From: Guillaume Nault <gnault@redhat.com> stable inclusion from stable-v6.6.81 commit 661c63cb34cf8dedc01bfec3caa8dd1da2f5778e category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15230 CVE: CVE-2026-45905 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit 7e863e5db6185b1add0df4cb01b31a4ed1c4b738 ] Pass a dscp_t variable to ip_route_input(), instead of a plain u8, to prevent accidental setting of ECN bits in ->flowi4_tos. Callers of ip_route_input() to consider are: * input_action_end_dx4_finish() and input_action_end_dt4() in net/ipv6/seg6_local.c. These functions set the tos parameter to 0, which is already a valid dscp_t value, so they don't need to be adjusted for the new prototype. * icmp_route_lookup(), which already has a dscp_t variable to pass as parameter. We just need to remove the inet_dscp_to_dsfield() conversion. * br_nf_pre_routing_finish(), ip_options_rcv_srr() and ip4ip6_err(), which get the DSCP directly from IPv4 headers. Define a helper to read the .tos field of struct iphdr as dscp_t, so that these function don't have to do the conversion manually. While there, declare *iph as const in br_nf_pre_routing_finish(), declare its local variables in reverse-christmas-tree order and move the "err = ip_route_input()" assignment out of the conditional to avoid checkpatch warning. Signed-off-by: Guillaume Nault <gnault@redhat.com> Reviewed-by: David Ahern <dsahern@kernel.org> Link: https://patch.msgid.link/e9d40781d64d3d69f4c79ac8a008b8d67a033e8d.1727807926... Signed-off-by: Jakub Kicinski <kuba@kernel.org> Stable-dep-of: 27843ce6ba3d ("ipvlan: ensure network headers are in skb linear part") Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2@huawei.com> --- include/net/ip.h | 5 +++++ include/net/route.h | 5 +++-- net/bridge/br_netfilter_hooks.c | 8 +++++--- net/ipv4/icmp.c | 2 +- net/ipv4/ip_options.c | 3 ++- net/ipv6/ip6_tunnel.c | 4 ++-- 6 files changed, 18 insertions(+), 9 deletions(-) diff --git a/include/net/ip.h b/include/net/ip.h index 2fa407767f33..51117dcac303 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -409,18 +409,23 @@ static inline bool ip_is_fragment(const struct iphdr *iph) static inline int ip_decrease_ttl(struct iphdr *iph) { u32 check = (__force u32)iph->check; check += (__force u32)htons(0x0100); iph->check = (__force __sum16)(check + (check>=0xFFFF)); return --iph->ttl; } +static inline dscp_t ip4h_dscp(const struct iphdr *ip4h) +{ + return inet_dsfield_to_dscp(ip4h->tos); +} + static inline int ip_mtu_locked(const struct dst_entry *dst) { const struct rtable *rt = (const struct rtable *)dst; return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU); } static inline int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) diff --git a/include/net/route.h b/include/net/route.h index 25e61f392633..14e074d50cf4 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -188,24 +188,25 @@ int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct in_device *in_dev, u32 *itag); int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin); int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin, const struct sk_buff *hint); static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, - u8 tos, struct net_device *devin) + dscp_t dscp, struct net_device *devin) { int err; rcu_read_lock(); - err = ip_route_input_noref(skb, dst, src, tos, devin); + err = ip_route_input_noref(skb, dst, src, inet_dscp_to_dsfield(dscp), + devin); if (!err) { skb_dst_force(skb); if (!skb_dst(skb)) err = -EINVAL; } rcu_read_unlock(); return err; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 8ca424dc5b15..e6962d693359 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -360,39 +360,41 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb, * ip_route_output_key() can return success. The source * address for ip_route_output_key() is set to zero, so ip_route_output_key() * thinks we're handling a locally generated packet and won't care * if IP forwarding is enabled. If the output device equals the logical bridge * device, we proceed as if ip_route_input() succeeded. If it differs from the * logical bridge port or if ip_route_output_key() fails we drop the packet. */ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb->dev, *br_indev; - struct iphdr *iph = ip_hdr(skb); struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); + struct net_device *dev = skb->dev, *br_indev; + const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; int err; br_indev = nf_bridge_get_physindev(skb, net); if (!br_indev) { kfree_skb(skb); return 0; } nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } nf_bridge->in_prerouting = 0; if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) { - if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { + err = ip_route_input(skb, iph->daddr, iph->saddr, + ip4h_dscp(iph), dev); + if (err) { struct in_device *in_dev = __in_dev_get_rcu(dev); /* If err equals -EHOSTUNREACH the error is due to a * martian destination or due to the fact that * forwarding is disabled. For most martian packets, * ip_route_output_key() will fail. It won't fail for 2 types of * martian destinations: loopback destinations and destination * 0.0.0.0. In both cases the packet will be dropped because the * destination is the loopback device and not the bridge. */ diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index b2f396126a51..c59ca4fa9d9b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -551,19 +551,19 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, rt2 = ip_route_output_key(net, &fl4_2); if (IS_ERR(rt2)) { err = PTR_ERR(rt2); goto relookup_failed; } /* Ugh! */ orefdst = skb_in->_skb_refdst; /* save old refdst */ skb_dst_set(skb_in, NULL); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, - inet_dscp_to_dsfield(dscp), rt2->dst.dev); + dscp, rt2->dst.dev); dst_release(&rt2->dst); rt2 = skb_rtable(skb_in); skb_in->_skb_refdst = orefdst; /* restore old refdst */ } if (err) goto relookup_failed; diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 90b55384700e..95d3c39ac072 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -615,19 +615,20 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev) for (srrptr = optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4) { if (srrptr + 3 > srrspace) { icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((opt->srr+2)<<24)); return -EINVAL; } memcpy(&nexthop, &optptr[srrptr-1], 4); orefdst = skb->_skb_refdst; skb_dst_set(skb, NULL); - err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev); + err = ip_route_input(skb, nexthop, iph->saddr, ip4h_dscp(iph), + dev); rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { skb_dst_drop(skb); skb->_skb_refdst = orefdst; return -EINVAL; } refdst_drop(orefdst); if (rt2->rt_type != RTN_LOCAL) break; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b006e61e776a..5a2583a82f97 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -627,20 +627,20 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, eiph->daddr, eiph->saddr, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; } skb_dst_set(skb2, &rt->dst); } else { - if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, - skb2->dev) || + if (ip_route_input(skb2, eiph->daddr, eiph->saddr, + ip4h_dscp(eiph), skb2->dev) || skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6) goto out; } /* change mtu on this route */ if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) { if (rel_info > dst_mtu(skb_dst(skb2))) goto out; -- 2.43.0