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 in this cycle is the rewrite of the main SMP load
  balancing metric: the CPU load/utilization.  The main goal was to make
  the metric more precise and more representative - see the changelog of
  this commit for the gory details:

    9d89c257dfb9 ("sched/fair: Rewrite runnable load and utilization average tracking")

  It is done in a way that significantly reduces complexity of the code:

    5 files changed, 249 insertions(+), 494 deletions(-)

  and the performance testing results are encouraging.  Nevertheless we
  need to keep an eye on potential regressions, since this potentially
  affects every SMP workload in existence.

  This work comes from Yuyang Du.

  Other changes:

   - SCHED_DL updates.  (Andrea Parri)

   - Simplify architecture callbacks by removing finish_arch_switch().
     (Peter Zijlstra et al)

   - cputime accounting: guarantee stime + utime == rtime.  (Peter
     Zijlstra)

   - optimize idle CPU wakeups some more - inspired by Facebook server
     loads.  (Mike Galbraith)

   - stop_machine fixes and updates.  (Oleg Nesterov)

   - Introduce the 'trace_sched_waking' tracepoint.  (Peter Zijlstra)

   - sched/numa tweaks.  (Srikar Dronamraju)

   - misc fixes and small cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  sched/deadline: Fix comment in enqueue_task_dl()
  sched/deadline: Fix comment in push_dl_tasks()
  sched: Change the sched_class::set_cpus_allowed() calling context
  sched: Make sched_class::set_cpus_allowed() unconditional
  sched: Fix a race between __kthread_bind() and sched_setaffinity()
  sched: Ensure a task has a non-normalized vruntime when returning back to CFS
  sched/numa: Fix NUMA_DIRECT topology identification
  tile: Reorganize _switch_to()
  sched, sparc32: Update scheduler comments in copy_thread()
  sched: Remove finish_arch_switch()
  sched, tile: Remove finish_arch_switch
  sched, sh: Fold finish_arch_switch() into switch_to()
  sched, score: Remove finish_arch_switch()
  sched, avr32: Remove finish_arch_switch()
  sched, MIPS: Get rid of finish_arch_switch()
  sched, arm: Remove finish_arch_switch()
  sched/fair: Clean up load average references
  sched/fair: Provide runnable_load_avg back to cfs_rq
  sched/fair: Remove task and group entity load when they are dead
  sched/fair: Init cfs_rq's sched_entity load average
  ...

11 files changed, 562 insertions, 780 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5e73c79fadd0..a585c7b2ccf0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1151,15 +1151,45 @@ static int migration_cpu_stop(void *data)
 	return 0;
 }
 
-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+/*
+ * sched_class::set_cpus_allowed must do the below, but is not required to
+ * actually call this function.
+ */
+void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask)
 {
-	if (p->sched_class->set_cpus_allowed)
-		p->sched_class->set_cpus_allowed(p, new_mask);
-
 	cpumask_copy(&p->cpus_allowed, new_mask);
 	p->nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+	struct rq *rq = task_rq(p);
+	bool queued, running;
+
+	lockdep_assert_held(&p->pi_lock);
+
+	queued = task_on_rq_queued(p);
+	running = task_current(rq, p);
+
+	if (queued) {
+		/*
+		 * Because __kthread_bind() calls this on blocked tasks without
+		 * holding rq->lock.
+		 */
+		lockdep_assert_held(&rq->lock);
+		dequeue_task(rq, p, 0);
+	}
+	if (running)
+		put_prev_task(rq, p);
+
+	p->sched_class->set_cpus_allowed(p, new_mask);
+
+	if (running)
+		p->sched_class->set_curr_task(rq);
+	if (queued)
+		enqueue_task(rq, p, 0);
+}
+
 /*
  * Change a given task's CPU affinity. Migrate the thread to a
  * proper CPU and schedule it away if the CPU it's executing on
@@ -1169,7 +1199,8 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
  * task must not exit() & deallocate itself prematurely. The
  * call is not atomic; no spinlocks may be held.
  */
-int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
+static int __set_cpus_allowed_ptr(struct task_struct *p,
+				  const struct cpumask *new_mask, bool check)
 {
 	unsigned long flags;
 	struct rq *rq;
@@ -1178,6 +1209,15 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 
 	rq = task_rq_lock(p, &flags);
 
+	/*
+	 * Must re-check here, to close a race against __kthread_bind(),
+	 * sched_setaffinity() is not guaranteed to observe the flag.
+	 */
+	if (check && (p->flags & PF_NO_SETAFFINITY)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (cpumask_equal(&p->cpus_allowed, new_mask))
 		goto out;
 
@@ -1214,6 +1254,11 @@ out:
 
 	return ret;
 }
+
+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
+{
+	return __set_cpus_allowed_ptr(p, new_mask, false);
+}
 EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
@@ -1595,6 +1640,15 @@ static void update_avg(u64 *avg, u64 sample)
 	s64 diff = sample - *avg;
 	*avg += diff >> 3;
 }
+
+#else
+
+static inline int __set_cpus_allowed_ptr(struct task_struct *p,
+					 const struct cpumask *new_mask, bool check)
+{
+	return set_cpus_allowed_ptr(p, new_mask);
+}
+
 #endif /* CONFIG_SMP */
 
 static void
@@ -1654,9 +1708,9 @@ static void
 ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 {
 	check_preempt_curr(rq, p, wake_flags);
-	trace_sched_wakeup(p, true);
-
 	p->state = TASK_RUNNING;
+	trace_sched_wakeup(p);
+
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken) {
 		/*
@@ -1874,6 +1928,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	if (!(p->state & state))
 		goto out;
 
+	trace_sched_waking(p);
+
 	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
 
@@ -1949,6 +2005,8 @@ static void try_to_wake_up_local(struct task_struct *p)
 	if (!(p->state & TASK_NORMAL))
 		goto out;
 
+	trace_sched_waking(p);
+
 	if (!task_on_rq_queued(p))
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
@@ -2016,9 +2074,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
 	p->se.vruntime			= 0;
-#ifdef CONFIG_SMP
-	p->se.avg.decay_count		= 0;
-#endif
 	INIT_LIST_HEAD(&p->se.group_node);
 
 #ifdef CONFIG_SCHEDSTATS
@@ -2303,11 +2358,11 @@ void wake_up_new_task(struct task_struct *p)
 #endif
 
 	/* Initialize new task's runnable average */
-	init_task_runnable_average(p);
+	init_entity_runnable_average(&p->se);
 	rq = __task_rq_lock(p);
 	activate_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_QUEUED;
-	trace_sched_wakeup_new(p, true);
+	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken)
@@ -2469,7 +2524,6 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 */
 	prev_state = prev->state;
 	vtime_task_switch(prev);
-	finish_arch_switch(prev);
 	perf_event_task_sched_in(prev, current);
 	finish_lock_switch(rq, prev);
 	finish_arch_post_lock_switch();
@@ -4340,7 +4394,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	}
 #endif
 again:
-	retval = set_cpus_allowed_ptr(p, new_mask);
+	retval = __set_cpus_allowed_ptr(p, new_mask, true);
 
 	if (!retval) {
 		cpuset_cpus_allowed(p, cpus_allowed);
@@ -4492,7 +4546,7 @@ SYSCALL_DEFINE0(sched_yield)
 
 int __sched _cond_resched(void)
 {
-	if (should_resched()) {
+	if (should_resched(0)) {
 		preempt_schedule_common();
 		return 1;
 	}
@@ -4510,7 +4564,7 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
-	int resched = should_resched();
+	int resched = should_resched(PREEMPT_LOCK_OFFSET);
 	int ret = 0;
 
 	lockdep_assert_held(lock);
@@ -4532,7 +4586,7 @@ int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	if (should_resched()) {
+	if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
 		local_bh_enable();
 		preempt_schedule_common();
 		local_bh_disable();
@@ -4865,7 +4919,8 @@ void init_idle(struct task_struct *idle, int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	raw_spin_lock_irqsave(&idle->pi_lock, flags);
+	raw_spin_lock(&rq->lock);
 
 	__sched_fork(0, idle);
 	idle->state = TASK_RUNNING;
@@ -4891,7 +4946,8 @@ void init_idle(struct task_struct *idle, int cpu)
 #if defined(CONFIG_SMP)
 	idle->on_cpu = 1;
 #endif
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_unlock(&rq->lock);
+	raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
 
 	/* Set the preempt count _outside_ the spinlocks! */
 	init_idle_preempt_count(idle, cpu);
@@ -5311,8 +5367,7 @@ static void register_sched_domain_sysctl(void)
 /* may be called multiple times per register */
 static void unregister_sched_domain_sysctl(void)
 {
-	if (sd_sysctl_header)
-		unregister_sysctl_table(sd_sysctl_header);
+	unregister_sysctl_table(sd_sysctl_header);
 	sd_sysctl_header = NULL;
 	if (sd_ctl_dir[0].child)
 		sd_free_ctl_entry(&sd_ctl_dir[0].child);
@@ -6445,8 +6500,10 @@ static void init_numa_topology_type(void)
 
 	n = sched_max_numa_distance;
 
-	if (n <= 1)
+	if (sched_domains_numa_levels <= 1) {
 		sched_numa_topology_type = NUMA_DIRECT;
+		return;
+	}
 
 	for_each_online_node(a) {
 		for_each_online_node(b) {
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index f5a64ffad176..8cbc3db671df 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -555,48 +555,43 @@ drop_precision:
 }
 
 /*
- * Atomically advance counter to the new value. Interrupts, vcpu
- * scheduling, and scaling inaccuracies can cause cputime_advance
- * to be occasionally called with a new value smaller than counter.
- * Let's enforce atomicity.
+ * Adjust tick based cputime random precision against scheduler runtime
+ * accounting.
  *
- * Normally a caller will only go through this loop once, or not
- * at all in case a previous caller updated counter the same jiffy.
- */
-static void cputime_advance(cputime_t *counter, cputime_t new)
-{
-	cputime_t old;
-
-	while (new > (old = READ_ONCE(*counter)))
-		cmpxchg_cputime(counter, old, new);
-}
-
-/*
- * Adjust tick based cputime random precision against scheduler
- * runtime 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.
+ *
+ * This code provides the following guarantees:
+ *
+ *   stime + utime == rtime
+ *   stime_i+1 >= stime_i, utime_i+1 >= utime_i
+ *
+ * Assuming that rtime_i+1 >= rtime_i.
  */
 static void cputime_adjust(struct task_cputime *curr,
-			   struct cputime *prev,
+			   struct prev_cputime *prev,
 			   cputime_t *ut, cputime_t *st)
 {
 	cputime_t rtime, stime, utime;
+	unsigned long flags;
 
-	/*
-	 * 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.
-	 */
+	/* Serialize concurrent callers such that we can honour our guarantees */
+	raw_spin_lock_irqsave(&prev->lock, flags);
 	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
 
 	/*
-	 * Update userspace visible utime/stime values only if actual execution
-	 * time is bigger than already exported. Note that can happen, that we
-	 * provided bigger values due to scaling inaccuracy on big numbers.
+	 * This is possible under two circumstances:
+	 *  - rtime isn't monotonic after all (a bug);
+	 *  - we got reordered by the lock.
+	 *
+	 * In both cases this acts as a filter such that the rest of the code
+	 * can assume it is monotonic regardless of anything else.
 	 */
 	if (prev->stime + prev->utime >= rtime)
 		goto out;
@@ -606,22 +601,46 @@ static void cputime_adjust(struct task_cputime *curr,
 
 	if (utime == 0) {
 		stime = rtime;
-	} else if (stime == 0) {
-		utime = rtime;
-	} else {
-		cputime_t total = stime + utime;
+		goto update;
+	}
 
-		stime = scale_stime((__force u64)stime,
-				    (__force u64)rtime, (__force u64)total);
-		utime = rtime - stime;
+	if (stime == 0) {
+		utime = rtime;
+		goto update;
 	}
 
-	cputime_advance(&prev->stime, stime);
-	cputime_advance(&prev->utime, utime);
+	stime = scale_stime((__force u64)stime, (__force u64)rtime,
+			    (__force u64)(stime + utime));
+
+	/*
+	 * Make sure stime doesn't go backwards; this preserves monotonicity
+	 * for utime because rtime is monotonic.
+	 *
+	 *  utime_i+1 = rtime_i+1 - stime_i
+	 *            = rtime_i+1 - (rtime_i - utime_i)
+	 *            = (rtime_i+1 - rtime_i) + utime_i
+	 *            >= utime_i
+	 */
+	if (stime < prev->stime)
+		stime = prev->stime;
+	utime = rtime - stime;
+
+	/*
+	 * Make sure utime doesn't go backwards; this still preserves
+	 * monotonicity for stime, analogous argument to above.
+	 */
+	if (utime < prev->utime) {
+		utime = prev->utime;
+		stime = rtime - utime;
+	}
 
+update:
+	prev->stime = stime;
+	prev->utime = utime;
 out:
 	*ut = prev->utime;
 	*st = prev->stime;
+	raw_spin_unlock_irqrestore(&prev->lock, flags);
 }
 
 void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0a17af35670a..fc8f01083527 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -953,7 +953,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 
 	/*
 	 * Use the scheduling parameters of the top pi-waiter
-	 * task if we have one and its (relative) deadline is
+	 * task if we have one and its (absolute) deadline is
 	 * smaller than our one... OTW we keep our runtime and
 	 * deadline.
 	 */
@@ -1563,7 +1563,7 @@ out:
 
 static void push_dl_tasks(struct rq *rq)
 {
-	/* Terminates as it moves a -deadline task */
+	/* push_dl_task() will return true if it moved a -deadline task */
 	while (push_dl_task(rq))
 		;
 }
@@ -1657,7 +1657,6 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 {
 	if (!task_running(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
-	    has_pushable_dl_tasks(rq) &&
 	    p->nr_cpus_allowed > 1 &&
 	    dl_task(rq->curr) &&
 	    (rq->curr->nr_cpus_allowed < 2 ||
@@ -1669,9 +1668,8 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 static void set_cpus_allowed_dl(struct task_struct *p,
 				const struct cpumask *new_mask)
 {
-	struct rq *rq;
 	struct root_domain *src_rd;
-	int weight;
+	struct rq *rq;
 
 	BUG_ON(!dl_task(p));
 
@@ -1697,37 +1695,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 		raw_spin_unlock(&src_dl_b->lock);
 	}
 
-	/*
-	 * Update only if the task is actually running (i.e.,
-	 * it is on the rq AND it is not throttled).
-	 */
-	if (!on_dl_rq(&p->dl))
-		return;
-
-	weight = cpumask_weight(new_mask);
-
-	/*
-	 * Only update if the process changes its state from whether it
-	 * can migrate or not.
-	 */
-	if ((p->nr_cpus_allowed > 1) == (weight > 1))
-		return;
-
-	/*
-	 * The process used to be able to migrate OR it can now migrate
-	 */
-	if (weight <= 1) {
-		if (!task_current(rq, p))
-			dequeue_pushable_dl_task(rq, p);
-		BUG_ON(!rq->dl.dl_nr_migratory);
-		rq->dl.dl_nr_migratory--;
-	} else {
-		if (!task_current(rq, p))
-			enqueue_pushable_dl_task(rq, p);
-		rq->dl.dl_nr_migratory++;
-	}
-
-	update_dl_migration(&rq->dl);
+	set_cpus_allowed_common(p, new_mask);
 }
 
 /* Assumes rq->lock is held */
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 4222ec50ab88..641511771ae6 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -68,13 +68,8 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 #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->avg_period);
+	if (!se)
 		return;
-	}
-
 
 	PN(se->exec_start);
 	PN(se->vruntime);
@@ -93,12 +88,8 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 #endif
 	P(se->load.weight);
 #ifdef CONFIG_SMP
-	P(se->avg.runnable_avg_sum);
-	P(se->avg.running_avg_sum);
-	P(se->avg.avg_period);
-	P(se->avg.load_avg_contrib);
-	P(se->avg.utilization_avg_contrib);
-	P(se->avg.decay_count);
+	P(se->avg.load_avg);
+	P(se->avg.util_avg);
 #endif
 #undef PN
 #undef P
@@ -214,21 +205,21 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_SMP
-	SEQ_printf(m, "  .%-30s: %ld\n", "runnable_load_avg",
+	SEQ_printf(m, "  .%-30s: %lu\n", "load_avg",
+			cfs_rq->avg.load_avg);
+	SEQ_printf(m, "  .%-30s: %lu\n", "runnable_load_avg",
 			cfs_rq->runnable_load_avg);
-	SEQ_printf(m, "  .%-30s: %ld\n", "blocked_load_avg",
-			cfs_rq->blocked_load_avg);
-	SEQ_printf(m, "  .%-30s: %ld\n", "utilization_load_avg",
-			cfs_rq->utilization_load_avg);
+	SEQ_printf(m, "  .%-30s: %lu\n", "util_avg",
+			cfs_rq->avg.util_avg);
+	SEQ_printf(m, "  .%-30s: %ld\n", "removed_load_avg",
+			atomic_long_read(&cfs_rq->removed_load_avg));
+	SEQ_printf(m, "  .%-30s: %ld\n", "removed_util_avg",
+			atomic_long_read(&cfs_rq->removed_util_avg));
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	SEQ_printf(m, "  .%-30s: %ld\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: %lu\n", "tg_load_avg_contrib",
+			cfs_rq->tg_load_avg_contrib);
 	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_avg",
 			atomic_long_read(&cfs_rq->tg->load_avg));
-	SEQ_printf(m, "  .%-30s: %d\n", "tg->runnable_avg",
-			atomic_read(&cfs_rq->tg->runnable_avg));
 #endif
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
@@ -636,12 +627,11 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 
 	P(se.load.weight);
 #ifdef CONFIG_SMP
-	P(se.avg.runnable_avg_sum);
-	P(se.avg.running_avg_sum);
-	P(se.avg.avg_period);
-	P(se.avg.load_avg_contrib);
-	P(se.avg.utilization_avg_contrib);
-	P(se.avg.decay_count);
+	P(se.avg.load_sum);
+	P(se.avg.util_sum);
+	P(se.avg.load_avg);
+	P(se.avg.util_avg);
+	P(se.avg.last_update_time);
 #endif
 	P(policy);
 	P(prio);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d113c3ba8bc4..6e2e3483b1ec 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -283,9 +283,6 @@ 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) {
@@ -305,8 +302,6 @@ 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);
 	}
 }
 
@@ -616,15 +611,10 @@ static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
  */
 static u64 __sched_period(unsigned long nr_running)
 {
-	u64 period = sysctl_sched_latency;
-	unsigned long nr_latency = sched_nr_latency;
-
-	if (unlikely(nr_running > nr_latency)) {
-		period = sysctl_sched_min_granularity;
-		period *= nr_running;
-	}
-
-	return period;
+	if (unlikely(nr_running > sched_nr_latency))
+		return nr_running * sysctl_sched_min_granularity;
+	else
+		return sysctl_sched_latency;
 }
 
 /*
@@ -669,22 +659,37 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static int select_idle_sibling(struct task_struct *p, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
 
-static inline void __update_task_entity_contrib(struct sched_entity *se);
-static inline void __update_task_entity_utilization(struct sched_entity *se);
+/*
+ * 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 */
 
-/* Give new task start runnable values to heavy its load in infant time */
-void init_task_runnable_average(struct task_struct *p)
+/* Give new sched_entity start runnable values to heavy its load in infant time */
+void init_entity_runnable_average(struct sched_entity *se)
 {
-	u32 slice;
+	struct sched_avg *sa = &se->avg;
 
-	slice = sched_slice(task_cfs_rq(p), &p->se) >> 10;
-	p->se.avg.runnable_avg_sum = p->se.avg.running_avg_sum = slice;
-	p->se.avg.avg_period = slice;
-	__update_task_entity_contrib(&p->se);
-	__update_task_entity_utilization(&p->se);
+	sa->last_update_time = 0;
+	/*
+	 * sched_avg's period_contrib should be strictly less then 1024, so
+	 * we give it 1023 to make sure it is almost a period (1024us), and
+	 * will definitely be update (after enqueue).
+	 */
+	sa->period_contrib = 1023;
+	sa->load_avg = scale_load_down(se->load.weight);
+	sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
+	sa->util_avg = scale_load_down(SCHED_LOAD_SCALE);
+	sa->util_sum = LOAD_AVG_MAX;
+	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
+
+static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
+static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
 #else
-void init_task_runnable_average(struct task_struct *p)
+void init_entity_runnable_average(struct sched_entity *se)
 {
 }
 #endif
@@ -1415,8 +1420,9 @@ static bool numa_has_capacity(struct task_numa_env *env)
 	 * --------------------- vs ---------------------
 	 * src->compute_capacity    dst->compute_capacity
 	 */
-	if (src->load * dst->compute_capacity >
-	    dst->load * src->compute_capacity)
+	if (src->load * dst->compute_capacity * env->imbalance_pct >
+
+	    dst->load * src->compute_capacity * 100)
 		return true;
 
 	return false;
@@ -1702,8 +1708,8 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
 		delta = runtime - p->last_sum_exec_runtime;
 		*period = now - p->last_task_numa_placement;
 	} else {
-		delta = p->se.avg.runnable_avg_sum;
-		*period = p->se.avg.avg_period;
+		delta = p->se.avg.load_sum / p->se.load.weight;
+		*period = LOAD_AVG_MAX;
 	}
 
 	p->last_sum_exec_runtime = runtime;
@@ -2351,13 +2357,13 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
 	long tg_weight;
 
 	/*
-	 * Use this CPU's actual weight instead of the last load_contribution
-	 * to gain a more accurate current total weight. See
-	 * update_cfs_rq_load_contribution().
+	 * Use this CPU's real-time load instead of the last load contribution
+	 * as the updating of the contribution is delayed, and we will use the
+	 * the real-time load to calc the share. See update_tg_load_avg().
 	 */
 	tg_weight = atomic_long_read(&tg->load_avg);
-	tg_weight -= cfs_rq->tg_load_contrib;
-	tg_weight += cfs_rq->load.weight;
+	tg_weight -= cfs_rq->tg_load_avg_contrib;
+	tg_weight += cfs_rq_load_avg(cfs_rq);
 
 	return tg_weight;
 }
@@ -2367,7 +2373,7 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 	long tg_weight, load, shares;
 
 	tg_weight = calc_tg_weight(tg, cfs_rq);
-	load = cfs_rq->load.weight;
+	load = cfs_rq_load_avg(cfs_rq);
 
 	shares = (tg->shares * load);
 	if (tg_weight)
@@ -2429,14 +2435,6 @@ static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 #endif /* 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.
- */
-#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,
@@ -2485,9 +2483,8 @@ static __always_inline u64 decay_load(u64 val, u64 n)
 		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;
+	val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
+	return val;
 }
 
 /*
@@ -2546,23 +2543,22 @@ static u32 __compute_runnable_contrib(u64 n)
  *   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, int cpu,
-							struct sched_avg *sa,
-							int runnable,
-							int running)
+static __always_inline int
+__update_load_avg(u64 now, int cpu, struct sched_avg *sa,
+		  unsigned long weight, int running, struct cfs_rq *cfs_rq)
 {
 	u64 delta, periods;
-	u32 runnable_contrib;
+	u32 contrib;
 	int delta_w, decayed = 0;
 	unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
 
-	delta = now - sa->last_runnable_update;
+	delta = now - sa->last_update_time;
 	/*
 	 * 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;
+		sa->last_update_time = now;
 		return 0;
 	}
 
@@ -2573,26 +2569,29 @@ static __always_inline int __update_entity_runnable_avg(u64 now, int cpu,
 	delta >>= 10;
 	if (!delta)
 		return 0;
-	sa->last_runnable_update = now;
+	sa->last_update_time = now;
 
 	/* delta_w is the amount already accumulated against our next period */
-	delta_w = sa->avg_period % 1024;
+	delta_w = sa->period_contrib;
 	if (delta + delta_w >= 1024) {
-		/* period roll-over */
 		decayed = 1;
 
+		/* how much left for next period will start over, we don't know yet */
+		sa->period_contrib = 0;
+
 		/*
 		 * 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;
+		if (weight) {
+			sa->load_sum += weight * delta_w;
+			if (cfs_rq)
+				cfs_rq->runnable_load_sum += weight * delta_w;
+		}
 		if (running)
-			sa->running_avg_sum += delta_w * scale_freq
-				>> SCHED_CAPACITY_SHIFT;
-		sa->avg_period += delta_w;
+			sa->util_sum += delta_w * scale_freq >> SCHED_CAPACITY_SHIFT;
 
 		delta -= delta_w;
 
@@ -2600,341 +2599,186 @@ static __always_inline int __update_entity_runnable_avg(u64 now, int cpu,
 		periods = delta / 1024;
 		delta %= 1024;
 
-		sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
-						  periods + 1);
-		sa->running_avg_sum = decay_load(sa->running_avg_sum,
-						  periods + 1);
-		sa->avg_period = decay_load(sa->avg_period,
-						     periods + 1);
+		sa->load_sum = decay_load(sa->load_sum, periods + 1);
+		if (cfs_rq) {
+			cfs_rq->runnable_load_sum =
+				decay_load(cfs_rq->runnable_load_sum, periods + 1);
+		}
+		sa->util_sum = decay_load((u64)(sa->util_sum), 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;
+		contrib = __compute_runnable_contrib(periods);
+		if (weight) {
+			sa->load_sum += weight * contrib;
+			if (cfs_rq)
+				cfs_rq->runnable_load_sum += weight * contrib;
+		}
 		if (running)
-			sa->running_avg_sum += runnable_contrib * scale_freq
-				>> SCHED_CAPACITY_SHIFT;
-		sa->avg_period += runnable_contrib;
+			sa->util_sum += contrib * scale_freq >> SCHED_CAPACITY_SHIFT;
 	}
 
 	/* Remainder of delta accrued against u_0` */
-	if (runnable)
-		sa->runnable_avg_sum += delta;
+	if (weight) {
+		sa->load_sum += weight * delta;
+		if (cfs_rq)
+			cfs_rq->runnable_load_sum += weight * delta;
+	}
 	if (running)
-		sa->running_avg_sum += delta * scale_freq
-			>> SCHED_CAPACITY_SHIFT;
-	sa->avg_period += delta;
-
-	return decayed;
-}
+		sa->util_sum += delta * scale_freq >> SCHED_CAPACITY_SHIFT;
 
-/* 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;
-	se->avg.decay_count = 0;
-	if (!decays)
-		return 0;
+	sa->period_contrib += delta;
 
-	se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
-	se->avg.utilization_avg_contrib =
-		decay_load(se->avg.utilization_avg_contrib, decays);
+	if (decayed) {
+		sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
+		if (cfs_rq) {
+			cfs_rq->runnable_load_avg =
+				div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
+		}
+		sa->util_avg = (sa->util_sum << SCHED_LOAD_SHIFT) / LOAD_AVG_MAX;
+	}
 
-	return decays;
+	return decayed;
 }
 
 #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;
-	long tg_contrib;
-
-	tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg;
-	tg_contrib -= cfs_rq->tg_load_contrib;
-
-	if (!tg_contrib)
-		return;
-
-	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;
-	}
-}
-
 /*
- * Aggregate cfs_rq runnable averages into an equivalent task_group
- * representation for computing load contributions.
+ * Updating tg's load_avg is necessary before update_cfs_share (which is done)
+ * and effective_load (which is not done because it is too costly).
  */
-static inline void __update_tg_runnable_avg(struct sched_avg *sa,
-						  struct cfs_rq *cfs_rq)
+static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 {
-	struct task_group *tg = cfs_rq->tg;
-	long contrib;
+	long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
 
-	/* The fraction of a cpu used by this cfs_rq */
-	contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT,
-			  sa->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;
+	if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
+		atomic_long_add(delta, &cfs_rq->tg->load_avg);
+		cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
 	}
 }
 
-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 = div_u64(contrib,
-				     atomic_long_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 peri