;
 	}
 
-	se->last_wakeup = se->sum_exec_runtime;
 	if (unlikely(se == pse))
 		return;
 
 	cfs_rq_of(pse)->next = pse;
 
 	/*
+	 * We can come here with TIF_NEED_RESCHED already set from new task
+	 * wake up path.
+	 */
+	if (test_tsk_need_resched(curr))
+		return;
+
+	/*
 	 * Batch tasks do not preempt (their preemption is driven by
 	 * the tick):
 	 */
@@ -1193,33 +1270,15 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
 
-	/*
-	 * 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);
-	}
-
-	while (!is_same_group(se, pse)) {
-		se = parent_entity(se);
-		pse = parent_entity(pse);
+	if (sched_feat(WAKEUP_OVERLAP) && (sync ||
+			(se->avg_overlap < sysctl_sched_migration_cost &&
+			 pse->avg_overlap < sysctl_sched_migration_cost))) {
+		resched_task(curr);
+		return;
 	}
 
-	if (wakeup_preempt_entity(se, pse) == 1)
+	delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+	if (delta_exec > wakeup_gran(pse))
 		resched_task(curr);
 }
 
@@ -1278,19 +1337,9 @@ __load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
 	if (next == &cfs_rq->tasks)
 		return NULL;
 
-	/* 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);
+	se = list_entry(next, struct sched_entity, group_node);
+	p = task_of(se);
+	cfs_rq->balance_iterator = next->next;
 
 	return p;
 }
@@ -1309,75 +1358,82 @@ static struct task_struct *load_balance_next_fair(void *arg)
 	return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
 }
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static int cfs_rq_best_prio(struct cfs_rq *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 sched_entity *curr;
-	struct task_struct *p;
-
-	if (!cfs_rq->nr_running || !first_fair(cfs_rq))
-		return MAX_PRIO;
-
-	curr = cfs_rq->curr;
-	if (!curr)
-		curr = __pick_next_entity(cfs_rq);
+	struct rq_iterator cfs_rq_iterator;
 
-	p = task_of(curr);
+	cfs_rq_iterator.start = load_balance_start_fair;
+	cfs_rq_iterator.next = load_balance_next_fair;
+	cfs_rq_iterator.arg = cfs_rq;
 
-	return p->prio;
+	return balance_tasks(this_rq, this_cpu, busiest,
+			max_load_move, sd, idle, all_pinned,
+			this_best_prio, &cfs_rq_iterator);
 }
-#endif
 
+#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)
 {
-	struct cfs_rq *busy_cfs_rq;
 	long rem_load_move = max_load_move;
-	struct rq_iterator cfs_rq_iterator;
-
-	cfs_rq_iterator.start = load_balance_start_fair;
-	cfs_rq_iterator.next = load_balance_next_fair;
+	int busiest_cpu = cpu_of(busiest);
+	struct task_group *tg;
 
-	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
-#ifdef CONFIG_FAIR_GROUP_SCHED
-		struct cfs_rq *this_cfs_rq;
-		long imbalance;
-		unsigned long maxload;
+	rcu_read_lock();
+	update_h_load(busiest_cpu);
 
-		this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_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;
 
-		imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
-		/* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
-		if (imbalance <= 0)
+		/*
+		 * empty group
+		 */
+		if (!busiest_cfs_rq->task_weight)
 			continue;
 
-		/* Don't pull more than imbalance/2 */
-		imbalance /= 2;
-		maxload = min(rem_load_move, imbalance);
+		rem_load = (u64)rem_load_move * busiest_weight;
+		rem_load = div_u64(rem_load, busiest_h_load + 1);
 
-		*this_best_prio = cfs_rq_best_prio(this_cfs_rq);
-#else
-# define maxload rem_load_move
-#endif
-		/*
-		 * pass busy_cfs_rq argument into
-		 * load_balance_[start|next]_fair iterators
-		 */
-		cfs_rq_iterator.arg = busy_cfs_rq;
-		rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
-					       maxload, sd, idle, all_pinned,
-					       this_best_prio,
-					       &cfs_rq_iterator);
+		moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
+				rem_load, sd, idle, all_pinned, this_best_prio,
+				tg->cfs_rq[busiest_cpu]);
+
+		if (!moved_load)
+			continue;
+
+		moved_load *= busiest_h_load;
+		moved_load = div_u64(moved_load, busiest_weight + 1);
 
-		if (rem_load_move <= 0)
+		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 __load_balance_fair(this_rq, this_cpu, busiest,
+			max_load_move, sd, idle, all_pinned,
+			this_best_prio, &busiest->cfs);
+}
+#endif
 
 static int
 move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
@@ -1402,7 +1458,7 @@ move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 
 	return 0;
 }
-#endif
+#endif /* CONFIG_SMP */
 
 /*
  * scheduler tick hitting a task of our scheduling class:
@@ -1446,10 +1502,10 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
 		 * 'current' within the tree based on its new key value.
 		 */
 		swap(curr->vruntime, se->vruntime);
+		resched_task(rq->curr);
 	}
 
 	enqueue_task_fair(rq, p, 0);
-	resched_task(rq->curr);
 }
 
 /*
@@ -1468,7 +1524,7 @@ static void prio_changed_fair(struct rq *rq, struct task_struct *p,
 		if (p->prio > oldprio)
 			resched_task(rq->curr);
 	} else
-		check_preempt_curr(rq, p);
+		check_preempt_curr(rq, p, 0);
 }
 
 /*
@@ -1485,7 +1541,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p,
 	if (running)
 		resched_task(rq->curr);
 	else
-		check_preempt_curr(rq, p);
+		check_preempt_curr(rq, p, 0);
 }
 
 /* Account for a task changing its policy or group.