From a98240621d414112d74aa99f9d3e91cfe711a0b9 Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Thu, 10 Mar 2016 12:32:42 +0800 Subject: [PATCH] vhost: remove rte_memcpy from header copy First of all, rte_memcpy() is mostly useful for copying 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 --- lib/librte_vhost/vhost_rxtx.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c index 3ebeceea80..c7a34721ec 100644 --- a/lib/librte_vhost/vhost_rxtx.c +++ b/lib/librte_vhost/vhost_rxtx.c @@ -129,6 +129,16 @@ 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) @@ -145,8 +155,7 @@ 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); vhost_log_write(dev, desc->addr, vq->vhost_hlen); PRINT_PACKET(dev, (uintptr_t)desc_addr, vq->vhost_hlen, 0); @@ -444,8 +453,7 @@ 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); vhost_log_write(dev, vq->buf_vec[vec_idx].buf_addr, vq->vhost_hlen); PRINT_PACKET(dev, (uintptr_t)desc_addr, vq->vhost_hlen, 0); -- 2.20.1