sched/eevdf: Propagate min_slice up the cgroup hierarchy

In the absence of an explicit cgroup slice configureation, make mixed
slice length work with cgroups by propagating the min_slice up the
hierarchy.

This ensures the cgroup entity gets timely service to service its
entities that have this timing constraint set on them.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Valentin Schneider <vschneid@redhat.com>
Link: https://lkml.kernel.org/r/20240727105030.948188417@infradead.org

include/linux/sched.h

@@ -542,6 +542,7 @@ struct sched_entity {
 	struct rb_node			run_node;
 	u64				deadline;
 	u64				min_vruntime;
+	u64				min_slice;
 
 	struct list_head		group_node;
 	unsigned char			on_rq;

kernel/sched/fair.c

@@ -782,6 +782,21 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 	cfs_rq->min_vruntime = __update_min_vruntime(cfs_rq, vruntime);
 }
 
+static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq)
+{
+	struct sched_entity *root = __pick_root_entity(cfs_rq);
+	struct sched_entity *curr = cfs_rq->curr;
+	u64 min_slice = ~0ULL;
+
+	if (curr && curr->on_rq)
+		min_slice = curr->slice;
+
+	if (root)
+		min_slice = min(min_slice, root->min_slice);
+
+	return min_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));
@@ -798,19 +813,34 @@ static inline void __min_vruntime_update(struct sched_entity *se, struct rb_node
 	}
 }
 
+static inline void __min_slice_update(struct sched_entity *se, struct rb_node *node)
+{
+	if (node) {
+		struct sched_entity *rse = __node_2_se(node);
+		if (rse->min_slice < se->min_slice)
+			se->min_slice = rse->min_slice;
+	}
+}
+
 /*
  * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
  */
 static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
 {
 	u64 old_min_vruntime = se->min_vruntime;
+	u64 old_min_slice = se->min_slice;
 	struct rb_node *node = &se->run_node;
 
 	se->min_vruntime = se->vruntime;
 	__min_vruntime_update(se, node->rb_right);
 	__min_vruntime_update(se, node->rb_left);
 
-	return se->min_vruntime == old_min_vruntime;
+	se->min_slice = se->slice;
+	__min_slice_update(se, node->rb_right);
+	__min_slice_update(se, node->rb_left);
+
+	return se->min_vruntime == old_min_vruntime &&
+	       se->min_slice == old_min_slice;
 }
 
 RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
@@ -823,6 +853,7 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	avg_vruntime_add(cfs_rq, se);
 	se->min_vruntime = se->vruntime;
+	se->min_slice = se->slice;
 	rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
 				__entity_less, &min_vruntime_cb);
 }
@@ -6911,6 +6942,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	int idle_h_nr_running = task_has_idle_policy(p);
 	int task_new = !(flags & ENQUEUE_WAKEUP);
 	int rq_h_nr_running = rq->cfs.h_nr_running;
+	u64 slice = 0;
 
 	if (flags & ENQUEUE_DELAYED) {
 		requeue_delayed_entity(se);
@@ -6940,7 +6972,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 			break;
 		}
 		cfs_rq = cfs_rq_of(se);
+
+		/*
+		 * Basically set the slice of group entries to the min_slice of
+		 * their respective cfs_rq. This ensures the group can service
+		 * its entities in the desired time-frame.
+		 */
+		if (slice) {
+			se->slice = slice;
+			se->custom_slice = 1;
+		}
 		enqueue_entity(cfs_rq, se, flags);
+		slice = cfs_rq_min_slice(cfs_rq);
 
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
@@ -6962,6 +7005,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		se_update_runnable(se);
 		update_cfs_group(se);
 
+		se->slice = slice;
+		slice = cfs_rq_min_slice(cfs_rq);
+
 		cfs_rq->h_nr_running++;
 		cfs_rq->idle_h_nr_running += idle_h_nr_running;
 
@@ -7027,11 +7073,15 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 	int idle_h_nr_running = 0;
 	int h_nr_running = 0;
 	struct cfs_rq *cfs_rq;
+	u64 slice = 0;
 
 	if (entity_is_task(se)) {
 		p = task_of(se);
 		h_nr_running = 1;
 		idle_h_nr_running = task_has_idle_policy(p);
+	} else {
+		cfs_rq = group_cfs_rq(se);
+		slice = cfs_rq_min_slice(cfs_rq);
 	}
 
 	for_each_sched_entity(se) {
@@ -7056,6 +7106,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight) {
+			slice = cfs_rq_min_slice(cfs_rq);
+
 			/* Avoid re-evaluating load for this entity: */
 			se = parent_entity(se);
 			/*
@@ -7077,6 +7129,9 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 		se_update_runnable(se);
 		update_cfs_group(se);
 
+		se->slice = slice;
+		slice = cfs_rq_min_slice(cfs_rq);
+
 		cfs_rq->h_nr_running -= h_nr_running;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;