* [dpdk-stable] [PATCH 18.11] net/virtio: fix mbuf data and packet length mismatch
@ 2020-03-16 12:35 Marvin Liu
2020-03-18 23:01 ` Kevin Traynor
0 siblings, 1 reply; 2+ messages in thread
From: Marvin Liu @ 2020-03-16 12:35 UTC (permalink / raw)
To: stable; +Cc: ktraynor, Marvin Liu
[ upstream commit 1ae55ad38e5e00b61704e4cb29037098b143688a ]
If reserve virtio header room by function rte_pktmbuf_prepend, both
segment data length and packet length of mbuf will be increased.
Data length will be equal to descriptor length, while packet length
should be decreased as virtio-net header won't be taken into packet.
Thus will cause mismatch in mbuf structure. Fix this issue by calculate
mbuf data address directly.
Fixes: 58169a9c8153 ("net/virtio: support Tx checksum offload")
Fixes: 892dc798fa9c ("net/virtio: implement Tx path for packed queues")
Fixes: e5f456a98d3c ("net/virtio: support in-order Rx and Tx")
Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Marvin Liu <yong.liu@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c
index 306009d96..915674f31 100644
--- a/drivers/net/virtio/virtio_rxtx.c
+++ b/drivers/net/virtio/virtio_rxtx.c
@@ -413,8 +413,8 @@ virtqueue_enqueue_xmit_inorder(struct virtnet_tx *txvq,
dxp->cookie = (void *)cookies[i];
dxp->ndescs = 1;
- hdr = (struct virtio_net_hdr *)
- rte_pktmbuf_prepend(cookies[i], head_size);
+ hdr = rte_pktmbuf_mtod_offset(cookies[i],
+ struct virtio_net_hdr *, -head_size);
cookies[i]->pkt_len -= head_size;
/* if offload disabled, it is not zeroed below, do it now */
@@ -430,8 +430,9 @@ virtqueue_enqueue_xmit_inorder(struct virtnet_tx *txvq,
virtqueue_xmit_offload(hdr, cookies[i],
vq->hw->has_tx_offload);
- start_dp[idx].addr = VIRTIO_MBUF_DATA_DMA_ADDR(cookies[i], vq);
- start_dp[idx].len = cookies[i]->data_len;
+ 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;
vq_update_avail_ring(vq, idx);
@@ -456,6 +457,7 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
uint16_t seg_num = cookie->nb_segs;
uint16_t head_idx, idx;
uint16_t head_size = vq->hw->vtnet_hdr_size;
+ bool prepend_header = false;
struct virtio_net_hdr *hdr;
head_idx = vq->vq_desc_head_idx;
@@ -471,13 +473,9 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
if (can_push) {
/* prepend cannot fail, checked by caller */
- hdr = (struct virtio_net_hdr *)
- rte_pktmbuf_prepend(cookie, head_size);
- /* rte_pktmbuf_prepend() counts the hdr size to the pkt length,
- * which is wrong. Below subtract restores correct pkt size.
- */
- cookie->pkt_len -= head_size;
-
+ hdr = rte_pktmbuf_mtod_offset(cookie, struct virtio_net_hdr *,
+ -head_size);
+ prepend_header = true;
/* if offload disabled, it is not zeroed below, do it now */
if (!vq->hw->has_tx_offload) {
ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0);
@@ -521,6 +519,11 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
do {
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;
+ }
start_dp[idx].flags = cookie->next ? VRING_DESC_F_NEXT : 0;
idx = start_dp[idx].next;
} while ((cookie = cookie->next) != NULL);
--
2.17.1
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [dpdk-stable] [PATCH 18.11] net/virtio: fix mbuf data and packet length mismatch
2020-03-16 12:35 [dpdk-stable] [PATCH 18.11] net/virtio: fix mbuf data and packet length mismatch Marvin Liu
@ 2020-03-18 23:01 ` Kevin Traynor
0 siblings, 0 replies; 2+ messages in thread
From: Kevin Traynor @ 2020-03-18 23:01 UTC (permalink / raw)
To: Marvin Liu, stable
On 16/03/2020 12:35, Marvin Liu wrote:
> [ upstream commit 1ae55ad38e5e00b61704e4cb29037098b143688a ]
>
> If reserve virtio header room by function rte_pktmbuf_prepend, both
> segment data length and packet length of mbuf will be increased.
> Data length will be equal to descriptor length, while packet length
> should be decreased as virtio-net header won't be taken into packet.
> Thus will cause mismatch in mbuf structure. Fix this issue by calculate
> mbuf data address directly.
>
> Fixes: 58169a9c8153 ("net/virtio: support Tx checksum offload")
> Fixes: 892dc798fa9c ("net/virtio: implement Tx path for packed queues")
> Fixes: e5f456a98d3c ("net/virtio: support in-order Rx and Tx")
>
> Reported-by: Stephen Hemminger <stephen@networkplumber.org>
> Signed-off-by: Marvin Liu <yong.liu@intel.com>
> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Applied, thanks.
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2020-03-18 23:01 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-03-16 12:35 [dpdk-stable] [PATCH 18.11] net/virtio: fix mbuf data and packet length mismatch Marvin Liu
2020-03-18 23:01 ` Kevin Traynor
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).