Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (26 commits)
  sched: Resched proper CPU on yield_to()
  sched: Allow users with sufficient RLIMIT_NICE to change from SCHED_IDLE policy
  sched: Allow SCHED_BATCH to preempt SCHED_IDLE tasks
  sched: Clean up the IRQ_TIME_ACCOUNTING code
  sched: Add #ifdef around irq time accounting functions
  sched, autogroup: Stop claiming ownership of the root task group
  sched, autogroup: Stop going ahead if autogroup is disabled
  sched, autogroup, sysctl: Use proc_dointvec_minmax() instead
  sched: Fix the group_imb logic
  sched: Clean up some f_b_g() comments
  sched: Clean up remnants of sd_idle
  sched: Wholesale removal of sd_idle logic
  sched: Add yield_to(task, preempt) functionality
  sched: Use a buddy to implement yield_task_fair()
  sched: Limit the scope of clear_buddies
  sched: Check the right ->nr_running in yield_task_fair()
  sched: Avoid expensive initial update_cfs_load(), on UP too
  sched: Fix switch_from_fair()
  sched: Simplify the idle scheduling class
  softirqs: Account ksoftirqd time as cpustat softirq
  ...

11 files changed, 549 insertions, 253 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 57a18e8d28c8..27125e413576 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -324,7 +324,7 @@ struct cfs_rq {
 	 * 'curr' points to currently running entity on this cfs_rq.
 	 * It is set to NULL otherwise (i.e when none are currently running).
 	 */
-	struct sched_entity *curr, *next, *last;
+	struct sched_entity *curr, *next, *last, *skip;
 
 	unsigned int nr_spread_over;
 
@@ -1683,6 +1683,39 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 		__release(rq2->lock);
 }
 
+#else /* CONFIG_SMP */
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+	__acquires(rq1->lock)
+	__acquires(rq2->lock)
+{
+	BUG_ON(!irqs_disabled());
+	BUG_ON(rq1 != rq2);
+	raw_spin_lock(&rq1->lock);
+	__acquire(rq2->lock);	/* Fake it out ;) */
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+	__releases(rq1->lock)
+	__releases(rq2->lock)
+{
+	BUG_ON(rq1 != rq2);
+	raw_spin_unlock(&rq1->lock);
+	__release(rq2->lock);
+}
+
 #endif
 
 static void calc_load_account_idle(struct rq *this_rq);
@@ -1877,7 +1910,7 @@ void account_system_vtime(struct task_struct *curr)
 	 */
 	if (hardirq_count())
 		__this_cpu_add(cpu_hardirq_time, delta);
-	else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
 		__this_cpu_add(cpu_softirq_time, delta);
 
 	irq_time_write_end();
@@ -1917,8 +1950,40 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 		sched_rt_avg_update(rq, irq_delta);
 }
 
+static int irqtime_account_hi_update(void)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	unsigned long flags;
+	u64 latest_ns;
+	int ret = 0;
+
+	local_irq_save(flags);
+	latest_ns = this_cpu_read(cpu_hardirq_time);
+	if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq))
+		ret = 1;
+	local_irq_restore(flags);
+	return ret;
+}
+
+static int irqtime_account_si_update(void)
+{
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	unsigned long flags;
+	u64 latest_ns;
+	int ret = 0;
+
+	local_irq_save(flags);
+	latest_ns = this_cpu_read(cpu_softirq_time);
+	if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq))
+		ret = 1;
+	local_irq_restore(flags);
+	return ret;
+}
+
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 
+#define sched_clock_irqtime	(0)
+
 static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
 	rq->clock_task += delta;
@@ -2022,14 +2087,14 @@ inline int task_curr(const struct task_struct *p)
 
 static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 				       const struct sched_class *prev_class,
-				       int oldprio, int running)
+				       int oldprio)
 {
 	if (prev_class != p->sched_class) {
 		if (prev_class->switched_from)
-			prev_class->switched_from(rq, p, running);
-		p->sched_class->switched_to(rq, p, running);
-	} else
-		p->sched_class->prio_changed(rq, p, oldprio, running);
+			prev_class->switched_from(rq, p);
+		p->sched_class->switched_to(rq, p);
+	} else if (oldprio != p->prio)
+		p->sched_class->prio_changed(rq, p, oldprio);
 }
 
 static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
@@ -2542,6 +2607,7 @@ static void __sched_fork(struct task_struct *p)
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
+	p->se.vruntime			= 0;
 
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
@@ -3547,6 +3613,32 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime,
 }
 
 /*
+ * Account system cpu time to a process and desired cpustat field
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * @target_cputime64: pointer to cpustat field that has to be updated
+ */
+static inline
+void __account_system_time(struct task_struct *p, cputime_t cputime,
+			cputime_t cputime_scaled, cputime64_t *target_cputime64)
+{
+	cputime64_t tmp = cputime_to_cputime64(cputime);
+
+	/* Add system time to process. */
+	p->stime = cputime_add(p->stime, cputime);
+	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
+	account_group_system_time(p, cputime);
+
+	/* Add system time to cpustat. */
+	*target_cputime64 = cputime64_add(*target_cputime64, tmp);
+	cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
+
+	/* Account for system time used */
+	acct_update_integrals(p);
+}
+
+/*
  * Account system cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @hardirq_offset: the offset to subtract from hardirq_count()
@@ -3557,36 +3649,26 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 			 cputime_t cputime, cputime_t cputime_scaled)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-	cputime64_t tmp;
+	cputime64_t *target_cputime64;
 
 	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
 		account_guest_time(p, cputime, cputime_scaled);
 		return;
 	}
 
-	/* Add system time to process. */
-	p->stime = cputime_add(p->stime, cputime);
-	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
-	account_group_system_time(p, cputime);
-
-	/* Add system time to cpustat. */
-	tmp = cputime_to_cputime64(cputime);
 	if (hardirq_count() - hardirq_offset)
-		cpustat->irq = cputime64_add(cpustat->irq, tmp);
+		target_cputime64 = &cpustat->irq;
 	else if (in_serving_softirq())
-		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+		target_cputime64 = &cpustat->softirq;
 	else
-		cpustat->system = cputime64_add(cpustat->system, tmp);
-
-	cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
+		target_cputime64 = &cpustat->system;
 
-	/* Account for system time used */
-	acct_update_integrals(p);
+	__account_system_time(p, cputime, cputime_scaled, target_cputime64);
 }
 
 /*
  * Account for involuntary wait time.
- * @steal: the cpu time spent in involuntary wait
+ * @cputime: the cpu time spent in involuntary wait
  */
 void account_steal_time(cputime_t cputime)
 {
@@ -3614,6 +3696,73 @@ void account_idle_time(cputime_t cputime)
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * Account a tick to a process and cpustat
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: is the tick from userspace
+ * @rq: the pointer to rq
+ *
+ * Tick demultiplexing follows the order
+ * - pending hardirq update
+ * - pending softirq update
+ * - user_time
+ * - idle_time
+ * - system time
+ *   - check for guest_time
+ *   - else account as system_time
+ *
+ * Check for hardirq is done both for system and user time as there is
+ * no timer going off while we are on hardirq and hence we may never get an
+ * opportunity to update it solely in system time.
+ * p->stime and friends are only updated on system time and not on irq
+ * softirq as those do not count in task exec_runtime any more.
+ */
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+						struct rq *rq)
+{
+	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+	cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy);
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+
+	if (irqtime_account_hi_update()) {
+		cpustat->irq = cputime64_add(cpustat->irq, tmp);
+	} else if (irqtime_account_si_update()) {
+		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+	} else if (this_cpu_ksoftirqd() == p) {
+		/*
+		 * ksoftirqd time do not get accounted in cpu_softirq_time.
+		 * So, we have to handle it separately here.
+		 * Also, p->stime needs to be updated for ksoftirqd.
+		 */
+		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+					&cpustat->softirq);
+	} else if (user_tick) {
+		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+	} else if (p == rq->idle) {
+		account_idle_time(cputime_one_jiffy);
+	} else if (p->flags & PF_VCPU) { /* System time or guest time */
+		account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+	} else {
+		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+					&cpustat->system);
+	}
+}
+
+static void irqtime_account_idle_ticks(int ticks)
+{
+	int i;
+	struct rq *rq = this_rq();
+
+	for (i = 0; i < ticks; i++)
+		irqtime_account_process_tick(current, 0, rq);
+}
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+static void irqtime_account_idle_ticks(int ticks) {}
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+						struct rq *rq) {}
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
 /*
  * Account a single tick of cpu time.
  * @p: the process that the cpu time gets accounted to
@@ -3624,6 +3773,11 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
 	struct rq *rq = this_rq();
 
+	if (sched_clock_irqtime) {
+		irqtime_account_process_tick(p, user_tick, rq);
+		return;
+	}
+
 	if (user_tick)
 		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
 	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
@@ -3649,6 +3803,12 @@ void account_steal_ticks(unsigned long ticks)
  */
 void account_idle_ticks(unsigned long ticks)
 {
+
+	if (sched_clock_irqtime) {
+		irqtime_account_idle_ticks(ticks);
+		return;
+	}
+
 	account_idle_time(jiffies_to_cputime(ticks));
 }
 
@@ -4547,11 +4707,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq) {
+	if (on_rq)
 		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
-		check_class_changed(rq, p, prev_class, oldprio, running);
-	}
+	check_class_changed(rq, p, prev_class, oldprio);
 	task_rq_unlock(rq, &flags);
 }
 
@@ -4799,12 +4958,15 @@ recheck:
 			    param->sched_priority > rlim_rtprio)
 				return -EPERM;
 		}
+
 		/*
-		 * Like positive nice levels, dont allow tasks to
-		 * move out of SCHED_IDLE either:
+		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
+		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
 		 */
-		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE)
-			return -EPERM;
+		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
+			if (!can_nice(p, TASK_NICE(p)))
+				return -EPERM;
+		}
 
 		/* can't change other user's priorities */
 		if (!check_same_owner(p))
@@ -4879,11 +5041,10 @@ recheck:
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq) {
+	if (on_rq)
 		activate_task(rq, p, 0);
 
-		check_class_changed(rq, p, prev_class, oldprio, running);
-	}
+	check_class_changed(rq, p, prev_class, oldprio);
 	__task_rq_unlock(rq);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
@@ -5300,6 +5461,65 @@ void __sched yield(void)
 }
 EXPORT_SYMBOL(yield);
 
+/**
+ * yield_to - yield the current processor to another thread in
+ * your thread group, or accelerate that thread toward the
+ * processor it's on.
+ *
+ * It's the caller's job to ensure that the target task struct
+ * can't go away on us before we can do any checks.
+ *
+ * Returns true if we indeed boosted the target task.
+ */
+bool __sched yield_to(struct task_struct *p, bool preempt)
+{
+	struct task_struct *curr = current;
+	struct rq *rq, *p_rq;
+	unsigned long flags;
+	bool yielded = 0;
+
+	local_irq_save(flags);
+	rq = this_rq();
+
+again:
+	p_rq = task_rq(p);
+	double_rq_lock(rq, p_rq);
+	while (task_rq(p) != p_rq) {
+		double_rq_unlock(rq, p_rq);
+		goto again;
+	}
+
+	if (!curr->sched_class->yield_to_task)
+		goto out;
+
+	if (curr->sched_class != p->sched_class)
+		goto out;
+
+	if (task_running(p_rq, p) || p->state)
+		goto out;
+
+	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+	if (yielded) {
+		schedstat_inc(rq, yld_count);
+		/*
+		 * Make p's CPU reschedule; pick_next_entity takes care of
+		 * fairness.
+		 */
+		if (preempt && rq != p_rq)
+			resched_task(p_rq->curr);
+	}
+
+out:
+	double_rq_unlock(rq, p_rq);
+	local_irq_restore(flags);
+
+	if (yielded)
+		schedule();
+
+	return yielded;
+}
+EXPORT_SYMBOL_GPL(yield_to);
+
 /*
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
@@ -7773,6 +7993,10 @@ static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
 	INIT_LIST_HEAD(&cfs_rq->tasks);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	cfs_rq->rq = rq;
+	/* allow initial update_cfs_load() to truncate */
+#ifdef CONFIG_SMP
+	cfs_rq->load_stamp = 1;
+#endif
 #endif
 	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
 }
@@ -8086,6 +8310,8 @@ EXPORT_SYMBOL(__might_sleep);
 #ifdef CONFIG_MAGIC_SYSRQ
 static void normalize_task(struct rq *rq, struct task_struct *p)
 {
+	const struct sched_class *prev_class = p->sched_class;
+	int old_prio = p->prio;
 	int on_rq;
 
 	on_rq = p->se.on_rq;
@@ -8096,6 +8322,8 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 		activate_task(rq, p, 0);
 		resched_task(rq->curr);
 	}
+
+	check_class_changed(rq, p, prev_class, old_prio);
 }
 
 void normalize_rt_tasks(void)
@@ -8487,7 +8715,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 		/* Propagate contribution to hierarchy */
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		for_each_sched_entity(se)
-			update_cfs_shares(group_cfs_rq(se), 0);
+			update_cfs_shares(group_cfs_rq(se));
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}
 
diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c
index 9fb656283157..5946ac515602 100644
--- a/kernel/sched_autogroup.c
+++ b/kernel/sched_autogroup.c
@@ -12,7 +12,6 @@ static atomic_t autogroup_seq_nr;
 static void __init autogroup_init(struct task_struct *init_task)
 {
 	autogroup_default.tg = &root_task_group;
-	root_task_group.autogroup = &autogroup_default;
 	kref_init(&autogroup_default.kref);
 	init_rwsem(&autogroup_default.lock);
 	init_task->signal->autogroup = &autogroup_default;
@@ -130,7 +129,7 @@ task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 
 static inline bool task_group_is_autogroup(struct task_group *tg)
 {
-	return tg != &root_task_group && tg->autogroup;
+	return !!tg->autogroup;
 }
 
 static inline struct task_group *
@@ -161,11 +160,15 @@ 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);
 }
@@ -247,10 +250,14 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
 {
 	struct autogroup *ag = autogroup_task_get(p);
 
+	if (!task_group_is_autogroup(ag->tg))
+		goto out;
+
 	down_read(&ag->lock);
 	seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
 	up_read(&ag->lock);
 
+out:
 	autogroup_kref_put(ag);
 }
 #endif /* CONFIG_PROC_FS */
@@ -258,9 +265,7 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
 #ifdef CONFIG_SCHED_DEBUG
 static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
 {
-	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
-
-	if (!enabled || !tg->autogroup)
+	if (!task_group_is_autogroup(tg))
 		return 0;
 
 	return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h
index 7b859ffe5dad..05577055cfca 100644
--- a/kernel/sched_autogroup.h
+++ b/kernel/sched_autogroup.h
@@ -1,6 +1,11 @@
 #ifdef CONFIG_SCHED_AUTOGROUP
 
 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_debug.c b/kernel/sched_debug.c
index eb6cb8edd075..7bacd83a4158 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -179,7 +179,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
 	if (cfs_rq->rb_leftmost)
-		MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime;
+		MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
 	last = __pick_last_entity(cfs_rq);
 	if (last)
 		max_vruntime = last->vruntime;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 0c26e2df450e..3f7ec9e27ee1 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -69,14 +69,6 @@ static unsigned int sched_nr_latency = 8;
 unsigned int sysctl_sched_child_runs_first __read_mostly;
 
 /*
- * sys_sched_yield() compat mode
- *
- * This option switches the agressive yield implementation of the
- * old scheduler back on.
- */
-unsigned int __read_mostly sysctl_sched_compat_yield;
-
-/*
  * SCHED_OTHER wake-up granularity.
  * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  *
@@ -419,7 +411,7 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
 }
 
-static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *left = cfs_rq->rb_leftmost;
 
@@ -429,6 +421,17 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
 	return rb_entry(left, struct sched_entity, run_node);
 }
 
+static struct sched_entity *__pick_next_entity(struct sched_entity *se)
+{
+	struct rb_node *next = rb_next(&se->run_node);
+
+	if (!next)
+		return NULL;
+
+	return rb_entry(next, struct sched_entity, run_node);
+}
+
+#ifdef CONFIG_SCHED_DEBUG
 static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
@@ -443,7 +446,6 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
  * Scheduling class statistics methods:
  */
 
-#ifdef CONFIG_SCHED_DEBUG
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
@@ -540,7 +542,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta);
+static void update_cfs_shares(struct cfs_rq *cfs_rq);
 
 /*
  * Update the current task's runtime statistics. Skip current tasks that
@@ -733,6 +735,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 	    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;
@@ -763,16 +766,15 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 		list_del_leaf_cfs_rq(cfs_rq);
 }
 
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
-				long weight_delta)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
 	long load_weight, load, shares;
 
-	load = cfs_rq->load.weight + weight_delta;
+	load = cfs_rq->load.weight;
 
 	load_weight = atomic_read(&tg->load_weight);
-	load_weight -= cfs_rq->load_contribution;
 	load_weight += load;
+	load_weight -= cfs_rq->load_contribution;
 
 	shares = (tg->shares * load);
 	if (load_weight)
@@ -790,7 +792,7 @@ 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, 0);
+		update_cfs_shares(cfs_rq);
 	}
 }
 # else /* CONFIG_SMP */
@@ -798,8 +800,7 @@ 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,
-				long weight_delta)
+static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
 	return tg->shares;
 }
@@ -824,7 +825,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		account_entity_enqueue(cfs_rq, se);
 }
 
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static void update_cfs_shares(struct cfs_rq *cfs_rq)
 {
 	struct task_group *tg;
 	struct sched_entity *se;
@@ -838,7 +839,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
 	if (likely(se->load.weight == tg->shares))
 		return;
 #endif
-	shares = calc_cfs_shares(cfs_rq, tg, weight_delta);
+	shares = calc_cfs_shares(cfs_rq, tg);
 
 	reweight_entity(cfs_rq_of(se), se, shares);
 }
@@ -847,7 +848,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 {
 }
 
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 {
 }
 
@@ -978,8 +979,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	update_curr(cfs_rq);
 	update_cfs_load(cfs_rq, 0);
-	update_cfs_shares(cfs_rq, se->load.weight);
 	account_entity_enqueue(cfs_rq, se);
+	update_cfs_shares(cfs_rq);
 
 	if (flags & ENQUEUE_WAKEUP) {
 		place_entity(cfs_rq, se, 0);
@@ -996,19 +997,49 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		list_add_leaf_cfs_rq(cfs_rq);
 }
 
-static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies_last(struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		if (cfs_rq->last == se)
+			cfs_rq->last = NULL;
+		else
+			break;
+	}
+}
+
+static void __clear_buddies_next(struct sched_entity *se)
 {
-	if (!se || cfs_rq->last == se)
-		cfs_rq->last = NULL;
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		if (cfs_rq->next == se)
+			cfs_rq->next = NULL;
+		else
+			break;
+	}
+}
 
-	if (!se || cfs_rq->next == se)
-		cfs_rq->next = NULL;
+static void __clear_buddies_skip(struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+		if (cfs_rq->skip == se)
+			cfs_rq->skip = NULL;
+		else
+			break;
+	}
 }
 
 static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	for_each_sched_entity(se)
-		__clear_buddies(cfs_rq_of(se), se);
+	if (cfs_rq->last == se)
+		__clear_buddies_last(se);
+
+	if (cfs_rq->next == se)
+		__clear_buddies_next(se);
+
+	if (cfs_rq->skip == se)
+		__clear_buddies_skip(se);
 }
 
 static void
@@ -1041,7 +1072,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_cfs_load(cfs_rq, 0);
 	account_entity_dequeue(cfs_rq, se);
 	update_min_vruntime(cfs_rq);
-	update_cfs_shares(cfs_rq, 0);
+	update_cfs_shares(cfs_rq);
 
 	/*
 	 * Normalize the entity after updating the min_vruntime because the
@@ -1084,7 +1115,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		return;
 
 	if (cfs_rq->nr_running > 1) {
-		struct sched_entity *se = __pick_next_entity(cfs_rq);
+		struct sched_entity *se = __pick_first_entity(cfs_rq);
 		s64 delta = curr->vruntime - se->vruntime;
 
 		if (delta < 0)
@@ -1128,13 +1159,27 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static int
 wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 
+/*
+ * Pick the next process, keeping these things in mind, in this order:
+ * 1) keep things fair between processes/task groups
+ * 2) pick the "next" process, since someone really wants that to run
+ * 3) pick the "last" process, for cache locality
+ * 4) do not run the "skip" process, if something else is available
+ */
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
-	struct sched_entity *se = __pick_next_entity(cfs_rq);
+	struct sched_entity *se = __pick_first_entity(cfs_rq);
 	struct sched_entity *left = se;
 
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
-		se = cfs_rq->next;
+	/*
+	 * Avoid running the skip buddy, if running something else can
+	 * be done without getting too unfair.
+	 */
+	if (cfs_rq->skip == se) {
+		struct sched_entity *second = __pick_next_entity(se);
+		if (second && wakeup_preempt_entity(second, left) < 1)
+			se = second;
+	}
 
 	/*
 	 * Prefer last buddy, try to return the CPU to a preempted task.
@@ -1142,6 +1187,12 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
 		se = cfs_rq->last;
 
+	/*
+	 * Someone really wants this to run. If it's not unfair, run it.
+	 */
+	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+		se = cfs_rq->next;
+
 	clear_buddies(cfs_rq, se);
 
 	return se;
@@ -1282,7 +1333,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq, 0);
+		update_cfs_shares(cfs_rq);
 	}
 
 	hrtick_update(rq);
@@ -1312,58 +1363,12 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 		update_cfs_load(cfs_rq, 0);
-		update_cfs_shares(cfs_rq, 0);
+		update_cfs_shares(cfs_rq);
 	}
 
 	hrtick_update(rq);
 }
 
-/*
- * sched_yield() support is very simple - we dequeue and enqueue.
- *
- * If compat_yield is turned on then we requeue to the end of the tree.
- */
-static void yield_task_fair(struct rq *rq)
-{
-	struct task_struct *curr = rq->curr;
-	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
-	struct sched_entity *rightmost, *se = &curr->se;
-
-	/*
-	 * Are we the only task in the tree?
-	 */
-	if (unlikely(cfs_rq->nr_running == 1))
-		return;
-
-	clear_buddies(cfs_rq, se);
-
-	if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
-		update_rq_clock(rq);
-		/*
-		 * Update run-time statistics of the 'current'.
-		 */
-		update_curr(cfs_rq);
-
-		return;
-	}
-	/*
-	 * Find the rightmost entry in the rbtree:
-	 */
-	rightmost = __pick_last_entity(cfs_rq);
-	/*
-	 * Already in the rightmost position?
-	 */
-	if (unlikely(!rightmost || entity_before(rightmost, se)))
-		return;
-
-	/*
-	 * Minimally necessary key value to be last in the tree:
-	 * Upon rescheduling, sched_class::put_prev_task() will place
-	 * 'current' within the tree based on its new key value.
-	 */
-	se->vruntime = rightmost->vruntime + 1;
-}
-
 #ifdef CONFIG_SMP
 
 static void task_waking_fair(struct rq *rq, struct task_struct *p)
@@ -1834,6 +1839,14 @@ static void set_next_buddy(struct sched_entity *se)
 	}
 }
 
+static void set_skip_buddy(struct sched_entity *se)
+{
+	if (likely(task_of(se)->policy != SCHED_IDLE)) {
+		for_each_sched_entity(se)
+			cfs_rq_of(se)->skip = se;
+	}
+}
+
 /*
  * Preempt the current task with a newly woken task if needed:
  */
@@ -1857,16 +1870,18 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (test_tsk_need_resched(curr))
 		return;
 
+	/* Idle tasks are by definition preempted by non-idle tasks. */
+	if (unlikely(curr->policy == SCHED_IDLE) &&
+	    likely(p->policy != SCHED_IDLE))
+		goto preempt;
+
 	/*
-	 * Batch and idle tasks do not preempt (their preemption is driven by
-	 * the tick):
+	 * Batch and idle tasks do not preempt non-idle tasks (their preemption
+	 * is driven by the tick):
 	 */
 	if (unlikely(p->policy != SCHED_NORMAL))
 		return;
 
-	/* Idle tasks are by definition preempted by everybody. */
-	if (unlikely(curr->policy == SCHED_IDLE))
-		goto preempt;
 
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
@@ -1932,6 +1947,51 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
 	}
 }
 
+/*
+ * sched_yield() is very simple
+ *
+ * The magic of dealing with the ->skip buddy is in pick_next_entity.
+ */
+static void yield_task_fair(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+	struct sched_entity *se = &curr->se;
+
+	/*
+	 * Are we the only task in the tree?
+	 */
+	if (unlikely(rq->nr_running == 1))
+		return;
+
+	clear_buddies(cfs_rq, se);
+
+	if (curr->policy != SCHED_BATCH) {
+		update_rq_clock(rq);
+		/*
+		 * Update run-time statistics of the 'current'.
+		 */
+		update_curr(cfs_rq);
+	}
+
+	set_skip_buddy(se);
+}
+
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+{
+	struct sched_entity *se = &p->se;
+
+	if (!se->on_rq)
+		return false;
+
+	/* Tell the scheduler that we'd really like pse to run next. */
+	set_next_buddy(se);
+
+	yield_task_fair(rq);
+
+	return true;
+}
+
 #ifdef CONFIG_SMP
 /**************************************************
  * Fair scheduling class load-balancing methods:
@@ -2123,7 +2183,7 @@ static int update_shares_cpu(struct task_group *tg, int cpu)
 	 * We need to update shares after updating tg->load_weight in
 	 * order to adjust the weight of groups with long running tasks.
 	 */
-	update_cfs_shares(cfs_rq, 0);
+	update_cfs_shares(cfs_rq);
 
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
@@ -2610,7 +2670,6 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  * @this_cpu: Cpu for which load balance is currently performed.
  * @idle: Idle status of this_cpu
  * @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @sd_idle: Idle status of the sched_domain containing group.
  * @local_group: Does group contain this_cpu.
  * @cpus: Set of cpus considered for load balancing.
  * @balance: Should we balance.
@@ -2618,7 +2677,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  */
 static inline void update_sg_lb_stats(struct sched_domain *sd,
 			struct sched_group *group, int this_cpu,
-			enum cpu_idle_type idle, int load_idx, int *sd_idle,
+			enum cpu_idle_type idle, int load_idx,
 			int local_group, const struct cpumask *cpus,
 			int *balance, struct sg_lb_stats *sgs)
 {
@@ -2638,9 +2697,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
 		struct rq *rq = cpu_rq(i);