[NETFILTER]: Add tcp window tracking

This is the tcp window tracking patch, incremental to all previous
changes.  It is now by default enabled (i.e. in 'conservative' mode).
If you think it's better to leave it disabled ('liberal' mode), you can
change ip_conntrack_tcp_be_liberal to a different default value.

Cheers,
Signed-off-by: Jozsef Kadlecski <kadlec@blackhole.kfki.hu>
Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: David S. Miller <davem@redhat.com>

include/linux/netfilter_ipv4/ip_conntrack.h

@@ -262,6 +262,11 @@ extern void ip_ct_refresh_acct(struct ip_conntrack *ct,
 			       unsigned long extra_jiffies);
 
 /* These are for NAT.  Icky. */
+/* Update TCP window tracking data when NAT mangles the packet */
+extern int ip_conntrack_tcp_update(struct sk_buff *skb,
+				   struct ip_conntrack *conntrack,
+				   int dir);
+
 /* Call me when a conntrack is destroyed. */
 extern void (*ip_conntrack_destroyed)(struct ip_conntrack *conntrack);
 

include/linux/netfilter_ipv4/ip_conntrack_tcp.h

@@ -4,25 +4,44 @@
 
 enum tcp_conntrack {
 	TCP_CONNTRACK_NONE,
-	TCP_CONNTRACK_ESTABLISHED,
 	TCP_CONNTRACK_SYN_SENT,
 	TCP_CONNTRACK_SYN_RECV,
+	TCP_CONNTRACK_ESTABLISHED,
 	TCP_CONNTRACK_FIN_WAIT,
-	TCP_CONNTRACK_TIME_WAIT,
-	TCP_CONNTRACK_CLOSE,
 	TCP_CONNTRACK_CLOSE_WAIT,
 	TCP_CONNTRACK_LAST_ACK,
+	TCP_CONNTRACK_TIME_WAIT,
+	TCP_CONNTRACK_CLOSE,
 	TCP_CONNTRACK_LISTEN,
-	TCP_CONNTRACK_MAX
+	TCP_CONNTRACK_MAX,
+	TCP_CONNTRACK_IGNORE
+};
+
+/* Window scaling is advertised by the sender */
+#define IP_CT_TCP_STATE_FLAG_WINDOW_SCALE	0x01
+
+/* SACK is permitted by the sender */
+#define IP_CT_TCP_FLAG_SACK_PERM		0x02
+
+struct ip_ct_tcp_state {
+	u_int32_t	td_end;		/* max of seq + len */
+	u_int32_t	td_maxend;	/* max of ack + max(win, 1) */
+	u_int32_t	td_maxwin;	/* max(win) */
+	u_int8_t	td_scale;	/* window scale factor */
+	u_int8_t	loose;		/* used when connection picked up from the middle */
+	u_int8_t	flags;		/* per direction state flags */
 };
 
 struct ip_ct_tcp
 {
-	enum tcp_conntrack state;
-
-	/* Poor man's window tracking: sequence number of valid ACK
-           handshake completion packet */
-	u_int32_t handshake_ack;
+	struct ip_ct_tcp_state seen[2];	/* connection parameters per direction */
+	u_int8_t	state;		/* state of the connection (enum tcp_conntrack) */
+	/* For detecting stale connections */
+	u_int8_t	last_dir;	/* Direction of the last packet (enum ip_conntrack_dir) */
+	u_int8_t	retrans;	/* Number of retransmitted packets */
+	u_int8_t	last_index;	/* Index of the last packet */
+	u_int32_t	last_seq;	/* Last sequence number seen in dir */
+	u_int32_t	last_end;	/* Last seq + len */
 };
 
 #endif /* _IP_CONNTRACK_TCP_H */

net/ipv4/netfilter/ip_conntrack_core.c

@@ -807,12 +807,13 @@ unsigned int ip_conntrack_in(unsigned int hooknum,
 	IP_NF_ASSERT((*pskb)->nfct);
 
 	ret = proto->packet(ct, *pskb, ctinfo);
-	if (ret == -1) {
-		/* Invalid */
+	if (ret < 0) {
+		/* Invalid: inverse of the return code tells
+		 * the netfilter core what to do*/
 		nf_conntrack_put((*pskb)->nfct);
 		(*pskb)->nfct = NULL;
 		__get_cpu_var(ip_conntrack_stat).invalid++;
-		return NF_ACCEPT;
+		return -ret;
 	}
 
 	if (ret != NF_DROP && ct->helper) {

net/ipv4/netfilter/ip_conntrack_standalone.c

@@ -505,6 +505,10 @@ extern unsigned long ip_ct_tcp_timeout_close_wait;
 extern unsigned long ip_ct_tcp_timeout_last_ack;
 extern unsigned long ip_ct_tcp_timeout_time_wait;
 extern unsigned long ip_ct_tcp_timeout_close;
+extern unsigned long ip_ct_tcp_timeout_max_retrans;
+extern int ip_ct_tcp_loose;
+extern int ip_ct_tcp_be_liberal;
+extern int ip_ct_tcp_max_retrans;
 
 /* From ip_conntrack_proto_udp.c */
 extern unsigned long ip_ct_udp_timeout;
@@ -647,6 +651,38 @@ static ctl_table ip_ct_sysctl_table[] = {
 		.extra1		= &log_invalid_proto_min,
 		.extra2		= &log_invalid_proto_max,
 	},
+	{
+		.ctl_name	= NET_IPV4_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS,
+		.procname	= "ip_conntrack_tcp_timeout_max_retrans",
+		.data		= &ip_ct_tcp_timeout_max_retrans,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+	},
+	{
+		.ctl_name	= NET_IPV4_NF_CONNTRACK_TCP_LOOSE,
+		.procname	= "ip_conntrack_tcp_loose",
+		.data		= &ip_ct_tcp_loose,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL,
+		.procname	= "ip_conntrack_tcp_be_liberal",
+		.data		= &ip_ct_tcp_be_liberal,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS,
+		.procname	= "ip_conntrack_tcp_max_retrans",
+		.data		= &ip_ct_tcp_max_retrans,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 	{ .ctl_name = 0 }
 };