1 files changed, 391 insertions, 356 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index e7f2cfa6a257..87f1f47beffe 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -141,7 +141,7 @@ struct rt_prio_array {
 
 struct rt_bandwidth {
         /* nests inside the rq lock: */
-        spinlock_t              rt_runtime_lock;
+        raw_spinlock_t          rt_runtime_lock;
         ktime_t                 rt_period;
         u64                     rt_runtime;
         struct hrtimer          rt_period_timer;
@@ -178,7 +178,7 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
         rt_b->rt_period = ns_to_ktime(period);
         rt_b->rt_runtime = runtime;
 
-        spin_lock_init(&rt_b->rt_runtime_lock);
+        raw_spin_lock_init(&rt_b->rt_runtime_lock);
 
         hrtimer_init(&rt_b->rt_period_timer,
                         CLOCK_MONOTONIC, HRTIMER_MODE_REL);
@@ -200,7 +200,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
         if (hrtimer_active(&rt_b->rt_period_timer))
                 return;
 
-        spin_lock(&rt_b->rt_runtime_lock);
+        raw_spin_lock(&rt_b->rt_runtime_lock);
         for (;;) {
                 unsigned long delta;
                 ktime_t soft, hard;
@@ -217,7 +217,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
                 __hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
                                 HRTIMER_MODE_ABS_PINNED, 0);
         }
-        spin_unlock(&rt_b->rt_runtime_lock);
+        raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -298,7 +298,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq);
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq_var);
 #endif /* CONFIG_RT_GROUP_SCHED */
 #else /* !CONFIG_USER_SCHED */
 #define root_task_group init_task_group
@@ -470,7 +470,7 @@ struct rt_rq {
         u64 rt_time;
         u64 rt_runtime;
         /* Nests inside the rq lock: */
-        spinlock_t rt_runtime_lock;
+        raw_spinlock_t rt_runtime_lock;
 
 #ifdef CONFIG_RT_GROUP_SCHED
         unsigned long rt_nr_boosted;
@@ -525,7 +525,7 @@ static struct root_domain def_root_domain;
  */
 struct rq {
         /* runqueue lock: */
-        spinlock_t lock;
+        raw_spinlock_t lock;
 
         /*
          * nr_running and cpu_load should be in the same cacheline because
@@ -685,7 +685,7 @@ inline void update_rq_clock(struct rq *rq)
  */
 int runqueue_is_locked(int cpu)
 {
-        return spin_is_locked(&cpu_rq(cpu)->lock);
+        return raw_spin_is_locked(&cpu_rq(cpu)->lock);
 }
 
 /*
@@ -814,6 +814,7 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
  * default: 0.25ms
  */
 unsigned int sysctl_sched_shares_ratelimit = 250000;
+unsigned int normalized_sysctl_sched_shares_ratelimit = 250000;
 
 /*
  * Inject some fuzzyness into changing the per-cpu group shares
@@ -892,7 +893,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
          */
         spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
 
-        spin_unlock_irq(&rq->lock);
+        raw_spin_unlock_irq(&rq->lock);
 }
 
 #else /* __ARCH_WANT_UNLOCKED_CTXSW */
@@ -916,9 +917,9 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
         next->oncpu = 1;
 #endif
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
-        spin_unlock_irq(&rq->lock);
+        raw_spin_unlock_irq(&rq->lock);
 #else
-        spin_unlock(&rq->lock);
+        raw_spin_unlock(&rq->lock);
 #endif
 }
 
@@ -948,10 +949,10 @@ static inline struct rq *__task_rq_lock(struct task_struct *p)
 {
         for (;;) {
                 struct rq *rq = task_rq(p);
-                spin_lock(&rq->lock);
+                raw_spin_lock(&rq->lock);
                 if (likely(rq == task_rq(p)))
                         return rq;
-                spin_unlock(&rq->lock);
+                raw_spin_unlock(&rq->lock);
         }
 }
 
@@ -968,10 +969,10 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
         for (;;) {
                 local_irq_save(*flags);
                 rq = task_rq(p);
-                spin_lock(&rq->lock);
+                raw_spin_lock(&rq->lock);
                 if (likely(rq == task_rq(p)))
                         return rq;
-                spin_unlock_irqrestore(&rq->lock, *flags);
+                raw_spin_unlock_irqrestore(&rq->lock, *flags);
         }
 }
 
@@ -980,19 +981,19 @@ void task_rq_unlock_wait(struct task_struct *p)
         struct rq *rq = task_rq(p);
 
         smp_mb(); /* spin-unlock-wait is not a full memory barrier */
-        spin_unlock_wait(&rq->lock);
+        raw_spin_unlock_wait(&rq->lock);
 }
 
 static void __task_rq_unlock(struct rq *rq)
         __releases(rq->lock)
 {
-        spin_unlock(&rq->lock);
+        raw_spin_unlock(&rq->lock);
 }
 
 static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
         __releases(rq->lock)
 {
-        spin_unlock_irqrestore(&rq->lock, *flags);
+        raw_spin_unlock_irqrestore(&rq->lock, *flags);
 }
 
 /*
@@ -1005,7 +1006,7 @@ static struct rq *this_rq_lock(void)
 
         local_irq_disable();
         rq = this_rq();
-        spin_lock(&rq->lock);
+        raw_spin_lock(&rq->lock);
 
         return rq;
 }
@@ -1052,10 +1053,10 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 
         WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
 
-        spin_lock(&rq->lock);
+        raw_spin_lock(&rq->lock);
         update_rq_clock(rq);
         rq->curr->sched_class->task_tick(rq, rq->curr, 1);
-        spin_unlock(&rq->lock);
+        raw_spin_unlock(&rq->lock);
 
         return HRTIMER_NORESTART;
 }
@@ -1068,10 +1069,10 @@ static void __hrtick_start(void *arg)
 {
         struct rq *rq = arg;
 
-        spin_lock(&rq->lock);
+        raw_spin_lock(&rq->lock);
         hrtimer_restart(&rq->hrtick_timer);
         rq->hrtick_csd_pending = 0;
-        spin_unlock(&rq->lock);
+        raw_spin_unlock(&rq->lock);
 }
 
 /*
@@ -1178,7 +1179,7 @@ static void resched_task(struct task_struct *p)
 {
         int cpu;
 
-        assert_spin_locked(&task_rq(p)->lock);
+        assert_raw_spin_locked(&task_rq(p)->lock);
 
         if (test_tsk_need_resched(p))
                 return;
@@ -1200,10 +1201,10 @@ static void resched_cpu(int cpu)
         struct rq *rq = cpu_rq(cpu);
         unsigned long flags;
 
-        if (!spin_trylock_irqsave(&rq->lock, flags))
+        if (!raw_spin_trylock_irqsave(&rq->lock, flags))
                 return;
         resched_task(cpu_curr(cpu));
-        spin_unlock_irqrestore(&rq->lock, flags);
+        raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
 #ifdef CONFIG_NO_HZ
@@ -1272,7 +1273,7 @@ static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
 #else /* !CONFIG_SMP */
 static void resched_task(struct task_struct *p)
 {
-        assert_spin_locked(&task_rq(p)->lock);
+        assert_raw_spin_locked(&task_rq(p)->lock);
         set_tsk_need_resched(p);
 }
 
@@ -1599,11 +1600,11 @@ static void update_group_shares_cpu(struct task_group *tg, int cpu,
                 struct rq *rq = cpu_rq(cpu);
                 unsigned long flags;
 
-                spin_lock_irqsave(&rq->lock, flags);
+                raw_spin_lock_irqsave(&rq->lock, flags);
                 tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
                 tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
                 __set_se_shares(tg->se[cpu], shares);
-                spin_unlock_irqrestore(&rq->lock, flags);
+                raw_spin_unlock_irqrestore(&rq->lock, flags);
         }
 }
 
@@ -1614,7 +1615,7 @@ static void update_group_shares_cpu(struct task_group *tg, int cpu,
  */
 static int tg_shares_up(struct task_group *tg, void *data)
 {
-        unsigned long weight, rq_weight = 0, shares = 0;
+        unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0;
         unsigned long *usd_rq_weight;
         struct sched_domain *sd = data;
         unsigned long flags;
@@ -1630,6 +1631,7 @@ static int tg_shares_up(struct task_group *tg, void *data)
                 weight = tg->cfs_rq[i]->load.weight;
                 usd_rq_weight[i] = weight;
 
+                rq_weight += weight;
                 /*
                  * If there are currently no tasks on the cpu pretend there
                  * is one of average load so that when a new task gets to
@@ -1638,10 +1640,13 @@ static int tg_shares_up(struct task_group *tg, void *data)
                 if (!weight)
                         weight = NICE_0_LOAD;
 
-                rq_weight += weight;
+                sum_weight += weight;
                 shares += tg->cfs_rq[i]->shares;
         }
 
+        if (!rq_weight)
+                rq_weight = sum_weight;
+
         if ((!shares && rq_weight) || shares > tg->shares)
                 shares = tg->shares;
 
@@ -1701,9 +1706,9 @@ static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
         if (root_task_group_empty())
                 return;
 
-        spin_unlock(&rq->lock);
+        raw_spin_unlock(&rq->lock);
         update_shares(sd);
-        spin_lock(&rq->lock);
+        raw_spin_lock(&rq->lock);
 }
 
 static void update_h_load(long cpu)
@@ -1743,7 +1748,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
         __acquires(busiest->lock)
         __acquires(this_rq->lock)
 {
-        spin_unlock(&this_rq->lock);
+        raw_spin_unlock(&this_rq->lock);
         double_rq_lock(this_rq, busiest);
 
         return 1;
@@ -1764,14 +1769,16 @@ static int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
 {
         int ret = 0;
 
-        if (unlikely(!spin_trylock(&busiest->lock))) {
+        if (unlikely(!raw_spin_trylock(&busiest->lock))) {
                 if (busiest < this_rq) {
-                        spin_unlock(&this_rq->lock);
-                        spin_lock(&busiest->lock);
-                        spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
+                        raw_spin_unlock(&this_rq->lock);
+                        raw_spin_lock(&busiest->lock);
+                        raw_spin_lock_nested(&this_rq->lock,
+                                              SINGLE_DEPTH_NESTING);
                         ret = 1;
                 } else
-                        spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
+                        raw_spin_lock_nested(&busiest->lock,
+                                              SINGLE_DEPTH_NESTING);
         }
         return ret;
 }
@@ -1785,7 +1792,7 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
 {
         if (unlikely(!irqs_disabled())) {
                 /* printk() doesn't work good under rq->lock */
-                spin_unlock(&this_rq->lock);
+                raw_spin_unlock(&this_rq->lock);
                 BUG_ON(1);
         }
 
@@ -1795,7 +1802,7 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
 static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
         __releases(busiest->lock)
 {
-        spin_unlock(&busiest->lock);
+        raw_spin_unlock(&busiest->lock);
         lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
 }
 #endif
@@ -1810,6 +1817,22 @@ 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 update_sysctl(void);
+static int get_update_sysctl_factor(void);
+
+static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
+{
+        set_task_rq(p, cpu);
+#ifdef CONFIG_SMP
+        /*
+         * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
+         * successfuly executed on another CPU. We must ensure that updates of
+         * per-task data have been completed by this moment.
+         */
+        smp_wmb();
+        task_thread_info(p)->cpu = cpu;
+#endif
+}
 
 #include "sched_stats.h"
 #include "sched_idletask.c"
@@ -1967,20 +1990,6 @@ inline int task_curr(const struct task_struct *p)
         return cpu_curr(task_cpu(p)) == p;
 }
 
-static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
-{
-        set_task_rq(p, cpu);
-#ifdef CONFIG_SMP
-        /*
-         * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
-         * successfuly executed on another CPU. We must ensure that updates of
-         * per-task data have been completed by this moment.
-         */
-        smp_wmb();
-        task_thread_info(p)->cpu = cpu;
-#endif
-}
-
 static inline void check_class_changed(struct rq *rq, struct task_struct *p,
                                        const struct sched_class *prev_class,
                                        int oldprio, int running)
@@ -1993,39 +2002,6 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
                 p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
-/**
- * kthread_bind - bind a just-created kthread to a cpu.
- * @p: thread created by kthread_create().
- * @cpu: cpu (might not be online, must be possible) for @k to run on.
- *
- * Description: This function is equivalent to set_cpus_allowed(),
- * except that @cpu doesn't need to be online, and the thread must be
- * stopped (i.e., just returned from kthread_create()).
- *
- * Function lives here instead of kthread.c because it messes with
- * scheduler internals which require locking.
- */
-void kthread_bind(struct task_struct *p, unsigned int cpu)
-{
-        struct rq *rq = cpu_rq(cpu);
-        unsigned long flags;
-
-        /* Must have done schedule() in kthread() before we set_task_cpu */
-        if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
-                WARN_ON(1);
-                return;
-        }
-
-        spin_lock_irqsave(&rq->lock, flags);
-        update_rq_clock(rq);
-        set_task_cpu(p, cpu);
-        p->cpus_allowed = cpumask_of_cpu(cpu);
-        p->rt.nr_cpus_allowed = 1;
-        p->flags |= PF_THREAD_BOUND;
-        spin_unlock_irqrestore(&rq->lock, flags);
-}
-EXPORT_SYMBOL(kthread_bind);
-
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
@@ -2035,6 +2011,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 {
         s64 delta;
 
+        if (p->sched_class != &fair_sched_class)
+                return 0;
+
         /*
          * Buddy candidates are cache hot:
          */
@@ -2043,9 +2022,6 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
                          &p->se == cfs_rq_of(&p->se)->last))
                 return 1;
 
-        if (p->sched_class != &fair_sched_class)
-                return 0;
-
         if (sysctl_sched_migration_cost == -1)
                 return 1;
         if (sysctl_sched_migration_cost == 0)
@@ -2056,38 +2032,24 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
         return delta < (s64)sysctl_sched_migration_cost;
 }
 
-
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
-        int old_cpu = task_cpu(p);
-        struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
-        struct cfs_rq *old_cfsrq = task_cfs_rq(p),
-                      *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu);
-        u64 clock_offset;
-
-        clock_offset = old_rq->clock - new_rq->clock;
+#ifdef CONFIG_SCHED_DEBUG
+        /*
+         * We should never call set_task_cpu() on a blocked task,
+         * ttwu() will sort out the placement.
+         */
+        WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
+                        !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
+#endif
 
         trace_sched_migrate_task(p, new_cpu);
 
-#ifdef CONFIG_SCHEDSTATS
-        if (p->se.wait_start)
-                p->se.wait_start -= clock_offset;
-        if (p->se.sleep_start)
-                p->se.sleep_start -= clock_offset;
-        if (p->se.block_start)
-                p->se.block_start -= clock_offset;
-#endif
-        if (old_cpu != new_cpu) {
-                p->se.nr_migrations++;
-#ifdef CONFIG_SCHEDSTATS
-                if (task_hot(p, old_rq->clock, NULL))
-                        schedstat_inc(p, se.nr_forced2_migrations);
-#endif
-                perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS,
-                                     1, 1, NULL, 0);
-        }
-        p->se.vruntime -= old_cfsrq->min_vruntime -
-                                         new_cfsrq->min_vruntime;
+        if (task_cpu(p) == new_cpu)
+                return;
+
+        p->se.nr_migrations++;
+        perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0);
 
         __set_task_cpu(p, new_cpu);
 }
@@ -2112,13 +2074,10 @@ 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
-         * it is sufficient to simply update the task's cpu field.
+         * the next wake-up will properly place the task.
          */
-        if (!p->se.on_rq && !task_running(rq, p)) {
-                update_rq_clock(rq);
-                set_task_cpu(p, dest_cpu);
+        if (!p->se.on_rq && !task_running(rq, p))
                 return 0;
-        }
 
         init_completion(&req->done);
         req->task = p;
@@ -2323,6 +2282,77 @@ void task_oncpu_function_call(struct task_struct *p,
         preempt_enable();
 }
 
+#ifdef CONFIG_SMP
+static int select_fallback_rq(int cpu, struct task_struct *p)
+{
+        int dest_cpu;
+        const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
+
+        /* Look for allowed, online CPU in same node. */
+        for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
+                if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+                        return dest_cpu;
+
+        /* Any allowed, online CPU? */
+        dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask);
+        if (dest_cpu < nr_cpu_ids)
+                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);
+
+                /*
+                 * Don't tell them about moving exiting tasks or
+                 * kernel threads (both mm NULL), since they never
+                 * leave kernel.
+                 */
+                if (p->mm && printk_ratelimit()) {
+                        printk(KERN_INFO "process %d (%s) no "
+                               "longer affine to cpu%d\n",
+                               task_pid_nr(p), p->comm, cpu);
+                }
+        }
+
+        return dest_cpu;
+}
+
+/*
+ * Called from:
+ *
+ *  - fork, @p is stable because it isn't on the tasklist yet
+ *
+ *  - exec, @p is unstable, retry loop
+ *
+ *  - wake-up, we serialize ->cpus_allowed against TASK_WAKING so
+ *             we should be good.
+ */
+static inline
+int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+{
+        int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+
+        /*
+         * In order not to call set_task_cpu() on a blocking task we need
+         * to rely on ttwu() to place the task on a valid ->cpus_allowed
+         * cpu.
+         *
+         * Since this is common to all placement strategies, this lives here.
+         *
+         * [ this allows ->select_task() to simply return task_cpu(p) and
+         *   not worry about this generic constraint ]
+         */
+        if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
+                     !cpu_online(cpu)))
+                cpu = select_fallback_rq(task_cpu(p), p);
+
+        return cpu;
+}
+#endif
+
 /***
  * try_to_wake_up - wake up a thread
  * @p: the to-be-woken-up thread
@@ -2374,17 +2404,18 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
         if (task_contributes_to_load(p))
                 rq->nr_uninterruptible--;
         p->state = TASK_WAKING;
-        task_rq_unlock(rq, &flags);
 
-        cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-        if (cpu != orig_cpu) {
-                local_irq_save(flags);
-                rq = cpu_rq(cpu);
-                update_rq_clock(rq);
+        if (p->sched_class->task_waking)
+                p->sched_class->task_waking(rq, p);
+
+        __task_rq_unlock(rq);
+
+        cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+        if (cpu != orig_cpu)
                 set_task_cpu(p, cpu);
-                local_irq_restore(flags);
-        }
-        rq = task_rq_lock(p, &flags);
+
+        rq = __task_rq_lock(p);
+        update_rq_clock(rq);
 
         WARN_ON(p->state != TASK_WAKING);
         cpu = task_cpu(p);
@@ -2440,8 +2471,8 @@ out_running:
 
         p->state = TASK_RUNNING;
 #ifdef CONFIG_SMP
-        if (p->sched_class->task_wake_up)
-                p->sched_class->task_wake_up(rq, p);
+        if (p->sched_class->task_woken)
+                p->sched_class->task_woken(rq, p);
 
         if (unlikely(rq->idle_stamp)) {
                 u64 delta = rq->clock - rq->idle_stamp;
@@ -2499,7 +2530,6 @@ static void __sched_fork(struct task_struct *p)
         p->se.avg_overlap               = 0;
         p->se.start_runtime             = 0;
         p->se.avg_wakeup                = sysctl_sched_wakeup_granularity;
-        p->se.avg_running               = 0;
 
 #ifdef CONFIG_SCHEDSTATS
         p->se.wait_start                        = 0;
@@ -2521,7 +2551,6 @@ static void __sched_fork(struct task_struct *p)
         p->se.nr_failed_migrations_running      = 0;
         p->se.nr_failed_migrations_hot          = 0;
         p->se.nr_forced_migrations              = 0;
-        p->se.nr_forced2_migrations             = 0;
 
         p->se.nr_wakeups                        = 0;
         p->se.nr_wakeups_sync                   = 0;
@@ -2542,14 +2571,6 @@ static void __sched_fork(struct task_struct *p)
 #ifdef CONFIG_PREEMPT_NOTIFIERS
         INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
-
-        /*
-         * We mark the process as running here, but have not actually
-         * inserted it onto the runqueue yet. 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_RUNNING;
 }
 
 /*
@@ -2558,9 +2579,14 @@ static void __sched_fork(struct task_struct *p)
 void sched_fork(struct task_struct *p, int clone_flags)
 {
         int cpu = get_cpu();
-        unsigned long flags;
 
         __sched_fork(p);
+        /*
+         * We mark the process as waking 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;
 
         /*
          * Revert to default priority/policy on fork if requested.
@@ -2592,13 +2618,13 @@ void sched_fork(struct task_struct *p, int clone_flags)
         if (!rt_prio(p->prio))
                 p->sched_class = &fair_sched_class;
 
+        if (p->sched_class->task_fork)
+                p->sched_class->task_fork(p);
+
 #ifdef CONFIG_SMP
-        cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0);
+        cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
 #endif
-        local_irq_save(flags);
-        update_rq_clock(cpu_rq(cpu));
         set_task_cpu(p, cpu);
-        local_irq_restore(flags);
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
         if (likely(sched_info_on()))
@@ -2629,24 +2655,15 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
         struct rq *rq;
 
         rq = task_rq_lock(p, &flags);
-        BUG_ON(p->state != TASK_RUNNING);
+        BUG_ON(p->state != TASK_WAKING);
+        p->state = TASK_RUNNING;
         update_rq_clock(rq);
-
-        if (!p->sched_class->task_new || !current->se.on_rq) {
-                activate_task(rq, p, 0);
-        } else {
-                /*
-                 * Let the scheduling class do new task startup
-                 * management (if any):
-                 */
-                p->sched_class->task_new(rq, p);
-                inc_nr_running(rq);
-        }
+        activate_task(rq, p, 0);
         trace_sched_wakeup_new(rq, p, 1);
         check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
-        if (p->sched_class->task_wake_up)
-                p->sched_class->task_wake_up(rq, p);
+        if (p->sched_class->task_woken)
+                p->sched_class->task_woken(rq, p);
 #endif
         task_rq_unlock(rq, &flags);
 }
@@ -2798,10 +2815,10 @@ static inline void post_schedule(struct rq *rq)
         if (rq->post_schedule) {
                 unsigned long flags;
 
-                spin_lock_irqsave(&rq->lock, flags);
+                raw_spin_lock_irqsave(&rq->lock, flags);
                 if (rq->curr->sched_class->post_schedule)
                         rq->curr->sched_class->post_schedule(rq);
-                spin_unlock_irqrestore(&rq->lock, flags);
+                raw_spin_unlock_irqrestore(&rq->lock, flags);
 
                 rq->post_schedule = 0;
         }
@@ -3083,15 +3100,15 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
 {
         BUG_ON(!irqs_disabled());
         if (rq1 == rq2) {
-                spin_lock(&rq1->lock);
+                raw_spin_lock(&rq1->lock);
                 __acquire(rq2->lock);   /* Fake it out ;) */
         } else {
                 if (rq1 < rq2) {
-                        spin_lock(&rq1->lock);
-                        spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
+                        raw_spin_lock(&rq1->lock);
+                        raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
                 } else {
-                        spin_lock(&rq2->lock);
-                        spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
+                        raw_spin_lock(&rq2->lock);
+                        raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
                 }
         }
         update_rq_clock(rq1);
@@ -3108,29 +3125,44 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
         __releases(rq1->lock)
         __releases(rq2->lock)
 {
-        spin_unlock(&rq1->lock);
+        raw_spin_unlock(&rq1->lock);
         if (rq1 != rq2)
-                spin_unlock(&rq2->lock);
+                raw_spin_unlock(&rq2->lock);
         else
                 __release(rq2->lock);
 }
 
 /*
- * If dest_cpu is allowed for this process, migrate the task to it.
- * This is accomplished by forcing the cpu_allowed mask to only
- * allow dest_cpu, which will force the cpu onto dest_cpu. Then
- * the cpu_allowed mask is restored.
+ * sched_exec - execve() is a valuable balancing opportunity, because at
+ * this point the task has the smallest effective memory and cache footprint.
  */
-static void sched_migrate_task(struct task_struct *p, int dest_cpu)
+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;
+        }
+
         rq = task_rq_lock(p, &flags);
+        put_cpu();
+
+        /*
+         * select_task_rq() can race against ->cpus_allowed
+         */
         if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
-            || unlikely(!cpu_active(dest_cpu)))
-                goto out;
+            || unlikely(!cpu_active(dest_cpu))) {
+                task_rq_unlock(rq, &flags);
+                goto again;
+        }
 
         /* force the process onto the specified CPU */
         if (migrate_task(p, dest_cpu, &req)) {
@@ -3145,24 +3177,10 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
 
                 return;
         }
-out:
         task_rq_unlock(rq, &flags);
 }
 
 /*
- * sched_exec - execve() is a valuable balancing opportunity, because at
- * this point the task has the smallest effective memory and cache footprint.
- */
-void sched_exec(void)
-{
-        int new_cpu, this_cpu = get_cpu();
-        new_cpu = current->sched_class->select_task_rq(current, SD_BALANCE_EXEC, 0);
-        put_cpu();
-        if (new_cpu != this_cpu)
-                sched_migrate_task(current, new_cpu);
-}
-
-/*
  * pull_task - move a task from a remote runqueue to the local runqueue.
  * Both runqueues must be locked.
  */
@@ -3172,10 +3190,6 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
         deactivate_task(src_rq, p, 0);
         set_task_cpu(p, this_cpu);
         activate_task(this_rq, p, 0);
-        /*
-         * Note that idle threads have a prio of MAX_PRIO, for this test
-         * to be always true for them.
-         */
         check_preempt_curr(this_rq, p, 0);
 }
 
@@ -4134,7 +4148,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
         unsigned long flags;
         struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
-        cpumask_copy(cpus, cpu_online_mask);
+        cpumask_copy(cpus, cpu_active_mask);
 
         /*
          * When power savings policy is enabled for the parent domain, idle
@@ -4207,14 +4221,15 @@ redo:
 
                 if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
 
-                        spin_lock_irqsave(&busiest->lock, flags);
+                        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
                          */
                         if (!cpumask_test_cpu(this_cpu,
                                               &busiest->curr->cpus_allowed)) {
-                                spin_unlock_irqrestore(&busiest->lock, flags);
+                                raw_spin_unlock_irqrestore(&busiest->lock,
+                                                            flags);
                                 all_pinned = 1;
                                 goto out_one_pinned;
                         }
@@ -4224,7 +4239,7 @@ redo:
                                 busiest->push_cpu = this_cpu;
                                 active_balance = 1;
                         }
-                        spin_unlock_irqrestore(&busiest->lock, flags);
+                        raw_spin_unlock_irqrestore(&busiest->lock, flags);
                         if (active_balance)
                                 wake_up_process(busiest->migration_thread);
 
@@ -4297,7 +4312,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
         int all_pinned = 0;
         struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
-        cpumask_copy(cpus, cpu_online_mask);
+        cpumask_copy(cpus, cpu_active_mask);
 
         /*
          * When power savings policy is enabled for the parent domain, idle
@@ -4406,10 +4421,10 @@ redo:
                 /*
                  * Should not call ttwu while holding a rq->lock
                  */
-                spin_unlock(&this_rq->lock);
+                raw_spin_unlock(&this_rq->lock);
                 if (active_balance)
                         wake_up_process(busiest->migration_thread);
-                spin_lock(&this_rq->lock);
+                raw_spin_lock(&this_rq->lock);
 
         } else
                 sd->nr_balance_failed = 0;
@@ -4694,7 +4709,7 @@ int select_nohz_load_balancer(int stop_tick)
                 cpumask_set_cpu(cpu, nohz.cpu_mask);
 
                 /* time for ilb owner also to sleep */
-                if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
+                if (cpumask_weight(nohz.cpu_mask) == num_active_cpus()) {
                         if (atomic_read(&nohz.load_balancer) == cpu)
                                 atomic_set(&nohz.load_balancer, -1);
                         return 0;
@@ -5278,11 +5293,11 @@ void scheduler_tick(void)
 
         sched_clock_tick();
 
-        spin_lock(&rq->lock);
+        raw_spin_lock(&rq->lock);
         update_rq_clock(rq);
         update_cpu_load(rq);
         curr->sched_class->task_tick(rq, curr, 0);
-        spin_unlock(&rq->lock);
+        raw_spin_unlock(&rq->lock);
 
         perf_event_task_tick(curr, cpu);
 
@@ -5396,13 +5411,14 @@ static inline void schedule_debug(struct task_struct *prev)
 #endif
 }
 
-static void put_prev_task(struct rq *rq, struct task_struct *p)
+static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
-        u64 runtime = p->se.sum_exec_runtime - p->se.prev_sum_exec_runtime;
+        if (prev->state == TASK_RUNNING) {
+                u64 runtime = prev->se.sum_exec_runtime;
 
-        update_avg(&p->se.avg_running, runtime);
+                runtime -= prev->se.prev_sum_exec_runtime;
+                runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
 
-        if (p->state == TASK_RUNNING) {
                 /*
                  * In order to avoid avg_overlap growing stale when we are
                  * indeed overlapping and hence not getting put to sleep, grow
@@ -5412,12 +5428,9 @@ static void put_prev_task(struct rq *rq, struct task_struct *p)
                  * correlates to the amount of cache footprint a task can
                  * build up.
                  */
-                runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
-                update_avg(&p->se.avg_overlap, runtime);
-        } else {
-                update_avg(&p->se.avg_running, 0);
+                update_avg(&prev->se.avg_overlap, runtime);
         }
-        p->sched_class->put_prev_task(rq, p);
+        prev->sched_class->put_prev_task(rq, prev);
 }
 
 /*
@@ -5478,7 +5491,7 @@ need_resched_nonpreemptible:
         if (sched_feat(HRTICK))
                 hrtick_clear(rq);
 
-        spin_lock_irq(&rq->lock);
+        raw_spin_lock_irq(&rq->lock);
         update_rq_clock(rq);
         clear_tsk_need_resched(prev);
 
@@ -5514,7 +5527,7 @@ need_resched_nonpreemptible:
                 cpu = smp_processor_id();
                 rq = cpu_rq(cpu);
         } else
-                spin_unlock_irq(&rq->lock);
+                raw_spin_unlock_irq(&rq->lock);
 
         post_schedule(rq);
 
@@ -5931,14 +5944,15 @@ EXPORT_SYMBOL(wait_for_completion_killable);
  */
 bool try_wait_for_completion(struct completion *x)
 {
+        unsigned long flags;
         int ret = 1;
 
-        spin_lock_irq(&x->wait.lock);
+        spin_lock_irqsave(&x->wait.lock, flags);
         if (!x->done)
                 ret = 0;
         else
                 x->done--;
-        spin_unlock_irq(&x->wait.lock);
+        spin_unlock_irqrestore(&x->wait.lock, flags);
         return ret;
 }
 EXPORT_SYMBOL(try_wait_for_completion);
@@ -5953,12 +5967,13 @@ EXPORT_SYMBOL(try_wait_for_completion);
  */
 bool completion_done(struct completion *x)
 {
+        unsigned long flags;
         int ret = 1;
 
-        spin_lock_irq(&x->wait.lock);
+        spin_lock_irqsave(&x->wait.lock, flags);
         if (!x->done)
                 ret = 0;
-        spin_unlock_irq(&x->wait.lock);
+        spin_unlock_irqrestore(&x->wait.lock, flags);
         return ret;
 }
 EXPORT_SYMBOL(completion_done);
@@ -6343,7 +6358,7 @@ recheck:
          * make sure no PI-waiters arrive (or leave) while we are
          * changing the priority of the task:
          */
-        spin_lock_irqsave(&p->pi_lock, flags);
+        raw_spin_lock_irqsave(&p->pi_lock, flags);
         /*
          * To be able to change p->policy safely, the apropriate
          * runqueue lock must be held.
@@ -6353,7 +6368,7 @@ recheck:
         if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
                 policy = oldpolicy = -1;
                 __task_rq_unlock(rq);
-                spin_unlock_irqrestore(&p->pi_lock, flags);
+                raw_spin_unlock_irqrestore(&p->pi_lock, flags);
                 goto recheck;
         }
         update_rq_clock(rq);
@@ -6377,7 +6392,7 @@ recheck:
                 check_class_changed(rq, p, prev_class, oldprio, running);
         }
         __task_rq_unlock(rq);
-        spin_unlock_irqrestore(&p->pi_lock, flags);
+        raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
         rt_mutex_adjust_pi(p);
 
@@ -6477,7 +6492,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
                 return -EINVAL;
 
         retval = -ESRCH;
-        read_lock(&tasklist_lock);
+        rcu_read_lock();
         p = find_process_by_pid(pid);
         if (p) {
                 retval = security_task_getscheduler(p);
@@ -6485,7 +6500,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
                         retval = p->policy
                                 | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
         }
-        read_unlock(&tasklist_lock);
+        rcu_read_unlock();
         return retval;
 }
 
@@ -6503,7 +6518,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
         if (!param || pid < 0)
                 return -EINVAL;
 
-        read_lock(&tasklist_lock);
+        rcu_read_lock();
         p = find_process_by_pid(pid);
         retval = -ESRCH;
         if (!p)
@@ -6514,7 +6529,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
                 goto out_unlock;
 
         lp.sched_priority = p->rt_priority;
-        read_unlock(&tasklist_lock);
+        rcu_read_unlock();
 
         /*
          * This one might sleep, we cannot do it with a spinlock held ...
@@ -6524,7 +6539,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
         return retval;
 
 out_unlock:
-        read_unlock(&tasklist_lock);
+        rcu_read_unlock();
         return retval;
 }
 
@@ -6535,22 +6550,18 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
         int retval;
 
         get_online_cpus();
-        read_lock(&tasklist_lock);
+        rcu_read_lock();
 
         p = find_process_by_pid(pid);
         if (!p) {
-                read_unlock(&tasklist_lock);
+                rcu_read_unlock();
                 put_online_cpus();
                 return -ESRCH;
         }
 
-        /*
-         * It is not safe to call set_cpus_allowed with the
-         * tasklist_lock held. We will bump the task_struct's
-         * usage count and then drop tasklist_lock.
-         */
+        /* Prevent p going away */
         get_task_struct(p);
-        read_unlock(&tasklist_lock);
+        rcu_read_unlock();
 
         if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
                 retval = -ENOMEM;
@@ -6631,10 +6642,12 @@ SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
 long sched_getaffinity(pid_t pid, struct cpumask *mask)
 {
         struct task_struct *p;
+        unsigned long flags;
+        struct rq *rq;
         int retval;
 
         get_online_cpus();
-        read_lock(&tasklist_lock);
+        rcu_read_lock();
 
         retval = -ESRCH;
         p = find_process_by_pid(pid);
@@ -6645,10 +6658,12 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
         if (retval)
                 goto out_unlock;
 
+        rq = task_rq_lock(p, &flags);
         cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
+        task_rq_unlock(rq, &flags);
 
 out_unlock:
-        read_unlock(&tasklist_lock);
+        rcu_read_unlock();
         put_online_cpus();
 
         return retval;
@@ -6703,7 +6718,7 @@ SYSCALL_DEFINE0(sched_yield)
          */
         __release(rq->lock);
         spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
-        _raw_spin_unlock(&rq->lock);
+        do_raw_spin_unlock(&rq->lock);
         preempt_enable_no_resched();
 
         schedule();
@@ -6883,6 +6898,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 {
         struct task_struct *p;
         unsigned int time_slice;
+        unsigned long flags;
+        struct rq *rq;
         int retval;
         struct timespec t;
 
@@ -6890,7 +6907,7 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
                 return -EINVAL;
 
         retval = -ESRCH;
-        read_lock(&tasklist_lock);
+        rcu_read_lock();
         p = find_process_by_pid(pid);
         if (!p)
                 goto out_unlock;
@@ -6899,15 +6916,17 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
         if (retval)
                 goto out_unlock;
 
-        time_slice = p->sched_class->get_rr_interval(p);
+        rq = task_rq_lock(p, &flags);
+        time_slice = p->sched_class->get_rr_interval(rq, p);
+        task_rq_unlock(rq, &flags);
 
-        read_unlock(&tasklist_lock);
+        rcu_read_unlock();
         jiffies_to_timespec(time_slice, &t);
         retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
         return retval;
 
 out_unlock:
-        read_unlock(&tasklist_lock);
+        rcu_read_unlock();
         return retval;
 }
 
@@ -6995,12 +7014,12 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
         struct rq *rq = cpu_rq(cpu);
         unsigned long flags;
 
-        spin_lock_irqsave(&rq->lock, flags);
+        raw_spin_lock_irqsave(&rq->lock, flags);
 
         __sched_fork(idle);
+        idle->state = TASK_RUNNING;
         idle->se.exec_start = sched_clock();
 
-        idle->prio = idle->normal_prio = MAX_PRIO;
         cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
         __set_task_cpu(idle, cpu);
 
@@ -7008,7 +7027,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
         idle->oncpu = 1;
 #endif
-        spin_unlock_irqrestore(&rq->lock, flags);
+        raw_spin_unlock_irqrestore(&rq->lock, flags);
 
         /* Set the preempt count _outside_ the spinlocks! */
 #if defined(CONFIG_PREEMPT)
@@ -7041,22 +7060,43 @@ cpumask_var_t nohz_cpu_mask;
  *
  * This idea comes from the SD scheduler of Con Kolivas:
  */
-static inline void sched_init_granularity(void)
+static int get_update_sysctl_factor(void)
 {
-        unsigned int factor = 1 + ilog2(num_online_cpus());
-        const unsigned long limit = 200000000;
+        unsigned int cpus = min_t(int, num_online_cpus(), 8);
+        unsigned int factor;
+
+        switch (sysctl_sched_tunable_scaling) {
+        case SCHED_TUNABLESCALING_NONE:
+                factor = 1;
+                break;
+        case SCHED_TUNABLESCALING_LINEAR:
+                factor = cpus;
+                break;
+        case SCHED_TUNABLESCALING_LOG:
+        default:
+                factor = 1 + ilog2(cpus);
+                break;
+        }
 
-        sysctl_sched_min_granularity *= factor;
-        if (sysctl_sched_min_granularity > limit)
-                sysctl_sched_min_granularity = limit;
+        return factor;
+}
 
-        sysctl_sched_latency *= factor;
-        if (sysctl_sched_latency > limit)
-                sysctl_sched_latency = limit;
+static void update_sysctl(void)
+{
+        unsigned int factor = get_update_sysctl_factor();
 
-        sysctl_sched_wakeup_granularity *= factor;
+#define SET_SYSCTL(name) \
+        (sysctl_##name = (factor) * normalized_sysctl_##name)
+        SET_SYSCTL(sched_min_granularity);
+        SET_SYSCTL(sched_latency);
+        SET_SYSCTL(sched_wakeup_granularity);
+        SET_SYSCTL(sched_shares_ratelimit);
+#undef SET_SYSCTL
+}
 
-        sysctl_sched_shares_ratelimit *= factor;
+static inline void sched_init_granularity(void)
+{
+        update_sysctl();
 }
 
 #ifdef CONFIG_SMP
@@ -7092,8 +7132,24 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
         struct rq *rq;
         int ret = 0;
 
+        /*
+         * Since we rely on wake-ups to migrate sleeping tasks, don't change
+         * the ->cpus_allowed mask from under waking tasks, which would be
+         * possible when we change rq->lock in ttwu(), so synchronize against
+         * TASK_WAKING to avoid that.
+         */
+again:
+        while (p->state == TASK_WAKING)
+                cpu_relax();
+
         rq = task_rq_lock(p, &flags);
-        if (!cpumask_intersects(new_mask, cpu_online_mask)) {
+
+        if (p->state == TASK_WAKING) {
+                task_rq_unlock(rq, &flags);
+                goto again;
+        }
+
+        if (!cpumask_intersects(new_mask, cpu_active_mask)) {
                 ret = -EINVAL;
                 goto out;
         }
@@ -7115,7 +7171,7 @@ 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_online_mask, new_mask), &req)) {
+        if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) {
                 /* Need help from migration thread: drop lock and wait. */
                 struct task_struct *mt = rq->migration_thread;
 
@@ -7148,7 +7204,7 @@ EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 {
         struct rq *rq_dest, *rq_src;
-        int ret = 0, on_rq;
+        int ret = 0;
 
         if (unlikely(!cpu_active(dest_cpu)))
                 return ret;
@@ -7164,12 +7220,13 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
         if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
                 goto fail;
 
-        on_rq = p->se.on_rq;
-        if (on_rq)
+        /*
+         * If we're not on a rq, the next wake-up will ensure we're
+         * placed properly.
+         */
+        if (p->se.on_rq) {
                 deactivate_task(rq_src, p, 0);
-
-        set_task_cpu(p, dest_cpu);
-        if (on_rq) {
+                set_task_cpu(p, dest_cpu);
                 activate_task(rq_dest, p, 0);
                 check_preempt_curr(rq_dest, p, 0);
         }
@@ -7204,10 +7261,10 @@ static int migration_thread(void *data)
                 struct migration_req *req;
                 struct list_head *head;
 
-                spin_lock_irq(&rq->lock);
+                raw_spin_lock_irq(&rq->lock);
 
                 if (cpu_is_offline(cpu)) {
-                        spin_unlock_irq(&rq->lock);
+                        raw_spin_unlock_irq(&rq->lock);
                         break;
                 }
 
@@ -7219,7 +7276,7 @@ static int migration_thread(void *data)
                 head = &rq->migration_queue;
 
                 if (list_empty(head)) {
-                        spin_unlock_irq(&rq->lock);
+                        raw_spin_unlock_irq(&rq->lock);
                         schedule();
                         set_current_state(TASK_INTERRUPTIBLE);
                         continue;
@@ -7228,14 +7285,14 @@ static int migration_thread(void *data)
                 list_del_init(head->next);
 
                 if (req->task != NULL) {
-                        spin_unlock(&rq->lock);
+                        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;
-                        spin_unlock(&rq->lock);
+                        raw_spin_unlock(&rq->lock);
                 } else {
                         req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
-                        spin_unlock(&rq->lock);
+                        raw_spin_unlock(&rq->lock);
                         WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
                 }
                 local_irq_enable();
@@ -7265,37 +7322,10 @@ static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
 static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 {
         int dest_cpu;
-        const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu));
 
 again:
-        /* Look for allowed, online CPU in same node. */
-        for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask)
-                if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
-                        goto move;
-
-        /* Any allowed, online CPU? */
-        dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask);
-        if (dest_cpu < nr_cpu_ids)
-                goto move;
+        dest_cpu = select_fallback_rq(dead_cpu, p);
 
-        /* No more Mr. Nice Guy. */
-        if (dest_cpu >= nr_cpu_ids) {
-                cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
-                dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed);
-
-                /*
-                 * Don't tell them about moving exiting tasks or
-                 * kernel threads (both mm NULL), since they never
-                 * leave kernel.
-                 */
-                if (p->mm && printk_ratelimit()) {
-                        printk(KERN_INFO "process %d (%s) no "
-                               "longer affine to cpu%d\n",
-                               task_pid_nr(p), p->comm, dead_cpu);
-                }
-        }
-
-move:
         /* It can have affinity changed while we were choosing. */
         if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
                 goto again;
@@ -7310,7 +7340,7 @@ move:
  */
 static void migrate_nr_uninterruptible(struct rq *rq_src)
 {
-        struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask));
+        struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
         unsigned long flags;
 
         local_irq_save(flags);
@@ -7358,14 +7388,14 @@ void sched_idle_next(void)
          * Strictly not necessary since rest of the CPUs are stopped by now
          * and interrupts disabled on the current cpu.
          */
-        spin_lock_irqsave(&rq->lock, flags);
+        raw_spin_lock_irqsave(&rq->lock, flags);
 
         __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
 
         update_rq_clock(rq);
         activate_task(rq, p, 0);
 
-        spin_unlock_irqrestore(&rq->lock, flags);
+        raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
 /*
@@ -7401,9 +7431,9 @@ static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
          * that's OK. No task can be added to this CPU, so iteration is
          * fine.
          */
-        spin_unlock_irq(&rq->lock);
+        raw_spin_unlock_irq(&rq->lock);
         move_task_off_dead_cpu(dead_cpu, p);
-        spin_lock_irq(&rq->lock);
+        raw_spin_lock_irq(&rq->lock);
 
         put_task_struct(p);
 }
@@ -7563,7 +7593,7 @@ static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
 static struct ctl_table_header *sd_sysctl_header;
 static void register_sched_domain_sysctl(void)
 {
-        int i, cpu_num = num_online_cpus();
+        int i, cpu_num = num_possible_cpus();
         struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
         char buf[32];
 
@@ -7573,7 +7603,7 @@ static void register_sched_domain_sysctl(void)
         if (entry == NULL)
                 return;
 
-        for_each_online_cpu(i) {
+        for_each_possible_cpu(i) {
                 snprintf(buf, 32, "cpu%d", i);
                 entry->procname = kstrdup(buf, GFP_KERNEL);
                 entry->mode = 0555;
@@ -7669,13 +7699,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
                 /* Update our root-domain */
                 rq = cpu_rq(cpu);
-                spin_lock_irqsave(&rq->lock, flags);
+                raw_spin_lock_irqsave(&rq->lock, flags);
                 if (rq->rd) {
                         BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 
                         set_rq_online(rq);
                 }
-                spin_unlock_irqrestore(&rq->lock, flags);
+                raw_spin_unlock_irqrestore(&rq->lock, flags);
                 break;
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -7700,14 +7730,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 put_task_struct(rq->migration_thread);
                 rq->migration_thread = NULL;
                 /* Idle task back to normal (off runqueue, low prio) */
-                spin_lock_irq(&rq->lock);
+                raw_spin_lock_irq(&rq->lock);
                 update_rq_clock(rq);
                 deactivate_task(rq, rq->idle, 0);
-                rq->idle->static_prio = MAX_PRIO;
                 __setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
                 rq->idle->sched_class = &idle_sched_class;
                 migrate_dead_tasks(cpu);
-                spin_unlock_irq(&rq->lock);
+                raw_spin_unlock_irq(&rq->lock);
                 cpuset_unlock();
                 migrate_nr_uninterruptible(rq);
                 BUG_ON(rq->nr_running != 0);
@@ -7717,30 +7746,30 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                  * they didn't take sched_hotcpu_mutex. Just wake up
                  * the requestors.
                  */
-                spin_lock_irq(&rq->lock);
+                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);
-                        spin_unlock_irq(&rq->lock);
+                        raw_spin_unlock_irq(&rq->lock);
                         complete(&req->done);
-                        spin_lock_irq(&rq->lock);
+                        raw_spin_lock_irq(&rq->lock);
                 }
-                spin_unlock_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);
-                spin_lock_irqsave(&rq->lock, flags);
+                raw_spin_lock_irqsave(&rq->lock, flags);
                 if (rq->rd) {
                         BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
                         set_rq_offline(rq);
                 }
-                spin_unlock_irqrestore(&rq->lock, flags);
+                raw_spin_unlock_irqrestore(&rq->lock, flags);
                 break;
 #endif
         }
@@ -7970,7 +7999,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
         struct root_domain *old_rd = NULL;
         unsigned long flags;
 
-        spin_lock_irqsave(&rq->lock, flags);
+        raw_spin_lock_irqsave(&rq->lock, flags);
 
         if (rq->rd) {
                 old_rd = rq->rd;
@@ -7996,7 +8025,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
         if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
                 set_rq_online(rq);
 
-        spin_unlock_irqrestore(&rq->lock, flags);
+        raw_spin_unlock_irqrestore(&rq->lock, flags);
 
         if (old_rd)
                 free_rootdomain(old_rd);
@@ -8282,14 +8311,14 @@ enum s_alloc {
  */
 #ifdef CONFIG_SCHED_SMT
 static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
+static DEFINE_PER_CPU(struct static_sched_group, sched_groups);
 
 static int
 cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
                  struct sched_group **sg, struct cpumask *unused)
 {
         if (sg)
-                *sg = &per_cpu(sched_group_cpus, cpu).sg;
+                *sg = &per_cpu(sched_groups, cpu).sg;
         return cpu;
 }
 #endif /* CONFIG_SCHED_SMT */
@@ -9099,7 +9128,7 @@ match1:
         if (doms_new == NULL) {
                 ndoms_cur = 0;
                 doms_new = &fallback_doms;
-                cpumask_andnot(doms_new[0], cpu_online_mask, cpu_isolated_map);
+                cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
                 WARN_ON_ONCE(dattr_new);
         }
 
@@ -9230,8 +9259,10 @@ static int update_sched_domains(struct notifier_block *nfb,
         switch (action) {
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
-        case CPU_DEAD:
-        case CPU_DEAD_FROZEN:
+        case CPU_DOWN_PREPARE:
+        case CPU_DOWN_PREPARE_FROZEN:
+        case CPU_DOWN_FAILED:
+        case CPU_DOWN_FAILED_FROZEN:
                 partition_sched_domains(1, NULL, NULL);
                 return NOTIFY_OK;
 
@@ -9278,7 +9309,7 @@ void __init sched_init_smp(void)
 #endif
         get_online_cpus();
         mutex_lock(&sched_domains_mutex);
-        arch_init_sched_domains(cpu_online_mask);
+        arch_init_sched_domains(cpu_active_mask);
         cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
         if (cpumask_empty(non_isolated_cpus))
                 cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
@@ -9351,13 +9382,13 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 #ifdef CONFIG_SMP
         rt_rq->rt_nr_migratory = 0;
         rt_rq->overloaded = 0;
-        plist_head_init(&rt_rq->pushable_tasks, &rq->lock);
+        plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock);
 #endif
 
         rt_rq->rt_time = 0;
         rt_rq->rt_throttled = 0;
         rt_rq->rt_runtime = 0;
-        spin_lock_init(&rt_rq->rt_runtime_lock);
+        raw_spin_lock_init(&rt_rq->rt_runtime_lock);
 
 #ifdef CONFIG_RT_GROUP_SCHED
         rt_rq->rt_nr_boosted = 0;
@@ -9517,7 +9548,7 @@ void __init sched_init(void)
                 struct rq *rq;
 
                 rq = cpu_rq(i);
-                spin_lock_init(&rq->lock);
+                raw_spin_lock_init(&rq->lock);
                 rq->nr_running = 0;
                 rq->calc_load_active = 0;
                 rq->calc_load_update = jiffies + LOAD_FREQ;
@@ -9577,7 +9608,7 @@ void __init sched_init(void)
 #elif defined CONFIG_USER_SCHED
                 init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
                 init_tg_rt_entry(&init_task_group,
-                                &per_cpu(init_rt_rq, i),
+                                &per_cpu(init_rt_rq_var, i),
                                 &per_cpu(init_sched_rt_entity, i), i, 1,
                                 root_task_group.rt_se[i]);
 #endif
@@ -9615,7 +9646,7 @@ void __init sched_init(void)
 #endif
 
 #ifdef CONFIG_RT_MUTEXES
-        plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
+        plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock);
 #endif
 
         /*
@@ -9659,7 +9690,7 @@ void __init sched_init(void)
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
 static inline int preempt_count_equals(int preempt_offset)
 {
-        int nested = preempt_count() & ~PREEMPT_ACTIVE;
+        int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
 
         return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
 }
@@ -9740,13 +9771,13 @@ void normalize_rt_tasks(void)
                         continue;
                 }
 
-                spin_lock(&p->pi_lock);
+                raw_spin_lock(&p->pi_lock);
                 rq = __task_rq_lock(p);
 
                 normalize_task(rq, p);
 
                 __task_rq_unlock(rq);
-                spin_unlock(&p->pi_lock);
+                raw_spin_unlock(&p->pi_lock);
         } while_each_thread(g, p);
 
         read_unlock_irqrestore(&tasklist_lock, flags);
@@ -9842,13 +9873,15 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
                 se = kzalloc_node(sizeof(struct sched_entity),
                                   GFP_KERNEL, cpu_to_node(i));
                 if (!se)
-                        goto err;
+                        goto err_free_rq;
 
                 init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
         }
 
         return 1;
 
+ err_free_rq:
+        kfree(cfs_rq);
  err:
         return 0;
 }
@@ -9930,13 +9963,15 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
                 rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
                                      GFP_KERNEL, cpu_to_node(i));
                 if (!rt_se)
-                        goto err;
+                        goto err_free_rq;
 
                 init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
         }
 
         return 1;
 
+ err_free_rq:
+        kfree(rt_rq);
  err:
         return 0;
 }
@@ -10070,7 +10105,7 @@ void sched_move_task(struct task_struct *tsk)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
         if (tsk->sched_class->moved_group)
-                tsk->sched_class->moved_group(tsk);
+                tsk->sched_class->moved_group(tsk, on_rq);
 #endif
 
         if (unlikely(running))
@@ -10105,9 +10140,9 @@ static void set_se_shares(struct sched_entity *se, unsigned long shares)
         struct rq *rq = cfs_rq->rq;
         unsigned long flags;
 
-        spin_lock_irqsave(&rq->lock, flags);
+        raw_spin_lock_irqsave(&rq->lock, flags);
         __set_se_shares(se, shares);
-        spin_unlock_irqrestore(&rq->lock, flags);
+        raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
 static DEFINE_MUTEX(shares_mutex);
@@ -10292,18 +10327,18 @@ static int tg_set_bandwidth(struct task_group *tg,
         if (err)
                 goto unlock;
 
-        spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+        raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
         tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
         tg->rt_bandwidth.rt_runtime = rt_runtime;
 
         for_each_possible_cpu(i) {
                 struct rt_rq *rt_rq = tg->rt_rq[i];
 
-                spin_lock(&rt_rq->rt_runtime_lock);
+                raw_spin_lock(&rt_rq->rt_runtime_lock);
                 rt_rq->rt_runtime = rt_runtime;
-                spin_unlock(&rt_rq->rt_runtime_lock);
+                raw_spin_unlock(&rt_rq->rt_runtime_lock);
         }
-        spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+        raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
  unlock:
         read_unlock(&tasklist_lock);
         mutex_unlock(&rt_constraints_mutex);
@@ -10408,15 +10443,15 @@ static int sched_rt_global_constraints(void)
         if (sysctl_sched_rt_runtime == 0)
                 return -EBUSY;
 
-        spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
+        raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
         for_each_possible_cpu(i) {
                 struct rt_rq *rt_rq = &cpu_rq(i)->rt;
 
-                spin_lock(&rt_rq->rt_runtime_lock);
+                raw_spin_lock(&rt_rq->rt_runtime_lock);
                 rt_rq->rt_runtime = global_rt_runtime();
-                spin_unlock(&rt_rq->rt_runtime_lock);
+                raw_spin_unlock(&rt_rq->rt_runtime_lock);
         }
-        spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
+        raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 
         return 0;
 }
@@ -10707,9 +10742,9 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
         /*
          * Take rq->lock to make 64-bit read safe on 32-bit platforms.
          */
-        spin_lock_irq(&cpu_rq(cpu)->lock);
+        raw_spin_lock_irq(&cpu_rq(cpu)->lock);
         data = *cpuusage;
-        spin_unlock_irq(&cpu_rq(cpu)->lock);
+        raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
 #else
         data = *cpuusage;
 #endif
@@ -10725,9 +10760,9 @@ static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
         /*
          * Take rq->lock to make 64-bit write safe on 32-bit platforms.
          */
-        spin_lock_irq(&cpu_rq(cpu)->lock);
+        raw_spin_lock_irq(&cpu_rq(cpu)->lock);
         *cpuusage = val;
-        spin_unlock_irq(&cpu_rq(cpu)->lock);
+        raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
 #else
         *cpuusage = val;
 #endif
@@ -10961,9 +10996,9 @@ void synchronize_sched_expedited(void)
                 init_completion(&req->done);
                 req->task = NULL;
                 req->dest_cpu = RCU_MIGRATION_NEED_QS;
-                spin_lock_irqsave(&rq->lock, flags);
+                raw_spin_lock_irqsave(&rq->lock, flags);
                 list_add(&req->list, &rq->migration_queue);
-                spin_unlock_irqrestore(&rq->lock, flags);
+                raw_spin_unlock_irqrestore(&rq->lock, flags);
                 wake_up_process(rq->migration_thread);
         }
         for_each_online_cpu(cpu) {
@@ -10971,11 +11006,11 @@ void synchronize_sched_expedited(void)
                 req = &per_cpu(rcu_migration_req, cpu);
                 rq = cpu_rq(cpu);
                 wait_for_completion(&req->done);
-                spin_lock_irqsave(&rq->lock, flags);
+                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;
-                spin_unlock_irqrestore(&rq->lock, flags);
+                raw_spin_unlock_irqrestore(&rq->lock, flags);
         }
         rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
         synchronize_sched_expedited_count++;