1 files changed, 208 insertions, 148 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 81fa5364340..f77f9c52744 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -113,6 +113,24 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
 unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
 #endif
 
+static inline void update_load_add(struct load_weight *lw, unsigned long inc)
+{
+	lw->weight += inc;
+	lw->inv_weight = 0;
+}
+
+static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
+{
+	lw->weight -= dec;
+	lw->inv_weight = 0;
+}
+
+static inline void update_load_set(struct load_weight *lw, unsigned long w)
+{
+	lw->weight = w;
+	lw->inv_weight = 0;
+}
+
 /*
  * Increase the granularity value when there are more CPUs,
  * because with more CPUs the 'effective latency' as visible
@@ -431,13 +449,13 @@ void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec);
  * Scheduling class tree data structure manipulation methods:
  */
 
-static inline u64 max_vruntime(u64 min_vruntime, u64 vruntime)
+static inline u64 max_vruntime(u64 max_vruntime, u64 vruntime)
 {
-	s64 delta = (s64)(vruntime - min_vruntime);
+	s64 delta = (s64)(vruntime - max_vruntime);
 	if (delta > 0)
-		min_vruntime = vruntime;
+		max_vruntime = vruntime;
 
-	return min_vruntime;
+	return max_vruntime;
 }
 
 static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
@@ -473,6 +491,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 			vruntime = min_vruntime(vruntime, se->vruntime);
 	}
 
+	/* ensure we never gain time by being placed backwards. */
 	cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
 #ifndef CONFIG_64BIT
 	smp_wmb();
@@ -652,7 +671,7 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 /*
- * We calculate the vruntime slice of a to be inserted task
+ * We calculate the vruntime slice of a to-be-inserted task.
  *
  * vs = s/w
  */
@@ -661,6 +680,26 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	return calc_delta_fair(sched_slice(cfs_rq, se), se);
 }
 
+#ifdef CONFIG_SMP
+static inline void __update_task_entity_contrib(struct sched_entity *se);
+
+/* Give new task start runnable values to heavy its load in infant time */
+void init_task_runnable_average(struct task_struct *p)
+{
+	u32 slice;
+
+	p->se.avg.decay_count = 0;
+	slice = sched_slice(task_cfs_rq(p), &p->se) >> 10;
+	p->se.avg.runnable_avg_sum = slice;
+	p->se.avg.runnable_avg_period = slice;
+	__update_task_entity_contrib(&p->se);
+}
+#else
+void init_task_runnable_average(struct task_struct *p)
+{
+}
+#endif
+
 /*
  * Update the current task's runtime statistics. Skip current tasks that
  * are not in our scheduling class.
@@ -685,7 +724,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 static void update_curr(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
-	u64 now = rq_of(cfs_rq)->clock_task;
+	u64 now = rq_clock_task(rq_of(cfs_rq));
 	unsigned long delta_exec;
 
 	if (unlikely(!curr))
@@ -717,7 +756,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock);
+	schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq)));
 }
 
 /*
@@ -737,14 +776,14 @@ static void
 update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
-			rq_of(cfs_rq)->clock - se->statistics.wait_start));
+			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start));
 	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
 	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
-			rq_of(cfs_rq)->clock - se->statistics.wait_start);
+			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
 #ifdef CONFIG_SCHEDSTATS
 	if (entity_is_task(se)) {
 		trace_sched_stat_wait(task_of(se),
-			rq_of(cfs_rq)->clock - se->statistics.wait_start);
+			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
 	}
 #endif
 	schedstat_set(se->statistics.wait_start, 0);
@@ -770,7 +809,7 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	/*
 	 * We are starting a new run period:
 	 */
-	se->exec_start = rq_of(cfs_rq)->clock_task;
+	se->exec_start = rq_clock_task(rq_of(cfs_rq));
 }
 
 /**************************************************
@@ -1036,7 +1075,7 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
 	 * to gain a more accurate current total weight. See
 	 * update_cfs_rq_load_contribution().
 	 */
-	tg_weight = atomic64_read(&tg->load_avg);
+	tg_weight = atomic_long_read(&tg->load_avg);
 	tg_weight -= cfs_rq->tg_load_contrib;
 	tg_weight += cfs_rq->load.weight;
 
@@ -1109,8 +1148,7 @@ static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-/* Only depends on SMP, FAIR_GROUP_SCHED may be removed when useful in lb */
-#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+#ifdef CONFIG_SMP
 /*
  * We choose a half-life close to 1 scheduling period.
  * Note: The tables below are dependent on this value.
@@ -1318,13 +1356,13 @@ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
 						 int force_update)
 {
 	struct task_group *tg = cfs_rq->tg;
-	s64 tg_contrib;
+	long tg_contrib;
 
 	tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg;
 	tg_contrib -= cfs_rq->tg_load_contrib;
 
-	if (force_update || abs64(tg_contrib) > cfs_rq->tg_load_contrib / 8) {
-		atomic64_add(tg_contrib, &tg->load_avg);
+	if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) {
+		atomic_long_add(tg_contrib, &tg->load_avg);
 		cfs_rq->tg_load_contrib += tg_contrib;
 	}
 }
@@ -1359,8 +1397,8 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 	u64 contrib;
 
 	contrib = cfs_rq->tg_load_contrib * tg->shares;
-	se->avg.load_avg_contrib = div64_u64(contrib,
-					     atomic64_read(&tg->load_avg) + 1);
+	se->avg.load_avg_contrib = div_u64(contrib,
+				     atomic_long_read(&tg->load_avg) + 1);
 
 	/*
 	 * For group entities we need to compute a correction term in the case
@@ -1479,8 +1517,9 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
 	if (!decays && !force_update)
 		return;
 
-	if (atomic64_read(&cfs_rq->removed_load)) {
-		u64 removed_load = atomic64_xchg(&cfs_rq->removed_load, 0);
+	if (atomic_long_read(&cfs_rq->removed_load)) {
+		unsigned long removed_load;
+		removed_load = atomic_long_xchg(&cfs_rq->removed_load, 0);
 		subtract_blocked_load_contrib(cfs_rq, removed_load);
 	}
 
@@ -1496,7 +1535,7 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 {
-	__update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable);
+	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
 	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
 }
 
@@ -1509,9 +1548,13 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 	 * We track migrations using entity decay_count <= 0, on a wake-up
 	 * migration we use a negative decay count to track the remote decays
 	 * accumulated while sleeping.
+	 *
+	 * Newly forked tasks are enqueued with se->avg.decay_count == 0, they
+	 * are seen by enqueue_entity_load_avg() as a migration with an already
+	 * constructed load_avg_contrib.
 	 */
 	if (unlikely(se->avg.decay_count <= 0)) {
-		se->avg.last_runnable_update = rq_of(cfs_rq)->clock_task;
+		se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq));
 		if (se->avg.decay_count) {
 			/*
 			 * In a wake-up migration we have to approximate the
@@ -1529,7 +1572,13 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 		}
 		wakeup = 0;
 	} else {
-		__synchronize_entity_decay(se);
+		/*
+		 * Task re-woke on same cpu (or else migrate_task_rq_fair()
+		 * would have made count negative); we must be careful to avoid
+		 * double-accounting blocked time after synchronizing decays.
+		 */
+		se->avg.last_runnable_update += __synchronize_entity_decay(se)
+							<< 20;
 	}
 
 	/* migrated tasks did not contribute to our blocked load */
@@ -1562,6 +1611,27 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
 		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
 	} /* migrations, e.g. sleep=0 leave decay_count == 0 */
 }
+
+/*
+ * Update the rq's load with the elapsed running time before entering
+ * idle. if the last scheduled task is not a CFS task, idle_enter will
+ * be the only way to update the runnable statistic.
+ */
+void idle_enter_fair(struct rq *this_rq)
+{
+	update_rq_runnable_avg(this_rq, 1);
+}
+
+/*
+ * Update the rq's load with the elapsed idle time before a task is
+ * scheduled. if the newly scheduled task is not a CFS task, idle_exit will
+ * be the only way to update the runnable statistic.
+ */
+void idle_exit_fair(struct rq *this_rq)
+{
+	update_rq_runnable_avg(this_rq, 0);
+}
+
 #else
 static inline void update_entity_load_avg(struct sched_entity *se,
 					  int update_cfs_rq) {}
@@ -1585,7 +1655,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		tsk = task_of(se);
 
 	if (se->statistics.sleep_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start;
+		u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.sleep_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
@@ -1602,7 +1672,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		}
 	}
 	if (se->statistics.block_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start;
+		u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.block_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
@@ -1680,9 +1750,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 	}
 
 	/* ensure we never gain time by being placed backwards. */
-	vruntime = max_vruntime(se->vruntime, vruntime);
-
-	se->vruntime = vruntime;
+	se->vruntime = max_vruntime(se->vruntime, vruntime);
 }
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
@@ -1692,7 +1760,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	/*
 	 * Update the normalized vruntime before updating min_vruntime
-	 * through callig update_curr().
+	 * through calling update_curr().
 	 */
 	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
 		se->vruntime += cfs_rq->min_vruntime;
@@ -1785,9 +1853,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 			struct task_struct *tsk = task_of(se);
 
 			if (tsk->state & TASK_INTERRUPTIBLE)
-				se->statistics.sleep_start = rq_of(cfs_rq)->clock;
+				se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
 			if (tsk->state & TASK_UNINTERRUPTIBLE)
-				se->statistics.block_start = rq_of(cfs_rq)->clock;
+				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
 		}
 #endif
 	}
@@ -2062,7 +2130,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 	if (unlikely(cfs_rq->throttle_count))
 		return cfs_rq->throttled_clock_task;
 
-	return rq_of(cfs_rq)->clock_task - cfs_rq->throttled_clock_task_time;
+	return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
 }
 
 /* returns 0 on failure to allocate runtime */
@@ -2118,10 +2186,9 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
-	struct rq *rq = rq_of(cfs_rq);
 
 	/* if the deadline is ahead of our clock, nothing to do */
-	if (likely((s64)(rq->clock - cfs_rq->runtime_expires) < 0))
+	if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0))
 		return;
 
 	if (cfs_rq->runtime_remaining < 0)
@@ -2210,7 +2277,7 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 #ifdef CONFIG_SMP
 	if (!cfs_rq->throttle_count) {
 		/* adjust cfs_rq_clock_task() */
-		cfs_rq->throttled_clock_task_time += rq->clock_task -
+		cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
 					     cfs_rq->throttled_clock_task;
 	}
 #endif
@@ -2225,7 +2292,7 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 
 	/* group is entering throttled state, stop time */
 	if (!cfs_rq->throttle_count)
-		cfs_rq->throttled_clock_task = rq->clock_task;
+		cfs_rq->throttled_clock_task = rq_clock_task(rq);
 	cfs_rq->throttle_count++;
 
 	return 0;
@@ -2264,7 +2331,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		rq->nr_running -= task_delta;
 
 	cfs_rq->throttled = 1;
-	cfs_rq->throttled_clock = rq->clock;
+	cfs_rq->throttled_clock = rq_clock(rq);
 	raw_spin_lock(&cfs_b->lock);
 	list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
 	raw_spin_unlock(&cfs_b->lock);
@@ -2278,15 +2345,17 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	int enqueue = 1;
 	long task_delta;
 
-	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
+	se = cfs_rq->tg->se[cpu_of(rq)];
 
 	cfs_rq->throttled = 0;
+
+	update_rq_clock(rq);
+
 	raw_spin_lock(&cfs_b->lock);
-	cfs_b->throttled_time += rq->clock - cfs_rq->throttled_clock;
+	cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
 	list_del_rcu(&cfs_rq->throttled_list);
 	raw_spin_unlock(&cfs_b->lock);
 
-	update_rq_clock(rq);
 	/* update hierarchical throttle state */
 	walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq);
 
@@ -2579,10 +2648,6 @@ static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	throttle_cfs_rq(cfs_rq);
 }
 
-static inline u64 default_cfs_period(void);
-static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun);
-static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b);
-
 static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
@@ -2686,7 +2751,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 #else /* CONFIG_CFS_BANDWIDTH */
 static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 {
-	return rq_of(cfs_rq)->clock_task;
+	return rq_clock_task(rq_of(cfs_rq));
 }
 
 static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
@@ -2899,7 +2964,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 /* Used instead of source_load when we know the type == 0 */
 static unsigned long weighted_cpuload(const int cpu)
 {
-	return cpu_rq(cpu)->load.weight;
+	return cpu_rq(cpu)->cfs.runnable_load_avg;
 }
 
 /*
@@ -2944,9 +3009,10 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long nr_running = ACCESS_ONCE(rq->nr_running);
+	unsigned long load_avg = rq->cfs.runnable_load_avg;
 
 	if (nr_running)
-		return rq->load.weight / nr_running;
+		return load_avg / nr_running;
 
 	return 0;
 }
@@ -3254,25 +3320,18 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
  */
 static int select_idle_sibling(struct task_struct *p, int target)
 {
-	int cpu = smp_processor_id();
-	int prev_cpu = task_cpu(p);
 	struct sched_domain *sd;
 	struct sched_group *sg;
-	int i;
+	int i = task_cpu(p);
 
-	/*
-	 * If the task is going to be woken-up on this cpu and if it is
-	 * already idle, then it is the right target.
-	 */
-	if (target == cpu && idle_cpu(cpu))
-		return cpu;
+	if (idle_cpu(target))
+		return target;
 
 	/*
-	 * If the task is going to be woken-up on the cpu where it previously
-	 * ran and if it is currently idle, then it the right target.
+	 * If the prevous cpu is cache affine and idle, don't be stupid.
 	 */
-	if (target == prev_cpu && idle_cpu(prev_cpu))
-		return prev_cpu;
+	if (i != target && cpus_share_cache(i, target) && idle_cpu(i))
+		return i;
 
 	/*
 	 * Otherwise, iterate the domains and find an elegible idle cpu.
@@ -3286,7 +3345,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
 				goto next;
 
 			for_each_cpu(i, sched_group_cpus(sg)) {
-				if (!idle_cpu(i))
+				if (i == target || !idle_cpu(i))
 					goto next;
 			}
 
@@ -3403,12 +3462,6 @@ unlock:
 }
 
 /*
- * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
- * removed when useful for applications beyond shares distribution (e.g.
- * load-balance).
- */
-#ifdef CONFIG_FAIR_GROUP_SCHED
-/*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
  * previous cpu.  However, the caller only guarantees p->pi_lock is held; no
@@ -3428,10 +3481,10 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu)
 	 */
 	if (se->avg.decay_count) {
 		se->avg.decay_count = -__synchronize_entity_decay(se);
-		atomic64_add(se->avg.load_avg_contrib, &cfs_rq->removed_load);
+		atomic_long_add(se->avg.load_avg_contrib,
+						&cfs_rq->removed_load);
 	}
 }
-#endif
 #endif /* CONFIG_SMP */
 
 static unsigned long
@@ -3883,12 +3936,16 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	int tsk_cache_hot = 0;
 	/*
 	 * We do not migrate tasks that are:
-	 * 1) running (obviously), or
+	 * 1) throttled_lb_pair, or
 	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
-	 * 3) are cache-hot on their current CPU.
+	 * 3) running (obviously), or
+	 * 4) are cache-hot on their current CPU.
 	 */
+	if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
+		return 0;
+
 	if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
-		int new_dst_cpu;
+		int cpu;
 
 		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
 
@@ -3903,12 +3960,15 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 		if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED))
 			return 0;
 
-		new_dst_cpu = cpumask_first_and(env->dst_grpmask,
-						tsk_cpus_allowed(p));
-		if (new_dst_cpu < nr_cpu_ids) {
-			env->flags |= LBF_SOME_PINNED;
-			env->new_dst_cpu = new_dst_cpu;
+		/* Prevent to re-select dst_cpu via env's cpus */
+		for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
+			if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) {
+				env->flags |= LBF_SOME_PINNED;
+				env->new_dst_cpu = cpu;
+				break;
+			}
 		}
+
 		return 0;
 	}
 
@@ -3926,23 +3986,20 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	 * 2) too many balance attempts have failed.
 	 */
 
-	tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
+	tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
 	if (!tsk_cache_hot ||
 		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
-#ifdef CONFIG_SCHEDSTATS
+
 		if (tsk_cache_hot) {
 			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
 			schedstat_inc(p, se.statistics.nr_forced_migrations);
 		}
-#endif
+
 		return 1;
 	}
 
-	if (tsk_cache_hot) {
-		schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
-		return 0;
-	}
-	return 1;
+	schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
+	return 0;
 }
 
 /*
@@ -3957,9 +4014,6 @@ static int move_one_task(struct lb_env *env)
 	struct task_struct *p, *n;
 
 	list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
-		if (throttled_lb_pair(task_group(p), env->src_rq->cpu, env->dst_cpu))
-			continue;
-
 		if (!can_migrate_task(p, env))
 			continue;
 
@@ -4011,7 +4065,7 @@ static int move_tasks(struct lb_env *env)
 			break;
 		}
 
-		if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
+		if (!can_migrate_task(p, env))
 			goto next;
 
 		load = task_h_load(p);
@@ -4022,9 +4076,6 @@ static int move_tasks(struct lb_env *env)
 		if ((load / 2) > env->imbalance)
 			goto next;
 
-		if (!can_migrate_task(p, env))
-			goto next;
-
 		move_task(p, env);
 		pulled++;
 		env->imbalance -= load;
@@ -4130,11 +4181,11 @@ static int tg_load_down(struct task_group *tg, void *data)
 	long cpu = (long)data;
 
 	if (!tg->parent) {
-		load = cpu_rq(cpu)->load.weight;
+		load = cpu_rq(cpu)->avg.load_avg_contrib;
 	} else {
 		load = tg->parent->cfs_rq[cpu]->h_load;
-		load *= tg->se[cpu]->load.weight;
-		load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
+		load = div64_ul(load * tg->se[cpu]->avg.load_avg_contrib,
+				tg->parent->cfs_rq[cpu]->runnable_load_avg + 1);
 	}
 
 	tg->cfs_rq[cpu]->h_load = load;
@@ -4160,12 +4211,9 @@ static void update_h_load(long cpu)
 static unsigned long task_h_load(struct task_struct *p)
 {
 	struct cfs_rq *cfs_rq = task_cfs_rq(p);
-	unsigned long load;
 
-	load = p->se.load.weight;
-	load = div_u64(load * cfs_rq->h_load, cfs_rq->load.weight + 1);
-
-	return load;
+	return div64_ul(p->se.avg.load_avg_contrib * cfs_rq->h_load,
+			cfs_rq->runnable_load_avg + 1);
 }
 #else
 static inline void update_blocked_averages(int cpu)
@@ -4178,7 +4226,7 @@ static inline void update_h_load(long cpu)
 
 static unsigned long task_h_load(struct task_struct *p)
 {
-	return p->se.load.weight;
+	return p->se.avg.load_avg_contrib;
 }
 #endif
 
@@ -4254,7 +4302,7 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 	return load_idx;
 }
 
-unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
+static unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
 {
 	return SCHED_POWER_SCALE;
 }
@@ -4264,7 +4312,7 @@ 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)
+static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
 {
 	unsigned long weight = sd->span_weight;
 	unsigned long smt_gain = sd->smt_gain;
@@ -4279,7 +4327,7 @@ 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)
+static unsigned long scale_rt_power(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	u64 total, available, age_stamp, avg;
@@ -4291,7 +4339,7 @@ unsigned long scale_rt_power(int cpu)
 	age_stamp = ACCESS_ONCE(rq->age_stamp);
 	avg = ACCESS_ONCE(rq->rt_avg);
 
-	total = sched_avg_period() + (rq->clock - age_stamp);
+	total = sched_avg_period() + (rq_clock(rq) - age_stamp);
 
 	if (unlikely(total < avg)) {
 		/* Ensures that power won't end up being negative */
@@ -4969,7 +5017,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 #define MAX_PINNED_INTERVAL	512
 
 /* Working cpumask for load_balance and load_balance_newidle. */
-DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
 
 static int need_active_balance(struct lb_env *env)
 {
@@ -5000,11 +5048,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			int *balance)
 {
 	int ld_moved, cur_ld_moved, active_balance = 0;
-	int lb_iterations, max_lb_iterations;
 	struct sched_group *group;
 	struct rq *busiest;
 	unsigned long flags;
-	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
+	struct cpumask *cpus = __get_cpu_var(load_balance_mask);
 
 	struct lb_env env = {
 		.sd		= sd,
@@ -5016,8 +5063,14 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.cpus		= cpus,
 	};
 
+	/*
+	 * For NEWLY_IDLE load_balancing, we don't need to consider
+	 * other cpus in our group
+	 */
+	if (idle == CPU_NEWLY_IDLE)
+		env.dst_grpmask = NULL;
+
 	cpumask_copy(cpus, cpu_active_mask);
-	max_lb_iterations = cpumask_weight(env.dst_grpmask);
 
 	schedstat_inc(sd, lb_count[idle]);
 
@@ -5043,7 +5096,6 @@ redo:
 	schedstat_add(sd, lb_imbalance[idle], env.imbalance);
 
 	ld_moved = 0;
-	lb_iterations = 1;
 	if (busiest->nr_running > 1) {
 		/*
 		 * Attempt to move tasks. If find_busiest_group has found
@@ -5070,17 +5122,17 @@ more_balance:
 		double_rq_unlock(env.dst_rq, busiest);
 		local_irq_restore(flags);
 
-		if (env.flags & LBF_NEED_BREAK) {
-			env.flags &= ~LBF_NEED_BREAK;
-			goto more_balance;
-		}
-
 		/*
 		 * some other cpu did the load balance for us.
 		 */
 		if (cur_ld_moved && env.dst_cpu != smp_processor_id())
 			resched_cpu(env.dst_cpu);
 
+		if (env.flags & LBF_NEED_BREAK) {
+			env.flags &= ~LBF_NEED_BREAK;
+			goto more_balance;
+		}
+
 		/*
 		 * Revisit (affine) tasks on src_cpu that couldn't be moved to
 		 * us and move them to an alternate dst_cpu in our sched_group
@@ -5100,14 +5152,17 @@ more_balance:
 		 * moreover subsequent load balance cycles should correct the
 		 * excess load moved.
 		 */
-		if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 &&
-				lb_iterations++ < max_lb_iterations) {
+		if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) {
 
 			env.dst_rq	 = cpu_rq(env.new_dst_cpu);
 			env.dst_cpu	 = env.new_dst_cpu;
 			env.flags	&= ~LBF_SOME_PINNED;
 			env.loop	 = 0;
 			env.loop_break	 = sched_nr_migrate_break;
+
+			/* Prevent to re-select dst_cpu via env's cpus */
+			cpumask_clear_cpu(env.dst_cpu, env.cpus);
+
 			/*
 			 * Go back to "more_balance" rather than "redo" since we
 			 * need to continue with same src_cpu.
@@ -5223,13 +5278,11 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
 
-	this_rq->idle_stamp = this_rq->clock;
+	this_rq->idle_stamp = rq_clock(this_rq);
 
 	if (this_rq->avg_idle < sysctl_sched_migration_cost)
 		return;
 
-	update_rq_runnable_avg(this_rq, 1);
-
 	/*
 	 * Drop the rq->lock, but keep IRQ/preempt disabled.
 	 */
@@ -5339,7 +5392,7 @@ out_unlock:
 	return 0;
 }
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 /*
  * idle load balancing details
  * - When one of the busy CPUs notice that there may be an idle rebalancing
@@ -5402,30 +5455,34 @@ static inline void nohz_balance_exit_idle(int cpu)
 static inline void set_cpu_sd_state_busy(void)
 {
 	struct sched_domain *sd;
-	int cpu = smp_processor_id();
-
-	if (!test_bit(NOHZ_IDLE, nohz_flags(cpu)))
-		return;
-	clear_bit(NOHZ_IDLE, nohz_flags(cpu));
 
 	rcu_read_lock();
-	for_each_domain(cpu, sd)
+	sd = rcu_dereference_check_sched_domain(this_rq()->sd);
+
+	if (!sd || !sd->nohz_idle)
+		goto unlock;
+	sd->nohz_idle = 0;
+
+	for (; sd; sd = sd->parent)
 		atomic_inc(&sd->groups->sgp->nr_busy_cpus);
+unlock:
 	rcu_read_unlock();
 }
 
 void set_cpu_sd_state_idle(void)
 {
 	struct sched_domain *sd;
-	int cpu = smp_processor_id();
-
-	if (test_bit(NOHZ_IDLE, nohz_flags(cpu)))
-		return;
-	set_bit(NOHZ_IDLE, nohz_flags(cpu));
 
 	rcu_read_lock();
-	for_each_domain(cpu, sd)
+	sd = rcu_dereference_check_sched_domain(this_rq()->sd);
+
+	if (!sd || sd->nohz_idle)
+		goto unlock;
+	sd->nohz_idle = 1;
+
+	for (; sd; sd = sd->parent)
 		atomic_dec(&sd->groups->sgp->nr_busy_cpus);
+unlock:
 	rcu_read_unlock();
 }
 
@@ -5477,7 +5534,7 @@ void update_max_interval(void)
  * 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.
+ * Balancing parameters are set up in init_sched_domains.
  */
 static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 {
@@ -5515,10 +5572,11 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		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.
+				 * The LBF_SOME_PINNED logic could have changed
+				 * env->dst_cpu, so we can't know our idle
+				 * state even if we migrated tasks. Update it.
 				 */
-				idle = CPU_NOT_IDLE;
+				idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
 			}
 			sd->last_balance = jiffies;
 		}
@@ -5549,9 +5607,9 @@ out:
 		rq->next_balance = next_balance;
 }
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 /*
- * In CONFIG_NO_HZ case, the idle balance kickee will do the
+ * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
  * rebalancing for all the cpus for whom scheduler ticks are stopped.
  */
 static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
@@ -5694,7 +5752,7 @@ void trigger_load_balance(struct rq *rq, int cpu)
 	if (time_after_eq(jiffies, rq->next_balance) &&
 	    likely(!on_null_domain(cpu)))
 		raise_softirq(SCHED_SOFTIRQ);
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 	if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
 		nohz_balancer_kick(cpu);
 #endif
@@ -5825,7 +5883,7 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 		se->vruntime -= cfs_rq->min_vruntime;
 	}
 
-#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	/*
 	* Remove our load from contribution when we leave sched_fair
 	* and ensure we don't carry in an old decay_count if we
@@ -5884,9 +5942,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 #ifndef CONFIG_64BIT
 	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
 #endif
-#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	atomic64_set(&cfs_rq->decay_counter, 1);
-	atomic64_set(&cfs_rq->removed_load, 0);
+	atomic_long_set(&cfs_rq->removed_load, 0);
 #endif
 }
 
@@ -6068,6 +6126,9 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 		se = tg->se[i];
 		/* Propagate contribution to hierarchy */
 		raw_spin_lock_irqsave(&rq->lock, flags);
+
+		/* Possible calls to update_curr() need rq clock */
+		update_rq_clock(rq);
 		for_each_sched_entity(se)
 			update_cfs_shares(group_cfs_rq(se));
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
@@ -6101,7 +6162,7 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
 	 * idle runqueue:
 	 */
 	if (rq->cfs.load.weight)
-		rr_interval = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
+		rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));
 
 	return rr_interval;
 }
@@ -6123,9 +6184,8 @@ const struct sched_class fair_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_fair,
-#ifdef CONFIG_FAIR_GROUP_SCHED
 	.migrate_task_rq	= migrate_task_rq_fair,
-#endif
+
 	.rq_online		= rq_online_fair,
 	.rq_offline		= rq_offline_fair,
 
@@ -6164,7 +6224,7 @@ __init void init_sched_fair_class(void)
 #ifdef CONFIG_SMP
 	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
 
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
 	nohz.next_balance = jiffies;
 	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
 	cpu_notifier(sched_ilb_notifier, 0);