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: (49 commits) stop_machine: Move local variable closer to the usage site in cpu_stop_cpu_callback() sched, wait: Use wrapper functions sched: Remove a stale comment ondemand: Make the iowait-is-busy time a sysfs tunable ondemand: Solve a big performance issue by counting IOWAIT time as busy sched: Intoduce get_cpu_iowait_time_us() sched: Eliminate the ts->idle_lastupdate field sched: Fold updating of the last_update_time_info into update_ts_time_stats() sched: Update the idle statistics in get_cpu_idle_time_us() sched: Introduce a function to update the idle statistics sched: Add a comment to get_cpu_idle_time_us() cpu_stop: add dummy implementation for UP sched: Remove rq argument to the tracepoints rcu: need barrier() in UP synchronize_sched_expedited() sched: correctly place paranioa memory barriers in synchronize_sched_expedited() sched: kill paranoia check in synchronize_sched_expedited() sched: replace migration_thread with cpu_stop stop_machine: reimplement using cpu_stop cpu_stop: implement stop_cpu[s]() sched: Fix select_idle_sibling() logic in select_task_rq_fair() ...
2010-05-18 08:27:54 -07:00
parent 4d7b4ac22f 9c6f7e43b4
commit b8ae30ee26
39 changed files with 1253 additions and 1261 deletions
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -68,7 +68,7 @@ obj-$(CONFIG_USER_NS) += user_namespace.o
 obj-$(CONFIG_PID_NS) += pid_namespace.o
 obj-$(CONFIG_IKCONFIG) += configs.o
 obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
-obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
+obj-$(CONFIG_SMP) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o audit_watch.o
 obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -15,7 +15,6 @@
 #include <linux/syscalls.h>
 #include <linux/pid_namespace.h>
 #include <asm/uaccess.h>
-#include "cred-internals.h"

 /*
 * Leveraged for setting/resetting capabilities
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -3016,7 +3016,7 @@ static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
 	unsigned long flags = (unsigned long)key;

 	if (flags & POLLHUP) {
-		remove_wait_queue_locked(event->wqh, &event->wait);
+		__remove_wait_queue(event->wqh, &event->wait);
 		spin_lock(&cgrp->event_list_lock);
 		list_del(&event->list);
 		spin_unlock(&cgrp->event_list_lock);
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -164,6 +164,7 @@ static inline void check_for_tasks(int cpu)
 }

 struct take_cpu_down_param {
+	struct task_struct *caller;
 	unsigned long mod;
 	void *hcpu;
 };
@@ -172,6 +173,7 @@ struct take_cpu_down_param {
 static int __ref take_cpu_down(void *_param)
 {
 	struct take_cpu_down_param *param = _param;
+	unsigned int cpu = (unsigned long)param->hcpu;
 	int err;

 	/* Ensure this CPU doesn't handle any more interrupts. */
@@ -182,6 +184,8 @@ static int __ref take_cpu_down(void *_param)
 	raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
 				param->hcpu);

+	if (task_cpu(param->caller) == cpu)
+		move_task_off_dead_cpu(cpu, param->caller);
 	/* Force idle task to run as soon as we yield: it should
 	   immediately notice cpu is offline and die quickly. */
 	sched_idle_next();
@@ -192,10 +196,10 @@ static int __ref take_cpu_down(void *_param)
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
 	int err, nr_calls = 0;
-	cpumask_var_t old_allowed;
 	void *hcpu = (void *)(long)cpu;
 	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
 	struct take_cpu_down_param tcd_param = {
+		.caller = current,
 		.mod = mod,
 		.hcpu = hcpu,
 	};
@@ -206,9 +210,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	if (!cpu_online(cpu))
 		return -EINVAL;

-	if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
-		return -ENOMEM;
-
 	cpu_hotplug_begin();
 	set_cpu_active(cpu, false);
 	err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
@@ -225,10 +226,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 		goto out_release;
 	}

-	/* Ensure that we are not runnable on dying cpu */
-	cpumask_copy(old_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpu_active_mask);
-
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		set_cpu_active(cpu, true);
@@ -237,7 +234,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 					    hcpu) == NOTIFY_BAD)
 			BUG();

-		goto out_allowed;
+		goto out_release;
 	}
 	BUG_ON(cpu_online(cpu));

@@ -255,8 +252,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)

 	check_for_tasks(cpu);

-out_allowed:
-	set_cpus_allowed_ptr(current, old_allowed);
 out_release:
 	cpu_hotplug_done();
 	if (!err) {
@@ -264,7 +259,6 @@ out_release:
 					    hcpu) == NOTIFY_BAD)
 			BUG();
 	}
-	free_cpumask_var(old_allowed);
 	return err;
 }

@@ -272,9 +266,6 @@ int __ref cpu_down(unsigned int cpu)
 {
 	int err;

-	err = stop_machine_create();
-	if (err)
-		return err;
 	cpu_maps_update_begin();

 	if (cpu_hotplug_disabled) {
@@ -286,7 +277,6 @@ int __ref cpu_down(unsigned int cpu)

 out:
 	cpu_maps_update_done();
-	stop_machine_destroy();
 	return err;
 }
 EXPORT_SYMBOL(cpu_down);
@@ -367,9 +357,6 @@ int disable_nonboot_cpus(void)
 {
 	int cpu, first_cpu, error;

-	error = stop_machine_create();
-	if (error)
-		return error;
 	cpu_maps_update_begin();
 	first_cpu = cpumask_first(cpu_online_mask);
 	/*
@@ -400,7 +387,6 @@ int disable_nonboot_cpus(void)
 		printk(KERN_ERR "Non-boot CPUs are not disabled\n");
 	}
 	cpu_maps_update_done();
-	stop_machine_destroy();
 	return error;
 }

--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2182,19 +2182,52 @@ void __init cpuset_init_smp(void)
 void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
 	mutex_lock(&callback_mutex);
-	cpuset_cpus_allowed_locked(tsk, pmask);
-	mutex_unlock(&callback_mutex);
-}
-
-/**
- * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
- * Must be called with callback_mutex held.
- **/
-void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
-{
 	task_lock(tsk);
 	guarantee_online_cpus(task_cs(tsk), pmask);
 	task_unlock(tsk);
+	mutex_unlock(&callback_mutex);
+}
+
+int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
+{
+	const struct cpuset *cs;
+	int cpu;
+
+	rcu_read_lock();
+	cs = task_cs(tsk);
+	if (cs)
+		cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed);
+	rcu_read_unlock();
+
+	/*
+	 * We own tsk->cpus_allowed, nobody can change it under us.
+	 *
+	 * But we used cs && cs->cpus_allowed lockless and thus can
+	 * race with cgroup_attach_task() or update_cpumask() and get
+	 * the wrong tsk->cpus_allowed. However, both cases imply the
+	 * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr()
+	 * which takes task_rq_lock().
+	 *
+	 * If we are called after it dropped the lock we must see all
+	 * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary
+	 * set any mask even if it is not right from task_cs() pov,
+	 * the pending set_cpus_allowed_ptr() will fix things.
+	 */
+
+	cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask);
+	if (cpu >= nr_cpu_ids) {
+		/*
+		 * Either tsk->cpus_allowed is wrong (see above) or it
+		 * is actually empty. The latter case is only possible
+		 * if we are racing with remove_tasks_in_empty_cpuset().
+		 * Like above we can temporary set any mask and rely on
+		 * set_cpus_allowed_ptr() as synchronization point.
+		 */
+		cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask);
+		cpu = cpumask_any(cpu_active_mask);
+	}
+
+	return cpu;
 }

 void cpuset_init_current_mems_allowed(void)
@@ -2382,22 +2415,6 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 	return 0;
 }

-/**
- * cpuset_lock - lock out any changes to cpuset structures
- *
- * The out of memory (oom) code needs to mutex_lock cpusets
- * from being changed while it scans the tasklist looking for a
- * task in an overlapping cpuset.  Expose callback_mutex via this
- * cpuset_lock() routine, so the oom code can lock it, before
- * locking the task list.  The tasklist_lock is a spinlock, so
- * must be taken inside callback_mutex.
- */
-
-void cpuset_lock(void)
-{
-	mutex_lock(&callback_mutex);
-}
-
 /**
 * cpuset_unlock - release lock on cpuset changes
 *
--- a/kernel/cred-internals.h
+++ b/kernel/cred-internals.h
@@ -1,21 +0,0 @@
-/* Internal credentials stuff
- *
- * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-/*
- * user.c
- */
-static inline void sched_switch_user(struct task_struct *p)
-{
-#ifdef CONFIG_USER_SCHED
-	sched_move_task(p);
-#endif	/* CONFIG_USER_SCHED */
-}
-
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -17,7 +17,6 @@
 #include <linux/init_task.h>
 #include <linux/security.h>
 #include <linux/cn_proc.h>
-#include "cred-internals.h"

 #if 0
 #define kdebug(FMT, ...) \
@@ -560,8 +559,6 @@ int commit_creds(struct cred *new)
 		atomic_dec(&old->user->processes);
 	alter_cred_subscribers(old, -2);

-	sched_switch_user(task);
-
 	/* send notifications */
 	if (new->uid   != old->uid  ||
 	    new->euid  != old->euid ||
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -55,7 +55,6 @@
 #include <asm/unistd.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
-#include "cred-internals.h"

 static void exit_mm(struct task_struct * tsk);

--- a/kernel/module.c
+++ b/kernel/module.c
@@ -724,16 +724,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		return -EFAULT;
 	name[MODULE_NAME_LEN-1] = '\0';

-	/* Create stop_machine threads since free_module relies on
-	 * a non-failing stop_machine call. */
-	ret = stop_machine_create();
-	if (ret)
-		return ret;
-
-	if (mutex_lock_interruptible(&module_mutex) != 0) {
-		ret = -EINTR;
-		goto out_stop;
-	}
+	if (mutex_lock_interruptible(&module_mutex) != 0)
+		return -EINTR;

 	mod = find_module(name);
 	if (!mod) {
@@ -793,8 +785,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,

 out:
 	mutex_unlock(&module_mutex);
-out_stop:
-	stop_machine_destroy();
 	return ret;
 }

--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -671,7 +671,7 @@ static struct rcu_torture_ops sched_expedited_ops = {
 	.sync		= synchronize_sched_expedited,
 	.cb_barrier	= NULL,
 	.fqs		= rcu_sched_force_quiescent_state,
-	.stats		= rcu_expedited_torture_stats,
+	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "sched_expedited"
 };
--- a/kernel/sched.c
+++ b/kernel/sched.c
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -70,16 +70,16 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu,
 	PN(se->vruntime);
 	PN(se->sum_exec_runtime);
 #ifdef CONFIG_SCHEDSTATS
-	PN(se->wait_start);
-	PN(se->sleep_start);
-	PN(se->block_start);
-	PN(se->sleep_max);
-	PN(se->block_max);
-	PN(se->exec_max);
-	PN(se->slice_max);
-	PN(se->wait_max);
-	PN(se->wait_sum);
-	P(se->wait_count);
+	PN(se->statistics.wait_start);
+	PN(se->statistics.sleep_start);
+	PN(se->statistics.block_start);
+	PN(se->statistics.sleep_max);
+	PN(se->statistics.block_max);
+	PN(se->statistics.exec_max);
+	PN(se->statistics.slice_max);
+	PN(se->statistics.wait_max);
+	PN(se->statistics.wait_sum);
+	P(se->statistics.wait_count);
 #endif
 	P(se->load.weight);
 #undef PN
@@ -104,7 +104,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
 		SPLIT_NS(p->se.vruntime),
 		SPLIT_NS(p->se.sum_exec_runtime),
-		SPLIT_NS(p->se.sum_sleep_runtime));
+		SPLIT_NS(p->se.statistics.sum_sleep_runtime));
 #else
 	SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
@@ -175,11 +175,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	task_group_path(tg, path, sizeof(path));

 	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
-#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
-	{
-		uid_t uid = cfs_rq->tg->uid;
-		SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid);
-	}
 #else
 	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
 #endif
@@ -409,40 +404,38 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	PN(se.exec_start);
 	PN(se.vruntime);
 	PN(se.sum_exec_runtime);
-	PN(se.avg_overlap);
-	PN(se.avg_wakeup);

 	nr_switches = p->nvcsw + p->nivcsw;

 #ifdef CONFIG_SCHEDSTATS
-	PN(se.wait_start);
-	PN(se.sleep_start);
-	PN(se.block_start);
-	PN(se.sleep_max);
-	PN(se.block_max);
-	PN(se.exec_max);
-	PN(se.slice_max);
-	PN(se.wait_max);
-	PN(se.wait_sum);
-	P(se.wait_count);
-	PN(se.iowait_sum);
-	P(se.iowait_count);
+	PN(se.statistics.wait_start);
+	PN(se.statistics.sleep_start);
+	PN(se.statistics.block_start);
+	PN(se.statistics.sleep_max);
+	PN(se.statistics.block_max);
+	PN(se.statistics.exec_max);
+	PN(se.statistics.slice_max);
+	PN(se.statistics.wait_max);
+	PN(se.statistics.wait_sum);
+	P(se.statistics.wait_count);
+	PN(se.statistics.iowait_sum);
+	P(se.statistics.iowait_count);
 	P(sched_info.bkl_count);
 	P(se.nr_migrations);
-	P(se.nr_migrations_cold);
-	P(se.nr_failed_migrations_affine);
-	P(se.nr_failed_migrations_running);
-	P(se.nr_failed_migrations_hot);
-	P(se.nr_forced_migrations);
-	P(se.nr_wakeups);
-	P(se.nr_wakeups_sync);
-	P(se.nr_wakeups_migrate);
-	P(se.nr_wakeups_local);
-	P(se.nr_wakeups_remote);
-	P(se.nr_wakeups_affine);
-	P(se.nr_wakeups_affine_attempts);
-	P(se.nr_wakeups_passive);
-	P(se.nr_wakeups_idle);
+	P(se.statistics.nr_migrations_cold);
+	P(se.statistics.nr_failed_migrations_affine);
+	P(se.statistics.nr_failed_migrations_running);
+	P(se.statistics.nr_failed_migrations_hot);
+	P(se.statistics.nr_forced_migrations);
+	P(se.statistics.nr_wakeups);
+	P(se.statistics.nr_wakeups_sync);
+	P(se.statistics.nr_wakeups_migrate);
+	P(se.statistics.nr_wakeups_local);
+	P(se.statistics.nr_wakeups_remote);
+	P(se.statistics.nr_wakeups_affine);
+	P(se.statistics.nr_wakeups_affine_attempts);
+	P(se.statistics.nr_wakeups_passive);
+	P(se.statistics.nr_wakeups_idle);

 	{
 		u64 avg_atom, avg_per_cpu;
@@ -493,31 +486,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 void proc_sched_set_task(struct task_struct *p)
 {
 #ifdef CONFIG_SCHEDSTATS
-	p->se.wait_max				= 0;
-	p->se.wait_sum				= 0;
-	p->se.wait_count			= 0;
-	p->se.iowait_sum			= 0;
-	p->se.iowait_count			= 0;
-	p->se.sleep_max				= 0;
-	p->se.sum_sleep_runtime			= 0;
-	p->se.block_max				= 0;
-	p->se.exec_max				= 0;
-	p->se.slice_max				= 0;
-	p->se.nr_migrations			= 0;
-	p->se.nr_migrations_cold		= 0;
-	p->se.nr_failed_migrations_affine	= 0;
-	p->se.nr_failed_migrations_running	= 0;
-	p->se.nr_failed_migrations_hot		= 0;
-	p->se.nr_forced_migrations		= 0;
-	p->se.nr_wakeups			= 0;
-	p->se.nr_wakeups_sync			= 0;
-	p->se.nr_wakeups_migrate		= 0;
-	p->se.nr_wakeups_local			= 0;
-	p->se.nr_wakeups_remote			= 0;
-	p->se.nr_wakeups_affine			= 0;
-	p->se.nr_wakeups_affine_attempts	= 0;
-	p->se.nr_wakeups_passive		= 0;
-	p->se.nr_wakeups_idle			= 0;
-	p->sched_info.bkl_count			= 0;
+	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 }
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -35,8 +35,8 @@
 * (to see the precise effective timeslice length of your workload,
 *  run vmstat and monitor the context-switches (cs) field)
 */
-unsigned int sysctl_sched_latency = 5000000ULL;
-unsigned int normalized_sysctl_sched_latency = 5000000ULL;
+unsigned int sysctl_sched_latency = 6000000ULL;
+unsigned int normalized_sysctl_sched_latency = 6000000ULL;

 /*
 * The initial- and re-scaling of tunables is configurable
@@ -52,15 +52,15 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling

 /*
 * Minimal preemption granularity for CPU-bound tasks:
- * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
 */
-unsigned int sysctl_sched_min_granularity = 1000000ULL;
-unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL;
+unsigned int sysctl_sched_min_granularity = 2000000ULL;
+unsigned int normalized_sysctl_sched_min_granularity = 2000000ULL;

 /*
 * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
 */
-static unsigned int sched_nr_latency = 5;
+static unsigned int sched_nr_latency = 3;

 /*
 * After fork, child runs first. If set to 0 (default) then
@@ -505,7 +505,8 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 {
 	unsigned long delta_exec_weighted;

-	schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
+	schedstat_set(curr->statistics.exec_max,
+		      max((u64)delta_exec, curr->statistics.exec_max));

 	curr->sum_exec_runtime += delta_exec;
 	schedstat_add(cfs_rq, exec_clock, delta_exec);
@@ -548,7 +549,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
+	schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock);
 }

 /*
@@ -567,18 +568,18 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->wait_max, max(se->wait_max,
-			rq_of(cfs_rq)->clock - se->wait_start));
-	schedstat_set(se->wait_count, se->wait_count + 1);
-	schedstat_set(se->wait_sum, se->wait_sum +
-			rq_of(cfs_rq)->clock - se->wait_start);
+	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
+			rq_of(cfs_rq)->clock - se->statistics.wait_start));
+	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
+	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
+			rq_of(cfs_rq)->clock - se->statistics.wait_start);
 #ifdef CONFIG_SCHEDSTATS
 	if (entity_is_task(se)) {
 		trace_sched_stat_wait(task_of(se),
-			rq_of(cfs_rq)->clock - se->wait_start);
+			rq_of(cfs_rq)->clock - se->statistics.wait_start);
 	}
 #endif
-	schedstat_set(se->wait_start, 0);
+	schedstat_set(se->statistics.wait_start, 0);
 }

 static inline void
@@ -657,39 +658,39 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	if (entity_is_task(se))
 		tsk = task_of(se);

-	if (se->sleep_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
+	if (se->statistics.sleep_start) {
+		u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start;

 		if ((s64)delta < 0)
 			delta = 0;

-		if (unlikely(delta > se->sleep_max))
-			se->sleep_max = delta;
+		if (unlikely(delta > se->statistics.sleep_max))
+			se->statistics.sleep_max = delta;

-		se->sleep_start = 0;
-		se->sum_sleep_runtime += delta;
+		se->statistics.sleep_start = 0;
+		se->statistics.sum_sleep_runtime += delta;

 		if (tsk) {
 			account_scheduler_latency(tsk, delta >> 10, 1);
 			trace_sched_stat_sleep(tsk, delta);
 		}
 	}
-	if (se->block_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->block_start;
+	if (se->statistics.block_start) {
+		u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start;

 		if ((s64)delta < 0)
 			delta = 0;

-		if (unlikely(delta > se->block_max))
-			se->block_max = delta;
+		if (unlikely(delta > se->statistics.block_max))
+			se->statistics.block_max = delta;

-		se->block_start = 0;
-		se->sum_sleep_runtime += delta;
+		se->statistics.block_start = 0;
+		se->statistics.sum_sleep_runtime += delta;

 		if (tsk) {
 			if (tsk->in_iowait) {
-				se->iowait_sum += delta;
-				se->iowait_count++;
+				se->statistics.iowait_sum += delta;
+				se->statistics.iowait_count++;
 				trace_sched_stat_iowait(tsk, delta);
 			}

@@ -737,19 +738,9 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 		vruntime += sched_vslice(cfs_rq, se);

 	/* sleeps up to a single latency don't count. */
-	if (!initial && sched_feat(FAIR_SLEEPERS)) {
+	if (!initial) {
 		unsigned long thresh = sysctl_sched_latency;

-		/*
-		 * Convert the sleeper threshold into virtual time.
-		 * SCHED_IDLE is a special sub-class.  We care about
-		 * fairness only relative to other SCHED_IDLE tasks,
-		 * all of which have the same weight.
-		 */
-		if (sched_feat(NORMALIZED_SLEEPER) && (!entity_is_task(se) ||
-				 task_of(se)->policy != SCHED_IDLE))
-			thresh = calc_delta_fair(thresh, se);
-
 		/*
 		 * Halve their sleep time's effect, to allow
 		 * for a gentler effect of sleepers:
@@ -766,9 +757,6 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 	se->vruntime = vruntime;
 }

-#define ENQUEUE_WAKEUP	1
-#define ENQUEUE_MIGRATE 2
-
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -776,7 +764,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update the normalized vruntime before updating min_vruntime
 	 * through callig update_curr().
 	 */
-	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATE))
+	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
 		se->vruntime += cfs_rq->min_vruntime;

 	/*
@@ -812,7 +800,7 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }

 static void
-dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
+dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	/*
 	 * Update run-time statistics of the 'current'.
@@ -820,15 +808,15 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 	update_curr(cfs_rq);

 	update_stats_dequeue(cfs_rq, se);
-	if (sleep) {
+	if (flags & DEQUEUE_SLEEP) {
 #ifdef CONFIG_SCHEDSTATS
 		if (entity_is_task(se)) {
 			struct task_struct *tsk = task_of(se);

 			if (tsk->state & TASK_INTERRUPTIBLE)
-				se->sleep_start = rq_of(cfs_rq)->clock;
+				se->statistics.sleep_start = rq_of(cfs_rq)->clock;
 			if (tsk->state & TASK_UNINTERRUPTIBLE)
-				se->block_start = rq_of(cfs_rq)->clock;
+				se->statistics.block_start = rq_of(cfs_rq)->clock;
 		}
 #endif
 	}
@@ -845,7 +833,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 	 * update can refer to the ->curr item and we need to reflect this
 	 * movement in our normalized position.
 	 */
-	if (!sleep)
+	if (!(flags & DEQUEUE_SLEEP))
 		se->vruntime -= cfs_rq->min_vruntime;
 }

@@ -912,7 +900,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * when there are only lesser-weight tasks around):
 	 */
 	if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
-		se->slice_max = max(se->slice_max,
+		se->statistics.slice_max = max(se->statistics.slice_max,
 			se->sum_exec_runtime - se->prev_sum_exec_runtime);
 	}
 #endif
@@ -1054,16 +1042,10 @@ static inline void hrtick_update(struct rq *rq)
 * then put the task into the rbtree:
 */
 static void
-enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
+enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
-	int flags = 0;
-
-	if (wakeup)
-		flags |= ENQUEUE_WAKEUP;
-	if (p->state == TASK_WAKING)
-		flags |= ENQUEUE_MIGRATE;

 	for_each_sched_entity(se) {
 		if (se->on_rq)
@@ -1081,18 +1063,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
 * decreased. We remove the task from the rbtree and
 * update the fair scheduling stats:
 */
-static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;

 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		dequeue_entity(cfs_rq, se, sleep);
+		dequeue_entity(cfs_rq, se, flags);
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight)
 			break;
-		sleep = 1;
+		flags |= DEQUEUE_SLEEP;
 	}

 	hrtick_update(rq);
@@ -1240,7 +1222,6 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,

 static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 {
-	struct task_struct *curr = current;
 	unsigned long this_load, load;
 	int idx, this_cpu, prev_cpu;
 	unsigned long tl_per_task;
@@ -1255,18 +1236,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	load	  = source_load(prev_cpu, idx);
 	this_load = target_load(this_cpu, idx);

-	if (sync) {
-	       if (sched_feat(SYNC_LESS) &&
-		   (curr->se.avg_overlap > sysctl_sched_migration_cost ||
-		    p->se.avg_overlap > sysctl_sched_migration_cost))
-		       sync = 0;
-	} else {
-		if (sched_feat(SYNC_MORE) &&
-		    (curr->se.avg_overlap < sysctl_sched_migration_cost &&
-		     p->se.avg_overlap < sysctl_sched_migration_cost))
-			sync = 1;
-	}
-
 	/*
 	 * If sync wakeup then subtract the (maximum possible)
 	 * effect of the currently running task from the load
@@ -1306,7 +1275,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	if (sync && balanced)
 		return 1;

-	schedstat_inc(p, se.nr_wakeups_affine_attempts);
+	schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts);
 	tl_per_task = cpu_avg_load_per_task(this_cpu);

 	if (balanced ||
@@ -1318,7 +1287,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 		 * there is no bad imbalance.
 		 */
 		schedstat_inc(sd, ttwu_move_affine);
-		schedstat_inc(p, se.nr_wakeups_affine);
+		schedstat_inc(p, se.statistics.nr_wakeups_affine);

 		return 1;
 	}
@@ -1406,29 +1375,48 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 /*
 * Try and locate an idle CPU in the sched_domain.
 */
-static int
-select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
+static int select_idle_sibling(struct task_struct *p, int target)
 {
 	int cpu = smp_processor_id();
 	int prev_cpu = task_cpu(p);
+	struct sched_domain *sd;
 	int i;

 	/*
-	 * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
-	 * test in select_task_rq_fair) and the prev_cpu is idle then that's
-	 * always a better target than the current cpu.
+	 * If the task is going to be woken-up on this cpu and if it is
+	 * already idle, then it is the right target.
 	 */
-	if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
+	if (target == cpu && idle_cpu(cpu))
+		return cpu;
+
+	/*
+	 * If the task is going to be woken-up on the cpu where it previously
+	 * ran and if it is currently idle, then it the right target.
+	 */
+	if (target == prev_cpu && idle_cpu(prev_cpu))
 		return prev_cpu;

 	/*
-	 * Otherwise, iterate the domain and find an elegible idle cpu.
+	 * Otherwise, iterate the domains and find an elegible idle cpu.
 	 */
-	for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
-		if (!cpu_rq(i)->cfs.nr_running) {
-			target = i;
+	for_each_domain(target, sd) {
+		if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
 			break;
+
+		for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+			if (idle_cpu(i)) {
+				target = i;
+				break;
+			}
 		}
+
+		/*
+		 * Lets stop looking for an idle sibling when we reached
+		 * the domain that spans the current cpu and prev_cpu.
+		 */
+		if (cpumask_test_cpu(cpu, sched_domain_span(sd)) &&
+		    cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
+			break;
 	}

 	return target;
@@ -1445,7 +1433,8 @@ select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
 *
 * preempt must be disabled.
 */
-static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+static int
+select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags)
 {
 	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
 	int cpu = smp_processor_id();
@@ -1456,8 +1445,7 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 	int sync = wake_flags & WF_SYNC;

 	if (sd_flag & SD_BALANCE_WAKE) {
-		if (sched_feat(AFFINE_WAKEUPS) &&
-		    cpumask_test_cpu(cpu, &p->cpus_allowed))
+		if (cpumask_test_cpu(cpu, &p->cpus_allowed))
 			want_affine = 1;
 		new_cpu = prev_cpu;
 	}
@@ -1491,34 +1479,13 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 		}

 		/*
-		 * While iterating the domains looking for a spanning
-		 * WAKE_AFFINE domain, adjust the affine target to any idle cpu
-		 * in cache sharing domains along the way.
+		 * If both cpu and prev_cpu are part of this domain,
+		 * cpu is a valid SD_WAKE_AFFINE target.
 		 */
-		if (want_affine) {
-			int target = -1;
-
-			/*
-			 * If both cpu and prev_cpu are part of this domain,
-			 * cpu is a valid SD_WAKE_AFFINE target.
-			 */
-			if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
-				target = cpu;
-
-			/*
-			 * If there's an idle sibling in this domain, make that
-			 * the wake_affine target instead of the current cpu.
-			 */
-			if (tmp->flags & SD_SHARE_PKG_RESOURCES)
-				target = select_idle_sibling(p, tmp, target);
-
-			if (target >= 0) {
-				if (tmp->flags & SD_WAKE_AFFINE) {
-					affine_sd = tmp;
-					want_affine = 0;
-				}
-				cpu = target;
-			}
+		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
+		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+			affine_sd = tmp;
+			want_affine = 0;
 		}

 		if (!want_sd && !want_affine)
@@ -1531,22 +1498,29 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 			sd = tmp;
 	}

+#ifdef CONFIG_FAIR_GROUP_SCHED
 	if (sched_feat(LB_SHARES_UPDATE)) {
 		/*
 		 * Pick the largest domain to update shares over
 		 */
 		tmp = sd;
-		if (affine_sd && (!tmp ||
-				  cpumask_weight(sched_domain_span(affine_sd)) >
-				  cpumask_weight(sched_domain_span(sd))))
+		if (affine_sd && (!tmp || affine_sd->span_weight > sd->span_weight))
 			tmp = affine_sd;

-		if (tmp)
+		if (tmp) {
+			raw_spin_unlock(&rq->lock);
 			update_shares(tmp);
+			raw_spin_lock(&rq->lock);
+		}
 	}
+#endif

-	if (affine_sd && wake_affine(affine_sd, p, sync))
-		return cpu;
+	if (affine_sd) {
+		if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
+			return select_idle_sibling(p, cpu);
+		else
+			return select_idle_sibling(p, prev_cpu);
+	}

 	while (sd) {
 		int load_idx = sd->forkexec_idx;
@@ -1576,10 +1550,10 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag

 		/* Now try balancing at a lower domain level of new_cpu */
 		cpu = new_cpu;
-		weight = cpumask_weight(sched_domain_span(sd));
+		weight = sd->span_weight;
 		sd = NULL;
 		for_each_domain(cpu, tmp) {
-			if (weight <= cpumask_weight(sched_domain_span(tmp)))
+			if (weight <= tmp->span_weight)
 				break;
 			if (tmp->flags & sd_flag)
 				sd = tmp;
@@ -1591,63 +1565,26 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 }
 #endif /* CONFIG_SMP */

-/*
- * Adaptive granularity
- *
- * se->avg_wakeup gives the average time a task runs until it does a wakeup,
- * with the limit of wakeup_gran -- when it never does a wakeup.
- *
- * So the smaller avg_wakeup is the faster we want this task to preempt,
- * but we don't want to treat the preemptee unfairly and therefore allow it
- * to run for at least the amount of time we'd like to run.
- *
- * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one
- *
- * NOTE: we use *nr_running to scale with load, this nicely matches the
- *       degrading latency on load.
- */
-static unsigned long
-adaptive_gran(struct sched_entity *curr, struct sched_entity *se)
-{
-	u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-	u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running;
-	u64 gran = 0;
-
-	if (this_run < expected_wakeup)
-		gran = expected_wakeup - this_run;
-
-	return min_t(s64, gran, sysctl_sched_wakeup_granularity);
-}
-
 static unsigned long
 wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
 {
 	unsigned long gran = sysctl_sched_wakeup_granularity;

-	if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN))
-		gran = adaptive_gran(curr, se);
-
 	/*
 	 * Since its curr running now, convert the gran from real-time
 	 * to virtual-time in his units.
+	 *
+	 * By using 'se' instead of 'curr' we penalize light tasks, so
+	 * they get preempted easier. That is, if 'se' < 'curr' then
+	 * the resulting gran will be larger, therefore penalizing the
+	 * lighter, if otoh 'se' > 'curr' then the resulting gran will
+	 * be smaller, again penalizing the lighter task.
+	 *
+	 * This is especially important for buddies when the leftmost
+	 * task is higher priority than the buddy.
 	 */
-	if (sched_feat(ASYM_GRAN)) {
-		/*
-		 * By using 'se' instead of 'curr' we penalize light tasks, so
-		 * they get preempted easier. That is, if 'se' < 'curr' then
-		 * the resulting gran will be larger, therefore penalizing the
-		 * lighter, if otoh 'se' > 'curr' then the resulting gran will
-		 * be smaller, again penalizing the lighter task.
-		 *
-		 * This is especially important for buddies when the leftmost
-		 * task is higher priority than the buddy.
-		 */
-		if (unlikely(se->load.weight != NICE_0_LOAD))
-			gran = calc_delta_fair(gran, se);
-	} else {
-		if (unlikely(curr->load.weight != NICE_0_LOAD))
-			gran = calc_delta_fair(gran, curr);
-	}
+	if (unlikely(se->load.weight != NICE_0_LOAD))
+		gran = calc_delta_fair(gran, se);

 	return gran;
 }
@@ -1705,7 +1642,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct task_struct *curr = rq->curr;
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
-	int sync = wake_flags & WF_SYNC;
 	int scale = cfs_rq->nr_running >= sched_nr_latency;

 	if (unlikely(rt_prio(p->prio)))
@@ -1738,14 +1674,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (unlikely(curr->policy == SCHED_IDLE))
 		goto preempt;

-	if (sched_feat(WAKEUP_SYNC) && sync)
-		goto preempt;
-
-	if (sched_feat(WAKEUP_OVERLAP) &&
-			se->avg_overlap < sysctl_sched_migration_cost &&
-			pse->avg_overlap < sysctl_sched_migration_cost)
-		goto preempt;
-
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;

@@ -1844,13 +1772,13 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 	 * 3) are cache-hot on their current CPU.
 	 */
 	if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
-		schedstat_inc(p, se.nr_failed_migrations_affine);
+		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
 		return 0;
 	}
 	*all_pinned = 0;

 	if (task_running(rq, p)) {
-		schedstat_inc(p, se.nr_failed_migrations_running);
+		schedstat_inc(p, se.statistics.nr_failed_migrations_running);
 		return 0;
 	}

@@ -1866,14 +1794,14 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 #ifdef CONFIG_SCHEDSTATS
 		if (tsk_cache_hot) {
 			schedstat_inc(sd, lb_hot_gained[idle]);
-			schedstat_inc(p, se.nr_forced_migrations);
+			schedstat_inc(p, se.statistics.nr_forced_migrations);
 		}
 #endif
 		return 1;
 	}

 	if (tsk_cache_hot) {
-		schedstat_inc(p, se.nr_failed_migrations_hot);
+		schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
 		return 0;
 	}
 	return 1;
@@ -2311,7 +2239,7 @@ unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)

 unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
 {
-	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long weight = sd->span_weight;
 	unsigned long smt_gain = sd->smt_gain;

 	smt_gain /= weight;
@@ -2344,7 +2272,7 @@ unsigned long scale_rt_power(int cpu)

 static void update_cpu_power(struct sched_domain *sd, int cpu)
 {
-	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long weight = sd->span_weight;
 	unsigned long power = SCHED_LOAD_SCALE;
 	struct sched_group *sdg = sd->groups;

@@ -2870,6 +2798,8 @@ static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle)
 	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
 }

+static int active_load_balance_cpu_stop(void *data);
+
 /*
 * Check this_cpu to ensure it is balanced within domain. Attempt to move
 * tasks if there is an imbalance.
@@ -2959,8 +2889,9 @@ redo:
 		if (need_active_balance(sd, sd_idle, idle)) {
 			raw_spin_lock_irqsave(&busiest->lock, flags);

-			/* don't kick the migration_thread, if the curr
-			 * task on busiest cpu can't be moved to this_cpu
+			/* don't kick the active_load_balance_cpu_stop,
+			 * if the curr task on busiest cpu can't be
+			 * moved to this_cpu
 			 */
 			if (!cpumask_test_cpu(this_cpu,
 					      &busiest->curr->cpus_allowed)) {
@@ -2970,14 +2901,22 @@ redo:
 				goto out_one_pinned;
 			}

+			/*
+			 * ->active_balance synchronizes accesses to
+			 * ->active_balance_work.  Once set, it's cleared
+			 * only after active load balance is finished.
+			 */
 			if (!busiest->active_balance) {
 				busiest->active_balance = 1;
 				busiest->push_cpu = this_cpu;
 				active_balance = 1;
 			}
 			raw_spin_unlock_irqrestore(&busiest->lock, flags);
+
 			if (active_balance)
-				wake_up_process(busiest->migration_thread);
+				stop_one_cpu_nowait(cpu_of(busiest),
+					active_load_balance_cpu_stop, busiest,
+					&busiest->active_balance_work);

 			/*
 			 * We've kicked active balancing, reset the failure
@@ -3084,24 +3023,29 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 }

 /*
- * active_load_balance is run by migration threads. It pushes running tasks
- * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
- * running on each physical CPU where possible, and avoids physical /
- * logical imbalances.
- *
- * Called with busiest_rq locked.
+ * active_load_balance_cpu_stop is run by cpu stopper. It pushes
+ * running tasks off the busiest CPU onto idle CPUs. It requires at
+ * least 1 task to be running on each physical CPU where possible, and
+ * avoids physical / logical imbalances.
 */
-static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
+static int active_load_balance_cpu_stop(void *data)
 {
+	struct rq *busiest_rq = data;
+	int busiest_cpu = cpu_of(busiest_rq);
 	int target_cpu = busiest_rq->push_cpu;
+	struct rq *target_rq = cpu_rq(target_cpu);
 	struct sched_domain *sd;
-	struct rq *target_rq;
+
+	raw_spin_lock_irq(&busiest_rq->lock);
+
+	/* make sure the requested cpu hasn't gone down in the meantime */
+	if (unlikely(busiest_cpu != smp_processor_id() ||
+		     !busiest_rq->active_balance))
+		goto out_unlock;

 	/* Is there any task to move? */
 	if (busiest_rq->nr_running <= 1)
-		return;
-
-	target_rq = cpu_rq(target_cpu);
+		goto out_unlock;

 	/*
 	 * This condition is "impossible", if it occurs
@@ -3112,8 +3056,6 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)

 	/* move a task from busiest_rq to target_rq */
 	double_lock_balance(busiest_rq, target_rq);
-	update_rq_clock(busiest_rq);
-	update_rq_clock(target_rq);

 	/* Search for an sd spanning us and the target CPU. */
 	for_each_domain(target_cpu, sd) {
@@ -3132,6 +3074,10 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 			schedstat_inc(sd, alb_failed);
 	}
 	double_unlock_balance(busiest_rq, target_rq);
+out_unlock:
+	busiest_rq->active_balance = 0;
+	raw_spin_unlock_irq(&busiest_rq->lock);
+	return 0;
 }

 #ifdef CONFIG_NO_HZ
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -1,10 +1,3 @@
-/*
- * Disregards a certain amount of sleep time (sched_latency_ns) and
- * considers the task to be running during that period. This gives it
- * a service deficit on wakeup, allowing it to run sooner.
- */
-SCHED_FEAT(FAIR_SLEEPERS, 1)
-
 /*
 * Only give sleepers 50% of their service deficit. This allows
 * them to run sooner, but does not allow tons of sleepers to
@@ -12,13 +5,6 @@ SCHED_FEAT(FAIR_SLEEPERS, 1)
 */
 SCHED_FEAT(GENTLE_FAIR_SLEEPERS, 1)

-/*
- * By not normalizing the sleep time, heavy tasks get an effective
- * longer period, and lighter task an effective shorter period they
- * are considered running.
- */
-SCHED_FEAT(NORMALIZED_SLEEPER, 0)
-
 /*
 * Place new tasks ahead so that they do not starve already running
 * tasks
@@ -30,37 +16,6 @@ SCHED_FEAT(START_DEBIT, 1)
 */
 SCHED_FEAT(WAKEUP_PREEMPT, 1)

-/*
- * Compute wakeup_gran based on task behaviour, clipped to
- *  [0, sched_wakeup_gran_ns]
- */
-SCHED_FEAT(ADAPTIVE_GRAN, 1)
-
-/*
- * When converting the wakeup granularity to virtual time, do it such
- * that heavier tasks preempting a lighter task have an edge.
- */
-SCHED_FEAT(ASYM_GRAN, 1)
-
-/*
- * Always wakeup-preempt SYNC wakeups, see SYNC_WAKEUPS.
- */
-SCHED_FEAT(WAKEUP_SYNC, 0)
-
-/*
- * Wakeup preempt based on task behaviour. Tasks that do not overlap
- * don't get preempted.
- */
-SCHED_FEAT(WAKEUP_OVERLAP, 0)
-
-/*
- * Use the SYNC wakeup hint, pipes and the likes use this to indicate
- * the remote end is likely to consume the data we just wrote, and
- * therefore has cache benefit from being placed on the same cpu, see
- * also AFFINE_WAKEUPS.
- */
-SCHED_FEAT(SYNC_WAKEUPS, 1)
-
 /*
 * Based on load and program behaviour, see if it makes sense to place
 * a newly woken task on the same cpu as the task that woke it --
@@ -69,16 +24,6 @@ SCHED_FEAT(SYNC_WAKEUPS, 1)
 */
 SCHED_FEAT(AFFINE_WAKEUPS, 1)

-/*
- * Weaken SYNC hint based on overlap
- */
-SCHED_FEAT(SYNC_LESS, 1)
-
-/*
- * Add SYNC hint based on overlap
- */
-SCHED_FEAT(SYNC_MORE, 0)
-
 /*
 * Prefer to schedule the task we woke last (assuming it failed
 * wakeup-preemption), since its likely going to consume data we
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -6,7 +6,8 @@
 */

 #ifdef CONFIG_SMP
-static int select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
+static int
+select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
@@ -22,8 +23,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 static struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	schedstat_inc(rq, sched_goidle);
-	/* adjust the active tasks as we might go into a long sleep */
-	calc_load_account_active(rq);
+	calc_load_account_idle(rq);
 	return rq->idle;
 }

@@ -32,7 +32,7 @@ static struct task_struct *pick_next_task_idle(struct rq *rq)
 * message if some code attempts to do it:
 */
 static void
-dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep)
+dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 {
 	raw_spin_unlock_irq(&rq->lock);
 	printk(KERN_ERR "bad: scheduling from the idle thread!\n");
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -613,7 +613,7 @@ static void update_curr_rt(struct rq *rq)
 	if (unlikely((s64)delta_exec < 0))
 		delta_exec = 0;

-	schedstat_set(curr->se.exec_max, max(curr->se.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);
@@ -888,20 +888,20 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
 * Adding/removing a task to/from a priority array:
 */
 static void
-enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, bool head)
+enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;

-	if (wakeup)
+	if (flags & ENQUEUE_WAKEUP)
 		rt_se->timeout = 0;

-	enqueue_rt_entity(rt_se, head);
+	enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);

 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }

-static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;

@@ -948,10 +948,9 @@ static void yield_task_rt(struct rq *rq)
 #ifdef CONFIG_SMP
 static int find_lowest_rq(struct task_struct *task);

-static int select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
+static int
+select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 {
-	struct rq *rq = task_rq(p);
-
 	if (sd_flag != SD_BALANCE_WAKE)
 		return smp_processor_id();

--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -1,17 +1,384 @@
-/* Copyright 2008, 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
- * GPL v2 and any later version.
+/*
+ * kernel/stop_machine.c
+ *
+ * Copyright (C) 2008, 2005	IBM Corporation.
+ * Copyright (C) 2008, 2005	Rusty Russell rusty@rustcorp.com.au
+ * Copyright (C) 2010		SUSE Linux Products GmbH
+ * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2 and any later version.
 */
+#include <linux/completion.h>
 #include <linux/cpu.h>
-#include <linux/err.h>
+#include <linux/init.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
+#include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/stop_machine.h>
-#include <linux/syscalls.h>
 #include <linux/interrupt.h>
+#include <linux/kallsyms.h>

 #include <asm/atomic.h>
-#include <asm/uaccess.h>
+
+/*
+ * Structure to determine completion condition and record errors.  May
+ * be shared by works on different cpus.
+ */
+struct cpu_stop_done {
+	atomic_t		nr_todo;	/* nr left to execute */
+	bool			executed;	/* actually executed? */
+	int			ret;		/* collected return value */
+	struct completion	completion;	/* fired if nr_todo reaches 0 */
+};
+
+/* the actual stopper, one per every possible cpu, enabled on online cpus */
+struct cpu_stopper {
+	spinlock_t		lock;
+	struct list_head	works;		/* list of pending works */
+	struct task_struct	*thread;	/* stopper thread */
+	bool			enabled;	/* is this stopper enabled? */
+};
+
+static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
+
+static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
+{
+	memset(done, 0, sizeof(*done));
+	atomic_set(&done->nr_todo, nr_todo);
+	init_completion(&done->completion);
+}
+
+/* signal completion unless @done is NULL */
+static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
+{
+	if (done) {
+		if (executed)
+			done->executed = true;
+		if (atomic_dec_and_test(&done->nr_todo))
+			complete(&done->completion);
+	}
+}
+
+/* queue @work to @stopper.  if offline, @work is completed immediately */
+static void cpu_stop_queue_work(struct cpu_stopper *stopper,
+				struct cpu_stop_work *work)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&stopper->lock, flags);
+
+	if (stopper->enabled) {
+		list_add_tail(&work->list, &stopper->works);
+		wake_up_process(stopper->thread);
+	} else
+		cpu_stop_signal_done(work->done, false);
+
+	spin_unlock_irqrestore(&stopper->lock, flags);
+}
+
+/**
+ * stop_one_cpu - stop a cpu
+ * @cpu: cpu to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Execute @fn(@arg) on @cpu.  @fn is run in a process context with
+ * the highest priority preempting any task on the cpu and
+ * monopolizing it.  This function returns after the execution is
+ * complete.
+ *
+ * This function doesn't guarantee @cpu stays online till @fn
+ * completes.  If @cpu goes down in the middle, execution may happen
+ * partially or fully on different cpus.  @fn should either be ready
+ * for that or the caller should ensure that @cpu stays online until
+ * this function completes.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * -ENOENT if @fn(@arg) was not executed because @cpu was offline;
+ * otherwise, the return value of @fn.
+ */
+int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
+{
+	struct cpu_stop_done done;
+	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done };
+
+	cpu_stop_init_done(&done, 1);
+	cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &work);
+	wait_for_completion(&done.completion);
+	return done.executed ? done.ret : -ENOENT;
+}
+
+/**
+ * stop_one_cpu_nowait - stop a cpu but don't wait for completion
+ * @cpu: cpu to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Similar to stop_one_cpu() but doesn't wait for completion.  The
+ * caller is responsible for ensuring @work_buf is currently unused
+ * and will remain untouched until stopper starts executing @fn.
+ *
+ * CONTEXT:
+ * Don't care.
+ */
+void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+			struct cpu_stop_work *work_buf)
+{
+	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };
+	cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), work_buf);
+}
+
+/* static data for stop_cpus */
+static DEFINE_MUTEX(stop_cpus_mutex);
+static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work);
+
+int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+{
+	struct cpu_stop_work *work;
+	struct cpu_stop_done done;
+	unsigned int cpu;
+
+	/* initialize works and done */
+	for_each_cpu(cpu, cpumask) {
+		work = &per_cpu(stop_cpus_work, cpu);
+		work->fn = fn;
+		work->arg = arg;
+		work->done = &done;
+	}
+	cpu_stop_init_done(&done, cpumask_weight(cpumask));
+
+	/*
+	 * Disable preemption while queueing to avoid getting
+	 * preempted by a stopper which might wait for other stoppers
+	 * to enter @fn which can lead to deadlock.
+	 */
+	preempt_disable();
+	for_each_cpu(cpu, cpumask)
+		cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu),
+				    &per_cpu(stop_cpus_work, cpu));
+	preempt_enable();
+
+	wait_for_completion(&done.completion);
+	return done.executed ? done.ret : -ENOENT;
+}
+
+/**
+ * stop_cpus - stop multiple cpus
+ * @cpumask: cpus to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Execute @fn(@arg) on online cpus in @cpumask.  On each target cpu,
+ * @fn is run in a process context with the highest priority
+ * preempting any task on the cpu and monopolizing it.  This function
+ * returns after all executions are complete.
+ *
+ * This function doesn't guarantee the cpus in @cpumask stay online
+ * till @fn completes.  If some cpus go down in the middle, execution
+ * on the cpu may happen partially or fully on different cpus.  @fn
+ * should either be ready for that or the caller should ensure that
+ * the cpus stay online until this function completes.
+ *
+ * All stop_cpus() calls are serialized making it safe for @fn to wait
+ * for all cpus to start executing it.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * -ENOENT if @fn(@arg) was not executed at all because all cpus in
+ * @cpumask were offline; otherwise, 0 if all executions of @fn
+ * returned 0, any non zero return value if any returned non zero.
+ */
+int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+{
+	int ret;
+
+	/* static works are used, process one request at a time */
+	mutex_lock(&stop_cpus_mutex);
+	ret = __stop_cpus(cpumask, fn, arg);
+	mutex_unlock(&stop_cpus_mutex);
+	return ret;
+}
+
+/**
+ * try_stop_cpus - try to stop multiple cpus
+ * @cpumask: cpus to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Identical to stop_cpus() except that it fails with -EAGAIN if
+ * someone else is already using the facility.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * -EAGAIN if someone else is already stopping cpus, -ENOENT if
+ * @fn(@arg) was not executed at all because all cpus in @cpumask were
+ * offline; otherwise, 0 if all executions of @fn returned 0, any non
+ * zero return value if any returned non zero.
+ */
+int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+{
+	int ret;
+
+	/* static works are used, process one request at a time */
+	if (!mutex_trylock(&stop_cpus_mutex))
+		return -EAGAIN;
+	ret = __stop_cpus(cpumask, fn, arg);
+	mutex_unlock(&stop_cpus_mutex);
+	return ret;
+}
+
+static int cpu_stopper_thread(void *data)
+{
+	struct cpu_stopper *stopper = data;
+	struct cpu_stop_work *work;
+	int ret;
+
+repeat:
+	set_current_state(TASK_INTERRUPTIBLE);	/* mb paired w/ kthread_stop */
+
+	if (kthread_should_stop()) {
+		__set_current_state(TASK_RUNNING);
+		return 0;
+	}
+
+	work = NULL;
+	spin_lock_irq(&stopper->lock);
+	if (!list_empty(&stopper->works)) {
+		work = list_first_entry(&stopper->works,
+					struct cpu_stop_work, list);
+		list_del_init(&work->list);
+	}
+	spin_unlock_irq(&stopper->lock);
+
+	if (work) {
+		cpu_stop_fn_t fn = work->fn;
+		void *arg = work->arg;
+		struct cpu_stop_done *done = work->done;
+		char ksym_buf[KSYM_NAME_LEN];
+
+		__set_current_state(TASK_RUNNING);
+
+		/* cpu stop callbacks are not allowed to sleep */
+		preempt_disable();
+
+		ret = fn(arg);
+		if (ret)
+			done->ret = ret;
+
+		/* restore preemption and check it's still balanced */
+		preempt_enable();
+		WARN_ONCE(preempt_count(),
+			  "cpu_stop: %s(%p) leaked preempt count\n",
+			  kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
+					  ksym_buf), arg);
+
+		cpu_stop_signal_done(done, true);
+	} else
+		schedule();
+
+	goto repeat;
+}
+
+/* manage stopper for a cpu, mostly lifted from sched migration thread mgmt */
+static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
+					   unsigned long action, void *hcpu)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+	unsigned int cpu = (unsigned long)hcpu;
+	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+	struct task_struct *p;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		BUG_ON(stopper->thread || stopper->enabled ||
+		       !list_empty(&stopper->works));
+		p = kthread_create(cpu_stopper_thread, stopper, "migration/%d",
+				   cpu);
+		if (IS_ERR(p))
+			return NOTIFY_BAD;
+		sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
+		get_task_struct(p);
+		stopper->thread = p;
+		break;
+
+	case CPU_ONLINE:
+		kthread_bind(stopper->thread, cpu);
+		/* strictly unnecessary, as first user will wake it */
+		wake_up_process(stopper->thread);
+		/* mark enabled */
+		spin_lock_irq(&stopper->lock);
+		stopper->enabled = true;
+		spin_unlock_irq(&stopper->lock);
+		break;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_UP_CANCELED:
+	case CPU_DEAD:
+	{
+		struct cpu_stop_work *work;
+
+		/* kill the stopper */
+		kthread_stop(stopper->thread);
+		/* drain remaining works */
+		spin_lock_irq(&stopper->lock);
+		list_for_each_entry(work, &stopper->works, list)
+			cpu_stop_signal_done(work->done, false);
+		stopper->enabled = false;
+		spin_unlock_irq(&stopper->lock);
+		/* release the stopper */
+		put_task_struct(stopper->thread);
+		stopper->thread = NULL;
+		break;
+	}
+#endif
+	}
+
+	return NOTIFY_OK;
+}
+
+/*
+ * Give it a higher priority so that cpu stopper is available to other
+ * cpu notifiers.  It currently shares the same priority as sched
+ * migration_notifier.
+ */
+static struct notifier_block __cpuinitdata cpu_stop_cpu_notifier = {
+	.notifier_call	= cpu_stop_cpu_callback,
+	.priority	= 10,
+};
+
+static int __init cpu_stop_init(void)
+{
+	void *bcpu = (void *)(long)smp_processor_id();
+	unsigned int cpu;
+	int err;
+
+	for_each_possible_cpu(cpu) {
+		struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+
+		spin_lock_init(&stopper->lock);
+		INIT_LIST_HEAD(&stopper->works);
+	}
+
+	/* start one for the boot cpu */
+	err = cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_UP_PREPARE,
+				    bcpu);
+	BUG_ON(err == NOTIFY_BAD);
+	cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_ONLINE, bcpu);
+	register_cpu_notifier(&cpu_stop_cpu_notifier);
+
+	return 0;
+}
+early_initcall(cpu_stop_init);
+
+#ifdef CONFIG_STOP_MACHINE

 /* This controls the threads on each CPU. */
 enum stopmachine_state {
@@ -26,174 +393,94 @@ enum stopmachine_state {
 	/* Exit */
 	STOPMACHINE_EXIT,
 };
-static enum stopmachine_state state;

 struct stop_machine_data {
-	int (*fn)(void *);
-	void *data;
-	int fnret;
+	int			(*fn)(void *);
+	void			*data;
+	/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+	unsigned int		num_threads;
+	const struct cpumask	*active_cpus;
+
+	enum stopmachine_state	state;
+	atomic_t		thread_ack;
 };

-/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
-static unsigned int num_threads;
-static atomic_t thread_ack;
-static DEFINE_MUTEX(lock);
-/* setup_lock protects refcount, stop_machine_wq and stop_machine_work. */
-static DEFINE_MUTEX(setup_lock);
-/* Users of stop_machine. */
-static int refcount;
-static struct workqueue_struct *stop_machine_wq;
-static struct stop_machine_data active, idle;
-static const struct cpumask *active_cpus;
-static void __percpu *stop_machine_work;
-
-static void set_state(enum stopmachine_state newstate)
+static void set_state(struct stop_machine_data *smdata,
+		      enum stopmachine_state newstate)
 {
 	/* Reset ack counter. */
-	atomic_set(&thread_ack, num_threads);
+	atomic_set(&smdata->thread_ack, smdata->num_threads);
 	smp_wmb();
-	state = newstate;
+	smdata->state = newstate;
 }

 /* Last one to ack a state moves to the next state. */
-static void ack_state(void)
+static void ack_state(struct stop_machine_data *smdata)
 {
-	if (atomic_dec_and_test(&thread_ack))
-		set_state(state + 1);
+	if (atomic_dec_and_test(&smdata->thread_ack))
+		set_state(smdata, smdata->state + 1);
 }

-/* This is the actual function which stops the CPU. It runs
- * in the context of a dedicated stopmachine workqueue. */
-static void stop_cpu(struct work_struct *unused)
+/* This is the cpu_stop function which stops the CPU. */
+static int stop_machine_cpu_stop(void *data)
 {
+	struct stop_machine_data *smdata = data;
 	enum stopmachine_state curstate = STOPMACHINE_NONE;
-	struct stop_machine_data *smdata = &idle;
-	int cpu = smp_processor_id();
-	int err;
+	int cpu = smp_processor_id(), err = 0;
+	bool is_active;
+
+	if (!smdata->active_cpus)
+		is_active = cpu == cpumask_first(cpu_online_mask);
+	else
+		is_active = cpumask_test_cpu(cpu, smdata->active_cpus);

-	if (!active_cpus) {
-		if (cpu == cpumask_first(cpu_online_mask))
-			smdata = &active;
-	} else {
-		if (cpumask_test_cpu(cpu, active_cpus))
-			smdata = &active;
-	}
 	/* Simple state machine */
 	do {
 		/* Chill out and ensure we re-read stopmachine_state. */
 		cpu_relax();
-		if (state != curstate) {
-			curstate = state;
+		if (smdata->state != curstate) {
+			curstate = smdata->state;
 			switch (curstate) {
 			case STOPMACHINE_DISABLE_IRQ:
 				local_irq_disable();
 				hard_irq_disable();
 				break;
 			case STOPMACHINE_RUN:
-				/* On multiple CPUs only a single error code
-				 * is needed to tell that something failed. */
-				err = smdata->fn(smdata->data);
-				if (err)
-					smdata->fnret = err;
+				if (is_active)
+					err = smdata->fn(smdata->data);
 				break;
 			default:
 				break;
 			}
-			ack_state();
+			ack_state(smdata);
 		}
 	} while (curstate != STOPMACHINE_EXIT);

 	local_irq_enable();
+	return err;
 }

-/* Callback for CPUs which aren't supposed to do anything. */
-static int chill(void *unused)
-{
-	return 0;
-}
-
-int stop_machine_create(void)
-{
-	mutex_lock(&setup_lock);
-	if (refcount)
-		goto done;
-	stop_machine_wq = create_rt_workqueue("kstop");
-	if (!stop_machine_wq)
-		goto err_out;
-	stop_machine_work = alloc_percpu(struct work_struct);
-	if (!stop_machine_work)
-		goto err_out;
-done:
-	refcount++;
-	mutex_unlock(&setup_lock);
-	return 0;
-
-err_out:
-	if (stop_machine_wq)
-		destroy_workqueue(stop_machine_wq);
-	mutex_unlock(&setup_lock);
-	return -ENOMEM;
-}
-EXPORT_SYMBOL_GPL(stop_machine_create);
-
-void stop_machine_destroy(void)
-{
-	mutex_lock(&setup_lock);
-	refcount--;
-	if (refcount)
-		goto done;
-	destroy_workqueue(stop_machine_wq);
-	free_percpu(stop_machine_work);
-done:
-	mutex_unlock(&setup_lock);
-}
-EXPORT_SYMBOL_GPL(stop_machine_destroy);
-
 int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
-	struct work_struct *sm_work;
-	int i, ret;
+	struct stop_machine_data smdata = { .fn = fn, .data = data,
+					    .num_threads = num_online_cpus(),
+					    .active_cpus = cpus };

-	/* Set up initial state. */
-	mutex_lock(&lock);
-	num_threads = num_online_cpus();
-	active_cpus = cpus;
-	active.fn = fn;
-	active.data = data;
-	active.fnret = 0;
-	idle.fn = chill;
-	idle.data = NULL;
-
-	set_state(STOPMACHINE_PREPARE);
-
-	/* Schedule the stop_cpu work on all cpus: hold this CPU so one
-	 * doesn't hit this CPU until we're ready. */
-	get_cpu();
-	for_each_online_cpu(i) {
-		sm_work = per_cpu_ptr(stop_machine_work, i);
-		INIT_WORK(sm_work, stop_cpu);
-		queue_work_on(i, stop_machine_wq, sm_work);
-	}
-	/* This will release the thread on our CPU. */
-	put_cpu();
-	flush_workqueue(stop_machine_wq);
-	ret = active.fnret;
-	mutex_unlock(&lock);
-	return ret;
+	/* Set the initial state and stop all online cpus. */
+	set_state(&smdata, STOPMACHINE_PREPARE);
+	return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata);
 }

 int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
 	int ret;

-	ret = stop_machine_create();
-	if (ret)
-		return ret;
 	/* No CPUs can come up or down during this. */
 	get_online_cpus();
 	ret = __stop_machine(fn, data, cpus);
 	put_online_cpus();
-	stop_machine_destroy();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(stop_machine);
+
+#endif	/* CONFIG_STOP_MACHINE */
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -150,14 +150,32 @@ static void tick_nohz_update_jiffies(ktime_t now)
 	touch_softlockup_watchdog();
 }

+/*
+ * Updates the per cpu time idle statistics counters
+ */
+static void
+update_ts_time_stats(struct tick_sched *ts, ktime_t now, u64 *last_update_time)
+{
+	ktime_t delta;
+
+	if (ts->idle_active) {
+		delta = ktime_sub(now, ts->idle_entrytime);
+		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+		if (nr_iowait_cpu() > 0)
+			ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
+		ts->idle_entrytime = now;
+	}
+
+	if (last_update_time)
+		*last_update_time = ktime_to_us(now);
+
+}
+
 static void tick_nohz_stop_idle(int cpu, ktime_t now)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-	ktime_t delta;

-	delta = ktime_sub(now, ts->idle_entrytime);
-	ts->idle_lastupdate = now;
-	ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+	update_ts_time_stats(ts, now, NULL);
 	ts->idle_active = 0;

 	sched_clock_idle_wakeup_event(0);
@@ -165,20 +183,32 @@ static void tick_nohz_stop_idle(int cpu, ktime_t now)

 static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
 {
-	ktime_t now, delta;
+	ktime_t now;

 	now = ktime_get();
-	if (ts->idle_active) {
-		delta = ktime_sub(now, ts->idle_entrytime);
-		ts->idle_lastupdate = now;
-		ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-	}
+
+	update_ts_time_stats(ts, now, NULL);
+
 	ts->idle_entrytime = now;
 	ts->idle_active = 1;
 	sched_clock_idle_sleep_event();
 	return now;
 }

+/**
+ * get_cpu_idle_time_us - get the total idle time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in
+ *
+ * Return the cummulative idle time (since boot) for a given
+ * CPU, in microseconds. The idle time returned includes
+ * the iowait time (unlike what "top" and co report).
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
 u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
@@ -186,15 +216,38 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 	if (!tick_nohz_enabled)
 		return -1;

-	if (ts->idle_active)
-		*last_update_time = ktime_to_us(ts->idle_lastupdate);
-	else
-		*last_update_time = ktime_to_us(ktime_get());
+	update_ts_time_stats(ts, ktime_get(), last_update_time);

 	return ktime_to_us(ts->idle_sleeptime);
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);

+/*
+ * get_cpu_iowait_time_us - get the total iowait time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in
+ *
+ * Return the cummulative iowait time (since boot) for a given
+ * CPU, in microseconds.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
+u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
+{
+	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+	if (!tick_nohz_enabled)
+		return -1;
+
+	update_ts_time_stats(ts, ktime_get(), last_update_time);
+
+	return ktime_to_us(ts->iowait_sleeptime);
+}
+EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
+
 /**
 * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
 *
@@ -262,6 +315,9 @@ void tick_nohz_stop_sched_tick(int inidle)
 		goto end;
 	}

+	if (nohz_ratelimit(cpu))
+		goto end;
+
 	ts->idle_calls++;
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -176,6 +176,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 		P_ns(idle_waketime);
 		P_ns(idle_exittime);
 		P_ns(idle_sleeptime);
+		P_ns(iowait_sleeptime);
 		P(last_jiffies);
 		P(next_jiffies);
 		P_ns(idle_expires);
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3212,8 +3212,7 @@ free:
 }

 static void
-ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
-				struct task_struct *next)
+ftrace_graph_probe_sched_switch(struct task_struct *prev, struct task_struct *next)
 {
 	unsigned long long timestamp;
 	int index;
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -50,8 +50,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 }

 static void
-probe_sched_switch(struct rq *__rq, struct task_struct *prev,
-			struct task_struct *next)
+probe_sched_switch(struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array_cpu *data;
 	unsigned long flags;
@@ -109,7 +108,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 }

 static void
-probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
+probe_sched_wakeup(struct task_struct *wakee, int success)
 {
 	struct trace_array_cpu *data;
 	unsigned long flags;
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -107,8 +107,7 @@ static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
 }

 static void notrace
-probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
-	struct task_struct *next)
+probe_wakeup_sched_switch(struct task_struct *prev, struct task_struct *next)
 {
 	struct trace_array_cpu *data;
 	cycle_t T0, T1, delta;
@@ -200,7 +199,7 @@ static void wakeup_reset(struct trace_array *tr)
 }

 static void
-probe_wakeup(struct rq *rq, struct task_struct *p, int success)
+probe_wakeup(struct task_struct *p, int success)
 {
 	struct trace_array_cpu *data;
 	int cpu = smp_processor_id();
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/user_namespace.h>
-#include "cred-internals.h"

 struct user_namespace init_user_ns = {
 	.kref = {
@@ -137,9 +136,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 	struct hlist_head *hashent = uidhashentry(ns, uid);
 	struct user_struct *up, *new;

-	/* Make uid_hash_find() + uids_user_create() + uid_hash_insert()
-	 * atomic.
-	 */
 	spin_lock_irq(&uidhash_lock);
 	up = uid_hash_find(uid, hashent);
 	spin_unlock_irq(&uidhash_lock);
@@ -161,11 +157,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		spin_lock_irq(&uidhash_lock);
 		up = uid_hash_find(uid, hashent);
 		if (up) {
-			/* This case is not possible when CONFIG_USER_SCHED
-			 * is defined, since we serialize alloc_uid() using
-			 * uids_mutex. Hence no need to call
-			 * sched_destroy_user() or remove_user_sysfs_dir().
-			 */
 			key_put(new->uid_keyring);
 			key_put(new->session_keyring);
 			kmem_cache_free(uid_cachep, new);
@@ -178,8 +169,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)

 	return up;

-	put_user_ns(new->user_ns);
-	kmem_cache_free(uid_cachep, new);
 out_unlock:
 	return NULL;
 }