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>

1 files changed, 8 insertions, 7 deletions

diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 010f8bd2d577..09c76a7b474d 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -120,7 +120,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(xfrm6_prepare_output);
 
-int xfrm6_output_finish(struct sk_buff *skb)
+int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 
@@ -128,10 +128,10 @@ int xfrm6_output_finish(struct sk_buff *skb)
 	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
 #endif
 
-	return xfrm_output(skb);
+	return xfrm_output(sk, skb);
 }
 
-static int __xfrm6_output(struct sk_buff *skb)
+static int __xfrm6_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct xfrm_state *x = dst->xfrm;
@@ -140,7 +140,7 @@ static int __xfrm6_output(struct sk_buff *skb)
 #ifdef CONFIG_NETFILTER
 	if (!x) {
 		IP6CB(skb)->flags |= IP6SKB_REROUTED;
-		return dst_output(skb);
+		return dst_output_sk(sk, skb);
 	}
 #endif
 
@@ -160,14 +160,15 @@ static int __xfrm6_output(struct sk_buff *skb)
 	if (x->props.mode == XFRM_MODE_TUNNEL &&
 	    ((skb->len > mtu && !skb_is_gso(skb)) ||
 		dst_allfrag(skb_dst(skb)))) {
-			return ip6_fragment(skb, x->outer_mode->afinfo->output_finish);
+		return ip6_fragment(sk, skb,
+				    x->outer_mode->afinfo->output_finish);
 	}
-	return x->outer_mode->afinfo->output_finish(skb);
+	return x->outer_mode->afinfo->output_finish(sk, skb);
 }
 
 int xfrm6_output(struct sock *sk, struct sk_buff *skb)
 {
-	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb,
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, sk, skb,
 			    NULL, skb_dst(skb)->dev, __xfrm6_output,
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }