Device use descriptors table in order, so there's no need to read
index from available ring. This eliminate the cache contention on
avail ring completely.
Virito-user + vhost_kernel + XDP_DROP gives about ~10% improvement on
TX from 4.8Mpps to 5.3Mpps on Intel(R) Core(TM) i7-5600U CPU @
2.60GHz.
Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
---
drivers/vhost/vhost.c | 19 ++++++++++++-------
1 file changed, 12 insertions(+), 7 deletions(-)
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 3a5f81a66d34..c8be151bc897 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2002,6 +2002,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
__virtio16 avail_idx;
__virtio16 ring_head;
int ret, access;
+ bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER);
/* Check it isn't doing very strange things with descriptor numbers. */
last_avail_idx = vq->last_avail_idx;
@@ -2034,15 +2035,19 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
/* Grab the next descriptor number they're advertising, and increment
* the index we've seen. */
- if (unlikely(vhost_get_avail(vq, ring_head,
- &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
- vq_err(vq, "Failed to read head: idx %d address %p\n",
- last_avail_idx,
- &vq->avail->ring[last_avail_idx % vq->num]);
- return -EFAULT;
+ if (!in_order) {
+ if (unlikely(vhost_get_avail(vq, ring_head,
+ &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
+ vq_err(vq, "Failed to read head: idx %d address %p\n",
+ last_avail_idx,
+ &vq->avail->ring[last_avail_idx % vq->num]);
+ return -EFAULT;
+ }
+ head = vhost16_to_cpu(vq, ring_head);
+ } else {
+ head = last_avail_idx & (vq->num - 1);
}
- head = vhost16_to_cpu(vq, ring_head);
/* If their number is silly, that's an error. */
if (unlikely(head >= vq->num)) {
--
2.17.1
