The following commit has been merged into the sched/core branch of tip:
Commit-ID: 75b6499024a6c1a4ef0288f280534a5c54269076
Gitweb: https://git.kernel.org/tip/75b6499024a6c1a4ef0288f280534a5c54269076
Author: Valentin Schneider <vschneid@xxxxxxxxxx>
AuthorDate: Thu, 29 Aug 2024 15:53:53 +02:00
Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Tue, 03 Sep 2024 15:26:30 +02:00
sched/fair: Properly deactivate sched_delayed task upon class change
__sched_setscheduler() goes through an enqueue/dequeue cycle like so:
flags := DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
prev_class->dequeue_task(rq, p, flags);
new_class->enqueue_task(rq, p, flags);
when prev_class := fair_sched_class, this is followed by:
dequeue_task(rq, p, DEQUEUE_NOCLOCK | DEQUEUE_SLEEP);
the idea being that since the task has switched classes, we need to drop
the sched_delayed logic and have that task be deactivated per its previous
dequeue_task(..., DEQUEUE_SLEEP).
Unfortunately, this leaves the task on_rq. This is missing the tail end of
dequeue_entities() that issues __block_task(), which __sched_setscheduler()
won't have done due to not using DEQUEUE_DELAYED - not that it should, as
it is pretty much a fair_sched_class specific thing.
Make switched_from_fair() properly deactivate sched_delayed tasks upon
class changes via __block_task(), as if a
dequeue_task(..., DEQUEUE_DELAYED)
had been issued.
Fixes: 2e0199df252a ("sched/fair: Prepare exit/cleanup paths for delayed_dequeue")
Reported-by: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
Reported-by: Chen Yu <yu.c.chen@xxxxxxxxx>
Signed-off-by: Valentin Schneider <vschneid@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20240829135353.1524260-1-vschneid@xxxxxxxxxx
---
kernel/sched/fair.c | 25 +++++++++++++++++--------
1 file changed, 17 insertions(+), 8 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fea057b..3a3286d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5456,6 +5456,13 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
+static inline void finish_delayed_dequeue_entity(struct sched_entity *se)
+{
+ se->sched_delayed = 0;
+ if (sched_feat(DELAY_ZERO) && se->vlag > 0)
+ se->vlag = 0;
+}
+
static bool
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
@@ -5531,11 +5538,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
update_min_vruntime(cfs_rq);
- if (flags & DEQUEUE_DELAYED) {
- se->sched_delayed = 0;
- if (sched_feat(DELAY_ZERO) && se->vlag > 0)
- se->vlag = 0;
- }
+ if (flags & DEQUEUE_DELAYED)
+ finish_delayed_dequeue_entity(se);
if (cfs_rq->nr_running == 0)
update_idle_cfs_rq_clock_pelt(cfs_rq);
@@ -13107,11 +13111,16 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
* and we cannot use DEQUEUE_DELAYED.
*/
if (p->se.sched_delayed) {
+ /* First, dequeue it from its new class' structures */
dequeue_task(rq, p, DEQUEUE_NOCLOCK | DEQUEUE_SLEEP);
- p->se.sched_delayed = 0;
+ /*
+ * Now, clean up the fair_sched_class side of things
+ * related to sched_delayed being true and that wasn't done
+ * due to the generic dequeue not using DEQUEUE_DELAYED.
+ */
+ finish_delayed_dequeue_entity(&p->se);
p->se.rel_deadline = 0;
- if (sched_feat(DELAY_ZERO) && p->se.vlag > 0)
- p->se.vlag = 0;
+ __block_task(rq, p);
}
}
|