This patch reorders the code to delay virtio header write to optimize cache
access efficiency for cases where the mrg_rxbuf feature is turned on. It
reduces CPU pipeline stall cycles significantly.
Signed-off-by: Zhihong Wang <zhihong.wang at intel.com>
---
lib/librte_vhost/vhost_rxtx.c | 23 ++++++++++++++++-------
1 file changed, 16 insertions(+), 7 deletions(-)
diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c
index 60d63d3..15f7f9c 100644
--- a/lib/librte_vhost/vhost_rxtx.c
+++ b/lib/librte_vhost/vhost_rxtx.c
@@ -154,6 +154,7 @@ enqueue_packet(struct virtio_net *dev, struct
vhost_virtqueue *vq,
uint32_t mbuf_len = 0;
uint32_t mbuf_len_left = 0;
uint32_t copy_len = 0;
+ uint32_t copy_virtio_hdr = 0;
uint32_t extra_buffers = 0;
/* start with the first mbuf of the packet */
@@ -168,18 +169,17 @@ enqueue_packet(struct virtio_net *dev, struct
vhost_virtqueue *vq,
if (unlikely(!desc_host_write_addr))
goto error;
- /* handle virtio header */
+ /*
+ * handle virtio header, the actual write operation
+ * is delayed for cache optimization.
+ */
virtio_hdr = (struct virtio_net_hdr_mrg_rxbuf *)
(uintptr_t)desc_host_write_addr;
- memset((void *)(uintptr_t)&(virtio_hdr->hdr),
- 0, dev->vhost_hlen);
- virtio_enqueue_offload(mbuf, &(virtio_hdr->hdr));
+ copy_virtio_hdr = 1;
vhost_log_write(dev, desc->addr, dev->vhost_hlen);
desc_write_offset = dev->vhost_hlen;
desc_chain_len = desc_write_offset;
desc_host_write_addr += desc_write_offset;
- if (is_mrg_rxbuf)
- virtio_hdr->num_buffers = 1;
/* start copy from mbuf to desc */
while (1) {
@@ -233,9 +233,18 @@ enqueue_packet(struct virtio_net *dev, struct
vhost_virtqueue *vq,
goto rollback;
}
- /* copy mbuf data */
+ /* copy virtio header and mbuf data */
copy_len = RTE_MIN(desc->len - desc_write_offset,
mbuf_len_left);
+ if (copy_virtio_hdr) {
+ copy_virtio_hdr = 0;
+ memset((void *)(uintptr_t)&(virtio_hdr->hdr),
+ 0, dev->vhost_hlen);
+ virtio_enqueue_offload(mbuf, &(virtio_hdr->hdr));
+ if (is_mrg_rxbuf)
+ virtio_hdr->num_buffers = extra_buffers + 1;
+ }
+
rte_memcpy((void *)(uintptr_t)desc_host_write_addr,
rte_pktmbuf_mtod_offset(mbuf, void *,
mbuf_len - mbuf_len_left),
--
2.7.4
