netfilter: use actual socket sk rather than skb sk when routing harder

commit 46d6c5ae953cc0be38efd0e469284df7c4328cf8 upstream.

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>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[Jason: backported to 4.19 from Sasha's 5.4 backport]
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h
index 95ab5cc64422687a0003a8719facb8f4a480285b..45ff1330b3393887f6a567fe9cdd0ec6e9f9ab87 100644 (file)
--- 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;
 

diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index c0dc4dd78887a69757291f25d66d2906f3786555..47a2de582f574ab5b0cb90b7cfef5194f8924e4c 100644 (file)
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -36,7 +36,7 @@ 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);
 

diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 8d2e5dc9a827dec61792be581c3407258c324723..3d670d5aea34481d21ea8029762e90cb55e742c8 100644 (file)
--- 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)
@@ -91,8 +93,8 @@ int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry)
                      skb->mark == rt_info->mark &&
                      iph->daddr == rt_info->daddr &&
                      iph->saddr == rt_info->saddr))
-                       return ip_route_me_harder(entry->state.net, skb,
-                                                 RTN_UNSPEC);
+                       return ip_route_me_harder(entry->state.net, entry->state.sk,
+                                                 skb, RTN_UNSPEC);
        }
        return 0;
 }

diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index 690b17ef6a44a11d953d19bc844020ed194ac959..d64b1ef43c10699cc2e677c3ea75efb71b9d89d1 100644 (file)
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -54,7 +54,7 @@ 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) {

diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index dea138ca892543cbc560f56cb6aedc7aa93336f2..0829f46ddfddf2ecbd69857422085cd2eaececa6 100644 (file)
--- 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, const struct nf_hook_state *state)
                    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);
                }

diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 6115bf1ff6f0a16f5114a095646808ab2ef63405..6a27766b7d0ff22cb32b3bc402bdd16eb1f10d6c 100644 (file)
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -329,7 +329,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
 
                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);
                }

diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 5cd06ba3535df62181e9803f0dfd2407b5e06177..4996db1f64a151dd066e9fa584c67e146acff046 100644 (file)
--- 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, struct sk_buff *oldskb, int hook)
                                   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);

diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
index 7d82934c46f424bdbd8e0c0280b082c43858567f..61003768e52bf6f8f20b6ad4bf2c9a7837bffc18 100644 (file)
--- 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(void *priv,
                    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);
                }

diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 6d0b1f3e927bd75f07cc36fe7b087723e05b85b2..5679fa3f696adde01b9c6a8e7b7051c2cb65109c 100644 (file)
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -17,10 +17,10 @@
 #include <net/xfrm.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) &
@@ -81,7 +81,7 @@ static int nf_ip6_reroute(struct sk_buff *skb,
                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;
 }

diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index b0524b18c4fb3b64f941ea2531c3e0ccba800ba7..acba3757ff60524954f69a1238689a6cb2a4b3df 100644 (file)
--- 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, const struct nf_hook_state *state)
             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);
        }

diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index ca6d38698b1ad74e2018af73bd8e1e6dab2763ae..2b6a3b27f6704b6a5ab0385c253fedce03d82793 100644 (file)
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -352,7 +352,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
 
                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);
                }

diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
index da3f1f8cb325cbdcb26665abe21fd818384769e1..afe79cb46e63042b682b3ed413084728c52304bf 100644 (file)
--- 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(void *priv,
             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);
        }

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index d5e4329579e28ce24672c8496d0f8413c5a54234..acaeeaf8144157591436d4786af847fc79002afa 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -725,12 +725,12 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af,
                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;