[PATCH 0/2] vhost-user, dhcp: Fix iPXE network boot over vhost-user

[PATCH 0/2] vhost-user, dhcp: Fix iPXE network boot over vhost-user

[Laurent Vivier]

iPXE network boot over vhost-user was broken because passt
unconditionally skipped TCP/UDP checksum computation, relying on
VIRTIO_NET_HDR_F_DATA_VALID to tell the guest the checksums were
valid.  Linux guests happened to work because their virtio-net driver
honours DATA_VALID regardless of feature negotiation, but iPXE
verifies checksums strictly and never negotiates VIRTIO_NET_F_GUEST_CSUM.

This series handles correctly VIRTIO_NET_F_GUEST_CSUM feature to fix that
and adds a minimal --dhcp-boot option that populates the BOOTP/DHCP 'file'
field, providing just enough for testing iPXE UDP and TCP support.

This can be tested as following:

- Create an ipxe file configuration

cat > boot-alpine.ipxe <<EOF
kernel http://dl-cdn.alpinelinux.org/alpine/v3.23/releases/x86_64/netboot/vmlinuz-lts console=ttyS0,115200 alpine_repo=http://dl-cdn.alpinelinux.org/alpine/v3.23/main modloop=http://dl-cdn.alpinelinux.org/alpine/v3.23/releases/x86_64/netboot/modloop-lts
initrd http://dl-cdn.alpinelinux.org/alpine/v3.23/releases/x86_64/netboot/initramfs-lts
boot
EOF

- Start a web server in the same directory as boot-alpine.ipxe

  python -m http.server 8080

- Start passt:

   ./passt -f --dhcp-boot http://<host ip address>:8080/boot-alpine.ipxe --vhost-user

- Start QEMU without boot disk but with passt as networking backend

Based-on: 20260401215508.2149752-1-lvivier@redhat.com

Laurent Vivier (2):
  vhost_user: Offer VIRTIO_NET_F_GUEST_CSUM
  dhcp: Add --dhcp-boot option to set boot filename in DHCP replies

 conf.c       | 10 ++++++++++
 dhcp.c       |  5 ++++-
 passt.1      |  6 ++++++
 passt.h      |  1 +
 tcp_vu.c     |  8 ++++++--
 udp_vu.c     |  7 ++++---
 vhost_user.c |  1 +
 7 files changed, 32 insertions(+), 6 deletions(-)

-- 
2.53.0

[PATCH 1/2] vhost_user: Offer VIRTIO_NET_F_GUEST_CSUM

[Laurent Vivier]

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>
---
 tcp_vu.c     | 8 ++++++--
 udp_vu.c     | 7 ++++---
 vhost_user.c | 1 +
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/tcp_vu.c b/tcp_vu.c
index 1927b14e0962..49d39e7de201 100644
--- a/tcp_vu.c
+++ b/tcp_vu.c
@@ -126,6 +126,7 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
 	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
 	size_t optlen, hdrlen, iov_cnt, iov_used;
 	struct vu_virtq_element flags_elem[2];
+	uint32_t csum_flags = IP4_CSUM;
 	struct iovec flags_iov[64];
 	struct tcp_syn_opts opts;
 	struct iov_tail payload;
@@ -137,6 +138,9 @@ int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
 	int elem_cnt;
 	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,
@@ -175,7 +179,7 @@ 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);
 	vu_flush(vdev, vq, flags_elem, elem_cnt, hdrlen + optlen);
@@ -516,7 +520,7 @@ 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 5bc9509a1b98..ed888a2baab3 100644
--- a/udp_vu.c
+++ b/udp_vu.c
@@ -234,12 +234,13 @@ void udp_vu_sock_to_tap(const struct ctx *c, int s, int n, flow_sidx_t tosidx)
 		if (iov_cnt > 0) {
 			struct iov_tail data = IOV_TAIL(iov_vu, iov_cnt, VNET_HLEN);
 			size_t l4len = udp_vu_prepare(c, &data, toside, dlen);
-			if (*c->pcap) {
+			if (!vu_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM) ||
+			    *c->pcap)
 				udp_vu_csum(toside, &data, l4len);
+			vu_pad(iov_vu, iov_cnt, hdrlen + dlen);
+			if (*c->pcap)
 				pcap_iov(iov_vu, iov_cnt, VNET_HLEN,
 					 hdrlen + dlen - VNET_HLEN);
-			}
-			vu_pad(iov_vu, iov_cnt, hdrlen + dlen);
 			vu_flush(vdev, vq, elem, elem_used, hdrlen + dlen);
 			vu_queue_notify(vdev, vq);
 		}
diff --git a/vhost_user.c b/vhost_user.c
index f062badd3311..a1259c2624c0 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;
-- 
2.53.0

[PATCH 2/2] dhcp: Add --dhcp-boot option to set boot filename in DHCP replies

[Laurent Vivier]

Add a --dhcp-boot option that populates the 'file' field in DHCP reply
messages with the given filename.

Using --dhcp-boot together with --no-dhcp is rejected at startup.

Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
 conf.c  | 10 ++++++++++
 dhcp.c  |  5 ++++-
 passt.1 |  6 ++++++
 passt.h |  1 +
 4 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/conf.c b/conf.c
index ae37bf96dac4..2cf1bc7420d3 100644
--- a/conf.c
+++ b/conf.c
@@ -984,6 +984,7 @@ static void usage(const char *name, FILE *f, int status)
 		"  --no-udp		Disable UDP protocol handler\n"
 		"  --no-icmp		Disable ICMP/ICMPv6 protocol handler\n"
 		"  --no-dhcp		Disable DHCP server\n"
+		"  --dhcp-boot FILE	DHCP boot filename option\n"
 		"  --no-ndp		Disable NDP responses\n"
 		"  --no-dhcpv6		Disable DHCPv6 server\n"
 		"  --no-ra		Disable router advertisements\n"
@@ -1537,6 +1538,7 @@ void conf(struct ctx *c, int argc, char **argv)
 		{"migrate-exit", no_argument,		NULL,		29 },
 		{"migrate-no-linger", no_argument,	NULL,		30 },
 		{"stats", required_argument,		NULL,		31 },
+		{"dhcp-boot", required_argument,	NULL,		32 },
 		{ 0 },
 	};
 	const char *optstring = "+dqfel:hs:F:I:p:P:m:a:n:M:g:i:o:D:S:H:461t:u:T:U:";
@@ -1775,6 +1777,11 @@ void conf(struct ctx *c, int argc, char **argv)
 				die("Can't display statistics if not running in foreground");
 			c->stats = strtol(optarg, NULL, 0);
 			break;
+		case 32:
+			if (snprintf_check(c->dhcp_boot, sizeof(c->dhcp_boot),
+					   "%s", optarg))
+				die("Invalid DHCP bootfile name: %s", optarg);
+			break;
 		case 'd':
 			c->debug = 1;
 			c->quiet = 0;
@@ -2206,6 +2213,9 @@ void conf(struct ctx *c, int argc, char **argv)
 		c->no_dhcpv6 = 1;
 	}
 
+	if (c->no_dhcp && c->dhcp_boot[0])
+		die("--dhcp-boot cannot be used with --no-dhcp");
+
 	get_dns(c);
 
 	if (!*c->pasta_ifn) {
diff --git a/dhcp.c b/dhcp.c
index 1ff8cba9f93d..7fdb6e051dec 100644
--- a/dhcp.c
+++ b/dhcp.c
@@ -344,6 +344,9 @@ int dhcp(const struct ctx *c, struct iov_tail *data)
 	    m->op != BOOTREQUEST)
 		return -1;
 
+	static_assert(sizeof(reply.file) == sizeof(c->dhcp_boot),
+		      "dhcp_boot must have the same size as reply.file");
+
 	reply.op		= BOOTREPLY;
 	reply.htype		= m->htype;
 	reply.hlen		= m->hlen;
@@ -357,7 +360,7 @@ int dhcp(const struct ctx *c, struct iov_tail *data)
 	reply.giaddr		= m->giaddr;
 	memcpy(&reply.chaddr,	m->chaddr,	sizeof(reply.chaddr));
 	memset(&reply.sname,	0,		sizeof(reply.sname));
-	memset(&reply.file,	0,		sizeof(reply.file));
+	memcpy(&reply.file,	c->dhcp_boot,	sizeof(reply.file));
 	reply.magic		= m->magic;
 
 	for (i = 0; i < ARRAY_SIZE(opts); i++)
diff --git a/passt.1 b/passt.1
index 13e8df9de9f3..a6ac2884bf3f 100644
--- a/passt.1
+++ b/passt.1
@@ -342,6 +342,12 @@ Disable the DHCP server. DHCP client requests coming from guest or target
 namespace will be silently dropped. Implied if there is no gateway on the
 selected IPv4 default route.
 
+.TP
+.BR \-\-dhcp-boot " " \fIfile
+Set the boot filename in DHCP replies to \fIfile\fR. This populates the
+\fIfile\fR field in BOOTP/DHCP reply messages, which can be used for
+network booting (PXE). Cannot be used with \fB--no-dhcp\fR.
+
 .TP
 .BR \-\-no-ndp
 Disable Neighbor Discovery. NDP messages coming from guest or target
diff --git a/passt.h b/passt.h
index 62b8dcdf0a41..4044a4c07ea3 100644
--- a/passt.h
+++ b/passt.h
@@ -255,6 +255,7 @@ struct ctx {
 
 	char hostname[PASST_MAXDNAME];
 	char fqdn[PASST_MAXDNAME];
+	char dhcp_boot[128];
 
 	int ifi6;
 	struct ip6_ctx ip6;
-- 
2.53.0