[IPVS]: ip_vs_ftp breaks connections using persistence

ip_vs_ftp when loaded can create NAT connections with unknown client
port for passive FTP. For such expectations we lookup with cport=0 on
incoming packet but it matches the format of the persistence templates
causing packets to other persistent virtual servers to be forwarded to
real server without creating connection. Later the reply packets are
treated as foreign and not SNAT-ed.

This patch changes the connection lookup for packets from clients:

* introduce IP_VS_CONN_F_TEMPLATE connection flag to mark the
  connection as template

* create new connection lookup function just for templates -
  ip_vs_ct_in_get

* make sure ip_vs_conn_in_get hits only connections with
  IP_VS_CONN_F_NO_CPORT flag set when s_port is 0. By this way
  we avoid returning template when looking for cport=0 (ftp)

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 63 insertions, 17 deletions

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index e426641c519..06b4235aa01 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -84,6 +84,7 @@
 #define IP_VS_CONN_F_IN_SEQ	0x0400		/* must do input seq adjust */
 #define IP_VS_CONN_F_SEQ_MASK	0x0600		/* in/out sequence mask */
 #define IP_VS_CONN_F_NO_CPORT	0x0800		/* no client port set yet */
+#define IP_VS_CONN_F_TEMPLATE	0x1000		/* template, not connection */
 
 /* Move it to better place one day, for now keep it unique */
 #define NFC_IPVS_PROPERTY	0x10000
@@ -739,6 +740,8 @@ enum {
 
 extern struct ip_vs_conn *ip_vs_conn_in_get
 (int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port);
+extern struct ip_vs_conn *ip_vs_ct_in_get
+(int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port);
 extern struct ip_vs_conn *ip_vs_conn_out_get
 (int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port);
 
diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c
index 5994521fddc..f828fa2eb7d 100644
--- a/net/ipv4/ipvs/ip_vs_conn.c
+++ b/net/ipv4/ipvs/ip_vs_conn.c
@@ -196,6 +196,7 @@ static inline struct ip_vs_conn *__ip_vs_conn_in_get
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
 		if (s_addr==cp->caddr && s_port==cp->cport &&
 		    d_port==cp->vport && d_addr==cp->vaddr &&
+		    ((!s_port) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
 		    protocol==cp->protocol) {
 			/* HIT */
 			atomic_inc(&cp->refcnt);
@@ -227,6 +228,40 @@ struct ip_vs_conn *ip_vs_conn_in_get
 	return cp;
 }
 
+/* Get reference to connection template */
+struct ip_vs_conn *ip_vs_ct_in_get
+(int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port)
+{
+	unsigned hash;
+	struct ip_vs_conn *cp;
+
+	hash = ip_vs_conn_hashkey(protocol, s_addr, s_port);
+
+	ct_read_lock(hash);
+
+	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+		if (s_addr==cp->caddr && s_port==cp->cport &&
+		    d_port==cp->vport && d_addr==cp->vaddr &&
+		    cp->flags & IP_VS_CONN_F_TEMPLATE &&
+		    protocol==cp->protocol) {
+			/* HIT */
+			atomic_inc(&cp->refcnt);
+			goto out;
+		}
+	}
+	cp = NULL;
+
+  out:
+	ct_read_unlock(hash);
+
+	IP_VS_DBG(7, "template lookup/in %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d %s\n",
+		  ip_vs_proto_name(protocol),
+		  NIPQUAD(s_addr), ntohs(s_port),
+		  NIPQUAD(d_addr), ntohs(d_port),
+		  cp?"hit":"not hit");
+
+	return cp;
+}
 
 /*
  *  Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab.
@@ -367,7 +402,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
 		  atomic_read(&dest->refcnt));
 
 	/* Update the connection counters */
-	if (cp->cport || (cp->flags & IP_VS_CONN_F_NO_CPORT)) {
+	if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
 		/* It is a normal connection, so increase the inactive
 		   connection counter because it is in TCP SYNRECV
 		   state (inactive) or other protocol inacive state */
@@ -406,7 +441,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
 		  atomic_read(&dest->refcnt));
 
 	/* Update the connection counters */
-	if (cp->cport || (cp->flags & IP_VS_CONN_F_NO_CPORT)) {
+	if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
 		/* It is a normal connection, so decrease the inactconns
 		   or activeconns counter */
 		if (cp->flags & IP_VS_CONN_F_INACTIVE) {
@@ -776,7 +811,7 @@ void ip_vs_random_dropentry(void)
 		ct_write_lock_bh(hash);
 
 		list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
-			if (!cp->cport && !(cp->flags & IP_VS_CONN_F_NO_CPORT))
+			if (cp->flags & IP_VS_CONN_F_TEMPLATE)
 				/* connection template */
 				continue;
 
diff --git a/net/ipv4/ipvs/ip_vs_core.c b/net/ipv4/ipvs/ip_vs_core.c
index 3ac7eeca04a..981cc3244ef 100644
--- a/net/ipv4/ipvs/ip_vs_core.c
+++ b/net/ipv4/ipvs/ip_vs_core.c
@@ -243,10 +243,10 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	if (ports[1] == svc->port) {
 		/* Check if a template already exists */
 		if (svc->port != FTPPORT)
-			ct = ip_vs_conn_in_get(iph->protocol, snet, 0,
+			ct = ip_vs_ct_in_get(iph->protocol, snet, 0,
 					       iph->daddr, ports[1]);
 		else
-			ct = ip_vs_conn_in_get(iph->protocol, snet, 0,
+			ct = ip_vs_ct_in_get(iph->protocol, snet, 0,
 					       iph->daddr, 0);
 
 		if (!ct || !ip_vs_check_template(ct)) {
@@ -272,14 +272,14 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 						    iph->daddr,
 						    ports[1],
 						    dest->addr, dest->port,
-						    0,
+						    IP_VS_CONN_F_TEMPLATE,
 						    dest);
 			else
 				ct = ip_vs_conn_new(iph->protocol,
 						    snet, 0,
 						    iph->daddr, 0,
 						    dest->addr, 0,
-						    0,
+						    IP_VS_CONN_F_TEMPLATE,
 						    dest);
 			if (ct == NULL)
 				return NULL;
@@ -298,10 +298,10 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		 * port zero template: <protocol,caddr,0,vaddr,0,daddr,0>
 		 */
 		if (svc->fwmark)
-			ct = ip_vs_conn_in_get(IPPROTO_IP, snet, 0,
+			ct = ip_vs_ct_in_get(IPPROTO_IP, snet, 0,
 					       htonl(svc->fwmark), 0);
 		else
-			ct = ip_vs_conn_in_get(iph->protocol, snet, 0,
+			ct = ip_vs_ct_in_get(iph->protocol, snet, 0,
 					       iph->daddr, 0);
 
 		if (!ct || !ip_vs_check_template(ct)) {
@@ -326,14 +326,14 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 						    snet, 0,
 						    htonl(svc->fwmark), 0,
 						    dest->addr, 0,
-						    0,
+						    IP_VS_CONN_F_TEMPLATE,
 						    dest);
 			else
 				ct = ip_vs_conn_new(iph->protocol,
 						    snet, 0,
 						    iph->daddr, 0,
 						    dest->addr, 0,
-						    0,
+						    IP_VS_CONN_F_TEMPLATE,
 						    dest);
 			if (ct == NULL)
 				return NULL;
diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c
index 574d1f509b4..2e5ced3d806 100644
--- a/net/ipv4/ipvs/ip_vs_sync.c
+++ b/net/ipv4/ipvs/ip_vs_sync.c
@@ -297,16 +297,24 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
 
 	p = (char *)buffer + sizeof(struct ip_vs_sync_mesg);
 	for (i=0; i<m->nr_conns; i++) {
+		unsigned flags;
+
 		s = (struct ip_vs_sync_conn *)p;
-		cp = ip_vs_conn_in_get(s->protocol,
-				       s->caddr, s->cport,
-				       s->vaddr, s->vport);
+		flags = ntohs(s->flags);
+		if (!(flags & IP_VS_CONN_F_TEMPLATE))
+			cp = ip_vs_conn_in_get(s->protocol,
+					       s->caddr, s->cport,
+					       s->vaddr, s->vport);
+		else
+			cp = ip_vs_ct_in_get(s->protocol,
+					       s->caddr, s->cport,
+					       s->vaddr, s->vport);
 		if (!cp) {
 			cp = ip_vs_conn_new(s->protocol,
 					    s->caddr, s->cport,
 					    s->vaddr, s->vport,
 					    s->daddr, s->dport,
-					    ntohs(s->flags), NULL);
+					    flags, NULL);
 			if (!cp) {
 				IP_VS_ERR("ip_vs_conn_new failed\n");
 				return;
@@ -315,11 +323,11 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
 		} else if (!cp->dest) {
 			/* it is an entry created by the synchronization */
 			cp->state = ntohs(s->state);
-			cp->flags = ntohs(s->flags) | IP_VS_CONN_F_HASHED;
+			cp->flags = flags | IP_VS_CONN_F_HASHED;
 		}	/* Note that we don't touch its state and flags
 			   if it is a normal entry. */
 
-		if (ntohs(s->flags) & IP_VS_CONN_F_SEQ_MASK) {
+		if (flags & IP_VS_CONN_F_SEQ_MASK) {
 			opt = (struct ip_vs_sync_conn_options *)&s[1];
 			memcpy(&cp->in_seq, opt, sizeof(*opt));
 			p += FULL_CONN_SIZE;