Merge branch 'sched/core' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip into trace/tip/tracing/core-4

24 files changed, 1001 insertions, 1049 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index a987aa1676b5..149e18ef1ab1 100644
--- 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
diff --git a/kernel/capability.c b/kernel/capability.c
index 9e4697e9b276..2f05303715a5 100644
--- 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
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e2769e13980c..4a07d057a265 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -3010,7 +3010,7 @@ 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);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 25bba73b1be3..545777574779 100644
--- 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;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index d10946748ec2..9a50c5f6e727 100644
--- 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);
+        task_lock(tsk);
+        guarantee_online_cpus(task_cs(tsk), pmask);
+        task_unlock(tsk);
         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)
+int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
-        task_lock(tsk);
-        guarantee_online_cpus(task_cs(tsk), pmask);
-        task_unlock(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)
@@ -2383,22 +2416,6 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 }
 
 /**
- * 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
  *
  * Undo the lock taken in a previous cpuset_lock() call.
diff --git a/kernel/cred-internals.h b/kernel/cred-internals.h
deleted file mode 100644
index 2dc4fc2d0bf1..000000000000
--- a/kernel/cred-internals.h
+++ /dev/null
@@ -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 */
-}
-
diff --git a/kernel/cred.c b/kernel/cred.c
index e1dbe9eef800..8f3672a58a1e 100644
--- 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, ...) \
@@ -398,6 +397,8 @@ struct cred *prepare_usermodehelper_creds(void)
 
 error:
         put_cred(new);
+        return NULL;
+
 free_tgcred:
 #ifdef CONFIG_KEYS
         kfree(tgcred);
@@ -558,8 +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 ||
@@ -791,8 +790,6 @@ bool creds_are_invalid(const struct cred *cred)
 {
         if (cred->magic != CRED_MAGIC)
                 return true;
-        if (atomic_read(&cred->usage) < atomic_read(&cred->subscribers))
-                return true;
 #ifdef CONFIG_SECURITY_SELINUX
         if (selinux_is_enabled()) {
                 if ((unsigned long) cred->security < PAGE_SIZE)
diff --git a/kernel/exit.c b/kernel/exit.c
index 7f2683a10ac4..eabca5a73a85 100644
--- 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);
 
diff --git a/kernel/module.c b/kernel/module.c
index b8a1e313448c..e2564580f3f1 100644
--- 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;
 }
 
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 58df55bf83ed..2b676f3a0f26 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -669,7 +669,7 @@ 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"
 };
diff --git a/kernel/sched.c b/kernel/sched.c
index 6af210a7de70..b531d7934083 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -55,9 +55,9 @@
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/percpu.h>
-#include <linux/kthread.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/stop_machine.h>
 #include <linux/sysctl.h>
 #include <linux/syscalls.h>
 #include <linux/times.h>
@@ -493,8 +493,11 @@ struct rq {
         #define CPU_LOAD_IDX_MAX 5
         unsigned long cpu_load[CPU_LOAD_IDX_MAX];
 #ifdef CONFIG_NO_HZ
+        u64 nohz_stamp;
         unsigned char in_nohz_recently;
 #endif
+        unsigned int skip_clock_update;
+
         /* capture load from *all* tasks on this cpu: */
         struct load_weight load;
         unsigned long nr_load_updates;
@@ -536,15 +539,13 @@ struct rq {
         int post_schedule;
         int active_balance;
         int push_cpu;
+        struct cpu_stop_work active_balance_work;
         /* cpu of this runqueue: */
         int cpu;
         int online;
 
         unsigned long avg_load_per_task;
 
-        struct task_struct *migration_thread;
-        struct list_head migration_queue;
-
         u64 rt_avg;
         u64 age_stamp;
         u64 idle_stamp;
@@ -592,6 +593,13 @@ static inline
 void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
         rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+
+        /*
+         * A queue event has occurred, and we're going to schedule.  In
+         * this case, we can save a useless back to back clock update.
+         */
+        if (test_tsk_need_resched(p))
+                rq->skip_clock_update = 1;
 }
 
 static inline int cpu_of(struct rq *rq)
@@ -626,7 +634,8 @@ static inline int cpu_of(struct rq *rq)
 
 inline void update_rq_clock(struct rq *rq)
 {
-        rq->clock = sched_clock_cpu(cpu_of(rq));
+        if (!rq->skip_clock_update)
+                rq->clock = sched_clock_cpu(cpu_of(rq));
 }
 
 /*
@@ -904,16 +913,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #endif /* __ARCH_WANT_UNLOCKED_CTXSW */
 
 /*
- * Check whether the task is waking, we use this to synchronize against
- * ttwu() so that task_cpu() reports a stable number.
- *
- * We need to make an exception for PF_STARTING tasks because the fork
- * path might require task_rq_lock() to work, eg. it can call
- * set_cpus_allowed_ptr() from the cpuset clone_ns code.
+ * Check whether the task is waking, we use this to synchronize ->cpus_allowed
+ * against ttwu().
  */
 static inline int task_is_waking(struct task_struct *p)
 {
-        return unlikely((p->state == TASK_WAKING) && !(p->flags & PF_STARTING));
+        return unlikely(p->state == TASK_WAKING);
 }
 
 /*
@@ -926,11 +931,9 @@ static inline struct rq *__task_rq_lock(struct task_struct *p)
         struct rq *rq;
 
         for (;;) {
-                while (task_is_waking(p))
-                        cpu_relax();
                 rq = task_rq(p);
                 raw_spin_lock(&rq->lock);
-                if (likely(rq == task_rq(p) && !task_is_waking(p)))
+                if (likely(rq == task_rq(p)))
                         return rq;
                 raw_spin_unlock(&rq->lock);
         }
@@ -947,12 +950,10 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
         struct rq *rq;
 
         for (;;) {
-                while (task_is_waking(p))
-                        cpu_relax();
                 local_irq_save(*flags);
                 rq = task_rq(p);
                 raw_spin_lock(&rq->lock);
-                if (likely(rq == task_rq(p) && !task_is_waking(p)))
+                if (likely(rq == task_rq(p)))
                         return rq;
                 raw_spin_unlock_irqrestore(&rq->lock, *flags);
         }
@@ -1229,6 +1230,17 @@ void wake_up_idle_cpu(int cpu)
         if (!tsk_is_polling(rq->idle))
                 smp_send_reschedule(cpu);
 }
+
+int nohz_ratelimit(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+        u64 diff = rq->clock - rq->nohz_stamp;
+
+        rq->nohz_stamp = rq->clock;
+
+        return diff < (NSEC_PER_SEC / HZ) >> 1;
+}
+
 #endif /* CONFIG_NO_HZ */
 
 static u64 sched_avg_period(void)
@@ -1771,8 +1783,6 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
                         raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
                 }
         }
-        update_rq_clock(rq1);
-        update_rq_clock(rq2);
 }
 
 /*
@@ -1803,7 +1813,7 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 }
 #endif
 
-static void calc_load_account_active(struct rq *this_rq);
+static void calc_load_account_idle(struct rq *this_rq);
 static void update_sysctl(void);
 static int get_update_sysctl_factor(void);
 
@@ -1860,62 +1870,43 @@ static void set_load_weight(struct task_struct *p)
         p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
 }
 
-static void update_avg(u64 *avg, u64 sample)
+static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-        s64 diff = sample - *avg;
-        *avg += diff >> 3;
-}
-
-static void
-enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head)
-{
-        if (wakeup)
-                p->se.start_runtime = p->se.sum_exec_runtime;
-
+        update_rq_clock(rq);
         sched_info_queued(p);
-        p->sched_class->enqueue_task(rq, p, wakeup, head);
+        p->sched_class->enqueue_task(rq, p, flags);
         p->se.on_rq = 1;
 }
 
-static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-        if (sleep) {
-                if (p->se.last_wakeup) {
-                        update_avg(&p->se.avg_overlap,
-                                p->se.sum_exec_runtime - p->se.last_wakeup);
-                        p->se.last_wakeup = 0;
-                } else {
-                        update_avg(&p->se.avg_wakeup,
-                                sysctl_sched_wakeup_granularity);
-                }
-        }
-
+        update_rq_clock(rq);
         sched_info_dequeued(p);
-        p->sched_class->dequeue_task(rq, p, sleep);
+        p->sched_class->dequeue_task(rq, p, flags);
         p->se.on_rq = 0;
 }
 
 /*
  * activate_task - move a task to the runqueue.
  */
-static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
+static void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
         if (task_contributes_to_load(p))
                 rq->nr_uninterruptible--;
 
-        enqueue_task(rq, p, wakeup, false);
+        enqueue_task(rq, p, flags);
         inc_nr_running(rq);
 }
 
 /*
  * deactivate_task - remove a task from the runqueue.
  */
-static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
+static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
         if (task_contributes_to_load(p))
                 rq->nr_uninterruptible++;
 
-        dequeue_task(rq, p, sleep);
+        dequeue_task(rq, p, flags);
         dec_nr_running(rq);
 }
 
@@ -2044,21 +2035,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
         __set_task_cpu(p, new_cpu);
 }
 
-struct migration_req {
-        struct list_head list;
-
+struct migration_arg {
         struct task_struct *task;
         int dest_cpu;
-
-        struct completion done;
 };
 
+static int migration_cpu_stop(void *data);
+
 /*
  * The task's runqueue lock must be held.
  * Returns true if you have to wait for migration thread.
  */
-static int
-migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
+static bool migrate_task(struct task_struct *p, int dest_cpu)
 {
         struct rq *rq = task_rq(p);
 
@@ -2066,15 +2054,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
          * If the task is not on a runqueue (and not running), then
          * the next wake-up will properly place the task.
          */
-        if (!p->se.on_rq && !task_running(rq, p))
-                return 0;
-
-        init_completion(&req->done);
-        req->task = p;
-        req->dest_cpu = dest_cpu;
-        list_add(&req->list, &rq->migration_queue);
-
-        return 1;
+        return p->se.on_rq || task_running(rq, p);
 }
 
 /*
@@ -2175,7 +2155,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
                  * just go back and repeat.
                  */
                 rq = task_rq_lock(p, &flags);
-                trace_sched_wait_task(rq, p);
+                trace_sched_wait_task(p);
                 running = task_running(rq, p);
                 on_rq = p->se.on_rq;
                 ncsw = 0;
@@ -2273,6 +2253,9 @@ void task_oncpu_function_call(struct task_struct *p,
 }
 
 #ifdef CONFIG_SMP
+/*
+ * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
+ */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
         int dest_cpu;
@@ -2289,12 +2272,8 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
                 return dest_cpu;
 
         /* No more Mr. Nice Guy. */
-        if (dest_cpu >= nr_cpu_ids) {
-                rcu_read_lock();
-                cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
-                rcu_read_unlock();
-                dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
-
+        if (unlikely(dest_cpu >= nr_cpu_ids)) {
+                dest_cpu = cpuset_cpus_allowed_fallback(p);
                 /*
                  * Don't tell them about moving exiting tasks or
                  * kernel threads (both mm NULL), since they never
@@ -2311,17 +2290,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 }
 
 /*
- * Gets called from 3 sites (exec, fork, wakeup), since it is called without
- * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done
- * by:
- *
- *  exec:           is unstable, retry loop
- *  fork & wake-up: serialize ->cpus_allowed against TASK_WAKING
+ * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags)
 {
-        int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+        int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags);
 
         /*
          * In order not to call set_task_cpu() on a blocking task we need
@@ -2339,6 +2313,12 @@ int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
 
         return cpu;
 }
+
+static void update_avg(u64 *avg, u64 sample)
+{
+        s64 diff = sample - *avg;
+        *avg += diff >> 3;
+}
 #endif
 
 /***
@@ -2360,16 +2340,13 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
         int cpu, orig_cpu, this_cpu, success = 0;
         unsigned long flags;
+        unsigned long en_flags = ENQUEUE_WAKEUP;
         struct rq *rq;
 
-        if (!sched_feat(SYNC_WAKEUPS))
-                wake_flags &= ~WF_SYNC;
-
         this_cpu = get_cpu();
 
         smp_wmb();
         rq = task_rq_lock(p, &flags);
-        update_rq_clock(rq);
         if (!(p->state & state))
                 goto out;
 
@@ -2389,28 +2366,26 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
          *
          * First fix up the nr_uninterruptible count:
          */
-        if (task_contributes_to_load(p))
-                rq->nr_uninterruptible--;
+        if (task_contributes_to_load(p)) {
+                if (likely(cpu_online(orig_cpu)))
+                        rq->nr_uninterruptible--;
+                else
+                        this_rq()->nr_uninterruptible--;
+        }
         p->state = TASK_WAKING;
 
-        if (p->sched_class->task_waking)
+        if (p->sched_class->task_waking) {
                 p->sched_class->task_waking(rq, p);
+                en_flags |= ENQUEUE_WAKING;
+        }
 
-        __task_rq_unlock(rq);
-
-        cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-        if (cpu != orig_cpu) {
-                /*
-                 * Since we migrate the task without holding any rq->lock,
-                 * we need to be careful with task_rq_lock(), since that
-                 * might end up locking an invalid rq.
-                 */
+        cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags);
+        if (cpu != orig_cpu)
                 set_task_cpu(p, cpu);
-        }
+        __task_rq_unlock(rq);
 
         rq = cpu_rq(cpu);
         raw_spin_lock(&rq->lock);
-        update_rq_clock(rq);
 
         /*
          * We migrated the task without holding either rq->lock, however
@@ -2438,36 +2413,20 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 
 out_activate:
 #endif /* CONFIG_SMP */
-        schedstat_inc(p, se.nr_wakeups);
+        schedstat_inc(p, se.statistics.nr_wakeups);
         if (wake_flags & WF_SYNC)
-                schedstat_inc(p, se.nr_wakeups_sync);
+                schedstat_inc(p, se.statistics.nr_wakeups_sync);
         if (orig_cpu != cpu)
-                schedstat_inc(p, se.nr_wakeups_migrate);
+                schedstat_inc(p, se.statistics.nr_wakeups_migrate);
         if (cpu == this_cpu)
-                schedstat_inc(p, se.nr_wakeups_local);
+                schedstat_inc(p, se.statistics.nr_wakeups_local);
         else
-                schedstat_inc(p, se.nr_wakeups_remote);
-        activate_task(rq, p, 1);
+                schedstat_inc(p, se.statistics.nr_wakeups_remote);
+        activate_task(rq, p, en_flags);
         success = 1;
 
-        /*
-         * Only attribute actual wakeups done by this task.
-         */
-        if (!in_interrupt()) {
-                struct sched_entity *se = &current->se;
-                u64 sample = se->sum_exec_runtime;
-
-                if (se->last_wakeup)
-                        sample -= se->last_wakeup;
-                else
-                        sample -= se->start_runtime;
-                update_avg(&se->avg_wakeup, sample);
-
-                se->last_wakeup = se->sum_exec_runtime;
-        }
-
 out_running:
-        trace_sched_wakeup(rq, p, success);
+        trace_sched_wakeup(p, success);
         check_preempt_curr(rq, p, wake_flags);
 
         p->state = TASK_RUNNING;
@@ -2527,42 +2486,9 @@ static void __sched_fork(struct task_struct *p)
         p->se.sum_exec_runtime          = 0;
         p->se.prev_sum_exec_runtime     = 0;
         p->se.nr_migrations             = 0;
-        p->se.last_wakeup               = 0;
-        p->se.avg_overlap               = 0;
-        p->se.start_runtime             = 0;
-        p->se.avg_wakeup                = sysctl_sched_wakeup_granularity;
 
 #ifdef CONFIG_SCHEDSTATS
-        p->se.wait_start                        = 0;
-        p->se.wait_max                          = 0;
-        p->se.wait_count                        = 0;
-        p->se.wait_sum                          = 0;
-
-        p->se.sleep_start                       = 0;
-        p->se.sleep_max                         = 0;
-        p->se.sum_sleep_runtime                 = 0;
-
-        p->se.block_start                       = 0;
-        p->se.block_max                         = 0;
-        p->se.exec_max                          = 0;
-        p->se.slice_max                         = 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;
-
+        memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
         INIT_LIST_HEAD(&p->rt.run_list);
@@ -2583,11 +2509,11 @@ void sched_fork(struct task_struct *p, int clone_flags)
 
         __sched_fork(p);
         /*
-         * We mark the process as waking here. This guarantees that
+         * We mark the process as running here. This guarantees that
          * nobody will actually run it, and a signal or other external
          * event cannot wake it up and insert it on the runqueue either.
          */
-        p->state = TASK_WAKING;
+        p->state = TASK_RUNNING;
 
         /*
          * Revert to default priority/policy on fork if requested.
@@ -2654,31 +2580,27 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
         int cpu __maybe_unused = get_cpu();
 
 #ifdef CONFIG_SMP
+        rq = task_rq_lock(p, &flags);
+        p->state = TASK_WAKING;
+
         /*
          * Fork balancing, do it here and not earlier because:
          *  - cpus_allowed can change in the fork path
          *  - any previously selected cpu might disappear through hotplug
          *
-         * We still have TASK_WAKING but PF_STARTING is gone now, meaning
-         * ->cpus_allowed is stable, we have preemption disabled, meaning
-         * cpu_online_mask is stable.
+         * We set TASK_WAKING so that select_task_rq() can drop rq->lock
+         * without people poking at ->cpus_allowed.
          */
-        cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
+        cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0);
         set_task_cpu(p, cpu);
-#endif
 
-        /*
-         * Since the task is not on the rq and we still have TASK_WAKING set
-         * nobody else will migrate this task.
-         */
-        rq = cpu_rq(cpu);
-        raw_spin_lock_irqsave(&rq->lock, flags);
-
-        BUG_ON(p->state != TASK_WAKING);
         p->state = TASK_RUNNING;
-        update_rq_clock(rq);
+        task_rq_unlock(rq, &flags);
+#endif
+
+        rq = task_rq_lock(p, &flags);
         activate_task(rq, p, 0);
-        trace_sched_wakeup_new(rq, p, 1);
+        trace_sched_wakeup_new(p, 1);
         check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
         if (p->sched_class->task_woken)
@@ -2898,7 +2820,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
         struct mm_struct *mm, *oldmm;
 
         prepare_task_switch(rq, prev, next);
-        trace_sched_switch(rq, prev, next);
+        trace_sched_switch(prev, next);
         mm = next->mm;
         oldmm = prev->active_mm;
         /*
@@ -3015,6 +2937,61 @@ static unsigned long calc_load_update;
 unsigned long avenrun[3];
 EXPORT_SYMBOL(avenrun);
 
+static long calc_load_fold_active(struct rq *this_rq)
+{
+        long nr_active, delta = 0;
+
+        nr_active = this_rq->nr_running;
+        nr_active += (long) this_rq->nr_uninterruptible;
+
+        if (nr_active != this_rq->calc_load_active) {
+                delta = nr_active - this_rq->calc_load_active;
+                this_rq->calc_load_active = nr_active;
+        }
+
+        return delta;
+}
+
+#ifdef CONFIG_NO_HZ
+/*
+ * For NO_HZ we delay the active fold to the next LOAD_FREQ update.
+ *
+ * When making the ILB scale, we should try to pull this in as well.
+ */
+static atomic_long_t calc_load_tasks_idle;
+
+static void calc_load_account_idle(struct rq *this_rq)
+{
+        long delta;
+
+        delta = calc_load_fold_active(this_rq);
+        if (delta)
+                atomic_long_add(delta, &calc_load_tasks_idle);
+}
+
+static long calc_load_fold_idle(void)
+{
+        long delta = 0;
+
+        /*
+         * Its got a race, we don't care...
+         */
+        if (atomic_long_read(&calc_load_tasks_idle))
+                delta = atomic_long_xchg(&calc_load_tasks_idle, 0);
+
+        return delta;
+}
+#else
+static void calc_load_account_idle(struct rq *this_rq)
+{
+}
+
+static inline long calc_load_fold_idle(void)
+{
+        return 0;
+}
+#endif
+
 /**
  * get_avenrun - get the load average array
  * @loads:      pointer to dest load array
@@ -3061,20 +3038,22 @@ void calc_global_load(void)
 }
 
 /*
- * Either called from update_cpu_load() or from a cpu going idle
+ * Called from update_cpu_load() to periodically update this CPU's
+ * active count.
  */
 static void calc_load_account_active(struct rq *this_rq)
 {
-        long nr_active, delta;
+        long delta;
 
-        nr_active = this_rq->nr_running;
-        nr_active += (long) this_rq->nr_uninterruptible;
+        if (time_before(jiffies, this_rq->calc_load_update))
+                return;
 
-        if (nr_active != this_rq->calc_load_active) {
-                delta = nr_active - this_rq->calc_load_active;
-                this_rq->calc_load_active = nr_active;
+        delta  = calc_load_fold_active(this_rq);
+        delta += calc_load_fold_idle();
+        if (delta)
                 atomic_long_add(delta, &calc_load_tasks);
-        }
+
+        this_rq->calc_load_update += LOAD_FREQ;
 }
 
 /*
@@ -3106,10 +3085,7 @@ static void update_cpu_load(struct rq *this_rq)
                 this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
         }
 
-        if (time_after_eq(jiffies, this_rq->calc_load_update)) {
-                this_rq->calc_load_update += LOAD_FREQ;
-                calc_load_account_active(this_rq);
-        }
+        calc_load_account_active(this_rq);
 }
 
 #ifdef CONFIG_SMP
@@ -3121,44 +3097,27 @@ static void update_cpu_load(struct rq *this_rq)
 void sched_exec(void)
 {
         struct task_struct *p = current;
-        struct migration_req req;
-        int dest_cpu, this_cpu;
         unsigned long flags;
         struct rq *rq;
-
-again:
-        this_cpu = get_cpu();
-        dest_cpu = select_task_rq(p, SD_BALANCE_EXEC, 0);
-        if (dest_cpu == this_cpu) {
-                put_cpu();
-                return;
-        }
+        int dest_cpu;
 
         rq = task_rq_lock(p, &flags);
-        put_cpu();
+        dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
+        if (dest_cpu == smp_processor_id())
+                goto unlock;
 
         /*
          * select_task_rq() can race against ->cpus_allowed
          */
-        if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
-            || unlikely(!cpu_active(dest_cpu))) {
-                task_rq_unlock(rq, &flags);
-                goto again;
-        }
+        if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
+            likely(cpu_active(dest_cpu)) && migrate_task(p, dest_cpu)) {
+                struct migration_arg arg = { p, dest_cpu };
 
-        /* force the process onto the specified CPU */
-        if (migrate_task(p, dest_cpu, &req)) {
-                /* Need to wait for migration thread (might exit: take ref). */
-                struct task_struct *mt = rq->migration_thread;
-
-                get_task_struct(mt);
                 task_rq_unlock(rq, &flags);
-                wake_up_process(mt);
-                put_task_struct(mt);
-                wait_for_completion(&req.done);
-
+                stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
                 return;
         }
+unlock:
         task_rq_unlock(rq, &flags);
 }
 
@@ -3630,23 +3589,9 @@ static inline void schedule_debug(struct task_struct *prev)
 
 static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
-        if (prev->state == TASK_RUNNING) {
-                u64 runtime = prev->se.sum_exec_runtime;
-
-                runtime -= prev->se.prev_sum_exec_runtime;
-                runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
-
-                /*
-                 * In order to avoid avg_overlap growing stale when we are
-                 * indeed overlapping and hence not getting put to sleep, grow
-                 * the avg_overlap on preemption.
-                 *
-                 * We use the average preemption runtime because that
-                 * correlates to the amount of cache footprint a task can
-                 * build up.
-                 */
-                update_avg(&prev->se.avg_overlap, runtime);
-        }
+        if (prev->se.on_rq)
+                update_rq_clock(rq);
+        rq->skip_clock_update = 0;
         prev->sched_class->put_prev_task(rq, prev);
 }
 
@@ -3709,14 +3654,13 @@ need_resched_nonpreemptible:
                 hrtick_clear(rq);
 
         raw_spin_lock_irq(&rq->lock);
-        update_rq_clock(rq);
         clear_tsk_need_resched(prev);
 
         if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
                 if (unlikely(signal_pending_state(prev->state, prev)))
                         prev->state = TASK_RUNNING;
                 else
-                        deactivate_task(rq, prev, 1);
+                        deactivate_task(rq, prev, DEQUEUE_SLEEP);
                 switch_count = &prev->nvcsw;
         }
 
@@ -4039,8 +3983,7 @@ do_wait_for_common(struct completion *x, long timeout, int state)
         if (!x->done) {
                 DECLARE_WAITQUEUE(wait, current);
 
-                wait.flags |= WQ_FLAG_EXCLUSIVE;
-                __add_wait_queue_tail(&x->wait, &wait);
+                __add_wait_queue_tail_exclusive(&x->wait, &wait);
                 do {
                         if (signal_pending_state(state, current)) {
                                 timeout = -ERESTARTSYS;
@@ -4266,7 +4209,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
         BUG_ON(prio < 0 || prio > MAX_PRIO);
 
         rq = task_rq_lock(p, &flags);
-        update_rq_clock(rq);
 
         oldprio = p->prio;
         prev_class = p->sched_class;
@@ -4287,7 +4229,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
         if (running)
                 p->sched_class->set_curr_task(rq);
         if (on_rq) {
-                enqueue_task(rq, p, 0, oldprio < prio);
+                enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
                 check_class_changed(rq, p, prev_class, oldprio, running);
         }
@@ -4309,7 +4251,6 @@ void set_user_nice(struct task_struct *p, long nice)
          * the task might be in the middle of scheduling on another CPU.
          */
         rq = task_rq_lock(p, &flags);
-        update_rq_clock(rq);
         /*
          * The RT priorities are set via sched_setscheduler(), but we still
          * allow the 'normal' nice value to be set - but as expected
@@ -4331,7 +4272,7 @@ void set_user_nice(struct task_struct *p, long nice)
         delta = p->prio - old_prio;
 
         if (on_rq) {
-                enqueue_task(rq, p, 0, false);
+                enqueue_task(rq, p, 0);
                 /*
                  * If the task increased its priority or is running and
                  * lowered its priority, then reschedule its CPU:
@@ -4592,7 +4533,6 @@ recheck:
                 raw_spin_unlock_irqrestore(&p->pi_lock, flags);
                 goto recheck;
         }
-        update_rq_clock(rq);
         on_rq = p->se.on_rq;
         running = task_current(rq, p);
         if (on_rq)
@@ -5329,17 +5269,15 @@ static inline void sched_init_granularity(void)
 /*
  * This is how migration works:
  *
- * 1) we queue a struct migration_req structure in the source CPU's
- *    runqueue and wake up that CPU's migration thread.
- * 2) we down() the locked semaphore => thread blocks.
- * 3) migration thread wakes up (implicitly it forces the migrated
- *    thread off the CPU)
- * 4) it gets the migration request and checks whether the migrated
- *    task is still in the wrong runqueue.
- * 5) if it's in the wrong runqueue then the migration thread removes
+ * 1) we invoke migration_cpu_stop() on the target CPU using
+ *    stop_one_cpu().
+ * 2) stopper starts to run (implicitly forcing the migrated thread
+ *    off the CPU)
+ * 3) it checks whether the migrated task is still in the wrong runqueue.
+ * 4) if it's in the wrong runqueue then the migration thread removes
  *    it and puts it into the right queue.
- * 6) migration thread up()s the semaphore.
- * 7) we wake up and the migration is done.
+ * 5) stopper completes and stop_one_cpu() returns and the migration
+ *    is done.
  */
 
 /*
@@ -5353,12 +5291,23 @@ static inline void sched_init_granularity(void)
  */
 int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 {
-        struct migration_req req;
         unsigned long flags;
         struct rq *rq;
+        unsigned int dest_cpu;
         int ret = 0;
 
+        /*
+         * Serialize against TASK_WAKING so that ttwu() and wunt() can
+         * drop the rq->lock and still rely on ->cpus_allowed.
+         */
+again:
+        while (task_is_waking(p))
+                cpu_relax();
         rq = task_rq_lock(p, &flags);
+        if (task_is_waking(p)) {
+                task_rq_unlock(rq, &flags);
+                goto again;
+        }
 
         if (!cpumask_intersects(new_mask, cpu_active_mask)) {
                 ret = -EINVAL;
@@ -5382,15 +5331,12 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
         if (cpumask_test_cpu(task_cpu(p), new_mask))
                 goto out;
 
-        if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) {
+        dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
+        if (migrate_task(p, dest_cpu)) {
+                struct migration_arg arg = { p, dest_cpu };
                 /* Need help from migration thread: drop lock and wait. */
-                struct task_struct *mt = rq->migration_thread;
-
-                get_task_struct(mt);
                 task_rq_unlock(rq, &flags);
-                wake_up_process(mt);
-                put_task_struct(mt);
-                wait_for_completion(&req.done);
+                stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
                 tlb_migrate_finish(p->mm);
                 return 0;
         }
@@ -5448,98 +5394,49 @@ fail:
         return ret;
 }
 
-#define RCU_MIGRATION_IDLE      0
-#define RCU_MIGRATION_NEED_QS   1
-#define RCU_MIGRATION_GOT_QS    2
-#define RCU_MIGRATION_MUST_SYNC 3
-
 /*
- * migration_thread - this is a highprio system thread that performs
- * thread migration by bumping thread off CPU then 'pushing' onto
- * another runqueue.
+ * migration_cpu_stop - this will be executed by a highprio stopper thread
+ * and performs thread migration by bumping thread off CPU then
+ * 'pushing' onto another runqueue.
  */
-static int migration_thread(void *data)
+static int migration_cpu_stop(void *data)
 {
-        int badcpu;
-        int cpu = (long)data;
-        struct rq *rq;
-
-        rq = cpu_rq(cpu);
-        BUG_ON(rq->migration_thread != current);
-
-        set_current_state(TASK_INTERRUPTIBLE);
-        while (!kthread_should_stop()) {
-                struct migration_req *req;
-                struct list_head *head;
-
-                raw_spin_lock_irq(&rq->lock);
-
-                if (cpu_is_offline(cpu)) {
-                        raw_spin_unlock_irq(&rq->lock);
-                        break;
-                }
-
-                if (rq->active_balance) {
-                        active_load_balance(rq, cpu);
-                        rq->active_balance = 0;
-                }
-
-                head = &rq->migration_queue;
-
-                if (list_empty(head)) {
-                        raw_spin_unlock_irq(&rq->lock);
-                        schedule();
-                        set_current_state(TASK_INTERRUPTIBLE);
-                        continue;
-                }
-                req = list_entry(head->next, struct migration_req, list);
-                list_del_init(head->next);
-
-                if (req->task != NULL) {
-                        raw_spin_unlock(&rq->lock);
-                        __migrate_task(req->task, cpu, req->dest_cpu);
-                } else if (likely(cpu == (badcpu = smp_processor_id()))) {
-                        req->dest_cpu = RCU_MIGRATION_GOT_QS;
-                        raw_spin_unlock(&rq->lock);
-                } else {
-                        req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
-                        raw_spin_unlock(&rq->lock);
-                        WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
-                }
-                local_irq_enable();
-
-                complete(&req->done);
-        }
-        __set_current_state(TASK_RUNNING);
-
-        return 0;
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
-{
-        int ret;
+        struct migration_arg *arg = data;
 
+        /*
+         * The original target cpu might have gone down and we might
+         * be on another cpu but it doesn't matter.
+         */
         local_irq_disable();
-        ret = __migrate_task(p, src_cpu, dest_cpu);
+        __migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu);
         local_irq_enable();
-        return ret;
+        return 0;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * Figure out where task on dead CPU should go, use force if necessary.
  */
-static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
+void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 {
-        int dest_cpu;
+        struct rq *rq = cpu_rq(dead_cpu);
+        int needs_cpu, uninitialized_var(dest_cpu);
+        unsigned long flags;
 
-again:
-        dest_cpu = select_fallback_rq(dead_cpu, p);
+        local_irq_save(flags);
 
-        /* It can have affinity changed while we were choosing. */
-        if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
-                goto again;
+        raw_spin_lock(&rq->lock);
+        needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING);
+        if (needs_cpu)
+                dest_cpu = select_fallback_rq(dead_cpu, p);
+        raw_spin_unlock(&rq->lock);
+        /*
+         * It can only fail if we race with set_cpus_allowed(),
+         * in the racer should migrate the task anyway.
+         */
+        if (needs_cpu)
+                __migrate_task(p, dead_cpu, dest_cpu);
+        local_irq_restore(flags);
 }
 
 /*
@@ -5603,7 +5500,6 @@ void sched_idle_next(void)
 
         __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
 
-        update_rq_clock(rq);
         activate_task(rq, p, 0);
 
         raw_spin_unlock_irqrestore(&rq->lock, flags);
@@ -5658,7 +5554,6 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
         for ( ; ; ) {
                 if (!rq->nr_running)
                         break;
-                update_rq_clock(rq);
                 next = pick_next_task(rq);
                 if (!next)
                         break;
@@ -5881,35 +5776,20 @@ static void set_rq_offline(struct rq *rq)
 static int __cpuinit
 migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
-        struct task_struct *p;
         int cpu = (long)hcpu;
         unsigned long flags;
-        struct rq *rq;
+        struct rq *rq = cpu_rq(cpu);
 
         switch (action) {
 
         case CPU_UP_PREPARE:
         case CPU_UP_PREPARE_FROZEN:
-                p = kthread_create(migration_thread, hcpu, "migration/%d", cpu);
-                if (IS_ERR(p))
-                        return NOTIFY_BAD;
-                kthread_bind(p, cpu);
-                /* Must be high prio: stop_machine expects to yield to it. */
-                rq = task_rq_lock(p, &flags);
-                __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
-                task_rq_unlock(rq, &flags);
-                get_task_struct(p);
-                cpu_rq(cpu)->migration_thread = p;
                 rq->calc_load_update = calc_load_update;
                 break;
 
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
-                /* Strictly unnecessary, as first user will wake it. */
-                wake_up_process(cpu_rq(cpu)->migration_thread);
-
                 /* Update our root-domain */
-                rq = cpu_rq(cpu);
                 raw_spin_lock_irqsave(&rq->lock, flags);
                 if (rq->rd) {
                         BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
@@ -5920,61 +5800,24 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 break;
 
 #ifdef CONFIG_HOTPLUG_CPU
-        case CPU_UP_CANCELED:
-        case CPU_UP_CANCELED_FROZEN:
-                if (!cpu_rq(cpu)->migration_thread)
-                        break;
-                /* Unbind it from offline cpu so it can run. Fall thru. */
-                kthread_bind(cpu_rq(cpu)->migration_thread,
-                             cpumask_any(cpu_online_mask));
-                kthread_stop(cpu_rq(cpu)->migration_thread);
-                put_task_struct(cpu_rq(cpu)->migration_thread);
-                cpu_rq(cpu)->migration_thread = NULL;
-                break;
-
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
-                cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */
                 migrate_live_tasks(cpu);
-                rq = cpu_rq(cpu);
-                kthread_stop(rq->migration_thread);
-                put_task_struct(rq->migration_thread);
-                rq->migration_thread = NULL;
                 /* Idle task back to normal (off runqueue, low prio) */
                 raw_spin_lock_irq(&rq->lock);
-                update_rq_clock(rq);
                 deactivate_task(rq, rq->idle, 0);
                 __setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
                 rq->idle->sched_class = &idle_sched_class;
                 migrate_dead_tasks(cpu);
                 raw_spin_unlock_irq(&rq->lock);
-                cpuset_unlock();
                 migrate_nr_uninterruptible(rq);
                 BUG_ON(rq->nr_running != 0);
                 calc_global_load_remove(rq);
-                /*
-                 * No need to migrate the tasks: it was best-effort if
-                 * they didn't take sched_hotcpu_mutex. Just wake up
-                 * the requestors.
-                 */
-                raw_spin_lock_irq(&rq->lock);
-                while (!list_empty(&rq->migration_queue)) {
-                        struct migration_req *req;
-
-                        req = list_entry(rq->migration_queue.next,
-                                         struct migration_req, list);
-                        list_del_init(&req->list);
-                        raw_spin_unlock_irq(&rq->lock);
-                        complete(&req->done);
-                        raw_spin_lock_irq(&rq->lock);
-                }
-                raw_spin_unlock_irq(&rq->lock);
                 break;
 
         case CPU_DYING:
         case CPU_DYING_FROZEN:
                 /* Update our root-domain */
-                rq = cpu_rq(cpu);
                 raw_spin_lock_irqsave(&rq->lock, flags);
                 if (rq->rd) {
                         BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
@@ -6305,6 +6148,9 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
         struct rq *rq = cpu_rq(cpu);
         struct sched_domain *tmp;
 
+        for (tmp = sd; tmp; tmp = tmp->parent)
+                tmp->span_weight = cpumask_weight(sched_domain_span(tmp));
+
         /* Remove the sched domains which do not contribute to scheduling. */
         for (tmp = sd; tmp; ) {
                 struct sched_domain *parent = tmp->parent;
@@ -7788,10 +7634,8 @@ void __init sched_init(void)
                 rq->push_cpu = 0;
                 rq->cpu = i;
                 rq->online = 0;
-                rq->migration_thread = NULL;
                 rq->idle_stamp = 0;
                 rq->avg_idle = 2*sysctl_sched_migration_cost;
-                INIT_LIST_HEAD(&rq->migration_queue);
                 rq_attach_root(rq, &def_root_domain);
 #endif
                 init_rq_hrtick(rq);
@@ -7892,7 +7736,6 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 {
         int on_rq;
 
-        update_rq_clock(rq);
         on_rq = p->se.on_rq;
         if (on_rq)
                 deactivate_task(rq, p, 0);
@@ -7919,9 +7762,9 @@ void normalize_rt_tasks(void)
 
                 p->se.exec_start                = 0;
 #ifdef CONFIG_SCHEDSTATS
-                p->se.wait_start                = 0;
-                p->se.sleep_start               = 0;
-                p->se.block_start               = 0;
+                p->se.statistics.wait_start     = 0;
+                p->se.statistics.sleep_start    = 0;
+                p->se.statistics.block_start    = 0;
 #endif
 
                 if (!rt_task(p)) {
@@ -8254,8 +8097,6 @@ void sched_move_task(struct task_struct *tsk)
 
         rq = task_rq_lock(tsk, &flags);
 
-        update_rq_clock(rq);
-
         running = task_current(rq, tsk);
         on_rq = tsk->se.on_rq;
 
@@ -8274,7 +8115,7 @@ void sched_move_task(struct task_struct *tsk)
         if (unlikely(running))
                 tsk->sched_class->set_curr_task(rq);
         if (on_rq)
-                enqueue_task(rq, tsk, 0, false);
+                enqueue_task(rq, tsk, 0);
 
         task_rq_unlock(rq, &flags);
 }
@@ -9088,43 +8929,32 @@ struct cgroup_subsys cpuacct_subsys = {
 
 #ifndef CONFIG_SMP
 
-int rcu_expedited_torture_stats(char *page)
-{
-        return 0;
-}
-EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
-
 void synchronize_sched_expedited(void)
 {
+        barrier();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
 
 #else /* #ifndef CONFIG_SMP */
 
-static DEFINE_PER_CPU(struct migration_req, rcu_migration_req);
-static DEFINE_MUTEX(rcu_sched_expedited_mutex);
-
-#define RCU_EXPEDITED_STATE_POST -2
-#define RCU_EXPEDITED_STATE_IDLE -1
-
-static int rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0);
 
-int rcu_expedited_torture_stats(char *page)
+static int synchronize_sched_expedited_cpu_stop(void *data)
 {
-        int cnt = 0;
-        int cpu;
-
-        cnt += sprintf(&page[cnt], "state: %d /", rcu_expedited_state);
-        for_each_online_cpu(cpu) {
-                 cnt += sprintf(&page[cnt], " %d:%d",
-                                cpu, per_cpu(rcu_migration_req, cpu).dest_cpu);
-        }
-        cnt += sprintf(&page[cnt], "\n");
-        return cnt;
+        /*
+         * There must be a full memory barrier on each affected CPU
+         * between the time that try_stop_cpus() is called and the
+         * time that it returns.
+         *
+         * In the current initial implementation of cpu_stop, the
+         * above condition is already met when the control reaches
+         * this point and the following smp_mb() is not strictly
+         * necessary.  Do smp_mb() anyway for documentation and
+         * robustness against future implementation changes.
+         */
+        smp_mb(); /* See above comment block. */
+        return 0;
 }
-EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
-
-static long synchronize_sched_expedited_count;
 
 /*
  * Wait for an rcu-sched grace period to elapse, but use "big hammer"
@@ -9138,18 +8968,14 @@ static long synchronize_sched_expedited_count;
  */
 void synchronize_sched_expedited(void)
 {
-        int cpu;
-        unsigned long flags;
-        bool need_full_sync = 0;
-        struct rq *rq;
-        struct migration_req *req;
-        long snap;
-        int trycount = 0;
+        int snap, trycount = 0;
 
         smp_mb();  /* ensure prior mod happens before capturing snap. */
-        snap = ACCESS_ONCE(synchronize_sched_expedited_count) + 1;
+        snap = atomic_read(&synchronize_sched_expedited_count) + 1;
         get_online_cpus();
-        while (!mutex_trylock(&rcu_sched_expedited_mutex)) {
+        while (try_stop_cpus(cpu_online_mask,
+                             synchronize_sched_expedited_cpu_stop,
+                             NULL) == -EAGAIN) {
                 put_online_cpus();
                 if (trycount++ < 10)
                         udelay(trycount * num_online_cpus());
@@ -9157,41 +8983,15 @@ void synchronize_sched_expedited(void)
                         synchronize_sched();
                         return;
                 }
-                if (ACCESS_ONCE(synchronize_sched_expedited_count) - snap > 0) {
+                if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) {
                         smp_mb(); /* ensure test happens before caller kfree */
                         return;
                 }
                 get_online_cpus();
         }
-        rcu_expedited_state = RCU_EXPEDITED_STATE_POST;
-        for_each_online_cpu(cpu) {
-                rq = cpu_rq(cpu);
-                req = &per_cpu(rcu_migration_req, cpu);
-                init_completion(&req->done);
-                req->task = NULL;
-                req->dest_cpu = RCU_MIGRATION_NEED_QS;
-                raw_spin_lock_irqsave(&rq->lock, flags);
-                list_add(&req->list, &rq->migration_queue);
-                raw_spin_unlock_irqrestore(&rq->lock, flags);
-                wake_up_process(rq->migration_thread);
-        }
-        for_each_online_cpu(cpu) {
-                rcu_expedited_state = cpu;
-                req = &per_cpu(rcu_migration_req, cpu);
-                rq = cpu_rq(cpu);
-                wait_for_completion(&req->done);
-                raw_spin_lock_irqsave(&rq->lock, flags);
-                if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC))
-                        need_full_sync = 1;
-                req->dest_cpu = RCU_MIGRATION_IDLE;
-                raw_spin_unlock_irqrestore(&rq->lock, flags);
-        }
-        rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
-        synchronize_sched_expedited_count++;
-        mutex_unlock(&rcu_sched_expedited_mutex);
+        atomic_inc(&synchronize_sched_expedited_count);
+        smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */
         put_online_cpus();
-        if (need_full_sync)
-                synchronize_sched();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
 
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 9b49db144037..9cf1baf6616a 100644
--- 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);
@@ -173,11 +173,6 @@ 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
@@ -407,40 +402,38 @@ 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;
@@ -491,31 +484,6 @@ 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
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5a5ea2cd924f..217e4a9393e4 100644
--- 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);
                         }
 
@@ -737,20 +738,10 @@ 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
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index d5059fd761d9..83c66e8ad3ee 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -1,11 +1,4 @@
 /*
- * 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
  * rip the spread apart.
@@ -13,13 +6,6 @@ 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
  */
@@ -31,37 +17,6 @@ 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 --
  * improve cache locality. Typically used with SYNC wakeups as
@@ -70,16 +25,6 @@ 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
  * touched, increases cache locality.
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index a8a6d8a50947..9fa0f402c87c 100644
--- 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");
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index b5b920ae2ea7..8afb953e31c6 100644
--- 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();
 
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 9bb9fb1bd79c..ef51d1fcf5e6 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -1,17 +1,381 @@
-/* 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 cpu_stop_work *work;
+        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:
+                /* 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 +390,94 @@ 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;
-
-        /* 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;
+        struct stop_machine_data smdata = { .fn = fn, .data = data,
+                                            .num_threads = num_online_cpus(),
+                                            .active_cpus = cpus };
+
+        /* 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 */
diff --git a/kernel/sys.c b/kernel/sys.c
index 6d1a7e0f9d5b..7cb426a58965 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1118,7 +1118,7 @@ DECLARE_RWSEM(uts_sem);
 
 #ifdef COMPAT_UTS_MACHINE
 #define override_architecture(name) \
-        (current->personality == PER_LINUX32 && \
+        (personality(current->personality) == PER_LINUX32 && \
          copy_to_user(name->machine, COMPAT_UTS_MACHINE, \
                       sizeof(COMPAT_UTS_MACHINE)))
 #else
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f992762d7f51..1d7b9bc1c034 100644
--- 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 {
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 1a4a7dd78777..ab8f5e33fa92 100644
--- 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);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8c9c2934c45f..32837e19e3bd 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3234,8 +3234,7 @@ 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;
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 5fca0f51fde4..a55fccfede5d 100644
--- 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;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 0271742abb8d..8052446ceeaa 100644
--- 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();
diff --git a/kernel/user.c b/kernel/user.c
index 766467b3bcb7..7e72614b736d 100644
--- 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;
 }