1 files changed, 96 insertions, 425 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index e2e985eeee78..70cb127e3495 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -137,7 +137,7 @@ static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
 
 static inline int rt_policy(int policy)
 {
-        if (unlikely(policy == SCHED_FIFO) || unlikely(policy == SCHED_RR))
+        if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
                 return 1;
         return 0;
 }
@@ -313,12 +313,15 @@ static DEFINE_SPINLOCK(task_group_lock);
 #endif
 
 /*
- * A weight of 0, 1 or ULONG_MAX can cause arithmetics problems.
+ * A weight of 0 or 1 can cause arithmetics problems.
+ * A weight of a cfs_rq is the sum of weights of which entities
+ * are queued on this cfs_rq, so a weight of a entity should not be
+ * too large, so as the shares value of a task group.
  * (The default weight is 1024 - so there's no practical
  *  limitation from this.)
  */
 #define MIN_SHARES      2
-#define MAX_SHARES      (ULONG_MAX - 1)
+#define MAX_SHARES      (1UL << 18)
 
 static int init_task_group_load = INIT_TASK_GROUP_LOAD;
 #endif
@@ -399,43 +402,6 @@ struct cfs_rq {
          */
         struct list_head leaf_cfs_rq_list;
         struct task_group *tg;  /* group that "owns" this runqueue */
-
-#ifdef CONFIG_SMP
-        unsigned long task_weight;
-        unsigned long shares;
-        /*
-         * We need space to build a sched_domain wide view of the full task
-         * group tree, in order to avoid depending on dynamic memory allocation
-         * during the load balancing we place this in the per cpu task group
-         * hierarchy. This limits the load balancing to one instance per cpu,
-         * but more should not be needed anyway.
-         */
-        struct aggregate_struct {
-                /*
-                 *   load = weight(cpus) * f(tg)
-                 *
-                 * Where f(tg) is the recursive weight fraction assigned to
-                 * this group.
-                 */
-                unsigned long load;
-
-                /*
-                 * part of the group weight distributed to this span.
-                 */
-                unsigned long shares;
-
-                /*
-                 * The sum of all runqueue weights within this span.
-                 */
-                unsigned long rq_weight;
-
-                /*
-                 * Weight contributed by tasks; this is the part we can
-                 * influence by moving tasks around.
-                 */
-                unsigned long task_weight;
-        } aggregate;
-#endif
 #endif
 };
 
@@ -1180,6 +1146,7 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
         return HRTIMER_NORESTART;
 }
 
+#ifdef CONFIG_SMP
 static void hotplug_hrtick_disable(int cpu)
 {
         struct rq *rq = cpu_rq(cpu);
@@ -1235,6 +1202,7 @@ static void init_hrtick(void)
 {
         hotcpu_notifier(hotplug_hrtick, 0);
 }
+#endif /* CONFIG_SMP */
 
 static void init_rq_hrtick(struct rq *rq)
 {
@@ -1387,17 +1355,19 @@ static void __resched_task(struct task_struct *p, int tif_bit)
  */
 #define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
 
-/*
- * delta *= weight / lw
- */
 static unsigned long
 calc_delta_mine(unsigned long delta_exec, unsigned long weight,
                 struct load_weight *lw)
 {
         u64 tmp;
 
-        if (!lw->inv_weight)
-                lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)/(lw->weight+1);
+        if (!lw->inv_weight) {
+                if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
+                        lw->inv_weight = 1;
+                else
+                        lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
+                                / (lw->weight+1);
+        }
 
         tmp = (u64)delta_exec * weight;
         /*
@@ -1412,6 +1382,12 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
         return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
 }
 
+static inline unsigned long
+calc_delta_fair(unsigned long delta_exec, struct load_weight *lw)
+{
+        return calc_delta_mine(delta_exec, NICE_0_LOAD, lw);
+}
+
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
 {
         lw->weight += inc;
@@ -1524,326 +1500,6 @@ static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
 static unsigned long cpu_avg_load_per_task(int cpu);
 static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-
-/*
- * Group load balancing.
- *
- * We calculate a few balance domain wide aggregate numbers; load and weight.
- * Given the pictures below, and assuming each item has equal weight:
- *
- *         root          1 - thread
- *         / | \         A - group
- *        A  1  B
- *       /|\   / \
- *      C 2 D 3   4
- *      |   |
- *      5   6
- *
- * load:
- *    A and B get 1/3-rd of the total load. C and D get 1/3-rd of A's 1/3-rd,
- *    which equals 1/9-th of the total load.
- *
- * shares:
- *    The weight of this group on the selected cpus.
- *
- * rq_weight:
- *    Direct sum of all the cpu's their rq weight, e.g. A would get 3 while
- *    B would get 2.
- *
- * task_weight:
- *    Part of the rq_weight contributed by tasks; all groups except B would
- *    get 1, B gets 2.
- */
-
-static inline struct aggregate_struct *
-aggregate(struct task_group *tg, struct sched_domain *sd)
-{
-        return &tg->cfs_rq[sd->first_cpu]->aggregate;
-}
-
-typedef void (*aggregate_func)(struct task_group *, struct sched_domain *);
-
-/*
- * Iterate the full tree, calling @down when first entering a node and @up when
- * leaving it for the final time.
- */
-static
-void aggregate_walk_tree(aggregate_func down, aggregate_func up,
-                         struct sched_domain *sd)
-{
-        struct task_group *parent, *child;
-
-        rcu_read_lock();
-        parent = &root_task_group;
-down:
-        (*down)(parent, sd);
-        list_for_each_entry_rcu(child, &parent->children, siblings) {
-                parent = child;
-                goto down;
-
-up:
-                continue;
-        }
-        (*up)(parent, sd);
-
-        child = parent;
-        parent = parent->parent;
-        if (parent)
-                goto up;
-        rcu_read_unlock();
-}
-
-/*
- * Calculate the aggregate runqueue weight.
- */
-static
-void aggregate_group_weight(struct task_group *tg, struct sched_domain *sd)
-{
-        unsigned long rq_weight = 0;
-        unsigned long task_weight = 0;
-        int i;
-
-        for_each_cpu_mask(i, sd->span) {
-                rq_weight += tg->cfs_rq[i]->load.weight;
-                task_weight += tg->cfs_rq[i]->task_weight;
-        }
-
-        aggregate(tg, sd)->rq_weight = rq_weight;
-        aggregate(tg, sd)->task_weight = task_weight;
-}
-
-/*
- * Compute the weight of this group on the given cpus.
- */
-static
-void aggregate_group_shares(struct task_group *tg, struct sched_domain *sd)
-{
-        unsigned long shares = 0;
-        int i;
-
-        for_each_cpu_mask(i, sd->span)
-                shares += tg->cfs_rq[i]->shares;
-
-        if ((!shares && aggregate(tg, sd)->rq_weight) || shares > tg->shares)
-                shares = tg->shares;
-
-        aggregate(tg, sd)->shares = shares;
-}
-
-/*
- * Compute the load fraction assigned to this group, relies on the aggregate
- * weight and this group's parent's load, i.e. top-down.
- */
-static
-void aggregate_group_load(struct task_group *tg, struct sched_domain *sd)
-{
-        unsigned long load;
-
-        if (!tg->parent) {
-                int i;
-
-                load = 0;
-                for_each_cpu_mask(i, sd->span)
-                        load += cpu_rq(i)->load.weight;
-
-        } else {
-                load = aggregate(tg->parent, sd)->load;
-
-                /*
-                 * shares is our weight in the parent's rq so
-                 * shares/parent->rq_weight gives our fraction of the load
-                 */
-                load *= aggregate(tg, sd)->shares;
-                load /= aggregate(tg->parent, sd)->rq_weight + 1;
-        }
-
-        aggregate(tg, sd)->load = load;
-}
-
-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, struct sched_domain *sd,
-                          int tcpu)
-{
-        int boost = 0;
-        unsigned long shares;
-        unsigned long rq_weight;
-
-        if (!tg->se[tcpu])
-                return;
-
-        rq_weight = tg->cfs_rq[tcpu]->load.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 (!rq_weight) {
-                boost = 1;
-                rq_weight = NICE_0_LOAD;
-        }
-
-        /*
-         *           \Sum shares * rq_weight
-         * shares =  -----------------------
-         *               \Sum rq_weight
-         *
-         */
-        shares = aggregate(tg, sd)->shares * rq_weight;
-        shares /= aggregate(tg, sd)->rq_weight + 1;
-
-        /*
-         * record the actual number of shares, not the boosted amount.
-         */
-        tg->cfs_rq[tcpu]->shares = boost ? 0 : shares;
-
-        if (shares < MIN_SHARES)
-                shares = MIN_SHARES;
-        else if (shares > MAX_SHARES)
-                shares = MAX_SHARES;
-
-        __set_se_shares(tg->se[tcpu], shares);
-}
-
-/*
- * Re-adjust the weights on the cpu the task came from and on the cpu the
- * task went to.
- */
-static void
-__move_group_shares(struct task_group *tg, struct sched_domain *sd,
-                    int scpu, int dcpu)
-{
-        unsigned long shares;
-
-        shares = tg->cfs_rq[scpu]->shares + tg->cfs_rq[dcpu]->shares;
-
-        __update_group_shares_cpu(tg, sd, scpu);
-        __update_group_shares_cpu(tg, sd, dcpu);
-
-        /*
-         * ensure we never loose shares due to rounding errors in the
-         * above redistribution.
-         */
-        shares -= tg->cfs_rq[scpu]->shares + tg->cfs_rq[dcpu]->shares;
-        if (shares)
-                tg->cfs_rq[dcpu]->shares += shares;
-}
-
-/*
- * Because changing a group's shares changes the weight of the super-group
- * we need to walk up the tree and change all shares until we hit the root.
- */
-static void
-move_group_shares(struct task_group *tg, struct sched_domain *sd,
-                  int scpu, int dcpu)
-{
-        while (tg) {
-                __move_group_shares(tg, sd, scpu, dcpu);
-                tg = tg->parent;
-        }
-}
-
-static
-void aggregate_group_set_shares(struct task_group *tg, struct sched_domain *sd)
-{
-        unsigned long shares = aggregate(tg, sd)->shares;
-        int i;
-
-        for_each_cpu_mask(i, sd->span) {
-                struct rq *rq = cpu_rq(i);
-                unsigned long flags;
-
-                spin_lock_irqsave(&rq->lock, flags);
-                __update_group_shares_cpu(tg, sd, i);
-                spin_unlock_irqrestore(&rq->lock, flags);
-        }
-
-        aggregate_group_shares(tg, sd);
-
-        /*
-         * ensure we never loose shares due to rounding errors in the
-         * above redistribution.
-         */
-        shares -= aggregate(tg, sd)->shares;
-        if (shares) {
-                tg->cfs_rq[sd->first_cpu]->shares += shares;
-                aggregate(tg, sd)->shares += shares;
-        }
-}
-
-/*
- * Calculate the accumulative weight and recursive load of each task group
- * while walking down the tree.
- */
-static
-void aggregate_get_down(struct task_group *tg, struct sched_domain *sd)
-{
-        aggregate_group_weight(tg, sd);
-        aggregate_group_shares(tg, sd);
-        aggregate_group_load(tg, sd);
-}
-
-/*
- * Rebalance the cpu shares while walking back up the tree.
- */
-static
-void aggregate_get_up(struct task_group *tg, struct sched_domain *sd)
-{
-        aggregate_group_set_shares(tg, sd);
-}
-
-static DEFINE_PER_CPU(spinlock_t, aggregate_lock);
-
-static void __init init_aggregate(void)
-{
-        int i;
-
-        for_each_possible_cpu(i)
-                spin_lock_init(&per_cpu(aggregate_lock, i));
-}
-
-static int get_aggregate(struct sched_domain *sd)
-{
-        if (!spin_trylock(&per_cpu(aggregate_lock, sd->first_cpu)))
-                return 0;
-
-        aggregate_walk_tree(aggregate_get_down, aggregate_get_up, sd);
-        return 1;
-}
-
-static void put_aggregate(struct sched_domain *sd)
-{
-        spin_unlock(&per_cpu(aggregate_lock, sd->first_cpu));
-}
-
-static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
-{
-        cfs_rq->shares = shares;
-}
-
-#else
-
-static inline void init_aggregate(void)
-{
-}
-
-static inline int get_aggregate(struct sched_domain *sd)
-{
-        return 0;
-}
-
-static inline void put_aggregate(struct sched_domain *sd)
-{
-}
-#endif
-
 #else /* CONFIG_SMP */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1864,14 +1520,26 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 
 #define sched_class_highest (&rt_sched_class)
 
-static void inc_nr_running(struct rq *rq)
+static inline void inc_load(struct rq *rq, const struct task_struct *p)
+{
+        update_load_add(&rq->load, p->se.load.weight);
+}
+
+static inline void dec_load(struct rq *rq, const struct task_struct *p)
+{
+        update_load_sub(&rq->load, p->se.load.weight);
+}
+
+static void inc_nr_running(struct task_struct *p, struct rq *rq)
 {
         rq->nr_running++;
+        inc_load(rq, p);
 }
 
-static void dec_nr_running(struct rq *rq)
+static void dec_nr_running(struct task_struct *p, struct rq *rq)
 {
         rq->nr_running--;
+        dec_load(rq, p);
 }
 
 static void set_load_weight(struct task_struct *p)
@@ -1963,7 +1631,7 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
                 rq->nr_uninterruptible--;
 
         enqueue_task(rq, p, wakeup);
-        inc_nr_running(rq);
+        inc_nr_running(p, rq);
 }
 
 /*
@@ -1975,7 +1643,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
                 rq->nr_uninterruptible++;
 
         dequeue_task(rq, p, sleep);
-        dec_nr_running(rq);
+        dec_nr_running(p, rq);
 }
 
 /**
@@ -2631,7 +2299,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
                  * management (if any):
                  */
                 p->sched_class->task_new(rq, p);
-                inc_nr_running(rq);
+                inc_nr_running(p, rq);
         }
         trace_mark(kernel_sched_wakeup_new,
                 "pid %d state %ld ## rq %p task %p rq->curr %p",
@@ -3630,12 +3298,9 @@ static int load_balance(int this_cpu, struct rq *this_rq,
         unsigned long imbalance;
         struct rq *busiest;
         unsigned long flags;
-        int unlock_aggregate;
 
         cpus_setall(*cpus);
 
-        unlock_aggregate = get_aggregate(sd);
-
         /*
          * When power savings policy is enabled for the parent domain, idle
          * sibling can pick up load irrespective of busy siblings. In this case,
@@ -3751,9 +3416,8 @@ redo:
 
         if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
             !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-                ld_moved = -1;
-
-        goto out;
+                return -1;
+        return ld_moved;
 
 out_balanced:
         schedstat_inc(sd, lb_balanced[idle]);
@@ -3768,13 +3432,8 @@ out_one_pinned:
 
         if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
             !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-                ld_moved = -1;
-        else
-                ld_moved = 0;
-out:
-        if (unlock_aggregate)
-                put_aggregate(sd);
-        return ld_moved;
+                return -1;
+        return 0;
 }
 
 /*
@@ -4481,7 +4140,7 @@ static inline void schedule_debug(struct task_struct *prev)
          * schedule() atomically, we ignore that path for now.
          * Otherwise, whine if we are scheduling when we should not be.
          */
-        if (unlikely(in_atomic_preempt_off()) && unlikely(!prev->exit_state))
+        if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
                 __schedule_bug(prev);
 
         profile_hit(SCHED_PROFILING, __builtin_return_address(0));
@@ -4561,12 +4220,10 @@ need_resched_nonpreemptible:
         clear_tsk_need_resched(prev);
 
         if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
-                if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
-                                signal_pending(prev))) {
+                if (unlikely(signal_pending_state(prev->state, prev)))
                         prev->state = TASK_RUNNING;
-                } else {
+                else
                         deactivate_task(rq, prev, 1);
-                }
                 switch_count = &prev->nvcsw;
         }
 
@@ -4792,22 +4449,20 @@ do_wait_for_common(struct completion *x, long timeout, int state)
                              signal_pending(current)) ||
                             (state == TASK_KILLABLE &&
                              fatal_signal_pending(current))) {
-                                __remove_wait_queue(&x->wait, &wait);
-                                return -ERESTARTSYS;
+                                timeout = -ERESTARTSYS;
+                                break;
                         }
                         __set_current_state(state);
                         spin_unlock_irq(&x->wait.lock);
                         timeout = schedule_timeout(timeout);
                         spin_lock_irq(&x->wait.lock);
-                        if (!timeout) {
-                                __remove_wait_queue(&x->wait, &wait);
-                                return timeout;
-                        }
-                } while (!x->done);
+                } while (!x->done && timeout);
                 __remove_wait_queue(&x->wait, &wait);
+                if (!x->done)
+                        return timeout;
         }
         x->done--;
-        return timeout;
+        return timeout ?: 1;
 }
 
 static long __sched
@@ -4982,8 +4637,10 @@ void set_user_nice(struct task_struct *p, long nice)
                 goto out_unlock;
         }
         on_rq = p->se.on_rq;
-        if (on_rq)
+        if (on_rq) {
                 dequeue_task(rq, p, 0);
+                dec_load(rq, p);
+        }
 
         p->static_prio = NICE_TO_PRIO(nice);
         set_load_weight(p);
@@ -4993,6 +4650,7 @@ void set_user_nice(struct task_struct *p, long nice)
 
         if (on_rq) {
                 enqueue_task(rq, p, 0);
+                inc_load(rq, p);
                 /*
                  * If the task increased its priority or is running and
                  * lowered its priority, then reschedule its CPU:
@@ -6280,6 +5938,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
                 next = pick_next_task(rq, rq->curr);
                 if (!next)
                         break;
+                next->sched_class->put_prev_task(rq, next);
                 migrate_dead(dead_cpu, next);
 
         }
@@ -7270,7 +6929,12 @@ static int default_relax_domain_level = -1;
 
 static int __init setup_relax_domain_level(char *str)
 {
-        default_relax_domain_level = simple_strtoul(str, NULL, 0);
+        unsigned long val;
+
+        val = simple_strtoul(str, NULL, 0);
+        if (val < SD_LV_MAX)
+                default_relax_domain_level = val;
+
         return 1;
 }
 __setup("relax_domain_level=", setup_relax_domain_level);
@@ -7367,7 +7031,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
                         SD_INIT(sd, ALLNODES);
                         set_domain_attribute(sd, attr);
                         sd->span = *cpu_map;
-                        sd->first_cpu = first_cpu(sd->span);
                         cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
                         p = sd;
                         sd_allnodes = 1;
@@ -7378,7 +7041,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
                 SD_INIT(sd, NODE);
                 set_domain_attribute(sd, attr);
                 sched_domain_node_span(cpu_to_node(i), &sd->span);
-                sd->first_cpu = first_cpu(sd->span);
                 sd->parent = p;
                 if (p)
                         p->child = sd;
@@ -7390,7 +7052,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
                 SD_INIT(sd, CPU);
                 set_domain_attribute(sd, attr);
                 sd->span = *nodemask;
-                sd->first_cpu = first_cpu(sd->span);
                 sd->parent = p;
                 if (p)
                         p->child = sd;
@@ -7402,7 +7063,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
                 SD_INIT(sd, MC);
                 set_domain_attribute(sd, attr);
                 sd->span = cpu_coregroup_map(i);
-                sd->first_cpu = first_cpu(sd->span);
                 cpus_and(sd->span, sd->span, *cpu_map);
                 sd->parent = p;
                 p->child = sd;
@@ -7415,7 +7075,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
                 SD_INIT(sd, SIBLING);
                 set_domain_attribute(sd, attr);
                 sd->span = per_cpu(cpu_sibling_map, i);
-                sd->first_cpu = first_cpu(sd->span);
                 cpus_and(sd->span, sd->span, *cpu_map);
                 sd->parent = p;
                 p->child = sd;
@@ -7619,8 +7278,8 @@ static int build_sched_domains(const cpumask_t *cpu_map)
 
 static cpumask_t *doms_cur;     /* current sched domains */
 static int ndoms_cur;           /* number of sched domains in 'doms_cur' */
-static struct sched_domain_attr *dattr_cur;     /* attribues of custom domains
-                                                   in 'doms_cur' */
+static struct sched_domain_attr *dattr_cur;
+                                /* attribues of custom domains in 'doms_cur' */
 
 /*
  * Special case: If a kmalloc of a doms_cur partition (array of
@@ -7634,6 +7293,18 @@ void __attribute__((weak)) arch_update_cpu_topology(void)
 }
 
 /*
+ * Free current domain masks.
+ * Called after all cpus are attached to NULL domain.
+ */
+static void free_sched_domains(void)
+{
+        ndoms_cur = 0;
+        if (doms_cur != &fallback_doms)
+                kfree(doms_cur);
+        doms_cur = &fallback_doms;
+}
+
+/*
  * Set up scheduler domains and groups. Callers must hold the hotplug lock.
  * For now this just excludes isolated cpus, but could be used to
  * exclude other special cases in the future.
@@ -7780,6 +7451,7 @@ int arch_reinit_sched_domains(void)
         get_online_cpus();
         mutex_lock(&sched_domains_mutex);
         detach_destroy_domains(&cpu_online_map);
+        free_sched_domains();
         err = arch_init_sched_domains(&cpu_online_map);
         mutex_unlock(&sched_domains_mutex);
         put_online_cpus();
@@ -7865,6 +7537,7 @@ static int update_sched_domains(struct notifier_block *nfb,
         case CPU_DOWN_PREPARE:
         case CPU_DOWN_PREPARE_FROZEN:
                 detach_destroy_domains(&cpu_online_map);
+                free_sched_domains();
                 return NOTIFY_OK;
 
         case CPU_UP_CANCELED:
@@ -7883,8 +7556,16 @@ static int update_sched_domains(struct notifier_block *nfb,
                 return NOTIFY_DONE;
         }
 
+#ifndef CONFIG_CPUSETS
+        /*
+         * Create default domain partitioning if cpusets are disabled.
+         * Otherwise we let cpusets rebuild the domains based on the
+         * current setup.
+         */
+
         /* The hotplug lock is already held by cpu_up/cpu_down */
         arch_init_sched_domains(&cpu_online_map);
+#endif
 
         return NOTIFY_OK;
 }
@@ -8024,7 +7705,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
         else
                 rt_se->rt_rq = parent->my_q;
 
-        rt_se->rt_rq = &rq->rt;
         rt_se->my_q = rt_rq;
         rt_se->parent = parent;
         INIT_LIST_HEAD(&rt_se->run_list);
@@ -8085,7 +7765,6 @@ void __init sched_init(void)
         }
 
 #ifdef CONFIG_SMP
-        init_aggregate();
         init_defrootdomain();
 #endif
 
@@ -8650,11 +8329,14 @@ void sched_move_task(struct task_struct *tsk)
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void __set_se_shares(struct sched_entity *se, unsigned long shares)
+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;
         int on_rq;
 
+        spin_lock_irq(&rq->lock);
+
         on_rq = se->on_rq;
         if (on_rq)
                 dequeue_entity(cfs_rq, se, 0);
@@ -8664,17 +8346,8 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares)
 
         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;
-
-        spin_lock_irqsave(&rq->lock, flags);
-        __set_se_shares(se, shares);
-        spin_unlock_irqrestore(&rq->lock, flags);
+        spin_unlock_irq(&rq->lock);
 }
 
 static DEFINE_MUTEX(shares_mutex);
@@ -8713,13 +8386,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
          * 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);
+        for_each_possible_cpu(i)
                 set_se_shares(tg->se[i], shares);
-        }
 
         /*
          * Enable load balance activity on this group, by inserting it back on
@@ -8758,7 +8426,7 @@ static unsigned long to_ratio(u64 period, u64 runtime)
 #ifdef CONFIG_CGROUP_SCHED
 static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 {
-        struct task_group *tgi, *parent = tg->parent;
+        struct task_group *tgi, *parent = tg ? tg->parent : NULL;
         unsigned long total = 0;
 
         if (!parent) {
@@ -8885,6 +8553,9 @@ int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
         rt_period = (u64)rt_period_us * NSEC_PER_USEC;
         rt_runtime = tg->rt_bandwidth.rt_runtime;
 
+        if (rt_period == 0)
+                return -EINVAL;
+
         return tg_set_bandwidth(tg, rt_period, rt_runtime);
 }