sched: more accurate min_vruntime accounting

Mike noticed the current min_vruntime tracking can go wrong and skip the
current task. If the only remaining task in the tree is a nice 19 task
with huge vruntime, new tasks will be inserted too far to the right too,
causing some interactibity issues.

min_vruntime can only change due to the leftmost entry disappearing
(dequeue_entity()), or by the leftmost entry being incremented past the
next entry, which elects a new leftmost (__update_curr())

Due to the current entry not being part of the actual tree, we have to
compare the leftmost tree entry with the current entry, and take the
leftmost of these two.

So create a update_min_vruntime() function that takes computes the
leftmost vruntime in the system (either tree of current) and increases
the cfs_rq->min_vruntime if the computed value is larger than the
previously found min_vruntime. And call this from the two sites we've
identified that can change min_vruntime.

Reported-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 25 insertions, 24 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 42d211f08c94..b27ccc52f6aa 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -223,6 +223,27 @@ 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;
+
+	if (cfs_rq->curr)
+		vruntime = cfs_rq->curr->vruntime;
+
+	if (cfs_rq->rb_leftmost) {
+		struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost,
+						   struct sched_entity,
+						   run_node);
+
+		if (vruntime == cfs_rq->min_vruntime)
+			vruntime = se->vruntime;
+		else
+			vruntime = min_vruntime(vruntime, se->vruntime);
+	}
+
+	cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
+}
+
 /*
  * Enqueue an entity into the rb-tree:
  */
@@ -256,15 +277,8 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * Maintain a cache of leftmost tree entries (it is frequently
 	 * used):
 	 */
-	if (leftmost) {
+	if (leftmost)
 		cfs_rq->rb_leftmost = &se->run_node;
-		/*
-		 * maintain cfs_rq->min_vruntime to be a monotonic increasing
-		 * value tracking the leftmost vruntime in the tree.
-		 */
-		cfs_rq->min_vruntime =
-			max_vruntime(cfs_rq->min_vruntime, se->vruntime);
-	}
 
 	rb_link_node(&se->run_node, parent, link);
 	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
@@ -274,18 +288,9 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (cfs_rq->rb_leftmost == &se->run_node) {
 		struct rb_node *next_node;
-		struct sched_entity *next;
 
 		next_node = rb_next(&se->run_node);
 		cfs_rq->rb_leftmost = next_node;
-
-		if (next_node) {
-			next = rb_entry(next_node,
-					struct sched_entity, run_node);
-			cfs_rq->min_vruntime =
-				max_vruntime(cfs_rq->min_vruntime,
-					     next->vruntime);
-		}
 	}
 
 	if (cfs_rq->next == se)
@@ -424,6 +429,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 	schedstat_add(cfs_rq, exec_clock, delta_exec);
 	delta_exec_weighted = calc_delta_fair(delta_exec, curr);
 	curr->vruntime += delta_exec_weighted;
+	update_min_vruntime(cfs_rq);
 }
 
 static void update_curr(struct cfs_rq *cfs_rq)
@@ -613,13 +619,7 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
-	u64 vruntime;
-
-	if (first_fair(cfs_rq)) {
-		vruntime = min_vruntime(cfs_rq->min_vruntime,
-				__pick_next_entity(cfs_rq)->vruntime);
-	} else
-		vruntime = cfs_rq->min_vruntime;
+	u64 vruntime = cfs_rq->min_vruntime;
 
 	/*
 	 * The 'current' period is already promised to the current tasks,
@@ -696,6 +696,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 	if (se != cfs_rq->curr)
 		__dequeue_entity(cfs_rq, se);
 	account_entity_dequeue(cfs_rq, se);
+	update_min_vruntime(cfs_rq);
 }
 
 /*