tproxy: kick out TIME_WAIT sockets in case a new connection comes in with the same tuple

Without tproxy redirections an incoming SYN kicks out conflicting
TIME_WAIT sockets, in order to handle clients that reuse ports
within the TIME_WAIT period.

The same mechanism didn't work in case TProxy is involved in finding
the proper socket, as the time_wait processing code looked up the
listening socket assuming that the listener addr/port matches those
of the established connection.

This is not the case with TProxy as the listener addr/port is possibly
changed with the tproxy rule.

Signed-off-by: Balazs Scheidler <bazsi@balabit.hu>
Signed-off-by: KOVACS Krisztian <hidden@balabit.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>

3 files changed, 85 insertions, 14 deletions

diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c
index 5490fc3..8589e5e 100644
--- a/net/netfilter/nf_tproxy_core.c
+++ b/net/netfilter/nf_tproxy_core.c
@@ -22,21 +22,34 @@ struct sock *
 nf_tproxy_get_sock_v4(struct net *net, const u8 protocol,
 		      const __be32 saddr, const __be32 daddr,
 		      const __be16 sport, const __be16 dport,
-		      const struct net_device *in, bool listening_only)
+		      const struct net_device *in, int lookup_type)
 {
 	struct sock *sk;
 
 	/* look up socket */
 	switch (protocol) {
 	case IPPROTO_TCP:
-		if (listening_only)
-			sk = __inet_lookup_listener(net, &tcp_hashinfo,
-						    daddr, ntohs(dport),
-						    in->ifindex);
-		else
+		switch (lookup_type) {
+		case NFT_LOOKUP_ANY:
 			sk = __inet_lookup(net, &tcp_hashinfo,
 					   saddr, sport, daddr, dport,
 					   in->ifindex);
+			break;
+		case NFT_LOOKUP_LISTENER:
+			sk = inet_lookup_listener(net, &tcp_hashinfo,
+						    daddr, dport,
+						    in->ifindex);
+			break;
+		case NFT_LOOKUP_ESTABLISHED:
+			sk = inet_lookup_established(net, &tcp_hashinfo,
+						    saddr, sport, daddr, dport,
+						    in->ifindex);
+			break;
+		default:
+			WARN_ON(1);
+			sk = NULL;
+			break;
+		}
 		break;
 	case IPPROTO_UDP:
 		sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
@@ -47,8 +60,8 @@ nf_tproxy_get_sock_v4(struct net *net, const u8 protocol,
 		sk = NULL;
 	}
 
-	pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, listener only: %d, sock %p\n",
-		 protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), listening_only, sk);
+	pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n",
+		 protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk);
 
 	return sk;
 }
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 21bb2af..e0b6900 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -24,6 +24,57 @@
 #include <net/netfilter/ipv4/nf_defrag_ipv4.h>
 #include <net/netfilter/nf_tproxy_core.h>
 
+/**
+ * tproxy_handle_time_wait() - handle TCP TIME_WAIT reopen redirections
+ * @skb:	The skb being processed.
+ * @par:	Iptables target parameters.
+ * @sk:		The TIME_WAIT TCP socket found by the lookup.
+ *
+ * We have to handle SYN packets arriving to TIME_WAIT sockets
+ * differently: instead of reopening the connection we should rather
+ * redirect the new connection to the proxy if there's a listener
+ * socket present.
+ *
+ * tproxy_handle_time_wait() consumes the socket reference passed in.
+ *
+ * Returns the listener socket if there's one, the TIME_WAIT socket if
+ * no such listener is found, or NULL if the TCP header is incomplete.
+ */
+static struct sock *
+tproxy_handle_time_wait(struct sk_buff *skb, const struct xt_action_param *par, struct sock *sk)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	const struct xt_tproxy_target_info *tgi = par->targinfo;
+	struct tcphdr _hdr, *hp;
+
+	hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);
+	if (hp == NULL) {
+		inet_twsk_put(inet_twsk(sk));
+		return NULL;
+	}
+
+	if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
+		/* SYN to a TIME_WAIT socket, we'd rather redirect it
+		 * to a listener socket if there's one */
+		struct sock *sk2;
+
+		sk2 = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol,
+					    iph->saddr, tgi->laddr ? tgi->laddr : iph->daddr,
+					    hp->source, tgi->lport ? tgi->lport : hp->dest,
+					    par->in, NFT_LOOKUP_LISTENER);
+		if (sk2) {
+			/* yeah, there's one, let's kill the TIME_WAIT
+			 * socket and redirect to the listener
+			 */
+			inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
+			inet_twsk_put(inet_twsk(sk));
+			sk = sk2;
+		}
+	}
+
+	return sk;
+}
+
 static unsigned int
 tproxy_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
@@ -37,11 +88,18 @@ tproxy_tg(struct sk_buff *skb, const struct xt_action_param *par)
 		return NF_DROP;
 
 	sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol,
-				   iph->saddr,
-				   tgi->laddr ? tgi->laddr : iph->daddr,
-				   hp->source,
-				   tgi->lport ? tgi->lport : hp->dest,
-				   par->in, true);
+				   iph->saddr, iph->daddr,
+				   hp->source, hp->dest,
+				   par->in, NFT_LOOKUP_ESTABLISHED);
+
+	/* UDP has no TCP_TIME_WAIT state, so we never enter here */
+	if (sk && sk->sk_state == TCP_TIME_WAIT)
+		sk = tproxy_handle_time_wait(skb, par, sk);
+	else if (!sk)
+		sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol,
+					   iph->saddr, tgi->laddr ? tgi->laddr : iph->daddr,
+					   hp->source, tgi->lport ? tgi->lport : hp->dest,
+					   par->in, NFT_LOOKUP_LISTENER);
 
 	/* NOTE: assign_sock consumes our sk reference */
 	if (sk && nf_tproxy_assign_sock(skb, sk)) {
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 1ca8990..266faa0 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -142,7 +142,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 #endif
 
 	sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol,
-				   saddr, daddr, sport, dport, par->in, false);
+				   saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY);
 	if (sk != NULL) {
 		bool wildcard;
 		bool transparent = true;