sched/fair: Track cgroup depth

Track depth in cgroup tree, this is useful for things like
find_matching_se() where you need to get to a common parent of two
sched entities.

Keeping the depth avoids having to calculate it on the spot, which
saves a number of possible cache-misses.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1328936700.2476.17.camel@laptop
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 22 insertions, 26 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e3d556427b2e..555e27d717c0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1078,6 +1078,7 @@ struct sched_entity {
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+        int                     depth;
         struct sched_entity     *parent;
         /* rq on which this entity is (to be) queued: */
         struct cfs_rq           *cfs_rq;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 04fea7744a9f..748a7ac3388f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -322,13 +322,13 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
         list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
-static inline int
+static inline struct cfs_rq *
 is_same_group(struct sched_entity *se, struct sched_entity *pse)
 {
         if (se->cfs_rq == pse->cfs_rq)
-                return 1;
+                return se->cfs_rq;
 
-        return 0;
+        return NULL;
 }
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
@@ -336,17 +336,6 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
         return se->parent;
 }
 
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
-{
-        int depth = 0;
-
-        for_each_sched_entity(se)
-                depth++;
-
-        return depth;
-}
-
 static void
 find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 {
@@ -360,8 +349,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
          */
 
         /* First walk up until both entities are at same depth */
-        se_depth = depth_se(*se);
-        pse_depth = depth_se(*pse);
+        se_depth = (*se)->depth;
+        pse_depth = (*pse)->depth;
 
         while (se_depth > pse_depth) {
                 se_depth--;
@@ -426,10 +415,10 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 #define for_each_leaf_cfs_rq(rq, cfs_rq) \
                 for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
 
-static inline int
+static inline struct cfs_rq *
 is_same_group(struct sched_entity *se, struct sched_entity *pse)
 {
-        return 1;
+        return cfs_rq_of(se); /* always the same rq */
 }
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
@@ -7262,7 +7251,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void task_move_group_fair(struct task_struct *p, int on_rq)
 {
+        struct sched_entity *se = &p->se;
         struct cfs_rq *cfs_rq;
+
         /*
          * If the task was not on the rq at the time of this cgroup movement
          * it must have been asleep, sleeping tasks keep their ->vruntime
@@ -7288,23 +7279,24 @@ static void task_move_group_fair(struct task_struct *p, int on_rq)
          * To prevent boost or penalty in the new cfs_rq caused by delta
          * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
          */
-        if (!on_rq && (!p->se.sum_exec_runtime || p->state == TASK_WAKING))
+        if (!on_rq && (!se->sum_exec_runtime || p->state == TASK_WAKING))
                 on_rq = 1;
 
         if (!on_rq)
-                p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime;
+                se->vruntime -= cfs_rq_of(se)->min_vruntime;
         set_task_rq(p, task_cpu(p));
+        se->depth = se->parent ? se->parent->depth + 1 : 0;
         if (!on_rq) {
-                cfs_rq = cfs_rq_of(&p->se);
-                p->se.vruntime += cfs_rq->min_vruntime;
+                cfs_rq = cfs_rq_of(se);
+                se->vruntime += cfs_rq->min_vruntime;
 #ifdef CONFIG_SMP
                 /*
                  * migrate_task_rq_fair() will have removed our previous
                  * contribution, but we must synchronize for ongoing future
                  * decay.
                  */
-                p->se.avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
-                cfs_rq->blocked_load_avg += p->se.avg.load_avg_contrib;
+                se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
+                cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
 #endif
         }
 }
@@ -7400,10 +7392,13 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
         if (!se)
                 return;
 
-        if (!parent)
+        if (!parent) {
                 se->cfs_rq = &rq->cfs;
-        else
+                se->depth = 0;
+        } else {
                 se->cfs_rq = parent->my_q;
+                se->depth = parent->depth + 1;
+        }
 
         se->my_q = cfs_rq;
         /* guarantee group entities always have weight */