net/virtio: fix broken transmit functionality
Checks
Commit Message
Previous fix removes usage of rte_pktmbuf_prepend() to get pointer
to virtio net header which changes mbuf data_off and data_len.
Size of virtio net header is added to segment length when Tx descriptor
is composed, but segment address (calculated using data_off) is not
adjusted to take size of virtio net header into account.
Fixes: c100fc6849fb ("net/virtio: fix mbuf data and pkt length mismatch")
Cc: stable@dpdk.org
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
---
drivers/net/virtio/virtio_rxtx.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
Comments
On Tue, Oct 15, 2019 at 09:11:27AM +0100, Andrew Rybchenko wrote:
> Previous fix removes usage of rte_pktmbuf_prepend() to get pointer
> to virtio net header which changes mbuf data_off and data_len.
> Size of virtio net header is added to segment length when Tx descriptor
> is composed, but segment address (calculated using data_off) is not
> adjusted to take size of virtio net header into account.
>
> Fixes: c100fc6849fb ("net/virtio: fix mbuf data and pkt length mismatch")
The commit in main branch is:
Fixes: 1ae55ad38e5e ("net/virtio: fix mbuf data and packet length mismatch")
For the rest,
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
On 10/15/19 10:11 AM, Andrew Rybchenko wrote:
> Previous fix removes usage of rte_pktmbuf_prepend() to get pointer
> to virtio net header which changes mbuf data_off and data_len.
> Size of virtio net header is added to segment length when Tx descriptor
> is composed, but segment address (calculated using data_off) is not
> adjusted to take size of virtio net header into account.
>
> Fixes: c100fc6849fb ("net/virtio: fix mbuf data and pkt length mismatch")
> Cc: stable@dpdk.org
>
> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
> ---
> drivers/net/virtio/virtio_rxtx.c | 7 +++++--
> 1 file changed, 5 insertions(+), 2 deletions(-)
>
Applied to dpdk-next-virtio/master.
Thanks,
Maxime
@@ -649,7 +649,8 @@ virtqueue_enqueue_xmit_inorder(struct virtnet_tx *txvq,
else
virtqueue_xmit_offload(hdr, cookies[i], true);
- start_dp[idx].addr = VIRTIO_MBUF_DATA_DMA_ADDR(cookies[i], vq);
+ start_dp[idx].addr =
+ VIRTIO_MBUF_DATA_DMA_ADDR(cookies[i], vq) - head_size;
start_dp[idx].len = cookies[i]->data_len + head_size;
start_dp[idx].flags = 0;
@@ -696,7 +697,7 @@ virtqueue_enqueue_xmit_packed_fast(struct virtnet_tx *txvq,
else
virtqueue_xmit_offload(hdr, cookie, true);
- dp->addr = VIRTIO_MBUF_DATA_DMA_ADDR(cookie, vq);
+ dp->addr = VIRTIO_MBUF_DATA_DMA_ADDR(cookie, vq) - head_size;
dp->len = cookie->data_len + head_size;
dp->id = id;
@@ -779,6 +780,7 @@ virtqueue_enqueue_xmit_packed(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
start_dp[idx].addr = VIRTIO_MBUF_DATA_DMA_ADDR(cookie, vq);
start_dp[idx].len = cookie->data_len;
if (prepend_header) {
+ start_dp[idx].addr -= head_size;
start_dp[idx].len += head_size;
prepend_header = false;
}
@@ -882,6 +884,7 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
start_dp[idx].addr = VIRTIO_MBUF_DATA_DMA_ADDR(cookie, vq);
start_dp[idx].len = cookie->data_len;
if (prepend_header) {
+ start_dp[idx].addr -= head_size;
start_dp[idx].len += head_size;
prepend_header = false;
}