1 files changed, 320 insertions, 199 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 13dd2db9fb2d..558e5f284269 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -55,6 +55,7 @@
 #include <linux/cpuset.h>
 #include <linux/percpu.h>
 #include <linux/kthread.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/sysctl.h>
 #include <linux/syscalls.h>
@@ -71,6 +72,7 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
+#include <trace/sched.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -201,14 +203,19 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
         hrtimer_init(&rt_b->rt_period_timer,
                         CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         rt_b->rt_period_timer.function = sched_rt_period_timer;
-        rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+        rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
+}
+
+static inline int rt_bandwidth_enabled(void)
+{
+        return sysctl_sched_rt_runtime >= 0;
 }
 
 static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
         ktime_t now;
 
-        if (rt_b->rt_runtime == RUNTIME_INF)
+        if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF)
                 return;
 
         if (hrtimer_active(&rt_b->rt_period_timer))
@@ -221,9 +228,8 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 
                 now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
                 hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
-                hrtimer_start(&rt_b->rt_period_timer,
-                              rt_b->rt_period_timer.expires,
-                              HRTIMER_MODE_ABS);
+                hrtimer_start_expires(&rt_b->rt_period_timer,
+                                HRTIMER_MODE_ABS);
         }
         spin_unlock(&rt_b->rt_runtime_lock);
 }
@@ -298,9 +304,9 @@ static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
 static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
 static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
 #endif /* CONFIG_RT_GROUP_SCHED */
-#else /* !CONFIG_FAIR_GROUP_SCHED */
+#else /* !CONFIG_USER_SCHED */
 #define root_task_group init_task_group
-#endif /* CONFIG_FAIR_GROUP_SCHED */
+#endif /* CONFIG_USER_SCHED */
 
 /* task_group_lock serializes add/remove of task groups and also changes to
  * a task group's cpu shares.
@@ -380,7 +386,6 @@ struct cfs_rq {
 
         u64 exec_clock;
         u64 min_vruntime;
-        u64 pair_start;
 
         struct rb_root tasks_timeline;
         struct rb_node *rb_leftmost;
@@ -392,9 +397,9 @@ struct cfs_rq {
          * 'curr' points to currently running entity on this cfs_rq.
          * It is set to NULL otherwise (i.e when none are currently running).
          */
-        struct sched_entity *curr, *next;
+        struct sched_entity *curr, *next, *last;
 
-        unsigned long nr_spread_over;
+        unsigned int nr_spread_over;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
         struct rq *rq;  /* cpu runqueue to which this cfs_rq is attached */
@@ -604,9 +609,9 @@ struct rq {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static inline void check_preempt_curr(struct rq *rq, struct task_struct *p)
+static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync)
 {
-        rq->curr->sched_class->check_preempt_curr(rq, p);
+        rq->curr->sched_class->check_preempt_curr(rq, p, sync);
 }
 
 static inline int cpu_of(struct rq *rq)
@@ -813,6 +818,13 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
 unsigned int sysctl_sched_shares_ratelimit = 250000;
 
 /*
+ * Inject some fuzzyness into changing the per-cpu group shares
+ * this avoids remote rq-locks at the expense of fairness.
+ * default: 4
+ */
+unsigned int sysctl_sched_shares_thresh = 4;
+
+/*
  * period over which we measure -rt task cpu usage in us.
  * default: 1s
  */
@@ -957,6 +969,14 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
         }
 }
 
+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);
+}
+
 static void __task_rq_unlock(struct rq *rq)
         __releases(rq->lock)
 {
@@ -1058,7 +1078,7 @@ static void hrtick_start(struct rq *rq, u64 delay)
         struct hrtimer *timer = &rq->hrtick_timer;
         ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
 
-        timer->expires = time;
+        hrtimer_set_expires(timer, time);
 
         if (rq == this_rq()) {
                 hrtimer_restart(timer);
@@ -1102,7 +1122,7 @@ static void hrtick_start(struct rq *rq, u64 delay)
         hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
 }
 
-static void init_hrtick(void)
+static inline void init_hrtick(void)
 {
 }
 #endif /* CONFIG_SMP */
@@ -1119,9 +1139,9 @@ static void init_rq_hrtick(struct rq *rq)
 
         hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         rq->hrtick_timer.function = hrtick;
-        rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ;
+        rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 }
-#else
+#else   /* CONFIG_SCHED_HRTICK */
 static inline void hrtick_clear(struct rq *rq)
 {
 }
@@ -1133,7 +1153,7 @@ static inline void init_rq_hrtick(struct rq *rq)
 static inline void init_hrtick(void)
 {
 }
-#endif
+#endif  /* CONFIG_SCHED_HRTICK */
 
 /*
  * resched_task - mark a task 'to be rescheduled now'.
@@ -1380,38 +1400,24 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load)
         update_load_sub(&rq->load, load);
 }
 
-#ifdef CONFIG_SMP
-static unsigned long source_load(int cpu, int type);
-static unsigned long target_load(int cpu, int type);
-static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
-
-static unsigned long cpu_avg_load_per_task(int cpu)
-{
-        struct rq *rq = cpu_rq(cpu);
-
-        if (rq->nr_running)
-                rq->avg_load_per_task = rq->load.weight / rq->nr_running;
-
-        return rq->avg_load_per_task;
-}
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-
-typedef void (*tg_visitor)(struct task_group *, int, struct sched_domain *);
+#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED)
+typedef int (*tg_visitor)(struct task_group *, void *);
 
 /*
  * Iterate the full tree, calling @down when first entering a node and @up when
  * leaving it for the final time.
  */
-static void
-walk_tg_tree(tg_visitor down, tg_visitor up, int cpu, struct sched_domain *sd)
+static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
 {
         struct task_group *parent, *child;
+        int ret;
 
         rcu_read_lock();
         parent = &root_task_group;
 down:
-        (*down)(parent, cpu, sd);
+        ret = (*down)(parent, data);
+        if (ret)
+                goto out_unlock;
         list_for_each_entry_rcu(child, &parent->children, siblings) {
                 parent = child;
                 goto down;
@@ -1419,23 +1425,53 @@ down:
 up:
                 continue;
         }
-        (*up)(parent, cpu, sd);
+        ret = (*up)(parent, data);
+        if (ret)
+                goto out_unlock;
 
         child = parent;
         parent = parent->parent;
         if (parent)
                 goto up;
+out_unlock:
         rcu_read_unlock();
+
+        return ret;
 }
 
+static int tg_nop(struct task_group *tg, void *data)
+{
+        return 0;
+}
+#endif
+
+#ifdef CONFIG_SMP
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
+
+static unsigned long cpu_avg_load_per_task(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+
+        if (rq->nr_running)
+                rq->avg_load_per_task = rq->load.weight / rq->nr_running;
+        else
+                rq->avg_load_per_task = 0;
+
+        return rq->avg_load_per_task;
+}
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
 static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 
 /*
  * Calculate and set the cpu's group shares.
  */
 static void
-__update_group_shares_cpu(struct task_group *tg, int cpu,
-                          unsigned long sd_shares, unsigned long sd_rq_weight)
+update_group_shares_cpu(struct task_group *tg, int cpu,
+                        unsigned long sd_shares, unsigned long sd_rq_weight)
 {
         int boost = 0;
         unsigned long shares;
@@ -1466,19 +1502,23 @@ __update_group_shares_cpu(struct task_group *tg, int cpu,
          *
          */
         shares = (sd_shares * rq_weight) / (sd_rq_weight + 1);
+        shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
 
-        /*
-         * record the actual number of shares, not the boosted amount.
-         */
-        tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
-        tg->cfs_rq[cpu]->rq_weight = rq_weight;
+        if (abs(shares - tg->se[cpu]->load.weight) >
+                        sysctl_sched_shares_thresh) {
+                struct rq *rq = cpu_rq(cpu);
+                unsigned long flags;
 
-        if (shares < MIN_SHARES)
-                shares = MIN_SHARES;
-        else if (shares > MAX_SHARES)
-                shares = MAX_SHARES;
+                spin_lock_irqsave(&rq->lock, flags);
+                /*
+                 * record the actual number of shares, not the boosted amount.
+                 */
+                tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
+                tg->cfs_rq[cpu]->rq_weight = rq_weight;
 
-        __set_se_shares(tg->se[cpu], shares);
+                __set_se_shares(tg->se[cpu], shares);
+                spin_unlock_irqrestore(&rq->lock, flags);
+        }
 }
 
 /*
@@ -1486,11 +1526,11 @@ __update_group_shares_cpu(struct task_group *tg, int cpu,
  * This needs to be done in a bottom-up fashion because the rq weight of a
  * parent group depends on the shares of its child groups.
  */
-static void
-tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd)
+static int tg_shares_up(struct task_group *tg, void *data)
 {
         unsigned long rq_weight = 0;
         unsigned long shares = 0;
+        struct sched_domain *sd = data;
         int i;
 
         for_each_cpu_mask(i, sd->span) {
@@ -1507,14 +1547,10 @@ tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd)
         if (!rq_weight)
                 rq_weight = cpus_weight(sd->span) * NICE_0_LOAD;
 
-        for_each_cpu_mask(i, sd->span) {
-                struct rq *rq = cpu_rq(i);
-                unsigned long flags;
+        for_each_cpu_mask(i, sd->span)
+                update_group_shares_cpu(tg, i, shares, rq_weight);
 
-                spin_lock_irqsave(&rq->lock, flags);
-                __update_group_shares_cpu(tg, i, shares, rq_weight);
-                spin_unlock_irqrestore(&rq->lock, flags);
-        }
+        return 0;
 }
 
 /*
@@ -1522,10 +1558,10 @@ tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd)
  * This needs to be done in a top-down fashion because the load of a child
  * group is a fraction of its parents load.
  */
-static void
-tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd)
+static int tg_load_down(struct task_group *tg, void *data)
 {
         unsigned long load;
+        long cpu = (long)data;
 
         if (!tg->parent) {
                 load = cpu_rq(cpu)->load.weight;
@@ -1536,11 +1572,8 @@ tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd)
         }
 
         tg->cfs_rq[cpu]->h_load = load;
-}
 
-static void
-tg_nop(struct task_group *tg, int cpu, struct sched_domain *sd)
-{
+        return 0;
 }
 
 static void update_shares(struct sched_domain *sd)
@@ -1550,7 +1583,7 @@ static void update_shares(struct sched_domain *sd)
 
         if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
                 sd->last_update = now;
-                walk_tg_tree(tg_nop, tg_shares_up, 0, sd);
+                walk_tg_tree(tg_nop, tg_shares_up, sd);
         }
 }
 
@@ -1561,9 +1594,9 @@ static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
         spin_lock(&rq->lock);
 }
 
-static void update_h_load(int cpu)
+static void update_h_load(long cpu)
 {
-        walk_tg_tree(tg_load_down, tg_nop, cpu, NULL);
+        walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 }
 
 #else
@@ -1782,7 +1815,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
         /*
          * Buddy candidates are cache hot:
          */
-        if (sched_feat(CACHE_HOT_BUDDY) && (&p->se == cfs_rq_of(&p->se)->next))
+        if (sched_feat(CACHE_HOT_BUDDY) &&
+                        (&p->se == cfs_rq_of(&p->se)->next ||
+                         &p->se == cfs_rq_of(&p->se)->last))
                 return 1;
 
         if (p->sched_class != &fair_sched_class)
@@ -1918,14 +1953,12 @@ 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);
                 running = task_running(rq, p);
                 on_rq = p->se.on_rq;
                 ncsw = 0;
-                if (!match_state || p->state == match_state) {
-                        ncsw = p->nivcsw + p->nvcsw;
-                        if (unlikely(!ncsw))
-                                ncsw = 1;
-                }
+                if (!match_state || p->state == match_state)
+                        ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
                 task_rq_unlock(rq, &flags);
 
                 /*
@@ -2282,10 +2315,8 @@ out_activate:
         success = 1;
 
 out_running:
-        trace_mark(kernel_sched_wakeup,
-                "pid %d state %ld ## rq %p task %p rq->curr %p",
-                p->pid, p->state, rq, p, rq->curr);
-        check_preempt_curr(rq, p);
+        trace_sched_wakeup(rq, p);
+        check_preempt_curr(rq, p, sync);
 
         p->state = TASK_RUNNING;
 #ifdef CONFIG_SMP
@@ -2417,10 +2448,8 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
                 p->sched_class->task_new(rq, p);
                 inc_nr_running(rq);
         }
-        trace_mark(kernel_sched_wakeup_new,
-                "pid %d state %ld ## rq %p task %p rq->curr %p",
-                p->pid, p->state, rq, p, rq->curr);
-        check_preempt_curr(rq, p);
+        trace_sched_wakeup_new(rq, p);
+        check_preempt_curr(rq, p, 0);
 #ifdef CONFIG_SMP
         if (p->sched_class->task_wake_up)
                 p->sched_class->task_wake_up(rq, p);
@@ -2592,11 +2621,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
         struct mm_struct *mm, *oldmm;
 
         prepare_task_switch(rq, prev, next);
-        trace_mark(kernel_sched_schedule,
-                "prev_pid %d next_pid %d prev_state %ld "
-                "## rq %p prev %p next %p",
-                prev->pid, next->pid, prev->state,
-                rq, prev, next);
+        trace_sched_switch(rq, prev, next);
         mm = next->mm;
         oldmm = prev->active_mm;
         /*
@@ -2836,6 +2861,7 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
             || unlikely(!cpu_active(dest_cpu)))
                 goto out;
 
+        trace_sched_migrate_task(rq, 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). */
@@ -2880,7 +2906,7 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
          * 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);
+        check_preempt_curr(this_rq, p, 0);
 }
 
 /*
@@ -3329,7 +3355,7 @@ small_imbalance:
                 } else
                         this_load_per_task = cpu_avg_load_per_task(this_cpu);
 
-                if (max_load - this_load + 2*busiest_load_per_task >=
+                if (max_load - this_load + busiest_load_per_task >=
                                         busiest_load_per_task * imbn) {
                         *imbalance = busiest_load_per_task;
                         return busiest;
@@ -4037,23 +4063,26 @@ DEFINE_PER_CPU(struct kernel_stat, kstat);
 EXPORT_PER_CPU_SYMBOL(kstat);
 
 /*
- * Return p->sum_exec_runtime plus any more ns on the sched_clock
- * that have not yet been banked in case the task is currently running.
+ * Return any ns on the sched_clock that have not yet been banked in
+ * @p in case that task is currently running.
  */
-unsigned long long task_sched_runtime(struct task_struct *p)
+unsigned long long task_delta_exec(struct task_struct *p)
 {
         unsigned long flags;
-        u64 ns, delta_exec;
         struct rq *rq;
+        u64 ns = 0;
 
         rq = task_rq_lock(p, &flags);
-        ns = p->se.sum_exec_runtime;
+
         if (task_current(rq, p)) {
+                u64 delta_exec;
+
                 update_rq_clock(rq);
                 delta_exec = rq->clock - p->se.exec_start;
                 if ((s64)delta_exec > 0)
-                        ns += delta_exec;
+                        ns = delta_exec;
         }
+
         task_rq_unlock(rq, &flags);
 
         return ns;
@@ -4070,6 +4099,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
         cputime64_t tmp;
 
         p->utime = cputime_add(p->utime, cputime);
+        account_group_user_time(p, cputime);
 
         /* Add user time to cpustat. */
         tmp = cputime_to_cputime64(cputime);
@@ -4094,6 +4124,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime)
         tmp = cputime_to_cputime64(cputime);
 
         p->utime = cputime_add(p->utime, cputime);
+        account_group_user_time(p, cputime);
         p->gtime = cputime_add(p->gtime, cputime);
 
         cpustat->user = cputime64_add(cpustat->user, tmp);
@@ -4129,6 +4160,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
         }
 
         p->stime = cputime_add(p->stime, cputime);
+        account_group_system_time(p, cputime);
 
         /* Add system time to cpustat. */
         tmp = cputime_to_cputime64(cputime);
@@ -4305,7 +4337,7 @@ void __kprobes sub_preempt_count(int val)
         /*
          * Underflow?
          */
-        if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
+       if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
                 return;
         /*
          * Is the spinlock portion underflowing?
@@ -4426,12 +4458,8 @@ need_resched_nonpreemptible:
         if (sched_feat(HRTICK))
                 hrtick_clear(rq);
 
-        /*
-         * Do the rq-clock update outside the rq lock:
-         */
-        local_irq_disable();
+        spin_lock_irq(&rq->lock);
         update_rq_clock(rq);
-        spin_lock(&rq->lock);
         clear_tsk_need_resched(prev);
 
         if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
@@ -4627,6 +4655,15 @@ __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync);      /* For internal use only */
 
+/**
+ * complete: - signals a single thread waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up a single thread waiting on this completion. Threads will be
+ * awakened in the same order in which they were queued.
+ *
+ * See also complete_all(), wait_for_completion() and related routines.
+ */
 void complete(struct completion *x)
 {
         unsigned long flags;
@@ -4638,6 +4675,12 @@ void complete(struct completion *x)
 }
 EXPORT_SYMBOL(complete);
 
+/**
+ * complete_all: - signals all threads waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up all threads waiting on this particular completion event.
+ */
 void complete_all(struct completion *x)
 {
         unsigned long flags;
@@ -4658,10 +4701,7 @@ do_wait_for_common(struct completion *x, long timeout, int state)
                 wait.flags |= WQ_FLAG_EXCLUSIVE;
                 __add_wait_queue_tail(&x->wait, &wait);
                 do {
-                        if ((state == TASK_INTERRUPTIBLE &&
-                             signal_pending(current)) ||
-                            (state == TASK_KILLABLE &&
-                             fatal_signal_pending(current))) {
+                        if (signal_pending_state(state, current)) {
                                 timeout = -ERESTARTSYS;
                                 break;
                         }
@@ -4689,12 +4729,31 @@ wait_for_common(struct completion *x, long timeout, int state)
         return timeout;
 }
 
+/**
+ * wait_for_completion: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout.
+ *
+ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
+ * and interrupt capability. Also see complete().
+ */
 void __sched wait_for_completion(struct completion *x)
 {
         wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(wait_for_completion);
 
+/**
+ * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible.
+ */
 unsigned long __sched
 wait_for_completion_timeout(struct completion *x, unsigned long timeout)
 {
@@ -4702,6 +4761,13 @@ wait_for_completion_timeout(struct completion *x, unsigned long timeout)
 }
 EXPORT_SYMBOL(wait_for_completion_timeout);
 
+/**
+ * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits for completion of a specific task to be signaled. It is
+ * interruptible.
+ */
 int __sched wait_for_completion_interruptible(struct completion *x)
 {
         long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
@@ -4711,6 +4777,14 @@ int __sched wait_for_completion_interruptible(struct completion *x)
 }
 EXPORT_SYMBOL(wait_for_completion_interruptible);
 
+/**
+ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ */
 unsigned long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
                                           unsigned long timeout)
@@ -4719,6 +4793,13 @@ wait_for_completion_interruptible_timeout(struct completion *x,
 }
 EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
 
+/**
+ * wait_for_completion_killable: - waits for completion of a task (killable)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It can be
+ * interrupted by a kill signal.
+ */
 int __sched wait_for_completion_killable(struct completion *x)
 {
         long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
@@ -5121,7 +5202,8 @@ recheck:
                  * Do not allow realtime tasks into groups that have no runtime
                  * assigned.
                  */
-                if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0)
+                if (rt_bandwidth_enabled() && rt_policy(policy) &&
+                                task_group(p)->rt_bandwidth.rt_runtime == 0)
                         return -EPERM;
 #endif
 
@@ -5787,6 +5869,8 @@ 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);
+
         __sched_fork(idle);
         idle->se.exec_start = sched_clock();
 
@@ -5794,7 +5878,6 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
         idle->cpus_allowed = cpumask_of_cpu(cpu);
         __set_task_cpu(idle, cpu);
 
-        spin_lock_irqsave(&rq->lock, flags);
         rq->curr = rq->idle = idle;
 #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
         idle->oncpu = 1;
@@ -5957,7 +6040,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
         set_task_cpu(p, dest_cpu);
         if (on_rq) {
                 activate_task(rq_dest, p, 0);
-                check_preempt_curr(rq_dest, p);
+                check_preempt_curr(rq_dest, p, 0);
         }
 done:
         ret = 1;
@@ -6282,7 +6365,7 @@ set_table_entry(struct ctl_table *entry,
 static struct ctl_table *
 sd_alloc_ctl_domain_table(struct sched_domain *sd)
 {
-        struct ctl_table *table = sd_alloc_ctl_entry(12);
+        struct ctl_table *table = sd_alloc_ctl_entry(13);
 
         if (table == NULL)
                 return NULL;
@@ -6310,7 +6393,9 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
                 sizeof(int), 0644, proc_dointvec_minmax);
         set_table_entry(&table[10], "flags", &sd->flags,
                 sizeof(int), 0644, proc_dointvec_minmax);
-        /* &table[11] is terminator */
+        set_table_entry(&table[11], "name", sd->name,
+                CORENAME_MAX_SIZE, 0444, proc_dostring);
+        /* &table[12] is terminator */
 
         return table;
 }
@@ -6802,15 +6887,17 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
         struct sched_domain *tmp;
 
         /* Remove the sched domains which do not contribute to scheduling. */
-        for (tmp = sd; tmp; tmp = tmp->parent) {
+        for (tmp = sd; tmp; ) {
                 struct sched_domain *parent = tmp->parent;
                 if (!parent)
                         break;
+
                 if (sd_parent_degenerate(tmp, parent)) {
                         tmp->parent = parent->parent;
                         if (parent->parent)
                                 parent->parent->child = tmp;
-                }
+                } else
+                        tmp = tmp->parent;
         }
 
         if (sd && sd_degenerate(sd)) {
@@ -7194,13 +7281,21 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
  * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
  */
 
+#ifdef CONFIG_SCHED_DEBUG
+# define SD_INIT_NAME(sd, type)         sd->name = #type
+#else
+# define SD_INIT_NAME(sd, type)         do { } while (0)
+#endif
+
 #define SD_INIT(sd, type)       sd_init_##type(sd)
+
 #define SD_INIT_FUNC(type)      \
 static noinline void sd_init_##type(struct sched_domain *sd)    \
 {                                                               \
         memset(sd, 0, sizeof(*sd));                             \
         *sd = SD_##type##_INIT;                                 \
         sd->level = SD_LV_##type;                               \
+        SD_INIT_NAME(sd, type);                                 \
 }
 
 SD_INIT_FUNC(CPU)
@@ -7591,6 +7686,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 error:
         free_sched_groups(cpu_map, tmpmask);
         SCHED_CPUMASK_FREE((void *)allmasks);
+        kfree(rd);
         return -ENOMEM;
 #endif
 }
@@ -7692,13 +7788,14 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  *
  * The passed in 'doms_new' should be kmalloc'd. This routine takes
  * ownership of it and will kfree it when done with it. If the caller
- * failed the kmalloc call, then it can pass in doms_new == NULL,
- * and partition_sched_domains() will fallback to the single partition
- * 'fallback_doms', it also forces the domains to be rebuilt.
+ * failed the kmalloc call, then it can pass in doms_new == NULL &&
+ * ndoms_new == 1, and partition_sched_domains() will fallback to
+ * the single partition 'fallback_doms', it also forces the domains
+ * to be rebuilt.
  *
- * If doms_new==NULL it will be replaced with cpu_online_map.
- * ndoms_new==0 is a special case for destroying existing domains.
- * It will not create the default domain.
+ * If doms_new == NULL it will be replaced with cpu_online_map.
+ * ndoms_new == 0 is a special case for destroying existing domains,
+ * and it will not create the default domain.
  *
  * Call with hotplug lock held
  */
@@ -8242,20 +8339,25 @@ void __might_sleep(char *file, int line)
 #ifdef in_atomic
         static unsigned long prev_jiffy;        /* ratelimiting */
 
-        if ((in_atomic() || irqs_disabled()) &&
-            system_state == SYSTEM_RUNNING && !oops_in_progress) {
-                if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
-                        return;
-                prev_jiffy = jiffies;
-                printk(KERN_ERR "BUG: sleeping function called from invalid"
-                                " context at %s:%d\n", file, line);
-                printk("in_atomic():%d, irqs_disabled():%d\n",
-                        in_atomic(), irqs_disabled());
-                debug_show_held_locks(current);
-                if (irqs_disabled())
-                        print_irqtrace_events(current);
-                dump_stack();
-        }
+        if ((!in_atomic() && !irqs_disabled()) ||
+                    system_state != SYSTEM_RUNNING || oops_in_progress)
+                return;
+        if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+                return;
+        prev_jiffy = jiffies;
+
+        printk(KERN_ERR
+                "BUG: sleeping function called from invalid context at %s:%d\n",
+                        file, line);
+        printk(KERN_ERR
+                "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
+                        in_atomic(), irqs_disabled(),
+                        current->pid, current->comm);
+
+        debug_show_held_locks(current);
+        if (irqs_disabled())
+                print_irqtrace_events(current);
+        dump_stack();
 #endif
 }
 EXPORT_SYMBOL(__might_sleep);
@@ -8753,73 +8855,95 @@ static DEFINE_MUTEX(rt_constraints_mutex);
 static unsigned long to_ratio(u64 period, u64 runtime)
 {
         if (runtime == RUNTIME_INF)
-                return 1ULL << 16;
+                return 1ULL << 20;
 
-        return div64_u64(runtime << 16, period);
+        return div64_u64(runtime << 20, period);
 }
 
-#ifdef CONFIG_CGROUP_SCHED
-static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
+/* Must be called with tasklist_lock held */
+static inline int tg_has_rt_tasks(struct task_group *tg)
 {
-        struct task_group *tgi, *parent = tg->parent;
-        unsigned long total = 0;
+        struct task_struct *g, *p;
 
-        if (!parent) {
-                if (global_rt_period() < period)
-                        return 0;
+        do_each_thread(g, p) {
+                if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
+                        return 1;
+        } while_each_thread(g, p);
 
-                return to_ratio(period, runtime) <
-                        to_ratio(global_rt_period(), global_rt_runtime());
-        }
+        return 0;
+}
 
-        if (ktime_to_ns(parent->rt_bandwidth.rt_period) < period)
-                return 0;
+struct rt_schedulable_data {
+        struct task_group *tg;
+        u64 rt_period;
+        u64 rt_runtime;
+};
 
-        rcu_read_lock();
-        list_for_each_entry_rcu(tgi, &parent->children, siblings) {
-                if (tgi == tg)
-                        continue;
+static int tg_schedulable(struct task_group *tg, void *data)
+{
+        struct rt_schedulable_data *d = data;
+        struct task_group *child;
+        unsigned long total, sum = 0;
+        u64 period, runtime;
+
+        period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+        runtime = tg->rt_bandwidth.rt_runtime;
 
-                total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period),
-                                tgi->rt_bandwidth.rt_runtime);
+        if (tg == d->tg) {
+                period = d->rt_period;
+                runtime = d->rt_runtime;
         }
-        rcu_read_unlock();
 
-        return total + to_ratio(period, runtime) <=
-                to_ratio(ktime_to_ns(parent->rt_bandwidth.rt_period),
-                                parent->rt_bandwidth.rt_runtime);
-}
-#elif defined CONFIG_USER_SCHED
-static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
-{
-        struct task_group *tgi;
-        unsigned long total = 0;
-        unsigned long global_ratio =
-                to_ratio(global_rt_period(), global_rt_runtime());
+        /*
+         * Cannot have more runtime than the period.
+         */
+        if (runtime > period && runtime != RUNTIME_INF)
+                return -EINVAL;
 
-        rcu_read_lock();
-        list_for_each_entry_rcu(tgi, &task_groups, list) {
-                if (tgi == tg)
-                        continue;
+        /*
+         * Ensure we don't starve existing RT tasks.
+         */
+        if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+                return -EBUSY;
+
+        total = to_ratio(period, runtime);
 
-                total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period),
-                                tgi->rt_bandwidth.rt_runtime);
+        /*
+         * Nobody can have more than the global setting allows.
+         */
+        if (total > to_ratio(global_rt_period(), global_rt_runtime()))
+                return -EINVAL;
+
+        /*
+         * The sum of our children's runtime should not exceed our own.
+         */
+        list_for_each_entry_rcu(child, &tg->children, siblings) {
+                period = ktime_to_ns(child->rt_bandwidth.rt_period);
+                runtime = child->rt_bandwidth.rt_runtime;
+
+                if (child == d->tg) {
+                        period = d->rt_period;
+                        runtime = d->rt_runtime;
+                }
+
+                sum += to_ratio(period, runtime);
         }
-        rcu_read_unlock();
 
-        return total + to_ratio(period, runtime) < global_ratio;
+        if (sum > total)
+                return -EINVAL;
+
+        return 0;
 }
-#endif
 
-/* Must be called with tasklist_lock held */
-static inline int tg_has_rt_tasks(struct task_group *tg)
+static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 {
-        struct task_struct *g, *p;
-        do_each_thread(g, p) {
-                if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
-                        return 1;
-        } while_each_thread(g, p);
-        return 0;
+        struct rt_schedulable_data data = {
+                .tg = tg,
+                .rt_period = period,
+                .rt_runtime = runtime,
+        };
+
+        return walk_tg_tree(tg_schedulable, tg_nop, &data);
 }
 
 static int tg_set_bandwidth(struct task_group *tg,
@@ -8829,14 +8953,9 @@ static int tg_set_bandwidth(struct task_group *tg,
 
         mutex_lock(&rt_constraints_mutex);
         read_lock(&tasklist_lock);
-        if (rt_runtime == 0 && tg_has_rt_tasks(tg)) {
-                err = -EBUSY;
-                goto unlock;
-        }
-        if (!__rt_schedulable(tg, rt_period, rt_runtime)) {
-                err = -EINVAL;
+        err = __rt_schedulable(tg, rt_period, rt_runtime);
+        if (err)
                 goto unlock;
-        }
 
         spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
         tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
@@ -8905,19 +9024,25 @@ long sched_group_rt_period(struct task_group *tg)
 
 static int sched_rt_global_constraints(void)
 {
-        struct task_group *tg = &root_task_group;
-        u64 rt_runtime, rt_period;
+        u64 runtime, period;
         int ret = 0;
 
         if (sysctl_sched_rt_period <= 0)
                 return -EINVAL;
 
-        rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
-        rt_runtime = tg->rt_bandwidth.rt_runtime;
+        runtime = global_rt_runtime();
+        period = global_rt_period();
+
+        /*
+         * Sanity check on the sysctl variables.
+         */
+        if (runtime > period && runtime != RUNTIME_INF)
+                return -EINVAL;
 
         mutex_lock(&rt_constraints_mutex);
-        if (!__rt_schedulable(tg, rt_period, rt_runtime))
-                ret = -EINVAL;
+        read_lock(&tasklist_lock);
+        ret = __rt_schedulable(NULL, 0, 0);
+        read_unlock(&tasklist_lock);
         mutex_unlock(&rt_constraints_mutex);
 
         return ret;
@@ -8991,7 +9116,6 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
 
         if (!cgrp->parent) {
                 /* This is early initialization for the top cgroup */
-                init_task_group.css.cgroup = cgrp;
                 return &init_task_group.css;
         }
 
@@ -9000,9 +9124,6 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
         if (IS_ERR(tg))
                 return ERR_PTR(-ENOMEM);
 
-        /* Bind the cgroup to task_group object we just created */
-        tg->css.cgroup = cgrp;
-
         return &tg->css;
 }