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

Pull scheduler changes for v3.4 from Ingo Molnar

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
  printk: Make it compile with !CONFIG_PRINTK
  sched/x86: Fix overflow in cyc2ns_offset
  sched: Fix nohz load accounting -- again!
  sched: Update yield() docs
  printk/sched: Introduce special printk_sched() for those awkward moments
  sched/nohz: Correctly initialize 'next_balance' in 'nohz' idle balancer
  sched: Cleanup cpu_active madness
  sched: Fix load-balance wreckage
  sched: Clean up parameter passing of proc_sched_autogroup_set_nice()
  sched: Ditch per cgroup task lists for load-balancing
  sched: Rename load-balancing fields
  sched: Move load-balancing arguments into helper struct
  sched/rt: Do not submit new work when PI-blocked
  sched/rt: Prevent idle task boosting
  sched/wait: Add __wake_up_all_locked() API
  sched/rt: Document scheduler related skip-resched-check sites
  sched/rt: Use schedule_preempt_disabled()
  sched/rt: Add schedule_preempt_disabled()
  sched/rt: Do not throttle when PI boosting
  sched/rt: Keep period timer ticking when rt throttling is active
  ...

10 files changed, 348 insertions, 300 deletions

diff --git a/kernel/mutex.c b/kernel/mutex.c
index 89096dd8786f..a307cc9c9526 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -240,9 +240,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 
 		/* didn't get the lock, go to sleep: */
 		spin_unlock_mutex(&lock->wait_lock, flags);
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 		spin_lock_mutex(&lock->wait_lock, flags);
 	}
 
diff --git a/kernel/printk.c b/kernel/printk.c
index 0b3ea2cbd5fb..b663c2c95d39 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -1216,13 +1216,27 @@ int is_console_locked(void)
 	return console_locked;
 }
 
+/*
+ * Delayed printk facility, for scheduler-internal messages:
+ */
+#define PRINTK_BUF_SIZE		512
+
+#define PRINTK_PENDING_WAKEUP	0x01
+#define PRINTK_PENDING_SCHED	0x02
+
 static DEFINE_PER_CPU(int, printk_pending);
+static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
 
 void printk_tick(void)
 {
 	if (__this_cpu_read(printk_pending)) {
-		__this_cpu_write(printk_pending, 0);
-		wake_up_interruptible(&log_wait);
+		int pending = __this_cpu_xchg(printk_pending, 0);
+		if (pending & PRINTK_PENDING_SCHED) {
+			char *buf = __get_cpu_var(printk_sched_buf);
+			printk(KERN_WARNING "[sched_delayed] %s", buf);
+		}
+		if (pending & PRINTK_PENDING_WAKEUP)
+			wake_up_interruptible(&log_wait);
 	}
 }
 
@@ -1236,7 +1250,7 @@ int printk_needs_cpu(int cpu)
 void wake_up_klogd(void)
 {
 	if (waitqueue_active(&log_wait))
-		this_cpu_write(printk_pending, 1);
+		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
 }
 
 /**
@@ -1629,6 +1643,26 @@ late_initcall(printk_late_init);
 
 #if defined CONFIG_PRINTK
 
+int printk_sched(const char *fmt, ...)
+{
+	unsigned long flags;
+	va_list args;
+	char *buf;
+	int r;
+
+	local_irq_save(flags);
+	buf = __get_cpu_var(printk_sched_buf);
+
+	va_start(args, fmt);
+	r = vsnprintf(buf, PRINTK_BUF_SIZE, fmt, args);
+	va_end(args);
+
+	__this_cpu_or(printk_pending, PRINTK_PENDING_SCHED);
+	local_irq_restore(flags);
+
+	return r;
+}
+
 /*
  * printk rate limiting, lifted from the networking subsystem.
  *
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index e8a1f83ee0e7..0984a21076a3 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -195,20 +195,20 @@ __setup("noautogroup", setup_autogroup);
 
 #ifdef CONFIG_PROC_FS
 
-int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice)
+int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
 {
 	static unsigned long next = INITIAL_JIFFIES;
 	struct autogroup *ag;
 	int err;
 
-	if (*nice < -20 || *nice > 19)
+	if (nice < -20 || nice > 19)
 		return -EINVAL;
 
-	err = security_task_setnice(current, *nice);
+	err = security_task_setnice(current, nice);
 	if (err)
 		return err;
 
-	if (*nice < 0 && !can_nice(current, *nice))
+	if (nice < 0 && !can_nice(current, nice))
 		return -EPERM;
 
 	/* this is a heavy operation taking global locks.. */
@@ -219,9 +219,9 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice)
 	ag = autogroup_task_get(p);
 
 	down_write(&ag->lock);
-	err = sched_group_set_shares(ag->tg, prio_to_weight[*nice + 20]);
+	err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]);
 	if (!err)
-		ag->nice = *nice;
+		ag->nice = nice;
 	up_write(&ag->lock);
 
 	autogroup_kref_put(ag);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6c41ba49767a..d2bd4647586c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1284,7 +1284,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	 * leave kernel.
 	 */
 	if (p->mm && printk_ratelimit()) {
-		printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n",
+		printk_sched("process %d (%s) no longer affine to cpu%d\n",
 				task_pid_nr(p), p->comm, cpu);
 	}
 
@@ -1507,7 +1507,7 @@ static int ttwu_activate_remote(struct task_struct *p, int wake_flags)
 }
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
 
-static inline int ttwu_share_cache(int this_cpu, int that_cpu)
+bool cpus_share_cache(int this_cpu, int that_cpu)
 {
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
@@ -1518,7 +1518,7 @@ static void ttwu_queue(struct task_struct *p, int cpu)
 	struct rq *rq = cpu_rq(cpu);
 
 #if defined(CONFIG_SMP)
-	if (sched_feat(TTWU_QUEUE) && !ttwu_share_cache(smp_processor_id(), cpu)) {
+	if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
 		sched_clock_cpu(cpu); /* sync clocks x-cpu */
 		ttwu_queue_remote(p, cpu);
 		return;
@@ -2266,13 +2266,10 @@ calc_load_n(unsigned long load, unsigned long exp,
  * Once we've updated the global active value, we need to apply the exponential
  * weights adjusted to the number of cycles missed.
  */
-static void calc_global_nohz(unsigned long ticks)
+static void calc_global_nohz(void)
 {
 	long delta, active, n;
 
-	if (time_before(jiffies, calc_load_update))
-		return;
-
 	/*
 	 * If we crossed a calc_load_update boundary, make sure to fold
 	 * any pending idle changes, the respective CPUs might have
@@ -2284,31 +2281,25 @@ static void calc_global_nohz(unsigned long ticks)
 		atomic_long_add(delta, &calc_load_tasks);
 
 	/*
-	 * If we were idle for multiple load cycles, apply them.
+	 * It could be the one fold was all it took, we done!
 	 */
-	if (ticks >= LOAD_FREQ) {
-		n = ticks / LOAD_FREQ;
+	if (time_before(jiffies, calc_load_update + 10))
+		return;
 
-		active = atomic_long_read(&calc_load_tasks);
-		active = active > 0 ? active * FIXED_1 : 0;
+	/*
+	 * Catch-up, fold however many we are behind still
+	 */
+	delta = jiffies - calc_load_update - 10;
+	n = 1 + (delta / LOAD_FREQ);
 
-		avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
-		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
-		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+	active = atomic_long_read(&calc_load_tasks);
+	active = active > 0 ? active * FIXED_1 : 0;
 
-		calc_load_update += n * LOAD_FREQ;
-	}
+	avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+	avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+	avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
 
-	/*
-	 * Its possible the remainder of the above division also crosses
-	 * a LOAD_FREQ period, the regular check in calc_global_load()
-	 * which comes after this will take care of that.
-	 *
-	 * Consider us being 11 ticks before a cycle completion, and us
-	 * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
-	 * age us 4 cycles, and the test in calc_global_load() will
-	 * pick up the final one.
-	 */
+	calc_load_update += n * LOAD_FREQ;
 }
 #else
 void calc_load_account_idle(struct rq *this_rq)
@@ -2320,7 +2311,7 @@ static inline long calc_load_fold_idle(void)
 	return 0;
 }
 
-static void calc_global_nohz(unsigned long ticks)
+static void calc_global_nohz(void)
 {
 }
 #endif
@@ -2348,8 +2339,6 @@ void calc_global_load(unsigned long ticks)
 {
 	long active;
 
-	calc_global_nohz(ticks);
-
 	if (time_before(jiffies, calc_load_update + 10))
 		return;
 
@@ -2361,6 +2350,16 @@ void calc_global_load(unsigned long ticks)
 	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
 
 	calc_load_update += LOAD_FREQ;
+
+	/*
+	 * Account one period with whatever state we found before
+	 * folding in the nohz state and ageing the entire idle period.
+	 *
+	 * This avoids loosing a sample when we go idle between 
+	 * calc_load_account_active() (10 ticks ago) and now and thus
+	 * under-accounting.
+	 */
+	calc_global_nohz();
 }
 
 /*
@@ -3220,14 +3219,14 @@ need_resched:
 
 	post_schedule(rq);
 
-	preempt_enable_no_resched();
+	sched_preempt_enable_no_resched();
 	if (need_resched())
 		goto need_resched;
 }
 
 static inline void sched_submit_work(struct task_struct *tsk)
 {
-	if (!tsk->state)
+	if (!tsk->state || tsk_is_pi_blocked(tsk))
 		return;
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
@@ -3246,6 +3245,18 @@ asmlinkage void __sched schedule(void)
 }
 EXPORT_SYMBOL(schedule);
 
+/**
+ * schedule_preempt_disabled - called with preemption disabled
+ *
+ * Returns with preemption disabled. Note: preempt_count must be 1
+ */
+void __sched schedule_preempt_disabled(void)
+{
+	sched_preempt_enable_no_resched();
+	schedule();
+	preempt_disable();
+}
+
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 
 static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
@@ -3406,9 +3417,9 @@ EXPORT_SYMBOL(__wake_up);
 /*
  * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
  */
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
 {
-	__wake_up_common(q, mode, 1, 0, NULL);
+	__wake_up_common(q, mode, nr, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
@@ -3767,6 +3778,24 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	rq = __task_rq_lock(p);
 
+	/*
+	 * Idle task boosting is a nono in general. There is one
+	 * exception, when PREEMPT_RT and NOHZ is active:
+	 *
+	 * The idle task calls get_next_timer_interrupt() and holds
+	 * the timer wheel base->lock on the CPU and another CPU wants
+	 * to access the timer (probably to cancel it). We can safely
+	 * ignore the boosting request, as the idle CPU runs this code
+	 * with interrupts disabled and will complete the lock
+	 * protected section without being interrupted. So there is no
+	 * real need to boost.
+	 */
+	if (unlikely(p == rq->idle)) {
+		WARN_ON(p != rq->curr);
+		WARN_ON(p->pi_blocked_on);
+		goto out_unlock;
+	}
+
 	trace_sched_pi_setprio(p, prio);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
@@ -3790,11 +3819,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
 	check_class_changed(rq, p, prev_class, oldprio);
+out_unlock:
 	__task_rq_unlock(rq);
 }
-
 #endif
-
 void set_user_nice(struct task_struct *p, long nice)
 {
 	int old_prio, delta, on_rq;
@@ -4474,7 +4502,7 @@ SYSCALL_DEFINE0(sched_yield)
 	__release(rq->lock);
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 	do_raw_spin_unlock(&rq->lock);
-	preempt_enable_no_resched();
+	sched_preempt_enable_no_resched();
 
 	schedule();
 
@@ -4548,8 +4576,24 @@ EXPORT_SYMBOL(__cond_resched_softirq);
 /**
  * yield - yield the current processor to other threads.
  *
- * This is a shortcut for kernel-space yielding - it marks the
- * thread runnable and calls sys_sched_yield().
+ * Do not ever use this function, there's a 99% chance you're doing it wrong.
+ *
+ * The scheduler is at all times free to pick the calling task as the most
+ * eligible task to run, if removing the yield() call from your code breaks
+ * it, its already broken.
+ *
+ * Typical broken usage is:
+ *
+ * while (!event)
+ * 	yield();
+ *
+ * where one assumes that yield() will let 'the other' process run that will
+ * make event true. If the current task is a SCHED_FIFO task that will never
+ * happen. Never use yield() as a progress guarantee!!
+ *
+ * If you want to use yield() to wait for something, use wait_event().
+ * If you want to use yield() to be 'nice' for others, use cond_resched().
+ * If you still want to use yield(), do not!
  */
 void __sched yield(void)
 {
@@ -5381,7 +5425,7 @@ static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
 				      unsigned long action, void *hcpu)
 {
 	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
+	case CPU_STARTING:
 	case CPU_DOWN_FAILED:
 		set_cpu_active((long)hcpu, true);
 		return NOTIFY_OK;
@@ -5753,7 +5797,7 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu)
  *
  * Also keep a unique ID per domain (we use the first cpu number in
  * the cpumask of the domain), this allows us to quickly tell if
- * two cpus are in the same cache domain, see ttwu_share_cache().
+ * two cpus are in the same cache domain, see cpus_share_cache().
  */
 DEFINE_PER_CPU(struct sched_domain *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_id);
@@ -6930,6 +6974,9 @@ void __init sched_init(void)
 		rq->online = 0;
 		rq->idle_stamp = 0;
 		rq->avg_idle = 2*sysctl_sched_migration_cost;
+
+		INIT_LIST_HEAD(&rq->cfs_tasks);
+
 		rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ
 		rq->nohz_flags = 0;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 2a075e10004b..09acaa15161d 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -288,7 +288,6 @@ static void print_cpu(struct seq_file *m, int cpu)
 
 	P(yld_count);
 
-	P(sched_switch);
 	P(sched_count);
 	P(sched_goidle);
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fd974faf467d..94340c7544a9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -776,29 +776,16 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
-#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
-static void
-add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
-{
-	cfs_rq->task_weight += weight;
-}
-#else
-static inline void
-add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
-{
-}
-#endif
-
 static void
 account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_add(&cfs_rq->load, se->load.weight);
 	if (!parent_entity(se))
 		update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
-	if (entity_is_task(se)) {
-		add_cfs_task_weight(cfs_rq, se->load.weight);
-		list_add(&se->group_node, &cfs_rq->tasks);
-	}
+#ifdef CONFIG_SMP
+	if (entity_is_task(se))
+		list_add_tail(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
+#endif
 	cfs_rq->nr_running++;
 }
 
@@ -808,10 +795,8 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	update_load_sub(&cfs_rq->load, se->load.weight);
 	if (!parent_entity(se))
 		update_load_sub(&rq_of(cfs_rq)->load, se->load.weight);
-	if (entity_is_task(se)) {
-		add_cfs_task_weight(cfs_rq, -se->load.weight);
+	if (entity_is_task(se))
 		list_del_init(&se->group_node);
-	}
 	cfs_rq->nr_running--;
 }
 
@@ -2672,8 +2657,6 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	/*
 	 * Otherwise, iterate the domains and find an elegible idle cpu.
 	 */
-	rcu_read_lock();
-
 	sd = rcu_dereference(per_cpu(sd_llc, target));
 	for_each_lower_domain(sd) {
 		sg = sd->groups;
@@ -2695,8 +2678,6 @@ next:
 		} while (sg != sd->groups);
 	}
 done:
-	rcu_read_unlock();
-
 	return target;
 }
 
@@ -2922,7 +2903,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 		return;
 
 	/*
-	 * This is possible from callers such as pull_task(), in which we
+	 * This is possible from callers such as move_task(), in which we
 	 * unconditionally check_prempt_curr() after an enqueue (which may have
 	 * lead to a throttle).  This both saves work and prevents false
 	 * next-buddy nomination below.
@@ -3086,17 +3067,39 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp
  * Fair scheduling class load-balancing methods:
  */
 
+static unsigned long __read_mostly max_load_balance_interval = HZ/10;
+
+#define LBF_ALL_PINNED	0x01
+#define LBF_NEED_BREAK	0x02
+
+struct lb_env {
+	struct sched_domain	*sd;
+
+	int			src_cpu;
+	struct rq		*src_rq;
+
+	int			dst_cpu;
+	struct rq		*dst_rq;
+
+	enum cpu_idle_type	idle;
+	long			load_move;
+	unsigned int		flags;
+
+	unsigned int		loop;
+	unsigned int		loop_break;
+	unsigned int		loop_max;
+};
+
 /*
- * pull_task - move a task from a remote runqueue to the local runqueue.
+ * move_task - move a task from one runqueue to another runqueue.
  * Both runqueues must be locked.
  */
-static void pull_task(struct rq *src_rq, struct task_struct *p,
-		      struct rq *this_rq, int this_cpu)
+static void move_task(struct task_struct *p, struct lb_env *env)
 {
-	deactivate_task(src_rq, p, 0);
-	set_task_cpu(p, this_cpu);
-	activate_task(this_rq, p, 0);
-	check_preempt_curr(this_rq, p, 0);
+	deactivate_task(env->src_rq, p, 0);
+	set_task_cpu(p, env->dst_cpu);
+	activate_task(env->dst_rq, p, 0);
+	check_preempt_curr(env->dst_rq, p, 0);
 }
 
 /*
@@ -3131,19 +3134,11 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 	return delta < (s64)sysctl_sched_migration_cost;
 }
 
-#define LBF_ALL_PINNED	0x01
-#define LBF_NEED_BREAK	0x02	/* clears into HAD_BREAK */
-#define LBF_HAD_BREAK	0x04
-#define LBF_HAD_BREAKS	0x0C	/* count HAD_BREAKs overflows into ABORT */
-#define LBF_ABORT	0x10
-
 /*
  * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
  */
 static
-int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
-		     struct sched_domain *sd, enum cpu_idle_type idle,
-		     int *lb_flags)
+int can_migrate_task(struct task_struct *p, struct lb_env *env)
 {
 	int tsk_cache_hot = 0;
 	/*
@@ -3152,13 +3147,13 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
 	 * 3) are cache-hot on their current CPU.
 	 */
-	if (!cpumask_test_cpu(this_cpu, tsk_cpus_allowed(p))) {
+	if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
 		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
 		return 0;
 	}
-	*lb_flags &= ~LBF_ALL_PINNED;
+	env->flags &= ~LBF_ALL_PINNED;
 
-	if (task_running(rq, p)) {
+	if (task_running(env->src_rq, p)) {
 		schedstat_inc(p, se.statistics.nr_failed_migrations_running);
 		return 0;
 	}
@@ -3169,12 +3164,12 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 	 * 2) too many balance attempts have failed.
 	 */
 
-	tsk_cache_hot = task_hot(p, rq->clock_task, sd);
+	tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
 	if (!tsk_cache_hot ||
-		sd->nr_balance_failed > sd->cache_nice_tries) {
+		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
 #ifdef CONFIG_SCHEDSTATS
 		if (tsk_cache_hot) {
-			schedstat_inc(sd, lb_hot_gained[idle]);
+			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
 			schedstat_inc(p, se.statistics.nr_forced_migrations);
 		}
 #endif
@@ -3195,65 +3190,80 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
  *
  * Called with both runqueues locked.
  */
-static int
-move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-	      struct sched_domain *sd, enum cpu_idle_type idle)
+static int move_one_task(struct lb_env *env)
 {
 	struct task_struct *p, *n;
-	struct cfs_rq *cfs_rq;
-	int pinned = 0;
 
-	for_each_leaf_cfs_rq(busiest, cfs_rq) {
-		list_for_each_entry_safe(p, n, &cfs_rq->tasks, se.group_node) {
-			if (throttled_lb_pair(task_group(p),
-					      busiest->cpu, this_cpu))
-				break;
+	list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
+		if (throttled_lb_pair(task_group(p), env->src_rq->cpu, env->dst_cpu))
+			continue;
 
-			if (!can_migrate_task(p, busiest, this_cpu,
-						sd, idle, &pinned))
-				continue;
+		if (!can_migrate_task(p, env))
+			continue;
 
-			pull_task(busiest, p, this_rq, this_cpu);
-			/*
-			 * Right now, this is only the second place pull_task()
-			 * is called, so we can safely collect pull_task()
-			 * stats here rather than inside pull_task().
-			 */
-			schedstat_inc(sd, lb_gained[idle]);
-			return 1;
-		}
+		move_task(p, env);
+		/*
+		 * Right now, this is only the second place move_task()
+		 * is called, so we can safely collect move_task()
+		 * stats here rather than inside move_task().
+		 */
+		schedstat_inc(env->sd, lb_gained[env->idle]);
+		return 1;
 	}
-
 	return 0;
 }
 
-static unsigned long
-balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
-	      unsigned long max_load_move, struct sched_domain *sd,
-	      enum cpu_idle_type idle, int *lb_flags,
-	      struct cfs_rq *busiest_cfs_rq)
+static unsigned long task_h_load(struct task_struct *p);
+
+/*
+ * move_tasks tries to move up to load_move weighted load from busiest to
+ * this_rq, as part of a balancing operation within domain "sd".
+ * Returns 1 if successful and 0 otherwise.
+ *
+ * Called with both runqueues locked.
+ */
+static int move_tasks(struct lb_env *env)
 {
-	int loops = 0, pulled = 0;
-	long rem_load_move = max_load_move;
-	struct task_struct *p, *n;
+	struct list_head *tasks = &env->src_rq->cfs_tasks;
+	struct task_struct *p;
+	unsigned long load;
+	int pulled = 0;
+
+	if (env->load_move <= 0)
+		return 0;
 
-	if (max_load_move == 0)
-		goto out;
+	while (!list_empty(tasks)) {
+		p = list_first_entry(tasks, struct task_struct, se.group_node);
 
-	list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) {
-		if (loops++ > sysctl_sched_nr_migrate) {
-			*lb_flags |= LBF_NEED_BREAK;
+		env->loop++;
+		/* We've more or less seen every task there is, call it quits */
+		if (env->loop > env->loop_max)
+			break;
+
+		/* take a breather every nr_migrate tasks */
+		if (env->loop > env->loop_break) {
+			env->loop_break += sysctl_sched_nr_migrate;
+			env->flags |= LBF_NEED_BREAK;
 			break;
 		}
 
-		if ((p->se.load.weight >> 1) > rem_load_move ||
-		    !can_migrate_task(p, busiest, this_cpu, sd, idle,
-				      lb_flags))
-			continue;
+		if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
+			goto next;
+
+		load = task_h_load(p);
+
+		if (load < 16 && !env->sd->nr_balance_failed)
+			goto next;
+
+		if ((load / 2) > env->load_move)
+			goto next;
 
-		pull_task(busiest, p, this_rq, this_cpu);
+		if (!can_migrate_task(p, env))
+			goto next;
+
+		move_task(p, env);
 		pulled++;
-		rem_load_move -= p->se.load.weight;
+		env->load_move -= load;
 
 #ifdef CONFIG_PREEMPT
 		/*
@@ -3261,28 +3271,30 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		 * kernels will stop after the first task is pulled to minimize
 		 * the critical section.
 		 */
-		if (idle == CPU_NEWLY_IDLE) {
-			*lb_flags |= LBF_ABORT;
+		if (env->idle == CPU_NEWLY_IDLE)
 			break;
-		}
 #endif
 
 		/*
 		 * We only want to steal up to the prescribed amount of
 		 * weighted load.
 		 */
-		if (rem_load_move <= 0)
+		if (env->load_move <= 0)
 			break;
+
+		continue;
+next:
+		list_move_tail(&p->se.group_node, tasks);
 	}
-out:
+
 	/*
-	 * Right now, this is one of only two places pull_task() is called,
-	 * so we can safely collect pull_task() stats here rather than
-	 * inside pull_task().
+	 * Right now, this is one of only two places move_task() is called,
+	 * so we can safely collect move_task() stats here rather than
+	 * inside move_task().
 	 */
-	schedstat_add(sd, lb_gained[idle], pulled);
+	schedstat_add(env->sd, lb_gained[env->idle], pulled);
 
-	return max_load_move - rem_load_move;
+	return pulled;
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -3362,113 +3374,35 @@ static int tg_load_down(struct task_group *tg, void *data)
 
 static void update_h_load(long cpu)
 {
+	rcu_read_lock();
 	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
+	rcu_read_unlock();
 }
 
-static unsigned long
-load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_load_move,
-		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *lb_flags)
+static unsigned long task_h_load(struct task_struct *p)
 {
-	long rem_load_move = max_load_move;
-	struct cfs_rq *busiest_cfs_rq;
-
-	rcu_read_lock();
-	update_h_load(cpu_of(busiest));
-
-	for_each_leaf_cfs_rq(busiest, busiest_cfs_rq) {
-		unsigned long busiest_h_load = busiest_cfs_rq->h_load;
-		unsigned long busiest_weight = busiest_cfs_rq->load.weight;
-		u64 rem_load, moved_load;
-
-		if (*lb_flags & (LBF_NEED_BREAK|LBF_ABORT))
-			break;
-
-		/*
-		 * empty group or part of a throttled hierarchy
-		 */
-		if (!busiest_cfs_rq->task_weight ||
-		    throttled_lb_pair(busiest_cfs_rq->tg, cpu_of(busiest), this_cpu))
-			continue;
-
-		rem_load = (u64)rem_load_move * busiest_weight;
-		rem_load = div_u64(rem_load, busiest_h_load + 1);
-
-		moved_load = balance_tasks(this_rq, this_cpu, busiest,
-				rem_load, sd, idle, lb_flags,
-				busiest_cfs_rq);
-
-		if (!moved_load)
-			continue;
+	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+	unsigned long load;
 
-		moved_load *= busiest_h_load;
-		moved_load = div_u64(moved_load, busiest_weight + 1);
+	load = p->se.load.weight;
+	load = div_u64(load * cfs_rq->h_load, cfs_rq->load.weight + 1);
 
-		rem_load_move -= moved_load;
-		if (rem_load_move < 0)
-			break;
-	}
-	rcu_read_unlock();
-
-	return max_load_move - rem_load_move;
+	return load;
 }
 #else
 static inline void update_shares(int cpu)
 {
 }
 
-static unsigned long
-load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_load_move,
-		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *lb_flags)
+static inline void update_h_load(long cpu)
 {
-	return balance_tasks(this_rq, this_cpu, busiest,
-			max_load_move, sd, idle, lb_flags,
-			&busiest->cfs);
 }
-#endif
 
-/*
- * move_tasks tries to move up to max_load_move weighted load from busiest to
- * this_rq, as part of a balancing operation within domain "sd".
- * Returns 1 if successful and 0 otherwise.
- *
- * Called with both runqueues locked.
- */
-static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		      unsigned long max_load_move,
-		      struct sched_domain *sd, enum cpu_idle_type idle,
-		      int *lb_flags)
+static unsigned long task_h_load(struct task_struct *p)
 {
-	unsigned long total_load_moved = 0, load_moved;
-
-	do {
-		load_moved = load_balance_fair(this_rq, this_cpu, busiest,
-				max_load_move - total_load_moved,
-				sd, idle, lb_flags);
-
-		total_load_moved += load_moved;
-
-		if (*lb_flags & (LBF_NEED_BREAK|LBF_ABORT))
-			break;
-
-#ifdef CONFIG_PREEMPT
-		/*
-		 * NEWIDLE balancing is a source of latency, so preemptible
-		 * kernels will stop after the first task is pulled to minimize
-		 * the critical section.
-		 */
-		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) {
-			*lb_flags |= LBF_ABORT;
-			break;
-		}
-#endif
-	} while (load_moved && max_load_move > total_load_moved);
-
-	return total_load_moved > 0;
+	return p->se.load.weight;
 }
+#endif
 
 /********** Helpers for find_busiest_group ************************/
 /*
@@ -3778,6 +3712,11 @@ void update_group_power(struct sched_domain *sd, int cpu)
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
 	unsigned long power;
+	unsigned long interval;
+
+	interval = msecs_to_jiffies(sd->balance_interval);
+	interval = clamp(interval, 1UL, max_load_balance_interval);
+	sdg->sgp->next_update = jiffies + interval;
 
 	if (!child) {
 		update_cpu_power(sd, cpu);
@@ -3885,12 +3824,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	 * domains. In the newly idle case, we will allow all the cpu's
 	 * to do the newly idle load balance.
 	 */
-	if (idle != CPU_NEWLY_IDLE && local_group) {
-		if (balance_cpu != this_cpu) {
-			*balance = 0;
-			return;
-		}
-		update_group_power(sd, this_cpu);
+	if (local_group) {
+		if (idle != CPU_NEWLY_IDLE) {
+			if (balance_cpu != this_cpu) {
+				*balance = 0;
+				return;
+			}
+			update_group_power(sd, this_cpu);
+		} else if (time_after_eq(jiffies, group->sgp->next_update))
+			update_group_power(sd, this_cpu);
 	}
 
 	/* Adjust by relative CPU power of the group */
@@ -4453,13 +4395,21 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			struct sched_domain *sd, enum cpu_idle_type idle,
 			int *balance)
 {
-	int ld_moved, lb_flags = 0, active_balance = 0;
+	int ld_moved, active_balance = 0;
 	struct sched_group *group;
 	unsigned long imbalance;
 	struct rq *busiest;
 	unsigned long flags;
 	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
+	struct lb_env env = {
+		.sd		= sd,
+		.dst_cpu	= this_cpu,
+		.dst_rq		= this_rq,
+		.idle		= idle,
+		.loop_break	= sysctl_sched_nr_migrate,
+	};
+
 	cpumask_copy(cpus, cpu_active_mask);
 
 	schedstat_inc(sd, lb_count[idle]);
@@ -4494,32 +4444,34 @@ redo:
 		 * still unbalanced. ld_moved simply stays zero, so it is
 		 * correctly treated as an imbalance.
 		 */
-		lb_flags |= LBF_ALL_PINNED;
+		env.flags |= LBF_ALL_PINNED;
+		env.load_move = imbalance;
+		env.src_cpu = busiest->cpu;
+		env.src_rq = busiest;
+		env.loop_max = busiest->nr_running;
+
+more_balance:
 		local_irq_save(flags);
 		double_rq_lock(this_rq, busiest);
-		ld_moved = move_tasks(this_rq, this_cpu, busiest,
-				      imbalance, sd, idle, &lb_flags);
+		if (!env.loop)
+			update_h_load(env.src_cpu);
+		ld_moved += move_tasks(&env);
 		double_rq_unlock(this_rq, busiest);
 		local_irq_restore(flags);
 
+		if (env.flags & LBF_NEED_BREAK) {
+			env.flags &= ~LBF_NEED_BREAK;
+			goto more_balance;
+		}
+
 		/*
 		 * some other cpu did the load balance for us.
 		 */
 		if (ld_moved && this_cpu != smp_processor_id())
 			resched_cpu(this_cpu);
 
-		if (lb_flags & LBF_ABORT)
-			goto out_balanced;
-
-		if (lb_flags & LBF_NEED_BREAK) {
-			lb_flags += LBF_HAD_BREAK - LBF_NEED_BREAK;
-			if (lb_flags & LBF_ABORT)
-				goto out_balanced;
-			goto redo;
-		}
-
 		/* All tasks on this runqueue were pinned by CPU affinity */
-		if (unlikely(lb_flags & LBF_ALL_PINNED)) {
+		if (unlikely(env.flags & LBF_ALL_PINNED)) {
 			cpumask_clear_cpu(cpu_of(busiest), cpus);
 			if (!cpumask_empty(cpus))
 				goto redo;
@@ -4549,7 +4501,7 @@ redo:
 					tsk_cpus_allowed(busiest->curr))) {
 				raw_spin_unlock_irqrestore(&busiest->lock,
 							    flags);
-				lb_flags |= LBF_ALL_PINNED;
+				env.flags |= LBF_ALL_PINNED;
 				goto out_one_pinned;
 			}
 
@@ -4602,7 +4554,7 @@ out_balanced:
 
 out_one_pinned:
 	/* tune up the balancing interval */
-	if (((lb_flags & LBF_ALL_PINNED) &&
+	if (((env.flags & LBF_ALL_PINNED) &&
 			sd->balance_interval < MAX_PINNED_INTERVAL) ||
 			(sd->balance_interval < sd->max_interval))
 		sd->balance_interval *= 2;
@@ -4712,10 +4664,18 @@ static int active_load_balance_cpu_stop(void *data)
 	}
 
 	if (likely(sd)) {
+		struct lb_env env = {
+			.sd		= sd,
+			.dst_cpu	= target_cpu,
+			.dst_rq		= target_rq,
+			.src_cpu	= busiest_rq->cpu,
+			.src_rq		= busiest_rq,
+			.idle		= CPU_IDLE,
+		};
+
 		schedstat_inc(sd, alb_count);
 
-		if (move_one_task(target_rq, target_cpu, busiest_rq,
-				  sd, CPU_IDLE))
+		if (move_one_task(&env))
 			schedstat_inc(sd, alb_pushed);
 		else
 			schedstat_inc(sd, alb_failed);
@@ -4947,8 +4907,6 @@ static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb,
 
 static DEFINE_SPINLOCK(balancing);
 
-static unsigned long __read_mostly max_load_balance_interval = HZ/10;
-
 /*
  * Scale the max load_balance interval with the number of CPUs in the system.
  * This trades load-balance latency on larger machines for less cross talk.
@@ -5342,7 +5300,6 @@ static void set_curr_task_fair(struct rq *rq)
 void init_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	cfs_rq->tasks_timeline = RB_ROOT;
-	INIT_LIST_HEAD(&cfs_rq->tasks);
 	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
 #ifndef CONFIG_64BIT
 	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
@@ -5614,6 +5571,7 @@ __init void init_sched_fair_class(void)
 	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
 
 #ifdef CONFIG_NO_HZ
+	nohz.next_balance = jiffies;
 	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
 	cpu_notifier(sched_ilb_notifier, 0);
 #endif
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index f42ae7fb5ec5..b60dad720173 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -778,12 +778,9 @@ static inline int balance_runtime(struct rt_rq *rt_rq)
 
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 {
-	int i, idle = 1;
+	int i, idle = 1, throttled = 0;
 	const struct cpumask *span;
 
-	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
-		return 1;
-
 	span = sched_rt_period_mask();
 	for_each_cpu(i, span) {
 		int enqueue = 0;
@@ -818,12 +815,17 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 			if (!rt_rq_throttled(rt_rq))
 				enqueue = 1;
 		}
+		if (rt_rq->rt_throttled)
+			throttled = 1;
 
 		if (enqueue)
 			sched_rt_rq_enqueue(rt_rq);
 		raw_spin_unlock(&rq->lock);
 	}
 
+	if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF))
+		return 1;
+
 	return idle;
 }
 
@@ -855,8 +857,30 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 		return 0;
 
 	if (rt_rq->rt_time > runtime) {
-		rt_rq->rt_throttled = 1;
-		printk_once(KERN_WARNING "sched: RT throttling activated\n");
+		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+		/*
+		 * Don't actually throttle groups that have no runtime assigned
+		 * but accrue some time due to boosting.
+		 */
+		if (likely(rt_b->rt_runtime)) {
+			static bool once = false;
+
+			rt_rq->rt_throttled = 1;
+
+			if (!once) {
+				once = true;
+				printk_sched("sched: RT throttling activated\n");
+			}
+		} else {
+			/*
+			 * In case we did anyway, make it go away,
+			 * replenishment is a joke, since it will replenish us
+			 * with exactly 0 ns.
+			 */
+			rt_rq->rt_time = 0;
+		}
+
 		if (rt_rq_throttled(rt_rq)) {
 			sched_rt_rq_dequeue(rt_rq);
 			return 1;
@@ -884,7 +908,8 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely((s64)delta_exec < 0))
 		delta_exec = 0;
 
-	schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec));
+	schedstat_set(curr->se.statistics.exec_max,
+		      max(curr->se.statistics.exec_max, delta_exec));
 
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
@@ -1972,7 +1997,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	if (--p->rt.time_slice)
 		return;
 
-	p->rt.time_slice = DEF_TIMESLICE;
+	p->rt.time_slice = RR_TIMESLICE;
 
 	/*
 	 * Requeue to the end of queue if we are not the only element
@@ -2000,7 +2025,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 	 * Time slice is 0 for SCHED_FIFO tasks
 	 */
 	if (task->policy == SCHED_RR)
-		return DEF_TIMESLICE;
+		return RR_TIMESLICE;
 	else
 		return 0;
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b4cd6d8ea150..42b1f304b044 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -36,11 +36,7 @@ extern __read_mostly int scheduler_running;
 
 /*
  * These are the 'tuning knobs' of the scheduler:
- *
- * default timeslice is 100 msecs (used only for SCHED_RR tasks).
- * Timeslices get refilled after they expire.
  */
-#define DEF_TIMESLICE		(100 * HZ / 1000)
 
 /*
  * single value that denotes runtime == period, ie unlimited time.
@@ -216,9 +212,6 @@ struct cfs_rq {
 	struct rb_root tasks_timeline;
 	struct rb_node *rb_leftmost;
 
-	struct list_head tasks;
-	struct list_head *balance_iterator;
-
 	/*
 	 * 'curr' points to currently running entity on this cfs_rq.
 	 * It is set to NULL otherwise (i.e when none are currently running).
@@ -246,11 +239,6 @@ struct cfs_rq {
 
 #ifdef CONFIG_SMP
 	/*
-	 * the part of load.weight contributed by tasks
-	 */
-	unsigned long task_weight;
-
-	/*
 	 *   h_load = weight * f(tg)
 	 *
 	 * Where f(tg) is the recursive weight fraction assigned to
@@ -424,6 +412,8 @@ struct rq {
 	int cpu;
 	int online;
 
+	struct list_head cfs_tasks;
+
 	u64 rt_avg;
 	u64 age_stamp;
 	u64 idle_stamp;
@@ -462,7 +452,6 @@ struct rq {
 	unsigned int yld_count;
 
 	/* schedule() stats */
-	unsigned int sched_switch;
 	unsigned int sched_count;
 	unsigned int sched_goidle;
 
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 2a581ba8e190..903ffa9e8872 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -32,9 +32,9 @@ static int show_schedstat(struct seq_file *seq, void *v)
 
 		/* runqueue-specific stats */
 		seq_printf(seq,
-		    "cpu%d %u %u %u %u %u %u %llu %llu %lu",
+		    "cpu%d %u 0 %u %u %u %u %llu %llu %lu",
 		    cpu, rq->yld_count,
-		    rq->sched_switch, rq->sched_count, rq->sched_goidle,
+		    rq->sched_count, rq->sched_goidle,
 		    rq->ttwu_count, rq->ttwu_local,
 		    rq->rq_cpu_time,
 		    rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 8afc6a8d4d7c..15352e0cbd5d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -343,7 +343,7 @@ void irq_exit(void)
 		tick_nohz_irq_exit();
 #endif
 	rcu_irq_exit();
-	preempt_enable_no_resched();
+	sched_preempt_enable_no_resched();
 }
 
 /*
@@ -740,9 +740,7 @@ static int run_ksoftirqd(void * __bind_cpu)
 	while (!kthread_should_stop()) {
 		preempt_disable();
 		if (!local_softirq_pending()) {
-			preempt_enable_no_resched();
-			schedule();
-			preempt_disable();
+			schedule_preempt_disabled();
 		}
 
 		__set_current_state(TASK_RUNNING);
@@ -757,7 +755,7 @@ static int run_ksoftirqd(void * __bind_cpu)
 			if (local_softirq_pending())
 				__do_softirq();
 			local_irq_enable();
-			preempt_enable_no_resched();
+			sched_preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
 			rcu_note_context_switch((long)__bind_cpu);