[PATCH] sched_ext: Place dsq_vtime next to dsq_priq

[Usama Arif <usama.arif@linux.dev>]

scx_dispatch_enqueue() calls rb_add() for a vtime-ordered DSQ while
holding dsq->lock. At each level of the descent, scx_dsq_priq_less()
loads the visited task's dsq_vtime, and that comparison selects rb_left
or rb_right from the same task's dsq_priq. In the x86-64 benchmark
configuration, these accesses fell on different 64-byte cache lines
before this change, so a cold visited task could require a second cache
line fill on the dependent descent path.

Move dsq_vtime immediately before dsq_priq, keeping dsq_seq and
dsq_flags next to dsq_list. In the two x86-64 layouts inspected, where
scx starts at offsets 776 and 840 in task_struct, the fields from
dsq_list through dsq_priq occupy one cache line. The exact cache line
placement depends on the containing task_struct layout and is not
guaranteed for every configuration or architecture. Where they share a
line, avoiding the dependent cache line fill helps reduce dsq->lock hold
time during vtime insertion and therefore contention on the lock.

In a 16-vCPU KVM guest, the instrumented enqueue interval was 4-6%
shorter with scx_lavd and scx_layered. scx_mitosis and end-to-end
workload time showed no consistent change.

This only reorders fields; no scheduling behavior change is intended.

Signed-off-by: Usama Arif <usama.arif@linux.dev>
---
 include/linux/sched/ext.h | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 1e1fc3312bc40..b856768716249 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -197,9 +197,19 @@ struct sched_ext_entity {
 	u64			ddsp_slice;
 	u64			ddsp_vtime;
 	struct scx_dsq_list_node dsq_list;	/* dispatch order */
-	struct rb_node		dsq_priq;	/* p->scx.dsq_vtime order */
 	u32			dsq_seq;
 	u32			dsq_flags;	/* protected by DSQ lock */
+
+	/*
+	 * Used to order tasks when dispatching to the vtime-ordered priority
+	 * queue of a dsq. This is usually set through
+	 * scx_bpf_dsq_insert_vtime() but can also be modified directly by the
+	 * BPF scheduler. Modifying it while a task is queued on a dsq may
+	 * mangle the ordering and is not recommended. Kept next to @dsq_priq
+	 * as rbtree insertion reads both on every visited node.
+	 */
+	u64			dsq_vtime;
+	struct rb_node		dsq_priq;	/* p->scx.dsq_vtime order */
 	u32			flags;		/* protected by rq lock */
 	u32			weight;
 	u32			reenq_cnt;	/* reenqueues since last run */
@@ -225,7 +235,7 @@ struct sched_ext_entity {
 	u64			tid;
 	struct rhash_head	tid_hash_node;	/* see SCX_OPS_TID_TO_TASK */
 
-	/* BPF scheduler modifiable fields */
+	/* BPF scheduler modifiable fields, along with @dsq_vtime above */
 
 	/*
 	 * Runtime budget in nsecs - how long the task may hold its cpu. Owned
@@ -240,15 +250,6 @@ struct sched_ext_entity {
 	 */
 	u64			slice;
 
-	/*
-	 * Used to order tasks when dispatching to the vtime-ordered priority
-	 * queue of a dsq. This is usually set through
-	 * scx_bpf_dsq_insert_vtime() but can also be modified directly by the
-	 * BPF scheduler. Modifying it while a task is queued on a dsq may
-	 * mangle the ordering and is not recommended.
-	 */
-	u64			dsq_vtime;
-
 	/*
 	 * Out-of-band slice request from scx_bpf_task_set_slice() when the
 	 * caller does not hold the rq lock, applied under the rq lock at the
-- 
2.53.0-Meta