6 files changed, 358 insertions, 250 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e5212ae294f6..bd314d7cd9f8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -692,8 +692,6 @@ int tg_nop(struct task_group *tg, void *data)
 }
 #endif
 
-void update_cpu_load(struct rq *this_rq);
-
 static void set_load_weight(struct task_struct *p)
 {
         int prio = p->static_prio - MAX_RT_PRIO;
@@ -2486,22 +2484,13 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
  * scheduler tick (TICK_NSEC). With tickless idle this will not be called
  * every tick. We fix it up based on jiffies.
  */
-void update_cpu_load(struct rq *this_rq)
+static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
+                              unsigned long pending_updates)
 {
-        unsigned long this_load = this_rq->load.weight;
-        unsigned long curr_jiffies = jiffies;
-        unsigned long pending_updates;
         int i, scale;
 
         this_rq->nr_load_updates++;
 
-        /* Avoid repeated calls on same jiffy, when moving in and out of idle */
-        if (curr_jiffies == this_rq->last_load_update_tick)
-                return;
-
-        pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-        this_rq->last_load_update_tick = curr_jiffies;
-
         /* Update our load: */
         this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
         for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
@@ -2526,9 +2515,45 @@ void update_cpu_load(struct rq *this_rq)
         sched_avg_update(this_rq);
 }
 
+/*
+ * Called from nohz_idle_balance() to update the load ratings before doing the
+ * idle balance.
+ */
+void update_idle_cpu_load(struct rq *this_rq)
+{
+        unsigned long curr_jiffies = jiffies;
+        unsigned long load = this_rq->load.weight;
+        unsigned long pending_updates;
+
+        /*
+         * Bloody broken means of dealing with nohz, but better than nothing..
+         * jiffies is updated by one cpu, another cpu can drift wrt the jiffy
+         * update and see 0 difference the one time and 2 the next, even though
+         * we ticked at roughtly the same rate.
+         *
+         * Hence we only use this from nohz_idle_balance() and skip this
+         * nonsense when called from the scheduler_tick() since that's
+         * guaranteed a stable rate.
+         */
+        if (load || curr_jiffies == this_rq->last_load_update_tick)
+                return;
+
+        pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+        this_rq->last_load_update_tick = curr_jiffies;
+
+        __update_cpu_load(this_rq, load, pending_updates);
+}
+
+/*
+ * Called from scheduler_tick()
+ */
 static void update_cpu_load_active(struct rq *this_rq)
 {
-        update_cpu_load(this_rq);
+        /*
+         * See the mess in update_idle_cpu_load().
+         */
+        this_rq->last_load_update_tick = jiffies;
+        __update_cpu_load(this_rq, this_rq->load.weight, 1);
 
         calc_load_account_active(this_rq);
 }
@@ -5560,7 +5585,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
                         break;
                 }
 
-                if (cpumask_intersects(groupmask, sched_group_cpus(group))) {
+                if (!(sd->flags & SD_OVERLAP) &&
+                    cpumask_intersects(groupmask, sched_group_cpus(group))) {
                         printk(KERN_CONT "\n");
                         printk(KERN_ERR "ERROR: repeated CPUs\n");
                         break;
@@ -5898,92 +5924,6 @@ static int __init isolated_cpu_setup(char *str)
 
 __setup("isolcpus=", isolated_cpu_setup);
 
-#ifdef CONFIG_NUMA
-
-/**
- * find_next_best_node - find the next node to include in a sched_domain
- * @node: node whose sched_domain we're building
- * @used_nodes: nodes already in the sched_domain
- *
- * Find the next node to include in a given scheduling domain. Simply
- * finds the closest node not already in the @used_nodes map.
- *
- * Should use nodemask_t.
- */
-static int find_next_best_node(int node, nodemask_t *used_nodes)
-{
-        int i, n, val, min_val, best_node = -1;
-
-        min_val = INT_MAX;
-
-        for (i = 0; i < nr_node_ids; i++) {
-                /* Start at @node */
-                n = (node + i) % nr_node_ids;
-
-                if (!nr_cpus_node(n))
-                        continue;
-
-                /* Skip already used nodes */
-                if (node_isset(n, *used_nodes))
-                        continue;
-
-                /* Simple min distance search */
-                val = node_distance(node, n);
-
-                if (val < min_val) {
-                        min_val = val;
-                        best_node = n;
-                }
-        }
-
-        if (best_node != -1)
-                node_set(best_node, *used_nodes);
-        return best_node;
-}
-
-/**
- * sched_domain_node_span - get a cpumask for a node's sched_domain
- * @node: node whose cpumask we're constructing
- * @span: resulting cpumask
- *
- * Given a node, construct a good cpumask for its sched_domain to span. It
- * should be one that prevents unnecessary balancing, but also spreads tasks
- * out optimally.
- */
-static void sched_domain_node_span(int node, struct cpumask *span)
-{
-        nodemask_t used_nodes;
-        int i;
-
-        cpumask_clear(span);
-        nodes_clear(used_nodes);
-
-        cpumask_or(span, span, cpumask_of_node(node));
-        node_set(node, used_nodes);
-
-        for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
-                int next_node = find_next_best_node(node, &used_nodes);
-                if (next_node < 0)
-                        break;
-                cpumask_or(span, span, cpumask_of_node(next_node));
-        }
-}
-
-static const struct cpumask *cpu_node_mask(int cpu)
-{
-        lockdep_assert_held(&sched_domains_mutex);
-
-        sched_domain_node_span(cpu_to_node(cpu), sched_domains_tmpmask);
-
-        return sched_domains_tmpmask;
-}
-
-static const struct cpumask *cpu_allnodes_mask(int cpu)
-{
-        return cpu_possible_mask;
-}
-#endif /* CONFIG_NUMA */
-
 static const struct cpumask *cpu_cpu_mask(int cpu)
 {
         return cpumask_of_node(cpu_to_node(cpu));
@@ -6020,6 +5960,7 @@ struct sched_domain_topology_level {
         sched_domain_init_f init;
         sched_domain_mask_f mask;
         int                 flags;
+        int                 numa_level;
         struct sd_data      data;
 };
 
@@ -6211,10 +6152,6 @@ sd_init_##type(struct sched_domain_topology_level *tl, int cpu) 	\
 }
 
 SD_INIT_FUNC(CPU)
-#ifdef CONFIG_NUMA
- SD_INIT_FUNC(ALLNODES)
- SD_INIT_FUNC(NODE)
-#endif
 #ifdef CONFIG_SCHED_SMT
  SD_INIT_FUNC(SIBLING)
 #endif
@@ -6336,15 +6273,185 @@ static struct sched_domain_topology_level default_topology[] = {
         { sd_init_BOOK, cpu_book_mask, },
 #endif
         { sd_init_CPU, cpu_cpu_mask, },
-#ifdef CONFIG_NUMA
-        { sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, },
-        { sd_init_ALLNODES, cpu_allnodes_mask, },
-#endif
         { NULL, },
 };
 
 static struct sched_domain_topology_level *sched_domain_topology = default_topology;
 
+#ifdef CONFIG_NUMA
+
+static int sched_domains_numa_levels;
+static int sched_domains_numa_scale;
+static int *sched_domains_numa_distance;
+static struct cpumask ***sched_domains_numa_masks;
+static int sched_domains_curr_level;
+
+static inline int sd_local_flags(int level)
+{
+        if (sched_domains_numa_distance[level] > REMOTE_DISTANCE)
+                return 0;
+
+        return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
+}
+
+static struct sched_domain *
+sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
+{
+        struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
+        int level = tl->numa_level;
+        int sd_weight = cpumask_weight(
+                        sched_domains_numa_masks[level][cpu_to_node(cpu)]);
+
+        *sd = (struct sched_domain){
+                .min_interval           = sd_weight,
+                .max_interval           = 2*sd_weight,
+                .busy_factor            = 32,
+                .imbalance_pct          = 125,
+                .cache_nice_tries       = 2,
+                .busy_idx               = 3,
+                .idle_idx               = 2,
+                .newidle_idx            = 0,
+                .wake_idx               = 0,
+                .forkexec_idx           = 0,
+
+                .flags                  = 1*SD_LOAD_BALANCE
+                                        | 1*SD_BALANCE_NEWIDLE
+                                        | 0*SD_BALANCE_EXEC
+                                        | 0*SD_BALANCE_FORK
+                                        | 0*SD_BALANCE_WAKE
+                                        | 0*SD_WAKE_AFFINE
+                                        | 0*SD_PREFER_LOCAL
+                                        | 0*SD_SHARE_CPUPOWER
+                                        | 0*SD_POWERSAVINGS_BALANCE
+                                        | 0*SD_SHARE_PKG_RESOURCES
+                                        | 1*SD_SERIALIZE
+                                        | 0*SD_PREFER_SIBLING
+                                        | sd_local_flags(level)
+                                        ,
+                .last_balance           = jiffies,
+                .balance_interval       = sd_weight,
+        };
+        SD_INIT_NAME(sd, NUMA);
+        sd->private = &tl->data;
+
+        /*
+         * Ugly hack to pass state to sd_numa_mask()...
+         */
+        sched_domains_curr_level = tl->numa_level;
+
+        return sd;
+}
+
+static const struct cpumask *sd_numa_mask(int cpu)
+{
+        return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
+}
+
+static void sched_init_numa(void)
+{
+        int next_distance, curr_distance = node_distance(0, 0);
+        struct sched_domain_topology_level *tl;
+        int level = 0;
+        int i, j, k;
+
+        sched_domains_numa_scale = curr_distance;
+        sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
+        if (!sched_domains_numa_distance)
+                return;
+
+        /*
+         * O(nr_nodes^2) deduplicating selection sort -- in order to find the
+         * unique distances in the node_distance() table.
+         *
+         * Assumes node_distance(0,j) includes all distances in
+         * node_distance(i,j) in order to avoid cubic time.
+         *
+         * XXX: could be optimized to O(n log n) by using sort()
+         */
+        next_distance = curr_distance;
+        for (i = 0; i < nr_node_ids; i++) {
+                for (j = 0; j < nr_node_ids; j++) {
+                        int distance = node_distance(0, j);
+                        if (distance > curr_distance &&
+                                        (distance < next_distance ||
+                                         next_distance == curr_distance))
+                                next_distance = distance;
+                }
+                if (next_distance != curr_distance) {
+                        sched_domains_numa_distance[level++] = next_distance;
+                        sched_domains_numa_levels = level;
+                        curr_distance = next_distance;
+                } else break;
+        }
+        /*
+         * 'level' contains the number of unique distances, excluding the
+         * identity distance node_distance(i,i).
+         *
+         * The sched_domains_nume_distance[] array includes the actual distance
+         * numbers.
+         */
+
+        sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
+        if (!sched_domains_numa_masks)
+                return;
+
+        /*
+         * Now for each level, construct a mask per node which contains all
+         * cpus of nodes that are that many hops away from us.
+         */
+        for (i = 0; i < level; i++) {
+                sched_domains_numa_masks[i] =
+                        kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
+                if (!sched_domains_numa_masks[i])
+                        return;
+
+                for (j = 0; j < nr_node_ids; j++) {
+                        struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j);
+                        if (!mask)
+                                return;
+
+                        sched_domains_numa_masks[i][j] = mask;
+
+                        for (k = 0; k < nr_node_ids; k++) {
+                                if (node_distance(j, k) > sched_domains_numa_distance[i])
+                                        continue;
+
+                                cpumask_or(mask, mask, cpumask_of_node(k));
+                        }
+                }
+        }
+
+        tl = kzalloc((ARRAY_SIZE(default_topology) + level) *
+                        sizeof(struct sched_domain_topology_level), GFP_KERNEL);
+        if (!tl)
+                return;
+
+        /*
+         * Copy the default topology bits..
+         */
+        for (i = 0; default_topology[i].init; i++)
+                tl[i] = default_topology[i];
+
+        /*
+         * .. and append 'j' levels of NUMA goodness.
+         */
+        for (j = 0; j < level; i++, j++) {
+                tl[i] = (struct sched_domain_topology_level){
+                        .init = sd_numa_init,
+                        .mask = sd_numa_mask,
+                        .flags = SDTL_OVERLAP,
+                        .numa_level = j,
+                };
+        }
+
+        sched_domain_topology = tl;
+}
+#else
+static inline void sched_init_numa(void)
+{
+}
+#endif /* CONFIG_NUMA */
+
 static int __sdt_alloc(const struct cpumask *cpu_map)
 {
         struct sched_domain_topology_level *tl;
@@ -6840,6 +6947,8 @@ void __init sched_init_smp(void)
         alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
         alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
+        sched_init_numa();
+
         get_online_cpus();
         mutex_lock(&sched_domains_mutex);
         init_sched_domains(cpu_active_mask);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 09acaa15161d..6f79596e0ea9 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -202,7 +202,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
                         SPLIT_NS(spread0));
         SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
                         cfs_rq->nr_spread_over);
-        SEQ_printf(m, "  .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
+        SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
         SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_SMP
@@ -260,8 +260,14 @@ static void print_cpu(struct seq_file *m, int cpu)
         SEQ_printf(m, "\ncpu#%d\n", cpu);
 #endif
 
-#define P(x) \
-        SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x))
+#define P(x)                                                            \
+do {                                                                    \
+        if (sizeof(rq->x) == 4)                                         \
+                SEQ_printf(m, "  .%-30s: %ld\n", #x, (long)(rq->x));    \
+        else                                                            \
+                SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x));\
+} while (0)
+
 #define PN(x) \
         SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x))
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e9553640c1c3..0b42f4487329 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3082,7 +3082,7 @@ struct lb_env {
         struct rq               *dst_rq;
 
         enum cpu_idle_type      idle;
-        long                    load_move;
+        long                    imbalance;
         unsigned int            flags;
 
         unsigned int            loop;
@@ -3218,7 +3218,7 @@ static unsigned long task_h_load(struct task_struct *p);
 static const unsigned int sched_nr_migrate_break = 32;
 
 /*
- * move_tasks tries to move up to load_move weighted load from busiest to
+ * move_tasks tries to move up to imbalance weighted load from busiest to
  * this_rq, as part of a balancing operation within domain "sd".
  * Returns 1 if successful and 0 otherwise.
  *
@@ -3231,7 +3231,7 @@ static int move_tasks(struct lb_env *env)
         unsigned long load;
         int pulled = 0;
 
-        if (env->load_move <= 0)
+        if (env->imbalance <= 0)
                 return 0;
 
         while (!list_empty(tasks)) {
@@ -3257,7 +3257,7 @@ static int move_tasks(struct lb_env *env)
                 if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
                         goto next;
 
-                if ((load / 2) > env->load_move)
+                if ((load / 2) > env->imbalance)
                         goto next;
 
                 if (!can_migrate_task(p, env))
@@ -3265,7 +3265,7 @@ static int move_tasks(struct lb_env *env)
 
                 move_task(p, env);
                 pulled++;
-                env->load_move -= load;
+                env->imbalance -= load;
 
 #ifdef CONFIG_PREEMPT
                 /*
@@ -3281,7 +3281,7 @@ static int move_tasks(struct lb_env *env)
                  * We only want to steal up to the prescribed amount of
                  * weighted load.
                  */
-                if (env->load_move <= 0)
+                if (env->imbalance <= 0)
                         break;
 
                 continue;
@@ -3578,10 +3578,9 @@ static inline void update_sd_power_savings_stats(struct sched_group *group,
 
 /**
  * check_power_save_busiest_group - see if there is potential for some power-savings balance
+ * @env: load balance environment
  * @sds: Variable containing the statistics of the sched_domain
  *      under consideration.
- * @this_cpu: Cpu at which we're currently performing load-balancing.
- * @imbalance: Variable to store the imbalance.
  *
  * Description:
  * Check if we have potential to perform some power-savings balance.
@@ -3591,8 +3590,8 @@ static inline void update_sd_power_savings_stats(struct sched_group *group,
  * Returns 1 if there is potential to perform power-savings balance.
  * Else returns 0.
  */
-static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
-                                        int this_cpu, unsigned long *imbalance)
+static inline
+int check_power_save_busiest_group(struct lb_env *env, struct sd_lb_stats *sds)
 {
         if (!sds->power_savings_balance)
                 return 0;
@@ -3601,7 +3600,7 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
                         sds->group_leader == sds->group_min)
                 return 0;
 
-        *imbalance = sds->min_load_per_task;
+        env->imbalance = sds->min_load_per_task;
         sds->busiest = sds->group_min;
 
         return 1;
@@ -3620,8 +3619,8 @@ static inline void update_sd_power_savings_stats(struct sched_group *group,
         return;
 }
 
-static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
-                                        int this_cpu, unsigned long *imbalance)
+static inline
+int check_power_save_busiest_group(struct lb_env *env, struct sd_lb_stats *sds)
 {
         return 0;
 }
@@ -3765,24 +3764,22 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
  * @sd: The sched_domain whose statistics are to be updated.
  * @group: sched_group whose statistics are to be updated.
- * @this_cpu: Cpu for which load balance is currently performed.
- * @idle: Idle status of this_cpu
  * @load_idx: Load index of sched_domain of this_cpu for load calc.
  * @local_group: Does group contain this_cpu.
  * @cpus: Set of cpus considered for load balancing.
  * @balance: Should we balance.
  * @sgs: variable to hold the statistics for this group.
  */
-static inline void update_sg_lb_stats(struct sched_domain *sd,
-                        struct sched_group *group, int this_cpu,
-                        enum cpu_idle_type idle, int load_idx,
+static inline void update_sg_lb_stats(struct lb_env *env,
+                        struct sched_group *group, int load_idx,
                         int local_group, const struct cpumask *cpus,
                         int *balance, struct sg_lb_stats *sgs)
 {
-        unsigned long load, max_cpu_load, min_cpu_load, max_nr_running;
-        int i;
+        unsigned long nr_running, max_nr_running, min_nr_running;
+        unsigned long load, max_cpu_load, min_cpu_load;
         unsigned int balance_cpu = -1, first_idle_cpu = 0;
         unsigned long avg_load_per_task = 0;
+        int i;
 
         if (local_group)
                 balance_cpu = group_first_cpu(group);
@@ -3791,10 +3788,13 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         max_cpu_load = 0;
         min_cpu_load = ~0UL;
         max_nr_running = 0;
+        min_nr_running = ~0UL;
 
         for_each_cpu_and(i, sched_group_cpus(group), cpus) {
                 struct rq *rq = cpu_rq(i);
 
+                nr_running = rq->nr_running;
+
                 /* Bias balancing toward cpus of our domain */
                 if (local_group) {
                         if (idle_cpu(i) && !first_idle_cpu) {
@@ -3805,16 +3805,19 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
                         load = target_load(i, load_idx);
                 } else {
                         load = source_load(i, load_idx);
-                        if (load > max_cpu_load) {
+                        if (load > max_cpu_load)
                                 max_cpu_load = load;
-                                max_nr_running = rq->nr_running;
-                        }
                         if (min_cpu_load > load)
                                 min_cpu_load = load;
+
+                        if (nr_running > max_nr_running)
+                                max_nr_running = nr_running;
+                        if (min_nr_running > nr_running)
+                                min_nr_running = nr_running;
                 }
 
                 sgs->group_load += load;
-                sgs->sum_nr_running += rq->nr_running;
+                sgs->sum_nr_running += nr_running;
                 sgs->sum_weighted_load += weighted_cpuload(i);
                 if (idle_cpu(i))
                         sgs->idle_cpus++;
@@ -3827,14 +3830,14 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
          * to do the newly idle load balance.
          */
         if (local_group) {
-                if (idle != CPU_NEWLY_IDLE) {
-                        if (balance_cpu != this_cpu) {
+                if (env->idle != CPU_NEWLY_IDLE) {
+                        if (balance_cpu != env->dst_cpu) {
                                 *balance = 0;
                                 return;
                         }
-                        update_group_power(sd, this_cpu);
+                        update_group_power(env->sd, env->dst_cpu);
                 } else if (time_after_eq(jiffies, group->sgp->next_update))
-                        update_group_power(sd, this_cpu);
+                        update_group_power(env->sd, env->dst_cpu);
         }
 
         /* Adjust by relative CPU power of the group */
@@ -3852,13 +3855,14 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         if (sgs->sum_nr_running)
                 avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
-        if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
+        if ((max_cpu_load - min_cpu_load) >= avg_load_per_task &&
+            (max_nr_running - min_nr_running) > 1)
                 sgs->group_imb = 1;
 
         sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power,
                                                 SCHED_POWER_SCALE);
         if (!sgs->group_capacity)
-                sgs->group_capacity = fix_small_capacity(sd, group);
+                sgs->group_capacity = fix_small_capacity(env->sd, group);
         sgs->group_weight = group->group_weight;
 
         if (sgs->group_capacity > sgs->sum_nr_running)
@@ -3876,11 +3880,10 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
  * Determine if @sg is a busier group than the previously selected
  * busiest group.
  */
-static bool update_sd_pick_busiest(struct sched_domain *sd,
+static bool update_sd_pick_busiest(struct lb_env *env,
                                    struct sd_lb_stats *sds,
                                    struct sched_group *sg,
-                                   struct sg_lb_stats *sgs,
-                                   int this_cpu)
+                                   struct sg_lb_stats *sgs)
 {
         if (sgs->avg_load <= sds->max_load)
                 return false;
@@ -3896,8 +3899,8 @@ static bool update_sd_pick_busiest(struct sched_domain *sd,
          * numbered CPUs in the group, therefore mark all groups
          * higher than ourself as busy.
          */
-        if ((sd->flags & SD_ASYM_PACKING) && sgs->sum_nr_running &&
-            this_cpu < group_first_cpu(sg)) {
+        if ((env->sd->flags & SD_ASYM_PACKING) && sgs->sum_nr_running &&
+            env->dst_cpu < group_first_cpu(sg)) {
                 if (!sds->busiest)
                         return true;
 
@@ -3917,28 +3920,28 @@ static bool update_sd_pick_busiest(struct sched_domain *sd,
  * @balance: Should we balance.
  * @sds: variable to hold the statistics for this sched_domain.
  */
-static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
-                        enum cpu_idle_type idle, const struct cpumask *cpus,
-                        int *balance, struct sd_lb_stats *sds)
+static inline void update_sd_lb_stats(struct lb_env *env,
+                                      const struct cpumask *cpus,
+                                      int *balance, struct sd_lb_stats *sds)
 {
-        struct sched_domain *child = sd->child;
-        struct sched_group *sg = sd->groups;
+        struct sched_domain *child = env->sd->child;
+        struct sched_group *sg = env->sd->groups;
         struct sg_lb_stats sgs;
         int load_idx, prefer_sibling = 0;
 
         if (child && child->flags & SD_PREFER_SIBLING)
                 prefer_sibling = 1;
 
-        init_sd_power_savings_stats(sd, sds, idle);
-        load_idx = get_sd_load_idx(sd, idle);
+        init_sd_power_savings_stats(env->sd, sds, env->idle);
+        load_idx = get_sd_load_idx(env->sd, env->idle);
 
         do {
                 int local_group;
 
-                local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg));
+                local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
                 memset(&sgs, 0, sizeof(sgs));
-                update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx,
-                                local_group, cpus, balance, &sgs);
+                update_sg_lb_stats(env, sg, load_idx, local_group,
+                                   cpus, balance, &sgs);
 
                 if (local_group && !(*balance))
                         return;
@@ -3966,7 +3969,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                         sds->this_load_per_task = sgs.sum_weighted_load;
                         sds->this_has_capacity = sgs.group_has_capacity;
                         sds->this_idle_cpus = sgs.idle_cpus;
-                } else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
+                } else if (update_sd_pick_busiest(env, sds, sg, &sgs)) {
                         sds->max_load = sgs.avg_load;
                         sds->busiest = sg;
                         sds->busiest_nr_running = sgs.sum_nr_running;
@@ -3980,7 +3983,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 
                 update_sd_power_savings_stats(sg, sds, local_group, &sgs);
                 sg = sg->next;
-        } while (sg != sd->groups);
+        } while (sg != env->sd->groups);
 }
 
 /**
@@ -4008,24 +4011,23 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
  * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
  * @imbalance: returns amount of imbalanced due to packing.
  */
-static int check_asym_packing(struct sched_domain *sd,
-                              struct sd_lb_stats *sds,
-                              int this_cpu, unsigned long *imbalance)
+static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
 {
         int busiest_cpu;
 
-        if (!(sd->flags & SD_ASYM_PACKING))
+        if (!(env->sd->flags & SD_ASYM_PACKING))
                 return 0;
 
         if (!sds->busiest)
                 return 0;
 
         busiest_cpu = group_first_cpu(sds->busiest);
-        if (this_cpu > busiest_cpu)
+        if (env->dst_cpu > busiest_cpu)
                 return 0;
 
-        *imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->sgp->power,
-                                       SCHED_POWER_SCALE);
+        env->imbalance = DIV_ROUND_CLOSEST(
+                sds->max_load * sds->busiest->sgp->power, SCHED_POWER_SCALE);
+
         return 1;
 }
 
@@ -4037,8 +4039,8 @@ static int check_asym_packing(struct sched_domain *sd,
  * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
  * @imbalance: Variable to store the imbalance.
  */
-static inline void fix_small_imbalance(struct sd_lb_stats *sds,
-                                int this_cpu, unsigned long *imbalance)
+static inline
+void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 {
         unsigned long tmp, pwr_now = 0, pwr_move = 0;
         unsigned int imbn = 2;
@@ -4049,9 +4051,10 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
                 if (sds->busiest_load_per_task >
                                 sds->this_load_per_task)
                         imbn = 1;
-        } else
+        } else {
                 sds->this_load_per_task =
-                        cpu_avg_load_per_task(this_cpu);
+                        cpu_avg_load_per_task(env->dst_cpu);
+        }
 
         scaled_busy_load_per_task = sds->busiest_load_per_task
                                          * SCHED_POWER_SCALE;
@@ -4059,7 +4062,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 
         if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
                         (scaled_busy_load_per_task * imbn)) {
-                *imbalance = sds->busiest_load_per_task;
+                env->imbalance = sds->busiest_load_per_task;
                 return;
         }
 
@@ -4096,18 +4099,16 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 
         /* Move if we gain throughput */
         if (pwr_move > pwr_now)
-                *imbalance = sds->busiest_load_per_task;
+                env->imbalance = sds->busiest_load_per_task;
 }
 
 /**
  * calculate_imbalance - Calculate the amount of imbalance present within the
  *                       groups of a given sched_domain during load balance.
+ * @env: load balance environment
  * @sds: statistics of the sched_domain whose imbalance is to be calculated.
- * @this_cpu: Cpu for which currently load balance is being performed.
- * @imbalance: The variable to store the imbalance.
  */
-static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
-                unsigned long *imbalance)
+static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 {
         unsigned long max_pull, load_above_capacity = ~0UL;
 
@@ -4123,8 +4124,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
          * its cpu_power, while calculating max_load..)
          */
         if (sds->max_load < sds->avg_load) {
-                *imbalance = 0;
-                return fix_small_imbalance(sds, this_cpu, imbalance);
+                env->imbalance = 0;
+                return fix_small_imbalance(env, sds);
         }
 
         if (!sds->group_imb) {
@@ -4152,7 +4153,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
         max_pull = min(sds->max_load - sds->avg_load, load_above_capacity);
 
         /* How much load to actually move to equalise the imbalance */
-        *imbalance = min(max_pull * sds->busiest->sgp->power,
+        env->imbalance = min(max_pull * sds->busiest->sgp->power,
                 (sds->avg_load - sds->this_load) * sds->this->sgp->power)
                         / SCHED_POWER_SCALE;
 
@@ -4162,8 +4163,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
          * a think about bumping its value to force at least one task to be
          * moved
          */
-        if (*imbalance < sds->busiest_load_per_task)
-                return fix_small_imbalance(sds, this_cpu, imbalance);
+        if (env->imbalance < sds->busiest_load_per_task)
+                return fix_small_imbalance(env, sds);
 
 }
 
@@ -4194,9 +4195,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
  *                 put to idle by rebalancing its tasks onto our group.
  */
 static struct sched_group *
-find_busiest_group(struct sched_domain *sd, int this_cpu,
-                   unsigned long *imbalance, enum cpu_idle_type idle,
-                   const struct cpumask *cpus, int *balance)
+find_busiest_group(struct lb_env *env, const struct cpumask *cpus, int *balance)
 {
         struct sd_lb_stats sds;
 
@@ -4206,7 +4205,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
          * Compute the various statistics relavent for load balancing at
          * this level.
          */
-        update_sd_lb_stats(sd, this_cpu, idle, cpus, balance, &sds);
+        update_sd_lb_stats(env, cpus, balance, &sds);
 
         /*
          * this_cpu is not the appropriate cpu to perform load balancing at
@@ -4215,8 +4214,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (!(*balance))
                 goto ret;
 
-        if ((idle == CPU_IDLE || idle == CPU_NEWLY_IDLE) &&
-            check_asym_packing(sd, &sds, this_cpu, imbalance))
+        if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) &&
+            check_asym_packing(env, &sds))
                 return sds.busiest;
 
         /* There is no busy sibling group to pull tasks from */
@@ -4234,7 +4233,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
                 goto force_balance;
 
         /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
-        if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
+        if (env->idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
                         !sds.busiest_has_capacity)
                 goto force_balance;
 
@@ -4252,7 +4251,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (sds.this_load >= sds.avg_load)
                 goto out_balanced;
 
-        if (idle == CPU_IDLE) {
+        if (env->idle == CPU_IDLE) {
                 /*
                  * This cpu is idle. If the busiest group load doesn't
                  * have more tasks than the number of available cpu's and
@@ -4267,13 +4266,13 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
                  * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
                  * imbalance_pct to be conservative.
                  */
-                if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+                if (100 * sds.max_load <= env->sd->imbalance_pct * sds.this_load)
                         goto out_balanced;
         }
 
 force_balance:
         /* Looks like there is an imbalance. Compute it */
-        calculate_imbalance(&sds, this_cpu, imbalance);
+        calculate_imbalance(env, &sds);
         return sds.busiest;
 
 out_balanced:
@@ -4281,20 +4280,19 @@ out_balanced:
          * There is no obvious imbalance. But check if we can do some balancing
          * to save power.
          */
-        if (check_power_save_busiest_group(&sds, this_cpu, imbalance))
+        if (check_power_save_busiest_group(env, &sds))
                 return sds.busiest;
 ret:
-        *imbalance = 0;
+        env->imbalance = 0;
         return NULL;
 }
 
 /*
  * find_busiest_queue - find the busiest runqueue among the cpus in group.
  */
-static struct rq *
-find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
-                   enum cpu_idle_type idle, unsigned long imbalance,
-                   const struct cpumask *cpus)
+static struct rq *find_busiest_queue(struct lb_env *env,
+                                     struct sched_group *group,
+                                     const struct cpumask *cpus)
 {
         struct rq *busiest = NULL, *rq;
         unsigned long max_load = 0;
@@ -4307,7 +4305,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
                 unsigned long wl;
 
                 if (!capacity)
-                        capacity = fix_small_capacity(sd, group);
+                        capacity = fix_small_capacity(env->sd, group);
 
                 if (!cpumask_test_cpu(i, cpus))
                         continue;
@@ -4319,7 +4317,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
                  * When comparing with imbalance, use weighted_cpuload()
                  * which is not scaled with the cpu power.
                  */
-                if (capacity && rq->nr_running == 1 && wl > imbalance)
+                if (capacity && rq->nr_running == 1 && wl > env->imbalance)
                         continue;
 
                 /*
@@ -4348,17 +4346,18 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
 /* Working cpumask for load_balance and load_balance_newidle. */
 DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
 
-static int need_active_balance(struct sched_domain *sd, int idle,
-                               int busiest_cpu, int this_cpu)
+static int need_active_balance(struct lb_env *env)
 {
-        if (idle == CPU_NEWLY_IDLE) {
+        struct sched_domain *sd = env->sd;
+
+        if (env->idle == CPU_NEWLY_IDLE) {
 
                 /*
                  * ASYM_PACKING needs to force migrate tasks from busy but
                  * higher numbered CPUs in order to pack all tasks in the
                  * lowest numbered CPUs.
                  */
-                if ((sd->flags & SD_ASYM_PACKING) && busiest_cpu > this_cpu)
+                if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu)
                         return 1;
 
                 /*
@@ -4399,7 +4398,6 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 {
         int ld_moved, active_balance = 0;
         struct sched_group *group;
-        unsigned long imbalance;
         struct rq *busiest;
         unsigned long flags;
         struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
@@ -4417,8 +4415,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
         schedstat_inc(sd, lb_count[idle]);
 
 redo:
-        group = find_busiest_group(sd, this_cpu, &imbalance, idle,
-                                   cpus, balance);
+        group = find_busiest_group(&env, cpus, balance);
 
         if (*balance == 0)
                 goto out_balanced;
@@ -4428,7 +4425,7 @@ redo:
                 goto out_balanced;
         }
 
-        busiest = find_busiest_queue(sd, group, idle, imbalance, cpus);
+        busiest = find_busiest_queue(&env, group, cpus);
         if (!busiest) {
                 schedstat_inc(sd, lb_nobusyq[idle]);
                 goto out_balanced;
@@ -4436,7 +4433,7 @@ redo:
 
         BUG_ON(busiest == this_rq);
 
-        schedstat_add(sd, lb_imbalance[idle], imbalance);
+        schedstat_add(sd, lb_imbalance[idle], env.imbalance);
 
         ld_moved = 0;
         if (busiest->nr_running > 1) {
@@ -4447,10 +4444,9 @@ redo:
                  * correctly treated as an imbalance.
                  */
                 env.flags |= LBF_ALL_PINNED;
-                env.load_move   = imbalance;
-                env.src_cpu     = busiest->cpu;
-                env.src_rq      = busiest;
-                env.loop_max    = min_t(unsigned long, sysctl_sched_nr_migrate, busiest->nr_running);
+                env.src_cpu   = busiest->cpu;
+                env.src_rq    = busiest;
+                env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
                 local_irq_save(flags);
@@ -4492,7 +4488,7 @@ more_balance:
                 if (idle != CPU_NEWLY_IDLE)
                         sd->nr_balance_failed++;
 
-                if (need_active_balance(sd, idle, cpu_of(busiest), this_cpu)) {
+                if (need_active_balance(&env)) {
                         raw_spin_lock_irqsave(&busiest->lock, flags);
 
                         /* don't kick the active_load_balance_cpu_stop,
@@ -4519,10 +4515,11 @@ more_balance:
                         }
                         raw_spin_unlock_irqrestore(&busiest->lock, flags);
 
-                        if (active_balance)
+                        if (active_balance) {
                                 stop_one_cpu_nowait(cpu_of(busiest),
                                         active_load_balance_cpu_stop, busiest,
                                         &busiest->active_balance_work);
+                        }
 
                         /*
                          * We've kicked active balancing, reset the failure
@@ -5023,7 +5020,7 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
 
                 raw_spin_lock_irq(&this_rq->lock);
                 update_rq_clock(this_rq);
-                update_cpu_load(this_rq);
+                update_idle_cpu_load(this_rq);
                 raw_spin_unlock_irq(&this_rq->lock);
 
                 rebalance_domains(balance_cpu, CPU_IDLE);
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 91b4c957f289..b44d604b35d1 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -4,7 +4,7 @@
  * idle-task scheduling class.
  *
  * (NOTE: these are not related to SCHED_IDLE tasks which are
- *  handled in sched_fair.c)
+ *  handled in sched/fair.c)
  */
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 44af55e6d5d0..c5565c3c515f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1803,44 +1803,40 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 static void set_cpus_allowed_rt(struct task_struct *p,
                                 const struct cpumask *new_mask)
 {
-        int weight = cpumask_weight(new_mask);
+        struct rq *rq;
+        int weight;
 
         BUG_ON(!rt_task(p));
 
-        /*
-         * Update the migration status of the RQ if we have an RT task
-         * which is running AND changing its weight value.
-         */
-        if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) {
-                struct rq *rq = task_rq(p);
-
-                if (!task_current(rq, p)) {
-                        /*
-                         * Make sure we dequeue this task from the pushable list
-                         * before going further.  It will either remain off of
-                         * the list because we are no longer pushable, or it
-                         * will be requeued.
-                         */
-                        if (p->rt.nr_cpus_allowed > 1)
-                                dequeue_pushable_task(rq, p);
+        if (!p->on_rq)
+                return;
 
-                        /*
-                         * Requeue if our weight is changing and still > 1
-                         */
-                        if (weight > 1)
-                                enqueue_pushable_task(rq, p);
+        weight = cpumask_weight(new_mask);
 
-                }
+        /*
+         * Only update if the process changes its state from whether it
+         * can migrate or not.
+         */
+        if ((p->rt.nr_cpus_allowed > 1) == (weight > 1))
+                return;
 
-                if ((p->rt.nr_cpus_allowed <= 1) && (weight > 1)) {
-                        rq->rt.rt_nr_migratory++;
-                } else if ((p->rt.nr_cpus_allowed > 1) && (weight <= 1)) {
-                        BUG_ON(!rq->rt.rt_nr_migratory);
-                        rq->rt.rt_nr_migratory--;
-                }
+        rq = task_rq(p);
 
-                update_rt_migration(&rq->rt);
+        /*
+         * The process used to be able to migrate OR it can now migrate
+         */
+        if (weight <= 1) {
+                if (!task_current(rq, p))
+                        dequeue_pushable_task(rq, p);
+                BUG_ON(!rq->rt.rt_nr_migratory);
+                rq->rt.rt_nr_migratory--;
+        } else {
+                if (!task_current(rq, p))
+                        enqueue_pushable_task(rq, p);
+                rq->rt.rt_nr_migratory++;
         }
+
+        update_rt_migration(&rq->rt);
 }
 
 /* Assumes rq->lock is held */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fb3acba4d52e..ba9dccfd24ce 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -201,7 +201,7 @@ struct cfs_bandwidth { };
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
         struct load_weight load;
-        unsigned long nr_running, h_nr_running;
+        unsigned int nr_running, h_nr_running;
 
         u64 exec_clock;
         u64 min_vruntime;
@@ -279,7 +279,7 @@ static inline int rt_bandwidth_enabled(void)
 /* Real-Time classes' related field in a runqueue: */
 struct rt_rq {
         struct rt_prio_array active;
-        unsigned long rt_nr_running;
+        unsigned int rt_nr_running;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
         struct {
                 int curr; /* highest queued rt task prio */
@@ -353,7 +353,7 @@ struct rq {
          * nr_running and cpu_load should be in the same cacheline because
          * remote CPUs use both these fields when doing load calculation.
          */
-        unsigned long nr_running;
+        unsigned int nr_running;
         #define CPU_LOAD_IDX_MAX 5
         unsigned long cpu_load[CPU_LOAD_IDX_MAX];
         unsigned long last_load_update_tick;
@@ -876,7 +876,7 @@ extern void resched_cpu(int cpu);
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 
-extern void update_cpu_load(struct rq *this_rq);
+extern void update_idle_cpu_load(struct rq *this_rq);
 
 #ifdef CONFIG_CGROUP_CPUACCT
 #include <linux/cgroup.h>