1 files changed, 32 insertions, 25 deletions

diff --git a/tcp_vu.c b/tcp_vu.c
index 1c81ce3..88be232 100644
--- a/tcp_vu.c
+++ b/tcp_vu.c
@@ -40,17 +40,16 @@ static struct vu_virtq_element elem[VIRTQUEUE_MAX_SIZE];
 static int head[VIRTQUEUE_MAX_SIZE + 1];
 
 /**
- * tcp_vu_hdrlen() - return the size of the header in level 2 frame (TCP)
+ * tcp_vu_hdrlen() - Sum size of all headers, from TCP to virtio-net
  * @v6:		Set for IPv6 packet
  *
- * Return: return the size of the header
+ * Return: total size of virtio-net, Ethernet, IP, and TCP headers
  */
 static size_t tcp_vu_hdrlen(bool v6)
 {
 	size_t hdrlen;
 
-	hdrlen = sizeof(struct virtio_net_hdr_mrg_rxbuf) +
-		 sizeof(struct ethhdr) + sizeof(struct tcphdr);
+	hdrlen = VNET_HLEN + sizeof(struct ethhdr) + sizeof(struct tcphdr);
 
 	if (v6)
 		hdrlen += sizeof(struct ipv6hdr);
@@ -72,8 +71,8 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
 {
 	struct vu_dev *vdev = c->vdev;
 	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
-	size_t optlen, hdrlen;
 	struct vu_virtq_element flags_elem[2];
+	size_t optlen, hdrlen, l2len;
 	struct ipv6hdr *ip6h = NULL;
 	struct iphdr *ip4h = NULL;
 	struct iovec flags_iov[2];
@@ -91,14 +90,14 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
 	vu_set_element(&flags_elem[0], NULL, &flags_iov[0]);
 
 	elem_cnt = vu_collect(vdev, vq, &flags_elem[0], 1,
-			      hdrlen + sizeof(struct tcp_syn_opts), NULL);
+			      MAX(hdrlen + sizeof(*opts), ETH_ZLEN + VNET_HLEN), NULL);
 	if (elem_cnt != 1)
 		return -1;
 
 	ASSERT(flags_elem[0].in_sg[0].iov_len >=
-	       hdrlen + sizeof(struct tcp_syn_opts));
+	       MAX(hdrlen + sizeof(*opts), ETH_ZLEN + VNET_HLEN));
 
-	vu_set_vnethdr(vdev, flags_elem[0].in_sg[0].iov_base, 1);
+	vu_set_vnethdr(flags_elem[0].in_sg[0].iov_base, 1);
 
 	eh = vu_eth(flags_elem[0].in_sg[0].iov_base);
 
@@ -135,13 +134,17 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
 	flags_elem[0].in_sg[0].iov_len = hdrlen + optlen;
 	payload = IOV_TAIL(flags_elem[0].in_sg, 1, hdrlen);
 
-	tcp_fill_headers(c, conn, NULL, eh, ip4h, ip6h, th, &payload,
+	if (flags & KEEPALIVE)
+		seq--;
+
+	tcp_fill_headers(c, conn, eh, ip4h, ip6h, th, &payload,
 			 NULL, seq, !*c->pcap);
 
-	if (*c->pcap) {
-		pcap_iov(&flags_elem[0].in_sg[0], 1,
-			 sizeof(struct virtio_net_hdr_mrg_rxbuf));
-	}
+	l2len = optlen + hdrlen - VNET_HLEN;
+	vu_pad(&flags_elem[0].in_sg[0], l2len);
+
+	if (*c->pcap)
+		pcap_iov(&flags_elem[0].in_sg[0], 1, VNET_HLEN);
 	nb_ack = 1;
 
 	if (flags & DUP_ACK) {
@@ -157,10 +160,8 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
 			       flags_elem[0].in_sg[0].iov_len);
 			nb_ack++;
 
-			if (*c->pcap) {
-				pcap_iov(&flags_elem[1].in_sg[0], 1,
-					 sizeof(struct virtio_net_hdr_mrg_rxbuf));
-			}
+			if (*c->pcap)
+				pcap_iov(&flags_elem[1].in_sg[0], 1, VNET_HLEN);
 		}
 	}
 
@@ -211,7 +212,8 @@ static ssize_t tcp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq,
 
 		cnt = vu_collect(vdev, vq, &elem[elem_cnt],
 				 VIRTQUEUE_MAX_SIZE - elem_cnt,
-				 MIN(mss, fillsize) + hdrlen, &frame_size);
+				 MAX(MIN(mss, fillsize) + hdrlen, ETH_ZLEN + VNET_HLEN),
+				 &frame_size);
 		if (cnt == 0)
 			break;
 
@@ -254,6 +256,7 @@ static ssize_t tcp_vu_sock_recv(const struct ctx *c, struct vu_virtq *vq,
 
 		len -= iov->iov_len;
 	}
+
 	/* adjust head count */
 	while (*head_cnt > 0 && head[*head_cnt - 1] >= i)
 		(*head_cnt)--;
@@ -301,7 +304,7 @@ static void tcp_vu_prepare(const struct ctx *c, struct tcp_tap_conn *conn,
 	struct ethhdr *eh;
 
 	/* we guess the first iovec provided by the guest can embed
-	 * all the headers needed by L2 frame
+	 * all the headers needed by L2 frame, including any padding
 	 */
 	ASSERT(iov[0].iov_len >= hdrlen);
 
@@ -331,7 +334,7 @@ static void tcp_vu_prepare(const struct ctx *c, struct tcp_tap_conn *conn,
 	th->ack = 1;
 	th->psh = push;
 
-	tcp_fill_headers(c, conn, NULL, eh, ip4h, ip6h, th, &payload,
+	tcp_fill_headers(c, conn, eh, ip4h, ip6h, th, &payload,
 			 *check, conn->seq_to_tap, no_tcp_csum);
 	if (ip4h)
 		*check = &ip4h->check;
@@ -421,6 +424,7 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn)
 			}
 
 			conn_event(c, conn, TAP_FIN_SENT);
+			conn_flag(c, conn, ACK_FROM_TAP_DUE);
 		}
 
 		return 0;
@@ -446,8 +450,9 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn)
 		int buf_cnt = head[i + 1] - head[i];
 		ssize_t dlen = iov_size(iov, buf_cnt) - hdrlen;
 		bool push = i == head_cnt - 1;
+		size_t l2len;
 
-		vu_set_vnethdr(vdev, iov->iov_base, buf_cnt);
+		vu_set_vnethdr(iov->iov_base, buf_cnt);
 
 		/* The IPv4 header checksum varies only with dlen */
 		if (previous_dlen != dlen)
@@ -456,10 +461,12 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn)
 
 		tcp_vu_prepare(c, conn, iov, buf_cnt, &check, !*c->pcap, push);
 
-		if (*c->pcap) {
-			pcap_iov(iov, buf_cnt,
-				 sizeof(struct virtio_net_hdr_mrg_rxbuf));
-		}
+		/* Pad first/single buffer only, it's at least ETH_ZLEN long */
+		l2len = dlen + hdrlen - VNET_HLEN;
+		vu_pad(iov, l2len);
+
+		if (*c->pcap)
+			pcap_iov(iov, buf_cnt, VNET_HLEN);
 
 		conn->seq_to_tap += dlen;
 	}