1 files changed, 521 insertions, 147 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d941c97dfbc3..6559d197e08a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -37,7 +37,6 @@
 
 /*
  * Targeted preemption latency for CPU-bound tasks:
- * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * NOTE: this latency value is not the same as the concept of
  * 'timeslice length' - timeslices in CFS are of variable length
@@ -46,31 +45,35 @@
  *
  * (to see the precise effective timeslice length of your workload,
  *  run vmstat and monitor the context-switches (cs) field)
+ *
+ * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_latency = 6000000ULL;
-unsigned int normalized_sysctl_sched_latency = 6000000ULL;
+unsigned int sysctl_sched_latency			= 6000000ULL;
+unsigned int normalized_sysctl_sched_latency		= 6000000ULL;
 
 /*
  * The initial- and re-scaling of tunables is configurable
- * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
  *
  * Options are:
- * SCHED_TUNABLESCALING_NONE - unscaled, always *1
- * SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus)
- * SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus
+ *
+ *   SCHED_TUNABLESCALING_NONE - unscaled, always *1
+ *   SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus)
+ *   SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus
+ *
+ * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
  */
-enum sched_tunable_scaling sysctl_sched_tunable_scaling
-	= SCHED_TUNABLESCALING_LOG;
+enum sched_tunable_scaling sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG;
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
+ *
  * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity = 750000ULL;
-unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
+unsigned int sysctl_sched_min_granularity		= 750000ULL;
+unsigned int normalized_sysctl_sched_min_granularity	= 750000ULL;
 
 /*
- * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
+ * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
  */
 static unsigned int sched_nr_latency = 8;
 
@@ -82,23 +85,27 @@ unsigned int sysctl_sched_child_runs_first __read_mostly;
 
 /*
  * SCHED_OTHER wake-up granularity.
- * (default: 1 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.
+ *
+ * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
-unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
+unsigned int sysctl_sched_wakeup_granularity		= 1000000UL;
+unsigned int normalized_sysctl_sched_wakeup_granularity	= 1000000UL;
 
-const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
+const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
 
+#ifdef CONFIG_SMP
 /*
- * The exponential sliding  window over which load is averaged for shares
- * distribution.
- * (default: 10msec)
+ * For asym packing, by default the lower numbered cpu has higher priority.
  */
-unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
+int __weak arch_asym_cpu_priority(int cpu)
+{
+	return -cpu;
+}
+#endif
 
 #ifdef CONFIG_CFS_BANDWIDTH
 /*
@@ -109,16 +116,18 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
  * to consumption or the quota being specified to be smaller than the slice)
  * we will always only issue the remaining available time.
  *
- * default: 5 msec, units: microseconds
-  */
-unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
+ * (default: 5 msec, units: microseconds)
+ */
+unsigned int sysctl_sched_cfs_bandwidth_slice		= 5000UL;
 #endif
 
 /*
  * The margin used when comparing utilization with CPU capacity:
- * util * 1024 < capacity * margin
+ * util * margin < capacity * 1024
+ *
+ * (default: ~20%)
  */
-unsigned int capacity_margin = 1280; /* ~20% */
+unsigned int capacity_margin				= 1280;
 
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
 {
@@ -290,19 +299,59 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
 static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	if (!cfs_rq->on_list) {
+		struct rq *rq = rq_of(cfs_rq);
+		int cpu = cpu_of(rq);
 		/*
 		 * Ensure we either appear before our parent (if already
 		 * enqueued) or force our parent to appear after us when it is
-		 * enqueued.  The fact that we always enqueue bottom-up
-		 * reduces this to two cases.
+		 * enqueued. The fact that we always enqueue bottom-up
+		 * reduces this to two cases and a special case for the root
+		 * cfs_rq. Furthermore, it also means that we will always reset
+		 * tmp_alone_branch either when the branch is connected
+		 * to a tree or when we reach the beg of the tree
 		 */
 		if (cfs_rq->tg->parent &&
-		    cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) {
-			list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
-				&rq_of(cfs_rq)->leaf_cfs_rq_list);
-		} else {
+		    cfs_rq->tg->parent->cfs_rq[cpu]->on_list) {
+			/*
+			 * If parent is already on the list, we add the child
+			 * just before. Thanks to circular linked property of
+			 * the list, this means to put the child at the tail
+			 * of the list that starts by parent.
+			 */
+			list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
+				&(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list));
+			/*
+			 * The branch is now connected to its tree so we can
+			 * reset tmp_alone_branch to the beginning of the
+			 * list.
+			 */
+			rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+		} else if (!cfs_rq->tg->parent) {
+			/*
+			 * cfs rq without parent should be put
+			 * at the tail of the list.
+			 */
 			list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
-				&rq_of(cfs_rq)->leaf_cfs_rq_list);
+				&rq->leaf_cfs_rq_list);
+			/*
+			 * We have reach the beg of a tree so we can reset
+			 * tmp_alone_branch to the beginning of the list.
+			 */
+			rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+		} else {
+			/*
+			 * The parent has not already been added so we want to
+			 * make sure that it will be put after us.
+			 * tmp_alone_branch points to the beg of the branch
+			 * where we will add parent.
+			 */
+			list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
+				rq->tmp_alone_branch);
+			/*
+			 * update tmp_alone_branch to points to the new beg
+			 * of the branch
+			 */
+			rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list;
 		}
 
 		cfs_rq->on_list = 1;
@@ -708,9 +757,7 @@ void init_entity_runnable_average(struct sched_entity *se)
 }
 
 static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
-static int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq);
-static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force);
-static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se);
+static void attach_entity_cfs_rq(struct sched_entity *se);
 
 /*
  * With new tasks being created, their initial util_avgs are extrapolated
@@ -742,7 +789,6 @@ void post_init_entity_util_avg(struct sched_entity *se)
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	struct sched_avg *sa = &se->avg;
 	long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
-	u64 now = cfs_rq_clock_task(cfs_rq);
 
 	if (cap > 0) {
 		if (cfs_rq->avg.util_avg != 0) {
@@ -770,14 +816,12 @@ void post_init_entity_util_avg(struct sched_entity *se)
 			 * such that the next switched_to_fair() has the
 			 * expected state.
 			 */
-			se->avg.last_update_time = now;
+			se->avg.last_update_time = cfs_rq_clock_task(cfs_rq);
 			return;
 		}
 	}
 
-	update_cfs_rq_load_avg(now, cfs_rq, false);
-	attach_entity_load_avg(cfs_rq, se);
-	update_tg_load_avg(cfs_rq, false);
+	attach_entity_cfs_rq(se);
 }
 
 #else /* !CONFIG_SMP */
@@ -2890,6 +2934,26 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 	return decayed;
 }
 
+/*
+ * Signed add and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define add_positive(_ptr, _val) do {                           \
+	typeof(_ptr) ptr = (_ptr);                              \
+	typeof(_val) val = (_val);                              \
+	typeof(*ptr) res, var = READ_ONCE(*ptr);                \
+								\
+	res = var + val;                                        \
+								\
+	if (val < 0 && res > var)                               \
+		res = 0;                                        \
+								\
+	WRITE_ONCE(*ptr, res);                                  \
+} while (0)
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /**
  * update_tg_load_avg - update the tg's load avg
@@ -2969,8 +3033,138 @@ void set_task_rq_fair(struct sched_entity *se,
 		se->avg.last_update_time = n_last_update_time;
 	}
 }
+
+/* Take into account change of utilization of a child task group */
+static inline void
+update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+	long delta = gcfs_rq->avg.util_avg - se->avg.util_avg;
+
+	/* Nothing to update */
+	if (!delta)
+		return;
+
+	/* Set new sched_entity's utilization */
+	se->avg.util_avg = gcfs_rq->avg.util_avg;
+	se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX;
+
+	/* Update parent cfs_rq utilization */
+	add_positive(&cfs_rq->avg.util_avg, delta);
+	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
+}
+
+/* Take into account change of load of a child task group */
+static inline void
+update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+	long delta, load = gcfs_rq->avg.load_avg;
+
+	/*
+	 * If the load of group cfs_rq is null, the load of the
+	 * sched_entity will also be null so we can skip the formula
+	 */
+	if (load) {
+		long tg_load;
+
+		/* Get tg's load and ensure tg_load > 0 */
+		tg_load = atomic_long_read(&gcfs_rq->tg->load_avg) + 1;
+
+		/* Ensure tg_load >= load and updated with current load*/
+		tg_load -= gcfs_rq->tg_load_avg_contrib;
+		tg_load += load;
+
+		/*
+		 * We need to compute a correction term in the case that the
+		 * task group is consuming more CPU than a task of equal
+		 * weight. A task with a weight equals to tg->shares will have
+		 * a load less or equal to scale_load_down(tg->shares).
+		 * Similarly, the sched_entities that represent the task group
+		 * at parent level, can't have a load higher than
+		 * scale_load_down(tg->shares). And the Sum of sched_entities'
+		 * load must be <= scale_load_down(tg->shares).
+		 */
+		if (tg_load > scale_load_down(gcfs_rq->tg->shares)) {
+			/* scale gcfs_rq's load into tg's shares*/
+			load *= scale_load_down(gcfs_rq->tg->shares);
+			load /= tg_load;
+		}
+	}
+
+	delta = load - se->avg.load_avg;
+
+	/* Nothing to update */
+	if (!delta)
+		return;
+
+	/* Set new sched_entity's load */
+	se->avg.load_avg = load;
+	se->avg.load_sum = se->avg.load_avg * LOAD_AVG_MAX;
+
+	/* Update parent cfs_rq load */
+	add_positive(&cfs_rq->avg.load_avg, delta);
+	cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * LOAD_AVG_MAX;
+
+	/*
+	 * If the sched_entity is already enqueued, we also have to update the
+	 * runnable load avg.
+	 */
+	if (se->on_rq) {
+		/* Update parent cfs_rq runnable_load_avg */
+		add_positive(&cfs_rq->runnable_load_avg, delta);
+		cfs_rq->runnable_load_sum = cfs_rq->runnable_load_avg * LOAD_AVG_MAX;
+	}
+}
+
+static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq)
+{
+	cfs_rq->propagate_avg = 1;
+}
+
+static inline int test_and_clear_tg_cfs_propagate(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq = group_cfs_rq(se);
+
+	if (!cfs_rq->propagate_avg)
+		return 0;
+
+	cfs_rq->propagate_avg = 0;
+	return 1;
+}
+
+/* Update task and its cfs_rq load average */
+static inline int propagate_entity_load_avg(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq;
+
+	if (entity_is_task(se))
+		return 0;
+
+	if (!test_and_clear_tg_cfs_propagate(se))
+		return 0;
+
+	cfs_rq = cfs_rq_of(se);
+
+	set_tg_cfs_propagate(cfs_rq);
+
+	update_tg_cfs_util(cfs_rq, se);
+	update_tg_cfs_load(cfs_rq, se);
+
+	return 1;
+}
+
 #else /* CONFIG_FAIR_GROUP_SCHED */
+
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
+
+static inline int propagate_entity_load_avg(struct sched_entity *se)
+{
+	return 0;
+}
+
+static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {}
+
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
@@ -3041,6 +3235,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 		sub_positive(&sa->load_avg, r);
 		sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
 		removed_load = 1;
+		set_tg_cfs_propagate(cfs_rq);
 	}
 
 	if (atomic_long_read(&cfs_rq->removed_util_avg)) {
@@ -3048,6 +3243,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 		sub_positive(&sa->util_avg, r);
 		sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
 		removed_util = 1;
+		set_tg_cfs_propagate(cfs_rq);
 	}
 
 	decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -3064,23 +3260,35 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 	return decayed || removed_load;
 }
 
+/*
+ * Optional action to be done while updating the load average
+ */
+#define UPDATE_TG	0x1
+#define SKIP_AGE_LOAD	0x2
+
 /* Update task and its cfs_rq load average */
-static inline void update_load_avg(struct sched_entity *se, int update_tg)
+static inline void update_load_avg(struct sched_entity *se, int flags)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	u64 now = cfs_rq_clock_task(cfs_rq);
 	struct rq *rq = rq_of(cfs_rq);
 	int cpu = cpu_of(rq);
+	int decayed;
 
 	/*
 	 * Track task load average for carrying it to new CPU after migrated, and
 	 * track group sched_entity load average for task_h_load calc in migration
 	 */
-	__update_load_avg(now, cpu, &se->avg,
+	if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) {
+		__update_load_avg(now, cpu, &se->avg,
 			  se->on_rq * scale_load_down(se->load.weight),
 			  cfs_rq->curr == se, NULL);
+	}
 
-	if (update_cfs_rq_load_avg(now, cfs_rq, true) && update_tg)
+	decayed  = update_cfs_rq_load_avg(now, cfs_rq, true);
+	decayed |= propagate_entity_load_avg(se);
+
+	if (decayed && (flags & UPDATE_TG))
 		update_tg_load_avg(cfs_rq, 0);
 }
 
@@ -3094,31 +3302,12 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
  */
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	if (!sched_feat(ATTACH_AGE_LOAD))
-		goto skip_aging;
-
-	/*
-	 * If we got migrated (either between CPUs or between cgroups) we'll
-	 * have aged the average right before clearing @last_update_time.
-	 *
-	 * Or we're fresh through post_init_entity_util_avg().
-	 */
-	if (se->avg.last_update_time) {
-		__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
-				  &se->avg, 0, 0, NULL);
-
-		/*
-		 * XXX: we could have just aged the entire load away if we've been
-		 * absent from the fair class for too long.
-		 */
-	}
-
-skip_aging:
 	se->avg.last_update_time = cfs_rq->avg.last_update_time;
 	cfs_rq->avg.load_avg += se->avg.load_avg;
 	cfs_rq->avg.load_sum += se->avg.load_sum;
 	cfs_rq->avg.util_avg += se->avg.util_avg;
 	cfs_rq->avg.util_sum += se->avg.util_sum;
+	set_tg_cfs_propagate(cfs_rq);
 
 	cfs_rq_util_change(cfs_rq);
 }
@@ -3133,14 +3322,12 @@ skip_aging:
  */
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
-			  &se->avg, se->on_rq * scale_load_down(se->load.weight),
-			  cfs_rq->curr == se, NULL);
 
 	sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
 	sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
 	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
 	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+	set_tg_cfs_propagate(cfs_rq);
 
 	cfs_rq_util_change(cfs_rq);
 }
@@ -3150,34 +3337,20 @@ static inline void
 enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	struct sched_avg *sa = &se->avg;
-	u64 now = cfs_rq_clock_task(cfs_rq);
-	int migrated, decayed;
-
-	migrated = !sa->last_update_time;
-	if (!migrated) {
-		__update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
-			se->on_rq * scale_load_down(se->load.weight),
-			cfs_rq->curr == se, NULL);
-	}
-
-	decayed = update_cfs_rq_load_avg(now, cfs_rq, !migrated);
 
 	cfs_rq->runnable_load_avg += sa->load_avg;
 	cfs_rq->runnable_load_sum += sa->load_sum;
 
-	if (migrated)
+	if (!sa->last_update_time) {
 		attach_entity_load_avg(cfs_rq, se);
-
-	if (decayed || migrated)
 		update_tg_load_avg(cfs_rq, 0);
+	}
 }
 
 /* Remove the runnable load generated by se from cfs_rq's runnable load average */
 static inline void
 dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	update_load_avg(se, 1);
-
 	cfs_rq->runnable_load_avg =
 		max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0);
 	cfs_rq->runnable_load_sum =
@@ -3206,13 +3379,25 @@ static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
 #endif
 
 /*
+ * Synchronize entity load avg of dequeued entity without locking
+ * the previous rq.
+ */
+void sync_entity_load_avg(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	u64 last_update_time;
+
+	last_update_time = cfs_rq_last_update_time(cfs_rq);
+	__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+}
+
+/*
  * Task first catches up with cfs_rq, and then subtract
  * itself from the cfs_rq (task must be off the queue now).
  */
 void remove_entity_load_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	u64 last_update_time;
 
 	/*
 	 * tasks cannot exit without having gone through wake_up_new_task() ->
@@ -3224,9 +3409,7 @@ void remove_entity_load_avg(struct sched_entity *se)
 	 * calls this.
 	 */
 
-	last_update_time = cfs_rq_last_update_time(cfs_rq);
-
-	__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+	sync_entity_load_avg(se);
 	atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
 	atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
 }
@@ -3251,7 +3434,10 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 	return 0;
 }
 
-static inline void update_load_avg(struct sched_entity *se, int not_used)
+#define UPDATE_TG	0x0
+#define SKIP_AGE_LOAD	0x0
+
+static inline void update_load_avg(struct sched_entity *se, int not_used1)
 {
 	cpufreq_update_util(rq_of(cfs_rq_of(se)), 0);
 }
@@ -3396,6 +3582,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	if (renorm && !curr)
 		se->vruntime += cfs_rq->min_vruntime;
 
+	update_load_avg(se, UPDATE_TG);
 	enqueue_entity_load_avg(cfs_rq, se);
 	account_entity_enqueue(cfs_rq, se);
 	update_cfs_shares(cfs_rq);
@@ -3470,6 +3657,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
+	update_load_avg(se, UPDATE_TG);
 	dequeue_entity_load_avg(cfs_rq, se);
 
 	update_stats_dequeue(cfs_rq, se, flags);
@@ -3557,7 +3745,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 */
 		update_stats_wait_end(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
-		update_load_avg(se, 1);
+		update_load_avg(se, UPDATE_TG);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
@@ -3675,7 +3863,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	/*
 	 * Ensure that runnable average is periodically updated.
 	 */
-	update_load_avg(curr, 1);
+	update_load_avg(curr, UPDATE_TG);
 	update_cfs_shares(cfs_rq);
 
 #ifdef CONFIG_SCHED_HRTICK
@@ -4572,7 +4760,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 
-		update_load_avg(se, 1);
+		update_load_avg(se, UPDATE_TG);
 		update_cfs_shares(cfs_rq);
 	}
 
@@ -4631,7 +4819,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 
-		update_load_avg(se, 1);
+		update_load_avg(se, UPDATE_TG);
 		update_cfs_shares(cfs_rq);
 	}
 
@@ -5199,6 +5387,14 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	return 1;
 }
 
+static inline int task_util(struct task_struct *p);
+static int cpu_util_wake(int cpu, struct task_struct *p);
+
+static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+{
+	return capacity_orig_of(cpu) - cpu_util_wake(cpu, p);
+}
+
 /*
  * find_idlest_group finds and returns the least busy CPU group within the
  * domain.
@@ -5208,15 +5404,21 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		  int this_cpu, int sd_flag)
 {
 	struct sched_group *idlest = NULL, *group = sd->groups;
-	unsigned long min_load = ULONG_MAX, this_load = 0;
+	struct sched_group *most_spare_sg = NULL;
+	unsigned long min_runnable_load = ULONG_MAX, this_runnable_load = 0;
+	unsigned long min_avg_load = ULONG_MAX, this_avg_load = 0;
+	unsigned long most_spare = 0, this_spare = 0;
 	int load_idx = sd->forkexec_idx;
-	int imbalance = 100 + (sd->imbalance_pct-100)/2;
+	int imbalance_scale = 100 + (sd->imbalance_pct-100)/2;
+	unsigned long imbalance = scale_load_down(NICE_0_LOAD) *
+				(sd->imbalance_pct-100) / 100;
 
 	if (sd_flag & SD_BALANCE_WAKE)
 		load_idx = sd->wake_idx;
 
 	do {
-		unsigned long load, avg_load;
+		unsigned long load, avg_load, runnable_load;
+		unsigned long spare_cap, max_spare_cap;
 		int local_group;
 		int i;
 
@@ -5228,8 +5430,13 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		local_group = cpumask_test_cpu(this_cpu,
 					       sched_group_cpus(group));
 
-		/* Tally up the load of all CPUs in the group */
+		/*
+		 * Tally up the load of all CPUs in the group and find
+		 * the group containing the CPU with most spare capacity.
+		 */
 		avg_load = 0;
+		runnable_load = 0;
+		max_spare_cap = 0;
 
 		for_each_cpu(i, sched_group_cpus(group)) {
 			/* Bias balancing toward cpus of our domain */
@@ -5238,22 +5445,84 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 			else
 				load = target_load(i, load_idx);
 
-			avg_load += load;
+			runnable_load += load;
+
+			avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
+
+			spare_cap = capacity_spare_wake(i, p);
+
+			if (spare_cap > max_spare_cap)
+				max_spare_cap = spare_cap;
 		}
 
 		/* Adjust by relative CPU capacity of the group */
-		avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity;
+		avg_load = (avg_load * SCHED_CAPACITY_SCALE) /
+					group->sgc->capacity;
+		runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) /
+					group->sgc->capacity;
 
 		if (local_group) {
-			this_load = avg_load;
-		} else if (avg_load < min_load) {
-			min_load = avg_load;
-			idlest = group;
+			this_runnable_load = runnable_load;
+			this_avg_load = avg_load;
+			this_spare = max_spare_cap;
+		} else {
+			if (min_runnable_load > (runnable_load + imbalance)) {
+				/*
+				 * The runnable load is significantly smaller
+				 * so we can pick this new cpu
+				 */
+				min_runnable_load = runnable_load;
+				min_avg_load = avg_load;
+				idlest = group;
+			} else if ((runnable_load < (min_runnable_load + imbalance)) &&
+				   (100*min_avg_load > imbalance_scale*avg_load)) {
+				/*
+				 * The runnable loads are close so take the
+				 * blocked load into account through avg_load.
+				 */
+				min_avg_load = avg_load;
+				idlest = group;
+			}
+
+			if (most_spare < max_spare_cap) {
+				most_spare = max_spare_cap;
+				most_spare_sg = group;
+			}
 		}
 	} while (group = group->next, group != sd->groups);
 
-	if (!idlest || 100*this_load < imbalance*min_load)
+	/*
+	 * The cross-over point between using spare capacity or least load
+	 * is too conservative for high utilization tasks on partially
+	 * utilized systems if we require spare_capacity > task_util(p),
+	 * so we allow for some task stuffing by using
+	 * spare_capacity > task_util(p)/2.
+	 *
+	 * Spare capacity can't be used for fork because the utilization has
+	 * not been set yet, we must first select a rq to compute the initial
+	 * utilization.
+	 */
+	if (sd_flag & SD_BALANCE_FORK)
+		goto skip_spare;
+
+	if (this_spare > task_util(p) / 2 &&
+	    imbalance_scale*this_spare > 100*most_spare)
 		return NULL;
+
+	if (most_spare > task_util(p) / 2)
+		return most_spare_sg;
+
+skip_spare:
+	if (!idlest)
+		return NULL;
+
+	if (min_runnable_load > (this_runnable_load + imbalance))
+		return NULL;
+
+	if ((this_runnable_load < (min_runnable_load + imbalance)) &&
+	     (100*this_avg_load < imbalance_scale*min_avg_load))
+		return NULL;
+
 	return idlest;
 }
 
@@ -5590,6 +5859,24 @@ static inline int task_util(struct task_struct *p)
 }
 
 /*
+ * cpu_util_wake: Compute cpu utilization with any contributions from
+ * the waking task p removed.
+ */
+static int cpu_util_wake(int cpu, struct task_struct *p)
+{
+	unsigned long util, capacity;
+
+	/* Task has no contribution or is new */
+	if (cpu != task_cpu(p) || !p->se.avg.last_update_time)
+		return cpu_util(cpu);
+
+	capacity = capacity_orig_of(cpu);
+	util = max_t(long, cpu_rq(cpu)->cfs.avg.util_avg - task_util(p), 0);
+
+	return (util >= capacity) ? capacity : util;
+}
+
+/*
  * Disable WAKE_AFFINE in the case where task @p doesn't fit in the
  * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
  *
@@ -5607,6 +5894,9 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 	if (max_cap - min_cap < max_cap >> 3)
 		return 0;
 
+	/* Bring task utilization in sync with prev_cpu */
+	sync_entity_load_avg(&p->se);
+
 	return min_cap * 1024 < task_util(p) * capacity_margin;
 }
 
@@ -6641,6 +6931,10 @@ static void update_blocked_averages(int cpu)
 
 		if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true))
 			update_tg_load_avg(cfs_rq, 0);
+
+		/* Propagate pending load changes to the parent */
+		if (cfs_rq->tg->se[cpu])
+			update_load_avg(cfs_rq->tg->se[cpu], 0);
 	}
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
@@ -6845,13 +7139,14 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 
 	cpu_rq(cpu)->cpu_capacity = capacity;
 	sdg->sgc->capacity = capacity;
+	sdg->sgc->min_capacity = capacity;
 }
 
 void update_group_capacity(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
-	unsigned long capacity;
+	unsigned long capacity, min_capacity;
 	unsigned long interval;
 
 	interval = msecs_to_jiffies(sd->balance_interval);
@@ -6864,6 +7159,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 	}
 
 	capacity = 0;
+	min_capacity = ULONG_MAX;
 
 	if (child->flags & SD_OVERLAP) {
 		/*
@@ -6888,11 +7184,12 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 			 */
 			if (unlikely(!rq->sd)) {
 				capacity += capacity_of(cpu);
-				continue;
+			} else {
+				sgc = rq->sd->groups->sgc;
+				capacity += sgc->capacity;
 			}
 
-			sgc = rq->sd->groups->sgc;
-			capacity += sgc->capacity;
+			min_capacity = min(capacity, min_capacity);
 		}
 	} else  {
 		/*
@@ -6902,12 +7199,16 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 
 		group = child->groups;
 		do {
-			capacity += group->sgc->capacity;
+			struct sched_group_capacity *sgc = group->sgc;
+
+			capacity += sgc->capacity;
+			min_capacity = min(sgc->min_capacity, min_capacity);
 			group = group->next;
 		} while (group != child->groups);
 	}
 
 	sdg->sgc->capacity = capacity;
+	sdg->sgc->min_capacity = min_capacity;
 }
 
 /*
@@ -6930,8 +7231,8 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
  * cpumask covering 1 cpu of the first group and 3 cpus of the second group.
  * Something like:
  *
- * 	{ 0 1 2 3 } { 4 5 6 7 }
- * 	        *     * * *
+ *	{ 0 1 2 3 } { 4 5 6 7 }
+ *	        *     * * *
  *
  * If we were to balance group-wise we'd place two tasks in the first group and
  * two tasks in the second group. Clearly this is undesired as it will overload
@@ -7002,6 +7303,17 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
 	return false;
 }
 
+/*
+ * group_smaller_cpu_capacity: Returns true if sched_group sg has smaller
+ * per-CPU capacity than sched_group ref.
+ */
+static inline bool
+group_smaller_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
+{
+	return sg->sgc->min_capacity * capacity_margin <
+						ref->sgc->min_capacity * 1024;
+}
+
 static inline enum
 group_type group_classify(struct sched_group *group,
 			  struct sg_lb_stats *sgs)
@@ -7105,6 +7417,20 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	if (sgs->avg_load <= busiest->avg_load)
 		return false;
 
+	if (!(env->sd->flags & SD_ASYM_CPUCAPACITY))
+		goto asym_packing;
+
+	/*
+	 * Candidate sg has no more than one task per CPU and
+	 * has higher per-CPU capacity. Migrating tasks to less
+	 * capable CPUs may harm throughput. Maximize throughput,
+	 * power/energy consequences are not considered.
+	 */
+	if (sgs->sum_nr_running <= sgs->group_weight &&
+	    group_smaller_cpu_capacity(sds->local, sg))
+		return false;
+
+asym_packing:
 	/* This is the busiest node in its class. */
 	if (!(env->sd->flags & SD_ASYM_PACKING))
 		return true;
@@ -7113,16 +7439,18 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	if (env->idle == CPU_NOT_IDLE)
 		return true;
 	/*
-	 * ASYM_PACKING needs to move all the work to the lowest
-	 * numbered CPUs in the group, therefore mark all groups
-	 * higher than ourself as busy.
+	 * ASYM_PACKING needs to move all the work to the highest
+	 * prority CPUs in the group, therefore mark all groups
+	 * of lower priority than ourself as busy.
 	 */
-	if (sgs->sum_nr_running && env->dst_cpu < group_first_cpu(sg)) {
+	if (sgs->sum_nr_running &&
+	    sched_asym_prefer(env->dst_cpu, sg->asym_prefer_cpu)) {
 		if (!sds->busiest)
 			return true;
 
-		/* Prefer to move from highest possible cpu's work */
-		if (group_first_cpu(sds->busiest) < group_first_cpu(sg))
+		/* Prefer to move from lowest priority cpu's work */
+		if (sched_asym_prefer(sds->busiest->asym_prefer_cpu,
+				      sg->asym_prefer_cpu))
 			return true;
 	}
 
@@ -7274,8 +7602,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
 	if (!sds->busiest)
 		return 0;
 
-	busiest_cpu = group_first_cpu(sds->busiest);
-	if (env->dst_cpu > busiest_cpu)
+	busiest_cpu = sds->busiest->asym_prefer_cpu;
+	if (sched_asym_prefer(busiest_cpu, env->dst_cpu))
 		return 0;
 
 	env->imbalance = DIV_ROUND_CLOSEST(
@@ -7613,10 +7941,11 @@ static int need_active_balance(struct lb_env *env)
 
 		/*
 		 * ASYM_PACKING needs to force migrate tasks from busy but
-		 * higher numbered CPUs in order to pack all tasks in the
-		 * lowest numbered CPUs.
+		 * lower priority CPUs in order to pack all tasks in the
+		 * highest priority CPUs.
 		 */
-		if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu)
+		if ((sd->flags & SD_ASYM_PACKING) &&
+		    sched_asym_prefer(env->dst_cpu, env->src_cpu))
 			return 1;
 	}
 
@@ -8465,7 +8794,7 @@ static inline bool nohz_kick_needed(struct rq *rq)
 	unsigned long now = jiffies;
 	struct sched_domain_shared *sds;
 	struct sched_domain *sd;
-	int nr_busy, cpu = rq->cpu;
+	int nr_busy, i, cpu = rq->cpu;
 	bool kick = false;
 
 	if (unlikely(rq->idle_balance))
@@ -8516,12 +8845,18 @@ static inline bool nohz_kick_needed(struct rq *rq)
 	}
 
 	sd = rcu_dereference(per_cpu(sd_asym, cpu));
-	if (sd && (cpumask_first_and(nohz.idle_cpus_mask,
-				  sched_domain_span(sd)) < cpu)) {
-		kick = true;
-		goto unlock;
-	}
+	if (sd) {
+		for_each_cpu(i, sched_domain_span(sd)) {
+			if (i == cpu ||
+			    !cpumask_test_cpu(i, nohz.idle_cpus_mask))
+				continue;
 
+			if (sched_asym_prefer(i, cpu)) {
+				kick = true;
+				goto unlock;
+			}
+		}
+	}
 unlock:
 	rcu_read_unlock();
 	return kick;
@@ -8687,32 +9022,45 @@ static inline bool vruntime_normalized(struct task_struct *p)
 	return false;
 }
 
-static void detach_task_cfs_rq(struct task_struct *p)
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * Propagate the changes of the sched_entity across the tg tree to make it
+ * visible to the root
+ */
+static void propagate_entity_cfs_rq(struct sched_entity *se)
 {
-	struct sched_entity *se = &p->se;
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	u64 now = cfs_rq_clock_task(cfs_rq);
+	struct cfs_rq *cfs_rq;
 
-	if (!vruntime_normalized(p)) {
-		/*
-		 * Fix up our vruntime so that the current sleep doesn't
-		 * cause 'unlimited' sleep bonus.
-		 */
-		place_entity(cfs_rq, se, 0);
-		se->vruntime -= cfs_rq->min_vruntime;
+	/* Start to propagate at parent */
+	se = se->parent;
+
+	for_each_sched_entity(se) {
+		cfs_rq = cfs_rq_of(se);
+
+		if (cfs_rq_throttled(cfs_rq))
+			break;
+
+		update_load_avg(se, UPDATE_TG);
 	}
+}
+#else
+static void propagate_entity_cfs_rq(struct sched_entity *se) { }
+#endif
+
+static void detach_entity_cfs_rq(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 	/* Catch up with the cfs_rq and remove our load when we leave */
-	update_cfs_rq_load_avg(now, cfs_rq, false);
+	update_load_avg(se, 0);
 	detach_entity_load_avg(cfs_rq, se);
 	update_tg_load_avg(cfs_rq, false);
+	propagate_entity_cfs_rq(se);
 }
 
-static void attach_task_cfs_rq(struct task_struct *p)
+static void attach_entity_cfs_rq(struct sched_entity *se)
 {
-	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	u64 now = cfs_rq_clock_task(cfs_rq);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/*
@@ -8722,10 +9070,36 @@ static void attach_task_cfs_rq(struct task_struct *p)
 	se->depth = se->parent ? se->parent->depth + 1 : 0;
 #endif
 
-	/* Synchronize task with its cfs_rq */
-	update_cfs_rq_load_avg(now, cfs_rq, false);
+	/* Synchronize entity with its cfs_rq */
+	update_load_avg(se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
 	attach_entity_load_avg(cfs_rq, se);
 	update_tg_load_avg(cfs_rq, false);
+	propagate_entity_cfs_rq(se);
+}
+
+static void detach_task_cfs_rq(struct task_struct *p)
+{
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+	if (!vruntime_normalized(p)) {
+		/*
+		 * Fix up our vruntime so that the current sleep doesn't
+		 * cause 'unlimited' sleep bonus.
+		 */
+		place_entity(cfs_rq, se, 0);
+		se->vruntime -= cfs_rq->min_vruntime;
+	}
+
+	detach_entity_cfs_rq(se);
+}
+
+static void attach_task_cfs_rq(struct task_struct *p)
+{
+	struct sched_entity *se = &p->se;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+	attach_entity_cfs_rq(se);
 
 	if (!vruntime_normalized(p))
 		se->vruntime += cfs_rq->min_vruntime;
@@ -8779,6 +9153,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
 #endif
 #ifdef CONFIG_SMP
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	cfs_rq->propagate_avg = 0;
+#endif
 	atomic_long_set(&cfs_rq->removed_load_avg, 0);
 	atomic_long_set(&cfs_rq->removed_util_avg, 0);
 #endif
@@ -8839,7 +9216,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	struct sched_entity *se;
 	struct cfs_rq *cfs_rq;
-	struct rq *rq;
 	int i;
 
 	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8854,8 +9230,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
 	for_each_possible_cpu(i) {
-		rq = cpu_rq(i);
-
 		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
 				      GFP_KERNEL, cpu_to_node(i));
 		if (!cfs_rq)
@@ -8890,7 +9264,7 @@ void online_fair_sched_group(struct task_group *tg)
 		se = tg->se[i];
 
 		raw_spin_lock_irq(&rq->lock);
-		post_init_entity_util_avg(se);
+		attach_entity_cfs_rq(se);
 		sync_throttle(tg, i);
 		raw_spin_unlock_irq(&rq->lock);
 	}