netfilter: push reasm skb through instead of original frag skbs

Pushing original fragments through causes several problems. For example
for matching, frags may not be matched correctly. Take following
example:

<example>
On HOSTA do:
ip6tables -I INPUT -p icmpv6 -j DROP
ip6tables -I INPUT -p icmpv6 -m icmp6 --icmpv6-type 128 -j ACCEPT

and on HOSTB you do:
ping6 HOSTA -s2000    (MTU is 1500)

Incoming echo requests will be filtered out on HOSTA. This issue does
not occur with smaller packets than MTU (where fragmentation does not happen)
</example>

As was discussed previously, the only correct solution seems to be to use
reassembled skb instead of separete frags. Doing this has positive side
effects in reducing sk_buff by one pointer (nfct_reasm) and also the reams
dances in ipvs and conntrack can be removed.

Future plan is to remove net/ipv6/netfilter/nf_conntrack_reasm.c
entirely and use code in net/ipv6/reassembly.c instead.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c

@@ -169,64 +169,13 @@ out:
 	return nf_conntrack_confirm(skb);
 }
 
-static unsigned int __ipv6_conntrack_in(struct net *net,
-					unsigned int hooknum,
-					struct sk_buff *skb,
-					const struct net_device *in,
-					const struct net_device *out,
-					int (*okfn)(struct sk_buff *))
-{
-	struct sk_buff *reasm = skb->nfct_reasm;
-	const struct nf_conn_help *help;
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-
-	/* This packet is fragmented and has reassembled packet. */
-	if (reasm) {
-		/* Reassembled packet isn't parsed yet ? */
-		if (!reasm->nfct) {
-			unsigned int ret;
-
-			ret = nf_conntrack_in(net, PF_INET6, hooknum, reasm);
-			if (ret != NF_ACCEPT)
-				return ret;
-		}
-
-		/* Conntrack helpers need the entire reassembled packet in the
-		 * POST_ROUTING hook. In case of unconfirmed connections NAT
-		 * might reassign a helper, so the entire packet is also
-		 * required.
-		 */
-		ct = nf_ct_get(reasm, &ctinfo);
-		if (ct != NULL && !nf_ct_is_untracked(ct)) {
-			help = nfct_help(ct);
-			if ((help && help->helper) || !nf_ct_is_confirmed(ct)) {
-				nf_conntrack_get_reasm(reasm);
-				NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
-					       (struct net_device *)in,
-					       (struct net_device *)out,
-					       okfn, NF_IP6_PRI_CONNTRACK + 1);
-				return NF_DROP_ERR(-ECANCELED);
-			}
-		}
-
-		nf_conntrack_get(reasm->nfct);
-		skb->nfct = reasm->nfct;
-		skb->nfctinfo = reasm->nfctinfo;
-		return NF_ACCEPT;
-	}
-
-	return nf_conntrack_in(net, PF_INET6, hooknum, skb);
-}
-
 static unsigned int ipv6_conntrack_in(const struct nf_hook_ops *ops,
 				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
-	return __ipv6_conntrack_in(dev_net(in), ops->hooknum, skb, in, out,
-				   okfn);
+	return nf_conntrack_in(dev_net(in), PF_INET6, ops->hooknum, skb);
 }
 
 static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops,
@@ -240,8 +189,7 @@ static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops,
 		net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
 		return NF_ACCEPT;
 	}
-	return __ipv6_conntrack_in(dev_net(out), ops->hooknum, skb, in, out,
-				   okfn);
+	return nf_conntrack_in(dev_net(out), PF_INET6, ops->hooknum, skb);
 }
 
 static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {

net/ipv6/netfilter/nf_conntrack_reasm.c

@@ -633,31 +633,16 @@ ret_orig:
 	return skb;
 }
 
-void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-			struct net_device *in, struct net_device *out,
-			int (*okfn)(struct sk_buff *))
+void nf_ct_frag6_consume_orig(struct sk_buff *skb)
 {
 	struct sk_buff *s, *s2;
-	unsigned int ret = 0;
 
 	for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
-		nf_conntrack_put_reasm(s->nfct_reasm);
-		nf_conntrack_get_reasm(skb);
-		s->nfct_reasm = skb;
-
 		s2 = s->next;
 		s->next = NULL;
-
-		if (ret != -ECANCELED)
-			ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s,
-					     in, out, okfn,
-					     NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
-		else
-			kfree_skb(s);
-
+		consume_skb(s);
 		s = s2;
 	}
-	nf_conntrack_put_reasm(skb);
 }
 
 static int nf_ct_net_init(struct net *net)

net/ipv6/netfilter/nf_defrag_ipv6_hooks.c

@@ -75,8 +75,11 @@ static unsigned int ipv6_defrag(const struct nf_hook_ops *ops,
 	if (reasm == skb)
 		return NF_ACCEPT;
 
-	nf_ct_frag6_output(ops->hooknum, reasm, (struct net_device *)in,
-			   (struct net_device *)out, okfn);
+	nf_ct_frag6_consume_orig(reasm);
+
+	NF_HOOK_THRESH(NFPROTO_IPV6, ops->hooknum, reasm,
+		       (struct net_device *) in, (struct net_device *) out,
+		       okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
 
 	return NF_STOLEN;
 }