netfilter: masquerade: don't flush all conntracks if only one address deleted on device

We configured iptables as below, which only allowed incoming data on
established connections:

iptables -t mangle -A PREROUTING -m state --state ESTABLISHED -j ACCEPT
iptables -t mangle -P PREROUTING DROP

When deleting a secondary address, current masquerade implements would
flush all conntracks on this device. All the established connections on
primary address also be deleted, then subsequent incoming data on the
connections would be dropped wrongly because it was identified as NEW
connection.

So when an address was delete, it should only flush connections related
with the address.

Signed-off-by: Tan Hu <tan.hu@zte.com.cn>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 16 insertions, 3 deletions

diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index e6eb7cf9b54f..3e4bf2286abe 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -87,18 +87,30 @@ static struct notifier_block masq_dev_notifier = {
 struct masq_dev_work {
 	struct work_struct work;
 	struct net *net;
+	struct in6_addr addr;
 	int ifindex;
 };
 
+static int inet_cmp(struct nf_conn *ct, void *work)
+{
+	struct masq_dev_work *w = (struct masq_dev_work *)work;
+	struct nf_conntrack_tuple *tuple;
+
+	if (!device_cmp(ct, (void *)(long)w->ifindex))
+		return 0;
+
+	tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+
+	return ipv6_addr_equal(&w->addr, &tuple->dst.u3.in6);
+}
+
 static void iterate_cleanup_work(struct work_struct *work)
 {
 	struct masq_dev_work *w;
-	long index;
 
 	w = container_of(work, struct masq_dev_work, work);
 
-	index = w->ifindex;
-	nf_ct_iterate_cleanup_net(w->net, device_cmp, (void *)index, 0, 0);
+	nf_ct_iterate_cleanup_net(w->net, inet_cmp, (void *)w, 0, 0);
 
 	put_net(w->net);
 	kfree(w);
@@ -147,6 +159,7 @@ static int masq_inet_event(struct notifier_block *this,
 		INIT_WORK(&w->work, iterate_cleanup_work);
 		w->ifindex = dev->ifindex;
 		w->net = net;
+		w->addr = ifa->addr;
 		schedule_work(&w->work);
 
 		return NOTIFY_DONE;