May 2026 - dev

[PATCH v11 3/3] udp: Pass iov_tail to udp_update_hdr4()/udp_update_hdr6()
by Laurent Vivier 20 May '26

20 May '26

Change udp_update_hdr4() and udp_update_hdr6() to take an iov_tail pointing at the UDP frame instead of a contiguous udp_payload_t buffer and explicit data length. This lets vhost-user pass scatter-gather virtqueue buffers directly without an intermediate copy. The UDP header is built into a local struct udphdr and written back with IOV_PUSH_HEADER(). On the tap side, udp_tap_prepare() wraps the existing udp_payload_t in a two-element iov to match the new interface. Signed-off-by: Laurent Vivier <lvivier(a)redhat.com> Reviewed-by: David Gibson <david(a)gibson.dropbear.id.au> --- iov.c | 1 - udp.c | 74 +++++++++++++++++----------------- udp_internal.h | 6 ++- udp_vu.c | 106 ++++++++++++++++++------------------------------- 4 files changed, 78 insertions(+), 109 deletions(-) diff --git a/iov.c b/iov.c index 6a5d7d35b67f..9248ba95a9f2 100644 --- a/iov.c +++ b/iov.c @@ -367,7 +367,6 @@ void *iov_peek_header_(struct iov_tail *tail, void *v, size_t len, size_t align) * * Return: number of bytes written */ -/* cppcheck-suppress unusedFunction */ size_t iov_push_header_(struct iov_tail *tail, const void *v, size_t len) { size_t l; diff --git a/udp.c b/udp.c index 66dc7766868c..c28d6ee2b691 100644 --- a/udp.c +++ b/udp.c @@ -255,20 +255,22 @@ static void udp_iov_init(const struct ctx *c) /** * udp_update_hdr4() - Update headers for one IPv4 datagram * @ip4h: Pre-filled IPv4 header (except for tot_len and saddr) - * @bp: Pointer to udp_payload_t to update + * @uh: UDP header to fill + * @payload: UDP payload * @toside: Flowside for destination side * @dlen: Length of UDP payload * @no_udp_csum: Do not set UDP checksum * - * Return: size of IPv4 payload (UDP header + data) + * Return: size of datagram (UDP header + data) */ -size_t udp_update_hdr4(struct iphdr *ip4h, struct udp_payload_t *bp, +size_t udp_update_hdr4(struct iphdr *ip4h, struct udphdr *uh, + struct iov_tail *payload, const struct flowside *toside, size_t dlen, bool no_udp_csum) { const struct in_addr *src = inany_v4(&toside->oaddr); const struct in_addr *dst = inany_v4(&toside->eaddr); - size_t l4len = dlen + sizeof(bp->uh); + size_t l4len = dlen + sizeof(*uh); size_t l3len = l4len + sizeof(*ip4h); assert(src && dst); @@ -278,19 +280,13 @@ size_t udp_update_hdr4(struct iphdr *ip4h, struct udp_payload_t *bp, ip4h->saddr = src->s_addr; ip4h->check = csum_ip4_header(l3len, IPPROTO_UDP, *src, *dst); - bp->uh.source = htons(toside->oport); - bp->uh.dest = htons(toside->eport); - bp->uh.len = htons(l4len); - if (no_udp_csum) { - bp->uh.check = 0; - } else { - const struct iovec iov = { - .iov_base = bp->data, - .iov_len = dlen - }; - struct iov_tail data = IOV_TAIL(&iov, 1, 0); - csum_udp4(&bp->uh, *src, *dst, &data, dlen); - } + uh->source = htons(toside->oport); + uh->dest = htons(toside->eport); + uh->len = htons(l4len); + if (no_udp_csum) + uh->check = 0; + else + csum_udp4(uh, *src, *dst, payload, dlen); return l4len; } @@ -299,18 +295,20 @@ size_t udp_update_hdr4(struct iphdr *ip4h, struct udp_payload_t *bp, * udp_update_hdr6() - Update headers for one IPv6 datagram * @ip6h: Pre-filled IPv6 header (except for payload_len and * addresses) - * @bp: Pointer to udp_payload_t to update + * @uh: UDP header to fill + * @payload: UDP payload * @toside: Flowside for destination side * @dlen: Length of UDP payload * @no_udp_csum: Do not set UDP checksum * - * Return: size of IPv6 payload (UDP header + data) + * Return: size of datagram (UDP header + data) */ -size_t udp_update_hdr6(struct ipv6hdr *ip6h, struct udp_payload_t *bp, +size_t udp_update_hdr6(struct ipv6hdr *ip6h, struct udphdr *uh, + struct iov_tail *payload, const struct flowside *toside, size_t dlen, bool no_udp_csum) { - uint16_t l4len = dlen + sizeof(bp->uh); + uint16_t l4len = dlen + sizeof(*uh); ip6h->payload_len = htons(l4len); ip6h->daddr = toside->eaddr.a6; @@ -319,23 +317,19 @@ size_t udp_update_hdr6(struct ipv6hdr *ip6h, struct udp_payload_t *bp, ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = 255; - bp->uh.source = htons(toside->oport); - bp->uh.dest = htons(toside->eport); - bp->uh.len = ip6h->payload_len; + uh->source = htons(toside->oport); + uh->dest = htons(toside->eport); + uh->len = htons(l4len); + if (no_udp_csum) { /* 0 is an invalid checksum for UDP IPv6 and dropped by * the kernel stack, even if the checksum is disabled by virtio * flags. We need to put any non-zero value here. */ - bp->uh.check = 0xffff; + uh->check = 0xffff; } else { - const struct iovec iov = { - .iov_base = bp->data, - .iov_len = dlen - }; - struct iov_tail data = IOV_TAIL(&iov, 1, 0); - csum_udp6(&bp->uh, &toside->oaddr.a6, &toside->eaddr.a6, &data, - dlen); + csum_udp6(uh, &toside->oaddr.a6, &toside->eaddr.a6, + payload, dlen); } return l4len; @@ -372,15 +366,20 @@ static void udp_tap_prepare(const struct mmsghdr *mmh, bool no_udp_csum) { struct iovec (*tap_iov)[UDP_NUM_IOVS] = &udp_l2_iov[idx]; + struct udphdr *uh = (*tap_iov)[UDP_IOV_PAYLOAD].iov_base; + struct iov_tail payload = IOV_TAIL(&(*tap_iov)[UDP_IOV_PAYLOAD], 1, + sizeof(*uh)); struct ethhdr *eh = (*tap_iov)[UDP_IOV_ETH].iov_base; - struct udp_payload_t *bp = &udp_payload[idx]; struct udp_meta_t *bm = &udp_meta[idx]; size_t l4len, l2len; + l4len = sizeof(*uh) + mmh[idx].msg_len; + (*tap_iov)[UDP_IOV_PAYLOAD].iov_len = l4len; + eth_update_mac(eh, NULL, tap_omac); if (!inany_v4(&toside->eaddr) || !inany_v4(&toside->oaddr)) { - l4len = udp_update_hdr6(&bm->ip6h, bp, toside, - mmh[idx].msg_len, no_udp_csum); + udp_update_hdr6(&bm->ip6h, uh, &payload, toside, + mmh[idx].msg_len, no_udp_csum); l2len = MAX(l4len + sizeof(bm->ip6h) + ETH_HLEN, ETH_ZLEN); tap_hdr_update(&bm->taph, l2len); @@ -388,8 +387,8 @@ static void udp_tap_prepare(const struct mmsghdr *mmh, eh->h_proto = htons_constant(ETH_P_IPV6); (*tap_iov)[UDP_IOV_IP] = IOV_OF_LVALUE(bm->ip6h); } else { - l4len = udp_update_hdr4(&bm->ip4h, bp, toside, - mmh[idx].msg_len, no_udp_csum); + udp_update_hdr4(&bm->ip4h, uh, &payload, toside, + mmh[idx].msg_len, no_udp_csum); l2len = MAX(l4len + sizeof(bm->ip4h) + ETH_HLEN, ETH_ZLEN); tap_hdr_update(&bm->taph, l2len); @@ -397,7 +396,6 @@ static void udp_tap_prepare(const struct mmsghdr *mmh, eh->h_proto = htons_constant(ETH_P_IP); (*tap_iov)[UDP_IOV_IP] = IOV_OF_LVALUE(bm->ip4h); } - (*tap_iov)[UDP_IOV_PAYLOAD].iov_len = l4len; udp_tap_pad(*tap_iov); } diff --git a/udp_internal.h b/udp_internal.h index 64e457748324..361cc7495a01 100644 --- a/udp_internal.h +++ b/udp_internal.h @@ -25,10 +25,12 @@ struct udp_payload_t { } __attribute__ ((packed, aligned(__alignof__(unsigned int)))); #endif -size_t udp_update_hdr4(struct iphdr *ip4h, struct udp_payload_t *bp, +size_t udp_update_hdr4(struct iphdr *ip4h, struct udphdr *uh, + struct iov_tail *payload, const struct flowside *toside, size_t dlen, bool no_udp_csum); -size_t udp_update_hdr6(struct ipv6hdr *ip6h, struct udp_payload_t *bp, +size_t udp_update_hdr6(struct ipv6hdr *ip6h, struct udphdr *uh, + struct iov_tail *payload, const struct flowside *toside, size_t dlen, bool no_udp_csum); void udp_sock_fwd(const struct ctx *c, int s, int rule_hint, diff --git a/udp_vu.c b/udp_vu.c index 74bf79d57969..4cfe5736d5e8 100644 --- a/udp_vu.c +++ b/udp_vu.c @@ -55,40 +55,33 @@ static size_t udp_vu_hdrlen(bool v6) /** * udp_vu_sock_recv() - Receive datagrams from socket into vhost-user buffers - * @iov: IO vector for the frame (in/out) - * @cnt: Number of available entries in @iov (input) - * Number of used entries in @iov to store the datagram (output) + * @payload: Buffer(s) for UDP payload + * @cnt: Number of used entries in @payload to store the datagram (output) * Unchanged on failure * @s: Socket to receive from - * @v6: Set for IPv6 connections * * Return: size of received data, -1 on error */ -static ssize_t udp_vu_sock_recv(struct iovec *iov, size_t *cnt, int s, bool v6) +static ssize_t udp_vu_sock_recv(struct iov_tail *payload, size_t *cnt, int s) { struct iovec msg_iov[VIRTQUEUE_MAX_SIZE]; struct msghdr msg = { 0 }; - struct iov_tail payload; - size_t hdrlen, iov_used; + size_t iov_used; ssize_t dlen; - /* compute L2 header length */ - hdrlen = udp_vu_hdrlen(v6); - - payload = IOV_TAIL(iov, *cnt, hdrlen); - msg.msg_iov = msg_iov; - msg.msg_iovlen = iov_tail_clone(msg.msg_iov, payload.cnt, &payload); + msg.msg_iovlen = iov_tail_clone(msg.msg_iov, ARRAY_SIZE(msg_iov), + payload); /* read data from the socket */ dlen = recvmsg(s, &msg, 0); if (dlen < 0) return -1; - iov_used = iov_skip_bytes(iov, *cnt, - MAX(dlen + hdrlen, VNET_HLEN + ETH_ZLEN), - NULL); - if (iov_used < *cnt) + iov_used = iov_skip_bytes(payload->iov, payload->cnt, + MAX(dlen + payload->off, + VNET_HLEN + ETH_ZLEN), NULL); + if (iov_used < payload->cnt) iov_used++; *cnt = iov_used; /* one iovec per element */ @@ -98,69 +91,44 @@ static ssize_t udp_vu_sock_recv(struct iovec *iov, size_t *cnt, int s, bool v6) /** * udp_vu_prepare() - Prepare the packet header * @c: Execution context - * @iov: IO vector for the frame (including vnet header) + * @data: IO vector tail for the L2 frame, on return points to the L4 header + * @payload: UDP payload * @toside: Address information for one side of the flow * @dlen: Packet data length */ -static void udp_vu_prepare(const struct ctx *c, const struct iovec *iov, - const struct flowside *toside, ssize_t dlen) +static void udp_vu_prepare(const struct ctx *c, struct iov_tail *data, + struct iov_tail *payload, + const struct flowside *toside, size_t dlen) { - struct ethhdr *eh; + bool ipv4 = inany_v4(&toside->eaddr) && inany_v4(&toside->oaddr); + struct ethhdr eh; + struct udphdr uh; /* ethernet header */ - eh = vu_eth(iov[0].iov_base); + memcpy(eh.h_dest, c->guest_mac, sizeof(eh.h_dest)); + memcpy(eh.h_source, c->our_tap_mac, sizeof(eh.h_source)); - memcpy(eh->h_dest, c->guest_mac, sizeof(eh->h_dest)); - memcpy(eh->h_source, c->our_tap_mac, sizeof(eh->h_source)); + if (ipv4) + eh.h_proto = htons(ETH_P_IP); + else + eh.h_proto = htons(ETH_P_IPV6); + IOV_PUSH_HEADER(data, eh); /* initialize header */ - if (inany_v4(&toside->eaddr) && inany_v4(&toside->oaddr)) { - struct iphdr *iph = vu_ip(iov[0].iov_base); - struct udp_payload_t *bp = vu_payloadv4(iov[0].iov_base); - - eh->h_proto = htons(ETH_P_IP); + if (ipv4) { + struct iphdr iph = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_UDP); - *iph = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_UDP); + udp_update_hdr4(&iph, &uh, payload, toside, dlen, !*c->pcap); - udp_update_hdr4(iph, bp, toside, dlen, true); + IOV_PUSH_HEADER(data, iph); } else { - struct ipv6hdr *ip6h = vu_ip(iov[0].iov_base); - struct udp_payload_t *bp = vu_payloadv6(iov[0].iov_base); + struct ipv6hdr ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_UDP); - eh->h_proto = htons(ETH_P_IPV6); + udp_update_hdr6(&ip6h, &uh, payload, toside, dlen, !*c->pcap); - *ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_UDP); - - udp_update_hdr6(ip6h, bp, toside, dlen, true); - } -} - -/** - * udp_vu_csum() - Calculate and set checksum for a UDP packet - * @toside: Address information for one side of the flow - * @iov: IO vector for the frame - * @cnt: Number of IO vector entries - * @dlen: Data length - */ -static void udp_vu_csum(const struct flowside *toside, const struct iovec *iov, - size_t cnt, size_t dlen) -{ - const struct in_addr *src4 = inany_v4(&toside->oaddr); - const struct in_addr *dst4 = inany_v4(&toside->eaddr); - char *base = iov[0].iov_base; - struct udp_payload_t *bp; - struct iov_tail data; - - if (src4 && dst4) { - bp = vu_payloadv4(base); - data = IOV_TAIL(iov, cnt, (char *)&bp->data - base); - csum_udp4(&bp->uh, *src4, *dst4, &data, dlen); - } else { - bp = vu_payloadv6(base); - data = IOV_TAIL(iov, cnt, (char *)&bp->data - base); - csum_udp6(&bp->uh, &toside->oaddr.a6, &toside->eaddr.a6, &data, - dlen); + IOV_PUSH_HEADER(data, ip6h); } + IOV_PUSH_HEADER(data, uh); } /** @@ -198,6 +166,7 @@ void udp_vu_sock_to_tap(const struct ctx *c, int s, int n, flow_sidx_t tosidx) for (i = 0; i < n; i++) { unsigned elem_cnt, elem_used, j, k; + struct iov_tail payload; size_t iov_cnt; ssize_t dlen; @@ -207,7 +176,8 @@ void udp_vu_sock_to_tap(const struct ctx *c, int s, int n, flow_sidx_t tosidx) if (elem_cnt == 0) break; - dlen = udp_vu_sock_recv(iov_vu, &iov_cnt, s, v6); + payload = IOV_TAIL(iov_vu, iov_cnt, hdrlen); + dlen = udp_vu_sock_recv(&payload, &iov_cnt, s); if (dlen < 0) { vu_queue_rewind(vq, elem_cnt); break; @@ -227,9 +197,9 @@ void udp_vu_sock_to_tap(const struct ctx *c, int s, int n, flow_sidx_t tosidx) vu_queue_rewind(vq, elem_cnt - elem_used); if (iov_cnt > 0) { - udp_vu_prepare(c, iov_vu, toside, dlen); + struct iov_tail data = IOV_TAIL(iov_vu, iov_cnt, VNET_HLEN); + udp_vu_prepare(c, &data, &payload, toside, dlen); if (*c->pcap) { - udp_vu_csum(toside, iov_vu, iov_cnt, dlen); pcap_iov(iov_vu, iov_cnt, VNET_HLEN, hdrlen + dlen - VNET_HLEN); } -- 2.54.0

1 0

[PATCH v11 2/3] iov: Introduce IOV_PUSH_HEADER() macro
by Laurent Vivier 20 May '26

20 May '26

Add iov_push_header_() and its typed wrapper IOV_PUSH_HEADER() to write a header into an iov_tail at the current offset and advance past it. This is the write counterpart to IOV_PEEK_HEADER() / IOV_REMOVE_HEADER(), using iov_from_buf() to copy the header data across iovec boundaries. Signed-off-by: Laurent Vivier <lvivier(a)redhat.com> Reviewed-by: David Gibson <david(a)gibson.dropbear.id.au> --- iov.c | 31 +++++++++++++++++++++++++++++++ iov.h | 11 +++++++++++ 2 files changed, 42 insertions(+) diff --git a/iov.c b/iov.c index 7c18941c0395..6a5d7d35b67f 100644 --- a/iov.c +++ b/iov.c @@ -359,6 +359,37 @@ void *iov_peek_header_(struct iov_tail *tail, void *v, size_t len, size_t align) return v; } +/** + * iov_push_header_() - Write a new header to an IOV tail + * @tail: IOV tail to write header to + * @v: Pointer to header data to write + * @len: Length of header to write, in bytes + * + * Return: number of bytes written + */ +/* cppcheck-suppress unusedFunction */ +size_t iov_push_header_(struct iov_tail *tail, const void *v, size_t len) +{ + size_t l; + + if (!iov_tail_prune(tail)) + return 0; /* No space */ + + if ((char *)tail->iov[0].iov_base + tail->off == v) /* already in place */ + l = len; + else + l = iov_from_buf(tail->iov, tail->cnt, tail->off, v, len); + + if (l != len) { + warn("iov_push_header_(): Not enough space to store header" + " (%zu != %zu)", l, len); + } + + tail->off = tail->off + l; + + return l; +} + /** * iov_remove_header_() - Remove a header from an IOV tail * @tail: IOV tail to remove header from (modified) diff --git a/iov.h b/iov.h index 3c63308e554f..4fdf14a85b19 100644 --- a/iov.h +++ b/iov.h @@ -93,6 +93,7 @@ bool iov_tail_prune(struct iov_tail *tail); size_t iov_tail_size(struct iov_tail *tail); bool iov_drop_header(struct iov_tail *tail, size_t len); void *iov_peek_header_(struct iov_tail *tail, void *v, size_t len, size_t align); +size_t iov_push_header_(struct iov_tail *tail, const void *v, size_t len); void *iov_remove_header_(struct iov_tail *tail, void *v, size_t len, size_t align); ssize_t iov_tail_clone(struct iovec *dst_iov, size_t dst_iov_cnt, struct iov_tail *tail); @@ -115,6 +116,16 @@ ssize_t iov_tail_clone(struct iovec *dst_iov, size_t dst_iov_cnt, sizeof(var_), \ __alignof__(var_)))) +/** + * IOV_PUSH_HEADER() - Write a new header to an IOV tail + * @tail_: IOV tail to write header to + * @var_: A variable containing the header data to write + * + * Return: number of bytes written + */ +#define IOV_PUSH_HEADER(tail_, var_) \ + (iov_push_header_((tail_), &(var_), sizeof(var_))) + /** * IOV_REMOVE_HEADER() - Remove and return typed header from an IOV tail * @tail_: IOV tail to remove header from (modified) -- 2.54.0

1 0

[PATCH v11 1/3] udp_vu: Allow virtqueue elements with multiple iovec entries
by Laurent Vivier 20 May '26

20 May '26

The previous code assumed a 1:1 mapping between virtqueue elements and iovec entries (enforced by an assert). Drop that assumption to allow elements that span multiple iovecs: track elem_used separately by walking the element list against the iov count returned after padding. This also fixes vu_queue_rewind() and vu_flush() to use the element count rather than the iov count. Use iov_tail_clone() in udp_vu_sock_recv() to handle header offset, replacing the manual base/len adjustment and restore pattern. Signed-off-by: Laurent Vivier <lvivier(a)redhat.com> Reviewed-by: David Gibson <david(a)gibson.dropbear.id.au> Reviewed-by: Jon Maloy <jmaloy(a)redhat.com> --- udp_vu.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/udp_vu.c b/udp_vu.c index dfff7bb1cd53..74bf79d57969 100644 --- a/udp_vu.c +++ b/udp_vu.c @@ -66,30 +66,25 @@ static size_t udp_vu_hdrlen(bool v6) */ static ssize_t udp_vu_sock_recv(struct iovec *iov, size_t *cnt, int s, bool v6) { + struct iovec msg_iov[VIRTQUEUE_MAX_SIZE]; struct msghdr msg = { 0 }; + struct iov_tail payload; size_t hdrlen, iov_used; ssize_t dlen; /* compute L2 header length */ hdrlen = udp_vu_hdrlen(v6); - /* reserve space for the headers */ - assert(iov[0].iov_len >= MAX(hdrlen, ETH_ZLEN + VNET_HLEN)); - iov[0].iov_base = (char *)iov[0].iov_base + hdrlen; - iov[0].iov_len -= hdrlen; + payload = IOV_TAIL(iov, *cnt, hdrlen); - /* read data from the socket */ - msg.msg_iov = iov; - msg.msg_iovlen = *cnt; + msg.msg_iov = msg_iov; + msg.msg_iovlen = iov_tail_clone(msg.msg_iov, payload.cnt, &payload); + /* read data from the socket */ dlen = recvmsg(s, &msg, 0); if (dlen < 0) return -1; - /* restore the pointer to the headers address */ - iov[0].iov_base = (char *)iov[0].iov_base - hdrlen; - iov[0].iov_len += hdrlen; - iov_used = iov_skip_bytes(iov, *cnt, MAX(dlen + hdrlen, VNET_HLEN + ETH_ZLEN), NULL); @@ -202,7 +197,7 @@ void udp_vu_sock_to_tap(const struct ctx *c, int s, int n, flow_sidx_t tosidx) } for (i = 0; i < n; i++) { - unsigned elem_cnt, elem_used; + unsigned elem_cnt, elem_used, j, k; size_t iov_cnt; ssize_t dlen; @@ -212,15 +207,21 @@ void udp_vu_sock_to_tap(const struct ctx *c, int s, int n, flow_sidx_t tosidx) if (elem_cnt == 0) break; - assert((size_t)elem_cnt == iov_cnt); /* one iovec per element */ - dlen = udp_vu_sock_recv(iov_vu, &iov_cnt, s, v6); if (dlen < 0) { vu_queue_rewind(vq, elem_cnt); break; } - elem_used = iov_cnt; /* one iovec per element */ + elem_used = 0; + for (j = 0, k = 0; k < iov_cnt && j < elem_cnt; j++) { + size_t iov_still_needed = iov_cnt - k; + + if (elem[j].in_num > iov_still_needed) + elem[j].in_num = iov_still_needed; + k += elem[j].in_num; + elem_used++; + } /* release unused buffers */ vu_queue_rewind(vq, elem_cnt - elem_used); -- 2.54.0

1 0

[PATCH v11 0/3] vhost-user,udp: Handle multiple iovec entries per virtqueue element
by Laurent Vivier 20 May '26

20 May '26

Some virtio-net drivers (notably iPXE) provide descriptors where the vnet header and the frame payload are in separate buffers, resulting in two iovec entries per virtqueue element. Currently, the RX (host to guest) path assumes a single iovec per element, which triggers: ASSERTION FAILED in virtqueue_map_desc (virtio.c:403): num_sg < max_num_sg This series reworks the UDP vhost-user receive path to support multiple iovec entries per element, fixing the iPXE crash. This series only addresses the UDP path. TCP vhost-user will be updated to use multi-iov elements in a subsequent series. v11: - Rebase on master - use sizeof(*uh) instead of sizeof(struct udphdr) in udp_tap_prepare() - improve @payload doc in udp_vu_sock_recv() - add R-b from David v10: - udp_update_hdr4()/udp_update_hdr6(): take separate @uh pointer and @payload - udp_tap_prepare(): extract uh from UDP_IOV_PAYLOAD, @payload is UDP payload only - udp_vu_sock_recv(): extract UDP payload from the function - udp_vu_prepare(): take @payload as parameter, compute checksum conditionally via !*c->pcap instead of hardcoded true - udp_vu_csum(): removed v9: - iov_push_header_(): skip memcpy() when the source pointer already aliases the iov buffer - udp_update_hdr4()//udp_update_hdr6()/usp_csum(): update payload doc - udp_tap_prepare(): use existing (*tap_iov)[UDP_IOV_PAYLOAD] v8: - Add Reviewed-by from David for 1/3 and 2/3 - Remove VLA to use fixed size (VIRTQUEUE_MAX_SIZE) - Rename udp_frame to datagram - Use sizeof(uh) instead of sizeof(struct udphdr) - Push back uh in memory in udp_vu_csum() v7: - In udp_vu_sock_to_tap(), introduce iov_still_needed variable - Fix iov_tail @data doc comments in udp_vu_prepare()/udp_vu_csum() - Don't rewrap the virtio checksum comment in udp_update_hdr6() - Add NULL check for uh in udp_vu_csum() v6: - Rebased on top of [PATCH 00/10] vhost-user: Preparatory series for multiple iovec entries per virtqueue element v5: - This version doesn't change the padding system regarding v4, it's a complex task that will be addressed in another version - reorder patches and add new patches - remove IOV_PUT_HEADER()/with_header() and introduce IOV_PUSH_HEADER() - don't use the iov_tail to provide the headers to the functions - move vu_set_vnethdr() to vu_flush(), extract vu_queue_notify() - move vu_flush() inside loop in tcp_vu_data_from_sock() to flush data by frame and not by full data length v4: - rebase - replace ASSERT() by assert() v3: - include the series "Decouple iovec management from virtqueues elements" - because of this series, drop: "vu_common: Accept explicit iovec counts in vu_set_element()" "vu_common: Accept explicit iovec count per element in vu_init_elem()" "vu_common: Prepare to use multibuffer with guest RX" "vhost-user,udp: Use 2 iovec entries per element" - drop "vu_common: Pass iov_tail to vu_set_vnethdr()" as the specs insures a buffer is big enough to contain vnet header - introduce "with_header()" and merge "udp: Pass iov_tail to udp_update_hdr4()/udp_update_hdr6()" and "udp_vu: Use iov_tail in udp_vu_prepare()" to use it v2: - add iov_truncate(), iov_memset() - remove iov_tail_truncate() and iov_tail_zero_end() - manage 802.3 minimum frame size Laurent Vivier (3): udp_vu: Allow virtqueue elements with multiple iovec entries iov: Introduce IOV_PUSH_HEADER() macro udp: Pass iov_tail to udp_update_hdr4()/udp_update_hdr6() iov.c | 30 ++++++++++++ iov.h | 11 +++++ udp.c | 74 ++++++++++++++-------------- udp_internal.h | 6 ++- udp_vu.c | 129 +++++++++++++++++++------------------------------ 5 files changed, 131 insertions(+), 119 deletions(-) -- 2.54.0

1 0

[PATCH RFT] fwd: Only do inbound IPv6 NAT to map_host_loopback / map_guest_addr with matching scope
by Stefano Brivio 20 May '26

20 May '26

I'm sharing this mostly for debugging / investigation of: https://github.com/containers/container-libs/pull/755#issuecomment-43904201… even though the change is probably correct and needed regardless of that. If we have map_guest_addr or map_host_loopback addresses set for IPv6, before using them for inbound NAT from the host, make sure they match the scope of the original packet, otherwise we might unexpectedly turn global unicast addresses into link-local ones for packets coming from the host itself. Link: https://github.com/containers/container-libs/pull/755#issuecomment-43904201… Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- fwd.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/fwd.c b/fwd.c index 0697435..d224c0a 100644 --- a/fwd.c +++ b/fwd.c @@ -974,6 +974,20 @@ uint8_t fwd_nat_from_splice(const struct fwd_rule *rule, uint8_t proto, return PIF_HOST; } +/** + * fwd_scope6_match() - Check if the IPv6 scope of two addresses match + * @a: First address + * @b: Second address + * + * Return: true for two IPv6 link-local or both not link-local, false otherwise + * + * NOTE: This currently ignores any other difference in scope + */ +bool fwd_scope6_match(const struct in6_addr *a, const struct in6_addr *b) +{ + return IN6_IS_ADDR_LINKLOCAL(a) == IN6_IS_ADDR_LINKLOCAL(b); +} + /** * nat_inbound() - Apply address translation for inbound (HOST to TAP) * @c: Execution context @@ -993,13 +1007,15 @@ bool nat_inbound(const struct ctx *c, const union inany_addr *addr, /* Specifically 127.0.0.1, not 127.0.0.0/8 */ *translated = inany_from_v4(c->ip4.map_host_loopback); } else if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.map_host_loopback) && - inany_equals6(addr, &in6addr_loopback)) { + inany_equals6(addr, &in6addr_loopback) && + fwd_scope6_match(&addr->a6, &c->ip6.map_host_loopback)) { translated->a6 = c->ip6.map_host_loopback; } else if (!IN4_IS_ADDR_UNSPECIFIED(&c->ip4.map_guest_addr) && inany_equals4(addr, &c->ip4.addr)) { *translated = inany_from_v4(c->ip4.map_guest_addr); } else if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.map_guest_addr) && - inany_equals6(addr, &c->ip6.addr)) { + inany_equals6(addr, &c->ip6.addr) && + fwd_scope6_match(&addr->a6, &c->ip6.map_guest_addr)) { translated->a6 = c->ip6.map_guest_addr; } else if (fwd_guest_accessible(c, addr)) { *translated = *addr; -- 2.43.0

2 7

[PATCH HACK] fwd, fwd_rule: Implement configurable destination address mapping
by Stefano Brivio 20 May '26

20 May '26

This isn't complete, it's rather a quick hack to enable early integration testing. Add a 'daddr' field to forwarding rules, and some rudimentary parsing. Format (for either command line or pesto): -t 2222:192.0.2.1/2222 This should work along with all the other bits, that is, say: -t 192.0.2.1%eth0/2222-2225:192.0.2.2/22-25 Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- fwd.c | 4 +++- fwd_rule.c | 46 +++++++++++++++++++++++++++++++++++----------- fwd_rule.h | 2 ++ 3 files changed, 40 insertions(+), 12 deletions(-) diff --git a/fwd.c b/fwd.c index d224c0a..75db350 100644 --- a/fwd.c +++ b/fwd.c @@ -1095,7 +1095,9 @@ uint8_t fwd_nat_from_host(const struct ctx *c, } tgt->oport = ini->eport; - if (inany_v4(&tgt->oaddr)) { + if (!inany_is_unspecified(&rule->daddr)) { + tgt->eaddr = rule->daddr; + } else if (inany_v4(&tgt->oaddr)) { tgt->eaddr = inany_from_v4(c->ip4.addr_seen); } else { if (inany_is_linklocal6(&tgt->oaddr)) diff --git a/fwd_rule.c b/fwd_rule.c index 5fc04d7..5bce2fb 100644 --- a/fwd_rule.c +++ b/fwd_rule.c @@ -465,6 +465,7 @@ static int parse_keyword(const char *s, const char **endptr, const char *kw) */ static void fwd_rule_range_except(struct fwd_table *fwd, bool del, uint8_t proto, const union inany_addr *addr, + const union inany_addr *daddr, const char *ifname, uint16_t first, uint16_t last, const uint8_t *exclude, uint16_t to, @@ -472,6 +473,7 @@ static void fwd_rule_range_except(struct fwd_table *fwd, bool del, { struct fwd_rule rule = { .addr = addr ? *addr : inany_any6, + .daddr = daddr ? *daddr : inany_any6, .ifname = { 0 }, .proto = proto, .flags = flags, @@ -544,13 +546,13 @@ fail: */ static void fwd_rule_parse_ports(struct fwd_table *fwd, bool del, uint8_t proto, const union inany_addr *addr, - const char *ifname, - const char *spec) + const char *ifname, char *spec) { + union inany_addr daddr_buf = inany_any6, *daddr = &daddr_buf; uint8_t exclude[PORT_BITMAP_SIZE] = { 0 }; bool exclude_only = true; - const char *p, *ep; uint8_t flags = 0; + char *p, *ep; unsigned i; if (!strcmp(spec, "all")) { @@ -568,7 +570,7 @@ static void fwd_rule_parse_ports(struct fwd_table *fwd, bool del, uint8_t proto, continue; } - if (parse_keyword(p, &p, "auto") == 0) { + if (parse_keyword(p, (const char **)&p, "auto") == 0) { if (p != ep) /* Garbage after the keyword */ goto bad; @@ -586,7 +588,7 @@ static void fwd_rule_parse_ports(struct fwd_table *fwd, bool del, uint8_t proto, goto bad; p++; - if (parse_port_range(p, &p, &xrange)) + if (parse_port_range(p, (const char **)&p, &xrange)) goto bad; if (p != ep) /* Garbage after the range */ goto bad; @@ -599,7 +601,7 @@ static void fwd_rule_parse_ports(struct fwd_table *fwd, bool del, uint8_t proto, /* Exclude ephemeral ports */ fwd_port_map_ephemeral(exclude); - fwd_rule_range_except(fwd, del, proto, addr, ifname, + fwd_rule_range_except(fwd, del, proto, addr, NULL, ifname, 1, NUM_PORTS - 1, exclude, 1, flags | FWD_WEAK); return; @@ -613,11 +615,32 @@ static void fwd_rule_parse_ports(struct fwd_table *fwd, bool del, uint8_t proto, /* Already parsed */ continue; - if (parse_port_range(p, &p, &orig_range)) + if (parse_port_range(p, (const char **)&p, &orig_range)) goto bad; - if (*p == ':') { /* There's a range to map to as well */ - if (parse_port_range(p + 1, &p, &mapped_range)) + if (*p == ':') { + /* There's a range or address to map to as well */ + char *addr_end = strchr(p, '/'); + + if (addr_end) { + *addr_end = '\0'; + + if (*p == '[' && p[strlen(p) - 1] == ']') { + p[strlen(p) - 1] = '\0'; + p++; + } + + if (!inany_pton(p + 1, daddr)) + die("Bad forwarding address '%s'", p); + + p = addr_end; + } else { + daddr = NULL; + } + + + if (parse_port_range(p + 1, (const char **)&p, + &mapped_range)) goto bad; if ((mapped_range.last - mapped_range.first) != (orig_range.last - orig_range.first)) @@ -629,7 +652,7 @@ static void fwd_rule_parse_ports(struct fwd_table *fwd, bool del, uint8_t proto, if (p != ep) /* Garbage after the ranges */ goto bad; - fwd_rule_range_except(fwd, del, proto, addr, ifname, + fwd_rule_range_except(fwd, del, proto, addr, daddr, ifname, orig_range.first, orig_range.last, exclude, mapped_range.first, flags); @@ -675,7 +698,8 @@ void fwd_rule_parse(char optname, bool del, const char *optarg, strncpy(buf, optarg, sizeof(buf) - 1); - if ((spec = strchr(buf, '/'))) { + if ((spec = strchr(buf, '/')) && + strchr(spec, ':') == strchr(buf, ':')) { *spec = 0; spec++; diff --git a/fwd_rule.h b/fwd_rule.h index ae9a3cb..3a2a809 100644 --- a/fwd_rule.h +++ b/fwd_rule.h @@ -35,6 +35,7 @@ /** * struct fwd_rule - Forwarding rule governing a range of ports * @addr: Address to forward from + * @daddr: Optional address to set as destination when forwarding * @ifname: Interface to forward from * @first: First port number to forward * @last: Last port number to forward @@ -47,6 +48,7 @@ */ struct fwd_rule { union inany_addr addr; + union inany_addr daddr; char ifname[IFNAMSIZ]; in_port_t first; in_port_t last; -- 2.43.0

2 5

[PATCH v3 00/12] Improvements to static checker invocation
by David Gibson 20 May '26

20 May '26

While working on pesto, I ran into a number of awkward errors with the static checkers. This series reworks the invocation of the checkers in a way that will let us deal with that. As a bonus, it also gives us static checking for passt-repair. It also a number of other cleanups to the Makefile that seemed natural along the way. v3: - Rework changes to $(FLAGS) so they're much less likely to have side effects we're not ready for. v2: - Fixed nasty test failure in test/build/build.py David Gibson (12): Makefile: Use make variables for static checker configuration Makefile: Make conditional definition of $(BIN) clearer Makefile: Use common binary compilation rule Makefile: Remove unhelpful $(HEADERS) variable Makefile: Add header dependencies for secondary binaries Makefile: Split $(FLAGS) into cpp and cc components cppcheck, clang-tidy: Static checkers don't need non-preprocessor flags Makefile: Split static checker targets passt-repair: Split out inotify handling to its own function passt-repair: Simplify construction of Unix path from inotify passt-repair: Run static checkers pesto: Run static checkers on pesto sources Makefile | 135 ++++++++++++++++++++++++-------------- linux_dep.h | 2 +- passt-repair.c | 171 +++++++++++++++++++++++++++---------------------- pesto.c | 1 - 4 files changed, 182 insertions(+), 127 deletions(-) -- 2.54.0

2 18

[PATCH] Makefile: Remove misleading comments on BASE_*FLAGS
by David Gibson 20 May '26

20 May '26

I added these comments attempting to describe the difference between BASE_CFLAGS and CFLAGS. However, the description given isn't really accurate, and I'm not even sure the concept I'm trying to describe is coherent. Just remove it. Suggested-by: Stefano Brivio <sbrivio(a)redhat.com> Signed-off-by: David Gibson <david(a)gibson.dropbear.id.au> --- Makefile | 4 ---- 1 file changed, 4 deletions(-) diff --git a/Makefile b/Makefile index c4af57b4..0a0a60b0 100644 --- a/Makefile +++ b/Makefile @@ -30,15 +30,11 @@ ifeq ($(shell $(CC) -O2 -dM -E - < /dev/null 2>&1 | grep ' _FORTIFY_SOURCE ' > / FORTIFY_FLAG := -D_FORTIFY_SOURCE=2 endif -# Mandatory preprocessor flags that won't be overridden with $(CPPFLAGS) -# FIXME: Could some of these be default, rather than required? BASE_CPPFLAGS := -D_XOPEN_SOURCE=700 -D_GNU_SOURCE $(FORTIFY_FLAG) BASE_CPPFLAGS += -DPAGE_SIZE=$(shell getconf PAGE_SIZE) BASE_CPPFLAGS += -DVERSION=\"$(VERSION)\" BASE_CPPFLAGS += -DDUAL_STACK_SOCKETS=$(DUAL_STACK_SOCKETS) -# Mandatory compiler flags that won't be overridden with $(CFLAGS) -# FIXME: Could some of these be default, rather than required? BASE_CFLAGS := -std=c11 -pie -fPIE -O2 BASE_CFLAGS += -pedantic -Wall -Wextra -Wno-format-zero-length -Wformat-security -- 2.54.0

1 0

[PATCH v10 0/3] vhost-user,udp: Handle multiple iovec entries per virtqueue element
by Laurent Vivier 20 May '26

20 May '26

Some virtio-net drivers (notably iPXE) provide descriptors where the vnet header and the frame payload are in separate buffers, resulting in two iovec entries per virtqueue element. Currently, the RX (host to guest) path assumes a single iovec per element, which triggers: ASSERTION FAILED in virtqueue_map_desc (virtio.c:403): num_sg < max_num_sg This series reworks the UDP vhost-user receive path to support multiple iovec entries per element, fixing the iPXE crash. This series only addresses the UDP path. TCP vhost-user will be updated to use multi-iov elements in a subsequent series. Based-on: 20260513115218.1662850-1-lvivier(a)redhat.com v10: - udp_update_hdr4()/udp_update_hdr6(): take separate @uh pointer and @payload - udp_tap_prepare(): extract uh from UDP_IOV_PAYLOAD, @payload is UDP payload only - udp_vu_sock_recv(): extract UDP payload from the function - udp_vu_prepare(): take @payload as parameter, compute checksum conditionally via !*c->pcap instead of hardcoded true - udp_vu_csum(): removed v9: - iov_push_header_(): skip memcpy() when the source pointer already aliases the iov buffer - udp_update_hdr4()//udp_update_hdr6()/usp_csum(): update payload doc - udp_tap_prepare(): use existing (*tap_iov)[UDP_IOV_PAYLOAD] v8: - Add Reviewed-by from David for 1/3 and 2/3 - Remove VLA to use fixed size (VIRTQUEUE_MAX_SIZE) - Rename udp_frame to datagram - Use sizeof(uh) instead of sizeof(struct udphdr) - Push back uh in memory in udp_vu_csum() v7: - In udp_vu_sock_to_tap(), introduce iov_still_needed variable - Fix iov_tail @data doc comments in udp_vu_prepare()/udp_vu_csum() - Don't rewrap the virtio checksum comment in udp_update_hdr6() - Add NULL check for uh in udp_vu_csum() v6: - Rebased on top of [PATCH 00/10] vhost-user: Preparatory series for multiple iovec entries per virtqueue element v5: - This version doesn't change the padding system regarding v4, it's a complex task that will be addressed in another version - reorder patches and add new patches - remove IOV_PUT_HEADER()/with_header() and introduce IOV_PUSH_HEADER() - don't use the iov_tail to provide the headers to the functions - move vu_set_vnethdr() to vu_flush(), extract vu_queue_notify() - move vu_flush() inside loop in tcp_vu_data_from_sock() to flush data by frame and not by full data length v4: - rebase - replace ASSERT() by assert() v3: - include the series "Decouple iovec management from virtqueues elements" - because of this series, drop: "vu_common: Accept explicit iovec counts in vu_set_element()" "vu_common: Accept explicit iovec count per element in vu_init_elem()" "vu_common: Prepare to use multibuffer with guest RX" "vhost-user,udp: Use 2 iovec entries per element" - drop "vu_common: Pass iov_tail to vu_set_vnethdr()" as the specs insures a buffer is big enough to contain vnet header - introduce "with_header()" and merge "udp: Pass iov_tail to udp_update_hdr4()/udp_update_hdr6()" and "udp_vu: Use iov_tail in udp_vu_prepare()" to use it v2: - add iov_truncate(), iov_memset() - remove iov_tail_truncate() and iov_tail_zero_end() - manage 802.3 minimum frame size Laurent Vivier (3): udp_vu: Allow virtqueue elements with multiple iovec entries iov: Introduce IOV_PUSH_HEADER() macro udp: Pass iov_tail to udp_update_hdr4()/udp_update_hdr6() iov.c | 30 ++++++++++++ iov.h | 11 +++++ udp.c | 74 ++++++++++++++-------------- udp_internal.h | 6 ++- udp_vu.c | 129 +++++++++++++++++++------------------------------ 5 files changed, 131 insertions(+), 119 deletions(-) -- 2.54.0

2 4

Re: [PATCH v9 3/3] udp: Pass iov_tail to udp_update_hdr4()/udp_update_hdr6()
by David Gibson 20 May '26

20 May '26

On Wed, May 20, 2026 at 11:07:50AM +1000, David Gibson wrote: > On Tue, May 19, 2026 at 10:03:39AM +0200, Laurent Vivier wrote: > > On 5/19/26 07:08, David Gibson wrote: > > > On Mon, May 18, 2026 at 02:26:25PM +0200, Laurent Vivier wrote: > > > > Change udp_update_hdr4() and udp_update_hdr6() to take an iov_tail > > > > pointing at the UDP frame instead of a contiguous udp_payload_t buffer > > > > and explicit data length. This lets vhost-user pass scatter-gather > > > > virtqueue buffers directly without an intermediate copy. > > > > > > > > The UDP header is built into a local struct udphdr and written back with > > > > IOV_PUSH_HEADER(). On the tap side, udp_tap_prepare() wraps the > > > > existing udp_payload_t in a two-element iov to match the new interface. > > > > > > > > Signed-off-by: Laurent Vivier <lvivier(a)redhat.com> > > > > > > Alas, this still has a potentially aliased memcpy(), see below. > > > > Did you see I updated patch 2 to avoid the memcpy() if the header is > > already in place? > > (I think I should have removed your R-b...) > > I saw the note in the changelog, but I didn't spot the place in the > code specifically - I think I skipped patch 2 because of the R-b and > assumed the change was in patch 3. Unfortunately the one in this > patch is still there. Duh, sorry, I misunderstood how you were fixing the problem. I see you changed PUSH_HEADER to be safe in this circumstance, which does also fix the case in patch 3. Will have that in mind when I review v10. -- David Gibson (he or they) | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you, not the other way | around. http://www.ozlabs.org/~dgibson

1 0