--- /dev/null
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+To: Pablo Neira Ayuso <pablo@netfilter.org>,
+ netfilter-devel@vger.kernel.org, netdev@vger.kernel.org
+Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Subject: [PATCH nf 2/2] netfilter: use actual socket sk rather than skb sk when routing harder
+Date: Thu, 29 Oct 2020 03:56:06 +0100
+Message-ID: <20201029025606.3523771-3-Jason@zx2c4.com> (raw)
+In-Reply-To: <20201029025606.3523771-1-Jason@zx2c4.com>
+
+If netfilter changes the packet mark when mangling, the packet is
+rerouted using the route_me_harder set of functions. Prior to this
+commit, there's one big difference between route_me_harder and the
+ordinary initial routing functions, described in the comment above
+__ip_queue_xmit():
+
+ /* Note: skb->sk can be different from sk, in case of tunnels */
+ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
+
+That function goes on to correctly make use of sk->sk_bound_dev_if,
+rather than skb->sk->sk_bound_dev_if. And indeed the comment is true: a
+tunnel will receive a packet in ndo_start_xmit with an initial skb->sk.
+It will make some transformations to that packet, and then it will send
+the encapsulated packet out of a *new* socket. That new socket will
+basically always have a different sk_bound_dev_if (otherwise there'd be
+a routing loop). So for the purposes of routing the encapsulated packet,
+the routing information as it pertains to the socket should come from
+that socket's sk, rather than the packet's original skb->sk. For that
+reason __ip_queue_xmit() and related functions all do the right thing.
+
+One might argue that all tunnels should just call skb_orphan(skb) before
+transmitting the encapsulated packet into the new socket. But tunnels do
+*not* do this -- and this is wisely avoided in skb_scrub_packet() too --
+because features like TSQ rely on skb->destructor() being called when
+that buffer space is truely available again. Calling skb_orphan(skb) too
+early would result in buffers filling up unnecessarily and accounting
+info being all wrong. Instead, additional routing must take into account
+the new sk, just as __ip_queue_xmit() notes.
+
+So, this commit addresses the problem by fishing the correct sk out of
+state->sk -- it's already set properly in the call to nf_hook() in
+__ip_local_out(), which receives the sk as part of its normal
+functionality. So we make sure to plumb state->sk through the various
+route_me_harder functions, and then make correct use of it following the
+example of __ip_queue_xmit().
+
+Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+[aaronjg@stanford.edu: backported to 4.14]
+Signed-off-by: Aaron Goodman <aaronjg@stanford.edu>
+--- a/include/linux/netfilter_ipv4.h
++++ b/include/linux/netfilter_ipv4.h
+@@ -16,7 +16,7 @@ struct ip_rt_info {
+ u_int32_t mark;
+ };
+
+-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type);
++int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned addr_type);
+
+ struct nf_queue_entry;
+
+--- a/include/linux/netfilter_ipv6.h
++++ b/include/linux/netfilter_ipv6.h
+@@ -41,7 +41,7 @@ struct nf_ipv6_ops {
+ };
+
+ #ifdef CONFIG_NETFILTER
+-int ip6_route_me_harder(struct net *net, struct sk_buff *skb);
++int ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb);
+ __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
+ unsigned int dataoff, u_int8_t protocol);
+
+--- a/net/ipv4/netfilter.c
++++ b/net/ipv4/netfilter.c
+@@ -17,17 +17,19 @@
+ #include <net/netfilter/nf_queue.h>
+
+ /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
+-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type)
++int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type)
+ {
+ const struct iphdr *iph = ip_hdr(skb);
+ struct rtable *rt;
+ struct flowi4 fl4 = {};
+ __be32 saddr = iph->saddr;
+- const struct sock *sk = skb_to_full_sk(skb);
+- __u8 flags = sk ? inet_sk_flowi_flags(sk) : 0;
++ __u8 flags;
+ struct net_device *dev = skb_dst(skb)->dev;
+ unsigned int hh_len;
+
++ sk = sk_to_full_sk(sk);
++ flags = sk ? inet_sk_flowi_flags(sk) : 0;
++
+ if (addr_type == RTN_UNSPEC)
+ addr_type = inet_addr_type_dev_table(net, dev, saddr);
+ if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
+@@ -91,7 +93,7 @@ int nf_ip_reroute(struct sk_buff *skb, c
+ skb->mark == rt_info->mark &&
+ iph->daddr == rt_info->daddr &&
+ iph->saddr == rt_info->saddr))
+- return ip_route_me_harder(entry->state.net, skb,
++ return ip_route_me_harder(entry->state.net, entry->state.sk, skb,
+ RTN_UNSPEC);
+ }
+ return 0;
+--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
++++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
+@@ -53,7 +53,7 @@ synproxy_send_tcp(struct net *net,
+
+ skb_dst_set_noref(nskb, skb_dst(skb));
+ nskb->protocol = htons(ETH_P_IP);
+- if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
++ if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
+ goto free_nskb;
+
+ if (nfct) {
+--- a/net/ipv4/netfilter/iptable_mangle.c
++++ b/net/ipv4/netfilter/iptable_mangle.c
+@@ -65,7 +65,7 @@ ipt_mangle_out(struct sk_buff *skb, cons
+ iph->daddr != daddr ||
+ skb->mark != mark ||
+ iph->tos != tos) {
+- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
++ err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
+--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
++++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+@@ -397,7 +397,7 @@ nf_nat_ipv4_local_fn(void *priv, struct
+
+ if (ct->tuplehash[dir].tuple.dst.u3.ip !=
+ ct->tuplehash[!dir].tuple.src.u3.ip) {
+- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
++ err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
+--- a/net/ipv4/netfilter/nf_reject_ipv4.c
++++ b/net/ipv4/netfilter/nf_reject_ipv4.c
+@@ -129,7 +129,7 @@ void nf_send_reset(struct net *net, stru
+ ip4_dst_hoplimit(skb_dst(nskb)));
+ nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
+
+- if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
++ if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
+ goto free_nskb;
+
+ niph = ip_hdr(nskb);
+--- a/net/ipv4/netfilter/nft_chain_route_ipv4.c
++++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c
+@@ -50,7 +50,7 @@ static unsigned int nf_route_table_hook(
+ iph->daddr != daddr ||
+ skb->mark != mark ||
+ iph->tos != tos) {
+- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
++ err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
+--- a/net/ipv6/netfilter.c
++++ b/net/ipv6/netfilter.c
+@@ -18,10 +18,10 @@
+ #include <net/ip6_checksum.h>
+ #include <net/netfilter/nf_queue.h>
+
+-int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
++int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb)
+ {
+ const struct ipv6hdr *iph = ipv6_hdr(skb);
+- struct sock *sk = sk_to_full_sk(skb->sk);
++ struct sock *sk = sk_to_full_sk(sk_partial);
+ unsigned int hh_len;
+ struct dst_entry *dst;
+ int strict = (ipv6_addr_type(&iph->daddr) &
+@@ -82,7 +82,7 @@ static int nf_ip6_reroute(struct sk_buff
+ if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
+ !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
+ skb->mark != rt_info->mark)
+- return ip6_route_me_harder(entry->state.net, skb);
++ return ip6_route_me_harder(entry->state.net, entry->state.sk, skb);
+ }
+ return 0;
+ }
+--- a/net/ipv6/netfilter/ip6table_mangle.c
++++ b/net/ipv6/netfilter/ip6table_mangle.c
+@@ -60,7 +60,7 @@ ip6t_mangle_out(struct sk_buff *skb, con
+ skb->mark != mark ||
+ ipv6_hdr(skb)->hop_limit != hop_limit ||
+ flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
+- err = ip6_route_me_harder(state->net, skb);
++ err = ip6_route_me_harder(state->net, state->sk, skb);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
+--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
++++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+@@ -414,7 +414,7 @@ nf_nat_ipv6_local_fn(void *priv, struct
+
+ if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
+ &ct->tuplehash[!dir].tuple.src.u3)) {
+- err = ip6_route_me_harder(state->net, skb);
++ err = ip6_route_me_harder(state->net, state->sk, skb);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
+--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
++++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c
+@@ -52,7 +52,7 @@ static unsigned int nf_route_table_hook(
+ skb->mark != mark ||
+ ipv6_hdr(skb)->hop_limit != hop_limit ||
+ flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
+- err = ip6_route_me_harder(state->net, skb);
++ err = ip6_route_me_harder(state->net, state->sk, skb);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
+--- a/net/netfilter/ipvs/ip_vs_core.c
++++ b/net/netfilter/ipvs/ip_vs_core.c
+@@ -713,12 +713,12 @@ static int ip_vs_route_me_harder(struct
+ struct dst_entry *dst = skb_dst(skb);
+
+ if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
+- ip6_route_me_harder(ipvs->net, skb) != 0)
++ ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0)
+ return 1;
+ } else
+ #endif
+ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
+- ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0)
++ ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0)
+ return 1;
+
+ return 0;
projects / openwrt / staging / adrian.git / commitdiff