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/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index dab7381..2878dbf 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -69,7 +69,7 @@
}
EXPORT_SYMBOL(xfrm4_prepare_output);
-int xfrm4_output_finish(struct sk_buff *skb)
+int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
{
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
@@ -77,26 +77,26 @@
IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
#endif
- return xfrm_output(skb);
+ return xfrm_output(sk, skb);
}
-static int __xfrm4_output(struct sk_buff *skb)
+static int __xfrm4_output(struct sock *sk, struct sk_buff *skb)
{
struct xfrm_state *x = skb_dst(skb)->xfrm;
#ifdef CONFIG_NETFILTER
if (!x) {
IPCB(skb)->flags |= IPSKB_REROUTED;
- return dst_output(skb);
+ return dst_output_sk(sk, skb);
}
#endif
- return x->outer_mode->afinfo->output_finish(skb);
+ return x->outer_mode->afinfo->output_finish(sk, skb);
}
int xfrm4_output(struct sock *sk, struct sk_buff *skb)
{
- return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb,
+ return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb,
NULL, skb_dst(skb)->dev, __xfrm4_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}