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>
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 2e0410e..2db4c87 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -187,7 +187,7 @@
return false;
}
-static int ip_local_deliver_finish(struct sk_buff *skb)
+static int ip_local_deliver_finish(struct sock *sk, struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
@@ -253,7 +253,8 @@
return 0;
}
- return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, skb, skb->dev, NULL,
+ return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, NULL, skb,
+ skb->dev, NULL,
ip_local_deliver_finish);
}
@@ -309,7 +310,7 @@
int sysctl_ip_early_demux __read_mostly = 1;
EXPORT_SYMBOL(sysctl_ip_early_demux);
-static int ip_rcv_finish(struct sk_buff *skb)
+static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
@@ -451,7 +452,8 @@
/* Must drop socket now because of tproxy. */
skb_orphan(skb);
- return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, dev, NULL,
+ return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb,
+ dev, NULL,
ip_rcv_finish);
csum_error: