netfilter: nf_conntrack_ipv6: improve fragmentation handling

The IPv6 conntrack fragmentation currently has a couple of shortcomings.
Fragmentes are collected in PREROUTING/OUTPUT, are defragmented, the
defragmented packet is then passed to conntrack, the resulting conntrack
information is attached to each original fragment and the fragments then
continue their way through the stack.

Helper invocation occurs in the POSTROUTING hook, at which point only
the original fragments are available. The result of this is that
fragmented packets are never passed to helpers.

This patch improves the situation in the following way:

- If a reassembled packet belongs to a connection that has a helper
  assigned, the reassembled packet is passed through the stack instead
  of the original fragments.

- During defragmentation, the largest received fragment size is stored.
  On output, the packet is refragmented if required. If the largest
  received fragment size exceeds the outgoing MTU, a "packet too big"
  message is generated, thus behaving as if the original fragments
  were passed through the stack from an outside point of view.

- The ipv6_helper() hook function can't receive fragments anymore for
  connections using a helper, so it is switched to use ipv6_skip_exthdr()
  instead of the netfilter specific nf_ct_ipv6_skip_exthdr() and the
  reassembled packets are passed to connection tracking helpers.

The result of this is that we can properly track fragmented packets, but
still generate ICMPv6 Packet too big messages if we would have before.

This patch is also required as a precondition for IPv6 NAT, where NAT
helpers might enlarge packets up to a point that they require
fragmentation. In that case we can't generate Packet too big messages
since the proper MTU can't be calculated in all cases (f.i. when
changing textual representation of a variable amount of addresses),
so the packet is transparently fragmented iff the original packet or
fragments would have fit the outgoing MTU.

IPVS parts by Jesper Dangaard Brouer <brouer@redhat.com>.

Signed-off-by: Patrick McHardy <kaber@trash.net>

1 files changed, 16 insertions, 3 deletions

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index c9c78c2e666b..f94fb3ac2a79 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -190,6 +190,7 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
 			     const struct frag_hdr *fhdr, int nhoff)
 {
 	struct sk_buff *prev, *next;
+	unsigned int payload_len;
 	int offset, end;
 
 	if (fq->q.last_in & INET_FRAG_COMPLETE) {
@@ -197,8 +198,10 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
 		goto err;
 	}
 
+	payload_len = ntohs(ipv6_hdr(skb)->payload_len);
+
 	offset = ntohs(fhdr->frag_off) & ~0x7;
-	end = offset + (ntohs(ipv6_hdr(skb)->payload_len) -
+	end = offset + (payload_len -
 			((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
 
 	if ((unsigned int)end > IPV6_MAXPLEN) {
@@ -307,6 +310,8 @@ found:
 	skb->dev = NULL;
 	fq->q.stamp = skb->tstamp;
 	fq->q.meat += skb->len;
+	if (payload_len > fq->q.max_size)
+		fq->q.max_size = payload_len;
 	atomic_add(skb->truesize, &nf_init_frags.mem);
 
 	/* The first fragment.
@@ -412,10 +417,12 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
 	}
 	atomic_sub(head->truesize, &nf_init_frags.mem);
 
+	head->local_df = 1;
 	head->next = NULL;
 	head->dev = dev;
 	head->tstamp = fq->q.stamp;
 	ipv6_hdr(head)->payload_len = htons(payload_len);
+	IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;
 
 	/* Yes, and fold redundant checksum back. 8) */
 	if (head->ip_summed == CHECKSUM_COMPLETE)
@@ -592,6 +599,7 @@ void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
 			int (*okfn)(struct sk_buff *))
 {
 	struct sk_buff *s, *s2;
+	unsigned int ret = 0;
 
 	for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
 		nf_conntrack_put_reasm(s->nfct_reasm);
@@ -601,8 +609,13 @@ void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
 		s2 = s->next;
 		s->next = NULL;
 
-		NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s, in, out, okfn,
-			       NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
+		if (ret != -ECANCELED)
+			ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s,
+					     in, out, okfn,
+					     NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
+		else
+			kfree_skb(s);
+
 		s = s2;
 	}
 	nf_conntrack_put_reasm(skb);