22 files changed, 2231 insertions, 726 deletions

diff --git a/net/ipv4/ipvs/Kconfig b/net/ipv4/ipvs/Kconfig
index 2e48a7e2722..de6004de80b 100644
--- a/net/ipv4/ipvs/Kconfig
+++ b/net/ipv4/ipvs/Kconfig
@@ -24,6 +24,14 @@ menuconfig IP_VS
 
 if IP_VS
 
+config	IP_VS_IPV6
+	bool "IPv6 support for IPVS (DANGEROUS)"
+	depends on EXPERIMENTAL && (IPV6 = y || IP_VS = IPV6)
+	---help---
+	  Add IPv6 support to IPVS. This is incomplete and might be dangerous.
+
+	  Say N if unsure.
+
 config	IP_VS_DEBUG
 	bool "IP virtual server debugging"
 	---help---
@@ -33,7 +41,8 @@ config	IP_VS_DEBUG
 
 config	IP_VS_TAB_BITS
 	int "IPVS connection table size (the Nth power of 2)"
-	default "12" 
+	range 8 20
+	default 12
 	---help---
 	  The IPVS connection hash table uses the chaining scheme to handle
 	  hash collisions. Using a big IPVS connection hash table will greatly
diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c
index 44a6872dc24..9a24332fbed 100644
--- a/net/ipv4/ipvs/ip_vs_conn.c
+++ b/net/ipv4/ipvs/ip_vs_conn.c
@@ -114,9 +114,18 @@ static inline void ct_write_unlock_bh(unsigned key)
 /*
  *	Returns hash value for IPVS connection entry
  */
-static unsigned int ip_vs_conn_hashkey(unsigned proto, __be32 addr, __be16 port)
+static unsigned int ip_vs_conn_hashkey(int af, unsigned proto,
+				       const union nf_inet_addr *addr,
+				       __be16 port)
 {
-	return jhash_3words((__force u32)addr, (__force u32)port, proto, ip_vs_conn_rnd)
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6)
+		return jhash_3words(jhash(addr, 16, ip_vs_conn_rnd),
+				    (__force u32)port, proto, ip_vs_conn_rnd)
+			& IP_VS_CONN_TAB_MASK;
+#endif
+	return jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
+			    ip_vs_conn_rnd)
 		& IP_VS_CONN_TAB_MASK;
 }
 
@@ -131,7 +140,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
 	int ret;
 
 	/* Hash by protocol, client address and port */
-	hash = ip_vs_conn_hashkey(cp->protocol, cp->caddr, cp->cport);
+	hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport);
 
 	ct_write_lock(hash);
 
@@ -162,7 +171,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
 	int ret;
 
 	/* unhash it and decrease its reference counter */
-	hash = ip_vs_conn_hashkey(cp->protocol, cp->caddr, cp->cport);
+	hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport);
 
 	ct_write_lock(hash);
 
@@ -187,20 +196,23 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
  *	d_addr, d_port: pkt dest address (load balancer)
  */
 static inline struct ip_vs_conn *__ip_vs_conn_in_get
-(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port)
+(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
+ const union nf_inet_addr *d_addr, __be16 d_port)
 {
 	unsigned hash;
 	struct ip_vs_conn *cp;
 
-	hash = ip_vs_conn_hashkey(protocol, s_addr, s_port);
+	hash = ip_vs_conn_hashkey(af, 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 &&
+		if (cp->af == af &&
+		    ip_vs_addr_equal(af, s_addr, &cp->caddr) &&
+		    ip_vs_addr_equal(af, d_addr, &cp->vaddr) &&
+		    s_port == cp->cport && d_port == cp->vport &&
 		    ((!s_port) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
-		    protocol==cp->protocol) {
+		    protocol == cp->protocol) {
 			/* HIT */
 			atomic_inc(&cp->refcnt);
 			ct_read_unlock(hash);
@@ -214,39 +226,44 @@ static inline struct ip_vs_conn *__ip_vs_conn_in_get
 }
 
 struct ip_vs_conn *ip_vs_conn_in_get
-(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port)
+(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
+ const union nf_inet_addr *d_addr, __be16 d_port)
 {
 	struct ip_vs_conn *cp;
 
-	cp = __ip_vs_conn_in_get(protocol, s_addr, s_port, d_addr, d_port);
+	cp = __ip_vs_conn_in_get(af, protocol, s_addr, s_port, d_addr, d_port);
 	if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt))
-		cp = __ip_vs_conn_in_get(protocol, s_addr, 0, d_addr, d_port);
+		cp = __ip_vs_conn_in_get(af, protocol, s_addr, 0, d_addr,
+					 d_port);
 
-	IP_VS_DBG(9, "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");
+	IP_VS_DBG_BUF(9, "lookup/in %s %s:%d->%s:%d %s\n",
+		      ip_vs_proto_name(protocol),
+		      IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port),
+		      IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port),
+		      cp ? "hit" : "not hit");
 
 	return cp;
 }
 
 /* Get reference to connection template */
 struct ip_vs_conn *ip_vs_ct_in_get
-(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port)
+(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
+ const union nf_inet_addr *d_addr, __be16 d_port)
 {
 	unsigned hash;
 	struct ip_vs_conn *cp;
 
-	hash = ip_vs_conn_hashkey(protocol, s_addr, s_port);
+	hash = ip_vs_conn_hashkey(af, 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 &&
+		if (cp->af == af &&
+		    ip_vs_addr_equal(af, s_addr, &cp->caddr) &&
+		    ip_vs_addr_equal(af, d_addr, &cp->vaddr) &&
+		    s_port == cp->cport && d_port == cp->vport &&
 		    cp->flags & IP_VS_CONN_F_TEMPLATE &&
-		    protocol==cp->protocol) {
+		    protocol == cp->protocol) {
 			/* HIT */
 			atomic_inc(&cp->refcnt);
 			goto out;
@@ -257,11 +274,11 @@ struct ip_vs_conn *ip_vs_ct_in_get
   out:
 	ct_read_unlock(hash);
 
-	IP_VS_DBG(9, "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");
+	IP_VS_DBG_BUF(9, "template lookup/in %s %s:%d->%s:%d %s\n",
+		      ip_vs_proto_name(protocol),
+		      IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port),
+		      IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port),
+		      cp ? "hit" : "not hit");
 
 	return cp;
 }
@@ -273,7 +290,8 @@ struct ip_vs_conn *ip_vs_ct_in_get
  *	d_addr, d_port: pkt dest address (foreign host)
  */
 struct ip_vs_conn *ip_vs_conn_out_get
-(int protocol, __be32 s_addr, __be16 s_port, __be32 d_addr, __be16 d_port)
+(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
+ const union nf_inet_addr *d_addr, __be16 d_port)
 {
 	unsigned hash;
 	struct ip_vs_conn *cp, *ret=NULL;
@@ -281,13 +299,15 @@ struct ip_vs_conn *ip_vs_conn_out_get
 	/*
 	 *	Check for "full" addressed entries
 	 */
-	hash = ip_vs_conn_hashkey(protocol, d_addr, d_port);
+	hash = ip_vs_conn_hashkey(af, protocol, d_addr, d_port);
 
 	ct_read_lock(hash);
 
 	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
-		if (d_addr == cp->caddr && d_port == cp->cport &&
-		    s_port == cp->dport && s_addr == cp->daddr &&
+		if (cp->af == af &&
+		    ip_vs_addr_equal(af, d_addr, &cp->caddr) &&
+		    ip_vs_addr_equal(af, s_addr, &cp->daddr) &&
+		    d_port == cp->cport && s_port == cp->dport &&
 		    protocol == cp->protocol) {
 			/* HIT */
 			atomic_inc(&cp->refcnt);
@@ -298,11 +318,11 @@ struct ip_vs_conn *ip_vs_conn_out_get
 
 	ct_read_unlock(hash);
 
-	IP_VS_DBG(9, "lookup/out %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),
-		  ret?"hit":"not hit");
+	IP_VS_DBG_BUF(9, "lookup/out %s %s:%d->%s:%d %s\n",
+		      ip_vs_proto_name(protocol),
+		      IP_VS_DBG_ADDR(af, s_addr), ntohs(s_port),
+		      IP_VS_DBG_ADDR(af, d_addr), ntohs(d_port),
+		      ret ? "hit" : "not hit");
 
 	return ret;
 }
@@ -369,6 +389,33 @@ static inline void ip_vs_bind_xmit(struct ip_vs_conn *cp)
 	}
 }
 
+#ifdef CONFIG_IP_VS_IPV6
+static inline void ip_vs_bind_xmit_v6(struct ip_vs_conn *cp)
+{
+	switch (IP_VS_FWD_METHOD(cp)) {
+	case IP_VS_CONN_F_MASQ:
+		cp->packet_xmit = ip_vs_nat_xmit_v6;
+		break;
+
+	case IP_VS_CONN_F_TUNNEL:
+		cp->packet_xmit = ip_vs_tunnel_xmit_v6;
+		break;
+
+	case IP_VS_CONN_F_DROUTE:
+		cp->packet_xmit = ip_vs_dr_xmit_v6;
+		break;
+
+	case IP_VS_CONN_F_LOCALNODE:
+		cp->packet_xmit = ip_vs_null_xmit;
+		break;
+
+	case IP_VS_CONN_F_BYPASS:
+		cp->packet_xmit = ip_vs_bypass_xmit_v6;
+		break;
+	}
+}
+#endif
+
 
 static inline int ip_vs_dest_totalconns(struct ip_vs_dest *dest)
 {
@@ -402,16 +449,16 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
 		cp->flags |= atomic_read(&dest->conn_flags);
 	cp->dest = dest;
 
-	IP_VS_DBG(7, "Bind-dest %s c:%u.%u.%u.%u:%d v:%u.%u.%u.%u:%d "
-		  "d:%u.%u.%u.%u:%d fwd:%c s:%u conn->flags:%X conn->refcnt:%d "
-		  "dest->refcnt:%d\n",
-		  ip_vs_proto_name(cp->protocol),
-		  NIPQUAD(cp->caddr), ntohs(cp->cport),
-		  NIPQUAD(cp->vaddr), ntohs(cp->vport),
-		  NIPQUAD(cp->daddr), ntohs(cp->dport),
-		  ip_vs_fwd_tag(cp), cp->state,
-		  cp->flags, atomic_read(&cp->refcnt),
-		  atomic_read(&dest->refcnt));
+	IP_VS_DBG_BUF(7, "Bind-dest %s c:%s:%d v:%s:%d "
+		      "d:%s:%d fwd:%c s:%u conn->flags:%X conn->refcnt:%d "
+		      "dest->refcnt:%d\n",
+		      ip_vs_proto_name(cp->protocol),
+		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
+		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
+		      IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),
+		      ip_vs_fwd_tag(cp), cp->state,
+		      cp->flags, atomic_read(&cp->refcnt),
+		      atomic_read(&dest->refcnt));
 
 	/* Update the connection counters */
 	if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
@@ -444,8 +491,9 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
 	struct ip_vs_dest *dest;
 
 	if ((cp) && (!cp->dest)) {
-		dest = ip_vs_find_dest(cp->daddr, cp->dport,
-				       cp->vaddr, cp->vport, cp->protocol);
+		dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport,
+				       &cp->vaddr, cp->vport,
+				       cp->protocol);
 		ip_vs_bind_dest(cp, dest);
 		return dest;
 	} else
@@ -464,16 +512,16 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
 	if (!dest)
 		return;
 
-	IP_VS_DBG(7, "Unbind-dest %s c:%u.%u.%u.%u:%d v:%u.%u.%u.%u:%d "
-		  "d:%u.%u.%u.%u:%d fwd:%c s:%u conn->flags:%X conn->refcnt:%d "
-		  "dest->refcnt:%d\n",
-		  ip_vs_proto_name(cp->protocol),
-		  NIPQUAD(cp->caddr), ntohs(cp->cport),
-		  NIPQUAD(cp->vaddr), ntohs(cp->vport),
-		  NIPQUAD(cp->daddr), ntohs(cp->dport),
-		  ip_vs_fwd_tag(cp), cp->state,
-		  cp->flags, atomic_read(&cp->refcnt),
-		  atomic_read(&dest->refcnt));
+	IP_VS_DBG_BUF(7, "Unbind-dest %s c:%s:%d v:%s:%d "
+		      "d:%s:%d fwd:%c s:%u conn->flags:%X conn->refcnt:%d "
+		      "dest->refcnt:%d\n",
+		      ip_vs_proto_name(cp->protocol),
+		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
+		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
+		      IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport),
+		      ip_vs_fwd_tag(cp), cp->state,
+		      cp->flags, atomic_read(&cp->refcnt),
+		      atomic_read(&dest->refcnt));
 
 	/* Update the connection counters */
 	if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
@@ -526,13 +574,16 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
 	    !(dest->flags & IP_VS_DEST_F_AVAILABLE) ||
 	    (sysctl_ip_vs_expire_quiescent_template &&
 	     (atomic_read(&dest->weight) == 0))) {
-		IP_VS_DBG(9, "check_template: dest not available for "
-			  "protocol %s s:%u.%u.%u.%u:%d v:%u.%u.%u.%u:%d "
-			  "-> d:%u.%u.%u.%u:%d\n",
-			  ip_vs_proto_name(ct->protocol),
-			  NIPQUAD(ct->caddr), ntohs(ct->cport),
-			  NIPQUAD(ct->vaddr), ntohs(ct->vport),
-			  NIPQUAD(ct->daddr), ntohs(ct->dport));
+		IP_VS_DBG_BUF(9, "check_template: dest not available for "
+			      "protocol %s s:%s:%d v:%s:%d "
+			      "-> d:%s:%d\n",
+			      ip_vs_proto_name(ct->protocol),
+			      IP_VS_DBG_ADDR(ct->af, &ct->caddr),
+			      ntohs(ct->cport),
+			      IP_VS_DBG_ADDR(ct->af, &ct->vaddr),
+			      ntohs(ct->vport),
+			      IP_VS_DBG_ADDR(ct->af, &ct->daddr),
+			      ntohs(ct->dport));
 
 		/*
 		 * Invalidate the connection template
@@ -625,8 +676,9 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
  *	Create a new connection entry and hash it into the ip_vs_conn_tab
  */
 struct ip_vs_conn *
-ip_vs_conn_new(int proto, __be32 caddr, __be16 cport, __be32 vaddr, __be16 vport,
-	       __be32 daddr, __be16 dport, unsigned flags,
+ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport,
+	       const union nf_inet_addr *vaddr, __be16 vport,
+	       const union nf_inet_addr *daddr, __be16 dport, unsigned flags,
 	       struct ip_vs_dest *dest)
 {
 	struct ip_vs_conn *cp;
@@ -640,12 +692,13 @@ ip_vs_conn_new(int proto, __be32 caddr, __be16 cport, __be32 vaddr, __be16 vport
 
 	INIT_LIST_HEAD(&cp->c_list);
 	setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
+	cp->af		   = af;
 	cp->protocol	   = proto;
-	cp->caddr	   = caddr;
+	ip_vs_addr_copy(af, &cp->caddr, caddr);
 	cp->cport	   = cport;
-	cp->vaddr	   = vaddr;
+	ip_vs_addr_copy(af, &cp->vaddr, vaddr);
 	cp->vport	   = vport;
-	cp->daddr          = daddr;
+	ip_vs_addr_copy(af, &cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
 	spin_lock_init(&cp->lock);
@@ -672,7 +725,12 @@ ip_vs_conn_new(int proto, __be32 caddr, __be16 cport, __be32 vaddr, __be16 vport
 	cp->timeout = 3*HZ;
 
 	/* Bind its packet transmitter */
-	ip_vs_bind_xmit(cp);
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6)
+		ip_vs_bind_xmit_v6(cp);
+	else
+#endif
+		ip_vs_bind_xmit(cp);
 
 	if (unlikely(pp && atomic_read(&pp->appcnt)))
 		ip_vs_bind_app(cp, pp);
@@ -760,12 +818,26 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
 	else {
 		const struct ip_vs_conn *cp = v;
 
-		seq_printf(seq,
-			"%-3s %08X %04X %08X %04X %08X %04X %-11s %7lu\n",
+#ifdef CONFIG_IP_VS_IPV6
+		if (cp->af == AF_INET6)
+			seq_printf(seq,
+				"%-3s " NIP6_FMT " %04X " NIP6_FMT
+				" %04X " NIP6_FMT " %04X %-11s %7lu\n",
+				ip_vs_proto_name(cp->protocol),
+				NIP6(cp->caddr.in6), ntohs(cp->cport),
+				NIP6(cp->vaddr.in6), ntohs(cp->vport),
+				NIP6(cp->daddr.in6), ntohs(cp->dport),
+				ip_vs_state_name(cp->protocol, cp->state),
+				(cp->timer.expires-jiffies)/HZ);
+		else
+#endif
+			seq_printf(seq,
+				"%-3s %08X %04X %08X %04X"
+				" %08X %04X %-11s %7lu\n",
 				ip_vs_proto_name(cp->protocol),
-				ntohl(cp->caddr), ntohs(cp->cport),
-				ntohl(cp->vaddr), ntohs(cp->vport),
-				ntohl(cp->daddr), ntohs(cp->dport),
+				ntohl(cp->caddr.ip), ntohs(cp->cport),
+				ntohl(cp->vaddr.ip), ntohs(cp->vport),
+				ntohl(cp->daddr.ip), ntohs(cp->dport),
 				ip_vs_state_name(cp->protocol, cp->state),
 				(cp->timer.expires-jiffies)/HZ);
 	}
@@ -809,12 +881,27 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
 	else {
 		const struct ip_vs_conn *cp = v;
 
-		seq_printf(seq,
-			"%-3s %08X %04X %08X %04X %08X %04X %-11s %-6s %7lu\n",
+#ifdef CONFIG_IP_VS_IPV6
+		if (cp->af == AF_INET6)
+			seq_printf(seq,
+				"%-3s " NIP6_FMT " %04X " NIP6_FMT
+				" %04X " NIP6_FMT " %04X %-11s %-6s %7lu\n",
+				ip_vs_proto_name(cp->protocol),
+				NIP6(cp->caddr.in6), ntohs(cp->cport),
+				NIP6(cp->vaddr.in6), ntohs(cp->vport),
+				NIP6(cp->daddr.in6), ntohs(cp->dport),
+				ip_vs_state_name(cp->protocol, cp->state),
+				ip_vs_origin_name(cp->flags),
+				(cp->timer.expires-jiffies)/HZ);
+		else
+#endif
+			seq_printf(seq,
+				"%-3s %08X %04X %08X %04X "
+				"%08X %04X %-11s %-6s %7lu\n",
 				ip_vs_proto_name(cp->protocol),
-				ntohl(cp->caddr), ntohs(cp->cport),
-				ntohl(cp->vaddr), ntohs(cp->vport),
-				ntohl(cp->daddr), ntohs(cp->dport),
+				ntohl(cp->caddr.ip), ntohs(cp->cport),
+				ntohl(cp->vaddr.ip), ntohs(cp->vport),
+				ntohl(cp->daddr.ip), ntohs(cp->dport),
 				ip_vs_state_name(cp->protocol, cp->state),
 				ip_vs_origin_name(cp->flags),
 				(cp->timer.expires-jiffies)/HZ);
diff --git a/net/ipv4/ipvs/ip_vs_core.c b/net/ipv4/ipvs/ip_vs_core.c
index 9fbf0a6d739..80a4fcf33a5 100644
--- a/net/ipv4/ipvs/ip_vs_core.c
+++ b/net/ipv4/ipvs/ip_vs_core.c
@@ -39,6 +39,11 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
 
+#ifdef CONFIG_IP_VS_IPV6
+#include <net/ipv6.h>
+#include <linux/netfilter_ipv6.h>
+#endif
+
 #include <net/ip_vs.h>
 
 
@@ -60,6 +65,7 @@ EXPORT_SYMBOL(ip_vs_get_debug_level);
 
 /* ID used in ICMP lookups */
 #define icmp_id(icmph)          (((icmph)->un).echo.id)
+#define icmpv6_id(icmph)        (icmph->icmp6_dataun.u_echo.identifier)
 
 const char *ip_vs_proto_name(unsigned proto)
 {
@@ -74,6 +80,10 @@ const char *ip_vs_proto_name(unsigned proto)
 		return "TCP";
 	case IPPROTO_ICMP:
 		return "ICMP";
+#ifdef CONFIG_IP_VS_IPV6
+	case IPPROTO_ICMPV6:
+		return "ICMPv6";
+#endif
 	default:
 		sprintf(buf, "IP_%d", proto);
 		return buf;
@@ -92,18 +102,18 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 	struct ip_vs_dest *dest = cp->dest;
 	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
 		spin_lock(&dest->stats.lock);
-		dest->stats.inpkts++;
-		dest->stats.inbytes += skb->len;
+		dest->stats.ustats.inpkts++;
+		dest->stats.ustats.inbytes += skb->len;
 		spin_unlock(&dest->stats.lock);
 
 		spin_lock(&dest->svc->stats.lock);
-		dest->svc->stats.inpkts++;
-		dest->svc->stats.inbytes += skb->len;
+		dest->svc->stats.ustats.inpkts++;
+		dest->svc->stats.ustats.inbytes += skb->len;
 		spin_unlock(&dest->svc->stats.lock);
 
 		spin_lock(&ip_vs_stats.lock);
-		ip_vs_stats.inpkts++;
-		ip_vs_stats.inbytes += skb->len;
+		ip_vs_stats.ustats.inpkts++;
+		ip_vs_stats.ustats.inbytes += skb->len;
 		spin_unlock(&ip_vs_stats.lock);
 	}
 }
@@ -115,18 +125,18 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 	struct ip_vs_dest *dest = cp->dest;
 	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
 		spin_lock(&dest->stats.lock);
-		dest->stats.outpkts++;
-		dest->stats.outbytes += skb->len;
+		dest->stats.ustats.outpkts++;
+		dest->stats.ustats.outbytes += skb->len;
 		spin_unlock(&dest->stats.lock);
 
 		spin_lock(&dest->svc->stats.lock);
-		dest->svc->stats.outpkts++;
-		dest->svc->stats.outbytes += skb->len;
+		dest->svc->stats.ustats.outpkts++;
+		dest->svc->stats.ustats.outbytes += skb->len;
 		spin_unlock(&dest->svc->stats.lock);
 
 		spin_lock(&ip_vs_stats.lock);
-		ip_vs_stats.outpkts++;
-		ip_vs_stats.outbytes += skb->len;
+		ip_vs_stats.ustats.outpkts++;
+		ip_vs_stats.ustats.outbytes += skb->len;
 		spin_unlock(&ip_vs_stats.lock);
 	}
 }
@@ -136,15 +146,15 @@ static inline void
 ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
 {
 	spin_lock(&cp->dest->stats.lock);
-	cp->dest->stats.conns++;
+	cp->dest->stats.ustats.conns++;
 	spin_unlock(&cp->dest->stats.lock);
 
 	spin_lock(&svc->stats.lock);
-	svc->stats.conns++;
+	svc->stats.ustats.conns++;
 	spin_unlock(&svc->stats.lock);
 
 	spin_lock(&ip_vs_stats.lock);
-	ip_vs_stats.conns++;
+	ip_vs_stats.ustats.conns++;
 	spin_unlock(&ip_vs_stats.lock);
 }
 
@@ -173,20 +183,28 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		    __be16 ports[2])
 {
 	struct ip_vs_conn *cp = NULL;
-	struct iphdr *iph = ip_hdr(skb);
+	struct ip_vs_iphdr iph;
 	struct ip_vs_dest *dest;
 	struct ip_vs_conn *ct;
-	__be16  dport;	 /* destination port to forward */
-	__be32  snet;	 /* source network of the client, after masking */
+	__be16  dport;			/* destination port to forward */
+	union nf_inet_addr snet;	/* source network of the client,
+					   after masking */
+
+	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
 
 	/* Mask saddr with the netmask to adjust template granularity */
-	snet = iph->saddr & svc->netmask;
+#ifdef CONFIG_IP_VS_IPV6
+	if (svc->af == AF_INET6)
+		ipv6_addr_prefix(&snet.in6, &iph.saddr.in6, svc->netmask);
+	else
+#endif
+		snet.ip = iph.saddr.ip & svc->netmask;
 
-	IP_VS_DBG(6, "p-schedule: src %u.%u.%u.%u:%u dest %u.%u.%u.%u:%u "
-		  "mnet %u.%u.%u.%u\n",
-		  NIPQUAD(iph->saddr), ntohs(ports[0]),
-		  NIPQUAD(iph->daddr), ntohs(ports[1]),
-		  NIPQUAD(snet));
+	IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u "
+		      "mnet %s\n",
+		      IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(ports[0]),
+		      IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(ports[1]),
+		      IP_VS_DBG_ADDR(svc->af, &snet));
 
 	/*
 	 * As far as we know, FTP is a very complicated network protocol, and
@@ -204,11 +222,11 @@ 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_ct_in_get(iph->protocol, snet, 0,
-					       iph->daddr, ports[1]);
+			ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0,
+					     &iph.daddr, ports[1]);
 		else
-			ct = ip_vs_ct_in_get(iph->protocol, snet, 0,
-					       iph->daddr, 0);
+			ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0,
+					     &iph.daddr, 0);
 
 		if (!ct || !ip_vs_check_template(ct)) {
 			/*
@@ -228,18 +246,18 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 			 * for ftp service.
 			 */
 			if (svc->port != FTPPORT)
-				ct = ip_vs_conn_new(iph->protocol,
-						    snet, 0,
-						    iph->daddr,
+				ct = ip_vs_conn_new(svc->af, iph.protocol,
+						    &snet, 0,
+						    &iph.daddr,
 						    ports[1],
-						    dest->addr, dest->port,
+						    &dest->addr, dest->port,
 						    IP_VS_CONN_F_TEMPLATE,
 						    dest);
 			else
-				ct = ip_vs_conn_new(iph->protocol,
-						    snet, 0,
-						    iph->daddr, 0,
-						    dest->addr, 0,
+				ct = ip_vs_conn_new(svc->af, iph.protocol,
+						    &snet, 0,
+						    &iph.daddr, 0,
+						    &dest->addr, 0,
 						    IP_VS_CONN_F_TEMPLATE,
 						    dest);
 			if (ct == NULL)
@@ -258,12 +276,16 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		 * fwmark template: <IPPROTO_IP,caddr,0,fwmark,0,daddr,0>
 		 * port zero template: <protocol,caddr,0,vaddr,0,daddr,0>
 		 */
-		if (svc->fwmark)
-			ct = ip_vs_ct_in_get(IPPROTO_IP, snet, 0,
-					       htonl(svc->fwmark), 0);
-		else
-			ct = ip_vs_ct_in_get(iph->protocol, snet, 0,
-					       iph->daddr, 0);
+		if (svc->fwmark) {
+			union nf_inet_addr fwmark = {
+				.all = { 0, 0, 0, htonl(svc->fwmark) }
+			};
+
+			ct = ip_vs_ct_in_get(svc->af, IPPROTO_IP, &snet, 0,
+					     &fwmark, 0);
+		} else
+			ct = ip_vs_ct_in_get(svc->af, iph.protocol, &snet, 0,
+					     &iph.daddr, 0);
 
 		if (!ct || !ip_vs_check_template(ct)) {
 			/*
@@ -282,18 +304,22 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 			/*
 			 * Create a template according to the service
 			 */
-			if (svc->fwmark)
-				ct = ip_vs_conn_new(IPPROTO_IP,
-						    snet, 0,
-						    htonl(svc->fwmark), 0,
-						    dest->addr, 0,
+			if (svc->fwmark) {
+				union nf_inet_addr fwmark = {
+					.all = { 0, 0, 0, htonl(svc->fwmark) }
+				};
+
+				ct = ip_vs_conn_new(svc->af, IPPROTO_IP,
+						    &snet, 0,
+						    &fwmark, 0,
+						    &dest->addr, 0,
 						    IP_VS_CONN_F_TEMPLATE,
 						    dest);
-			else
-				ct = ip_vs_conn_new(iph->protocol,
-						    snet, 0,
-						    iph->daddr, 0,
-						    dest->addr, 0,
+			} else
+				ct = ip_vs_conn_new(svc->af, iph.protocol,
+						    &snet, 0,
+						    &iph.daddr, 0,
+						    &dest->addr, 0,
 						    IP_VS_CONN_F_TEMPLATE,
 						    dest);
 			if (ct == NULL)
@@ -310,10 +336,10 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 	/*
 	 *    Create a new connection according to the template
 	 */
-	cp = ip_vs_conn_new(iph->protocol,
-			    iph->saddr, ports[0],
-			    iph->daddr, ports[1],
-			    dest->addr, dport,
+	cp = ip_vs_conn_new(svc->af, iph.protocol,
+			    &iph.saddr, ports[0],
+			    &iph.daddr, ports[1],
+			    &dest->addr, dport,
 			    0,
 			    dest);
 	if (cp == NULL) {
@@ -342,12 +368,12 @@ struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 {
 	struct ip_vs_conn *cp = NULL;
-	struct iphdr *iph = ip_hdr(skb);
+	struct ip_vs_iphdr iph;
 	struct ip_vs_dest *dest;
 	__be16 _ports[2], *pptr;
 
-	pptr = skb_header_pointer(skb, iph->ihl*4,
-				  sizeof(_ports), _ports);
+	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
+	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
 	if (pptr == NULL)
 		return NULL;
 
@@ -377,22 +403,22 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	/*
 	 *    Create a connection entry.
 	 */
-	cp = ip_vs_conn_new(iph->protocol,
-			    iph->saddr, pptr[0],
-			    iph->daddr, pptr[1],
-			    dest->addr, dest->port?dest->port:pptr[1],
+	cp = ip_vs_conn_new(svc->af, iph.protocol,
+			    &iph.saddr, pptr[0],
+			    &iph.daddr, pptr[1],
+			    &dest->addr, dest->port ? dest->port : pptr[1],
 			    0,
 			    dest);
 	if (cp == NULL)
 		return NULL;
 
-	IP_VS_DBG(6, "Schedule fwd:%c c:%u.%u.%u.%u:%u v:%u.%u.%u.%u:%u "
-		  "d:%u.%u.%u.%u:%u conn->flags:%X conn->refcnt:%d\n",
-		  ip_vs_fwd_tag(cp),
-		  NIPQUAD(cp->caddr), ntohs(cp->cport),
-		  NIPQUAD(cp->vaddr), ntohs(cp->vport),
-		  NIPQUAD(cp->daddr), ntohs(cp->dport),
-		  cp->flags, atomic_read(&cp->refcnt));
+	IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u "
+		      "d:%s:%u conn->flags:%X conn->refcnt:%d\n",
+		      ip_vs_fwd_tag(cp),
+		      IP_VS_DBG_ADDR(svc->af, &cp->caddr), ntohs(cp->cport),
+		      IP_VS_DBG_ADDR(svc->af, &cp->vaddr), ntohs(cp->vport),
+		      IP_VS_DBG_ADDR(svc->af, &cp->daddr), ntohs(cp->dport),
+		      cp->flags, atomic_read(&cp->refcnt));
 
 	ip_vs_conn_stats(cp, svc);
 	return cp;
@@ -408,20 +434,27 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 		struct ip_vs_protocol *pp)
 {
 	__be16 _ports[2], *pptr;
-	struct iphdr *iph = ip_hdr(skb);
+	struct ip_vs_iphdr iph;
+	int unicast;
+	ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
 
-	pptr = skb_header_pointer(skb, iph->ihl*4,
-				  sizeof(_ports), _ports);
+	pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
 	if (pptr == NULL) {
 		ip_vs_service_put(svc);
 		return NF_DROP;
 	}
 
+#ifdef CONFIG_IP_VS_IPV6
+	if (svc->af == AF_INET6)
+		unicast = ipv6_addr_type(&iph.daddr.in6) & IPV6_ADDR_UNICAST;
+	else
+#endif
+		unicast = (inet_addr_type(&init_net, iph.daddr.ip) == RTN_UNICAST);
+
 	/* if it is fwmark-based service, the cache_bypass sysctl is up
-	   and the destination is RTN_UNICAST (and not local), then create
+	   and the destination is a non-local unicast, then create
 	   a cache_bypass connection entry */
-	if (sysctl_ip_vs_cache_bypass && svc->fwmark
-	    && (inet_addr_type(&init_net, iph->daddr) == RTN_UNICAST)) {
+	if (sysctl_ip_vs_cache_bypass && svc->fwmark && unicast) {
 		int ret, cs;
 		struct ip_vs_conn *cp;
 
@@ -429,9 +462,9 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 
 		/* create a new connection entry */
 		IP_VS_DBG(6, "ip_vs_leave: create a cache_bypass entry\n");
-		cp = ip_vs_conn_new(iph->protocol,
-				    iph->saddr, pptr[0],
-				    iph->daddr, pptr[1],
+		cp = ip_vs_conn_new(svc->af, iph.protocol,
+				    &iph.saddr, pptr[0],
+				    &iph.daddr, pptr[1],
 				    0, 0,
 				    IP_VS_CONN_F_BYPASS,
 				    NULL);
@@ -473,7 +506,14 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
 	 * created, the TCP RST packet cannot be sent, instead that
 	 * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ
 	 */
-	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+#ifdef CONFIG_IP_VS_IPV6
+	if (svc->af == AF_INET6)
+		icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0,
+			    skb->dev);
+	else
+#endif
+		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
 	return NF_DROP;
 }
 
@@ -512,6 +552,14 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
 	return err;
 }
 
+#ifdef CONFIG_IP_VS_IPV6
+static inline int ip_vs_gather_frags_v6(struct sk_buff *skb, u_int32_t user)
+{
+	/* TODO IPv6: Find out what to do here for IPv6 */
+	return 0;
+}
+#endif
+
 /*
  * Packet has been made sufficiently writable in caller
  * - inout: 1=in->out, 0=out->in
@@ -526,14 +574,14 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
 	struct iphdr *ciph	 = (struct iphdr *)(icmph + 1);
 
 	if (inout) {
-		iph->saddr = cp->vaddr;
+		iph->saddr = cp->vaddr.ip;
 		ip_send_check(iph);
-		ciph->daddr = cp->vaddr;
+		ciph->daddr = cp->vaddr.ip;
 		ip_send_check(ciph);
 	} else {
-		iph->daddr = cp->daddr;
+		iph->daddr = cp->daddr.ip;
 		ip_send_check(iph);
-		ciph->saddr = cp->daddr;
+		ciph->saddr = cp->daddr.ip;
 		ip_send_check(ciph);
 	}
 
@@ -560,21 +608,112 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
 			"Forwarding altered incoming ICMP");
 }
 
+#ifdef CONFIG_IP_VS_IPV6
+void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		    struct ip_vs_conn *cp, int inout)
+{
+	struct ipv6hdr *iph	 = ipv6_hdr(skb);
+	unsigned int icmp_offset = sizeof(struct ipv6hdr);
+	struct icmp6hdr *icmph	 = (struct icmp6hdr *)(skb_network_header(skb) +
+						      icmp_offset);
+	struct ipv6hdr *ciph	 = (struct ipv6hdr *)(icmph + 1);
+
+	if (inout) {
+		iph->saddr = cp->vaddr.in6;
+		ciph->daddr = cp->vaddr.in6;
+	} else {
+		iph->daddr = cp->daddr.in6;
+		ciph->saddr = cp->daddr.in6;
+	}
+
+	/* the TCP/UDP port */
+	if (IPPROTO_TCP == ciph->nexthdr || IPPROTO_UDP == ciph->nexthdr) {
+		__be16 *ports = (void *)ciph + sizeof(struct ipv6hdr);