Merge tag 'sched-urgent-2026-05-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:

 - Fix the delayed dequeue negative lag increase fix in the
   fair scheduler (Peter Zijlstra)

 - Fix wakeup_preempt_fair() to do proper delayed dequeue
   (Vincent Guittot)

 - Clear sched_entity::rel_deadline when initializing
   forked entities, which bug can cause all tasks to be
   EEVDF-ineligible, causing a NULL pointer dereference
   crash in pick_next_entity() (Zicheng Qu)

* tag 'sched-urgent-2026-05-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Clear rel_deadline when initializing forked entities
  sched/fair: Fix wakeup_preempt_fair() vs delayed dequeue
  sched/fair: Fix the negative lag increase fix

2 files changed, 25 insertions, 18 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index da20fb6ea25a..b8871449d3c6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4458,6 +4458,7 @@ static void __sched_fork(u64 clone_flags, struct task_struct *p)
 	p->se.nr_migrations		= 0;
 	p->se.vruntime			= 0;
 	p->se.vlag			= 0;
+	p->se.rel_deadline		= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
 	/* A delayed task cannot be in clone(). */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 69361c63353a..728965851842 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -847,13 +847,19 @@ static s64 entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se, u64 avrunt
  * Similarly, check that the entity didn't gain positive lag when DELAY_ZERO
  * is set.
  *
- * Return true if the lag has been adjusted.
+ * Return true if the vlag has been modified. Specifically:
+ *
+ *   se->vlag != avg_vruntime() - se->vruntime
+ *
+ * This can be due to clamping in entity_lag() or clamping due to
+ * sched_delayed. Either way, when vlag is modified and the entity is
+ * retained, the tree needs to be adjusted.
  */
 static __always_inline
 bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	s64 vlag = entity_lag(cfs_rq, se, avg_vruntime(cfs_rq));
-	bool ret;
+	u64 avruntime = avg_vruntime(cfs_rq);
+	s64 vlag = entity_lag(cfs_rq, se, avruntime);
 
 	WARN_ON_ONCE(!se->on_rq);
 
@@ -863,10 +869,9 @@ bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		if (sched_feat(DELAY_ZERO))
 			vlag = min(vlag, 0);
 	}
-	ret = (vlag == se->vlag);
 	se->vlag = vlag;
 
-	return ret;
+	return avruntime - vlag != se->vruntime;
 }
 
 /*
@@ -1099,7 +1104,7 @@ static inline void cancel_protect_slice(struct sched_entity *se)
  *
  * Which allows tree pruning through eligibility.
  */
-static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq, bool protect)
+static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq, bool protect)
 {
 	struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
 	struct sched_entity *se = __pick_first_entity(cfs_rq);
@@ -1170,11 +1175,6 @@ found:
 	return best;
 }
 
-static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
-{
-	return __pick_eevdf(cfs_rq, true);
-}
-
 struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline.rb_root);
@@ -5749,11 +5749,11 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags);
  * 4) do not run the "skip" process, if something else is available
  */
 static struct sched_entity *
-pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
+pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq, bool protect)
 {
 	struct sched_entity *se;
 
-	se = pick_eevdf(cfs_rq);
+	se = pick_eevdf(cfs_rq, protect);
 	if (se->sched_delayed) {
 		dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
 		/*
@@ -9027,7 +9027,7 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
 {
 	enum preempt_wakeup_action preempt_action = PREEMPT_WAKEUP_PICK;
 	struct task_struct *donor = rq->donor;
-	struct sched_entity *se = &donor->se, *pse = &p->se;
+	struct sched_entity *nse, *se = &donor->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(donor);
 	int cse_is_idle, pse_is_idle;
 
@@ -9138,11 +9138,17 @@ static void wakeup_preempt_fair(struct rq *rq, struct task_struct *p, int wake_f
 	}
 
 pick:
+	nse = pick_next_entity(rq, cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT);
+	/* If @p has become the most eligible task, force preemption */
+	if (nse == pse)
+		goto preempt;
+
 	/*
-	 * If @p has become the most eligible task, force preemption.
+	 * Because p is enqueued, nse being null can only mean that we
+	 * dequeued a delayed task.
 	 */
-	if (__pick_eevdf(cfs_rq, preempt_action != PREEMPT_WAKEUP_SHORT) == pse)
-		goto preempt;
+	if (!nse)
+		goto pick;
 
 	if (sched_feat(RUN_TO_PARITY))
 		update_protect_slice(cfs_rq, se);
@@ -9179,7 +9185,7 @@ again:
 
 		throttled |= check_cfs_rq_runtime(cfs_rq);
 
-		se = pick_next_entity(rq, cfs_rq);
+		se = pick_next_entity(rq, cfs_rq, true);
 		if (!se)
 			goto again;
 		cfs_rq = group_cfs_rq(se);