From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Tue, 8 Jul 2025 16:56:26 +0000 (+0200)
Subject: sched/fair: Fix NO_RUN_TO_PARITY case
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=74eec63661d46a7153d04c2e0249eeb76cc76d44;p=thirdparty%2Flinux.git

sched/fair: Fix NO_RUN_TO_PARITY case

EEVDF expects the scheduler to allocate a time quantum to the selected
entity and then pick a new entity for next quantum.
Although this notion of time quantum is not strictly doable in our case,
we can ensure a minimum runtime for each task most of the time and pick a
new entity after a minimum time has elapsed.
Reuse the slice protection of run to parity to ensure such runtime
quantum.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250708165630.1948751-3-vincent.guittot@linaro.org
---

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4802fcf738cde..55921385927d8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -583,7 +583,15 @@ struct sched_entity {
 	u64				sum_exec_runtime;
 	u64				prev_sum_exec_runtime;
 	u64				vruntime;
-	s64				vlag;
+	union {
+		/*
+		 * When !@on_rq this field is vlag.
+		 * When cfs_rq->curr == se (which implies @on_rq)
+		 * this field is vprot. See protect_slice().
+		 */
+		s64                     vlag;
+		u64                     vprot;
+	};
 	u64				slice;
 
 	u64				nr_migrations;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 43fe5c831dd59..8d288df79a6bd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -882,23 +882,35 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 }
 
 /*
- * HACK, stash a copy of deadline at the point of pick in vlag,
- * which isn't used until dequeue.
+ * Set the vruntime up to which an entity can run before looking
+ * for another entity to pick.
+ * In case of run to parity, we protect the entity up to its deadline.
+ * When run to parity is disabled, we give a minimum quantum to the running
+ * entity to ensure progress.
  */
 static inline void set_protect_slice(struct sched_entity *se)
 {
-	se->vlag = se->deadline;
+	u64 slice = se->slice;
+	u64 vprot = se->deadline;
+
+	if (!sched_feat(RUN_TO_PARITY))
+		slice = min(slice, normalized_sysctl_sched_base_slice);
+
+	if (slice != se->slice)
+		vprot = min_vruntime(vprot, se->vruntime + calc_delta_fair(slice, se));
+
+	se->vprot = vprot;
 }
 
 static inline bool protect_slice(struct sched_entity *se)
 {
-	return se->vlag == se->deadline;
+	return ((s64)(se->vprot - se->vruntime) > 0);
 }
 
 static inline void cancel_protect_slice(struct sched_entity *se)
 {
 	if (protect_slice(se))
-		se->vlag = se->deadline + 1;
+		se->vprot = se->vruntime;
 }
 
 /*
@@ -937,7 +949,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 	if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
 		curr = NULL;
 
-	if (sched_feat(RUN_TO_PARITY) && curr && protect_slice(curr))
+	if (curr && protect_slice(curr))
 		return curr;
 
 	/* Pick the leftmost entity if it's eligible */
@@ -1156,11 +1168,8 @@ static inline void update_curr_task(struct task_struct *p, s64 delta_exec)
 	cgroup_account_cputime(p, delta_exec);
 }
 
-static inline bool did_preempt_short(struct cfs_rq *cfs_rq, struct sched_entity *curr)
+static inline bool resched_next_slice(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 {
-	if (!sched_feat(PREEMPT_SHORT))
-		return false;
-
 	if (protect_slice(curr))
 		return false;
 
@@ -1248,7 +1257,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	if (cfs_rq->nr_queued == 1)
 		return;
 
-	if (resched || did_preempt_short(cfs_rq, curr)) {
+	if (resched || resched_next_slice(cfs_rq, curr)) {
 		resched_curr_lazy(rq);
 		clear_buddies(cfs_rq, curr);
 	}