Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The biggest change affects group scheduling: we now track the runnable
  average on a per-task entity basis, allowing a smoother, exponential
  decay average based load/weight estimation instead of the previous
  binary on-the-runqueue/off-the-runqueue load weight method.

  This will inevitably disturb workloads that were in some sort of
  borderline balancing state or unstable equilibrium, so an eye has to
  be kept on regressions.

  For that reason the new load average is only limited to group
  scheduling (shares distribution) at the moment (which was also hurting
  the most from the prior, crude weight calculation and whose scheduling
  quality wins most from this change) - but we plan to extend this to
  regular SMP balancing as well in the future, which will simplify and
  speed up things a bit.

  Other changes involve ongoing preparatory work to extend NOHZ to the
  scheduler as well, eventually allowing completely irq-free user-space
  execution."

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  Revert "sched/autogroup: Fix crash on reboot when autogroup is disabled"
  cputime: Comment cputime's adjusting code
  cputime: Consolidate cputime adjustment code
  cputime: Rename thread_group_times to thread_group_cputime_adjusted
  cputime: Move thread_group_cputime() to sched code
  vtime: Warn if irqs aren't disabled on system time accounting APIs
  vtime: No need to disable irqs on vtime_account()
  vtime: Consolidate a bit the ctx switch code
  vtime: Explicitly account pending user time on process tick
  vtime: Remove the underscore prefix invasion
  sched/autogroup: Fix crash on reboot when autogroup is disabled
  cputime: Separate irqtime accounting from generic vtime
  cputime: Specialize irq vtime hooks
  kvm: Directly account vtime to system on guest switch
  vtime: Make vtime_account_system() irqsafe
  vtime: Gather vtime declarations to their own header file
  sched: Describe CFS load-balancer
  sched: Introduce temporary FAIR_GROUP_SCHED dependency for load-tracking
  sched: Make __update_entity_runnable_avg() fast
  sched: Update_cfs_shares at period edge
  ...

13 files changed, 938 insertions, 270 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 346616c0092c..618f7ee56003 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1186,11 +1186,11 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * as other threads in the parent group can be right
 		 * here reaping other children at the same time.
 		 *
-		 * We use thread_group_times() to get times for the thread
+		 * We use thread_group_cputime_adjusted() to get times for the thread
 		 * group, which consolidates times for all threads in the
 		 * group including the group leader.
 		 */
-		thread_group_times(p, &tgutime, &tgstime);
+		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
 		spin_lock_irq(&p->real_parent->sighand->siglock);
 		psig = p->real_parent->signal;
 		sig = p->signal;
diff --git a/kernel/fork.c b/kernel/fork.c
index c497e57aa654..850dde1e0c84 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1224,7 +1224,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->utime = p->stime = p->gtime = 0;
 	p->utimescaled = p->stimescaled = 0;
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	p->prev_utime = p->prev_stime = 0;
+	p->prev_cputime.utime = p->prev_cputime.stime = 0;
 #endif
 #if defined(SPLIT_RSS_COUNTING)
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 125cb67daa21..d73840271dce 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -217,30 +217,6 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 	return 0;
 }
 
-void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
-{
-	struct signal_struct *sig = tsk->signal;
-	struct task_struct *t;
-
-	times->utime = sig->utime;
-	times->stime = sig->stime;
-	times->sum_exec_runtime = sig->sum_sched_runtime;
-
-	rcu_read_lock();
-	/* make sure we can trust tsk->thread_group list */
-	if (!likely(pid_alive(tsk)))
-		goto out;
-
-	t = tsk;
-	do {
-		times->utime += t->utime;
-		times->stime += t->stime;
-		times->sum_exec_runtime += task_sched_runtime(t);
-	} while_each_thread(tsk, t);
-out:
-	rcu_read_unlock();
-}
-
 static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
 {
 	if (b->utime > a->utime)
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 15f60d01198b..0984a21076a3 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -143,11 +143,15 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 
 	p->signal->autogroup = autogroup_kref_get(ag);
 
+	if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+		goto out;
+
 	t = p;
 	do {
 		sched_move_task(t);
 	} while_each_thread(p, t);
 
+out:
 	unlock_task_sighand(p, &flags);
 	autogroup_kref_put(prev);
 }
diff --git a/kernel/sched/auto_group.h b/kernel/sched/auto_group.h
index 443232ebbb53..8bd047142816 100644
--- a/kernel/sched/auto_group.h
+++ b/kernel/sched/auto_group.h
@@ -4,6 +4,11 @@
 #include <linux/rwsem.h>
 
 struct autogroup {
+	/*
+	 * reference doesn't mean how many thread attach to this
+	 * autogroup now. It just stands for the number of task
+	 * could use this autogroup.
+	 */
 	struct kref		kref;
 	struct task_group	*tg;
 	struct rw_semaphore	lock;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 80f80dfca70e..f5066a61f971 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -953,6 +953,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	trace_sched_migrate_task(p, new_cpu);
 
 	if (task_cpu(p) != new_cpu) {
+		if (p->sched_class->migrate_task_rq)
+			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
 		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
 	}
@@ -1525,6 +1527,15 @@ static void __sched_fork(struct task_struct *p)
 	p->se.vruntime			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+/*
+ * 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).
+ */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+	p->se.avg.runnable_avg_period = 0;
+	p->se.avg.runnable_avg_sum = 0;
+#endif
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 81b763ba58a6..293b202fcf79 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -43,7 +43,7 @@ DEFINE_PER_CPU(seqcount_t, irq_time_seq);
  * Called before incrementing preempt_count on {soft,}irq_enter
  * and before decrementing preempt_count on {soft,}irq_exit.
  */
-void vtime_account(struct task_struct *curr)
+void irqtime_account_irq(struct task_struct *curr)
 {
 	unsigned long flags;
 	s64 delta;
@@ -73,7 +73,7 @@ void vtime_account(struct task_struct *curr)
 	irq_time_write_end();
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(vtime_account);
+EXPORT_SYMBOL_GPL(irqtime_account_irq);
 
 static int irqtime_account_hi_update(void)
 {
@@ -288,6 +288,34 @@ static __always_inline bool steal_account_process_tick(void)
 	return false;
 }
 
+/*
+ * Accumulate raw cputime values of dead tasks (sig->[us]time) and live
+ * tasks (sum on group iteration) belonging to @tsk's group.
+ */
+void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
+{
+	struct signal_struct *sig = tsk->signal;
+	struct task_struct *t;
+
+	times->utime = sig->utime;
+	times->stime = sig->stime;
+	times->sum_exec_runtime = sig->sum_sched_runtime;
+
+	rcu_read_lock();
+	/* make sure we can trust tsk->thread_group list */
+	if (!likely(pid_alive(tsk)))
+		goto out;
+
+	t = tsk;
+	do {
+		times->utime += t->utime;
+		times->stime += t->stime;
+		times->sum_exec_runtime += task_sched_runtime(t);
+	} while_each_thread(tsk, t);
+out:
+	rcu_read_unlock();
+}
+
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -417,13 +445,13 @@ void account_idle_ticks(unsigned long ticks)
  * Use precise platform statistics if available:
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	*ut = p->utime;
 	*st = p->stime;
 }
 
-void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	struct task_cputime cputime;
 
@@ -433,6 +461,29 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	*st = cputime.stime;
 }
 
+void vtime_account_system_irqsafe(struct task_struct *tsk)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	vtime_account_system(tsk);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(vtime_account_system_irqsafe);
+
+#ifndef __ARCH_HAS_VTIME_TASK_SWITCH
+void vtime_task_switch(struct task_struct *prev)
+{
+	if (is_idle_task(prev))
+		vtime_account_idle(prev);
+	else
+		vtime_account_system(prev);
+
+	vtime_account_user(prev);
+	arch_vtime_task_switch(prev);
+}
+#endif
+
 /*
  * Archs that account the whole time spent in the idle task
  * (outside irq) as idle time can rely on this and just implement
@@ -444,16 +495,10 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 #ifndef __ARCH_HAS_VTIME_ACCOUNT
 void vtime_account(struct task_struct *tsk)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-
 	if (in_interrupt() || !is_idle_task(tsk))
 		vtime_account_system(tsk);
 	else
 		vtime_account_idle(tsk);
-
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(vtime_account);
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */
@@ -478,14 +523,30 @@ static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
 	return (__force cputime_t) temp;
 }
 
-void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+/*
+ * Adjust tick based cputime random precision against scheduler
+ * runtime accounting.
+ */
+static void cputime_adjust(struct task_cputime *curr,
+			   struct cputime *prev,
+			   cputime_t *ut, cputime_t *st)
 {
-	cputime_t rtime, utime = p->utime, total = utime + p->stime;
+	cputime_t rtime, utime, total;
+
+	utime = curr->utime;
+	total = utime + curr->stime;
 
 	/*
-	 * Use CFS's precise accounting:
+	 * Tick based cputime accounting depend on random scheduling
+	 * timeslices of a task to be interrupted or not by the timer.
+	 * Depending on these circumstances, the number of these interrupts
+	 * may be over or under-optimistic, matching the real user and system
+	 * cputime with a variable precision.
+	 *
+	 * Fix this by scaling these tick based values against the total
+	 * runtime accounted by the CFS scheduler.
 	 */
-	rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
+	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
 
 	if (total)
 		utime = scale_utime(utime, rtime, total);
@@ -493,38 +554,36 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 		utime = rtime;
 
 	/*
-	 * Compare with previous values, to keep monotonicity:
+	 * If the tick based count grows faster than the scheduler one,
+	 * the result of the scaling may go backward.
+	 * Let's enforce monotonicity.
 	 */
-	p->prev_utime = max(p->prev_utime, utime);
-	p->prev_stime = max(p->prev_stime, rtime - p->prev_utime);
+	prev->utime = max(prev->utime, utime);
+	prev->stime = max(prev->stime, rtime - prev->utime);
 
-	*ut = p->prev_utime;
-	*st = p->prev_stime;
+	*ut = prev->utime;
+	*st = prev->stime;
+}
+
+void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	struct task_cputime cputime = {
+		.utime = p->utime,
+		.stime = p->stime,
+		.sum_exec_runtime = p->se.sum_exec_runtime,
+	};
+
+	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 
 /*
  * Must be called with siglock held.
  */
-void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
-	struct signal_struct *sig = p->signal;
 	struct task_cputime cputime;
-	cputime_t rtime, utime, total;
 
 	thread_group_cputime(p, &cputime);
-
-	total = cputime.utime + cputime.stime;
-	rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
-
-	if (total)
-		utime = scale_utime(cputime.utime, rtime, total);
-	else
-		utime = rtime;
-
-	sig->prev_utime = max(sig->prev_utime, utime);
-	sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime);
-
-	*ut = sig->prev_utime;
-	*st = sig->prev_stime;
+	cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st);
 }
 #endif
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 6f79596e0ea9..2cd3c1b4e582 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -61,14 +61,20 @@ static unsigned long nsec_low(unsigned long long nsec)
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
 	struct sched_entity *se = tg->se[cpu];
-	if (!se)
-		return;
 
 #define P(F) \
 	SEQ_printf(m, "  .%-30s: %lld\n", #F, (long long)F)
 #define PN(F) \
 	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
 
+	if (!se) {
+		struct sched_avg *avg = &cpu_rq(cpu)->avg;
+		P(avg->runnable_avg_sum);
+		P(avg->runnable_avg_period);
+		return;
+	}
+
+
 	PN(se->exec_start);
 	PN(se->vruntime);
 	PN(se->sum_exec_runtime);
@@ -85,6 +91,12 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	P(se->statistics.wait_count);
 #endif
 	P(se->load.weight);
+#ifdef CONFIG_SMP
+	P(se->avg.runnable_avg_sum);
+	P(se->avg.runnable_avg_period);
+	P(se->avg.load_avg_contrib);
+	P(se->avg.decay_count);
+#endif
 #undef PN
 #undef P
 }
@@ -206,14 +218,18 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_SMP
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_avg",
-			SPLIT_NS(cfs_rq->load_avg));
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_period",
-			SPLIT_NS(cfs_rq->load_period));
-	SEQ_printf(m, "  .%-30s: %ld\n", "load_contrib",
-			cfs_rq->load_contribution);
-	SEQ_printf(m, "  .%-30s: %d\n", "load_tg",
-			atomic_read(&cfs_rq->tg->load_weight));
+	SEQ_printf(m, "  .%-30s: %lld\n", "runnable_load_avg",
+			cfs_rq->runnable_load_avg);
+	SEQ_printf(m, "  .%-30s: %lld\n", "blocked_load_avg",
+			cfs_rq->blocked_load_avg);
+	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_avg",
+			atomic64_read(&cfs_rq->tg->load_avg));
+	SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_contrib",
+			cfs_rq->tg_load_contrib);
+	SEQ_printf(m, "  .%-30s: %d\n", "tg_runnable_contrib",
+			cfs_rq->tg_runnable_contrib);
+	SEQ_printf(m, "  .%-30s: %d\n", "tg->runnable_avg",
+			atomic_read(&cfs_rq->tg->runnable_avg));
 #endif
 
 	print_cfs_group_stats(m, cpu, cfs_rq->tg);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6b800a14b990..59e072b2db97 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -259,6 +259,9 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
 	return grp->my_q;
 }
 
+static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq,
+				       int force_update);
+
 static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	if (!cfs_rq->on_list) {
@@ -278,6 +281,8 @@ static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 		}
 
 		cfs_rq->on_list = 1;
+		/* We should have no load, but we need to update last_decay. */
+		update_cfs_rq_blocked_load(cfs_rq, 0);
 	}
 }
 
@@ -653,9 +658,6 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	return calc_delta_fair(sched_slice(cfs_rq, se), se);
 }
 
-static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
-static void update_cfs_shares(struct cfs_rq *cfs_rq);
-
 /*
  * Update the current task's runtime statistics. Skip current tasks that
  * are not in our scheduling class.
@@ -675,10 +677,6 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 
 	curr->vruntime += delta_exec_weighted;
 	update_min_vruntime(cfs_rq);
-
-#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
-	cfs_rq->load_unacc_exec_time += delta_exec;
-#endif
 }
 
 static void update_curr(struct cfs_rq *cfs_rq)
@@ -801,72 +799,7 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-/* we need this in update_cfs_load and load-balance functions below */
-static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
 # ifdef CONFIG_SMP
-static void update_cfs_rq_load_contribution(struct cfs_rq *cfs_rq,
-					    int global_update)
-{
-	struct task_group *tg = cfs_rq->tg;
-	long load_avg;
-
-	load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1);
-	load_avg -= cfs_rq->load_contribution;
-
-	if (global_update || abs(load_avg) > cfs_rq->load_contribution / 8) {
-		atomic_add(load_avg, &tg->load_weight);
-		cfs_rq->load_contribution += load_avg;
-	}
-}
-
-static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
-{
-	u64 period = sysctl_sched_shares_window;
-	u64 now, delta;
-	unsigned long load = cfs_rq->load.weight;
-
-	if (cfs_rq->tg == &root_task_group || throttled_hierarchy(cfs_rq))
-		return;
-
-	now = rq_of(cfs_rq)->clock_task;
-	delta = now - cfs_rq->load_stamp;
-
-	/* truncate load history at 4 idle periods */
-	if (cfs_rq->load_stamp > cfs_rq->load_last &&
-	    now - cfs_rq->load_last > 4 * period) {
-		cfs_rq->load_period = 0;
-		cfs_rq->load_avg = 0;
-		delta = period - 1;
-	}
-
-	cfs_rq->load_stamp = now;
-	cfs_rq->load_unacc_exec_time = 0;
-	cfs_rq->load_period += delta;
-	if (load) {
-		cfs_rq->load_last = now;
-		cfs_rq->load_avg += delta * load;
-	}
-
-	/* consider updating load contribution on each fold or truncate */
-	if (global_update || cfs_rq->load_period > period
-	    || !cfs_rq->load_period)
-		update_cfs_rq_load_contribution(cfs_rq, global_update);
-
-	while (cfs_rq->load_period > period) {
-		/*
-		 * Inline assembly required to prevent the compiler
-		 * optimising this loop into a divmod call.
-		 * See __iter_div_u64_rem() for another example of this.
-		 */
-		asm("" : "+rm" (cfs_rq->load_period));
-		cfs_rq->load_period /= 2;
-		cfs_rq->load_avg /= 2;
-	}
-
-	if (!cfs_rq->curr && !cfs_rq->nr_running && !cfs_rq->load_avg)
-		list_del_leaf_cfs_rq(cfs_rq);
-}
-
 static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
 {
 	long tg_weight;
@@ -876,8 +809,8 @@ 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 = atomic_read(&tg->load_weight);
-	tg_weight -= cfs_rq->load_contribution;
+	tg_weight = atomic64_read(&tg->load_avg);
+	tg_weight -= cfs_rq->tg_load_contrib;
 	tg_weight += cfs_rq->load.weight;
 
 	return tg_weight;
@@ -901,27 +834,11 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 
 	return shares;
 }
-
-static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
-{
-	if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
-		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq);
-	}
-}
 # else /* CONFIG_SMP */
-static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
-{
-}
-
 static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
 	return tg->shares;
 }
-
-static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
-{
-}
 # endif /* CONFIG_SMP */
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
@@ -939,6 +856,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		account_entity_enqueue(cfs_rq, se);
 }
 
+static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
+
 static void update_cfs_shares(struct cfs_rq *cfs_rq)
 {
 	struct task_group *tg;
@@ -958,18 +877,478 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq)
 	reweight_entity(cfs_rq_of(se), se, shares);
 }
 #else /* CONFIG_FAIR_GROUP_SCHED */
-static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 {
 }
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
+/* Only depends on SMP, FAIR_GROUP_SCHED may be removed when useful in lb */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+/*
+ * We choose a half-life close to 1 scheduling period.
+ * Note: The tables below are dependent on this value.
+ */
+#define LOAD_AVG_PERIOD 32
+#define LOAD_AVG_MAX 47742 /* maximum possible load avg */
+#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_MAX_AVG */
+
+/* Precomputed fixed inverse multiplies for multiplication by y^n */
+static const u32 runnable_avg_yN_inv[] = {
+	0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
+	0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
+	0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,
+	0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9,
+	0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80,
+	0x85aac367, 0x82cd8698,
+};
+
+/*
+ * Precomputed \Sum y^k { 1<=k<=n }.  These are floor(true_value) to prevent
+ * over-estimates when re-combining.
+ */
+static const u32 runnable_avg_yN_sum[] = {
+	    0, 1002, 1982, 2941, 3880, 4798, 5697, 6576, 7437, 8279, 9103,
+	 9909,10698,11470,12226,12966,13690,14398,15091,15769,16433,17082,
+	17718,18340,18949,19545,20128,20698,21256,21802,22336,22859,23371,
+};
+
+/*
+ * Approximate:
+ *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
+ */
+static __always_inline u64 decay_load(u64 val, u64 n)
 {
+	unsigned int local_n;
+
+	if (!n)
+		return val;
+	else if (unlikely(n > LOAD_AVG_PERIOD * 63))
+		return 0;
+
+	/* after bounds checking we can collapse to 32-bit */
+	local_n = n;
+
+	/*
+	 * As y^PERIOD = 1/2, we can combine
+	 *    y^n = 1/2^(n/PERIOD) * k^(n%PERIOD)
+	 * With a look-up table which covers k^n (n<PERIOD)
+	 *
+	 * To achieve constant time decay_load.
+	 */
+	if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
+		val >>= local_n / LOAD_AVG_PERIOD;
+		local_n %= LOAD_AVG_PERIOD;
+	}
+
+	val *= runnable_avg_yN_inv[local_n];
+	/* We don't use SRR here since we always want to round down. */
+	return val >> 32;
 }
 
-static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
+/*
+ * For updates fully spanning n periods, the contribution to runnable
+ * average will be: \Sum 1024*y^n
+ *
+ * We can compute this reasonably efficiently by combining:
+ *   y^PERIOD = 1/2 with precomputed \Sum 1024*y^n {for  n <PERIOD}
+ */
+static u32 __compute_runnable_contrib(u64 n)
 {
+	u32 contrib = 0;
+
+	if (likely(n <= LOAD_AVG_PERIOD))
+		return runnable_avg_yN_sum[n];
+	else if (unlikely(n >= LOAD_AVG_MAX_N))
+		return LOAD_AVG_MAX;
+
+	/* Compute \Sum k^n combining precomputed values for k^i, \Sum k^j */
+	do {
+		contrib /= 2; /* y^LOAD_AVG_PERIOD = 1/2 */
+		contrib += runnable_avg_yN_sum[LOAD_AVG_PERIOD];
+
+		n -= LOAD_AVG_PERIOD;
+	} while (n > LOAD_AVG_PERIOD);
+
+	contrib = decay_load(contrib, n);
+	return contrib + runnable_avg_yN_sum[n];
 }
-#endif /* CONFIG_FAIR_GROUP_SCHED */
+
+/*
+ * We can represent the historical contribution to runnable average as the
+ * coefficients of a geometric series.  To do this we sub-divide our runnable
+ * history into segments of approximately 1ms (1024us); label the segment that
+ * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
+ *
+ * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
+ *      p0            p1           p2
+ *     (now)       (~1ms ago)  (~2ms ago)
+ *
+ * Let u_i denote the fraction of p_i that the entity was runnable.
+ *
+ * We then designate the fractions u_i as our co-efficients, yielding the
+ * following representation of historical load:
+ *   u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
+ *
+ * We choose y based on the with of a reasonably scheduling period, fixing:
+ *   y^32 = 0.5
+ *
+ * This means that the contribution to load ~32ms ago (u_32) will be weighted
+ * approximately half as much as the contribution to load within the last ms
+ * (u_0).
+ *
+ * When a period "rolls over" and we have new u_0`, multiplying the previous
+ * sum again by y is sufficient to update:
+ *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
+ *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
+ */
+static __always_inline int __update_entity_runnable_avg(u64 now,
+							struct sched_avg *sa,
+							int runnable)
+{
+	u64 delta, periods;
+	u32 runnable_contrib;
+	int delta_w, decayed = 0;
+
+	delta = now - sa->last_runnable_update;
+	/*
+	 * This should only happen when time goes backwards, which it
+	 * unfortunately does during sched clock init when we swap over to TSC.
+	 */
+	if ((s64)delta < 0) {
+		sa->last_runnable_update = now;
+		return 0;
+	}
+
+	/*
+	 * Use 1024ns as the unit of measurement since it's a reasonable
+	 * approximation of 1us and fast to compute.
+	 */
+	delta >>= 10;
+	if (!delta)
+		return 0;
+	sa->last_runnable_update = now;
+
+	/* delta_w is the amount already accumulated against our next period */
+	delta_w = sa->runnable_avg_period % 1024;
+	if (delta + delta_w >= 1024) {
+		/* period roll-over */
+		decayed = 1;
+
+		/*
+		 * Now that we know we're crossing a period boundary, figure
+		 * out how much from delta we need to complete the current
+		 * period and accrue it.
+		 */
+		delta_w = 1024 - delta_w;
+		if (runnable)
+			sa->runnable_avg_sum += delta_w;
+		sa->runnable_avg_period += delta_w;
+
+		delta -= delta_w;
+
+		/* Figure out how many additional periods this update spans */
+		periods = delta / 1024;
+		delta %= 1024;
+
+		sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
+						  periods + 1);
+		sa->runnable_avg_period = decay_load(sa->runnable_avg_period,
+						     periods + 1);
+
+		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
+		runnable_contrib = __compute_runnable_contrib(periods);
+		if (runnable)
+			sa->runnable_avg_sum += runnable_contrib;
+		sa->runnable_avg_period += runnable_contrib;
+	}
+
+	/* Remainder of delta accrued against u_0` */
+	if (runnable)
+		sa->runnable_avg_sum += delta;
+	sa->runnable_avg_period += delta;
+
+	return decayed;
+}
+
+/* Synchronize an entity's decay with its parenting cfs_rq.*/
+static inline u64 __synchronize_entity_decay(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	u64 decays = atomic64_read(&cfs_rq->decay_counter);
+
+	decays -= se->avg.decay_count;
+	if (!decays)
+		return 0;
+
+	se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
+	se->avg.decay_count = 0;
+
+	return decays;
+}
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+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;
+
+	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);
+		cfs_rq->tg_load_contrib += tg_contrib;
+	}
+}
+
+/*
+ * Aggregate cfs_rq runnable averages into an equivalent task_group
+ * representation for computing load contributions.
+ */
+static inline void __update_tg_runnable_avg(struct sched_avg *sa,
+						  struct cfs_rq *cfs_rq)
+{
+	struct task_group *tg = cfs_rq->tg;
+	long contrib;
+
+	/* The fraction of a cpu used by this cfs_rq */
+	contrib = div_u64(sa->runnable_avg_sum << NICE_0_SHIFT,
+			  sa->runnable_avg_period + 1);
+	contrib -= cfs_rq->tg_runnable_contrib;
+
+	if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
+		atomic_add(contrib, &tg->runnable_avg);
+		cfs_rq->tg_runnable_contrib += contrib;
+	}
+}
+
+static inline void __update_group_entity_contrib(struct sched_entity *se)
+{
+	struct cfs_rq *cfs_rq = group_cfs_rq(se);
+	struct task_group *tg = cfs_rq->tg;
+	int runnable_avg;
+
+	u64 contrib;
+
+	contrib = cfs_rq->tg_load_contrib * tg->shares;
+	se->avg.load_avg_contrib = div64_u64(contrib,
+					     atomic64_read(&tg->load_avg) + 1);
+
+	/*
+	 * For group entities we need to compute a correction term in the case
+	 * that they are consuming <1 cpu so that we would contribute the same
+	 * load as a task of equal weight.
+	 *
+	 * Explicitly co-ordinating this measurement would be expensive, but
+	 * fortunately the sum of each cpus contribution forms a usable
+	 * lower-bound on the true value.
+	 *
+	 * Consider the aggregate of 2 contributions.  Either they are disjoint
+	 * (and the sum represents true value) or they are disjoint and we are
+	 * understating by the aggregate of their overlap.
+	 *
+	 * Extending this to N cpus, for a given overlap, the maximum amount we
+	 * understand is then n_i(n_i+1)/2 * w_i where n_i is the number of
+	 * cpus that overlap for this interval and w_i is the interval width.
+	 *
+	 * On a small machine; the first term is well-bounded which bounds the
+	 * total error since w_i is a subset of the period.  Whereas on a
+	 * larger machine, while this first term can be larger, if w_i is the
+	 * of consequential size guaranteed to see n_i*w_i quickly converge to
+	 * our upper bound of 1-cpu.
+	 */
+	runnable_avg = atomic_read(&tg->runnable_avg);
+	if (runnable_avg < NICE_0_LOAD) {
+		se->avg.load_avg_contrib *= runnable_avg;
+		se->avg.load_avg_contrib >>= NICE_0_SHIFT;
+	}
+}
+#else
+static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
+						 int force_update) {}
+static inline void __update_tg_runnable_avg(struct sched_avg *sa,
+						  struct cfs_rq *cfs_rq) {}
+static inline void __update_group_entity_contrib(struct sched_entity *se) {}
+#endif
+
+static inline void __update_task_entity_contrib(struct sched_entity *se)
+{
+	u32 contrib;
+
+	/* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
+	contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);
+	contrib /= (se->avg.runnable_avg_period + 1);
+	se->avg.load_avg_contrib = scale_load(contrib);
+}
+
+/* Compute the current contribution to load_avg by se, return any delta */
+static long __update_entity_load_avg_contrib(struct sched_entity *se)
+{
+	long old_contrib = se->avg.load_avg_contrib;
+
+	if (entity_is_task(se)) {
+		__update_task_entity_contrib(se);
+	} else {
+		__update_tg_runnable_avg(&se->avg, group_cfs_rq(se));
+		__update_group_entity_contrib(se);
+	}
+
+	return se->avg.load_avg_contrib - old_contrib;
+}
+
+static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq,
+						 long load_contrib)
+{
+	if (likely(load_contrib < cfs_rq->blocked_load_avg))
+		cfs_rq->blocked_load_avg -= load_contrib;
+	else
+		cfs_rq->blocked_load_avg = 0;
+}
+
+static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
+
+/* Update a sched_entity's runnable average */
+static inline void update_entity_load_avg(struct sched_entity *se,
+					  int update_cfs_rq)
+{
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	long contrib_delta;
+	u64 now;
+
+	/*
+	 * For a group entity we need to use their owned cfs_rq_clock_task() in
+	 * case they are the parent of a throttled hierarchy.
+	 */
+	if (entity_is_task(se))
+		now = cfs_rq_clock_task(cfs_rq);
+	else
+		now = cfs_rq_clock_task(group_cfs_rq(se));
+
+	if (!__update_ent