netfilter: Pass socket pointer down through okfn().

On the output paths in particular, we have to sometimes deal with two
socket contexts.  First, and usually skb->sk, is the local socket that
generated the frame.

And second, is potentially the socket used to control a tunneling
socket, such as one the encapsulates using UDP.

We do not want to disassociate skb->sk when encapsulating in order
to fix this, because that would break socket memory accounting.

The most extreme case where this can cause huge problems is an
AF_PACKET socket transmitting over a vxlan device.  We hit code
paths doing checks that assume they are dealing with an ipv4
socket, but are actually operating upon the AF_PACKET one.

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 12 insertions, 10 deletions

diff --git a/include/net/dn_neigh.h b/include/net/dn_neigh.h
index 0f26aa707e62..d0424269313f 100644
--- a/include/net/dn_neigh.h
+++ b/include/net/dn_neigh.h
@@ -18,11 +18,11 @@ struct dn_neigh {
 
 void dn_neigh_init(void);
 void dn_neigh_cleanup(void);
-int dn_neigh_router_hello(struct sk_buff *skb);
-int dn_neigh_endnode_hello(struct sk_buff *skb);
+int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb);
+int dn_neigh_endnode_hello(struct sock *sk, struct sk_buff *skb);
 void dn_neigh_pointopoint_hello(struct sk_buff *skb);
 int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n);
-int dn_to_neigh_output(struct sk_buff *skb);
+int dn_to_neigh_output(struct sock *sk, struct sk_buff *skb);
 
 extern struct neigh_table dn_neigh_table;
 
diff --git a/include/net/ip.h b/include/net/ip.h
index 69cd9cb8400c..d14af7edd197 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -108,7 +108,8 @@ int ip_local_deliver(struct sk_buff *skb);
 int ip_mr_input(struct sk_buff *skb);
 int ip_output(struct sock *sk, struct sk_buff *skb);
 int ip_mc_output(struct sock *sk, struct sk_buff *skb);
-int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
+int ip_fragment(struct sock *sk, struct sk_buff *skb,
+                int (*output)(struct sock *, struct sk_buff *));
 int ip_do_nat(struct sk_buff *skb);
 void ip_send_check(struct iphdr *ip);
 int __ip_local_out(struct sk_buff *skb);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index eda131d179d9..5e192068e6cb 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -170,7 +170,8 @@ static inline bool ipv6_anycast_destination(const struct sk_buff *skb)
         return rt->rt6i_flags & RTF_ANYCAST;
 }
 
-int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
+int ip6_fragment(struct sock *sk, struct sk_buff *skb,
+                 int (*output)(struct sock *, struct sk_buff *));
 
 static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 {
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 65142e6af440..b6ae959824ff 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -769,7 +769,7 @@ static inline u8 ip6_tclass(__be32 flowinfo)
 int ipv6_rcv(struct sk_buff *skb, struct net_device *dev,
              struct packet_type *pt, struct net_device *orig_dev);
 
-int ip6_rcv_finish(struct sk_buff *skb);
+int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb);
 
 /*
  *      upper-layer output functions
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 461f83539493..36ac102c97c7 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -332,7 +332,7 @@ struct xfrm_state_afinfo {
         int                     (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n);
         int                     (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n);
         int                     (*output)(struct sock *sk, struct sk_buff *skb);
-        int                     (*output_finish)(struct sk_buff *skb);
+        int                     (*output_finish)(struct sock *sk, struct sk_buff *skb);
         int                     (*extract_input)(struct xfrm_state *x,
                                                  struct sk_buff *skb);
         int                     (*extract_output)(struct xfrm_state *x,
@@ -1503,7 +1503,7 @@ int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);
 int xfrm_input_resume(struct sk_buff *skb, int nexthdr);
 int xfrm_output_resume(struct sk_buff *skb, int err);
-int xfrm_output(struct sk_buff *skb);
+int xfrm_output(struct sock *sk, struct sk_buff *skb);
 int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
 void xfrm_local_error(struct sk_buff *skb, int mtu);
 int xfrm4_extract_header(struct sk_buff *skb);
@@ -1524,7 +1524,7 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
 int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm4_output(struct sock *sk, struct sk_buff *skb);
-int xfrm4_output_finish(struct sk_buff *skb);
+int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb);
 int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err);
 int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol);
 int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol);
@@ -1549,7 +1549,7 @@ __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr);
 int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm6_output(struct sock *sk, struct sk_buff *skb);
-int xfrm6_output_finish(struct sk_buff *skb);
+int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb);
 int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
                           u8 **prevhdr);