[PATCH] vhost: fix sync dequeue offload

Xia, Chenbo chenbo.xia at intel.com
Fri Jul 1 11:54:47 CEST 2022


> -----Original Message-----
> From: Ding, Xuan <xuan.ding at intel.com>
> Sent: Friday, June 24, 2022 1:38 PM
> To: maxime.coquelin at redhat.com; Xia, Chenbo <chenbo.xia at intel.com>
> Cc: dev at dpdk.org; Hu, Jiayu <jiayu.hu at intel.com>; Ling, WeiX
> <weix.ling at intel.com>; Ding, Xuan <xuan.ding at intel.com>
> Subject: [PATCH] vhost: fix sync dequeue offload
> 
> From: Xuan Ding <xuan.ding at intel.com>
> 
> This patch fixes the missing virtio net header copy in sync
> dequeue path caused by refactoring, which affects dequeue
> offloading.
> 
> Fixes: 6d823bb302c7("vhost: prepare sync for descriptor to mbuf
> refactoring")
> 
> Signed-off-by: Xuan Ding <xuan.ding at intel.com>
> ---
>  lib/vhost/virtio_net.c | 14 +++++++++++---
>  1 file changed, 11 insertions(+), 3 deletions(-)
> 
> diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c
> index 68a26eb17d..d5a9f7c691 100644
> --- a/lib/vhost/virtio_net.c
> +++ b/lib/vhost/virtio_net.c
> @@ -2635,9 +2635,17 @@ desc_to_mbuf(struct virtio_net *dev, struct
> vhost_virtqueue *vq,
>  					   buf_iova + buf_offset, cpy_len, false) <
> 0)
>  				goto error;
>  		} else {
> -			sync_fill_seg(dev, vq, cur, mbuf_offset,
> -				      buf_addr + buf_offset,
> -				      buf_iova + buf_offset, cpy_len, false);
> +			if (hdr && cur == m) {
> +				rte_memcpy(rte_pktmbuf_mtod_offset(cur, void *,
> mbuf_offset),
> +					(void *)((uintptr_t)(buf_addr + buf_offset)),
> +					cpy_len);
> +				vhost_log_cache_write_iova(dev, vq, buf_iova +
> buf_offset, cpy_len);
> +				PRINT_PACKET(dev, (uintptr_t)(buf_addr +
> buf_offset), cpy_len, 0);

Although above logic can also be included in func sync_fill_seg, but it will need
to add a new dequeue-specific param, so I would think this patch is fine.

During review of this patch, I also notice one bug that writes dirty page log when
doing dequeue. But it's not related to this patch. So:

Reviewed-by: Chenbo Xia <chenbo.xia at intel.com> 

> +			} else {
> +				sync_fill_seg(dev, vq, cur, mbuf_offset,
> +					buf_addr + buf_offset,
> +					buf_iova + buf_offset, cpy_len, false);
> +			}
>  		}
> 
>  		mbuf_avail  -= cpy_len;
> --
> 2.17.1



More information about the dev mailing list