Merge branch 'stable/bug.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git...

[pandora-kernel.git] / kernel / sched_fair.c

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c768588..bc8ee99 100644 (file)
--- 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
@@ -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;