Improve data locality and reduce pointer chasing by allocating struct
cfs_rq and struct sched_entity together for non-root task groups. This
is achieved by introducing a new combined struct cfs_rq_with_se that
holds both objects in a single allocation.

This patch:

- Defines the new struct cfs_rq_with_se.

- Modifies alloc_fair_sched_group() and free_fair_sched_group() to
allocate and free the new struct as a single unit.

- Modifies the per-CPU pointers in task_group->se and task_group->cfs_rq
to point to the members in the new combined structure.

Signed-off-by: Zecheng Li <zecheng@google.com>
---
 kernel/sched/fair.c  | 23 ++++++++++-------------
 kernel/sched/sched.h |  8 ++++++++
 2 files changed, 18 insertions(+), 13 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index df8dc389af8e..fc8bc2d4614f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -13321,10 +13321,11 @@ void free_fair_sched_group(struct task_group *tg)
 	int i;
 
 	for_each_possible_cpu(i) {
-		if (tg->cfs_rq)
-			kfree(tg->cfs_rq[i]);
-		if (tg->se)
-			kfree(tg->se[i]);
+		if (tg->cfs_rq && tg->cfs_rq[i]) {
+			struct cfs_rq_with_se *combined =
+				container_of(tg->cfs_rq[i], struct cfs_rq_with_se, cfs_rq);
+			kfree(combined);
+		}
 	}
 
 	kfree(tg->cfs_rq);
@@ -13333,6 +13334,7 @@ void free_fair_sched_group(struct task_group *tg)
 
 int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
+	struct cfs_rq_with_se *combined;
 	struct sched_entity *se;
 	struct cfs_rq *cfs_rq;
 	int i;
@@ -13349,16 +13351,13 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg), tg_cfs_bandwidth(parent));
 
 	for_each_possible_cpu(i) {
-		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
+		combined = kzalloc_node(sizeof(struct cfs_rq_with_se),
 				      GFP_KERNEL, cpu_to_node(i));
-		if (!cfs_rq)
+		if (!combined)
 			goto err;
 
-		se = kzalloc_node(sizeof(struct sched_entity_stats),
-				  GFP_KERNEL, cpu_to_node(i));
-		if (!se)
-			goto err_free_rq;
-
+		cfs_rq = &combined->cfs_rq;
+		se = &combined->se;
 		init_cfs_rq(cfs_rq);
 		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
 		init_entity_runnable_average(se);
@@ -13366,8 +13365,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 
 	return 1;
 
-err_free_rq:
-	kfree(cfs_rq);
 err:
 	return 0;
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b5367c514c14..8b37de788eeb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -745,6 +745,14 @@ struct cfs_rq {
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 };
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+struct cfs_rq_with_se {
+	struct cfs_rq		cfs_rq;
+	/* cfs_rq's sched_entity on parent runqueue */
+	struct sched_entity	se ____cacheline_aligned;
+};
+#endif
+
 #ifdef CONFIG_SCHED_CLASS_EXT
 /* scx_rq->flags, protected by the rq lock */
 enum scx_rq_flags {

base-commit: 5b726e9bf9544a349090879a513a5e00da486c14
-- 
2.51.0.338.gd7d06c2dae-goog