[PATCH v2] sched: fix hierarchical order in rq->leaf_cfs_rq_list

[Vincent Guittot]

Fix the insertion of cfs_rq in rq->leaf_cfs_rq_list to ensure that
a child will always called before its parent.

The hierarchical order in shares update list has been introduced by
commit 67e86250f8ea ("sched: Introduce hierarchal order on shares update list")

With the current implementation a child can be still put after its parent.

Lets take the example of
       root
         \
          b
          /\
          c d*
            |
            e*

with root -> b -> c already enqueued but not d -> e so the leaf_cfs_rq_list
looks like: head -> c -> b -> root -> tail

The branch d -> e will be added the first time that they are enqueued,
starting with e then d.

When e is added, its parents is not already on the list so e is put at the
tail : head -> c -> b -> root -> e -> tail

Then, d is added at the head because its parent is already on the list:
head -> d -> c -> b -> root -> e -> tail

e is not placed at the right position and will be called the last whereas
it should be called at the beginning.

Because it follows the bottom-up enqueue sequence, we are sure that we
will finished to add either a cfs_rq without parent or a cfs_rq with a parent
that is already on the list. We can use this event to detect when we have
finished to add a new branch. For the others, whose parents are not already
added, we have to ensure that they will be added after their children that
have just been inserted the steps before, and after any potential parents that
are already in the list. The easiest way is to put the cfs_rq just after the
last inserted one and to keep track of it until the branch is fully added.

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---

v2:
- Add comments
- rename leaf_alone to tmp_alone_branch

 kernel/sched/core.c  |  1 +
 kernel/sched/fair.c  | 54 +++++++++++++++++++++++++++++++++++++++++++++-------
 kernel/sched/sched.h |  1 +
 3 files changed, 49 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 404c078..935267b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7386,6 +7386,7 @@ void __init sched_init(void)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
+		rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
 		/*
 		 * How much cpu bandwidth does root_task_group get?
 		 *
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 218f8e8..1a93c4e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -286,19 +286,59 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
 static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	if (!cfs_rq->on_list) {
+		struct rq *rq = rq_of(cfs_rq);
+		int cpu = cpu_of(rq);
 		/*
 		 * Ensure we either appear before our parent (if already
 		 * enqueued) or force our parent to appear after us when it is
-		 * enqueued.  The fact that we always enqueue bottom-up
-		 * reduces this to two cases.
+		 * enqueued. The fact that we always enqueue bottom-up
+		 * reduces this to two cases and a special case for the root
+		 * cfs_rq. Furthermore, it also means that we will always reset
+		 * tmp_alone_branch either when the branch is connected
+		 * to a tree or when we reach the beg of the tree
 		 */
 		if (cfs_rq->tg->parent &&
-		    cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) {
-			list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
-				&rq_of(cfs_rq)->leaf_cfs_rq_list);
-		} else {
+		    cfs_rq->tg->parent->cfs_rq[cpu]->on_list) {
+			/*
+			 * If parent is already on the list, we add the child
+			 * just before. Thanks to circular linked property of
+			 * the list, this means to put the child at the tail
+			 * of the list that starts by parent.
+			 */
+			list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
+				&(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list));
+			/*
+			 * The branch is now connected to its tree so we can
+			 * reset tmp_alone_branch to the beginning of the
+			 * list.
+			 */
+			rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+		} else if (!cfs_rq->tg->parent) {
+			/*
+			 * cfs rq without parent should be put
+			 * at the tail of the list.
+			 */
 			list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
-				&rq_of(cfs_rq)->leaf_cfs_rq_list);
+				&rq->leaf_cfs_rq_list);
+			/*
+			 * We have reach the beg of a tree so we can reset
+			 * tmp_alone_branch to the beginning of the list.
+			 */
+			rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+		} else {
+			/*
+			 * The parent has not already been added so we want to
+			 * make sure that it will be put after us.
+			 * tmp_alone_branch points to the beg of the branch
+			 * where we will add parent.
+			 */
+			list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
+				rq->tmp_alone_branch);
+			/*
+			 * upodate tmp_alone_branch to points to the new beg
+			 * of the branch
+			 */
+			rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list;
 		}
 
 		cfs_rq->on_list = 1;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e51145e..00cecd6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -614,6 +614,7 @@ struct rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this cpu: */
 	struct list_head leaf_cfs_rq_list;
+	struct list_head *tmp_alone_branch;
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 	/*
-- 
1.9.1