vhost_user: Offer VIRTIO_NET_F_GUEST_CSUM2026_05_26.038c51e

According to the virtio-net specification, when the VIRTIO_NET_F_GUEST_CSUM
is negotiated, the device can set VIRTIO_NET_HDR_F_DATA_VALID in the
virtio-net header to indicate that packet checksums have been validated,
allowing the guest to skip verification. Without this feature, the device
must provide fully checksummed packets.

The vhost-user TCP and UDP paths were unconditionally skipping checksum
computation, regardless of whether GUEST_CSUM was negotiated. This
went undetected with Linux guests because Linux's virtio-net driver
honours VIRTIO_NET_HDR_F_DATA_VALID regardless of whether
VIRTIO_NET_F_GUEST_CSUM was negotiated, marking such packets as
CHECKSUM_UNNECESSARY and skipping verification.

iPXE, however, does not negotiate GUEST_CSUM, ignores the DATA_VALID
flag entirely, and always verifies checksums. This caused TCP
connections to fail: the SYN-ACK had a zero TCP checksum, iPXE rejected
it, and the connection timed out in SYN_RCVD.

Adding --pcap happened to mask the bug, because the pcap code path
forces checksum computation to ensure correct captures.

Offer VIRTIO_NET_F_GUEST_CSUM in the device features, and only skip
checksum computation when the guest has actually negotiated it. When
GUEST_CSUM is not negotiated, always compute valid checksums as required
by the specification.

We keep setting VIRTIO_NET_HDR_F_DATA_VALID unconditionally in
VU_HEADER: when GUEST_CSUM is negotiated, the flag lets the guest skip
checksum verification; when it is not, the spec says the guest should
ignore the flags field, so setting it is harmless.

Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
[sbrivio: Resolved conflicts, in particular with commit dec66c02b5e4
 ("udp: Pass iov_tail to udp_update_hdr4()/udp_update_hdr6()")]
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>

3 files changed, 12 insertions, 4 deletions

diff --git a/tcp_vu.c b/tcp_vu.c
index 3063376..7e2a7db 100644
--- a/tcp_vu.c
+++ b/tcp_vu.c
@@ -129,6 +129,7 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
 	struct vu_virtq_element flags_elem[2];
 	struct iov_tail payload, l2frame;
 	int elem_cnt, dup_elem_cnt = 0;
+	uint32_t csum_flags = IP4_CSUM;
 	struct iovec flags_iov[64];
 	struct tcp_syn_opts opts;
 	struct tcphdr th = { 0 };
@@ -138,6 +139,9 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
 	uint32_t seq;
 	int ret;
 
+	if (*c->pcap || !vu_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
+		csum_flags |= TCP_CSUM;
+
 	hdrlen = tcp_vu_hdrlen(CONN_V6(conn));
 
 	elem_cnt = vu_collect(vdev, vq, &flags_elem[0], 1,
@@ -174,7 +178,7 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
 	iov_from_buf(payload.iov, payload.cnt, payload.off, &opts, optlen);
 	tcp_fill_headers(c, conn, &eh, CONN_V4(conn) ? &ip4h : NULL,
 			 CONN_V6(conn) ? &ip6h : NULL, &th, &payload,
-			 optlen, IP4_CSUM | (*c->pcap ? TCP_CSUM : 0), seq);
+			 optlen, csum_flags, seq);
 
 	vu_pad(flags_elem[0].in_sg, iov_cnt, hdrlen + optlen);
 
@@ -520,7 +524,7 @@ int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn)
 
 	hdrlen = tcp_vu_hdrlen(v6);
 	check = IP4_CSUM;
-	if (*c->pcap)
+	if (*c->pcap || !vu_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
 		check |= TCP_CSUM;
 	for (i = 0, previous_dlen = -1; i < frame_cnt; i++) {
 		struct iovec *iov = &iov_vu[frame[i].idx_iovec];
diff --git a/udp_vu.c b/udp_vu.c
index 4cfe573..e4fb105 100644
--- a/udp_vu.c
+++ b/udp_vu.c
@@ -103,6 +103,7 @@ static void udp_vu_prepare(const struct ctx *c, struct iov_tail *data,
 	bool ipv4 = inany_v4(&toside->eaddr) && inany_v4(&toside->oaddr);
 	struct ethhdr eh;
 	struct udphdr uh;
+	bool no_csum;
 
 	/* ethernet header */
 	memcpy(eh.h_dest, c->guest_mac, sizeof(eh.h_dest));
@@ -114,17 +115,19 @@ static void udp_vu_prepare(const struct ctx *c, struct iov_tail *data,
 		eh.h_proto = htons(ETH_P_IPV6);
 	IOV_PUSH_HEADER(data, eh);
 
+	no_csum = vu_has_feature(c->vdev, VIRTIO_NET_F_GUEST_CSUM) && !*c->pcap;
+
 	/* initialize header */
 	if (ipv4) {
 		struct iphdr iph = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_UDP);
 
-		udp_update_hdr4(&iph, &uh, payload, toside, dlen, !*c->pcap);
+		udp_update_hdr4(&iph, &uh, payload, toside, dlen, no_csum);
 
 		IOV_PUSH_HEADER(data, iph);
 	} else {
 		struct ipv6hdr ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_UDP);
 
-		udp_update_hdr6(&ip6h, &uh, payload, toside, dlen, !*c->pcap);
+		udp_update_hdr6(&ip6h, &uh, payload, toside, dlen, no_csum);
 
 		IOV_PUSH_HEADER(data, ip6h);
 	}
diff --git a/vhost_user.c b/vhost_user.c
index f062bad..a1259c2 100644
--- a/vhost_user.c
+++ b/vhost_user.c
@@ -322,6 +322,7 @@ static bool vu_get_features_exec(struct vu_dev *vdev,
 {
 	uint64_t features =
 		1ULL << VIRTIO_F_VERSION_1 |
+		1ULL << VIRTIO_NET_F_GUEST_CSUM |
 		1ULL << VIRTIO_NET_F_MRG_RXBUF |
 		1ULL << VHOST_F_LOG_ALL |
 		1ULL << VHOST_USER_F_PROTOCOL_FEATURES;