[PATCH OLK-5.10 00/14] CVE-2026-74724
Florian Westphal (4): netfilter: ipvs: prepare for hook function reduction netfilter: ipvs: remove unneeded output wrappers netfilter: ipvs: remove unneeded input wrappers netfilter: ipvs: merge ipv4 + ipv6 icmp reply handlers Julian Anastasov (9): ipvs: skip ipv6 extension headers for csum checks ipvs: fix the checksum validations ipvs: fix more places with wrong ipv6 transport offsets ipvs: ensure inner headers in ICMP errors are in headroom ipvs: fix places with wrong packet offsets ipvs: do not mangle ICMP replies for non-first fragments ipvs: avoid out-of-bounds write in ip_vs_nat_icmp ipvs: return the csum validation for forward hook ipvs: revalidate ihl to prevent out-of-bounds access Yizhou Zhao (1): ipvs: fix PMTU for GUE/GRE tunnel ICMP errors include/net/ip6_fib.h | 2 + include/net/ip_vs.h | 38 +++- net/netfilter/ipvs/ip_vs_app.c | 10 +- net/netfilter/ipvs/ip_vs_core.c | 416 +++++++++++++--------------------- net/netfilter/ipvs/ip_vs_proto_sctp.c | 29 ++- net/netfilter/ipvs/ip_vs_proto_tcp.c | 59 +---- net/netfilter/ipvs/ip_vs_proto_udp.c | 64 ++---- net/netfilter/ipvs/ip_vs_xmit.c | 43 +++- 8 files changed, 268 insertions(+), 393 deletions(-) -- 2.9.5
反馈： 您发送到kernel@openeuler.org的补丁/补丁集，已成功转换为PR！ PR链接地址： https://gitcode.com/openeuler/kernel/merge_requests/29163 邮件列表地址：https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/MBH... FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://gitcode.com/openeuler/kernel/merge_requests/29163 Mailing list address: https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/MBH...
From: Florian Westphal <fw@strlen.de> mainline inclusion from mainline-v5.16-rc1 commit 9dd43a5f4b11b161c9dfcce9391e843e65d6a4cc category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- ipvs has multiple one-line wrappers for hooks, compact them. To avoid a large patch make the two most common helpers use the same function signature as hooks. Next patches can then remove the oneline wrappers. Signed-off-by: Florian Westphal <fw@strlen.de> Acked-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Conflicts: net/netfilter/ipvs/ip_vs_core.c [commit c341179244f9 ("netfilter: ipvs: Fix reuse connection if RS weight is 0") remove conn_reuse_mode] Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- net/netfilter/ipvs/ip_vs_core.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 3a76da5..09d5f8b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1342,12 +1342,15 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int -ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) +ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { + struct netns_ipvs *ipvs = net_ipvs(state->net); + unsigned int hooknum = state->hook; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; + int af = state->pf; struct sock *sk; EnterFunction(11); @@ -1489,7 +1492,7 @@ static unsigned int ip_vs_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); + return ip_vs_out_hook(priv, skb, state); } /* @@ -1500,7 +1503,7 @@ static unsigned int ip_vs_local_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); + return ip_vs_out_hook(priv, skb, state); } #ifdef CONFIG_IP_VS_IPV6 @@ -1514,7 +1517,7 @@ static unsigned int ip_vs_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); + return ip_vs_out_hook(priv, skb, state); } /* @@ -1525,7 +1528,7 @@ static unsigned int ip_vs_local_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); + return ip_vs_out_hook(priv, skb, state); } #endif @@ -1969,14 +1972,17 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, * and send it on its way... */ static unsigned int -ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) +ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { + struct netns_ipvs *ipvs = net_ipvs(state->net); + unsigned int hooknum = state->hook; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; struct sock *sk; + int af = state->pf; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) @@ -2157,7 +2163,7 @@ static unsigned int ip_vs_remote_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); + return ip_vs_in_hook(priv, skb, state); } /* @@ -2168,7 +2174,7 @@ static unsigned int ip_vs_local_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); + return ip_vs_in_hook(priv, skb, state); } #ifdef CONFIG_IP_VS_IPV6 @@ -2181,7 +2187,7 @@ static unsigned int ip_vs_remote_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); + return ip_vs_in_hook(priv, skb, state); } /* @@ -2192,7 +2198,7 @@ static unsigned int ip_vs_local_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); + return ip_vs_in_hook(priv, skb, state); } #endif -- 2.9.5
From: Florian Westphal <fw@strlen.de> mainline inclusion from mainline-v5.16-rc1 commit 8a9941b42de5132eae0cd2c27d5da41024f278a2 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- After earlier patch we can use ip_vs_out_hook directly. Signed-off-by: Florian Westphal <fw@strlen.de> Acked-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- net/netfilter/ipvs/ip_vs_core.c | 62 ++++------------------------------------- 1 file changed, 6 insertions(+), 56 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 09d5f8b..5bd548b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1483,56 +1483,6 @@ ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat return NF_ACCEPT; } -/* - * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, - * used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_reply4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out_hook(priv, skb, state); -} - -/* - * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_local_reply4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out_hook(priv, skb, state); -} - -#ifdef CONFIG_IP_VS_IPV6 - -/* - * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, - * used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_reply6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out_hook(priv, skb, state); -} - -/* - * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. - * Check if packet is reply for established ip_vs_conn. - */ -static unsigned int -ip_vs_local_reply6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_out_hook(priv, skb, state); -} - -#endif - static unsigned int ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, @@ -2255,7 +2205,7 @@ ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb, static const struct nf_hook_ops ip_vs_ops4[] = { /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply4, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 2, @@ -2271,7 +2221,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = { }, /* Before ip_vs_in, change source only for VS/NAT */ { - .hook = ip_vs_local_reply4, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 1, @@ -2293,7 +2243,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = { }, /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply4, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 100, @@ -2304,7 +2254,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = { static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply6, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 2, @@ -2320,7 +2270,7 @@ static const struct nf_hook_ops ip_vs_ops6[] = { }, /* Before ip_vs_in, change source only for VS/NAT */ { - .hook = ip_vs_local_reply6, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, @@ -2342,7 +2292,7 @@ static const struct nf_hook_ops ip_vs_ops6[] = { }, /* After packet filtering, change source only for VS/NAT */ { - .hook = ip_vs_reply6, + .hook = ip_vs_out_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 100, -- 2.9.5
From: Florian Westphal <fw@strlen.de> mainline inclusion from mainline-v5.16-rc1 commit 540ff44b28f0b31d0c74b5e7082b050e1b14b36a category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- After earlier patch ip_vs_hook_in can be used directly. Signed-off-by: Florian Westphal <fw@strlen.de> Acked-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- net/netfilter/ipvs/ip_vs_core.c | 57 +++-------------------------------------- 1 file changed, 4 insertions(+), 53 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 5bd548b..f118236 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2106,55 +2106,6 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state } /* - * AF_INET handler in NF_INET_LOCAL_IN chain - * Schedule and forward packets from remote clients - */ -static unsigned int -ip_vs_remote_request4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in_hook(priv, skb, state); -} - -/* - * AF_INET handler in NF_INET_LOCAL_OUT chain - * Schedule and forward packets from local clients - */ -static unsigned int -ip_vs_local_request4(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in_hook(priv, skb, state); -} - -#ifdef CONFIG_IP_VS_IPV6 - -/* - * AF_INET6 handler in NF_INET_LOCAL_IN chain - * Schedule and forward packets from remote clients - */ -static unsigned int -ip_vs_remote_request6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in_hook(priv, skb, state); -} - -/* - * AF_INET6 handler in NF_INET_LOCAL_OUT chain - * Schedule and forward packets from local clients - */ -static unsigned int -ip_vs_local_request6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip_vs_in_hook(priv, skb, state); -} - -#endif - - -/* * It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP * related packets destined for 0.0.0.0/0. * When fwmark-based virtual service is used, such as transparent @@ -2214,7 +2165,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = { * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { - .hook = ip_vs_remote_request4, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 1, @@ -2228,7 +2179,7 @@ static const struct nf_hook_ops ip_vs_ops4[] = { }, /* After mangle, schedule and forward local requests */ { - .hook = ip_vs_local_request4, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 2, @@ -2263,7 +2214,7 @@ static const struct nf_hook_ops ip_vs_ops6[] = { * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { - .hook = ip_vs_remote_request6, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 1, @@ -2277,7 +2228,7 @@ static const struct nf_hook_ops ip_vs_ops6[] = { }, /* After mangle, schedule and forward local requests */ { - .hook = ip_vs_local_request6, + .hook = ip_vs_in_hook, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 2, -- 2.9.5
From: Florian Westphal <fw@strlen.de> mainline inclusion from mainline-v5.16-rc1 commit c650c35a2506d8eebe8a4d8d263317fba29fe078 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Similar to earlier patches: allow ipv4 and ipv6 to use the same handler. ipv4 and ipv6 specific actions can be done by checking state->pf. v2: split the pf == NFPROTO_IPV4 check (Julian Anastasov) Signed-off-by: Florian Westphal <fw@strlen.de> Acked-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- net/netfilter/ipvs/ip_vs_core.c | 37 ++++++++++++++----------------------- 1 file changed, 14 insertions(+), 23 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index f118236..1911c69 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2118,40 +2118,31 @@ static unsigned int ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - int r; struct netns_ipvs *ipvs = net_ipvs(state->net); - - if (ip_hdr(skb)->protocol != IPPROTO_ICMP) - return NF_ACCEPT; + int r; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; - return ip_vs_in_icmp(ipvs, skb, &r, state->hook); -} - + if (state->pf == NFPROTO_IPV4) { + if (ip_hdr(skb)->protocol != IPPROTO_ICMP) + return NF_ACCEPT; #ifdef CONFIG_IP_VS_IPV6 -static unsigned int -ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - int r; - struct netns_ipvs *ipvs = net_ipvs(state->net); - struct ip_vs_iphdr iphdr; + } else { + struct ip_vs_iphdr iphdr; - ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); - if (iphdr.protocol != IPPROTO_ICMPV6) - return NF_ACCEPT; + ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); - /* ipvs enabled in this netns ? */ - if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) - return NF_ACCEPT; + if (iphdr.protocol != IPPROTO_ICMPV6) + return NF_ACCEPT; - return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); -} + return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); #endif + } + return ip_vs_in_icmp(ipvs, skb, &r, state->hook); +} static const struct nf_hook_ops ip_vs_ops4[] = { /* After packet filtering, change source only for VS/NAT */ @@ -2236,7 +2227,7 @@ static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { - .hook = ip_vs_forward_icmp_v6, + .hook = ip_vs_forward_icmp, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 99, -- 2.9.5
From: Julian Anastasov <ja@ssi.bg> mainline inclusion from mainline-v7.0-rc1 commit 05cfe9863ef049d98141dc2969eefde72fb07625 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Protocol checksum validation fails for IPv6 if there are extension headers before the protocol header. iph->len already contains its offset, so use it to fix the problem. Fixes: 2906f66a5682 ("ipvs: SCTP Trasport Loadbalancing Support") Fixes: 0bbdd42b7efa ("IPVS: Extend protocol DNAT/SNAT and state handlers") Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- net/netfilter/ipvs/ip_vs_proto_sctp.c | 18 ++++++------------ net/netfilter/ipvs/ip_vs_proto_tcp.c | 21 +++++++-------------- net/netfilter/ipvs/ip_vs_proto_udp.c | 20 +++++++------------- 3 files changed, 20 insertions(+), 39 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 1e689c7..0039e7542 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -10,7 +10,8 @@ #include <net/ip_vs.h> static int -sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); +sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, + unsigned int sctphoff); static int sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -108,7 +109,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!sctp_csum_check(cp->af, skb, pp)) + if (!sctp_csum_check(cp->af, skb, pp, sctphoff)) return 0; /* Call application helper if needed */ @@ -156,7 +157,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!sctp_csum_check(cp->af, skb, pp)) + if (!sctp_csum_check(cp->af, skb, pp, sctphoff)) return 0; /* Call application helper if needed */ @@ -185,19 +186,12 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, } static int -sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) +sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, + unsigned int sctphoff) { - unsigned int sctphoff; struct sctphdr *sh; __le32 cmp, val; -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) - sctphoff = sizeof(struct ipv6hdr); - else -#endif - sctphoff = ip_hdrlen(skb); - sh = (struct sctphdr *)(skb->data + sctphoff); cmp = sh->checksum; val = sctp_compute_cksum(skb, sctphoff); diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 7da51390..ede4fa3 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -29,7 +29,8 @@ #include <net/ip_vs.h> static int -tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); +tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, + unsigned int tcphoff); static int tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -166,7 +167,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!tcp_csum_check(cp->af, skb, pp)) + if (!tcp_csum_check(cp->af, skb, pp, tcphoff)) return 0; /* Call application helper if needed */ @@ -244,7 +245,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!tcp_csum_check(cp->af, skb, pp)) + if (!tcp_csum_check(cp->af, skb, pp, tcphoff)) return 0; /* @@ -301,17 +302,9 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int -tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) +tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, + unsigned int tcphoff) { - unsigned int tcphoff; - -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) - tcphoff = sizeof(struct ipv6hdr); - else -#endif - tcphoff = ip_hdrlen(skb); - switch (skb->ip_summed) { case CHECKSUM_NONE: skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); @@ -322,7 +315,7 @@ tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - tcphoff, - ipv6_hdr(skb)->nexthdr, + IPPROTO_TCP, skb->csum)) { IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 68260d9..ffbebda 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -25,7 +25,8 @@ #include <net/ip6_checksum.h> static int -udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); +udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, + unsigned int udphoff); static int udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -155,7 +156,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!udp_csum_check(cp->af, skb, pp)) + if (!udp_csum_check(cp->af, skb, pp, udphoff)) return 0; /* @@ -238,7 +239,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!udp_csum_check(cp->af, skb, pp)) + if (!udp_csum_check(cp->af, skb, pp, udphoff)) return 0; /* @@ -297,17 +298,10 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int -udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) +udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, + unsigned int udphoff) { struct udphdr _udph, *uh; - unsigned int udphoff; - -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) - udphoff = sizeof(struct ipv6hdr); - else -#endif - udphoff = ip_hdrlen(skb); uh = skb_header_pointer(skb, udphoff, sizeof(_udph), &_udph); if (uh == NULL) @@ -325,7 +319,7 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - udphoff, - ipv6_hdr(skb)->nexthdr, + IPPROTO_UDP, skb->csum)) { IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); -- 2.9.5
From: Julian Anastasov <ja@ssi.bg> mainline inclusion from mainline-v7.2-rc6 commit e876b75b9020a97bbdc79721e7fc749024891c65 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- ip_vs_in_icmp_v6() is missing checksum validation for ICMPv6 packets from clients. In fact, as for TCP/UDP we should validate the checksum for ICMP packets only when we mangle the packets on MASQ or on reply for tunnel. Also, Sashiko points out that handle_response_icmp() being common for IPv4 and IPv6 is missing the pseudo-header calculation while validating ICMPv6 messages from real servers which is a problem if checksum is not validated by the hardware. Fix the problems by creating ip_vs_checksum_common_check() helper and use it for TCP/UDP/ICMP both for IPv4 and IPv6. Rely on the nf_checksum() for validating the ICMP messages but use it also for TCP and UDP. Use correct IP offset for IP_VS_DBG_RL_PKT for TCP/UDP/SCTP. IPVS packets (TCP/UDP/SCTP/ICMP) do not need checksum validation on LOCAL_OUT (local clients or local real servers) and on FORWARD (traffic from servers on LAN). Do it only on LOCAL_IN, in case nf_checksum() is not called on PRE_ROUTING. Also, ip_vs_checksum_complete() can be marked static. Fixes: 2a3b791e6e11 ("IPVS: Add/adjust Netfilter hook functions and helpers for v6") Link: https://sashiko.dev/#/patchset/20260708180315.77413-1-ja%40ssi.bg Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Conflicts: include/net/ip6_fib.h [Partially backport e8dfd42c17fa ("ipv6: introduce dst_rt6_info() helper"), and use container_of() instead of container_of_const()] Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- include/net/ip6_fib.h | 2 ++ include/net/ip_vs.h | 31 ++++++++++++++++++++-- net/netfilter/ipvs/ip_vs_core.c | 20 +++++++++++--- net/netfilter/ipvs/ip_vs_proto_sctp.c | 15 ++++++----- net/netfilter/ipvs/ip_vs_proto_tcp.c | 44 ++++++------------------------ net/netfilter/ipvs/ip_vs_proto_udp.c | 50 ++++++++--------------------------- 6 files changed, 76 insertions(+), 86 deletions(-) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index d8d79c6..4a3fca4 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -245,6 +245,8 @@ struct fib6_result { for (rt = (w)->leaf; rt; \ rt = rcu_dereference_protected(rt->fib6_next, 1)) +#define dst_rt6_info(_ptr) container_of(_ptr, struct rt6_info, dst) + static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) { return ((struct rt6_info *)dst)->rt6i_idev; diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 3aebba9..8731b99 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -24,7 +24,9 @@ #include <linux/netfilter.h> /* for union nf_inet_addr */ #include <linux/ip.h> #include <linux/ipv6.h> /* for struct ipv6hdr */ +#include <net/route.h> #include <net/ipv6.h> +#include <net/ip6_fib.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif @@ -1567,8 +1569,6 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int dir); #endif -__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset); - static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum) { __be32 diff[2] = { ~old, new }; @@ -1594,6 +1594,33 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } +static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af) +{ + /* Checksum unnecessary or already validated? */ + if (skb_csum_unnecessary(skb)) + return false; + /* LOCAL_OUT ? */ + if (!skb->dev || skb->dev->flags & IFF_LOOPBACK) + return false; + /* !LOCAL_IN (FORWARD) ? */ + if (af == AF_INET6) { + if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL)) + return false; + } else { + if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) + return false; + } + return true; +} + +static inline bool ip_vs_checksum_common_check(struct sk_buff *skb, + int offset, int proto, int af) +{ + if (!ip_vs_checksum_needed(skb, af)) + return true; + return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af); +} + /* Forget current conntrack (unconfirmed) and attach notrack entry */ static inline void ip_vs_notrack(struct sk_buff *skb) { diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 1911c69..0586011 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -701,7 +701,7 @@ static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; } #endif -__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) +static __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); } @@ -872,13 +872,14 @@ static int handle_response_icmp(int af, struct sk_buff *skb, unsigned int offset, unsigned int ihl, unsigned int hooknum) { + int iproto = af == AF_INET6 ? IPPROTO_ICMPV6 : IPPROTO_ICMP; unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; /* Ensure the checksum is correct */ - if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { + if (!ip_vs_checksum_common_check(skb, ihl, iproto, af)) { /* Failed checksum! */ IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n", IP_VS_DBG_ADDR(af, snet)); @@ -1736,7 +1737,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, verdict = NF_DROP; /* Ensure the checksum is correct */ - if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { + if ((IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ || tunnel) && + !ip_vs_checksum_common_check(skb, ihl, IPPROTO_ICMP, AF_INET)) { /* Failed checksum! */ IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n", &iph->saddr); @@ -1895,6 +1897,18 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, goto out; } + verdict = NF_DROP; + + /* Ensure the checksum is correct */ + if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ && + !ip_vs_checksum_common_check(skb, iph->len, IPPROTO_ICMPV6, + AF_INET6)) { + /* Failed checksum! */ + IP_VS_DBG(1, "Incoming ICMPv6: failed checksum from %pI6c!\n", + &iph->saddr); + goto out; + } + /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 0039e7542..48ce736 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -11,7 +11,7 @@ static int sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int sctphoff); + struct ip_vs_iphdr *iph); static int sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -109,7 +109,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!sctp_csum_check(cp->af, skb, pp, sctphoff)) + if (!sctp_csum_check(cp->af, skb, pp, iph)) return 0; /* Call application helper if needed */ @@ -157,7 +157,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!sctp_csum_check(cp->af, skb, pp, sctphoff)) + if (!sctp_csum_check(cp->af, skb, pp, iph)) return 0; /* Call application helper if needed */ @@ -187,19 +187,22 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int sctphoff) + struct ip_vs_iphdr *iph) { + unsigned int sctphoff = iph->len; struct sctphdr *sh; __le32 cmp, val; + if (!ip_vs_checksum_needed(skb, af)) + return 1; sh = (struct sctphdr *)(skb->data + sctphoff); cmp = sh->checksum; val = sctp_compute_cksum(skb, sctphoff); if (val != cmp) { /* CRC failure, dump it. */ - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); + IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off, + "Failed checksum for"); return 0; } return 1; diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index ede4fa3..cc48e73 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -30,7 +30,7 @@ static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int tcphoff); + struct ip_vs_iphdr *iph); static int tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -167,7 +167,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!tcp_csum_check(cp->af, skb, pp, tcphoff)) + if (!tcp_csum_check(cp->af, skb, pp, iph)) return 0; /* Call application helper if needed */ @@ -245,7 +245,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!tcp_csum_check(cp->af, skb, pp, tcphoff)) + if (!tcp_csum_check(cp->af, skb, pp, iph)) return 0; /* @@ -303,41 +303,13 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int tcphoff) + struct ip_vs_iphdr *iph) { - switch (skb->ip_summed) { - case CHECKSUM_NONE: - skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); - fallthrough; - case CHECKSUM_COMPLETE: -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - tcphoff, - IPPROTO_TCP, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - } else -#endif - if (csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - tcphoff, - ip_hdr(skb)->protocol, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - break; - default: - /* No need to checksum. */ - break; + if (!ip_vs_checksum_common_check(skb, iph->len, IPPROTO_TCP, af)) { + IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off, + "Failed checksum for"); + return 0; } - return 1; } diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index ffbebda..0d8520e 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -26,7 +26,7 @@ static int udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int udphoff); + struct ip_vs_iphdr *iph); static int udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, @@ -156,7 +156,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!udp_csum_check(cp->af, skb, pp, udphoff)) + if (!udp_csum_check(cp->af, skb, pp, iph)) return 0; /* @@ -239,7 +239,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (!udp_csum_check(cp->af, skb, pp, udphoff)) + if (!udp_csum_check(cp->af, skb, pp, iph)) return 0; /* @@ -299,48 +299,20 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, static int udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, - unsigned int udphoff) + struct ip_vs_iphdr *iph) { struct udphdr _udph, *uh; - uh = skb_header_pointer(skb, udphoff, sizeof(_udph), &_udph); + uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); if (uh == NULL) return 0; - if (uh->check != 0) { - switch (skb->ip_summed) { - case CHECKSUM_NONE: - skb->csum = skb_checksum(skb, udphoff, - skb->len - udphoff, 0); - fallthrough; - case CHECKSUM_COMPLETE: -#ifdef CONFIG_IP_VS_IPV6 - if (af == AF_INET6) { - if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - udphoff, - IPPROTO_UDP, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - } else -#endif - if (csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - udphoff, - ip_hdr(skb)->protocol, - skb->csum)) { - IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, - "Failed checksum for"); - return 0; - } - break; - default: - /* No need to checksum. */ - break; - } + if (!uh->check) + return 1; + if (!ip_vs_checksum_common_check(skb, iph->len, IPPROTO_UDP, af)) { + IP_VS_DBG_RL_PKT(0, af, pp, skb, iph->off, + "Failed checksum for"); + return 0; } return 1; } -- 2.9.5
From: Julian Anastasov <ja@ssi.bg> stable inclusion from stable-v5.10.261 commit 613ce63711b8d431bba90781f133c39a21684f87 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- commit b3fe4cbd583895987935a9bdad01c8f9d3a02310 upstream. Sashiko reports for more incorrect IPv6 transport offsets. The app code for TCP was assuming IPv4 network header even after the ipvsh argument was provided. This can cause problems with apps over IPv6. As for the only official app in the kernel tree (FTP) this problem is harmless because we use Netfilter to mangle the FTP ports and we do not adjust the TCP seq numbers. Also, provide correct offset of the ICMPV6 header in ip_vs_out_icmp_v6() for correct checksum checks when the IPv6 packet has extension headers. Fixes: d12e12299a69 ("ipvs: add ipv6 support to ftp") Fixes: 2a3b791e6e11 ("IPVS: Add/adjust Netfilter hook functions and helpers for v6") Cc: stable@vger.kernel.org Link: https://sashiko.dev/#/patchset/20260706101624.69471-1-zhaoyz24%40mails.tsing... Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- net/netfilter/ipvs/ip_vs_app.c | 10 ++++------ net/netfilter/ipvs/ip_vs_core.c | 3 +-- 2 files changed, 5 insertions(+), 8 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index fdacbc3..f9132b3 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -362,14 +362,13 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, struct ip_vs_iphdr *ipvsh) { int diff; - const unsigned int tcp_offset = ip_hdrlen(skb); struct tcphdr *th; __u32 seq; - if (skb_ensure_writable(skb, tcp_offset + sizeof(*th))) + if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th))) return 0; - th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset); + th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len); /* * Remember seq number in case this pkt gets resized @@ -439,14 +438,13 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, struct ip_vs_iphdr *ipvsh) { int diff; - const unsigned int tcp_offset = ip_hdrlen(skb); struct tcphdr *th; __u32 seq; - if (skb_ensure_writable(skb, tcp_offset + sizeof(*th))) + if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th))) return 0; - th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset); + th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len); /* * Remember seq number in case this pkt gets resized diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 0586011..1c2f1ab 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1054,8 +1054,7 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, snet.in6 = ciph.saddr.in6; offset = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, offset, sizeof(struct ipv6hdr), - hooknum); + pp, offset, ipvsh->len, hooknum); } #endif -- 2.9.5
From: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn> stable inclusion from stable-v5.10.261 commit 4f91536059b504b90e49bf3bf47363638b853a41 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit 6b335af0d0d1ff44ac579d106953bf19299e5233 ] When an ICMP Fragmentation Needed error is received for a tunneled IPVS connection, ip_vs_in_icmp() recomputes the MTU that the original packet can use by subtracting the tunnel overhead from the reported next-hop MTU. The current code always subtracts sizeof(struct iphdr), which is only the IPIP overhead. For GUE and GRE tunnels, ipvs_udp_decap() and ipvs_gre_decap() already compute the additional tunnel header length, but that value is scoped to the decapsulation block and is lost before the ICMP_FRAG_NEEDED handling. As a result, the ICMP error sent back to the client advertises an MTU that is too large, so PMTUD can fail to converge for GUE/GRE-tunneled real servers. With a reported next-hop MTU of 1400, a GUE tunnel currently returns 1380 to the client. The correct value is 1368: 1400 - sizeof(struct iphdr) - sizeof(struct udphdr) - sizeof(struct guehdr) Hoist the tunnel header length into the main ip_vs_in_icmp() scope and subtract sizeof(struct iphdr) + ulen in the Fragmentation Needed path. The IPIP path keeps ulen as 0, so its existing 1400 - 20 = 1380 result is unchanged. Fixes: 508f744c0de3 ("ipvs: strip udp tunnel headers from icmp errors") Cc: stable@vger.kernel.org Reported-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn> Reported-by: Yuxiang Yang <yangyx22@mails.tsinghua.edu.cn> Reported-by: Ao Wang <wangao@seu.edu.cn> Reported-by: Xuewei Feng <fengxw06@126.com> Reported-by: Qi Li <qli01@tsinghua.edu.cn> Reported-by: Ke Xu <xuke@tsinghua.edu.cn> Assisted-by: Claude-Code:GLM-5.2 Signed-off-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn> Acked-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Florian Westphal <fw@strlen.de> Stable-dep-of: 3f7a535ff0fa ("ipvs: ensure inner headers in ICMP errors are in headroom") Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- net/netfilter/ipvs/ip_vs_core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 1c2f1ab..5c631f0 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1606,6 +1606,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, bool tunnel, new_cp = false; union nf_inet_addr *raddr; char *outer_proto = "IPIP"; + int ulen = 0; *related = 1; @@ -1670,7 +1671,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Error for our tunnel must arrive at LOCAL_IN */ (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { __u8 iproto; - int ulen; /* Non-first fragment has no UDP/GRE header */ if (unlikely(cih->frag_off & htons(IP_OFFSET))) @@ -1776,8 +1776,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (dest_dst) mtu = dst_mtu(dest_dst->dst_cache); } - if (mtu > 68 + sizeof(struct iphdr)) - mtu -= sizeof(struct iphdr); + if (mtu > 68 + sizeof(struct iphdr) + ulen) + mtu -= sizeof(struct iphdr) + ulen; info = htonl(mtu); } /* Strip outer IP, ICMP and IPIP/UDP/GRE, go to IP header of -- 2.9.5
From: Julian Anastasov <ja@ssi.bg> stable inclusion from stable-v5.10.261 commit 19657b3a17b774ae4e2f2635b5ae8638c9344a40 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit 3f7a535ff0fa627a0132803e4c2f903ceffcbc1c ] Sashiko points out that after stripping the outer headers with pskb_pull() we should ensure the inner IP headers in ICMP errors from tunnels are present in the skb headroom for functions like ipv4_update_pmtu(), icmp_send() and IP_VS_DBG(). Also, add more checks for the length of the inner headers. Fixes: f2edb9f7706d ("ipvs: implement passive PMTUD for IPIP packets") Link: https://sashiko.dev/#/patchset/20260702073430.67680-1-zhaoyz24%40mails.tsing... Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- net/netfilter/ipvs/ip_vs_core.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 5c631f0..a3cb006 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1606,6 +1606,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, bool tunnel, new_cp = false; union nf_inet_addr *raddr; char *outer_proto = "IPIP"; + unsigned int hlen_ipip; int ulen = 0; *related = 1; @@ -1643,9 +1644,10 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + if (!(cih && cih->version == 4 && cih->ihl >= 5)) return NF_ACCEPT; /* The packet looks wrong, ignore */ raddr = (union nf_inet_addr *)&cih->daddr; + hlen_ipip = cih->ihl * 4; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; @@ -1661,9 +1663,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Only for known tunnel */ if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; - offset += cih->ihl * 4; + offset += hlen_ipip; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + if (!(cih && cih->version == 4 && cih->ihl >= 5)) return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ @@ -1675,7 +1677,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Non-first fragment has no UDP/GRE header */ if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; - offset2 = offset + cih->ihl * 4; + offset2 = offset + hlen_ipip; if (cih->protocol == IPPROTO_UDP) { ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); @@ -1745,6 +1747,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, } if (tunnel) { + unsigned int hlen_orig = cih->ihl * 4; __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; @@ -1761,6 +1764,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, goto ignore_tunnel; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); + /* Ensure the IP header is present in headroom */ + if (!pskb_may_pull(skb, hlen_ipip)) + goto ignore_tunnel; IP_VS_DBG(12, "ICMP for %s %pI4->%pI4: mtu=%u\n", outer_proto, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); @@ -1776,8 +1782,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (dest_dst) mtu = dst_mtu(dest_dst->dst_cache); } - if (mtu > 68 + sizeof(struct iphdr) + ulen) - mtu -= sizeof(struct iphdr) + ulen; + if (mtu > 68 + hlen_ipip + ulen) + mtu -= hlen_ipip + ulen; info = htonl(mtu); } /* Strip outer IP, ICMP and IPIP/UDP/GRE, go to IP header of @@ -1786,6 +1792,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (pskb_pull(skb, offset2) == NULL) goto ignore_tunnel; skb_reset_network_header(skb); + /* Ensure the IP header is present in headroom */ + if (!pskb_may_pull(skb, hlen_orig)) + goto ignore_tunnel; IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, type, code, ntohl(info)); -- 2.9.5
From: Julian Anastasov <ja@ssi.bg> mainline inclusion from mainline-v7.2-rc6 commit 15cab31a3730e05f0767b922a7450e5d784b2607 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The offsets we use to packet headers and payloads should be based on skb->data. We even already respect non-zero network offset in ip_vs_fill_iph_skb() but some places do it wrongly and support only zero offset which is expected for the IP layer where IPVS has hooks. Change all places that instead of skb->data use offsets based on the network header (skb_network_header, ip_hdr, etc) because this doubles the network offset as noted by Sashiko. For ip_vs_nat_icmp_v6() we can even rely on the IPv6 header parsing done by the caller. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://sashiko.dev/#/patchset/20260710143733.29741-2-fw%40strlen.de Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Conflicts: include/net/ip_vs.h net/netfilter/ipvs/ip_vs_core.c net/netfilter/ipvs/ip_vs_xmit.c [ip_vs.h: f20c73b0460d ("ipvs: use more keys for connection hashing") not merged. ip_vs_core.c: 944b6b216c03 ("ipvs: Use READ_ONCE/WRITE_ONCE for ipvs->enable") not merged. ip_vs_xmit.c: 210ffe4a74ca ("ipvs: Remove {Enter,Leave}Function") and e8dfd42c17fa ("ipv6: introduce dst_rt6_info() helper") not merged] Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- include/net/ip_vs.h | 15 ++-- net/netfilter/ipvs/ip_vs_app.c | 4 +- net/netfilter/ipvs/ip_vs_core.c | 133 +++++++++++++++++----------------- net/netfilter/ipvs/ip_vs_proto_sctp.c | 4 +- net/netfilter/ipvs/ip_vs_proto_tcp.c | 4 +- net/netfilter/ipvs/ip_vs_proto_udp.c | 4 +- net/netfilter/ipvs/ip_vs_xmit.c | 26 ++++--- 7 files changed, 97 insertions(+), 93 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 8731b99..871e66d 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1482,8 +1482,9 @@ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, - unsigned int hooknum, struct ip_vs_iphdr *iph); + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int wlen, unsigned int hooknum, + struct ip_vs_iphdr *ciph); void ip_vs_dest_dst_rcu_free(struct rcu_head *head); #ifdef CONFIG_IP_VS_IPV6 @@ -1496,8 +1497,9 @@ int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, - unsigned int hooknum, struct ip_vs_iphdr *iph); + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int wlen, unsigned int hooknum, + struct ip_vs_iphdr *ciph); #endif #ifdef CONFIG_SYSCTL @@ -1562,11 +1564,12 @@ static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp) } void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int dir); + struct ip_vs_conn *cp, int dir, unsigned int toff); #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int dir); + struct ip_vs_conn *cp, int dir, unsigned int toff, + struct ip_vs_iphdr *ciph); #endif static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum) diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index f9132b3..0c690a3 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -368,7 +368,7 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th))) return 0; - th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len); + th = (struct tcphdr *)(skb->data + ipvsh->len); /* * Remember seq number in case this pkt gets resized @@ -444,7 +444,7 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, if (skb_ensure_writable(skb, ipvsh->len + sizeof(*th))) return 0; - th = (struct tcphdr *)(skb_network_header(skb) + ipvsh->len); + th = (struct tcphdr *)(skb->data + ipvsh->len); /* * Remember seq number in case this pkt gets resized diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a3cb006..10c3667 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -758,13 +758,12 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, * - inout: 1=in->out, 0=out->in */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int inout) + struct ip_vs_conn *cp, int inout, unsigned int toff) { struct iphdr *iph = ip_hdr(skb); - unsigned int icmp_offset = iph->ihl*4; - struct icmphdr *icmph = (struct icmphdr *)(skb_network_header(skb) + - icmp_offset); + struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff); struct iphdr *ciph = (struct iphdr *)(icmph + 1); + unsigned int coff __maybe_unused = toff + sizeof(struct icmphdr); if (inout) { iph->saddr = cp->vaddr.ip; @@ -791,48 +790,45 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, /* And finally the ICMP checksum */ icmph->checksum = 0; - icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset); + icmph->checksum = ip_vs_checksum_complete(skb, toff); skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) - IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, - "Forwarding altered outgoing ICMP"); + IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + "Forwarding altered outgoing ICMP"); else - IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, - "Forwarding altered incoming ICMP"); + IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + "Forwarding altered incoming ICMP"); } #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int inout) + struct ip_vs_conn *cp, int inout, unsigned int toff, + struct ip_vs_iphdr *ciph) { struct ipv6hdr *iph = ipv6_hdr(skb); - unsigned int icmp_offset = 0; - unsigned int offs = 0; /* header offset*/ int protocol; struct icmp6hdr *icmph; - struct ipv6hdr *ciph; - unsigned short fragoffs; + struct ipv6hdr *cih; - ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL); - icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset); - offs = icmp_offset + sizeof(struct icmp6hdr); - ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs); + icmph = (struct icmp6hdr *)(skb->data + toff); + cih = (struct ipv6hdr *)(skb->data + ciph->off); - protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL); + protocol = ciph->protocol; if (inout) { iph->saddr = cp->vaddr.in6; - ciph->daddr = cp->vaddr.in6; + cih->daddr = cp->vaddr.in6; } else { iph->daddr = cp->daddr.in6; - ciph->saddr = cp->daddr.in6; + cih->saddr = cp->daddr.in6; } /* the TCP/UDP/SCTP port */ - if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || - IPPROTO_SCTP == protocol)) { - __be16 *ports = (void *)(skb_network_header(skb) + offs); + if (!ciph->fragoffs && + (protocol == IPPROTO_TCP || protocol == IPPROTO_UDP || + protocol == IPPROTO_SCTP)) { + __be16 *ports = (void *)(skb->data + ciph->len); IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__, ntohs(inout ? ports[1] : ports[0]), @@ -845,19 +841,17 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, /* And finally the ICMP checksum */ icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb->len - icmp_offset, + skb->len - toff, IPPROTO_ICMPV6, 0); - skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset; + skb->csum_start = skb_headroom(skb) + toff; skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum); skb->ip_summed = CHECKSUM_PARTIAL; if (inout) - IP_VS_DBG_PKT(11, AF_INET6, pp, skb, - (void *)ciph - (void *)iph, + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, ciph->off, "Forwarding altered outgoing ICMPv6"); else - IP_VS_DBG_PKT(11, AF_INET6, pp, skb, - (void *)ciph - (void *)iph, + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, ciph->off, "Forwarding altered incoming ICMPv6"); } #endif @@ -867,37 +861,38 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, */ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, - __u8 protocol, struct ip_vs_conn *cp, + struct ip_vs_conn *cp, struct ip_vs_protocol *pp, - unsigned int offset, unsigned int ihl, - unsigned int hooknum) + struct ip_vs_iphdr *ciph, + unsigned int toff, unsigned int hooknum) { int iproto = af == AF_INET6 ? IPPROTO_ICMPV6 : IPPROTO_ICMP; unsigned int verdict = NF_DROP; + unsigned int ctoff = ciph->len; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; /* Ensure the checksum is correct */ - if (!ip_vs_checksum_common_check(skb, ihl, iproto, af)) { + if (!ip_vs_checksum_common_check(skb, toff, iproto, af)) { /* Failed checksum! */ IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n", IP_VS_DBG_ADDR(af, snet)); goto out; } - if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || - IPPROTO_SCTP == protocol) - offset += 2 * sizeof(__u16); - if (skb_ensure_writable(skb, offset)) + if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP || + ciph->protocol == IPPROTO_SCTP) + ctoff += 2 * sizeof(__u16); + if (skb_ensure_writable(skb, ctoff)) goto out; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) - ip_vs_nat_icmp_v6(skb, pp, cp, 1); + ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, ciph); else #endif - ip_vs_nat_icmp(skb, pp, cp, 1); + ip_vs_nat_icmp(skb, pp, cp, 1, toff); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; @@ -925,9 +920,9 @@ static int handle_response_icmp(int af, struct sk_buff *skb, * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, - int *related, unsigned int hooknum) + int *related, unsigned int hooknum, + struct ip_vs_iphdr *ipvsh) { - struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; @@ -942,17 +937,19 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; + if (!ip_vs_fill_iph_skb(AF_INET, skb, false, ipvsh)) + return NF_ACCEPT; } - iph = ip_hdr(skb); - offset = ihl = iph->ihl * 4; + ihl = ipvsh->len; + offset = ipvsh->len; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), - &iph->saddr, &iph->daddr); + &ipvsh->saddr.ip, &ipvsh->daddr.ip); /* * Work through seeing if this is for us. @@ -971,7 +968,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + if (!(cih && cih->version == 4 && cih->ihl >= 5)) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(cih->protocol); @@ -994,9 +991,9 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, if (!cp) return NF_ACCEPT; - snet.ip = iph->saddr; - return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, - pp, ciph.len, ihl, hooknum); + snet.ip = ipvsh->saddr.ip; + return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, ihl, + hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -1009,7 +1006,6 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, struct ip_vs_conn *cp; struct ip_vs_protocol *pp; union nf_inet_addr snet; - unsigned int offset; *related = 1; ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph); @@ -1052,9 +1048,8 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; snet.in6 = ciph.saddr.in6; - offset = ciph.len; - return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, offset, ipvsh->len, hooknum); + return handle_response_icmp(AF_INET6, skb, &snet, cp, pp, &ciph, + ipvsh->len, hooknum); } #endif @@ -1389,7 +1384,8 @@ ip_vs_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; - int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum); + int verdict = ip_vs_out_icmp(ipvs, skb, &related, + hooknum, &iph); if (related) return verdict; @@ -1593,9 +1589,8 @@ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, */ static int ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, - unsigned int hooknum) + unsigned int hooknum, struct ip_vs_iphdr *iph) { - struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; @@ -1605,7 +1600,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int offset, offset2, ihl, verdict; bool tunnel, new_cp = false; union nf_inet_addr *raddr; - char *outer_proto = "IPIP"; + char *outer_proto __maybe_unused = "IPIP"; unsigned int hlen_ipip; int ulen = 0; @@ -1615,17 +1610,19 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; + if (!ip_vs_fill_iph_skb(AF_INET, skb, false, iph)) + return NF_ACCEPT; } - iph = ip_hdr(skb); - offset = ihl = iph->ihl * 4; + ihl = iph->len; + offset = iph->len; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), - &iph->saddr, &iph->daddr); + &iph->saddr.ip, &iph->daddr.ip); /* * Work through seeing if this is for us. @@ -1742,7 +1739,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, !ip_vs_checksum_common_check(skb, ihl, IPPROTO_ICMP, AF_INET)) { /* Failed checksum! */ IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n", - &iph->saddr); + &iph->saddr.ip); goto out; } @@ -1813,7 +1810,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol || IPPROTO_SCTP == cih->protocol) offset += 2 * sizeof(__u16); - verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); + verdict = ip_vs_icmp_xmit(skb, cp, pp, iph->len, offset, hooknum, + &ciph); out: if (likely(!new_cp)) @@ -1926,7 +1924,8 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, IPPROTO_SCTP == ciph.protocol) offset += 2 * sizeof(__u16); /* Also mangle ports */ - verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph); + verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, iph->len, offset, hooknum, + &ciph); out: if (likely(!new_cp)) @@ -2005,7 +2004,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_in_icmp(ipvs, skb, &related, - hooknum); + hooknum, &iph); if (related) return verdict; @@ -2141,6 +2140,7 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct netns_ipvs *ipvs = net_ipvs(state->net); + struct ip_vs_iphdr iphdr; int r; /* ipvs enabled in this netns ? */ @@ -2150,10 +2150,9 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb, if (state->pf == NFPROTO_IPV4) { if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; + ip_vs_fill_iph_skb(AF_INET, skb, false, &iphdr); #ifdef CONFIG_IP_VS_IPV6 } else { - struct ip_vs_iphdr iphdr; - ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); if (iphdr.protocol != IPPROTO_ICMPV6) @@ -2163,7 +2162,7 @@ ip_vs_forward_icmp(void *priv, struct sk_buff *skb, #endif } - return ip_vs_in_icmp(ipvs, skb, &r, state->hook); + return ip_vs_in_icmp(ipvs, skb, &r, state->hook, &iphdr); } static const struct nf_hook_ops ip_vs_ops4[] = { diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 48ce736..724d361 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -121,7 +121,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - sctph = (void *) skb_network_header(skb) + sctphoff; + sctph = (void *)skb->data + sctphoff; /* Only update csum if we really have to */ if (sctph->source != cp->vport || payload_csum || @@ -169,7 +169,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - sctph = (void *) skb_network_header(skb) + sctphoff; + sctph = (void *)skb->data + sctphoff; /* Only update csum if we really have to */ if (sctph->dest != cp->dport || payload_csum || diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index cc48e73..5b8b356 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -180,7 +180,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - tcph = (void *)skb_network_header(skb) + tcphoff; + tcph = (void *)skb->data + tcphoff; tcph->source = cp->vport; /* Adjust TCP checksums */ @@ -261,7 +261,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - tcph = (void *)skb_network_header(skb) + tcphoff; + tcph = (void *)skb->data + tcphoff; tcph->dest = cp->dport; /* diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 0d8520e..1a0de26 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -171,7 +171,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - udph = (void *)skb_network_header(skb) + udphoff; + udph = (void *)skb->data + udphoff; udph->source = cp->vport; /* @@ -255,7 +255,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, payload_csum = true; } - udph = (void *)skb_network_header(skb) + udphoff; + udph = (void *)skb->data + udphoff; udph->dest = cp->dport; /* diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index f8283434..14f7eed 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1511,8 +1511,9 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, */ int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, unsigned int hooknum, - struct ip_vs_iphdr *iph) + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int wlen, unsigned int hooknum, + struct ip_vs_iphdr *ciph) { struct rtable *rt; /* Route to the other host */ int rc; @@ -1526,7 +1527,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, translate address/port back */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { if (cp->packet_xmit) - rc = cp->packet_xmit(skb, cp, pp, iph); + rc = cp->packet_xmit(skb, cp, pp, ciph); else rc = NF_ACCEPT; /* do not touch skb anymore */ @@ -1544,7 +1545,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip, rt_mode, - NULL, iph); + NULL, ciph); if (local < 0) goto tx_error; rt = skb_rtable(skb); @@ -1576,13 +1577,13 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, } /* copy-on-write the packet before mangling it */ - if (skb_ensure_writable(skb, offset)) + if (skb_ensure_writable(skb, wlen)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp(skb, pp, cp, 0); + ip_vs_nat_icmp(skb, pp, cp, 0, toff); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; @@ -1601,8 +1602,9 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, #ifdef CONFIG_IP_VS_IPV6 int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, - struct ip_vs_protocol *pp, int offset, unsigned int hooknum, - struct ip_vs_iphdr *ipvsh) + struct ip_vs_protocol *pp, unsigned int toff, + unsigned int wlen, unsigned int hooknum, + struct ip_vs_iphdr *ciph) { struct rt6_info *rt; /* Route to the other host */ int rc; @@ -1616,7 +1618,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, translate address/port back */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { if (cp->packet_xmit) - rc = cp->packet_xmit(skb, cp, pp, ipvsh); + rc = cp->packet_xmit(skb, cp, pp, ciph); else rc = NF_ACCEPT; /* do not touch skb anymore */ @@ -1633,7 +1635,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest, - &cp->daddr.in6, NULL, ipvsh, 0, rt_mode); + &cp->daddr.in6, NULL, ciph, 0, rt_mode); if (local < 0) goto tx_error; rt = (struct rt6_info *) skb_dst(skb); @@ -1665,13 +1667,13 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } /* copy-on-write the packet before mangling it */ - if (skb_ensure_writable(skb, offset)) + if (skb_ensure_writable(skb, wlen)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp_v6(skb, pp, cp, 0); + ip_vs_nat_icmp_v6(skb, pp, cp, 0, toff, ciph); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; -- 2.9.5
From: Julian Anastasov <ja@ssi.bg> mainline inclusion from mainline-v7.2-rc6 commit 342e24a339b90e8e339a0f8c151ca479b8565661 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Sashiko warns that ip_vs_nat_icmp() unconditionally mangles the payload for embedded non-first IPv4 fragments. The problem is in the very old inverted pp->dont_defrag check which should not continue when embedded is a non-first TCP/UDP/SCTP fragment. Check for embedded non-first fragment is also missing from ip_vs_out_icmp_v6(), it is needed before any connection lookups that expect ports after the network headers. Drop the blocking code from ip_vs_in_icmp_v6() which prevents ICMPv6 from local clients to use non-MASQ forwarding. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://sashiko.dev/#/patchset/20260720201122.79882-1-ja%40ssi.bg Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Conflicts: include/net/ip_vs.h net/netfilter/ipvs/ip_vs_xmit.c [ip_vs.h: f20c73b0460d ("ipvs: use more keys for connection hashing") not merged. ip_vs_xmit.c: 210ffe4a74ca ("ipvs: Remove {Enter,Leave}Function") and e8dfd42c17fa ("ipv6: introduce dst_rt6_info() helper") not merged] Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- include/net/ip_vs.h | 11 ++++---- net/netfilter/ipvs/ip_vs_core.c | 61 ++++++++++++++--------------------------- net/netfilter/ipvs/ip_vs_xmit.c | 28 +++++++++++++++---- 3 files changed, 48 insertions(+), 52 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 871e66d..ab305a0 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1483,8 +1483,7 @@ int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, unsigned int toff, - unsigned int wlen, unsigned int hooknum, - struct ip_vs_iphdr *ciph); + unsigned int hooknum, struct ip_vs_iphdr *ciph); void ip_vs_dest_dst_rcu_free(struct rcu_head *head); #ifdef CONFIG_IP_VS_IPV6 @@ -1498,8 +1497,7 @@ int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, unsigned int toff, - unsigned int wlen, unsigned int hooknum, - struct ip_vs_iphdr *ciph); + unsigned int hooknum, struct ip_vs_iphdr *ciph); #endif #ifdef CONFIG_SYSCTL @@ -1564,12 +1562,13 @@ static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp) } void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int dir, unsigned int toff); + struct ip_vs_conn *cp, int dir, unsigned int toff, + bool has_ports); #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int dir, unsigned int toff, - struct ip_vs_iphdr *ciph); + bool has_ports, struct ip_vs_iphdr *ciph); #endif static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 10c3667..c6d50c6 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -758,7 +758,8 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, * - inout: 1=in->out, 0=out->in */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, int inout, unsigned int toff) + struct ip_vs_conn *cp, int inout, unsigned int toff, + bool has_ports) { struct iphdr *iph = ip_hdr(skb); struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff); @@ -778,8 +779,7 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, } /* the TCP/UDP/SCTP port */ - if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol || - IPPROTO_SCTP == ciph->protocol) { + if (has_ports) { __be16 *ports = (void *)ciph + ciph->ihl*4; if (inout) @@ -804,18 +804,15 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout, unsigned int toff, - struct ip_vs_iphdr *ciph) + bool has_ports, struct ip_vs_iphdr *ciph) { struct ipv6hdr *iph = ipv6_hdr(skb); - int protocol; struct icmp6hdr *icmph; struct ipv6hdr *cih; icmph = (struct icmp6hdr *)(skb->data + toff); cih = (struct ipv6hdr *)(skb->data + ciph->off); - protocol = ciph->protocol; - if (inout) { iph->saddr = cp->vaddr.in6; cih->daddr = cp->vaddr.in6; @@ -825,9 +822,7 @@ void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, } /* the TCP/UDP/SCTP port */ - if (!ciph->fragoffs && - (protocol == IPPROTO_TCP || protocol == IPPROTO_UDP || - protocol == IPPROTO_SCTP)) { + if (has_ports) { __be16 *ports = (void *)(skb->data + ciph->len); IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__, @@ -869,6 +864,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, int iproto = af == AF_INET6 ? IPPROTO_ICMPV6 : IPPROTO_ICMP; unsigned int verdict = NF_DROP; unsigned int ctoff = ciph->len; + bool has_ports = false; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; @@ -882,17 +878,19 @@ static int handle_response_icmp(int af, struct sk_buff *skb, } if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP || - ciph->protocol == IPPROTO_SCTP) + ciph->protocol == IPPROTO_SCTP) { ctoff += 2 * sizeof(__u16); + has_ports = true; + } if (skb_ensure_writable(skb, ctoff)) goto out; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) - ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, ciph); + ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph); else #endif - ip_vs_nat_icmp(skb, pp, cp, 1, toff); + ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; @@ -976,8 +974,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; /* Is the embedded protocol header present? */ - if (unlikely(cih->frag_off & htons(IP_OFFSET) && - pp->dont_defrag)) + if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, @@ -1041,6 +1038,10 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, if (!pp) return NF_ACCEPT; + /* Is the embedded protocol header present? */ + if (unlikely(ciph.fragoffs && !pp->dont_defrag)) + return NF_ACCEPT; + /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET6, skb, &ciph); @@ -1704,8 +1705,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, pp = pd->pp; /* Is the embedded protocol header present? */ - if (unlikely(cih->frag_off & htons(IP_OFFSET) && - pp->dont_defrag)) + if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, @@ -1713,7 +1713,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, offset2 = offset; ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); - offset = ciph.len; /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. @@ -1807,11 +1806,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); - if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol || - IPPROTO_SCTP == cih->protocol) - offset += 2 * sizeof(__u16); - verdict = ip_vs_icmp_xmit(skb, cp, pp, iph->len, offset, hooknum, - &ciph); + verdict = ip_vs_icmp_xmit(skb, cp, pp, iph->len, hooknum, &ciph); out: if (likely(!new_cp)) @@ -1871,8 +1866,8 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; pp = pd->pp; - /* Cannot handle fragmented embedded protocol */ - if (ciph.fragoffs) + /* Is the embedded protocol header present? */ + if (ciph.fragoffs && !pp->dont_defrag) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, @@ -1896,13 +1891,6 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, new_cp = true; } - /* VS/TUN, VS/DR and LOCALNODE just let it go */ - if ((hooknum == NF_INET_LOCAL_OUT) && - (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) { - verdict = NF_ACCEPT; - goto out; - } - verdict = NF_DROP; /* Ensure the checksum is correct */ @@ -1918,14 +1906,7 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); - /* Need to mangle contained IPv6 header in ICMPv6 packet */ - offset = ciph.len; - if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || - IPPROTO_SCTP == ciph.protocol) - offset += 2 * sizeof(__u16); /* Also mangle ports */ - - verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, iph->len, offset, hooknum, - &ciph); + verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, iph->len, hooknum, &ciph); out: if (likely(!new_cp)) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 14f7eed..eeba391 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1512,13 +1512,14 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, unsigned int toff, - unsigned int wlen, unsigned int hooknum, - struct ip_vs_iphdr *ciph) + unsigned int hooknum, struct ip_vs_iphdr *ciph) { struct rtable *rt; /* Route to the other host */ int rc; int local; int rt_mode, was_input; + bool has_ports = false; + unsigned int wlen; EnterFunction(10); @@ -1576,6 +1577,13 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } + wlen = ciph->len; + if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP || + ciph->protocol == IPPROTO_SCTP) { + wlen += 2 * sizeof(__u16); /* Also mangle ports */ + has_ports = true; + } + /* copy-on-write the packet before mangling it */ if (skb_ensure_writable(skb, wlen)) goto tx_error; @@ -1583,7 +1591,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp(skb, pp, cp, 0, toff); + ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; @@ -1603,10 +1611,11 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, unsigned int toff, - unsigned int wlen, unsigned int hooknum, - struct ip_vs_iphdr *ciph) + unsigned int hooknum, struct ip_vs_iphdr *ciph) { + bool has_ports = false; struct rt6_info *rt; /* Route to the other host */ + unsigned int wlen; int rc; int local; int rt_mode; @@ -1666,6 +1675,13 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; } + wlen = ciph->len; + if (ciph->protocol == IPPROTO_TCP || ciph->protocol == IPPROTO_UDP || + ciph->protocol == IPPROTO_SCTP) { + wlen += 2 * sizeof(__u16); /* Also mangle ports */ + has_ports = true; + } + /* copy-on-write the packet before mangling it */ if (skb_ensure_writable(skb, wlen)) goto tx_error; @@ -1673,7 +1689,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp_v6(skb, pp, cp, 0, toff, ciph); + ip_vs_nat_icmp_v6(skb, pp, cp, 0, toff, has_ports, ciph); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; -- 2.9.5
From: Julian Anastasov <ja@ssi.bg> mainline inclusion from mainline-v7.2-rc7 commit 646922a0379496154e8c8faca4f8e2fd9100cacc category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Sashiko warns that local attacker can modify the packet while it is processed by IPVS. Some places read the IP ihl field multiple times which can cause out-of-bounds access. One such place is ip_vs_nat_icmp where we can write after the validated area. Fix it by providing ciph argument just like it is done for IPv6 and use ciph->len as offset to the embedded transport header. Modify some IPv4 header checks by reading the ihl field only once. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://sashiko.dev/#/patchset/20260722101517.36313-1-ja%40ssi.bg Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Conflicts: include/net/ip_vs.h [ip_vs.h: f20c73b0460d ("ipvs: use more keys for connection hashing") not merged.] Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_core.c | 67 +++++++++++++++++++++-------------------- net/netfilter/ipvs/ip_vs_xmit.c | 2 +- 3 files changed, 36 insertions(+), 35 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ab305a0..c74e496 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1563,7 +1563,7 @@ static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp) void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int dir, unsigned int toff, - bool has_ports); + bool has_ports, struct ip_vs_iphdr *ciph); #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index c6d50c6..49123c9 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -759,28 +759,27 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout, unsigned int toff, - bool has_ports) + bool has_ports, struct ip_vs_iphdr *ciph) { struct iphdr *iph = ip_hdr(skb); struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff); - struct iphdr *ciph = (struct iphdr *)(icmph + 1); - unsigned int coff __maybe_unused = toff + sizeof(struct icmphdr); + struct iphdr *cih = (struct iphdr *)(icmph + 1); if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); - ciph->daddr = cp->vaddr.ip; - ip_send_check(ciph); + cih->daddr = cp->vaddr.ip; + ip_send_check(cih); } else { iph->daddr = cp->daddr.ip; ip_send_check(iph); - ciph->saddr = cp->daddr.ip; - ip_send_check(ciph); + cih->saddr = cp->daddr.ip; + ip_send_check(cih); } /* the TCP/UDP/SCTP port */ if (has_ports) { - __be16 *ports = (void *)ciph + ciph->ihl*4; + __be16 *ports = (void *)(skb->data + ciph->len); if (inout) ports[1] = cp->vport; @@ -794,10 +793,10 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) - IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off, "Forwarding altered outgoing ICMP"); else - IP_VS_DBG_PKT(11, AF_INET, pp, skb, coff, + IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off, "Forwarding altered incoming ICMP"); } @@ -890,7 +889,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph); else #endif - ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports); + ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; @@ -926,7 +925,7 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; - unsigned int offset, ihl; + unsigned int offset; union nf_inet_addr snet; *related = 1; @@ -939,7 +938,6 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; } - ihl = ipvsh->len; offset = ipvsh->len; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) @@ -965,11 +963,15 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, /* Now find the contained IP header */ offset += sizeof(_icmph); + if (!ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph)) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) + if (!(cih && cih->version == 4 && + ciph.len - ciph.off >= sizeof(struct iphdr))) return NF_ACCEPT; /* The packet looks wrong, ignore */ - pp = ip_vs_proto_get(cih->protocol); + pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; @@ -980,8 +982,6 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); - ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); - /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET, skb, &ciph); @@ -989,8 +989,8 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; snet.ip = ipvsh->saddr.ip; - return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, ihl, - hooknum); + return handle_response_icmp(AF_INET, skb, &snet, cp, pp, &ciph, + ipvsh->len, hooknum); } #ifdef CONFIG_IP_VS_IPV6 @@ -1642,10 +1642,12 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) + if (!cih) return NF_ACCEPT; /* The packet looks wrong, ignore */ - raddr = (union nf_inet_addr *)&cih->daddr; hlen_ipip = cih->ihl * 4; + if (!(cih->version == 4 && hlen_ipip >= sizeof(struct iphdr))) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + raddr = (union nf_inet_addr *)&cih->daddr; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; @@ -1662,9 +1664,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; offset += hlen_ipip; - cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (!(cih && cih->version == 4 && cih->ihl >= 5)) - return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ cih->protocol == IPPROTO_GRE) && /* Can be GRE encap */ @@ -1689,21 +1688,25 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Skip IP and UDP/GRE tunnel headers */ offset = offset2 + ulen; /* Now we should be at the original IP header */ - cih = skb_header_pointer(skb, offset, sizeof(_ciph), - &_ciph); - if (cih && cih->version == 4 && cih->ihl >= 5 && - iproto == IPPROTO_IPIP) + if (iproto == IPPROTO_IPIP) tunnel = true; else return NF_ACCEPT; } } - pd = ip_vs_proto_data_get(ipvs, cih->protocol); + if (!ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph)) + return NF_ACCEPT; + pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; + cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); + if (!(cih && cih->version == 4 && + ciph.len - ciph.off >= sizeof(struct iphdr))) + return NF_ACCEPT; /* The packet looks wrong, ignore */ + /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && !pp->dont_defrag)) return NF_ACCEPT; @@ -1711,9 +1714,6 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); - offset2 = offset; - ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); - /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. */ @@ -1743,11 +1743,12 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, } if (tunnel) { - unsigned int hlen_orig = cih->ihl * 4; + unsigned int hlen_orig = ciph.len - ciph.off; __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; + offset2 = offset; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index eeba391..32e304b 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1591,7 +1591,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports); + ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; -- 2.9.5
From: Julian Anastasov <ja@ssi.bg> mainline inclusion from mainline-v7.2-rc7 commit 99609cb0aa789c8d071050ce8579989551882cc6 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Sashiko notes that playing games with the skb dst and rt flags instead of providing hooknum is not a good idea when validating the checksums. Also, skipping checksum validation for FORWARD packets risk silent data corruption, even if the only user is the FTP-CMD packets coming from the real server. Sashiko also noticed that by using common checksum helper in the previous commit we actually fixed old bug where the TCP/UDP checksum for IPv6 on CHECKSUM_COMPLETE was not validated correctly. Fixes: e876b75b9020 ("ipvs: fix the checksum validations") Link: https://sashiko.dev/#/patchset/20260722211420.153933-1-pablo%40netfilter.org Link: https://sashiko.dev/#/patchset/20260727185024.67534-1-ja%40ssi.bg Link: https://sashiko.dev/#/patchset/20260728202520.59179-1-ja%40ssi.bg Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Conflicts: include/net/ip_vs.h [commit f0be83d54217 ("ipvs: add est_cpulist and est_nice sysctl vars") not merged] Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- include/net/ip_vs.h | 19 +++++-------------- net/netfilter/ipvs/ip_vs_proto_sctp.c | 2 +- 2 files changed, 6 insertions(+), 15 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index c74e496..0ab48a6 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -24,9 +24,7 @@ #include <linux/netfilter.h> /* for union nf_inet_addr */ #include <linux/ip.h> #include <linux/ipv6.h> /* for struct ipv6hdr */ -#include <net/route.h> #include <net/ipv6.h> -#include <net/ip6_fib.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif @@ -1596,30 +1594,23 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } -static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af) +static inline bool ip_vs_checksum_needed(struct sk_buff *skb) { /* Checksum unnecessary or already validated? */ if (skb_csum_unnecessary(skb)) return false; - /* LOCAL_OUT ? */ - if (!skb->dev || skb->dev->flags & IFF_LOOPBACK) + /* Locally generated ? */ + if (!skb->dev) return false; - /* !LOCAL_IN (FORWARD) ? */ - if (af == AF_INET6) { - if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL)) - return false; - } else { - if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) - return false; - } return true; } static inline bool ip_vs_checksum_common_check(struct sk_buff *skb, int offset, int proto, int af) { - if (!ip_vs_checksum_needed(skb, af)) + if (!ip_vs_checksum_needed(skb)) return true; + /* Validate csum even for FORWARD */ return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af); } diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 724d361..663c44c 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -193,7 +193,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, struct sctphdr *sh; __le32 cmp, val; - if (!ip_vs_checksum_needed(skb, af)) + if (!ip_vs_checksum_needed(skb)) return 1; sh = (struct sctphdr *)(skb->data + sctphoff); cmp = sh->checksum; -- 2.9.5
From: Julian Anastasov <ja@ssi.bg> mainline inclusion from mainline-v7.2 commit d93660df4dd1d116f608ada4a29a80a5d6f0a6ed category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18235 CVE: CVE-2026-74724 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- While the outer IP header is already pulled into the skb head, we must be careful and revalidate the embedded headers after reading them from the skb frags to prevent out-of-bounds access. One such place reported by Sashiko is ip_vs_nat_icmp() where local process can change the ihl field and after skb_ensure_writable() we can see larger value which is a problem for the ip_send_check(cih) calls. Add check to drop the packet if the ihl field is changed. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Link: https://sashiko.dev/#/patchset/20260730183506.87473-1-ja%40ssi.bg Signed-off-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Conflicts: include/net/ip_vs.h net/netfilter/ipvs/ip_vs_xmit.c [ip_vs.h: f20c73b0460d ("ipvs: use more keys for connection hashing") not merged. ip_vs_xmit.c: 210ffe4a74ca ("ipvs: Remove {Enter,Leave}Function") and e8dfd42c17fa ("ipv6: introduce dst_rt6_info() helper") not merged] Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com> --- include/net/ip_vs.h | 2 +- net/netfilter/ipvs/ip_vs_core.c | 11 +++++++++-- net/netfilter/ipvs/ip_vs_xmit.c | 3 ++- 3 files changed, 12 insertions(+), 4 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 0ab48a6..34eee63 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1559,7 +1559,7 @@ static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp) return fwd; } -void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, +bool ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int dir, unsigned int toff, bool has_ports, struct ip_vs_iphdr *ciph); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 49123c9..031d7ba 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -757,7 +757,7 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, * Packet has been made sufficiently writable in caller * - inout: 1=in->out, 0=out->in */ -void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, +bool ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout, unsigned int toff, bool has_ports, struct ip_vs_iphdr *ciph) { @@ -765,6 +765,11 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct icmphdr *icmph = (struct icmphdr *)(skb->data + toff); struct iphdr *cih = (struct iphdr *)(icmph + 1); + /* Before now we may used ihl from skb frag, revalidate it after + * copying it into skb head to prevent out-of-bounds access + */ + if (cih->ihl * 4 != ciph->len - ciph->off) + return false; if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); @@ -798,6 +803,7 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, else IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off, "Forwarding altered incoming ICMP"); + return true; } #ifdef CONFIG_IP_VS_IPV6 @@ -889,7 +895,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph); else #endif - ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph); + if (!ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph)) + goto out; if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 32e304b..df69042 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1591,7 +1591,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; - ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph); + if (!ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph)) + goto tx_error; /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; -- 2.9.5
participants (2)
-
patchwork bot -
Zhang Changzhong