sched/fair: Implement DELAY_ZERO

'Extend' DELAY_DEQUEUE by noting that since we wanted to dequeued them
at the 0-lag point, truncate lag (eg. don't let them earn positive
lag).

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Tested-by: Valentin Schneider <vschneid@redhat.com>
Link: https://lkml.kernel.org/r/20240727105030.403750550@infradead.org

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index da5065a226ee73e98c337144c1afdd607aa66851..1a593393e3088d835b9a81827f75e634219e497f 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5447,8 +5447,11 @@ 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)
+       if (flags & DEQUEUE_DELAYED) {
                se->sched_delayed = 0;
+               if (sched_feat(DELAY_ZERO) && se->vlag > 0)
+                       se->vlag = 0;
+       }
 
        if (cfs_rq->nr_running == 0)
                update_idle_cfs_rq_clock_pelt(cfs_rq);
@@ -5527,7 +5530,6 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
                dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
                SCHED_WARN_ON(se->sched_delayed);
                SCHED_WARN_ON(se->on_rq);
-
                return NULL;
        }
        return se;
@@ -6825,6 +6827,20 @@ requeue_delayed_entity(struct sched_entity *se)
        SCHED_WARN_ON(!se->sched_delayed);
        SCHED_WARN_ON(!se->on_rq);
 
+       if (sched_feat(DELAY_ZERO)) {
+               update_entity_lag(cfs_rq, se);
+               if (se->vlag > 0) {
+                       cfs_rq->nr_running--;
+                       if (se != cfs_rq->curr)
+                               __dequeue_entity(cfs_rq, se);
+                       se->vlag = 0;
+                       place_entity(cfs_rq, se, 0);
+                       if (se != cfs_rq->curr)
+                               __enqueue_entity(cfs_rq, se);
+                       cfs_rq->nr_running++;
+               }
+       }
+
        se->sched_delayed = 0;
 }
 

diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 1feaa7bbc2780c9991154059dda034adf427a103..7fdeb5576188c33342cb06a67c1421e108d2a5b4 100644 (file)
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -34,8 +34,11 @@ SCHED_FEAT(CACHE_HOT_BUDDY, true)
  * By delaying the dequeue for non-eligible tasks, they remain in the
  * competition and can burn off their negative lag. When they get selected
  * they'll have positive lag by definition.
+ *
+ * DELAY_ZERO clips the lag on dequeue (or wakeup) to 0.
  */
 SCHED_FEAT(DELAY_DEQUEUE, true)
+SCHED_FEAT(DELAY_ZERO, true)
 
 /*
  * Allow wakeup-time preemption of the current task: