[dpdk-dev] [PATCH v2 4/7] vhost: do not use rte_memcpy for virtio_hdr copy

[Yuanhan Liu]

First of all, rte_memcpy() is mostly useful for coping big packets
by leveraging hardware advanced instructions like AVX. But for virtio
net hdr, which is 12 bytes at most, invoking rte_memcpy() will not
introduce any performance boost.

And, to my suprise, rte_memcpy() is VERY huge. Since rte_memcpy()
is inlined, it increases the binary code size linearly every time
we call it at a different place. Replacing the two rte_memcpy()
with directly copy saves nearly 12K bytes of code size!

Signed-off-by: Yuanhan Liu <yuanhan.liu at linux.intel.com>
---
 lib/librte_vhost/vhost_rxtx.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c
index 3909584..97690c3 100644
--- a/lib/librte_vhost/vhost_rxtx.c
+++ b/lib/librte_vhost/vhost_rxtx.c
@@ -92,6 +92,17 @@ virtio_enqueue_offload(struct rte_mbuf *m_buf, struct 
virtio_net_hdr *net_hdr)
        return;
 }

+static inline void
+copy_virtio_net_hdr(struct vhost_virtqueue *vq, uint64_t desc_addr,
+                   struct virtio_net_hdr_mrg_rxbuf hdr)
+{
+       if (vq->vhost_hlen == sizeof(struct virtio_net_hdr_mrg_rxbuf)) {
+               *(struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)desc_addr = hdr;
+       } else {
+               *(struct virtio_net_hdr *)(uintptr_t)desc_addr = hdr.hdr;
+       }
+}
+
 static inline int __attribute__((always_inline))
 copy_mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
                  struct rte_mbuf *m, uint16_t desc_idx, uint32_t *copied)
@@ -108,8 +119,7 @@ copy_mbuf_to_desc(struct virtio_net *dev, struct 
vhost_virtqueue *vq,
        rte_prefetch0((void *)(uintptr_t)desc_addr);

        virtio_enqueue_offload(m, &virtio_hdr.hdr);
-       rte_memcpy((void *)(uintptr_t)desc_addr,
-                       (const void *)&virtio_hdr, vq->vhost_hlen);
+       copy_virtio_net_hdr(vq, desc_addr, virtio_hdr);
        PRINT_PACKET(dev, (uintptr_t)desc_addr, vq->vhost_hlen, 0);

        desc_offset = vq->vhost_hlen;
@@ -404,8 +414,7 @@ copy_mbuf_to_desc_mergeable(struct virtio_net *dev, struct 
vhost_virtqueue *vq,
                dev->device_fh, virtio_hdr.num_buffers);

        virtio_enqueue_offload(m, &virtio_hdr.hdr);
-       rte_memcpy((void *)(uintptr_t)desc_addr,
-               (const void *)&virtio_hdr, vq->vhost_hlen);
+       copy_virtio_net_hdr(vq, desc_addr, virtio_hdr);
        PRINT_PACKET(dev, (uintptr_t)desc_addr, vq->vhost_hlen, 0);

        desc_avail  = vq->buf_vec[vec_idx].buf_len - vq->vhost_hlen;
-- 
1.9.0