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>

5 files changed, 62 insertions, 15 deletions

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 879db26ec401..0b94e91ed685 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -256,6 +256,7 @@ struct inet6_skb_parm {
 #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
 	__u16			dsthao;
 #endif
+	__u16			frag_max_size;
 
 #define IP6SKB_XFRM_TRANSFORMED	1
 #define IP6SKB_FORWARDED	2
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5b2d63ed793e..a4f6263fddca 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -493,7 +493,8 @@ int ip6_forward(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if (skb->len > mtu && !skb_is_gso(skb)) {
+	if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
+	    (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -636,7 +637,9 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	/* We must not fragment if the socket is set to force MTU discovery
 	 * or if the skb it not generated by a local socket.
 	 */
-	if (unlikely(!skb->local_df && skb->len > mtu)) {
+	if (unlikely(!skb->local_df && skb->len > mtu) ||
+		     (IP6CB(skb)->frag_max_size &&
+		      IP6CB(skb)->frag_max_size > mtu)) {
 		if (skb->sk && dst_allfrag(skb_dst(skb)))
 			sk_nocaps_add(skb->sk, NETIF_F_GSO_MASK);
 
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 4794f96cf2e0..521ddca876f8 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -153,10 +153,10 @@ static unsigned int ipv6_helper(unsigned int hooknum,
 	const struct nf_conn_help *help;
 	const struct nf_conntrack_helper *helper;
 	enum ip_conntrack_info ctinfo;
-	unsigned int ret, protoff;
-	unsigned int extoff = (u8 *)(ipv6_hdr(skb) + 1) - skb->data;
-	unsigned char pnum = ipv6_hdr(skb)->nexthdr;
-
+	unsigned int ret;
+	__be16 frag_off;
+	int protoff;
+	u8 nexthdr;
 
 	/* This is where we call the helper: as the packet goes out. */
 	ct = nf_ct_get(skb, &ctinfo);
@@ -171,9 +171,10 @@ static unsigned int ipv6_helper(unsigned int hooknum,
 	if (!helper)
 		return NF_ACCEPT;
 
-	protoff = nf_ct_ipv6_skip_exthdr(skb, extoff, &pnum,
-					 skb->len - extoff);
-	if (protoff > skb->len || pnum == NEXTHDR_FRAGMENT) {
+	nexthdr = ipv6_hdr(skb)->nexthdr;
+	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+				   &frag_off);
+	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
 		pr_debug("proto header not found\n");
 		return NF_ACCEPT;
 	}
@@ -199,9 +200,14 @@ static unsigned int ipv6_confirm(unsigned int hooknum,
 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) {
@@ -213,6 +219,23 @@ static unsigned int __ipv6_conntrack_in(struct net *net,
 			if (ret != NF_ACCEPT)
 				return ret;
 		}
+
+		/* Conntrack helpers need the entire reassembled packet in the
+		 * POST_ROUTING hook.
+		 */
+		ct = nf_ct_get(reasm, &ctinfo);
+		if (ct != NULL && !nf_ct_is_untracked(ct)) {
+			help = nfct_help(ct);
+			if (help && help->helper) {
+				nf_conntrack_get_reasm(skb);
+				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;
@@ -228,7 +251,7 @@ static unsigned int ipv6_conntrack_in(unsigned int hooknum,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
-	return __ipv6_conntrack_in(dev_net(in), hooknum, skb, okfn);
+	return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn);
 }
 
 static unsigned int ipv6_conntrack_local(unsigned int hooknum,
@@ -242,7 +265,7 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum,
 		net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
 		return NF_ACCEPT;
 	}
-	return __ipv6_conntrack_in(dev_net(out), hooknum, skb, okfn);
+	return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn);
 }
 
 static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
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);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 67a39786b0a1..56f6d5d81a77 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -88,7 +88,14 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos)
 static inline bool
 __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu)
 {
-	if (skb->len > mtu && !skb_is_gso(skb)) {
+	if (IP6CB(skb)->frag_max_size) {
+		/* frag_max_size tell us that, this packet have been
+		 * defragmented by netfilter IPv6 conntrack module.
+		 */
+		if (IP6CB(skb)->frag_max_size > mtu)
+			return true; /* largest fragment violate MTU */
+	}
+	else if (skb->len > mtu && !skb_is_gso(skb)) {
 		return true; /* Packet size violate MTU size */
 	}
 	return false;