Merge commit 'v2.6.38-rc2' into core/locking

Reason: Update to mainline before adding the locking cleanup

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 443 insertions, 590 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index aa14a56f9d03..18d38e4ec7ba 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -75,9 +75,11 @@
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
+#include <asm/mutex.h>
 
 #include "sched_cpupri.h"
 #include "workqueue_sched.h"
+#include "sched_autogroup.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
@@ -253,6 +255,8 @@ struct task_group {
         /* runqueue "owned" by this group on each cpu */
         struct cfs_rq **cfs_rq;
         unsigned long shares;
+
+        atomic_t load_weight;
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -268,25 +272,18 @@ struct task_group {
         struct task_group *parent;
         struct list_head siblings;
         struct list_head children;
-};
 
-#define root_task_group init_task_group
+#ifdef CONFIG_SCHED_AUTOGROUP
+        struct autogroup *autogroup;
+#endif
+};
 
-/* task_group_lock serializes add/remove of task groups and also changes to
- * a task group's cpu shares.
- */
+/* task_group_lock serializes the addition/removal of task groups */
 static DEFINE_SPINLOCK(task_group_lock);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-#ifdef CONFIG_SMP
-static int root_task_group_empty(void)
-{
-        return list_empty(&root_task_group.children);
-}
-#endif
-
-# define INIT_TASK_GROUP_LOAD   NICE_0_LOAD
+# define ROOT_TASK_GROUP_LOAD   NICE_0_LOAD
 
 /*
  * A weight of 0 or 1 can cause arithmetics problems.
@@ -299,13 +296,13 @@ static int root_task_group_empty(void)
 #define MIN_SHARES      2
 #define MAX_SHARES      (1UL << 18)
 
-static int init_task_group_load = INIT_TASK_GROUP_LOAD;
+static int root_task_group_load = ROOT_TASK_GROUP_LOAD;
 #endif
 
 /* Default task group.
  *      Every task in system belong to this group at bootup.
  */
-struct task_group init_task_group;
+struct task_group root_task_group;
 
 #endif  /* CONFIG_CGROUP_SCHED */
 
@@ -342,6 +339,7 @@ struct cfs_rq {
          * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
          * list is used during load balance.
          */
+        int on_list;
         struct list_head leaf_cfs_rq_list;
         struct task_group *tg;  /* group that "owns" this runqueue */
 
@@ -360,14 +358,17 @@ struct cfs_rq {
         unsigned long h_load;
 
         /*
-         * this cpu's part of tg->shares
+         * Maintaining per-cpu shares distribution for group scheduling
+         *
+         * load_stamp is the last time we updated the load average
+         * load_last is the last time we updated the load average and saw load
+         * load_unacc_exec_time is currently unaccounted execution time
          */
-        unsigned long shares;
+        u64 load_avg;
+        u64 load_period;
+        u64 load_stamp, load_last, load_unacc_exec_time;
 
-        /*
-         * load.weight at the time we set shares
-         */
-        unsigned long rq_weight;
+        unsigned long load_contribution;
 #endif
 #endif
 };
@@ -552,26 +553,13 @@ struct rq {
         /* try_to_wake_up() stats */
         unsigned int ttwu_count;
         unsigned int ttwu_local;
-
-        /* BKL stats */
-        unsigned int bkl_count;
 #endif
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static inline
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
-{
-        rq->curr->sched_class->check_preempt_curr(rq, p, flags);
 
-        /*
-         * A queue event has occurred, and we're going to schedule.  In
-         * this case, we can save a useless back to back clock update.
-         */
-        if (test_tsk_need_resched(p))
-                rq->skip_clock_update = 1;
-}
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
 static inline int cpu_of(struct rq *rq)
 {
@@ -615,11 +603,17 @@ static inline int cpu_of(struct rq *rq)
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
+        struct task_group *tg;
         struct cgroup_subsys_state *css;
 
+        if (p->flags & PF_EXITING)
+                return &root_task_group;
+
         css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
                         lockdep_is_held(&task_rq(p)->lock));
-        return container_of(css, struct task_group, css);
+        tg = container_of(css, struct task_group, css);
+
+        return autogroup_task_group(p, tg);
 }
 
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
@@ -646,22 +640,18 @@ static inline struct task_group *task_group(struct task_struct *p)
 
 #endif /* CONFIG_CGROUP_SCHED */
 
-static u64 irq_time_cpu(int cpu);
-static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+static void update_rq_clock_task(struct rq *rq, s64 delta);
 
-inline void update_rq_clock(struct rq *rq)
+static void update_rq_clock(struct rq *rq)
 {
-        if (!rq->skip_clock_update) {
-                int cpu = cpu_of(rq);
-                u64 irq_time;
+        s64 delta;
 
-                rq->clock = sched_clock_cpu(cpu);
-                irq_time = irq_time_cpu(cpu);
-                if (rq->clock - irq_time > rq->clock_task)
-                        rq->clock_task = rq->clock - irq_time;
+        if (rq->skip_clock_update)
+                return;
 
-                sched_irq_time_avg_update(rq, irq_time);
-        }
+        delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+        rq->clock += delta;
+        update_rq_clock_task(rq, delta);
 }
 
 /*
@@ -751,7 +741,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
         buf[cnt] = 0;
         cmp = strstrip(buf);
 
-        if (strncmp(buf, "NO_", 3) == 0) {
+        if (strncmp(cmp, "NO_", 3) == 0) {
                 neg = 1;
                 cmp += 3;
         }
@@ -807,20 +797,6 @@ late_initcall(sched_init_debug);
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 
 /*
- * ratelimit for updating the group shares.
- * 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
- * this avoids remote rq-locks at the expense of fairness.
- * default: 4
- */
-unsigned int sysctl_sched_shares_thresh = 4;
-
-/*
  * period over which we average the RT time consumption, measured
  * in ms.
  *
@@ -1369,6 +1345,12 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
         lw->inv_weight = 0;
 }
 
+static inline void update_load_set(struct load_weight *lw, unsigned long w)
+{
+        lw->weight = w;
+        lw->inv_weight = 0;
+}
+
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
  * of tasks with abnormal "nice" values across CPUs the contribution that
@@ -1557,101 +1539,6 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-static __read_mostly unsigned long __percpu *update_shares_data;
-
-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,
-                                    unsigned long *usd_rq_weight)
-{
-        unsigned long shares, rq_weight;
-        int boost = 0;
-
-        rq_weight = usd_rq_weight[cpu];
-        if (!rq_weight) {
-                boost = 1;
-                rq_weight = NICE_0_LOAD;
-        }
-
-        /*
-         *             \Sum_j shares_j * rq_weight_i
-         * shares_i =  -----------------------------
-         *                  \Sum_j rq_weight_j
-         */
-        shares = (sd_shares * rq_weight) / sd_rq_weight;
-        shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
-
-        if (abs(shares - tg->se[cpu]->load.weight) >
-                        sysctl_sched_shares_thresh) {
-                struct rq *rq = cpu_rq(cpu);
-                unsigned long 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);
-                raw_spin_unlock_irqrestore(&rq->lock, flags);
-        }
-}
-
-/*
- * Re-compute the task group their per cpu shares over the given domain.
- * 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 int tg_shares_up(struct task_group *tg, void *data)
-{
-        unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0;
-        unsigned long *usd_rq_weight;
-        struct sched_domain *sd = data;
-        unsigned long flags;
-        int i;
-
-        if (!tg->se[0])
-                return 0;
-
-        local_irq_save(flags);
-        usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
-
-        for_each_cpu(i, sched_domain_span(sd)) {
-                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
-                 * run here it will not get delayed by group starvation.
-                 */
-                if (!weight)
-                        weight = NICE_0_LOAD;
-
-                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;
-
-        if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
-                shares = tg->shares;
-
-        for_each_cpu(i, sched_domain_span(sd))
-                update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
-
-        local_irq_restore(flags);
-
-        return 0;
-}
-
 /*
  * Compute the cpu's hierarchical load factor for each task group.
  * This needs to be done in a top-down fashion because the load of a child
@@ -1666,7 +1553,7 @@ static int tg_load_down(struct task_group *tg, void *data)
                 load = cpu_rq(cpu)->load.weight;
         } else {
                 load = tg->parent->cfs_rq[cpu]->h_load;
-                load *= tg->cfs_rq[cpu]->shares;
+                load *= tg->se[cpu]->load.weight;
                 load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
         }
 
@@ -1675,34 +1562,11 @@ static int tg_load_down(struct task_group *tg, void *data)
         return 0;
 }
 
-static void update_shares(struct sched_domain *sd)
-{
-        s64 elapsed;
-        u64 now;
-
-        if (root_task_group_empty())
-                return;
-
-        now = local_clock();
-        elapsed = now - sd->last_update;
-
-        if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
-                sd->last_update = now;
-                walk_tg_tree(tg_nop, tg_shares_up, sd);
-        }
-}
-
 static void update_h_load(long cpu)
 {
         walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 }
 
-#else
-
-static inline void update_shares(struct sched_domain *sd)
-{
-}
-
 #endif
 
 #ifdef CONFIG_PREEMPT
@@ -1824,15 +1688,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 
 #endif
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
-{
-#ifdef CONFIG_SMP
-        cfs_rq->shares = shares;
-#endif
-}
-#endif
-
 static void calc_load_account_idle(struct rq *this_rq);
 static void update_sysctl(void);
 static int get_update_sysctl_factor(void);
@@ -1934,10 +1789,9 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
  * They are read and saved off onto struct rq in update_rq_clock().
  * This may result in other CPU reading this CPU's irq time and can
  * race with irq/account_system_vtime on this CPU. We would either get old
- * or new value (or semi updated value on 32 bit) with a side effect of
- * accounting a slice of irq time to wrong task when irq is in progress
- * while we read rq->clock. That is a worthy compromise in place of having
- * locks on each irq in account_system_time.
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
  */
 static DEFINE_PER_CPU(u64, cpu_hardirq_time);
 static DEFINE_PER_CPU(u64, cpu_softirq_time);
@@ -1955,19 +1809,58 @@ void disable_sched_clock_irqtime(void)
         sched_clock_irqtime = 0;
 }
 
-static u64 irq_time_cpu(int cpu)
+#ifndef CONFIG_64BIT
+static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
+
+static inline void irq_time_write_begin(void)
 {
-        if (!sched_clock_irqtime)
-                return 0;
+        __this_cpu_inc(irq_time_seq.sequence);
+        smp_wmb();
+}
+
+static inline void irq_time_write_end(void)
+{
+        smp_wmb();
+        __this_cpu_inc(irq_time_seq.sequence);
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+        u64 irq_time;
+        unsigned seq;
+
+        do {
+                seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
+                irq_time = per_cpu(cpu_softirq_time, cpu) +
+                           per_cpu(cpu_hardirq_time, cpu);
+        } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
 
+        return irq_time;
+}
+#else /* CONFIG_64BIT */
+static inline void irq_time_write_begin(void)
+{
+}
+
+static inline void irq_time_write_end(void)
+{
+}
+
+static inline u64 irq_time_read(int cpu)
+{
         return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
 }
+#endif /* CONFIG_64BIT */
 
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
 void account_system_vtime(struct task_struct *curr)
 {
         unsigned long flags;
+        s64 delta;
         int cpu;
-        u64 now, delta;
 
         if (!sched_clock_irqtime)
                 return;
@@ -1975,9 +1868,10 @@ void account_system_vtime(struct task_struct *curr)
         local_irq_save(flags);
 
         cpu = smp_processor_id();
-        now = sched_clock_cpu(cpu);
-        delta = now - per_cpu(irq_start_time, cpu);
-        per_cpu(irq_start_time, cpu) = now;
+        delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+        __this_cpu_add(irq_start_time, delta);
+
+        irq_time_write_begin();
         /*
          * We do not account for softirq time from ksoftirqd here.
          * We want to continue accounting softirq time to ksoftirqd thread
@@ -1985,37 +1879,60 @@ void account_system_vtime(struct task_struct *curr)
          * that do not consume any time, but still wants to run.
          */
         if (hardirq_count())
-                per_cpu(cpu_hardirq_time, cpu) += delta;
+                __this_cpu_add(cpu_hardirq_time, delta);
         else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
-                per_cpu(cpu_softirq_time, cpu) += delta;
+                __this_cpu_add(cpu_softirq_time, delta);
 
+        irq_time_write_end();
         local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
-        if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
-                u64 delta_irq = curr_irq_time - rq->prev_irq_time;
-                rq->prev_irq_time = curr_irq_time;
-                sched_rt_avg_update(rq, delta_irq);
-        }
+        s64 irq_delta;
+
+        irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+        /*
+         * Since irq_time is only updated on {soft,}irq_exit, we might run into
+         * this case when a previous update_rq_clock() happened inside a
+         * {soft,}irq region.
+         *
+         * When this happens, we stop ->clock_task and only update the
+         * prev_irq_time stamp to account for the part that fit, so that a next
+         * update will consume the rest. This ensures ->clock_task is
+         * monotonic.
+         *
+         * It does however cause some slight miss-attribution of {soft,}irq
+         * time, a more accurate solution would be to update the irq_time using
+         * the current rq->clock timestamp, except that would require using
+         * atomic ops.
+         */
+        if (irq_delta > delta)
+                irq_delta = delta;
+
+        rq->prev_irq_time += irq_delta;
+        delta -= irq_delta;
+        rq->clock_task += delta;
+
+        if (irq_delta && sched_feat(NONIRQ_POWER))
+                sched_rt_avg_update(rq, irq_delta);
 }
 
-#else
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
 
-static u64 irq_time_cpu(int cpu)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
-        return 0;
+        rq->clock_task += delta;
 }
 
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
-
-#endif
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
+#include "sched_autogroup.c"
 #include "sched_stoptask.c"
 #ifdef CONFIG_SCHED_DEBUG
 # include "sched_debug.c"
@@ -2118,6 +2035,31 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
                 p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+{
+        const struct sched_class *class;
+
+        if (p->sched_class == rq->curr->sched_class) {
+                rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+        } else {
+                for_each_class(class) {
+                        if (class == rq->curr->sched_class)
+                                break;
+                        if (class == p->sched_class) {
+                                resched_task(rq->curr);
+                                break;
+                        }
+                }
+        }
+
+        /*
+         * A queue event has occurred, and we're going to schedule.  In
+         * this case, we can save a useless back to back clock update.
+         */
+        if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
+                rq->skip_clock_update = 1;
+}
+
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
@@ -2183,10 +2125,8 @@ static int migration_cpu_stop(void *data);
  * The task's runqueue lock must be held.
  * Returns true if you have to wait for migration thread.
  */
-static bool migrate_task(struct task_struct *p, int dest_cpu)
+static bool migrate_task(struct task_struct *p, struct rq *rq)
 {
-        struct rq *rq = task_rq(p);
-
         /*
          * If the task is not on a runqueue (and not running), then
          * the next wake-up will properly place the task.
@@ -2366,18 +2306,15 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
                 return dest_cpu;
 
         /* No more Mr. Nice Guy. */
-        if (unlikely(dest_cpu >= nr_cpu_ids)) {
-                dest_cpu = cpuset_cpus_allowed_fallback(p);
-                /*
-                 * Don't tell them about moving exiting tasks or
-                 * kernel threads (both mm NULL), since they never
-                 * 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);
-                }
+        dest_cpu = cpuset_cpus_allowed_fallback(p);
+        /*
+         * 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;
@@ -2568,7 +2505,7 @@ out:
  * try_to_wake_up_local - try to wake up a local task with rq lock held
  * @p: the thread to be awakened
  *
- * Put @p on the run-queue if it's not alredy there.  The caller must
+ * Put @p on the run-queue if it's not already there.  The caller must
  * ensure that this_rq() is locked, @p is bound to this_rq() and not
  * the current task.  this_rq() stays locked over invocation.
  */
@@ -2713,7 +2650,9 @@ void sched_fork(struct task_struct *p, int clone_flags)
         /* Want to start with kernel preemption disabled. */
         task_thread_info(p)->preempt_count = 1;
 #endif
+#ifdef CONFIG_SMP
         plist_node_init(&p->pushable_tasks, MAX_PRIO);
+#endif
 
         put_cpu();
 }
@@ -3104,6 +3043,15 @@ static long calc_load_fold_active(struct rq *this_rq)
         return delta;
 }
 
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+        load *= exp;
+        load += active * (FIXED_1 - exp);
+        load += 1UL << (FSHIFT - 1);
+        return load >> FSHIFT;
+}
+
 #ifdef CONFIG_NO_HZ
 /*
  * For NO_HZ we delay the active fold to the next LOAD_FREQ update.
@@ -3133,6 +3081,128 @@ static long calc_load_fold_idle(void)
 
         return delta;
 }
+
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x:         base of the power
+ * @frac_bits: fractional bits of @x
+ * @n:         power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
+ */
+static unsigned long
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
+{
+        unsigned long result = 1UL << frac_bits;
+
+        if (n) for (;;) {
+                if (n & 1) {
+                        result *= x;
+                        result += 1UL << (frac_bits - 1);
+                        result >>= frac_bits;
+                }
+                n >>= 1;
+                if (!n)
+                        break;
+                x *= x;
+                x += 1UL << (frac_bits - 1);
+                x >>= frac_bits;
+        }
+
+        return result;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ *    = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ *    = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ *    = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ *    = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ *  ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ *    = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ *    = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ *              n         1 - x^(n+1)
+ *     S_n := \Sum x^i = -------------
+ *             i=0          1 - x
+ */
+static unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+            unsigned long active, unsigned int n)
+{
+
+        return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
+}
+
+/*
+ * NO_HZ can leave us missing all per-cpu ticks calling
+ * calc_load_account_active(), but since an idle CPU folds its delta into
+ * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
+ * in the pending idle delta if our idle period crossed a load cycle boundary.
+ *
+ * Once we've updated the global active value, we need to apply the exponential
+ * weights adjusted to the number of cycles missed.
+ */
+static void calc_global_nohz(unsigned long ticks)
+{
+        long delta, active, n;
+
+        if (time_before(jiffies, calc_load_update))
+                return;
+
+        /*
+         * If we crossed a calc_load_update boundary, make sure to fold
+         * any pending idle changes, the respective CPUs might have
+         * missed the tick driven calc_load_account_active() update
+         * due to NO_HZ.
+         */
+        delta = calc_load_fold_idle();
+        if (delta)
+                atomic_long_add(delta, &calc_load_tasks);
+
+        /*
+         * If we were idle for multiple load cycles, apply them.
+         */
+        if (ticks >= LOAD_FREQ) {
+                n = ticks / LOAD_FREQ;
+
+                active = atomic_long_read(&calc_load_tasks);
+                active = active > 0 ? active * FIXED_1 : 0;
+
+                avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+                avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+                avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+
+                calc_load_update += n * LOAD_FREQ;
+        }
+
+        /*
+         * Its possible the remainder of the above division also crosses
+         * a LOAD_FREQ period, the regular check in calc_global_load()
+         * which comes after this will take care of that.
+         *
+         * Consider us being 11 ticks before a cycle completion, and us
+         * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
+         * age us 4 cycles, and the test in calc_global_load() will
+         * pick up the final one.
+         */
+}
 #else
 static void calc_load_account_idle(struct rq *this_rq)
 {
@@ -3142,6 +3212,10 @@ static inline long calc_load_fold_idle(void)
 {
         return 0;
 }
+
+static void calc_global_nohz(unsigned long ticks)
+{
+}
 #endif
 
 /**
@@ -3159,24 +3233,17 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
         loads[2] = (avenrun[2] + offset) << shift;
 }
 
-static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
-{
-        load *= exp;
-        load += active * (FIXED_1 - exp);
-        return load >> FSHIFT;
-}
-
 /*
  * calc_load - update the avenrun load estimates 10 ticks after the
  * CPUs have updated calc_load_tasks.
  */
-void calc_global_load(void)
+void calc_global_load(unsigned long ticks)
 {
-        unsigned long upd = calc_load_update + 10;
         long active;
 
-        if (time_before(jiffies, upd))
+        calc_global_nohz(ticks);
+
+        if (time_before(jiffies, calc_load_update + 10))
                 return;
 
         active = atomic_long_read(&calc_load_tasks);
@@ -3349,7 +3416,7 @@ void sched_exec(void)
          * select_task_rq() can race against ->cpus_allowed
          */
         if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
-            likely(cpu_active(dest_cpu)) && migrate_task(p, dest_cpu)) {
+            likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) {
                 struct migration_arg arg = { p, dest_cpu };
 
                 task_rq_unlock(rq, &flags);
@@ -3820,7 +3887,7 @@ static inline void schedule_debug(struct task_struct *prev)
         schedstat_inc(this_rq(), sched_count);
 #ifdef CONFIG_SCHEDSTATS
         if (unlikely(prev->lock_depth >= 0)) {
-                schedstat_inc(this_rq(), bkl_count);
+                schedstat_inc(this_rq(), rq_sched_info.bkl_count);
                 schedstat_inc(prev, sched_info.bkl_count);
         }
 #endif
@@ -3830,7 +3897,6 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
         if (prev->se.on_rq)
                 update_rq_clock(rq);
-        rq->skip_clock_update = 0;
         prev->sched_class->put_prev_task(rq, prev);
 }
 
@@ -3888,7 +3954,6 @@ need_resched_nonpreemptible:
                 hrtick_clear(rq);
 
         raw_spin_lock_irq(&rq->lock);
-        clear_tsk_need_resched(prev);
 
         switch_count = &prev->nivcsw;
         if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
@@ -3920,6 +3985,8 @@ need_resched_nonpreemptible:
 
         put_prev_task(rq, prev);
         next = pick_next_task(rq);
+        clear_tsk_need_resched(prev);
+        rq->skip_clock_update = 0;
 
         if (likely(prev != next)) {
                 sched_info_switch(prev, next);
@@ -4014,7 +4081,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
                 if (task_thread_info(rq->curr) != owner || need_resched())
                         return 0;
 
-                cpu_relax();
+                arch_mutex_cpu_relax();
         }
 
         return 1;
@@ -4326,7 +4393,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible);
  * 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
+long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
                                           unsigned long timeout)
 {
@@ -4359,7 +4426,7 @@ EXPORT_SYMBOL(wait_for_completion_killable);
  * signaled or for a specified timeout to expire. It can be
  * interrupted by a kill signal. The timeout is in jiffies.
  */
-unsigned long __sched
+long __sched
 wait_for_completion_killable_timeout(struct completion *x,
                                      unsigned long timeout)
 {
@@ -4701,7 +4768,7 @@ static bool check_same_owner(struct task_struct *p)
 }
 
 static int __sched_setscheduler(struct task_struct *p, int policy,
-                                struct sched_param *param, bool user)
+                                const struct sched_param *param, bool user)
 {
         int retval, oldprio, oldpolicy = -1, on_rq, running;
         unsigned long flags;
@@ -4804,7 +4871,8 @@ recheck:
                  * assigned.
                  */
                 if (rt_bandwidth_enabled() && rt_policy(policy) &&
-                                task_group(p)->rt_bandwidth.rt_runtime == 0) {
+                                task_group(p)->rt_bandwidth.rt_runtime == 0 &&
+                                !task_group_is_autogroup(task_group(p))) {
                         __task_rq_unlock(rq);
                         raw_spin_unlock_irqrestore(&p->pi_lock, flags);
                         return -EPERM;
@@ -4856,7 +4924,7 @@ recheck:
  * NOTE that the task may be already dead.
  */
 int sched_setscheduler(struct task_struct *p, int policy,
-                       struct sched_param *param)
+                       const struct sched_param *param)
 {
         return __sched_setscheduler(p, policy, param, true);
 }
@@ -4874,7 +4942,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
  * but our caller might not have that capability.
  */
 int sched_setscheduler_nocheck(struct task_struct *p, int policy,
-                               struct sched_param *param)
+                               const struct sched_param *param)
 {
         return __sched_setscheduler(p, policy, param, false);
 }
@@ -5390,7 +5458,7 @@ void sched_show_task(struct task_struct *p)
         unsigned state;
 
         state = p->state ? __ffs(p->state) + 1 : 0;
-        printk(KERN_INFO "%-13.13s %c", p->comm,
+        printk(KERN_INFO "%-15.15s %c", p->comm,
                 state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
 #if BITS_PER_LONG == 32
         if (state == TASK_RUNNING)
@@ -5554,7 +5622,6 @@ static void update_sysctl(void)
         SET_SYSCTL(sched_min_granularity);
         SET_SYSCTL(sched_latency);
         SET_SYSCTL(sched_wakeup_granularity);
-        SET_SYSCTL(sched_shares_ratelimit);
 #undef SET_SYSCTL
 }
 
@@ -5630,7 +5697,7 @@ again:
                 goto out;
 
         dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
-        if (migrate_task(p, dest_cpu)) {
+        if (migrate_task(p, rq)) {
                 struct migration_arg arg = { p, dest_cpu };
                 /* Need help from migration thread: drop lock and wait. */
                 task_rq_unlock(rq, &flags);
@@ -5712,29 +5779,20 @@ static int migration_cpu_stop(void *data)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+
 /*
- * Figure out where task on dead CPU should go, use force if necessary.
+ * Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
  */
-void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
+void idle_task_exit(void)
 {
-        struct rq *rq = cpu_rq(dead_cpu);
-        int needs_cpu, uninitialized_var(dest_cpu);
-        unsigned long flags;
+        struct mm_struct *mm = current->active_mm;
 
-        local_irq_save(flags);
+        BUG_ON(cpu_online(smp_processor_id()));
 
-        raw_spin_lock(&rq->lock);
-        needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING);
-        if (needs_cpu)
-                dest_cpu = select_fallback_rq(dead_cpu, p);
-        raw_spin_unlock(&rq->lock);
-        /*
-         * It can only fail if we race with set_cpus_allowed(),
-         * in the racer should migrate the task anyway.
-         */
-        if (needs_cpu)
-                __migrate_task(p, dead_cpu, dest_cpu);
-        local_irq_restore(flags);
+        if (mm != &init_mm)
+                switch_mm(mm, &init_mm, current);
+        mmdrop(mm);
 }
 
 /*
@@ -5747,128 +5805,69 @@ void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 static void migrate_nr_uninterruptible(struct rq *rq_src)
 {
         struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
-        unsigned long flags;
 
-        local_irq_save(flags);
-        double_rq_lock(rq_src, rq_dest);
         rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
         rq_src->nr_uninterruptible = 0;
-        double_rq_unlock(rq_src, rq_dest);
-        local_irq_restore(flags);
-}
-
-/* Run through task list and migrate tasks from the dead cpu. */
-static void migrate_live_tasks(int src_cpu)
-{
-        struct task_struct *p, *t;
-
-        read_lock(&tasklist_lock);
-
-        do_each_thread(t, p) {
-                if (p == current)
-                        continue;
-
-                if (task_cpu(p) == src_cpu)
-                        move_task_off_dead_cpu(src_cpu, p);
-        } while_each_thread(t, p);
-
-        read_unlock(&tasklist_lock);
 }
 
 /*
- * Schedules idle task to be the next runnable task on current CPU.
- * It does so by boosting its priority to highest possible.
- * Used by CPU offline code.
+ * remove the tasks which were accounted by rq from calc_load_tasks.
  */
-void sched_idle_next(void)
+static void calc_global_load_remove(struct rq *rq)
 {
-        int this_cpu = smp_processor_id();
-        struct rq *rq = cpu_rq(this_cpu);
-        struct task_struct *p = rq->idle;
-        unsigned long flags;
-
-        /* cpu has to be offline */
-        BUG_ON(cpu_online(this_cpu));
-
-        /*
-         * Strictly not necessary since rest of the CPUs are stopped by now
-         * and interrupts disabled on the current cpu.
-         */
-        raw_spin_lock_irqsave(&rq->lock, flags);
-
-        __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
-
-        activate_task(rq, p, 0);
-
-        raw_spin_unlock_irqrestore(&rq->lock, flags);
+        atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+        rq->calc_load_active = 0;
 }
 
 /*
- * Ensures that the idle task is using init_mm right before its cpu goes
- * offline.
+ * Migrate all tasks from the rq, sleeping tasks will be migrated by
+ * try_to_wake_up()->select_task_rq().
+ *
+ * Called with rq->lock held even though we'er in stop_machine() and
+ * there's no concurrency possible, we hold the required locks anyway
+ * because of lock validation efforts.
  */
-void idle_task_exit(void)
-{
-        struct mm_struct *mm = current->active_mm;
-
-        BUG_ON(cpu_online(smp_processor_id()));
-
-        if (mm != &init_mm)
-                switch_mm(mm, &init_mm, current);
-        mmdrop(mm);
-}
-
-/* called under rq->lock with disabled interrupts */
-static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
+static void migrate_tasks(unsigned int dead_cpu)
 {
         struct rq *rq = cpu_rq(dead_cpu);
-
-        /* Must be exiting, otherwise would be on tasklist. */
-        BUG_ON(!p->exit_state);
-
-        /* Cannot have done final schedule yet: would have vanished. */
-        BUG_ON(p->state == TASK_DEAD);
-
-        get_task_struct(p);
+        struct task_struct *next, *stop = rq->stop;
+        int dest_cpu;
 
         /*
-         * Drop lock around migration; if someone else moves it,
-         * that's OK. No task can be added to this CPU, so iteration is
-         * fine.
+         * Fudge the rq selection such that the below task selection loop
+         * doesn't get stuck on the currently eligible stop task.
+         *
+         * We're currently inside stop_machine() and the rq is either stuck
+         * in the stop_machine_cpu_stop() loop, or we're executing this code,
+         * either way we should never end up calling schedule() until we're
+         * done here.
          */
-        raw_spin_unlock_irq(&rq->lock);
-        move_task_off_dead_cpu(dead_cpu, p);
-        raw_spin_lock_irq(&rq->lock);
-
-        put_task_struct(p);
-}
-
-/* release_task() removes task from tasklist, so we won't find dead tasks. */
-static void migrate_dead_tasks(unsigned int dead_cpu)
-{
-        struct rq *rq = cpu_rq(dead_cpu);
-        struct task_struct *next;
+        rq->stop = NULL;
 
         for ( ; ; ) {
-                if (!rq->nr_running)
+                /*
+                 * There's this thread running, bail when that's the only
+                 * remaining thread.
+                 */
+                if (rq->nr_running == 1)
                         break;
+
                 next = pick_next_task(rq);
-                if (!next)
-                        break;
+                BUG_ON(!next);
                 next->sched_class->put_prev_task(rq, next);
-                migrate_dead(dead_cpu, next);
 
+                /* Find suitable destination for @next, with force if needed. */
+                dest_cpu = select_fallback_rq(dead_cpu, next);
+                raw_spin_unlock(&rq->lock);
+
+                __migrate_task(next, dead_cpu, dest_cpu);
+
+                raw_spin_lock(&rq->lock);
         }
-}
 
-/*
- * remove the tasks which were accounted by rq from calc_load_tasks.
- */
-static void calc_global_load_remove(struct rq *rq)
-{
-        atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
-        rq->calc_load_active = 0;
+        rq->stop = stop;
 }
+
 #endif /* CONFIG_HOTPLUG_CPU */
 
 #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
@@ -6078,15 +6077,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
         unsigned long flags;
         struct rq *rq = cpu_rq(cpu);
 
-        switch (action) {
+        switch (action & ~CPU_TASKS_FROZEN) {
 
         case CPU_UP_PREPARE:
-        case CPU_UP_PREPARE_FROZEN:
                 rq->calc_load_update = calc_load_update;
                 break;
 
         case CPU_ONLINE:
-        case CPU_ONLINE_FROZEN:
                 /* Update our root-domain */
                 raw_spin_lock_irqsave(&rq->lock, flags);
                 if (rq->rd) {
@@ -6098,30 +6095,19 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 break;
 
 #ifdef CONFIG_HOTPLUG_CPU
-        case CPU_DEAD:
-        case CPU_DEAD_FROZEN:
-                migrate_live_tasks(cpu);
-                /* Idle task back to normal (off runqueue, low prio) */
-                raw_spin_lock_irq(&rq->lock);
-                deactivate_task(rq, rq->idle, 0);
-                __setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
-                rq->idle->sched_class = &idle_sched_class;
-                migrate_dead_tasks(cpu);
-                raw_spin_unlock_irq(&rq->lock);
-                migrate_nr_uninterruptible(rq);
-                BUG_ON(rq->nr_running != 0);
-                calc_global_load_remove(rq);
-                break;
-
         case CPU_DYING:
-        case CPU_DYING_FROZEN:
                 /* Update our root-domain */
                 raw_spin_lock_irqsave(&rq->lock, flags);
                 if (rq->rd) {
                         BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
                         set_rq_offline(rq);
                 }
+                migrate_tasks(cpu);
+                BUG_ON(rq->nr_running != 1); /* the migration thread */
                 raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+                migrate_nr_uninterruptible(rq);
+                calc_global_load_remove(rq);
                 break;
 #endif
         }
@@ -6960,6 +6946,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
         if (cpu != group_first_cpu(sd->groups))
                 return;
 
+        sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
+
         child = sd->child;
 
         sd->groups->cpu_power = 0;
@@ -7850,18 +7838,16 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
-                                struct sched_entity *se, int cpu, int add,
+                                struct sched_entity *se, int cpu,
                                 struct sched_entity *parent)
 {
         struct rq *rq = cpu_rq(cpu);
         tg->cfs_rq[cpu] = cfs_rq;
         init_cfs_rq(cfs_rq, rq);
         cfs_rq->tg = tg;
-        if (add)
-                list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
 
         tg->se[cpu] = se;
-        /* se could be NULL for init_task_group */
+        /* se could be NULL for root_task_group */
         if (!se)
                 return;
 
@@ -7871,15 +7857,14 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
                 se->cfs_rq = parent->my_q;
 
         se->my_q = cfs_rq;
-        se->load.weight = tg->shares;
-        se->load.inv_weight = 0;
+        update_load_set(&se->load, 0);
         se->parent = parent;
 }
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
-                struct sched_rt_entity *rt_se, int cpu, int add,
+                struct sched_rt_entity *rt_se, int cpu,
                 struct sched_rt_entity *parent)
 {
         struct rq *rq = cpu_rq(cpu);
@@ -7888,8 +7873,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
         init_rt_rq(rt_rq, rq);
         rt_rq->tg = tg;
         rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
-        if (add)
-                list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);
 
         tg->rt_se[cpu] = rt_se;
         if (!rt_se)
@@ -7924,18 +7907,18 @@ void __init sched_init(void)
                 ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-                init_task_group.se = (struct sched_entity **)ptr;
+                root_task_group.se = (struct sched_entity **)ptr;
                 ptr += nr_cpu_ids * sizeof(void **);
 
-                init_task_group.cfs_rq = (struct cfs_rq **)ptr;
+                root_task_group.cfs_rq = (struct cfs_rq **)ptr;
                 ptr += nr_cpu_ids * sizeof(void **);
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
-                init_task_group.rt_se = (struct sched_rt_entity **)ptr;
+                root_task_group.rt_se = (struct sched_rt_entity **)ptr;
                 ptr += nr_cpu_ids * sizeof(void **);
 
-                init_task_group.rt_rq = (struct rt_rq **)ptr;
+                root_task_group.rt_rq = (struct rt_rq **)ptr;
                 ptr += nr_cpu_ids * sizeof(void **);
 
 #endif /* CONFIG_RT_GROUP_SCHED */
@@ -7955,20 +7938,16 @@ void __init sched_init(void)
                         global_rt_period(), global_rt_runtime());
 
 #ifdef CONFIG_RT_GROUP_SCHED
-        init_rt_bandwidth(&init_task_group.rt_bandwidth,
+        init_rt_bandwidth(&root_task_group.rt_bandwidth,
                         global_rt_period(), global_rt_runtime());
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_CGROUP_SCHED
-        list_add(&init_task_group.list, &task_groups);
-        INIT_LIST_HEAD(&init_task_group.children);
-
+        list_add(&root_task_group.list, &task_groups);
+        INIT_LIST_HEAD(&root_task_group.children);
+        autogroup_init(&init_task);
 #endif /* CONFIG_CGROUP_SCHED */
 
-#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
-        update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
-                                            __alignof__(unsigned long));
-#endif
         for_each_possible_cpu(i) {
                 struct rq *rq;
 
@@ -7980,38 +7959,34 @@ void __init sched_init(void)
                 init_cfs_rq(&rq->cfs, rq);
                 init_rt_rq(&rq->rt, rq);
 #ifdef CONFIG_FAIR_GROUP_SCHED
-                init_task_group.shares = init_task_group_load;
+                root_task_group.shares = root_task_group_load;
                 INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
-#ifdef CONFIG_CGROUP_SCHED
                 /*
-                 * How much cpu bandwidth does init_task_group get?
+                 * How much cpu bandwidth does root_task_group get?
                  *
                  * In case of task-groups formed thr' the cgroup filesystem, it
                  * gets 100% of the cpu resources in the system. This overall
                  * system cpu resource is divided among the tasks of
-                 * init_task_group and its child task-groups in a fair manner,
+                 * root_task_group and its child task-groups in a fair manner,
                  * based on each entity's (task or task-group's) weight
                  * (se->load.weight).
                  *
-                 * In other words, if init_task_group has 10 tasks of weight
+                 * In other words, if root_task_group has 10 tasks of weight
                  * 1024) and two child groups A0 and A1 (of weight 1024 each),
                  * then A0's share of the cpu resource is:
                  *
                  *      A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
                  *
-                 * We achieve this by letting init_task_group's tasks sit
-                 * directly in rq->cfs (i.e init_task_group->se[] = NULL).
+                 * We achieve this by letting root_task_group's tasks sit
+                 * directly in rq->cfs (i.e root_task_group->se[] = NULL).
                  */
-                init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL);
-#endif
+                init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
                 rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
 #ifdef CONFIG_RT_GROUP_SCHED
                 INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
-#ifdef CONFIG_CGROUP_SCHED
-                init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL);
-#endif
+                init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
 #endif
 
                 for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
@@ -8091,8 +8066,6 @@ void __init sched_init(void)
                 zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 #endif /* SMP */
 
-        perf_event_init();
-
         scheduler_running = 1;
 }
 
@@ -8286,7 +8259,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
                 if (!se)
                         goto err_free_rq;
 
-                init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
+                init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
         }
 
         return 1;
@@ -8297,15 +8270,21 @@ err:
         return 0;
 }
 
-static inline void register_fair_sched_group(struct task_group *tg, int cpu)
-{
-        list_add_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list,
-                        &cpu_rq(cpu)->leaf_cfs_rq_list);
-}
-
 static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
 {
-        list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list);
+        struct rq *rq = cpu_rq(cpu);
+        unsigned long flags;
+
+        /*
+        * Only empty task groups can be destroyed; so we can speculatively
+        * check on_list without danger of it being re-added.
+        */
+        if (!tg->cfs_rq[cpu]->on_list)
+                return;
+
+        raw_spin_lock_irqsave(&rq->lock, flags);
+        list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
+        raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 #else /* !CONFG_FAIR_GROUP_SCHED */
 static inline void free_fair_sched_group(struct task_group *tg)
@@ -8318,10 +8297,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
         return 1;
 }
 
-static inline void register_fair_sched_group(struct task_group *tg, int cpu)
-{
-}
-
 static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
 {
 }
@@ -8376,7 +8351,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
                 if (!rt_se)
                         goto err_free_rq;
 
-                init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
+                init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
         }
 
         return 1;
@@ -8386,17 +8361,6 @@ err_free_rq:
 err:
         return 0;
 }
-
-static inline void register_rt_sched_group(struct task_group *tg, int cpu)
-{
-        list_add_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list,
-                        &cpu_rq(cpu)->leaf_rt_rq_list);
-}
-
-static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
-{
-        list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list);
-}
 #else /* !CONFIG_RT_GROUP_SCHED */
 static inline void free_rt_sched_group(struct task_group *tg)
 {
@@ -8407,14 +8371,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 {
         return 1;
 }
-
-static inline void register_rt_sched_group(struct task_group *tg, int cpu)
-{
-}
-
-static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
-{
-}
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_CGROUP_SCHED
@@ -8422,6 +8378,7 @@ static void free_sched_group(struct task_group *tg)
 {
         free_fair_sched_group(tg);
         free_rt_sched_group(tg);
+        autogroup_free(tg);
         kfree(tg);
 }
 
@@ -8430,7 +8387,6 @@ struct task_group *sched_create_group(struct task_group *parent)
 {
         struct task_group *tg;
         unsigned long flags;
-        int i;
 
         tg = kzalloc(sizeof(*tg), GFP_KERNEL);
         if (!tg)
@@ -8443,10 +8399,6 @@ struct task_group *sched_create_group(struct task_group *parent)
                 goto err;
 
         spin_lock_irqsave(&task_group_lock, flags);
-        for_each_possible_cpu(i) {
-                register_fair_sched_group(tg, i);
-                register_rt_sched_group(tg, i);
-        }
         list_add_rcu(&tg->list, &task_groups);
 
         WARN_ON(!parent); /* root should already exist */
@@ -8476,11 +8428,11 @@ void sched_destroy_group(struct task_group *tg)
         unsigned long flags;
         int i;
 
-        spin_lock_irqsave(&task_group_lock, flags);
-        for_each_possible_cpu(i) {
+        /* end participation in shares distribution */
+        for_each_possible_cpu(i)
                 unregister_fair_sched_group(tg, i);
-                unregister_rt_sched_group(tg, i);
-        }
+
+        spin_lock_irqsave(&task_group_lock, flags);
         list_del_rcu(&tg->list);
         list_del_rcu(&tg->siblings);
         spin_unlock_irqrestore(&task_group_lock, flags);
@@ -8527,33 +8479,6 @@ void sched_move_task(struct task_struct *tsk)
 #endif /* CONFIG_CGROUP_SCHED */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void __set_se_shares(struct sched_entity *se, unsigned long shares)
-{
-        struct cfs_rq *cfs_rq = se->cfs_rq;
-        int on_rq;
-
-        on_rq = se->on_rq;
-        if (on_rq)
-                dequeue_entity(cfs_rq, se, 0);
-
-        se->load.weight = shares;
-        se->load.inv_weight = 0;
-
-        if (on_rq)
-                enqueue_entity(cfs_rq, se, 0);
-}
-
-static void set_se_shares(struct sched_entity *se, unsigned long shares)
-{
-        struct cfs_rq *cfs_rq = se->cfs_rq;
-        struct rq *rq = cfs_rq->rq;
-        unsigned long flags;
-
-        raw_spin_lock_irqsave(&rq->lock, flags);
-        __set_se_shares(se, shares);
-        raw_spin_unlock_irqrestore(&rq->lock, flags);
-}
-
 static DEFINE_MUTEX(shares_mutex);
 
 int sched_group_set_shares(struct task_group *tg, unsigned long shares)
@@ -8576,37 +8501,19 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
         if (tg->shares == shares)
                 goto done;
 
-        spin_lock_irqsave(&task_group_lock, flags);
-        for_each_possible_cpu(i)
-                unregister_fair_sched_group(tg, i);
-        list_del_rcu(&tg->siblings);
-        spin_unlock_irqrestore(&task_group_lock, flags);
-
-        /* wait for any ongoing reference to this group to finish */
-        synchronize_sched();
-
-        /*
-         * Now we are free to modify the group's share on each cpu
-         * w/o tripping rebalance_share or load_balance_fair.
-         */
         tg->shares = shares;
         for_each_possible_cpu(i) {
-                /*
-                 * force a rebalance
-                 */
-                cfs_rq_set_shares(tg->cfs_rq[i], 0);
-                set_se_shares(tg->se[i], shares);
+                struct rq *rq = cpu_rq(i);
+                struct sched_entity *se;
+
+                se = tg->se[i];
+                /* Propagate contribution to hierarchy */
+                raw_spin_lock_irqsave(&rq->lock, flags);
+                for_each_sched_entity(se)
+                        update_cfs_shares(group_cfs_rq(se), 0);
+                raw_spin_unlock_irqrestore(&rq->lock, flags);
         }
 
-        /*
-         * Enable load balance activity on this group, by inserting it back on
-         * each cpu's rq->leaf_cfs_rq_list.
-         */
-        spin_lock_irqsave(&task_group_lock, flags);
-        for_each_possible_cpu(i)
-                register_fair_sched_group(tg, i);
-        list_add_rcu(&tg->siblings, &tg->parent->children);
-        spin_unlock_irqrestore(&task_group_lock, flags);
 done:
         mutex_unlock(&shares_mutex);
         return 0;
@@ -8905,7 +8812,7 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
 
         if (!cgrp->parent) {
                 /* This is early initialization for the top cgroup */
-                return &init_task_group.css;
+                return &root_task_group.css;
         }
 
         parent = cgroup_tg(cgrp->parent);
@@ -8976,6 +8883,20 @@ cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
         }
 }
 
+static void
+cpu_cgroup_exit(struct cgroup_subsys *ss, struct task_struct *task)
+{
+        /*
+         * cgroup_exit() is called in the copy_process() failure path.
+         * Ignore this case since the task hasn't ran yet, this avoids
+         * trying to poke a half freed task state from generic code.
+         */
+        if (!(task->flags & PF_EXITING))
+                return;
+
+        sched_move_task(task);
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype,
                                 u64 shareval)
@@ -9048,6 +8969,7 @@ struct cgroup_subsys cpu_cgroup_subsys = {
         .destroy        = cpu_cgroup_destroy,
         .can_attach     = cpu_cgroup_can_attach,
         .attach         = cpu_cgroup_attach,
+        .exit           = cpu_cgroup_exit,
         .populate       = cpu_cgroup_populate,
         .subsys_id      = cpu_cgroup_subsys_id,
         .early_init     = 1,
@@ -9332,72 +9254,3 @@ struct cgroup_subsys cpuacct_subsys = {
 };
 #endif  /* CONFIG_CGROUP_CPUACCT */
 
-#ifndef CONFIG_SMP
-
-void synchronize_sched_expedited(void)
-{
-        barrier();
-}
-EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
-
-#else /* #ifndef CONFIG_SMP */
-
-static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0);
-
-static int synchronize_sched_expedited_cpu_stop(void *data)
-{
-        /*
-         * There must be a full memory barrier on each affected CPU
-         * between the time that try_stop_cpus() is called and the
-         * time that it returns.
-         *
-         * In the current initial implementation of cpu_stop, the
-         * above condition is already met when the control reaches
-         * this point and the following smp_mb() is not strictly
-         * necessary.  Do smp_mb() anyway for documentation and
-         * robustness against future implementation changes.
-         */
-        smp_mb(); /* See above comment block. */
-        return 0;
-}
-
-/*
- * Wait for an rcu-sched grace period to elapse, but use "big hammer"
- * approach to force grace period to end quickly.  This consumes
- * significant time on all CPUs, and is thus not recommended for
- * any sort of common-case code.
- *
- * Note that it is illegal to call this function while holding any
- * lock that is acquired by a CPU-hotplug notifier.  Failing to
- * observe this restriction will result in deadlock.
- */
-void synchronize_sched_expedited(void)
-{
-        int snap, trycount = 0;
-
-        smp_mb();  /* ensure prior mod happens before capturing snap. */
-        snap = atomic_read(&synchronize_sched_expedited_count) + 1;
-        get_online_cpus();
-        while (try_stop_cpus(cpu_online_mask,
-                             synchronize_sched_expedited_cpu_stop,
-                             NULL) == -EAGAIN) {
-                put_online_cpus();
-                if (trycount++ < 10)
-                        udelay(trycount * num_online_cpus());
-                else {
-                        synchronize_sched();
-                        return;
-                }
-                if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) {
-                        smp_mb(); /* ensure test happens before caller kfree */
-                        return;
-                }
-                get_online_cpus();
-        }
-        atomic_inc(&synchronize_sched_expedited_count);
-        smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */
-        put_online_cpus();
-}
-EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
-
-#endif /* #else #ifndef CONFIG_SMP */