1 files changed, 65 insertions, 53 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 433491c2dc8f..bc8ee9993814 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -135,14 +135,6 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
         return grp->my_q;
 }
 
-/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
- * another cpu ('this_cpu')
- */
-static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
-{
-        return cfs_rq->tg->cfs_rq[this_cpu];
-}
-
 static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
         if (!cfs_rq->on_list) {
@@ -271,11 +263,6 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
         return NULL;
 }
 
-static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
-{
-        return &cpu_rq(this_cpu)->cfs;
-}
-
 static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 }
@@ -334,11 +321,6 @@ static inline int entity_before(struct sched_entity *a,
         return (s64)(a->vruntime - b->vruntime) < 0;
 }
 
-static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-        return se->vruntime - cfs_rq->min_vruntime;
-}
-
 static void update_min_vruntime(struct cfs_rq *cfs_rq)
 {
         u64 vruntime = cfs_rq->min_vruntime;
@@ -372,7 +354,6 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
         struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
         struct rb_node *parent = NULL;
         struct sched_entity *entry;
-        s64 key = entity_key(cfs_rq, se);
         int leftmost = 1;
 
         /*
@@ -385,7 +366,7 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
                  * We dont care about collisions. Nodes with
                  * the same key stay together.
                  */
-                if (key < entity_key(cfs_rq, entry)) {
+                if (entity_before(se, entry)) {
                         link = &parent->rb_left;
                 } else {
                         link = &parent->rb_right;
@@ -1336,7 +1317,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
         }
 
         for_each_sched_entity(se) {
-                struct cfs_rq *cfs_rq = cfs_rq_of(se);
+                cfs_rq = cfs_rq_of(se);
 
                 update_cfs_load(cfs_rq, 0);
                 update_cfs_shares(cfs_rq);
@@ -1370,13 +1351,16 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
                          */
                         if (task_sleep && parent_entity(se))
                                 set_next_buddy(parent_entity(se));
+
+                        /* avoid re-evaluating load for this entity */
+                        se = parent_entity(se);
                         break;
                 }
                 flags |= DEQUEUE_SLEEP;
         }
 
         for_each_sched_entity(se) {
-                struct cfs_rq *cfs_rq = cfs_rq_of(se);
+                cfs_rq = cfs_rq_of(se);
 
                 update_cfs_load(cfs_rq, 0);
                 update_cfs_shares(cfs_rq);
@@ -1481,7 +1465,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
          * effect of the currently running task from the load
          * of the current CPU:
          */
-        rcu_read_lock();
         if (sync) {
                 tg = task_group(current);
                 weight = current->se.load.weight;
@@ -1517,7 +1500,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
                 balanced = this_eff_load <= prev_eff_load;
         } else
                 balanced = true;
-        rcu_read_unlock();
 
         /*
          * If the currently running task will sleep within
@@ -1585,7 +1567,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
                 }
 
                 /* Adjust by relative CPU power of the group */
-                avg_load = (avg_load * SCHED_POWER_SCALE) / group->cpu_power;
+                avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power;
 
                 if (local_group) {
                         this_load = avg_load;
@@ -1921,8 +1903,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
         if (!sched_feat(WAKEUP_PREEMPT))
                 return;
 
-        update_curr(cfs_rq);
         find_matching_se(&se, &pse);
+        update_curr(cfs_rq_of(se));
         BUG_ON(!pse);
         if (wakeup_preempt_entity(se, pse) == 1) {
                 /*
@@ -2231,11 +2213,43 @@ static void update_shares(int cpu)
         struct rq *rq = cpu_rq(cpu);
 
         rcu_read_lock();
+        /*
+         * Iterates the task_group tree in a bottom up fashion, see
+         * list_add_leaf_cfs_rq() for details.
+         */
         for_each_leaf_cfs_rq(rq, cfs_rq)
                 update_shares_cpu(cfs_rq->tg, cpu);
         rcu_read_unlock();
 }
 
+/*
+ * 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
+ * group is a fraction of its parents load.
+ */
+static int tg_load_down(struct task_group *tg, void *data)
+{
+        unsigned long load;
+        long cpu = (long)data;
+
+        if (!tg->parent) {
+                load = cpu_rq(cpu)->load.weight;
+        } else {
+                load = tg->parent->cfs_rq[cpu]->h_load;
+                load *= tg->se[cpu]->load.weight;
+                load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
+        }
+
+        tg->cfs_rq[cpu]->h_load = load;
+
+        return 0;
+}
+
+static void update_h_load(long cpu)
+{
+        walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
+}
+
 static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
                   unsigned long max_load_move,
@@ -2243,14 +2257,12 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
                   int *all_pinned)
 {
         long rem_load_move = max_load_move;
-        int busiest_cpu = cpu_of(busiest);
-        struct task_group *tg;
+        struct cfs_rq *busiest_cfs_rq;
 
         rcu_read_lock();
-        update_h_load(busiest_cpu);
+        update_h_load(cpu_of(busiest));
 
-        list_for_each_entry_rcu(tg, &task_groups, list) {
-                struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
+        for_each_leaf_cfs_rq(busiest, busiest_cfs_rq) {
                 unsigned long busiest_h_load = busiest_cfs_rq->h_load;
                 unsigned long busiest_weight = busiest_cfs_rq->load.weight;
                 u64 rem_load, moved_load;
@@ -2631,7 +2643,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
                 power >>= SCHED_POWER_SHIFT;
         }
 
-        sdg->cpu_power_orig = power;
+        sdg->sgp->power_orig = power;
 
         if (sched_feat(ARCH_POWER))
                 power *= arch_scale_freq_power(sd, cpu);
@@ -2647,7 +2659,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
                 power = 1;
 
         cpu_rq(cpu)->cpu_power = power;
-        sdg->cpu_power = power;
+        sdg->sgp->power = power;
 }
 
 static void update_group_power(struct sched_domain *sd, int cpu)
@@ -2665,11 +2677,11 @@ static void update_group_power(struct sched_domain *sd, int cpu)
 
         group = child->groups;
         do {
-                power += group->cpu_power;
+                power += group->sgp->power;
                 group = group->next;
         } while (group != child->groups);
 
-        sdg->cpu_power = power;
+        sdg->sgp->power = power;
 }
 
 /*
@@ -2691,7 +2703,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
         /*
          * If ~90% of the cpu_power is still there, we're good.
          */
-        if (group->cpu_power * 32 > group->cpu_power_orig * 29)
+        if (group->sgp->power * 32 > group->sgp->power_orig * 29)
                 return 1;
 
         return 0;
@@ -2771,7 +2783,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         }
 
         /* Adjust by relative CPU power of the group */
-        sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->cpu_power;
+        sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->sgp->power;
 
         /*
          * Consider the group unbalanced when the imbalance is larger
@@ -2788,7 +2800,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
                 sgs->group_imb = 1;
 
-        sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power,
+        sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power,
                                                 SCHED_POWER_SCALE);
         if (!sgs->group_capacity)
                 sgs->group_capacity = fix_small_capacity(sd, group);
@@ -2877,7 +2889,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                         return;
 
                 sds->total_load += sgs.group_load;
-                sds->total_pwr += sg->cpu_power;
+                sds->total_pwr += sg->sgp->power;
 
                 /*
                  * In case the child domain prefers tasks go to siblings
@@ -2962,7 +2974,7 @@ static int check_asym_packing(struct sched_domain *sd,
         if (this_cpu > busiest_cpu)
                 return 0;
 
-        *imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->cpu_power,
+        *imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->sgp->power,
                                        SCHED_POWER_SCALE);
         return 1;
 }
@@ -2993,7 +3005,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 
         scaled_busy_load_per_task = sds->busiest_load_per_task
                                          * SCHED_POWER_SCALE;
-        scaled_busy_load_per_task /= sds->busiest->cpu_power;
+        scaled_busy_load_per_task /= sds->busiest->sgp->power;
 
         if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
                         (scaled_busy_load_per_task * imbn)) {
@@ -3007,28 +3019,28 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
          * moving them.
          */
 
-        pwr_now += sds->busiest->cpu_power *
+        pwr_now += sds->busiest->sgp->power *
                         min(sds->busiest_load_per_task, sds->max_load);
-        pwr_now += sds->this->cpu_power *
+        pwr_now += sds->this->sgp->power *
                         min(sds->this_load_per_task, sds->this_load);
         pwr_now /= SCHED_POWER_SCALE;
 
         /* Amount of load we'd subtract */
         tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) /
-                sds->busiest->cpu_power;
+                sds->busiest->sgp->power;
         if (sds->max_load > tmp)
-                pwr_move += sds->busiest->cpu_power *
+                pwr_move += sds->busiest->sgp->power *
                         min(sds->busiest_load_per_task, sds->max_load - tmp);
 
         /* Amount of load we'd add */
-        if (sds->max_load * sds->busiest->cpu_power <
+        if (sds->max_load * sds->busiest->sgp->power <
                 sds->busiest_load_per_task * SCHED_POWER_SCALE)
-                tmp = (sds->max_load * sds->busiest->cpu_power) /
-                        sds->this->cpu_power;
+                tmp = (sds->max_load * sds->busiest->sgp->power) /
+                        sds->this->sgp->power;
         else
                 tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) /
-                        sds->this->cpu_power;
-        pwr_move += sds->this->cpu_power *
+                        sds->this->sgp->power;
+        pwr_move += sds->this->sgp->power *
                         min(sds->this_load_per_task, sds->this_load + tmp);
         pwr_move /= SCHED_POWER_SCALE;
 
@@ -3074,7 +3086,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 
                 load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE);
 
-                load_above_capacity /= sds->busiest->cpu_power;
+                load_above_capacity /= sds->busiest->sgp->power;
         }
 
         /*
@@ -3090,8 +3102,8 @@ 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->cpu_power,
-                (sds->avg_load - sds->this_load) * sds->this->cpu_power)
+        *imbalance = min(max_pull * sds->busiest->sgp->power,
+                (sds->avg_load - sds->this_load) * sds->this->sgp->power)
                         / SCHED_POWER_SCALE;
 
         /*