netfilter: nf_conntrack_tcp: decrease timeouts while data in unacknowledged

In order to time out dead connections quicker, keep track of outstanding data
and cap the timeout.

Suggested by Herbert Xu.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netfilter/nf_conntrack_tcp.h

@@ -30,6 +30,9 @@ enum tcp_conntrack {
 /* Be liberal in window checking */
 #define IP_CT_TCP_FLAG_BE_LIBERAL		0x08
 
+/* Has unacknowledged data */
+#define IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED	0x10
+
 struct nf_ct_tcp_flags {
 	u_int8_t flags;
 	u_int8_t mask;

net/netfilter/nf_conntrack_proto_tcp.c

@@ -67,7 +67,8 @@ static const char *const tcp_conntrack_names[] = {
 /* RFC1122 says the R2 limit should be at least 100 seconds.
    Linux uses 15 packets as limit, which corresponds
    to ~13-30min depending on RTO. */
-static unsigned int nf_ct_tcp_timeout_max_retrans __read_mostly =   5 MINS;
+static unsigned int nf_ct_tcp_timeout_max_retrans __read_mostly    =   5 MINS;
+static unsigned int nf_ct_tcp_timeout_unacknowledged __read_mostly =   5 MINS;
 
 static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = {
 	[TCP_CONNTRACK_SYN_SENT]	= 2 MINS,
@@ -625,8 +626,10 @@ static bool tcp_in_window(const struct nf_conn *ct,
 		swin = win + (sack - ack);
 		if (sender->td_maxwin < swin)
 			sender->td_maxwin = swin;
-		if (after(end, sender->td_end))
+		if (after(end, sender->td_end)) {
 			sender->td_end = end;
+			sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
+		}
 		/*
 		 * Update receiver data.
 		 */
@@ -637,6 +640,8 @@ static bool tcp_in_window(const struct nf_conn *ct,
 			if (win == 0)
 				receiver->td_maxend++;
 		}
+		if (ack == receiver->td_end)
+			receiver->flags &= ~IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
 
 		/*
 		 * Check retransmissions.
@@ -951,9 +956,16 @@ static int tcp_packet(struct nf_conn *ct,
 	if (old_state != new_state
 	    && new_state == TCP_CONNTRACK_FIN_WAIT)
 		ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
-	timeout = ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans
-		  && tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans
-		  ? nf_ct_tcp_timeout_max_retrans : tcp_timeouts[new_state];
+
+	if (ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans &&
+	    tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans)
+		timeout = nf_ct_tcp_timeout_max_retrans;
+	else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) &
+		 IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED &&
+		 tcp_timeouts[new_state] > nf_ct_tcp_timeout_unacknowledged)
+		timeout = nf_ct_tcp_timeout_unacknowledged;
+	else
+		timeout = tcp_timeouts[new_state];
 	write_unlock_bh(&tcp_lock);
 
 	nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, skb);
@@ -1235,6 +1247,13 @@ static struct ctl_table tcp_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec_jiffies,
 	},
+	{
+		.procname	= "nf_conntrack_tcp_timeout_unacknowledged",
+		.data		= &nf_ct_tcp_timeout_unacknowledged,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+	},
 	{
 		.ctl_name	= NET_NF_CONNTRACK_TCP_LOOSE,
 		.procname	= "nf_conntrack_tcp_loose",