[PATCH v2 4/7] sched/fair: Fix lag clamp

[Peter Zijlstra]

Vincent reported that he was seeing undue lag clamping in a mixed
slice workload. Implement the max_slice tracking as per the todo
comment.

Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy")
Reported-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Tested-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Tested-by: K Prateek Nayak <kprateek.nayak@xxxxxxx>
Tested-by: Shubhang Kaushik <shubhang@xxxxxxxxxxxxxxxxxxxxxx>
Link: https://patch.msgid.link/20250422101628.GA33555@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
---
 include/linux/sched.h |    1 +
 kernel/sched/fair.c   |   39 +++++++++++++++++++++++++++++++++++----
 2 files changed, 36 insertions(+), 4 deletions(-)

--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -574,6 +574,7 @@ struct sched_entity {
 	u64				deadline;
 	u64				min_vruntime;
 	u64				min_slice;
+	u64				max_slice;
 
 	struct list_head		group_node;
 	unsigned char			on_rq;
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -748,6 +748,8 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
 	return cfs_rq->zero_vruntime;
 }
 
+static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq);
+
 /*
  * lag_i = S - s_i = w_i * (V - v_i)
  *
@@ -761,17 +763,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
  * EEVDF gives the following limit for a steady state system:
  *
  *   -r_max < lag < max(r_max, q)
- *
- * XXX could add max_slice to the augmented data to track this.
  */
 static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	u64 max_slice = cfs_rq_max_slice(cfs_rq) + TICK_NSEC;
 	s64 vlag, limit;
 
 	WARN_ON_ONCE(!se->on_rq);
 
 	vlag = avg_vruntime(cfs_rq) - se->vruntime;
-	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
+	limit = calc_delta_fair(max_slice, se);
 
 	se->vlag = clamp(vlag, -limit, limit);
 }
@@ -829,6 +830,21 @@ static inline u64 cfs_rq_min_slice(struc
 	return min_slice;
 }
 
+static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq)
+{
+	struct sched_entity *root = __pick_root_entity(cfs_rq);
+	struct sched_entity *curr = cfs_rq->curr;
+	u64 max_slice = 0ULL;
+
+	if (curr && curr->on_rq)
+		max_slice = curr->slice;
+
+	if (root)
+		max_slice = max(max_slice, root->max_slice);
+
+	return max_slice;
+}
+
 static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
 {
 	return entity_before(__node_2_se(a), __node_2_se(b));
@@ -853,6 +869,15 @@ static inline void __min_slice_update(st
 	}
 }
 
+static inline void __max_slice_update(struct sched_entity *se, struct rb_node *node)
+{
+	if (node) {
+		struct sched_entity *rse = __node_2_se(node);
+		if (rse->max_slice > se->max_slice)
+			se->max_slice = rse->max_slice;
+	}
+}
+
 /*
  * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
  */
@@ -860,6 +885,7 @@ static inline bool min_vruntime_update(s
 {
 	u64 old_min_vruntime = se->min_vruntime;
 	u64 old_min_slice = se->min_slice;
+	u64 old_max_slice = se->max_slice;
 	struct rb_node *node = &se->run_node;
 
 	se->min_vruntime = se->vruntime;
@@ -870,8 +896,13 @@ static inline bool min_vruntime_update(s
 	__min_slice_update(se, node->rb_right);
 	__min_slice_update(se, node->rb_left);
 
+	se->max_slice = se->slice;
+	__max_slice_update(se, node->rb_right);
+	__max_slice_update(se, node->rb_left);
+
 	return se->min_vruntime == old_min_vruntime &&
-	       se->min_slice == old_min_slice;
+	       se->min_slice == old_min_slice &&
+	       se->max_slice == old_max_slice;
 }
 
 RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,