From: Wanpeng Li <wanpengli@tencent.com>

pick_eevdf()'s PICK_BUDDY path only returns cfs_rq->next when the
entity is eligible. A yield_to() target that is behind avg_vruntime at
any level of its sched_entity hierarchy is skipped, and the
set_next_buddy() hint is lost.

Add eevdf_credit_entity_vlag(), which can credit a nominated entity up to
the eligibility boundary so that pick_eevdf() can honor the buddy hint.
The helper handles cfs_rq->curr, which is off-tree and can be shifted in
place while carrying any active vprot window.

Gate the helper behind SCHED_FEAT(YIELD_TO_LAG_CREDIT). The helper has no
caller in this change, so mark it __maybe_unused; there is no functional
change.

Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
 kernel/sched/fair.c     | 48 +++++++++++++++++++++++++++++++++++++++++
 kernel/sched/features.h |  9 ++++++++
 2 files changed, 57 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3ebec186f982..e7f5ea25fdae 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9341,6 +9341,54 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct t
 	}
 }
 
+/*
+ * eevdf_credit_entity_vlag - credit a nominated next-buddy to eligibility
+ *
+ * Advance @se (already nominated by set_next_buddy(), so cfs_rq->next == se)
+ * just enough negative vlag to reach the eligibility boundary (vlag = 0) so
+ * pick_eevdf()'s PICK_BUDDY branch returns it. cfs_rq->curr is shifted in
+ * place (off-tree, carrying any vprot window). Queued entities are left
+ * unchanged.
+ *
+ * Idempotent: a no-op once @se is already eligible. Caller must hold
+ * rq_of(cfs_rq)->lock with rq_clock up to date.
+ */
+static void __maybe_unused
+eevdf_credit_entity_vlag(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	u64 avruntime, credit;
+	s64 vlag;
+
+	/* Callers gate this helper with YIELD_TO_LAG_CREDIT. */
+	if (cfs_rq->nr_queued < 2)
+		return;
+	if (throttled_hierarchy(cfs_rq))
+		return;
+	if (WARN_ON_ONCE(!se->on_rq) || se->sched_delayed)
+		return;
+
+	update_curr(cfs_rq);
+	avruntime = avg_vruntime(cfs_rq);
+	vlag = entity_lag(cfs_rq, se, avruntime);
+
+	/* Already eligible: nothing to do. */
+	if (vlag >= 0)
+		return;
+
+	credit = (u64)(-vlag);
+
+	if (cfs_rq->curr == se) {
+		/* curr is off-tree: in-place shift, carrying any vprot window. */
+		if (protect_slice(se))
+			se->vprot -= credit;
+		se->vruntime -= credit;
+		se->deadline -= credit;
+		return;
+	}
+
+	/* Queued entities are left unchanged by this helper path. */
+}
+
 /*
  * sched_yield() is very simple
  */
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 84c4fe3abd74..65c511c9ca28 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -40,6 +40,15 @@ SCHED_FEAT(NEXT_BUDDY, false)
  */
 SCHED_FEAT(PICK_BUDDY, true)
 
+/*
+ * Let yield_to_task_fair() credit bounded EEVDF lag to the nominated
+ * next-buddy so pick_eevdf() honors the hint even when the target has
+ * negative vlag at some level of its ancestor chain. The credit is bounded
+ * by a queue-depth-scaled margin within entity_lag()'s legal range, so
+ * fairness is preserved.
+ */
+SCHED_FEAT(YIELD_TO_LAG_CREDIT, true)
+
 /*
  * Consider buddies to be cache hot, decreases the likeliness of a
  * cache buddy being migrated away, increases cache locality.
-- 
2.43.0