summaryrefslogtreecommitdiff
path: root/kernel/sched
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2016-09-20 21:58:12 +0200
committerIngo Molnar <mingo@kernel.org>2016-09-30 11:03:29 +0200
commitb60205c7c558330e4e2b5df498355ec959457358 (patch)
tree3d54676c0af39e738ea7dded622a1685c0fc483a /kernel/sched
parent9148a3a10e0b74c5722174a0bbef16d821f8a48b (diff)
sched/fair: Fix min_vruntime tracking
While going through enqueue/dequeue to review the movement of set_curr_task() I noticed that the (2nd) update_min_vruntime() call in dequeue_entity() is suspect. It turns out, its actually wrong because it will consider cfs_rq->curr, which could be the entry we just normalized. This mixes different vruntime forms and leads to fail. The purpose of the second update_min_vruntime() is to move min_vruntime forward if the entity we just removed is the one that was holding it back; _except_ for the DEQUEUE_SAVE case, because then we know its a temporary removal and it will come back. However, since we do put_prev_task() _after_ dequeue(), cfs_rq->curr will still be set (and per the above, can be tranformed into a different unit), so update_min_vruntime() should also consider curr->on_rq. This also fixes another corner case where the enqueue (which also does update_curr()->update_min_vruntime()) happens on the rq->lock break in schedule(), between dequeue and put_prev_task. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Fixes: 1e876231785d ("sched: Fix ->min_vruntime calculation in dequeue_entity()") Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/fair.c29
1 files changed, 22 insertions, 7 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a6789485fcae..543b2f291152 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -460,17 +460,23 @@ static inline int entity_before(struct sched_entity *a,
static void update_min_vruntime(struct cfs_rq *cfs_rq)
{
+ struct sched_entity *curr = cfs_rq->curr;
+
u64 vruntime = cfs_rq->min_vruntime;
- if (cfs_rq->curr)
- vruntime = cfs_rq->curr->vruntime;
+ if (curr) {
+ if (curr->on_rq)
+ vruntime = curr->vruntime;
+ else
+ curr = NULL;
+ }
if (cfs_rq->rb_leftmost) {
struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost,
struct sched_entity,
run_node);
- if (!cfs_rq->curr)
+ if (!curr)
vruntime = se->vruntime;
else
vruntime = min_vruntime(vruntime, se->vruntime);
@@ -3478,9 +3484,10 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
account_entity_dequeue(cfs_rq, se);
/*
- * Normalize the entity after updating the min_vruntime because the
- * update can refer to the ->curr item and we need to reflect this
- * movement in our normalized position.
+ * Normalize after update_curr(); which will also have moved
+ * min_vruntime if @se is the one holding it back. But before doing
+ * update_min_vruntime() again, which will discount @se's position and
+ * can move min_vruntime forward still more.
*/
if (!(flags & DEQUEUE_SLEEP))
se->vruntime -= cfs_rq->min_vruntime;
@@ -3488,8 +3495,16 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
/* return excess runtime on last dequeue */
return_cfs_rq_runtime(cfs_rq);
- update_min_vruntime(cfs_rq);
update_cfs_shares(cfs_rq);
+
+ /*
+ * Now advance min_vruntime if @se was the entity holding it back,
+ * except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be
+ * put back on, and if we advance min_vruntime, we'll be placed back
+ * further than we started -- ie. we'll be penalized.
+ */
+ if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE)
+ update_min_vruntime(cfs_rq);
}
/*