IPVS: make FTP work with full NAT support

Use nf_conntrack/nf_nat code to do the packet mangling and the TCP
sequence adjusting.  The function 'ip_vs_skb_replace' is now dead
code, so it is removed.

To SNAT FTP, use something like:

% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
    --vport 21 -j SNAT --to-source 192.168.10.10
and for the data connections in passive mode:

% iptables -t nat -A POSTROUTING -m ipvs --vaddr 192.168.100.30/32 \
    --vportctl 21 -j SNAT --to-source 192.168.10.10
using '-m state --state RELATED' would also works.

Make sure the kernel modules ip_vs_ftp, nf_conntrack_ftp, and
nf_nat_ftp are loaded.

[ up-port and minor fixes by Simon Horman <horms@verge.net.au> ]
Signed-off-by: Hannes Eder <heder@google.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Patrick McHardy <kaber@trash.net>

include/net/ip_vs.h

@@ -736,8 +736,6 @@ extern void ip_vs_app_inc_put(struct ip_vs_app *inc);
 
 extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
 extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
-extern int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri,
-			     char *o_buf, int o_len, char *n_buf, int n_len);
 extern int ip_vs_app_init(void);
 extern void ip_vs_app_cleanup(void);
 

net/netfilter/ipvs/Kconfig

@@ -235,7 +235,7 @@ comment 'IPVS application helper'
 
 config	IP_VS_FTP
   	tristate "FTP protocol helper"
-        depends on IP_VS_PROTO_TCP
+        depends on IP_VS_PROTO_TCP && NF_NAT
 	---help---
 	  FTP is a protocol that transfers IP address and/or port number in
 	  the payload. In the virtual server via Network Address Translation,

net/netfilter/ipvs/ip_vs_app.c

@@ -569,49 +569,6 @@ static const struct file_operations ip_vs_app_fops = {
 };
 #endif
 
-
-/*
- *	Replace a segment of data with a new segment
- */
-int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri,
-		      char *o_buf, int o_len, char *n_buf, int n_len)
-{
-	int diff;
-	int o_offset;
-	int o_left;
-
-	EnterFunction(9);
-
-	diff = n_len - o_len;
-	o_offset = o_buf - (char *)skb->data;
-	/* The length of left data after o_buf+o_len in the skb data */
-	o_left = skb->len - (o_offset + o_len);
-
-	if (diff <= 0) {
-		memmove(o_buf + n_len, o_buf + o_len, o_left);
-		memcpy(o_buf, n_buf, n_len);
-		skb_trim(skb, skb->len + diff);
-	} else if (diff <= skb_tailroom(skb)) {
-		skb_put(skb, diff);
-		memmove(o_buf + n_len, o_buf + o_len, o_left);
-		memcpy(o_buf, n_buf, n_len);
-	} else {
-		if (pskb_expand_head(skb, skb_headroom(skb), diff, pri))
-			return -ENOMEM;
-		skb_put(skb, diff);
-		memmove(skb->data + o_offset + n_len,
-			skb->data + o_offset + o_len, o_left);
-		skb_copy_to_linear_data_offset(skb, o_offset, n_buf, n_len);
-	}
-
-	/* must update the iph total length here */
-	ip_hdr(skb)->tot_len = htons(skb->len);
-
-	LeaveFunction(9);
-	return 0;
-}
-
-
 int __init ip_vs_app_init(void)
 {
 	/* we will replace it with proc_net_ipvs_create() soon */

net/netfilter/ipvs/ip_vs_core.c

@@ -54,7 +54,6 @@
 
 EXPORT_SYMBOL(register_ip_vs_scheduler);
 EXPORT_SYMBOL(unregister_ip_vs_scheduler);
-EXPORT_SYMBOL(ip_vs_skb_replace);
 EXPORT_SYMBOL(ip_vs_proto_name);
 EXPORT_SYMBOL(ip_vs_conn_new);
 EXPORT_SYMBOL(ip_vs_conn_in_get);

net/netfilter/ipvs/ip_vs_ftp.c

@@ -20,6 +20,17 @@
  *
  * Author:	Wouter Gadeyne
  *
+ *
+ * Code for ip_vs_expect_related and ip_vs_expect_callback is taken from
+ * http://www.ssi.bg/~ja/nfct/:
+ *
+ * ip_vs_nfct.c:	Netfilter connection tracking support for IPVS
+ *
+ * Portions Copyright (C) 2001-2002
+ * Antefacto Ltd, 181 Parnell St, Dublin 1, Ireland.
+ *
+ * Portions Copyright (C) 2003-2008
+ * Julian Anastasov
  */
 
 #define KMSG_COMPONENT "IPVS"
@@ -32,6 +43,9 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/netfilter.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_nat_helper.h>
 #include <linux/gfp.h>
 #include <net/protocol.h>
 #include <net/tcp.h>
@@ -43,6 +57,16 @@
 #define SERVER_STRING "227 Entering Passive Mode ("
 #define CLIENT_STRING "PORT "
 
+#define FMT_TUPLE	"%pI4:%u->%pI4:%u/%u"
+#define ARG_TUPLE(T)	&(T)->src.u3.ip, ntohs((T)->src.u.all), \
+			&(T)->dst.u3.ip, ntohs((T)->dst.u.all), \
+			(T)->dst.protonum
+
+#define FMT_CONN	"%pI4:%u->%pI4:%u->%pI4:%u/%u:%u"
+#define ARG_CONN(C)	&((C)->caddr.ip), ntohs((C)->cport), \
+			&((C)->vaddr.ip), ntohs((C)->vport), \
+			&((C)->daddr.ip), ntohs((C)->dport), \
+			(C)->protocol, (C)->state
 
 /*
  * List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper
@@ -123,6 +147,119 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit,
 	return 1;
 }
 
+/*
+ * Called from init_conntrack() as expectfn handler.
+ */
+static void
+ip_vs_expect_callback(struct nf_conn *ct,
+		      struct nf_conntrack_expect *exp)
+{
+	struct nf_conntrack_tuple *orig, new_reply;
+	struct ip_vs_conn *cp;
+
+	if (exp->tuple.src.l3num != PF_INET)
+		return;
+
+	/*
+	 * We assume that no NF locks are held before this callback.
+	 * ip_vs_conn_out_get and ip_vs_conn_in_get should match their
+	 * expectations even if they use wildcard values, now we provide the
+	 * actual values from the newly created original conntrack direction.
+	 * The conntrack is confirmed when packet reaches IPVS hooks.
+	 */
+
+	/* RS->CLIENT */
+	orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+	cp = ip_vs_conn_out_get(exp->tuple.src.l3num, orig->dst.protonum,
+				&orig->src.u3, orig->src.u.tcp.port,
+				&orig->dst.u3, orig->dst.u.tcp.port);
+	if (cp) {
+		/* Change reply CLIENT->RS to CLIENT->VS */
+		new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+		IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", "
+			  FMT_TUPLE ", found inout cp=" FMT_CONN "\n",
+			  __func__, ct, ct->status,
+			  ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+			  ARG_CONN(cp));
+		new_reply.dst.u3 = cp->vaddr;
+		new_reply.dst.u.tcp.port = cp->vport;
+		IP_VS_DBG(7, "%s(): ct=%p, new tuples=" FMT_TUPLE ", " FMT_TUPLE
+			  ", inout cp=" FMT_CONN "\n",
+			  __func__, ct,
+			  ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+			  ARG_CONN(cp));
+		goto alter;
+	}
+
+	/* CLIENT->VS */
+	cp = ip_vs_conn_in_get(exp->tuple.src.l3num, orig->dst.protonum,
+			       &orig->src.u3, orig->src.u.tcp.port,
+			       &orig->dst.u3, orig->dst.u.tcp.port);
+	if (cp) {
+		/* Change reply VS->CLIENT to RS->CLIENT */
+		new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+		IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", "
+			  FMT_TUPLE ", found outin cp=" FMT_CONN "\n",
+			  __func__, ct, ct->status,
+			  ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+			  ARG_CONN(cp));
+		new_reply.src.u3 = cp->daddr;
+		new_reply.src.u.tcp.port = cp->dport;
+		IP_VS_DBG(7, "%s(): ct=%p, new tuples=" FMT_TUPLE ", "
+			  FMT_TUPLE ", outin cp=" FMT_CONN "\n",
+			  __func__, ct,
+			  ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+			  ARG_CONN(cp));
+		goto alter;
+	}
+
+	IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuple=" FMT_TUPLE
+		  " - unknown expect\n",
+		  __func__, ct, ct->status, ARG_TUPLE(orig));
+	return;
+
+alter:
+	/* Never alter conntrack for non-NAT conns */
+	if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ)
+		nf_conntrack_alter_reply(ct, &new_reply);
+	ip_vs_conn_put(cp);
+	return;
+}
+
+/*
+ * Create NF conntrack expectation with wildcard (optional) source port.
+ * Then the default callback function will alter the reply and will confirm
+ * the conntrack entry when the first packet comes.
+ */
+static void
+ip_vs_expect_related(struct sk_buff *skb, struct nf_conn *ct,
+		     struct ip_vs_conn *cp, u_int8_t proto,
+		     const __be16 *port, int from_rs)
+{
+	struct nf_conntrack_expect *exp;
+
+	BUG_ON(!ct || ct == &nf_conntrack_untracked);
+
+	exp = nf_ct_expect_alloc(ct);
+	if (!exp)
+		return;
+
+	if (from_rs)
+		nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
+				  nf_ct_l3num(ct), &cp->daddr, &cp->caddr,
+				  proto, port, &cp->cport);
+	else
+		nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
+				  nf_ct_l3num(ct), &cp->caddr, &cp->vaddr,
+				  proto, port, &cp->vport);
+
+	exp->expectfn = ip_vs_expect_callback;
+
+	IP_VS_DBG(7, "%s(): ct=%p, expect tuple=" FMT_TUPLE "\n",
+		  __func__, ct, ARG_TUPLE(&exp->tuple));
+	nf_ct_expect_related(exp);
+	nf_ct_expect_put(exp);
+}
 
 /*
  * Look at outgoing ftp packets to catch the response to a PASV command
@@ -149,7 +286,9 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	struct ip_vs_conn *n_cp;
 	char buf[24];		/* xxx.xxx.xxx.xxx,ppp,ppp\000 */
 	unsigned buf_len;
-	int ret;
+	int ret = 0;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
 
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
@@ -219,19 +358,26 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 
 		buf_len = strlen(buf);
 
+		ct = nf_ct_get(skb, &ctinfo);
+		if (ct && !nf_ct_is_untracked(ct)) {
+			/* If mangling fails this function will return 0
+			 * which will cause the packet to be dropped.
+			 * Mangling can only fail under memory pressure,
+			 * hopefully it will succeed on the retransmitted
+			 * packet.
+			 */
+			ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
+						       start-data, end-start,
+						       buf, buf_len);
+			if (ret)
+				ip_vs_expect_related(skb, ct, n_cp,
+						     IPPROTO_TCP, NULL, 0);
+		}
+
 		/*
-		 * Calculate required delta-offset to keep TCP happy
+		 * Not setting 'diff' is intentional, otherwise the sequence
+		 * would be adjusted twice.
 		 */
-		*diff = buf_len - (end-start);
-
-		if (*diff == 0) {
-			/* simply replace it with new passive address */
-			memcpy(start, buf, buf_len);
-			ret = 1;
-		} else {
-			ret = !ip_vs_skb_replace(skb, GFP_ATOMIC, start,
-					  end-start, buf, buf_len);
-		}
 
 		cp->app_data = NULL;
 		ip_vs_tcp_conn_listen(n_cp);
@@ -263,6 +409,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	union nf_inet_addr to;
 	__be16 port;
 	struct ip_vs_conn *n_cp;
+	struct nf_conn *ct;
 
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
@@ -349,6 +496,11 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		ip_vs_control_add(n_cp, cp);
 	}
 
+	ct = (struct nf_conn *)skb->nfct;
+	if (ct && ct != &nf_conntrack_untracked)
+		ip_vs_expect_related(skb, ct, n_cp,
+				     IPPROTO_TCP, &n_cp->dport, 1);
+
 	/*
 	 *	Move tunnel to listen state
 	 */