On Wed, Sep 25, 2024 at 10:11:25AM +0200, Laurent Vivier wrote:TCP header and payload are supposed to be in the same buffer, and tcp_update_check_tcp4()/tcp_update_check_tcp6() compute the checksum from the base address of the header using the length of the IP payload. In the future (for vhost-user) we need to dispatch the TCP header and the TCP payload through several buffers. To be able to manage that, we provide an iovec array that points to the data of the TCP frame. We provide also an offset to be able to provide an array that contains the TCP frame embedded in an lower level frame, and this offset points to the TCP header inside the iovec array. Signed-off-by: Laurent Vivier <lvivier(a)redhat.com> --- Notes: v2: - s/payload_offset/l4offset/ - check memory address of the checksum (alignment, iovec boundaries) checksum.c | 1 - tcp.c | 116 ++++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 88 insertions(+), 29 deletions(-) diff --git a/checksum.c b/checksum.c index 68ffaddb5bb0..4854c1937c39 100644 --- a/checksum.c +++ b/checksum.c @@ -503,7 +503,6 @@ uint16_t csum(const void *buf, size_t len, uint32_t init) * * Return: 16-bit folded, complemented checksum */ -/* cppcheck-suppress unusedFunction */ uint16_t csum_iov(const struct iovec *iov, size_t n, size_t offset, uint32_t init) { diff --git a/tcp.c b/tcp.c index c9472d905520..f0a6f7a507a7 100644 --- a/tcp.c +++ b/tcp.c @@ -755,36 +755,81 @@ static void tcp_sock_set_bufsize(const struct ctx *c, int s) } /** - * tcp_update_check_tcp4() - Update TCP checksum from stored one - * @iph: IPv4 header - * @bp: TCP header followed by TCP payload - */ -static void tcp_update_check_tcp4(const struct iphdr *iph, - struct tcp_payload_t *bp) + * tcp_update_check_tcp4() - Calculate TCP checksum for IPv6Nit: s/IPv6/IPv4/+ * @src: IPv4 source address + * @dst: IPv4 destination address + * @iov: Pointer to the array of IO vectors + * @iov_cnt: Length of the array + * @l4offset: IPv4 payload offset in the iovec array + */ +void tcp_update_check_tcp4(struct in_addr src, + struct in_addr dst, + const struct iovec *iov, int iov_cnt, + size_t l4offset) { - uint16_t l4len = ntohs(iph->tot_len) - sizeof(struct iphdr); - struct in_addr saddr = { .s_addr = iph->saddr }; - struct in_addr daddr = { .s_addr = iph->daddr }; - uint32_t sum = proto_ipv4_header_psum(l4len, IPPROTO_TCP, saddr, daddr); + size_t check_ofs; + __sum16 *check; + int check_idx; + uint32_t sum; + + sum = proto_ipv4_header_psum(iov_size(iov, iov_cnt) - l4offset, + IPPROTO_TCP, src, dst);Previously, we took the size from the IP header, which we'd previously calculated. It seems a shame to replace that with a call to iov_size() which will make another pass through the whole vector.+ + check_idx = iov_skip_bytes(iov, iov_cnt, + l4offset + offsetof(struct tcphdr, check), + &check_ofs); + + if (check_idx >= iov_cnt) + die("TCP4 buffer is too small"); + if (check_ofs + sizeof(*check) > iov[check_idx].iov_len) + die("TCP4 checksum field memory is not contiguous"); + + check = (__sum16 *)((char *)iov[check_idx].iov_base + check_ofs);Strictly speaking, it's UB to even *create* an improperly aligned pointer, even if you never dereference it. So the alignment check should go before casting to (__sum16 *).- bp->th.check = 0; - bp->th.check = csum(bp, l4len, sum); + if ((uintptr_t)check & (__alignof__(*check) - 1)) + die("TCP4 checksum field is not correctly aligned in memory");I really think it would be worth packaging this logic (skip_bytes + contiguous check + alignment check + pointer cast) into another helper (iov_field()?). I strongly suspect we'll have further use for it down the line.+ + *check = 0; + *check = csum_iov(iov, iov_cnt, l4offset, sum); } /** * tcp_update_check_tcp6() - Calculate TCP checksum for IPv6 - * @ip6h: IPv6 header - * @bp: TCP header followed by TCP payload - */ -static void tcp_update_check_tcp6(const struct ipv6hdr *ip6h, - struct tcp_payload_t *bp) + * @src: IPv6 source address + * @dst: IPv6 destination address + * @iov: Pointer to the array of IO vectors + * @iov_cnt: Length of the array + * @l4offset: IPv6 payload offset in the iovec array + */ +void tcp_update_check_tcp6(const struct in6_addr *src, + const struct in6_addr *dst, + const struct iovec *iov, int iov_cnt, + size_t l4offset)Same comments as the IPv4 version here apply here too.{ - uint16_t l4len = ntohs(ip6h->payload_len); - uint32_t sum = proto_ipv6_header_psum(l4len, IPPROTO_TCP, - &ip6h->saddr, &ip6h->daddr); + size_t check_ofs; + __sum16 *check; + int check_idx; + uint32_t sum; + + sum = proto_ipv6_header_psum(iov_size(iov, iov_cnt) - l4offset, + IPPROTO_TCP, src, dst); + + check_idx = iov_skip_bytes(iov, iov_cnt, + l4offset + offsetof(struct tcphdr, check), + &check_ofs); + + if (check_idx >= iov_cnt) + die("TCP6 buffer is too small");Alternatively, you could check the relevant offset against the total size, which you've already calculated. Or indeed, it might make sense to check the total IOV size against the minimum size for a TCP packet somewhere earlier in the call graph. In that case this could become an ASSERT().+ if (check_ofs + sizeof(*check) > iov[check_idx].iov_len) + die("TCP6 checksum field memory is not contiguous"); - bp->th.check = 0; - bp->th.check = csum(bp, l4len, sum); + check = (__sum16 *)((char *)iov[check_idx].iov_base + check_ofs); + + if ((uintptr_t)check & (__alignof__(*check) - 1)) + die("TCP6 checksum field is not correctly aligned in memory"); + + *check = 0; + *check = csum_iov(iov, iov_cnt, l4offset, sum); } /** @@ -935,10 +980,18 @@ static size_t tcp_fill_headers4(const struct tcp_tap_conn *conn, tcp_fill_header(&bp->th, conn, seq); - if (no_tcp_csum) + if (no_tcp_csum) { bp->th.check = 0; - else - tcp_update_check_tcp4(iph, bp); + } else { + const struct iovec iov = { + .iov_base = bp, + .iov_len = ntohs(iph->tot_len) - sizeof(struct iphdr), + }; + struct in_addr saddr = { .s_addr = iph->saddr }; + struct in_addr daddr = { .s_addr = iph->daddr }; + + tcp_update_check_tcp4(saddr, daddr, &iov, 1, 0); + } tap_hdr_update(taph, l3len + sizeof(struct ethhdr)); @@ -980,10 +1033,17 @@ static size_t tcp_fill_headers6(const struct tcp_tap_conn *conn, tcp_fill_header(&bp->th, conn, seq); - if (no_tcp_csum) + if (no_tcp_csum) { bp->th.check = 0; - else - tcp_update_check_tcp6(ip6h, bp); + } else { + const struct iovec iov = { + .iov_base = bp, + .iov_len = ntohs(ip6h->payload_len) + }; + + tcp_update_check_tcp6(&ip6h->saddr, &ip6h->daddr, + &iov, 1, 0); + } tap_hdr_update(taph, l4len + sizeof(*ip6h) + sizeof(struct ethhdr));-- 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