Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

15 files changed, 971 insertions, 238 deletions

diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index b32fb0dbe237..05dc1b77e466 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -225,6 +225,25 @@ config	IP_VS_SH
 	  If you want to compile it in kernel, say Y. To compile it as a
 	  module, choose M here. If unsure, say N.
 
+config	IP_VS_MH
+	tristate "maglev hashing scheduling"
+	---help---
+	  The maglev consistent hashing scheduling algorithm provides the
+	  Google's Maglev hashing algorithm as a IPVS scheduler. It assigns
+	  network connections to the servers through looking up a statically
+	  assigned special hash table called the lookup table. Maglev hashing
+	  is to assign a preference list of all the lookup table positions
+	  to each destination.
+
+	  Through this operation, The maglev hashing gives an almost equal
+	  share of the lookup table to each of the destinations and provides
+	  minimal disruption by using the lookup table. When the set of
+	  destinations changes, a connection will likely be sent to the same
+	  destination as it was before.
+
+	  If you want to compile it in kernel, say Y. To compile it as a
+	  module, choose M here. If unsure, say N.
+
 config	IP_VS_SED
 	tristate "shortest expected delay scheduling"
 	---help---
@@ -266,6 +285,24 @@ config IP_VS_SH_TAB_BITS
 	  needs to be large enough to effectively fit all the destinations
 	  multiplied by their respective weights.
 
+comment 'IPVS MH scheduler'
+
+config IP_VS_MH_TAB_INDEX
+	int "IPVS maglev hashing table index of size (the prime numbers)"
+	range 8 17
+	default 12
+	---help---
+	  The maglev hashing scheduler maps source IPs to destinations
+	  stored in a hash table. This table is assigned by a preference
+	  list of the positions to each destination until all slots in
+	  the table are filled. The index determines the prime for size of
+	  the table as 251, 509, 1021, 2039, 4093, 8191, 16381, 32749,
+	  65521 or 131071. When using weights to allow destinations to
+	  receive more connections, the table is assigned an amount
+	  proportional to the weights specified. The table needs to be large
+	  enough to effectively fit all the destinations multiplied by their
+	  respective weights.
+
 comment 'IPVS application helper'
 
 config	IP_VS_FTP
diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile
index c552993fa4b9..bfce2677fda2 100644
--- a/net/netfilter/ipvs/Makefile
+++ b/net/netfilter/ipvs/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_IP_VS_LBLC) += ip_vs_lblc.o
 obj-$(CONFIG_IP_VS_LBLCR) += ip_vs_lblcr.o
 obj-$(CONFIG_IP_VS_DH) += ip_vs_dh.o
 obj-$(CONFIG_IP_VS_SH) += ip_vs_sh.o
+obj-$(CONFIG_IP_VS_MH) += ip_vs_mh.o
 obj-$(CONFIG_IP_VS_SED) += ip_vs_sed.o
 obj-$(CONFIG_IP_VS_NQ) += ip_vs_nq.o
 
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index c3db074fc1f7..7588aeaa605f 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -355,7 +355,8 @@ static inline void vs_seq_update(struct ip_vs_conn *cp, struct ip_vs_seq *vseq,
 }
 
 static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb,
-				  struct ip_vs_app *app)
+				  struct ip_vs_app *app,
+				  struct ip_vs_iphdr *ipvsh)
 {
 	int diff;
 	const unsigned int tcp_offset = ip_hdrlen(skb);
@@ -386,7 +387,7 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb,
 	if (app->pkt_out == NULL)
 		return 1;
 
-	if (!app->pkt_out(app, cp, skb, &diff))
+	if (!app->pkt_out(app, cp, skb, &diff, ipvsh))
 		return 0;
 
 	/*
@@ -404,7 +405,8 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb,
  *	called by ipvs packet handler, assumes previously checked cp!=NULL
  *	returns false if it can't handle packet (oom)
  */
-int ip_vs_app_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb)
+int ip_vs_app_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb,
+		      struct ip_vs_iphdr *ipvsh)
 {
 	struct ip_vs_app *app;
 
@@ -417,7 +419,7 @@ int ip_vs_app_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb)
 
 	/* TCP is complicated */
 	if (cp->protocol == IPPROTO_TCP)
-		return app_tcp_pkt_out(cp, skb, app);
+		return app_tcp_pkt_out(cp, skb, app, ipvsh);
 
 	/*
 	 *	Call private output hook function
@@ -425,12 +427,13 @@ int ip_vs_app_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb)
 	if (app->pkt_out == NULL)
 		return 1;
 
-	return app->pkt_out(app, cp, skb, NULL);
+	return app->pkt_out(app, cp, skb, NULL, ipvsh);
 }
 
 
 static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb,
-				 struct ip_vs_app *app)
+				 struct ip_vs_app *app,
+				 struct ip_vs_iphdr *ipvsh)
 {
 	int diff;
 	const unsigned int tcp_offset = ip_hdrlen(skb);
@@ -461,7 +464,7 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb,
 	if (app->pkt_in == NULL)
 		return 1;
 
-	if (!app->pkt_in(app, cp, skb, &diff))
+	if (!app->pkt_in(app, cp, skb, &diff, ipvsh))
 		return 0;
 
 	/*
@@ -479,7 +482,8 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb,
  *	called by ipvs packet handler, assumes previously checked cp!=NULL.
  *	returns false if can't handle packet (oom).
  */
-int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb)
+int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb,
+		     struct ip_vs_iphdr *ipvsh)
 {
 	struct ip_vs_app *app;
 
@@ -492,7 +496,7 @@ int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb)
 
 	/* TCP is complicated */
 	if (cp->protocol == IPPROTO_TCP)
-		return app_tcp_pkt_in(cp, skb, app);
+		return app_tcp_pkt_in(cp, skb, app, ipvsh);
 
 	/*
 	 *	Call private input hook function
@@ -500,7 +504,7 @@ int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb)
 	if (app->pkt_in == NULL)
 		return 1;
 
-	return app->pkt_in(app, cp, skb, NULL);
+	return app->pkt_in(app, cp, skb, NULL, ipvsh);
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 141b1509c948..0c03c0e16a96 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -821,6 +821,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	if (add && udest->af != svc->af)
 		ipvs->mixed_address_family_dests++;
 
+	/* keep the last_weight with latest non-0 weight */
+	if (add || udest->weight != 0)
+		atomic_set(&dest->last_weight, udest->weight);
+
 	/* set the weight and the flags */
 	atomic_set(&dest->weight, udest->weight);
 	conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index 75f798f8e83b..07459e71d907 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -43,6 +43,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
+#include <linux/hash.h>
 
 #include <net/ip_vs.h>
 
@@ -81,7 +82,7 @@ static inline unsigned int ip_vs_dh_hashkey(int af, const union nf_inet_addr *ad
 		addr_fold = addr->ip6[0]^addr->ip6[1]^
 			    addr->ip6[2]^addr->ip6[3];
 #endif
-	return (ntohl(addr_fold)*2654435761UL) & IP_VS_DH_TAB_MASK;
+	return hash_32(ntohl(addr_fold), IP_VS_DH_TAB_BITS);
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 58d5d05aec24..4398a72edec5 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -29,6 +29,8 @@
 #include <linux/moduleparam.h>
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
+#include <linux/ctype.h>
+#include <linux/inet.h>
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/netfilter.h>
@@ -44,9 +46,18 @@
 #include <net/ip_vs.h>
 
 
-#define SERVER_STRING "227 "
-#define CLIENT_STRING "PORT"
+#define SERVER_STRING_PASV "227 "
+#define CLIENT_STRING_PORT "PORT"
+#define SERVER_STRING_EPSV "229 "
+#define CLIENT_STRING_EPRT "EPRT"
 
+enum {
+	IP_VS_FTP_ACTIVE = 0,
+	IP_VS_FTP_PORT = 0,
+	IP_VS_FTP_PASV,
+	IP_VS_FTP_EPRT,
+	IP_VS_FTP_EPSV,
+};
 
 /*
  * List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper
@@ -58,9 +69,15 @@ module_param_array(ports, ushort, &ports_count, 0444);
 MODULE_PARM_DESC(ports, "Ports to monitor for FTP control commands");
 
 
-/*	Dummy variable */
-static int ip_vs_ftp_pasv;
+static char *ip_vs_ftp_data_ptr(struct sk_buff *skb, struct ip_vs_iphdr *ipvsh)
+{
+	struct tcphdr *th = (struct tcphdr *)((char *)skb->data + ipvsh->len);
+
+	if ((th->doff << 2) < sizeof(struct tcphdr))
+		return NULL;
 
+	return (char *)th + (th->doff << 2);
+}
 
 static int
 ip_vs_ftp_init_conn(struct ip_vs_app *app, struct ip_vs_conn *cp)
@@ -78,20 +95,20 @@ ip_vs_ftp_done_conn(struct ip_vs_app *app, struct ip_vs_conn *cp)
 }
 
 
-/*
- * Get <addr,port> from the string "xxx.xxx.xxx.xxx,ppp,ppp", started
- * with the "pattern", ignoring before "skip" and terminated with
- * the "term" character.
- * <addr,port> is in network order.
+/* Get <addr,port> from the string "xxx.xxx.xxx.xxx,ppp,ppp", started
+ * with the "pattern". <addr,port> is in network order.
+ * Parse extended format depending on ext. In this case addr can be pre-set.
  */
 static int ip_vs_ftp_get_addrport(char *data, char *data_limit,
 				  const char *pattern, size_t plen,
-				  char skip, char term,
-				  __be32 *addr, __be16 *port,
-				  char **start, char **end)
+				  char skip, bool ext, int mode,
+				  union nf_inet_addr *addr, __be16 *port,
+				  __u16 af, char **start, char **end)
 {
 	char *s, c;
 	unsigned char p[6];
+	char edelim;
+	__u16 hport;
 	int i = 0;
 
 	if (data_limit - data < plen) {
@@ -113,6 +130,11 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit,
 			if (s == data_limit)
 				return -1;
 			if (!found) {
+				/* "(" is optional for non-extended format,
+				 * so catch the start of IPv4 address
+				 */
+				if (!ext && isdigit(*s))
+					break;
 				if (*s == skip)
 					found = 1;
 			} else if (*s != skip) {
@@ -120,41 +142,102 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit,
 			}
 		}
 	}
+	/* Old IPv4-only format? */
+	if (!ext) {
+		p[0] = 0;
+		for (data = s; ; data++) {
+			if (data == data_limit)
+				return -1;
+			c = *data;
+			if (isdigit(c)) {
+				p[i] = p[i]*10 + c - '0';
+			} else if (c == ',' && i < 5) {
+				i++;
+				p[i] = 0;
+			} else {
+				/* unexpected character or terminator */
+				break;
+			}
+		}
 
-	for (data = s; ; data++) {
-		if (data == data_limit)
+		if (i != 5)
 			return -1;
-		if (*data == term)
-			break;
+
+		*start = s;
+		*end = data;
+		addr->ip = get_unaligned((__be32 *) p);
+		*port = get_unaligned((__be16 *) (p + 4));
+		return 1;
 	}
-	*end = data;
+	if (s == data_limit)
+		return -1;
+	*start = s;
+	edelim = *s++;
+	if (edelim < 33 || edelim > 126)
+		return -1;
+	if (s == data_limit)
+		return -1;
+	if (*s == edelim) {
+		/* Address family is usually missing for EPSV response */
+		if (mode != IP_VS_FTP_EPSV)
+			return -1;
+		s++;
+		if (s == data_limit)
+			return -1;
+		/* Then address should be missing too */
+		if (*s != edelim)
+			return -1;
+		/* Caller can pre-set addr, if needed */
+		s++;
+	} else {
+		const char *ep;
 
-	memset(p, 0, sizeof(p));
-	for (data = s; ; data++) {
-		c = *data;
-		if (c == term)
-			break;
-		if (c >= '0' && c <= '9') {
-			p[i] = p[i]*10 + c - '0';
-		} else if (c == ',' && i < 5) {
-			i++;
-		} else {
-			/* unexpected character */
+		/* We allow address only from same family */
+		if (af == AF_INET6 && *s != '2')
 			return -1;
+		if (af == AF_INET && *s != '1')
+			return -1;
+		s++;
+		if (s == data_limit)
+			return -1;
+		if (*s != edelim)
+			return -1;
+		s++;
+		if (s == data_limit)
+			return -1;
+		if (af == AF_INET6) {
+			if (in6_pton(s, data_limit - s, (u8 *)addr, edelim,
+				     &ep) <= 0)
+				return -1;
+		} else {
+			if (in4_pton(s, data_limit - s, (u8 *)addr, edelim,
+				     &ep) <= 0)
+				return -1;
 		}
+		s = (char *) ep;
+		if (s == data_limit)
+			return -1;
+		if (*s != edelim)
+			return -1;
+		s++;
 	}
-
-	if (i != 5)
+	for (hport = 0; ; s++)
+	{
+		if (s == data_limit)
+			return -1;
+		if (!isdigit(*s))
+			break;
+		hport = hport * 10 + *s - '0';
+	}
+	if (s == data_limit || !hport || *s != edelim)
 		return -1;
-
-	*start = s;
-	*addr = get_unaligned((__be32 *) p);
-	*port = get_unaligned((__be16 *) (p + 4));
+	s++;
+	*end = s;
+	*port = htons(hport);
 	return 1;
 }
 
-/*
- * Look at outgoing ftp packets to catch the response to a PASV command
+/* Look at outgoing ftp packets to catch the response to a PASV/EPSV command
  * from the server (inside-to-outside).
  * When we see one, we build a connection entry with the client address,
  * client port 0 (unknown at the moment), the server address and the
@@ -165,12 +248,13 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit,
  * The outgoing packet should be something like
  *   "227 Entering Passive Mode (xxx,xxx,xxx,xxx,ppp,ppp)".
  * xxx,xxx,xxx,xxx is the server address, ppp,ppp is the server port number.
+ * The extended format for EPSV response provides usually only port:
+ *   "229 Entering Extended Passive Mode (|||ppp|)"
  */
 static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
-			 struct sk_buff *skb, int *diff)
+			 struct sk_buff *skb, int *diff,
+			 struct ip_vs_iphdr *ipvsh)
 {
-	struct iphdr *iph;
-	struct tcphdr *th;
 	char *data, *data_limit;
 	char *start, *end;
 	union nf_inet_addr from;
@@ -184,14 +268,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 
 	*diff = 0;
 
-#ifdef CONFIG_IP_VS_IPV6
-	/* This application helper doesn't work with IPv6 yet,
-	 * so turn this into a no-op for IPv6 packets
-	 */
-	if (cp->af == AF_INET6)
-		return 1;
-#endif
-
 	/* Only useful for established sessions */
 	if (cp->state != IP_VS_TCP_S_ESTABLISHED)
 		return 1;
@@ -200,53 +276,77 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	if (!skb_make_writable(skb, skb->len))
 		return 0;
 
-	if (cp->app_data == &ip_vs_ftp_pasv) {
-		iph = ip_hdr(skb);
-		th = (struct tcphdr *)&(((char *)iph)[iph->ihl*4]);
-		data = (char *)th + (th->doff << 2);
+	if (cp->app_data == (void *) IP_VS_FTP_PASV) {
+		data = ip_vs_ftp_data_ptr(skb, ipvsh);
 		data_limit = skb_tail_pointer(skb);
 
+		if (!data || data >= data_limit)
+			return 1;
+
 		if (ip_vs_ftp_get_addrport(data, data_limit,
-					   SERVER_STRING,
-					   sizeof(SERVER_STRING)-1,
-					   '(', ')',
-					   &from.ip, &port,
+					   SERVER_STRING_PASV,
+					   sizeof(SERVER_STRING_PASV)-1,
+					   '(', false, IP_VS_FTP_PASV,
+					   &from, &port, cp->af,
 					   &start, &end) != 1)
 			return 1;
 
-		IP_VS_DBG(7, "PASV response (%pI4:%d) -> %pI4:%d detected\n",
+		IP_VS_DBG(7, "PASV response (%pI4:%u) -> %pI4:%u detected\n",
 			  &from.ip, ntohs(port), &cp->caddr.ip, 0);
+	} else if (cp->app_data == (void *) IP_VS_FTP_EPSV) {
+		data = ip_vs_ftp_data_ptr(skb, ipvsh);
+		data_limit = skb_tail_pointer(skb);
 
-		/*
-		 * Now update or create an connection entry for it
+		if (!data || data >= data_limit)
+			return 1;
+
+		/* Usually, data address is not specified but
+		 * we support different address, so pre-set it.
 		 */
-		{
-			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(cp->ipvs, AF_INET,
-					      iph->protocol, &from, port,
-					      &cp->caddr, 0, &p);
-			n_cp = ip_vs_conn_out_get(&p);
-		}
-		if (!n_cp) {
-			struct ip_vs_conn_param p;
-			ip_vs_conn_fill_param(cp->ipvs,
-					      AF_INET, IPPROTO_TCP, &cp->caddr,
-					      0, &cp->vaddr, port, &p);
-			/* As above, this is ipv4 only */
-			n_cp = ip_vs_conn_new(&p, AF_INET, &from, port,
-					      IP_VS_CONN_F_NO_CPORT |
-					      IP_VS_CONN_F_NFCT,
-					      cp->dest, skb->mark);
-			if (!n_cp)
-				return 0;
+		from = cp->daddr;
+		if (ip_vs_ftp_get_addrport(data, data_limit,
+					   SERVER_STRING_EPSV,
+					   sizeof(SERVER_STRING_EPSV)-1,
+					   '(', true, IP_VS_FTP_EPSV,
+					   &from, &port, cp->af,
+					   &start, &end) != 1)
+			return 1;
 
-			/* add its controller */
-			ip_vs_control_add(n_cp, cp);
-		}
+		IP_VS_DBG_BUF(7, "EPSV response (%s:%u) -> %s:%u detected\n",
+			      IP_VS_DBG_ADDR(cp->af, &from), ntohs(port),
+			      IP_VS_DBG_ADDR(cp->af, &cp->caddr), 0);
+	} else {
+		return 1;
+	}
 
-		/*
-		 * Replace the old passive address with the new one
-		 */
+	/* Now update or create a connection entry for it */
+	{
+		struct ip_vs_conn_param p;
+
+		ip_vs_conn_fill_param(cp->ipvs, cp->af,
+				      ipvsh->protocol, &from, port,
+				      &cp->caddr, 0, &p);
+		n_cp = ip_vs_conn_out_get(&p);
+	}
+	if (!n_cp) {
+		struct ip_vs_conn_param p;
+
+		ip_vs_conn_fill_param(cp->ipvs,
+				      cp->af, ipvsh->protocol, &cp->caddr,
+				      0, &cp->vaddr, port, &p);
+		n_cp = ip_vs_conn_new(&p, cp->af, &from, port,
+				      IP_VS_CONN_F_NO_CPORT |
+				      IP_VS_CONN_F_NFCT,
+				      cp->dest, skb->mark);
+		if (!n_cp)
+			return 0;
+
+		/* add its controller */
+		ip_vs_control_add(n_cp, cp);
+	}
+
+	/* Replace the old passive address with the new one */
+	if (cp->app_data == (void *) IP_VS_FTP_PASV) {
 		from.ip = n_cp->vaddr.ip;
 		port = n_cp->vport;
 		snprintf(buf, sizeof(buf), "%u,%u,%u,%u,%u,%u",
@@ -256,50 +356,54 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 			 ((unsigned char *)&from.ip)[3],
 			 ntohs(port) >> 8,
 			 ntohs(port) & 0xFF);
+	} else if (cp->app_data == (void *) IP_VS_FTP_EPSV) {
+		from = n_cp->vaddr;
+		port = n_cp->vport;
+		/* Only port, client will use VIP for the data connection */
+		snprintf(buf, sizeof(buf), "|||%u|",
+			 ntohs(port));
+	} else {
+		*buf = 0;
+	}
+	buf_len = strlen(buf);
 
-		buf_len = strlen(buf);
-
-		ct = nf_ct_get(skb, &ctinfo);
-		if (ct) {
-			bool mangled;
-
-			/* 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.
-			 */
-			mangled = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
-							   iph->ihl * 4,
-							   start - data,
-							   end - start,
-							   buf, buf_len);
-			if (mangled) {
-				ip_vs_nfct_expect_related(skb, ct, n_cp,
-							  IPPROTO_TCP, 0, 0);
-				if (skb->ip_summed == CHECKSUM_COMPLETE)
-					skb->ip_summed = CHECKSUM_UNNECESSARY;
-				/* csum is updated */
-				ret = 1;
-			}
-		}
+	ct = nf_ct_get(skb, &ctinfo);
+	if (ct) {
+		bool mangled;
 
-		/*
-		 * Not setting 'diff' is intentional, otherwise the sequence
-		 * would be adjusted twice.
+		/* 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.
 		 */
-
-		cp->app_data = NULL;
-		ip_vs_tcp_conn_listen(n_cp);
-		ip_vs_conn_put(n_cp);
-		return ret;
+		mangled = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
+						   ipvsh->len,
+						   start - data,
+						   end - start,
+						   buf, buf_len);
+		if (mangled) {
+			ip_vs_nfct_expect_related(skb, ct, n_cp,
+						  ipvsh->protocol, 0, 0);
+			if (skb->ip_summed == CHECKSUM_COMPLETE)
+				skb->ip_summed = CHECKSUM_UNNECESSARY;
+			/* csum is updated */
+			ret = 1;
+		}
 	}
-	return 1;
+
+	/* Not setting 'diff' is intentional, otherwise the sequence
+	 * would be adjusted twice.
+	 */
+
+	cp->app_data = (void *) IP_VS_FTP_ACTIVE;
+	ip_vs_tcp_conn_listen(n_cp);
+	ip_vs_conn_put(n_cp);
+	return ret;
 }
 
 
-/*
- * Look at incoming ftp packets to catch the PASV/PORT command
+/* Look at incoming ftp packets to catch the PASV/PORT/EPRT/EPSV command
  * (outside-to-inside).
  *
  * The incoming packet having the PORT command should be something like
@@ -308,12 +412,19 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
  * In this case, we create a connection entry using the client address and
  * port, so that the active ftp data connection from the server can reach
  * the client.
+ * Extended format:
+ *	"EPSV\r\n" when client requests server address from same family
+ *	"EPSV 1\r\n" when client requests IPv4 server address
+ *	"EPSV 2\r\n" when client requests IPv6 server address
+ *	"EPSV ALL\r\n" - not supported
+ *	EPRT with specified delimiter (ASCII 33..126), "|" by default:
+ *	"EPRT |1|IPv4ADDR|PORT|\r\n" when client provides IPv4 addrport
+ *	"EPRT |2|IPv6ADDR|PORT|\r\n" when client provides IPv6 addrport
  */
 static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
-			struct sk_buff *skb, int *diff)
+			struct sk_buff *skb, int *diff,
+			struct ip_vs_iphdr *ipvsh)
 {
-	struct iphdr *iph;
-	struct tcphdr *th;
 	char *data, *data_start, *data_limit;
 	char *start, *end;
 	union nf_inet_addr to;
@@ -323,14 +434,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	/* no diff required for incoming packets */
 	*diff = 0;
 
-#ifdef CONFIG_IP_VS_IPV6
-	/* This application helper doesn't work with IPv6 yet,
-	 * so turn this into a no-op for IPv6 packets
-	 */
-	if (cp->af == AF_INET6)
-		return 1;
-#endif
-
 	/* Only useful for established sessions */
 	if (cp->state != IP_VS_TCP_S_ESTABLISHED)
 		return 1;
@@ -339,27 +442,48 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	if (!skb_make_writable(skb, skb->len))
 		return 0;
 
-	/*
-	 * Detecting whether it is passive
-	 */
-	iph = ip_hdr(skb);
-	th = (struct tcphdr *)&(((char *)iph)[iph->ihl*4]);
-
-	/* Since there may be OPTIONS in the TCP packet and the HLEN is
-	   the length of the header in 32-bit multiples, it is accurate
-	   to calculate data address by th+HLEN*4 */
-	data = data_start = (char *)th + (th->doff << 2);
+	data = data_start = ip_vs_ftp_data_ptr(skb, ipvsh);
 	data_limit = skb_tail_pointer(skb);
+	if (!data || data >= data_limit)
+		return 1;
 
 	while (data <= data_limit - 6) {
-		if (strncasecmp(data, "PASV\r\n", 6) == 0) {
+		if (cp->af == AF_INET &&
+		    strncasecmp(data, "PASV\r\n", 6) == 0) {
 			/* Passive mode on */
 			IP_VS_DBG(7, "got PASV at %td of %td\n",
 				  data - data_start,
 				  data_limit - data_start);
-			cp->app_data = &ip_vs_ftp_pasv;
+			cp->app_data = (void *) IP_VS_FTP_PASV;
 			return 1;
 		}
+
+		/* EPSV or EPSV<space><net-prt> */
+		if (strncasecmp(data, "EPSV", 4) == 0 &&
+		    (data[4] == ' ' || data[4] == '\r')) {
+			if (data[4] == ' ') {
+				char proto = data[5];
+
+				if (data > data_limit - 7 || data[6] != '\r')
+					return 1;
+
+#ifdef CONFIG_IP_VS_IPV6
+				if (cp->af == AF_INET6 && proto == '2') {
+				} else
+#endif
+				if (cp->af == AF_INET && proto == '1') {
+				} else {
+					return 1;
+				}
+			}
+			/* Extended Passive mode on */
+			IP_VS_DBG(7, "got EPSV at %td of %td\n",
+				  data - data_start,
+				  data_limit - data_start);
+			cp->app_data = (void *) IP_VS_FTP_EPSV;
+			return 1;
+		}
+
 		data++;
 	}
 
@@ -370,33 +494,52 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	 * then create a new connection entry for the coming data
 	 * connection.
 	 */
-	if (ip_vs_ftp_get_addrport(data_start, data_limit,
-				   CLIENT_STRING, sizeof(CLIENT_STRING)-1,
-				   ' ', '\r', &to.ip, &port,
-				   &start, &end) != 1)
+	if (cp->af == AF_INET &&
+	    ip_vs_ftp_get_addrport(data_start, data_limit,
+				   CLIENT_STRING_PORT,
+				   sizeof(CLIENT_STRING_PORT)-1,
+				   ' ', false, IP_VS_FTP_PORT,
+				   &to, &port, cp->af,
+				   &start, &end) == 1) {
+
+		IP_VS_DBG(7, "PORT %pI4:%u detected\n", &to.ip, ntohs(port));
+
+		/* Now update or create a connection entry for it */
+		IP_VS_DBG(7, "protocol %s %pI4:%u %pI4:%u\n",
+			  ip_vs_proto_name(ipvsh->protocol),
+			  &to.ip, ntohs(port), &cp->vaddr.ip,
+			  ntohs(cp->vport)-1);
+	} else if (ip_vs_ftp_get_addrport(data_start, data_limit,
+					  CLIENT_STRING_EPRT,
+					  sizeof(CLIENT_STRING_EPRT)-1,
+					  ' ', true, IP_VS_FTP_EPRT,
+					  &to, &port, cp->af,
+					  &start, &end) == 1) {
+
+		IP_VS_DBG_BUF(7, "EPRT %s:%u detected\n",
+			      IP_VS_DBG_ADDR(cp->af, &to), ntohs(port));
+
+		/* Now update or create a connection entry for it */
+		IP_VS_DBG_BUF(7, "protocol %s %s:%u %s:%u\n",
+			      ip_vs_proto_name(ipvsh->protocol),
+			      IP_VS_DBG_ADDR(cp->af, &to), ntohs(port),
+			      IP_VS_DBG_ADDR(cp->af, &cp->vaddr),
+			      ntohs(cp->vport)-1);
+	} else {
 		return 1;
-
-	IP_VS_DBG(7, "PORT %pI4:%d detected\n", &to.ip, ntohs(port));
+	}
 
 	/* Passive mode off */
-	cp->app_data = NULL;
-
-	/*
-	 * Now update or create a connection entry for it
-	 */
-	IP_VS_DBG(7, "protocol %s %pI4:%d %pI4:%d\n",
-		  ip_vs_proto_name(iph->protocol),
-		  &to.ip, ntohs(port), &cp->vaddr.ip, 0);
+	cp->app_data = (void *) IP_VS_FTP_ACTIVE;
 
 	{
 		struct ip_vs_conn_param p;
-		ip_vs_conn_fill_param(cp->ipvs, AF_INET,
-				      iph->protocol, &to, port, &cp->vaddr,
+		ip_vs_conn_fill_param(cp->ipvs, cp->af,
+				      ipvsh->protocol, &to, port, &cp->vaddr,
 				      htons(ntohs(cp->vport)-1), &p);
 		n_cp = ip_vs_conn_in_get(&p);
 		if (!n_cp) {
-			/* This is ipv4 only */
-			n_cp = ip_vs_conn_new(&p, AF_INET, &cp->daddr,
+			n_cp = ip_vs_conn_new(&p, cp->af, &cp->daddr,
 					      htons(ntohs(cp->dport)-1),
 					      IP_VS_CONN_F_NFCT, cp->dest,
 					      skb->mark);
@@ -454,7 +597,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
 		ret = register_ip_vs_app_inc(ipvs, app, app->protocol, ports[i]);
 		if (ret)
 			goto err_unreg;
-		pr_info("%s: loaded support on port[%d] = %d\n",
+		pr_info("%s: loaded support on port[%d] = %u\n",
 			app->name, i, ports[i]);
 	}
 	return 0;
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 3057e453bf31..b9f375e6dc93 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -48,6 +48,7 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <linux/jiffies.h>
+#include <linux/hash.h>
 
 /* for sysctl */
 #include <linux/fs.h>
@@ -160,7 +161,7 @@ ip_vs_lblc_hashkey(int af, const union nf_inet_addr *addr)
 		addr_fold = addr->ip6[0]^addr->ip6[1]^
 			    addr->ip6[2]^addr->ip6[3];
 #endif
-	return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLC_TAB_MASK;
+	return hash_32(ntohl(addr_fold), IP_VS_LBLC_TAB_BITS);
 }
 
 
@@ -371,6 +372,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc)
 	tbl->counter = 1;
 	tbl->dead = false;
 	tbl->svc = svc;
+	atomic_set(&tbl->entries, 0);
 
 	/*
 	 *    Hook periodic timer for garbage collection
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 92adc04557ed..542c4949937a 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -47,6 +47,7 @@
 #include <linux/jiffies.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/hash.h>
 
 /* for sysctl */
 #include <linux/fs.h>
@@ -323,7 +324,7 @@ ip_vs_lblcr_hashkey(int af, const union nf_inet_addr *addr)
 		addr_fold = addr->ip6[0]^addr->ip6[1]^
 			    addr->ip6[2]^addr->ip6[3];
 #endif
-	return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLCR_TAB_MASK;
+	return hash_32(ntohl(addr_fold), IP_VS_LBLCR_TAB_BITS);
 }
 
 
@@ -534,6 +535,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc)
 	tbl->counter = 1;