1 files changed, 56 insertions, 154 deletions

diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 4dcbd51a8e97..a06875a466a4 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -828,12 +828,18 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	return true;
 }
 
+static bool nf_conntrack_tcp_established(const struct nf_conn *ct)
+{
+	return ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED &&
+	       test_bit(IPS_ASSURED_BIT, &ct->status);
+}
+
 /* Returns verdict for packet, or -1 for invalid. */
-static int tcp_packet(struct nf_conn *ct,
-		      struct sk_buff *skb,
-		      unsigned int dataoff,
-		      enum ip_conntrack_info ctinfo,
-		      const struct nf_hook_state *state)
+int nf_conntrack_tcp_packet(struct nf_conn *ct,
+			    struct sk_buff *skb,
+			    unsigned int dataoff,
+			    enum ip_conntrack_info ctinfo,
+			    const struct nf_hook_state *state)
 {
 	struct net *net = nf_ct_net(ct);
 	struct nf_tcp_net *tn = nf_tcp_pernet(net);
@@ -1030,16 +1036,38 @@ static int tcp_packet(struct nf_conn *ct,
 			new_state = TCP_CONNTRACK_ESTABLISHED;
 		break;
 	case TCP_CONNTRACK_CLOSE:
-		if (index == TCP_RST_SET
-		    && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
-		    && before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) {
-			/* Invalid RST  */
-			spin_unlock_bh(&ct->lock);
-			nf_ct_l4proto_log_invalid(skb, ct, "invalid rst");
-			return -NF_ACCEPT;
+		if (index != TCP_RST_SET)
+			break;
+
+		if (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) {
+			u32 seq = ntohl(th->seq);
+
+			if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) {
+				/* Invalid RST  */
+				spin_unlock_bh(&ct->lock);
+				nf_ct_l4proto_log_invalid(skb, ct, "invalid rst");
+				return -NF_ACCEPT;
+			}
+
+			if (!nf_conntrack_tcp_established(ct) ||
+			    seq == ct->proto.tcp.seen[!dir].td_maxack)
+				break;
+
+			/* Check if rst is part of train, such as
+			 *   foo:80 > bar:4379: P, 235946583:235946602(19) ack 42
+			 *   foo:80 > bar:4379: R, 235946602:235946602(0)  ack 42
+			 */
+			if (ct->proto.tcp.last_index == TCP_ACK_SET &&
+			    ct->proto.tcp.last_dir == dir &&
+			    seq == ct->proto.tcp.last_end)
+				break;
+
+			/* ... RST sequence number doesn't match exactly, keep
+			 * established state to allow a possible challenge ACK.
+			 */
+			new_state = old_state;
 		}
-		if (index == TCP_RST_SET
-		    && ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
+		if (((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
 			 && ct->proto.tcp.last_index == TCP_SYN_SET)
 			|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
 			    && ct->proto.tcp.last_index == TCP_ACK_SET))
@@ -1055,7 +1083,7 @@ static int tcp_packet(struct nf_conn *ct,
 			 * segments we ignored. */
 			goto in_window;
 		}
-		/* Just fall through */
+		break;
 	default:
 		/* Keep compilers happy. */
 		break;
@@ -1090,6 +1118,8 @@ static int tcp_packet(struct nf_conn *ct,
 	if (ct->proto.tcp.retrans >= tn->tcp_max_retrans &&
 	    timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
 		timeout = timeouts[TCP_CONNTRACK_RETRANS];
+	else if (unlikely(index == TCP_RST_SET))
+		timeout = timeouts[TCP_CONNTRACK_CLOSE];
 	else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) &
 		 IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED &&
 		 timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK])
@@ -1387,146 +1417,21 @@ static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = {
 };
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
 
-#ifdef CONFIG_SYSCTL
-static struct ctl_table tcp_sysctl_table[] = {
-	{
-		.procname	= "nf_conntrack_tcp_timeout_syn_sent",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_timeout_syn_recv",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_timeout_established",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_timeout_fin_wait",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_timeout_close_wait",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_timeout_last_ack",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_timeout_time_wait",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_timeout_close",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_timeout_max_retrans",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_timeout_unacknowledged",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_loose",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname       = "nf_conntrack_tcp_be_liberal",
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
-	},
-	{
-		.procname	= "nf_conntrack_tcp_max_retrans",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{ }
-};
-#endif /* CONFIG_SYSCTL */
-
-static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn,
-				    struct nf_tcp_net *tn)
-{
-#ifdef CONFIG_SYSCTL
-	if (pn->ctl_table)
-		return 0;
-
-	pn->ctl_table = kmemdup(tcp_sysctl_table,
-				sizeof(tcp_sysctl_table),
-				GFP_KERNEL);
-	if (!pn->ctl_table)
-		return -ENOMEM;
-
-	pn->ctl_table[0].data = &tn->timeouts[TCP_CONNTRACK_SYN_SENT];
-	pn->ctl_table[1].data = &tn->timeouts[TCP_CONNTRACK_SYN_RECV];
-	pn->ctl_table[2].data = &tn->timeouts[TCP_CONNTRACK_ESTABLISHED];
-	pn->ctl_table[3].data = &tn->timeouts[TCP_CONNTRACK_FIN_WAIT];
-	pn->ctl_table[4].data = &tn->timeouts[TCP_CONNTRACK_CLOSE_WAIT];
-	pn->ctl_table[5].data = &tn->timeouts[TCP_CONNTRACK_LAST_ACK];
-	pn->ctl_table[6].data = &tn->timeouts[TCP_CONNTRACK_TIME_WAIT];
-	pn->ctl_table[7].data = &tn->timeouts[TCP_CONNTRACK_CLOSE];
-	pn->ctl_table[8].data = &tn->timeouts[TCP_CONNTRACK_RETRANS];
-	pn->ctl_table[9].data = &tn->timeouts[TCP_CONNTRACK_UNACK];
-	pn->ctl_table[10].data = &tn->tcp_loose;
-	pn->ctl_table[11].data = &tn->tcp_be_liberal;
-	pn->ctl_table[12].data = &tn->tcp_max_retrans;
-#endif
-	return 0;
-}
-
-static int tcp_init_net(struct net *net)
+void nf_conntrack_tcp_init_net(struct net *net)
 {
 	struct nf_tcp_net *tn = nf_tcp_pernet(net);
-	struct nf_proto_net *pn = &tn->pn;
-
-	if (!pn->users) {
-		int i;
-
-		for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++)
-			tn->timeouts[i] = tcp_timeouts[i];
+	int i;
 
-		/* timeouts[0] is unused, make it same as SYN_SENT so
-		 * ->timeouts[0] contains 'new' timeout, like udp or icmp.
-		 */
-		tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT];
-		tn->tcp_loose = nf_ct_tcp_loose;
-		tn->tcp_be_liberal = nf_ct_tcp_be_liberal;
-		tn->tcp_max_retrans = nf_ct_tcp_max_retrans;
-	}
+	for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++)
+		tn->timeouts[i] = tcp_timeouts[i];
 
-	return tcp_kmemdup_sysctl_table(pn, tn);
-}
-
-static struct nf_proto_net *tcp_get_net_proto(struct net *net)
-{
-	return &net->ct.nf_ct_proto.tcp.pn;
+	/* timeouts[0] is unused, make it same as SYN_SENT so
+	 * ->timeouts[0] contains 'new' timeout, like udp or icmp.
+	 */
+	tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT];
+	tn->tcp_loose = nf_ct_tcp_loose;
+	tn->tcp_be_liberal = nf_ct_tcp_be_liberal;
+	tn->tcp_max_retrans = nf_ct_tcp_max_retrans;
 }
 
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp =
@@ -1535,7 +1440,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp =
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack 	= tcp_print_conntrack,
 #endif
-	.packet 		= tcp_packet,
 	.can_early_drop		= tcp_can_early_drop,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= tcp_to_nlattr,
@@ -1556,6 +1460,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp =
 		.nla_policy	= tcp_timeout_nla_policy,
 	},
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
-	.init_net		= tcp_init_net,
-	.get_net_proto		= tcp_get_net_proto,
 };