Merge with /pub/scm/linux/kernel/git/torvalds/linux-2.6.git

36 files changed, 399 insertions, 539 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index b3cb49ce5fa..03942f13394 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1181,6 +1181,7 @@ EXPORT_SYMBOL(inet_stream_connect);
 EXPORT_SYMBOL(inet_stream_ops);
 EXPORT_SYMBOL(inet_unregister_protosw);
 EXPORT_SYMBOL(net_statistics);
+EXPORT_SYMBOL(sysctl_ip_nonlocal_bind);
 
 #ifdef INET_REFCNT_DEBUG
 EXPORT_SYMBOL(inet_sock_nr);
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 0e98f2235b6..514c85b2631 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -200,7 +200,7 @@ static void ah4_err(struct sk_buff *skb, u32 info)
 	xfrm_state_put(x);
 }
 
-static int ah_init_state(struct xfrm_state *x, void *args)
+static int ah_init_state(struct xfrm_state *x)
 {
 	struct ah_data *ahp = NULL;
 	struct xfrm_algo_desc *aalg_desc;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 3cc96730c4e..650dcb12d9a 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -233,11 +233,14 @@ int inet_addr_onlink(struct in_device *in_dev, u32 a, u32 b)
 static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 			 int destroy)
 {
+	struct in_ifaddr *promote = NULL;
 	struct in_ifaddr *ifa1 = *ifap;
 
 	ASSERT_RTNL();
 
-	/* 1. Deleting primary ifaddr forces deletion all secondaries */
+	/* 1. Deleting primary ifaddr forces deletion all secondaries 
+	 * unless alias promotion is set
+	 **/
 
 	if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) {
 		struct in_ifaddr *ifa;
@@ -251,11 +254,16 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 				continue;
 			}
 
-			*ifap1 = ifa->ifa_next;
+			if (!IN_DEV_PROMOTE_SECONDARIES(in_dev)) {
+				*ifap1 = ifa->ifa_next;
 
-			rtmsg_ifa(RTM_DELADDR, ifa);
-			notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa);
-			inet_free_ifa(ifa);
+				rtmsg_ifa(RTM_DELADDR, ifa);
+				notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa);
+				inet_free_ifa(ifa);
+			} else {
+				promote = ifa;
+				break;
+			}
 		}
 	}
 
@@ -281,6 +289,13 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 		if (!in_dev->ifa_list)
 			inetdev_destroy(in_dev);
 	}
+
+	if (promote && IN_DEV_PROMOTE_SECONDARIES(in_dev)) {
+		/* not sure if we should send a delete notify first? */
+		promote->ifa_flags &= ~IFA_F_SECONDARY;
+		rtmsg_ifa(RTM_NEWADDR, promote);
+		notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote);
+	}
 }
 
 static int inet_insert_ifa(struct in_ifaddr *ifa)
@@ -1015,14 +1030,13 @@ static struct notifier_block ip_netdev_notifier = {
 };
 
 static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
-			    u32 pid, u32 seq, int event)
+			    u32 pid, u32 seq, int event, unsigned int flags)
 {
 	struct ifaddrmsg *ifm;
 	struct nlmsghdr  *nlh;
 	unsigned char	 *b = skb->tail;
 
-	nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*ifm));
-	if (pid) nlh->nlmsg_flags |= NLM_F_MULTI;
+	nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags);
 	ifm = NLMSG_DATA(nlh);
 	ifm->ifa_family = AF_INET;
 	ifm->ifa_prefixlen = ifa->ifa_prefixlen;
@@ -1075,7 +1089,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 				continue;
 			if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid,
 					     cb->nlh->nlmsg_seq,
-					     RTM_NEWADDR) <= 0) {
+					     RTM_NEWADDR, NLM_F_MULTI) <= 0) {
 				rcu_read_unlock();
 				goto done;
 			}
@@ -1098,7 +1112,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr* ifa)
 
 	if (!skb)
 		netlink_set_err(rtnl, 0, RTMGRP_IPV4_IFADDR, ENOBUFS);
-	else if (inet_fill_ifaddr(skb, ifa, 0, 0, event) < 0) {
+	else if (inet_fill_ifaddr(skb, ifa, current->pid, 0, event, 0) < 0) {
 		kfree_skb(skb);
 		netlink_set_err(rtnl, 0, RTMGRP_IPV4_IFADDR, EINVAL);
 	} else {
@@ -1384,6 +1398,15 @@ static struct devinet_sysctl_table {
 			.proc_handler	= &ipv4_doint_and_flush,
 			.strategy	= &ipv4_doint_and_flush_strategy,
 		},
+		{
+			.ctl_name	= NET_IPV4_CONF_PROMOTE_SECONDARIES,
+			.procname	= "promote_secondaries",
+			.data		= &ipv4_devconf.promote_secondaries,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= &ipv4_doint_and_flush,
+			.strategy	= &ipv4_doint_and_flush_strategy,
+		},
 	},
 	.devinet_dev = {
 		{
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 053a883247b..ba57446d5d1 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -362,7 +362,7 @@ static void esp_destroy(struct xfrm_state *x)
 	kfree(esp);
 }
 
-static int esp_init_state(struct xfrm_state *x, void *args)
+static int esp_init_state(struct xfrm_state *x)
 {
 	struct esp_data *esp = NULL;
 
@@ -478,7 +478,7 @@ static int __init esp4_init(void)
 {
 	struct xfrm_decap_state decap;
 
-	if (sizeof(struct esp_decap_data)  <
+	if (sizeof(struct esp_decap_data)  >
 	    sizeof(decap.decap_data)) {
 		extern void decap_data_too_small(void);
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 563e7d61270..cd8e45ab958 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -516,6 +516,60 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa)
 #undef BRD1_OK
 }
 
+static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb )
+{
+	
+	struct fib_result       res;
+	struct flowi            fl = { .nl_u = { .ip4_u = { .daddr = frn->fl_addr, 
+							    .fwmark = frn->fl_fwmark,
+							    .tos = frn->fl_tos,
+							    .scope = frn->fl_scope } } };
+	if (tb) {
+		local_bh_disable();
+
+		frn->tb_id = tb->tb_id;
+		frn->err = tb->tb_lookup(tb, &fl, &res);
+
+		if (!frn->err) {
+			frn->prefixlen = res.prefixlen;
+			frn->nh_sel = res.nh_sel;
+			frn->type = res.type;
+			frn->scope = res.scope;
+		}
+		local_bh_enable();
+	}
+}
+
+static void nl_fib_input(struct sock *sk, int len)
+{
+	struct sk_buff *skb = NULL;
+        struct nlmsghdr *nlh = NULL;
+	struct fib_result_nl *frn;
+	int err;
+	u32 pid;     
+	struct fib_table *tb;
+	
+	skb = skb_recv_datagram(sk, 0, 0, &err);
+	nlh = (struct nlmsghdr *)skb->data;
+	
+	frn = (struct fib_result_nl *) NLMSG_DATA(nlh);
+	tb = fib_get_table(frn->tb_id_in);
+
+	nl_fib_lookup(frn, tb);
+	
+	pid = nlh->nlmsg_pid;           /*pid of sending process */
+	NETLINK_CB(skb).groups = 0;     /* not in mcast group */
+	NETLINK_CB(skb).pid = 0;         /* from kernel */
+	NETLINK_CB(skb).dst_pid = pid;
+	NETLINK_CB(skb).dst_groups = 0;  /* unicast */
+	netlink_unicast(sk, skb, pid, MSG_DONTWAIT);
+}    
+
+static void nl_fib_lookup_init(void)
+{
+      netlink_kernel_create(NETLINK_FIB_LOOKUP, nl_fib_input);
+}
+
 static void fib_disable_ip(struct net_device *dev, int force)
 {
 	if (fib_sync_down(0, dev, force))
@@ -604,6 +658,7 @@ void __init ip_fib_init(void)
 
 	register_netdevice_notifier(&fib_netdev_notifier);
 	register_inetaddr_notifier(&fib_inetaddr_notifier);
+	nl_fib_lookup_init();
 }
 
 EXPORT_SYMBOL(inet_addr_type);
diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c
index 6506dcc01b4..b10d6bb5ef3 100644
--- a/net/ipv4/fib_hash.c
+++ b/net/ipv4/fib_hash.c
@@ -703,7 +703,8 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb,
 					  &f->fn_key,
 					  fz->fz_order,
 					  fa->fa_tos,
-					  fa->fa_info) < 0) {
+					  fa->fa_info,
+					  NLM_F_MULTI) < 0) {
 				cb->args[3] = i;
 				return -1;
 			}
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index ac4485f75e9..b729d97cfa9 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -30,7 +30,8 @@ extern int fib_nh_match(struct rtmsg *r, struct nlmsghdr *,
 			struct kern_rta *rta, struct fib_info *fi);
 extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 			 u8 tb_id, u8 type, u8 scope, void *dst,
-			 int dst_len, u8 tos, struct fib_info *fi);
+			 int dst_len, u8 tos, struct fib_info *fi,
+			 unsigned int);
 extern void rtmsg_fib(int event, u32 key, struct fib_alias *fa,
 		      int z, int tb_id,
 		      struct nlmsghdr *n, struct netlink_skb_parms *req);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 39d0aadb9a2..0b298bbc151 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -367,13 +367,14 @@ static struct notifier_block fib_rules_notifier = {
 
 static __inline__ int inet_fill_rule(struct sk_buff *skb,
 				     struct fib_rule *r,
-				     struct netlink_callback *cb)
+				     struct netlink_callback *cb,
+				     unsigned int flags)
 {
 	struct rtmsg *rtm;
 	struct nlmsghdr  *nlh;
 	unsigned char	 *b = skb->tail;
 
-	nlh = NLMSG_PUT(skb, NETLINK_CREDS(cb->skb)->pid, cb->nlh->nlmsg_seq, RTM_NEWRULE, sizeof(*rtm));
+	nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWRULE, sizeof(*rtm), flags);
 	rtm = NLMSG_DATA(nlh);
 	rtm->rtm_family = AF_INET;
 	rtm->rtm_dst_len = r->r_dst_len;
@@ -422,7 +423,7 @@ int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb)
 	for (r=fib_rules, idx=0; r; r = r->r_next, idx++) {
 		if (idx < s_idx)
 			continue;
-		if (inet_fill_rule(skb, r, cb) < 0)
+		if (inet_fill_rule(skb, r, cb, NLM_F_MULTI) < 0)
 			break;
 	}
 	read_unlock(&fib_rules_lock);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 029362d6613..c886b28ba9f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -276,7 +276,7 @@ void rtmsg_fib(int event, u32 key, struct fib_alias *fa,
 	       struct nlmsghdr *n, struct netlink_skb_parms *req)
 {
 	struct sk_buff *skb;
-	u32 pid = req ? req->pid : 0;
+	u32 pid = req ? req->pid : n->nlmsg_pid;
 	int size = NLMSG_SPACE(sizeof(struct rtmsg)+256);
 
 	skb = alloc_skb(size, GFP_KERNEL);
@@ -286,7 +286,7 @@ void rtmsg_fib(int event, u32 key, struct fib_alias *fa,
 	if (fib_dump_info(skb, pid, n->nlmsg_seq, event, tb_id,
 			  fa->fa_type, fa->fa_scope, &key, z,
 			  fa->fa_tos,
-			  fa->fa_info) < 0) {
+			  fa->fa_info, 0) < 0) {
 		kfree_skb(skb);
 		return;
 	}
@@ -932,13 +932,13 @@ u32 __fib_res_prefsrc(struct fib_result *res)
 int
 fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 	      u8 tb_id, u8 type, u8 scope, void *dst, int dst_len, u8 tos,
-	      struct fib_info *fi)
+	      struct fib_info *fi, unsigned int flags)
 {
 	struct rtmsg *rtm;
 	struct nlmsghdr  *nlh;
 	unsigned char	 *b = skb->tail;
 
-	nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*rtm));
+	nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*rtm), flags);
 	rtm = NLMSG_DATA(nlh);
 	rtm->rtm_family = AF_INET;
 	rtm->rtm_dst_len = dst_len;
@@ -1035,7 +1035,7 @@ fib_convert_rtentry(int cmd, struct nlmsghdr *nl, struct rtmsg *rtm,
 	}
 
 	nl->nlmsg_flags = NLM_F_REQUEST;
-	nl->nlmsg_pid = 0;
+	nl->nlmsg_pid = current->pid;
 	nl->nlmsg_seq = 0;
 	nl->nlmsg_len = NLMSG_LENGTH(sizeof(*rtm));
 	if (cmd == SIOCDELRT) {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 85bf0d3e294..cb759484979 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -207,6 +207,7 @@ int sysctl_icmp_ignore_bogus_error_responses;
 
 int sysctl_icmp_ratelimit = 1 * HZ;
 int sysctl_icmp_ratemask = 0x1818;
+int sysctl_icmp_errors_use_inbound_ifaddr;
 
 /*
  *	ICMP control array. This specifies what to do with each ICMP.
@@ -511,8 +512,12 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info)
 	 */
 
 	saddr = iph->daddr;
-	if (!(rt->rt_flags & RTCF_LOCAL))
-		saddr = 0;
+	if (!(rt->rt_flags & RTCF_LOCAL)) {
+		if (sysctl_icmp_errors_use_inbound_ifaddr)
+			saddr = inet_select_addr(skb_in->dev, 0, RT_SCOPE_LINK);
+		else
+			saddr = 0;
+	}
 
 	tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
 					   IPTOS_PREC_INTERNETCONTROL) :
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 47012b93cad..f8b172f8981 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -360,14 +360,14 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
 	err = copied;
 
 	/* Reset and regenerate socket error */
-	spin_lock_irq(&sk->sk_error_queue.lock);
+	spin_lock_bh(&sk->sk_error_queue.lock);
 	sk->sk_err = 0;
 	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
 		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
-		spin_unlock_irq(&sk->sk_error_queue.lock);
+		spin_unlock_bh(&sk->sk_error_queue.lock);
 		sk->sk_error_report(sk);
 	} else
-		spin_unlock_irq(&sk->sk_error_queue.lock);
+		spin_unlock_bh(&sk->sk_error_queue.lock);
 
 out_free_skb:	
 	kfree_skb(skb);
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 1a23c5263b9..2065944fd9e 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -236,15 +236,10 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x)
 	t->props.mode = 1;
 	t->props.saddr.a4 = x->props.saddr.a4;
 	t->props.flags = x->props.flags;
-	
-	t->type = xfrm_get_type(IPPROTO_IPIP, t->props.family);
-	if (t->type == NULL)
-		goto error;
-		
-	if (t->type->init_state(t, NULL))
+
+	if (xfrm_init_state(t))
 		goto error;
 
-	t->km.state = XFRM_STATE_VALID;
 	atomic_set(&t->tunnel_users, 1);
 out:
 	return t;
@@ -422,7 +417,7 @@ static void ipcomp_destroy(struct xfrm_state *x)
 	kfree(ipcd);
 }
 
-static int ipcomp_init_state(struct xfrm_state *x, void *args)
+static int ipcomp_init_state(struct xfrm_state *x)
 {
 	int err;
 	struct ipcomp_data *ipcd;
diff --git a/net/ipv4/ipvs/Makefile b/net/ipv4/ipvs/Makefile
index a788461a40c..30e85de9fff 100644
--- a/net/ipv4/ipvs/Makefile
+++ b/net/ipv4/ipvs/Makefile
@@ -11,7 +11,7 @@ ip_vs_proto-objs-$(CONFIG_IP_VS_PROTO_AH) += ip_vs_proto_ah.o
 
 ip_vs-objs :=	ip_vs_conn.o ip_vs_core.o ip_vs_ctl.o ip_vs_sched.o	   \
 		ip_vs_xmit.o ip_vs_app.o ip_vs_sync.o	   		   \
-		ip_vs_est.o ip_vs_proto.o ip_vs_proto_icmp.o		   \
+		ip_vs_est.o ip_vs_proto.o 				   \
 		$(ip_vs_proto-objs-y)
 
 
diff --git a/net/ipv4/ipvs/ip_vs_proto.c b/net/ipv4/ipvs/ip_vs_proto.c
index 253c46252bd..867d4e9c659 100644
--- a/net/ipv4/ipvs/ip_vs_proto.c
+++ b/net/ipv4/ipvs/ip_vs_proto.c
@@ -216,9 +216,6 @@ int ip_vs_protocol_init(void)
 #ifdef CONFIG_IP_VS_PROTO_UDP
 	REGISTER_PROTOCOL(&ip_vs_protocol_udp);
 #endif
-#ifdef CONFIG_IP_VS_PROTO_ICMP
-	REGISTER_PROTOCOL(&ip_vs_protocol_icmp);
-#endif
 #ifdef CONFIG_IP_VS_PROTO_AH
 	REGISTER_PROTOCOL(&ip_vs_protocol_ah);
 #endif
diff --git a/net/ipv4/ipvs/ip_vs_proto_icmp.c b/net/ipv4/ipvs/ip_vs_proto_icmp.c
deleted file mode 100644
index 191e94aa1c1..00000000000
--- a/net/ipv4/ipvs/ip_vs_proto_icmp.c
+++ /dev/null
@@ -1,182 +0,0 @@
-/*
- * ip_vs_proto_icmp.c:	ICMP load balancing support for IP Virtual Server
- *
- * Authors:	Julian Anastasov <ja@ssi.bg>, March 2002
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		version 2 as published by the Free Software Foundation;
- *
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/icmp.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
-
-#include <net/ip_vs.h>
-
-
-static int icmp_timeouts[1] =		{ 1*60*HZ };
-
-static char * icmp_state_name_table[1] = { "ICMP" };
-
-static struct ip_vs_conn *
-icmp_conn_in_get(const struct sk_buff *skb,
-		 struct ip_vs_protocol *pp,
-		 const struct iphdr *iph,
-		 unsigned int proto_off,
-		 int inverse)
-{
-#if 0
-	struct ip_vs_conn *cp;
-
-	if (likely(!inverse)) {
-		cp = ip_vs_conn_in_get(iph->protocol,
-			iph->saddr, 0,
-			iph->daddr, 0);
-	} else {
-		cp = ip_vs_conn_in_get(iph->protocol,
-			iph->daddr, 0,
-			iph->saddr, 0);
-	}
-
-	return cp;
-
-#else
-	return NULL;
-#endif
-}
-
-static struct ip_vs_conn *
-icmp_conn_out_get(const struct sk_buff *skb,
-		  struct ip_vs_protocol *pp,
-		  const struct iphdr *iph,
-		  unsigned int proto_off,
-		  int inverse)
-{
-#if 0
-	struct ip_vs_conn *cp;
-
-	if (likely(!inverse)) {
-		cp = ip_vs_conn_out_get(iph->protocol,
-			iph->saddr, 0,
-			iph->daddr, 0);
-	} else {
-		cp = ip_vs_conn_out_get(IPPROTO_UDP,
-			iph->daddr, 0,
-			iph->saddr, 0);
-	}
-
-	return cp;
-#else
-	return NULL;
-#endif
-}
-
-static int
-icmp_conn_schedule(struct sk_buff *skb, struct ip_vs_protocol *pp,
-		   int *verdict, struct ip_vs_conn **cpp)
-{
-	*verdict = NF_ACCEPT;
-	return 0;
-}
-
-static int
-icmp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp)
-{
-	if (!(skb->nh.iph->frag_off & __constant_htons(IP_OFFSET))) {
-		if (skb->ip_summed != CHECKSUM_UNNECESSARY) {
-			if (ip_vs_checksum_complete(skb, skb->nh.iph->ihl * 4)) {
-				IP_VS_DBG_RL_PKT(0, pp, skb, 0, "Failed checksum for");
-				return 0;
-			}
-		}
-	}
-	return 1;
-}
-
-static void
-icmp_debug_packet(struct ip_vs_protocol *pp,
-		  const struct sk_buff *skb,
-		  int offset,
-		  const char *msg)
-{
-	char buf[256];
-	struct iphdr _iph, *ih;
-
-	ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph);
-	if (ih == NULL)
-		sprintf(buf, "%s TRUNCATED", pp->name);
-	else if (ih->frag_off & __constant_htons(IP_OFFSET))
-		sprintf(buf, "%s %u.%u.%u.%u->%u.%u.%u.%u frag",
-			pp->name, NIPQUAD(ih->saddr),
-			NIPQUAD(ih->daddr));
-	else {
-		struct icmphdr _icmph, *ic;
-
-		ic = skb_header_pointer(skb, offset + ih->ihl*4,
-					sizeof(_icmph), &_icmph);
-		if (ic == NULL)
-			sprintf(buf, "%s TRUNCATED to %u bytes\n",
-				pp->name, skb->len - offset);
-		else
-			sprintf(buf, "%s %u.%u.%u.%u->%u.%u.%u.%u T:%d C:%d",
-				pp->name, NIPQUAD(ih->saddr),
-				NIPQUAD(ih->daddr),
-				ic->type, ic->code);
-	}
-	printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf);
-}
-
-static int
-icmp_state_transition(struct ip_vs_conn *cp, int direction,
-		      const struct sk_buff *skb,
-		      struct ip_vs_protocol *pp)
-{
-	cp->timeout = pp->timeout_table[IP_VS_ICMP_S_NORMAL];
-	return 1;
-}
-
-static int
-icmp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
-{
-	int num;
-	char **names;
-
-	num = IP_VS_ICMP_S_LAST;
-	names = icmp_state_name_table;
-	return ip_vs_set_state_timeout(pp->timeout_table, num, names, sname, to);
-}
-
-
-static void icmp_init(struct ip_vs_protocol *pp)
-{
-	pp->timeout_table = icmp_timeouts;
-}
-
-static void icmp_exit(struct ip_vs_protocol *pp)
-{
-}
-
-struct ip_vs_protocol ip_vs_protocol_icmp = {
-	.name =			"ICMP",
-	.protocol =		IPPROTO_ICMP,
-	.dont_defrag =		0,
-	.init =			icmp_init,
-	.exit =			icmp_exit,
-	.conn_schedule =	icmp_conn_schedule,
-	.conn_in_get =		icmp_conn_in_get,
-	.conn_out_get =		icmp_conn_out_get,
-	.snat_handler =		NULL,
-	.dnat_handler =		NULL,
-	.csum_check =		icmp_csum_check,
-	.state_transition =	icmp_state_transition,
-	.register_app =		NULL,
-	.unregister_app =	NULL,
-	.app_conn_bind =	NULL,
-	.debug_packet =		icmp_debug_packet,
-	.timeout_change =	NULL,
-	.set_state_timeout =	icmp_set_state_timeout,
-};
diff --git a/net/ipv4/multipath_drr.c b/net/ipv4/multipath_drr.c
index 9349686131f..c9cf8726051 100644
--- a/net/ipv4/multipath_drr.c
+++ b/net/ipv4/multipath_drr.c
@@ -31,6 +31,7 @@
 #include <linux/igmp.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/module.h>
 #include <linux/mroute.h>
 #include <linux/init.h>
 #include <net/ip.h>
@@ -57,7 +58,6 @@ struct multipath_device {
 
 static struct multipath_device state[MULTIPATH_MAX_DEVICECANDIDATES];
 static DEFINE_SPINLOCK(state_lock);
-static struct rtable *last_selection = NULL;
 
 static int inline __multipath_findslot(void)
 {
@@ -111,11 +111,6 @@ struct notifier_block drr_dev_notifier = {
 	.notifier_call	= drr_dev_event,
 };
 
-static void drr_remove(struct rtable *rt)
-{
-	if (last_selection == rt)
-		last_selection = NULL;
-}
 
 static void drr_safe_inc(atomic_t *usecount)
 {
@@ -144,14 +139,6 @@ static void drr_select_route(const struct flowi *flp,
 	int devidx = -1;
 	int cur_min_devidx = -1;
 
-       	/* if necessary and possible utilize the old alternative */
-	if ((flp->flags & FLOWI_FLAG_MULTIPATHOLDROUTE) != 0 &&
-	    last_selection != NULL) {
-		result = last_selection;
-		*rp = result;
-		return;
-	}
-
 	/* 1. make sure all alt. nexthops have the same GC related data */
 	/* 2. determine the new candidate to be returned */
 	result = NULL;
@@ -229,12 +216,10 @@ static void drr_select_route(const struct flowi *flp,
 	}
 
 	*rp = result;
-	last_selection = result;
 }
 
 static struct ip_mp_alg_ops drr_ops = {
 	.mp_alg_select_route	=	drr_select_route,
-	.mp_alg_remove		=	drr_remove,
 };
 
 static int __init drr_init(void)
@@ -244,7 +229,7 @@ static int __init drr_init(void)
 	if (err)
 		return err;
 
-	err = multipath_alg_register(&drr_ops, IP_MP_ALG_RR);
+	err = multipath_alg_register(&drr_ops, IP_MP_ALG_DRR);
 	if (err)
 		goto fail;
 
@@ -263,3 +248,4 @@ static void __exit drr_exit(void)
 
 module_init(drr_init);
 module_exit(drr_exit);
+MODULE_LICENSE("GPL");
diff --git a/net/ipv4/multipath_random.c b/net/ipv4/multipath_random.c
index 805a16e47de..5249dbe7c55 100644
--- a/net/ipv4/multipath_random.c
+++ b/net/ipv4/multipath_random.c
@@ -31,6 +31,7 @@
 #include <linux/igmp.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/module.h>
 #include <linux/mroute.h>
 #include <linux/init.h>
 #include <net/ip.h>
@@ -126,3 +127,4 @@ static void __exit random_exit(void)
 
 module_init(random_init);
 module_exit(random_exit);
+MODULE_LICENSE("GPL");
diff --git a/net/ipv4/multipath_rr.c b/net/ipv4/multipath_rr.c
index 554a8256816..b6cd2870478 100644
--- a/net/ipv4/multipath_rr.c
+++ b/net/ipv4/multipath_rr.c
@@ -31,6 +31,7 @@
 #include <linux/igmp.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/module.h>
 #include <linux/mroute.h>
 #include <linux/init.h>
 #include <net/ip.h>
@@ -47,29 +48,12 @@
 #include <net/checksum.h>
 #include <net/ip_mp_alg.h>
 
-#define MULTIPATH_MAX_CANDIDATES 40
-
-static struct rtable* last_used = NULL;
-
-static void rr_remove(struct rtable *rt)
-{
-	if (last_used == rt)
-		last_used = NULL;
-}
-
 static void rr_select_route(const struct flowi *flp,
 			    struct rtable *first, struct rtable **rp)
 {
 	struct rtable *nh, *result, *min_use_cand = NULL;
 	int min_use = -1;
 
-	/* if necessary and possible utilize the old alternative */
-	if ((flp->flags & FLOWI_FLAG_MULTIPATHOLDROUTE) != 0 &&
-	    last_used != NULL) {
-		result = last_used;
-		goto out;
-	}
-
 	/* 1. make sure all alt. nexthops have the same GC related data
 	 * 2. determine the new candidate to be returned
 	 */
@@ -90,15 +74,12 @@ static void rr_select_route(const struct flowi *flp,
 	if (!result)
 		result = first;
 
-out:
-	last_used = result;
 	result->u.dst.__use++;
 	*rp = result;
 }
 
 static struct ip_mp_alg_ops rr_ops = {
 	.mp_alg_select_route	=	rr_select_route,
-	.mp_alg_remove		=	rr_remove,
 };
 
 static int __init rr_init(void)
@@ -113,3 +94,4 @@ static void __exit rr_exit(void)
 
 module_init(rr_init);
 module_exit(rr_exit);
+MODULE_LICENSE("GPL");
diff --git a/net/ipv4/multipath_wrandom.c b/net/ipv4/multipath_wrandom.c
index c3d2ca1a678..bd7d75b6abe 100644
--- a/net/ipv4/multipath_wrandom.c
+++ b/net/ipv4/multipath_wrandom.c
@@ -31,6 +31,7 @@
 #include <linux/igmp.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/module.h>
 #include <linux/mroute.h>
 #include <linux/init.h>
 #include <net/ip.h>
@@ -342,3 +343,4 @@ static void __exit wrandom_exit(void)
 
 module_init(wrandom_init);
 module_exit(wrandom_exit);
+MODULE_LICENSE("GPL");
diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c
index 46ca45f74d8..bc59f7b3980 100644
--- a/net/ipv4/netfilter/ip_conntrack_standalone.c
+++ b/net/ipv4/netfilter/ip_conntrack_standalone.c
@@ -256,6 +256,7 @@ static void *exp_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
  	struct list_head *e = v;
 
+	++*pos;
 	e = e->next;
 
 	if (e == &ip_conntrack_expect_list)
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index e5746b67441..eda1fba431a 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -3,6 +3,7 @@
  * communicating with userspace via netlink.
  *
  * (C) 2000-2002 James Morris <jmorris@intercode.com.au>
+ * (C) 2003-2005 Netfilter Core Team <coreteam@netfilter.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -17,6 +18,7 @@
  * 2005-01-10: Added /proc counter for dropped packets; fixed so
  *             packets aren't delivered to user space if they're going 
  *             to be dropped. 
+ * 2005-05-26: local_bh_{disable,enable} around nf_reinject (Harald Welte)
  *
  */
 #include <linux/module.h>
@@ -71,7 +73,15 @@ static DECLARE_MUTEX(ipqnl_sem);
 static void
 ipq_issue_verdict(struct ipq_queue_entry *entry, int verdict)
 {
+	/* TCP input path (and probably other bits) assume to be called
+	 * from softirq context, not from syscall, like ipq_issue_verdict is
+	 * called.  TCP input path deadlocks with locks taken from timer
+	 * softirq, e.g.  We therefore emulate this by local_bh_disable() */
+
+	local_bh_disable();
 	nf_reinject(entry->skb, entry->info, verdict);
+	local_bh_enable();
+
 	kfree(entry);
 }
 
diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c
index 25ab9fabdcb..2d44b07688a 100644
--- a/net/ipv4/netfilter/ipt_recent.c
+++ b/net/ipv4/netfilter/ipt_recent.c
@@ -223,7 +223,7 @@ static int ip_recent_ctrl(struct file *file, const char __user *input, unsigned
 			curr_table->table[count].last_seen = 0;
 			curr_table->table[count].addr = 0;
 			curr_table->table[count].ttl = 0;
-			memset(curr_table->table[count].last_pkts,0,ip_pkt_list_tot*sizeof(u_int32_t));
+			memset(curr_table->table[count].last_pkts,0,ip_pkt_list_tot*sizeof(unsigned long));
 			curr_table->table[count].oldest_pkt = 0;
 			curr_table->table[count].time_pos = 0;
 			curr_table->time_info[count].position = count;
@@ -502,7 +502,7 @@ match(const struct sk_buff *skb,
 		location = time_info[curr_table->time_pos].position;
 		hash_table[r_list[location].hash_entry] = -1;
 		hash_table[hash_result] = location;
-		memset(r_list[location].last_pkts,0,ip_pkt_list_tot*sizeof(u_int32_t));
+		memset(r_list[location].last_pkts,0,ip_pkt_list_tot*sizeof(unsigned long));
 		r_list[location].time_pos = curr_table->time_pos;
 		r_list[location].addr = addr;
 		r_list[location].ttl = ttl;
@@ -631,7 +631,7 @@ match(const struct sk_buff *skb,
 			r_list[location].last_seen = 0;
 			r_list[location].addr = 0;
 			r_list[location].ttl = 0;
-			memset(r_list[location].last_pkts,0,ip_pkt_list_tot*sizeof(u_int32_t));
+			memset(r_list[location].last_pkts,0,ip_pkt_list_tot*sizeof(unsigned long));
 			r_list[location].oldest_pkt = 0;
 			ans = !info->invert;
 		}
@@ -734,10 +734,10 @@ checkentry(const char *tablename,
 	memset(curr_table->table,0,sizeof(struct recent_ip_list)*ip_list_tot);
 #ifdef DEBUG
 	if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: Allocating %d for pkt_list.\n",
-			sizeof(u_int32_t)*ip_pkt_list_tot*ip_list_tot);
+			sizeof(unsigned long)*ip_pkt_list_tot*ip_list_tot);
 #endif
 
-	hold = vmalloc(sizeof(u_int32_t)*ip_pkt_list_tot*ip_list_tot);
+	hold = vmalloc(sizeof(unsigned long)*ip_pkt_list_tot*ip_list_tot);
 #ifdef DEBUG
 	if(debug) printk(KERN_INFO RECENT_NAME ": checkentry: After pkt_list allocation.\n");
 #endif
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 5b1ec586bae..d1835b1bc8c 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -259,7 +259,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb)
 	return 0;
 }
 
-static int raw_send_hdrinc(struct sock *sk, void *from, int length,
+static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
 			struct rtable *rt, 
 			unsigned int flags)
 {
@@ -298,7 +298,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, int length,
 		goto error_fault;
 
 	/* We don't modify invalid header */
-	if (length >= sizeof(*iph) && iph->ihl * 4 <= length) {
+	if (length >= sizeof(*iph) && iph->ihl * 4U <= length) {
 		if (!iph->saddr)
 			iph->saddr = rt->rt_src;
 		iph->check   = 0;
@@ -332,7 +332,7 @@ static void raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
 	u8 __user *type = NULL;
 	u8 __user *code = NULL;
 	int probed = 0;
-	int i;
+	unsigned int i;
 
 	if (!msg->msg_iov)
 		return;
@@ -384,7 +384,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	int err;
 
 	err = -EMSGSIZE;
-	if (len < 0 || len > 0xFFFF)
+	if (len > 0xFFFF)
 		goto out;
 
 	/*
@@ -514,7 +514,10 @@ done:
 		kfree(ipc.opt);
 	ip_rt_put(rt);
 
-out:	return err < 0 ? err : len;
+out:
+	if (err < 0)
+		return err;
+	return len;
 
 do_confirm:
 	dst_confirm(&rt->u.dst);
@@ -610,7 +613,10 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		copied = skb->len;
 done:
 	skb_free_datagram(sk, skb);
-out:	return err ? err : copied;
+out:
+	if (err)
+		return err;
+	return copied;
 }
 
 static int raw_init(struct sock *sk)
@@ -691,11 +697,11 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
 			struct sk_buff *skb;
 			int amount = 0;
 
-			spin_lock_irq(&sk->sk_receive_queue.lock);
+			spin_lock_bh(&sk->sk_receive_queue.lock);
 			skb = skb_peek(&sk->sk_receive_queue);
 			if (skb != NULL)
 				amount = skb->len;
-			spin_unlock_irq(&sk->sk_receive_queue.lock);
+			spin_unlock_bh(&sk->sk_receive_queue.lock);
 			return put_user(amount, (int __user *)arg);
 		}
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a682d28e247..f4d53c91986 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2581,7 +2581,7 @@ int ip_route_output_key(struct rtable **rp, struct flowi *flp)
 }
 
 static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
-			int nowait)
+			int nowait, unsigned int flags)
 {
 	struct rtable *rt = (struct rtable*)skb->dst;
 	struct rtmsg *r;
@@ -2591,9 +2591,8 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 #ifdef CONFIG_IP_MROUTE
 	struct rtattr *eptr;
 #endif
-	nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*r));
+	nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*r), flags);
 	r = NLMSG_DATA(nlh);
-	nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0;
 	r->rtm_family	 = AF_INET;
 	r->rtm_dst_len	= 32;
 	r->rtm_src_len	= 0;
@@ -2744,7 +2743,7 @@ int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
 	NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid;
 
 	err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
-				RTM_NEWROUTE, 0);
+				RTM_NEWROUTE, 0, 0);
 	if (!err)
 		goto out_free;
 	if (err < 0) {
@@ -2781,8 +2780,8 @@ int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
 				continue;
 			skb->dst = dst_clone(&rt->u.dst);
 			if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid,
-					 cb->nlh->nlmsg_seq,
-					 RTM_NEWROUTE, 1) <= 0) {
+					 cb->nlh->nlmsg_seq, RTM_NEWROUTE, 
+					 1, NLM_F_MULTI) <= 0) {
 				dst_release(xchg(&skb->dst, NULL));
 				rcu_read_unlock_bh();
 				goto done;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index e923d2f021a..72d01444218 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -169,10 +169,10 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie)
 	return mssind < NUM_MSS ? msstab[mssind] + 1 : 0;
 }
 
-extern struct or_calltable or_ipv4;
+extern struct request_sock_ops tcp_request_sock_ops;
 
 static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
-					   struct open_request *req,
+					   struct request_sock *req,
 					   struct dst_entry *dst)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -182,7 +182,7 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 	if (child)
 		tcp_acceptq_queue(sk, req, child);
 	else
-		tcp_openreq_free(req);
+		reqsk_free(req);
 
 	return child;
 }
@@ -190,10 +190,12 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 			     struct ip_options *opt)
 {
+	struct inet_request_sock *ireq;
+	struct tcp_request_sock *treq;
 	struct tcp_sock *tp = tcp_sk(sk);
 	__u32 cookie = ntohl(skb->h.th->ack_seq) - 1; 
 	struct sock *ret = sk;
-	struct open_request *req; 
+	struct request_sock *req; 
 	int mss; 
 	struct rtable *rt; 
 	__u8 rcv_wscale;
@@ -209,19 +211,20 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 
 	NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESRECV);
 
-	req = tcp_openreq_alloc();
 	ret = NULL;
+	req = reqsk_alloc(&tcp_request_sock_ops); /* for safety */
 	if (!req)
 		goto out;
 
-	req->rcv_isn		= htonl(skb->h.th->seq) - 1;
-	req->snt_isn		= cookie; 
+	ireq = inet_rsk(req);
+	treq = tcp_rsk(req);
+	treq->rcv_isn		= htonl(skb->h.th->seq) - 1;
+	treq->snt_isn		= cookie; 
 	req->mss		= mss;
- 	req->rmt_port		= skb->h.th->source;
-	req->af.v4_req.loc_addr = skb->nh.iph->daddr;
-	req->af.v4_req.rmt_addr = skb->nh.iph->saddr;
-	req->class		= &or_ipv4; /* for savety */
-	req->af.v4_req.opt	= NULL;
+ 	ireq->rmt_port		= skb->h.th->source;
+	ireq->loc_addr		= skb->nh.iph->daddr;
+	ireq->rmt_addr		= skb->nh.iph->saddr;
+	ireq->opt		= NULL;
 
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
@@ -229,17 +232,15 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	if (opt && opt->optlen) {
 		int opt_size = sizeof(struct ip_options) + opt->optlen;
 
-		req->af.v4_req.opt = kmalloc(opt_size, GFP_ATOMIC);
-		if (req->af.v4_req.opt) {
-			if (ip_options_echo(req->af.v4_req.opt, skb)) {
-				kfree(req->af.v4_req.opt);
-				req->af.v4_req.opt = NULL;
-			}
+		ireq->opt = kmalloc(opt_size, GFP_ATOMIC);
+		if (ireq->opt != NULL && ip_options_echo(ireq->opt, skb)) {
+			kfree(ireq->opt);
+			ireq->opt = NULL;
 		}
 	}
 
-	req->snd_wscale = req->rcv_wscale = req->tstamp_ok = 0;
-	req->wscale_ok	= req->sack_ok = 0; 
+	ireq->snd_wscale = ireq->rcv_wscale = ireq->tstamp_ok = 0;
+	ireq->wscale_ok	 = ireq->sack_ok = 0; 
 	req->expires	= 0UL; 
 	req->retrans	= 0; 
 	
@@ -253,15 +254,15 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 		struct flowi fl = { .nl_u = { .ip4_u =
 					      { .daddr = ((opt && opt->srr) ?
 							  opt->faddr :
-							  req->af.v4_req.rmt_addr),
-						.saddr = req->af.v4_req.loc_addr,
+							  ireq->rmt_addr),
+						.saddr = ireq->loc_addr,
 						.tos = RT_CONN_FLAGS(sk) } },
 				    .proto = IPPROTO_TCP,
 				    .uli_u = { .ports =
 					       { .sport = skb->h.th->dest,
 						 .dport = skb->h.th->source } } };
 		if (ip_route_output_key(&rt, &fl)) {
-			tcp_openreq_free(req);
+			reqsk_free(req);
 			goto out; 
 		}
 	}
@@ -272,7 +273,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 				  &req->rcv_wnd, &req->window_clamp, 
 				  0, &rcv_wscale);
 	/* BTW win scale with syncookies is 0 by definition */
-	req->rcv_wscale	  = rcv_wscale; 
+	ireq->rcv_wscale  = rcv_wscale; 
 
 	ret = get_cookie_sock(sk, skb, req, &rt->u.dst);
 out:	return ret;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3aafb298c1c..23068bddbf0 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -23,6 +23,7 @@ extern int sysctl_ip_nonlocal_bind;
 extern int sysctl_icmp_echo_ignore_all;
 extern int sysctl_icmp_echo_ignore_broadcasts;
 extern int sysctl_icmp_ignore_bogus_error_responses;
+extern int sysctl_icmp_errors_use_inbound_ifaddr;
 
 /* From ip_fragment.c */
 extern int sysctl_ipfrag_low_thresh;
@@ -396,6 +397,14 @@ ctl_table ipv4_table[] = {
 		.proc_handler	= &proc_dointvec
 	},
 	{
+		.ctl_name	= NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR,
+		.procname	= "icmp_errors_use_inbound_ifaddr",
+		.data		= &sysctl_icmp_errors_use_inbound_ifaddr,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec
+	},
+	{
 		.ctl_name	= NET_IPV4_ROUTE,
 		.procname	= "route",
 		.maxlen		= 0,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a037bafcba3..674bbd8cfd3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -271,7 +271,6 @@ int sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
 
 DEFINE_SNMP_STAT(struct tcp_mib, tcp_statistics);
 
-kmem_cache_t *tcp_openreq_cachep;
 kmem_cache_t *tcp_bucket_cachep;
 kmem_cache_t *tcp_timewait_cachep;
 
@@ -317,7 +316,7 @@ EXPORT_SYMBOL(tcp_enter_memory_pressure);
 static __inline__ unsigned int tcp_listen_poll(struct sock *sk,
 					       poll_table *wait)
 {
-	return tcp_sk(sk)->accept_queue ? (POLLIN | POLLRDNORM) : 0;
+	return !reqsk_queue_empty(&tcp_sk(sk)->accept_queue) ? (POLLIN | POLLRDNORM) : 0;
 }
 
 /*
@@ -463,28 +462,15 @@ int tcp_listen_start(struct sock *sk)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp_listen_opt *lopt;
+	int rc = reqsk_queue_alloc(&tp->accept_queue, TCP_SYNQ_HSIZE);
+
+	if (rc != 0)
+		return rc;
 
 	sk->sk_max_ack_backlog = 0;
 	sk->sk_ack_backlog = 0;
-	tp->accept_queue = tp->accept_queue_tail = NULL;
-	rwlock_init(&tp->syn_wait_lock);
 	tcp_delack_init(tp);
 
-	lopt = kmalloc(sizeof(struct tcp_listen_opt), GFP_KERNEL);
-	if (!lopt)
-		return -ENOMEM;
-
-	memset(lopt, 0, sizeof(struct tcp_listen_opt));
-	for (lopt->max_qlen_log = 6; ; lopt->max_qlen_log++)
-		if ((1 << lopt->max_qlen_log) >= sysctl_max_syn_backlog)
-			break;
-	get_random_bytes(&lopt->hash_rnd, 4);
-
-	write_lock_bh(&tp->syn_wait_lock);
-	tp->listen_opt = lopt;
-	write_unlock_bh(&tp->syn_wait_lock);
-
 	/* There is race window here: we announce ourselves listening,
 	 * but this transition is still not validated by get_port().
 	 * It is OK, because this socket enters to hash table only
@@ -501,10 +487,7 @@ int tcp_listen_start(struct sock *sk)
 	}
 
 	sk->sk_state = TCP_CLOSE;
-	write_lock_bh(&tp->syn_wait_lock);
-	tp->listen_opt = NULL;
-	write_unlock_bh(&tp->syn_wait_lock);
-	kfree(lopt);
+	reqsk_queue_destroy(&tp->accept_queue);
 	return -EADDRINUSE;
 }
 
@@ -516,25 +499,23 @@ int tcp_listen_start(struct sock *sk)
 static void tcp_listen_stop (struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp_listen_opt *lopt = tp->listen_opt;
-	struct open_request *acc_req = tp->accept_queue;
-	struct open_request *req;
+	struct listen_sock *lopt;
+	struct request_sock *acc_req;
+	struct request_sock *req;
 	int i;
 
 	tcp_delete_keepalive_timer(sk);
 
 	/* make all the listen_opt local to us */
-	write_lock_bh(&tp->syn_wait_lock);
-	tp->listen_opt = NULL;
-	write_unlock_bh(&tp->syn_wait_lock);
-	tp->accept_queue = tp->accept_queue_tail = NULL;
+	lopt = reqsk_queue_yank_listen_sk(&tp->accept_queue);
+	acc_req = reqsk_queue_yank_acceptq(&tp->accept_queue);
 
 	if (lopt->qlen) {
 		for (i = 0; i < TCP_SYNQ_HSIZE; i++) {
 			while ((req = lopt->syn_table[i]) != NULL) {
 				lopt->syn_table[i] = req->dl_next;
 				lopt->qlen--;
-				tcp_openreq_free(req);
+				reqsk_free(req);
 
 		/* Following specs, it would be better either to send FIN
 		 * (and enter FIN-WAIT-1, it is normal close)
@@ -574,7 +555,7 @@ static void tcp_listen_stop (struct sock *sk)
 		sock_put(child);
 
 		sk_acceptq_removed(sk);
-		tcp_openreq_fastfree(req);
+		__reqsk_free(req);
 	}
 	BUG_TRAP(!sk->sk_ack_backlog);
 }
@@ -1345,7 +1326,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 		cleanup_rbuf(sk, copied);
 
-		if (tp->ucopy.task == user_recv) {
+		if (!sysctl_tcp_low_latency && tp->ucopy.task == user_recv) {
 			/* Install new reader */
 			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
 				user_recv = current;
@@ -1868,11 +1849,11 @@ static int wait_for_connect(struct sock *sk, long timeo)
 		prepare_to_wait_exclusive(sk->sk_sleep, &wait,
 					  TASK_INTERRUPTIBLE);
 		release_sock(sk);
-		if (!tp->accept_queue)
+		if (reqsk_queue_empty(&tp->accept_queue))
 			timeo = schedule_timeout(timeo);
 		lock_sock(sk);
 		err = 0;
-		if (tp->accept_queue)
+		if (!reqsk_queue_empty(&tp->accept_queue))
 			break;
 		err = -EINVAL;
 		if (sk->sk_state != TCP_LISTEN)
@@ -1895,7 +1876,6 @@ static int wait_for_connect(struct sock *sk, long timeo)
 struct sock *tcp_accept(struct sock *sk, int flags, int *err)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct open_request *req;
 	struct sock *newsk;
 	int error;
 
@@ -1906,37 +1886,31 @@ struct sock *tcp_accept(struct sock *sk, int flags, int *err)
 	 */
 	error = -EINVAL;
 	if (sk->sk_state != TCP_LISTEN)
-		goto out;
+		goto out_err;
 
 	/* Find already established connection */
-	if (!tp->accept_queue) {
+	if (reqsk_queue_empty(&tp->accept_queue)) {
 		long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
 
 		/* If this is a non blocking socket don't sleep */
 		error = -EAGAIN;
 		if (!timeo)
-			goto out;
+			goto out_err;
 
 		error = wait_for_connect(sk, timeo);
 		if (error)
-			goto out;
+			goto out_err;
 	}
 
-	req = tp->accept_queue;
-	if ((tp->accept_queue = req->dl_next) == NULL)
-		tp->accept_queue_tail = NULL;
-
- 	newsk = req->sk;
-	sk_acceptq_removed(sk);
-	tcp_openreq_fastfree(req);
+	newsk = reqsk_queue_get_child(&tp->accept_queue, sk);
 	BUG_TRAP(newsk->sk_state != TCP_SYN_RECV);
-	release_sock(sk);
-	return newsk;
-
 out:
 	release_sock(sk);
+	return newsk;
+out_err:
+	newsk = NULL;
 	*err = error;
-	return NULL;
+	goto out;
 }
 
 /*
@@ -2271,13 +2245,6 @@ void __init tcp_init(void)
 		__skb_cb_too_small_for_tcp(sizeof(struct tcp_skb_cb),
 					   sizeof(skb->cb));
 
-	tcp_openreq_cachep = kmem_cache_create("tcp_open_request",
-						   sizeof(struct open_request),
-					       0, SLAB_HWCACHE_ALIGN,
-					       NULL, NULL);
-	if (!tcp_openreq_cachep)
-		panic("tcp_init: Cannot alloc open_request cache.");
-
 	tcp_bucket_cachep = kmem_cache_create("tcp_bind_bucket",
 					      sizeof(struct tcp_bind_bucket),
 					      0, SLAB_HWCACHE_ALIGN,
@@ -2338,7 +2305,7 @@ void __init tcp_init(void)
 			(tcp_bhash_size * sizeof(struct tcp_bind_hashbucket));
 			order++)
 		;
-	if (order > 4) {
+	if (order >= 4) {
 		sysctl_local_port_range[0] = 32768;
 		sysctl_local_port_range[1] = 61000;
 		sysctl_tcp_max_tw_buckets = 180000;
@@ -2374,7 +2341,6 @@ EXPORT_SYMBOL(tcp_destroy_sock);
 EXPORT_SYMBOL(tcp_disconnect);
 EXPORT_SYMBOL(tcp_getsockopt);
 EXPORT_SYMBOL(tcp_ioctl);
-EXPORT_SYMBOL(tcp_openreq_cachep);
 EXPORT_SYMBOL(tcp_poll);
 EXPORT_SYMBOL(tcp_read_sock);
 EXPORT_SYMBOL(tcp_recvmsg);
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 8faa8948f75..634befc0792 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -455,9 +455,10 @@ static int tcpdiag_dump_sock(struct sk_buff *skb, struct sock *sk,
 }
 
 static int tcpdiag_fill_req(struct sk_buff *skb, struct sock *sk,
-			    struct open_request *req,
+			    struct request_sock *req,
 			    u32 pid, u32 seq)
 {
+	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct inet_sock *inet = inet_sk(sk);
 	unsigned char *b = skb->tail;
 	struct tcpdiagmsg *r;
@@ -482,9 +483,9 @@ static int tcpdiag_fill_req(struct sk_buff *skb, struct sock *sk,
 		tmo = 0;
 
 	r->id.tcpdiag_sport = inet->sport;
-	r->id.tcpdiag_dport = req->rmt_port;
-	r->id.tcpdiag_src[0] = req->af.v4_req.loc_addr;
-	r->id.tcpdiag_dst[0] = req->af.v4_req.rmt_addr;
+	r->id.tcpdiag_dport = ireq->rmt_port;
+	r->id.tcpdiag_src[0] = ireq->loc_addr;
+	r->id.tcpdiag_dst[0] = ireq->rmt_addr;
 	r->tcpdiag_expires = jiffies_to_msecs(tmo),
 	r->tcpdiag_rqueue = 0;
 	r->tcpdiag_wqueue = 0;
@@ -493,9 +494,9 @@ static int tcpdiag_fill_req(struct sk_buff *skb, struct sock *sk,
 #ifdef CONFIG_IP_TCPDIAG_IPV6
 	if (r->tcpdiag_family == AF_INET6) {
 		ipv6_addr_copy((struct in6_addr *)r->id.tcpdiag_src,
-			       &req->af.v6_req.loc_addr);
+			       &tcp6_rsk(req)->loc_addr);
 		ipv6_addr_copy((struct in6_addr *)r->id.tcpdiag_dst,
-			       &req->af.v6_req.rmt_addr);
+			       &tcp6_rsk(req)->rmt_addr);
 	}
 #endif
 	nlh->nlmsg_len = skb->tail - b;
@@ -513,7 +514,7 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 	struct tcpdiag_entry entry;
 	struct tcpdiagreq *r = NLMSG_DATA(cb->nlh);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp_listen_opt *lopt;
+	struct listen_sock *lopt;
 	struct rtattr *bc = NULL;
 	struct inet_sock *inet = inet_sk(sk);
 	int j, s_j;
@@ -528,9 +529,9 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 
 	entry.family = sk->sk_family;
 
-	read_lock_bh(&tp->syn_wait_lock);
+	read_lock_bh(&tp->accept_queue.syn_wait_lock);
 
-	lopt = tp->listen_opt;
+	lopt = tp->accept_queue.listen_opt;
 	if (!lopt || !lopt->qlen)
 		goto out;
 
@@ -541,13 +542,15 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 	}
 
 	for (j = s_j; j < TCP_SYNQ_HSIZE; j++) {
-		struct open_request *req, *head = lopt->syn_table[j];
+		struct request_sock *req, *head = lopt->syn_table[j];
 
 		reqnum = 0;
 		for (req = head; req; reqnum++, req = req->dl_next) {
+			struct inet_request_sock *ireq = inet_rsk(req);
+
 			if (reqnum < s_reqnum)
 				continue;
-			if (r->id.tcpdiag_dport != req->rmt_port &&
+			if (r->id.tcpdiag_dport != ireq->rmt_port &&
 			    r->id.tcpdiag_dport)
 				continue;
 
@@ -555,16 +558,16 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 				entry.saddr =
 #ifdef CONFIG_IP_TCPDIAG_IPV6
 					(entry.family == AF_INET6) ?
-					req->af.v6_req.loc_addr.s6_addr32 :
+					tcp6_rsk(req)->loc_addr.s6_addr32 :
 #endif
-					&req->af.v4_req.loc_addr;
+					&ireq->loc_addr;
 				entry.daddr = 
 #ifdef CONFIG_IP_TCPDIAG_IPV6
 					(entry.family == AF_INET6) ?
-					req->af.v6_req.rmt_addr.s6_addr32 :
+					tcp6_rsk(req)->rmt_addr.s6_addr32 :
 #endif
-					&req->af.v4_req.rmt_addr;
-				entry.dport = ntohs(req->rmt_port);
+					&ireq->rmt_addr;
+				entry.dport = ntohs(ireq->rmt_port);
 
 				if (!tcpdiag_bc_run(RTA_DATA(bc),
 						    RTA_PAYLOAD(bc), &entry))
@@ -585,7 +588,7 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 	}
 
 out:
-	read_unlock_bh(&tp->syn_wait_lock);
+	read_unlock_bh(&tp->accept_queue.syn_wait_lock);
 
 	return err;
 }
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index dad98e4a504..2d41d5d6ad1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -36,7 +36,7 @@
  *					ACK bit.
  *		Andi Kleen :		Implemented fast path mtu discovery.
  *	     				Fixed many serious bugs in the
- *					open_request handling and moved
+ *					request_sock handling and moved
  *					most of it into the af independent code.
  *					Added tail drop and some other bugfixes.
  *					Added new listen sematics.
@@ -869,21 +869,23 @@ static __inline__ u32 tcp_v4_synq_hash(u32 raddr, u16 rport, u32 rnd)
 	return (jhash_2words(raddr, (u32) rport, rnd) & (TCP_SYNQ_HSIZE - 1));
 }
 
-static struct open_request *tcp_v4_search_req(struct tcp_sock *tp,
-					      struct open_request ***prevp,
+static struct request_sock *tcp_v4_search_req(struct tcp_sock *tp,
+					      struct request_sock ***prevp,
 					      __u16 rport,
 					      __u32 raddr, __u32 laddr)
 {
-	struct tcp_listen_opt *lopt = tp->listen_opt;
-	struct open_request *req, **prev;
+	struct listen_sock *lopt = tp->accept_queue.listen_opt;
+	struct request_sock *req, **prev;
 
 	for (prev = &lopt->syn_table[tcp_v4_synq_hash(raddr, rport, lopt->hash_rnd)];
 	     (req = *prev) != NULL;
 	     prev = &req->dl_next) {
-		if (req->rmt_port == rport &&
-		    req->af.v4_req.rmt_addr == raddr &&
-		    req->af.v4_req.loc_addr == laddr &&
-		    TCP_INET_FAMILY(req->class->family)) {
+		const struct inet_request_sock *ireq = inet_rsk(req);
+
+		if (ireq->rmt_port == rport &&
+		    ireq->rmt_addr == raddr &&
+		    ireq->loc_addr == laddr &&
+		    TCP_INET_FAMILY(req->rsk_ops->family)) {
 			BUG_TRAP(!req->sk);
 			*prevp = prev;
 			break;
@@ -893,21 +895,13 @@ static struct open_request *tcp_v4_search_req(struct tcp_sock *tp,
 	return req;
 }
 
-static void tcp_v4_synq_add(struct sock *sk, struct open_request *req)
+static void tcp_v4_synq_add(struct sock *sk, struct request_sock *req)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp_listen_opt *lopt = tp->listen_opt;
-	u32 h = tcp_v4_synq_hash(req->af.v4_req.rmt_addr, req->rmt_port, lopt->hash_rnd);
-
-	req->expires = jiffies + TCP_TIMEOUT_INIT;
-	req->retrans = 0;
-	req->sk = NULL;
-	req->dl_next = lopt->syn_table[h];
-
-	write_lock(&tp->syn_wait_lock);
-	lopt->syn_table[h] = req;
-	write_unlock(&tp->syn_wait_lock);
+	struct listen_sock *lopt = tp->accept_queue.listen_opt;
+	u32 h = tcp_v4_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd);
 
+	reqsk_queue_hash_req(&tp->accept_queue, h, req, TCP_TIMEOUT_INIT);
 	tcp_synq_added(sk);
 }
 
@@ -1050,7 +1044,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info)
 	}
 
 	switch (sk->sk_state) {
-		struct open_request *req, **prev;
+		struct request_sock *req, **prev;
 	case TCP_LISTEN:
 		if (sock_owned_by_user(sk))
 			goto out;
@@ -1065,7 +1059,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info)
 		 */
 		BUG_TRAP(!req->sk);
 
-		if (seq != req->snt_isn) {
+		if (seq != tcp_rsk(req)->snt_isn) {
 			NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
 			goto out;
 		}
@@ -1254,28 +1248,29 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	tcp_tw_put(tw);
 }
 
-static void tcp_v4_or_send_ack(struct sk_buff *skb, struct open_request *req)
+static void tcp_v4_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req)
 {
-	tcp_v4_send_ack(skb, req->snt_isn + 1, req->rcv_isn + 1, req->rcv_wnd,
+	tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
 			req->ts_recent);
 }
 
 static struct dst_entry* tcp_v4_route_req(struct sock *sk,
-					  struct open_request *req)
+					  struct request_sock *req)
 {
 	struct rtable *rt;
-	struct ip_options *opt = req->af.v4_req.opt;
+	const struct inet_request_sock *ireq = inet_rsk(req);
+	struct ip_options *opt = inet_rsk(req)->opt;
 	struct flowi fl = { .oif = sk->sk_bound_dev_if,
 			    .nl_u = { .ip4_u =
 				      { .daddr = ((opt && opt->srr) ?
 						  opt->faddr :
-						  req->af.v4_req.rmt_addr),
-					.saddr = req->af.v4_req.loc_addr,
+						  ireq->rmt_addr),
+					.saddr = ireq->loc_addr,
 					.tos = RT_CONN_FLAGS(sk) } },
 			    .proto = IPPROTO_TCP,
 			    .uli_u = { .ports =
 				       { .sport = inet_sk(sk)->sport,
-					 .dport = req->rmt_port } } };
+					 .dport = ireq->rmt_port } } };
 
 	if (ip_route_output_flow(&rt, &fl, sk, 0)) {
 		IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
@@ -1291,12 +1286,13 @@ static struct dst_entry* tcp_v4_route_req(struct sock *sk,
 
 /*
  *	Send a SYN-ACK after having received an ACK.
- *	This still operates on a open_request only, not on a big
+ *	This still operates on a request_sock only, not on a big
  *	socket.
  */
-static int tcp_v4_send_synack(struct sock *sk, struct open_request *req,
+static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
 			      struct dst_entry *dst)
 {
+	const struct inet_request_sock *ireq = inet_rsk(req);
 	int err = -1;
 	struct sk_buff * skb;
 
@@ -1310,14 +1306,14 @@ static int tcp_v4_send_synack(struct sock *sk, struct open_request *req,
 		struct tcphdr *th = skb->h.th;
 
 		th->check = tcp_v4_check(th, skb->len,
-					 req->af.v4_req.loc_addr,
-					 req->af.v4_req.rmt_addr,
+					 ireq->loc_addr,
+					 ireq->rmt_addr,
 					 csum_partial((char *)th, skb->len,
 						      skb->csum));
 
-		err = ip_build_and_send_pkt(skb, sk, req->af.v4_req.loc_addr,
-					    req->af.v4_req.rmt_addr,
-					    req->af.v4_req.opt);
+		err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
+					    ireq->rmt_addr,
+					    ireq->opt);
 		if (err == NET_XMIT_CN)
 			err = 0;
 	}
@@ -1328,12 +1324,12 @@ out:
 }
 
 /*
- *	IPv4 open_request destructor.
+ *	IPv4 request_sock destructor.
  */
-static void tcp_v4_or_free(struct open_request *req)
+static void tcp_v4_reqsk_destructor(struct request_sock *req)
 {
-	if (req->af.v4_req.opt)
-		kfree(req->af.v4_req.opt);
+	if (inet_rsk(req)->opt)
+		kfree(inet_rsk(req)->opt);
 }
 
 static inline void syn_flood_warning(struct sk_buff *skb)
@@ -1349,7 +1345,7 @@ static inline void syn_flood_warning(struct sk_buff *skb)
 }
 
 /*
- * Save and compile IPv4 options into the open_request if needed.
+ * Save and compile IPv4 options into the request_sock if needed.
  */
 static inline struct ip_options *tcp_v4_save_options(struct sock *sk,
 						     struct sk_buff *skb)
@@ -1370,33 +1366,20 @@ static inline struct ip_options *tcp_v4_save_options(struct sock *sk,
 	return dopt;
 }
 
-/*
- * Maximum number of SYN_RECV sockets in queue per LISTEN socket.
- * One SYN_RECV socket costs about 80bytes on a 32bit machine.
- * It would be better to replace it with a global counter for all sockets
- * but then some measure against one socket starving all other sockets
- * would be needed.
- *
- * It was 128 by default. Experiments with real servers show, that
- * it is absolutely not enough even at 100conn/sec. 256 cures most
- * of problems. This value is adjusted to 128 for very small machines
- * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb).
- * Further increasing requires to change hash table size.
- */
-int sysctl_max_syn_backlog = 256;
-
-struct or_calltable or_ipv4 = {
+struct request_sock_ops tcp_request_sock_ops = {
 	.family		=	PF_INET,
+	.obj_size	=	sizeof(struct tcp_request_sock),
 	.rtx_syn_ack	=	tcp_v4_send_synack,
-	.send_ack	=	tcp_v4_or_send_ack,
-	.destructor	=	tcp_v4_or_free,
+	.send_ack	=	tcp_v4_reqsk_send_ack,
+	.destructor	=	tcp_v4_reqsk_destructor,
 	.send_reset	=	tcp_v4_send_reset,
 };
 
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 {
+	struct inet_request_sock *ireq;
 	struct tcp_options_received tmp_opt;
-	struct open_request *req;
+	struct request_sock *req;
 	__u32 saddr = skb->nh.iph->saddr;
 	__u32 daddr = skb->nh.iph->daddr;
 	__u32 isn = TCP_SKB_CB(skb)->when;
@@ -1433,7 +1416,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (sk_acceptq_is_full(sk) && tcp_synq_young(sk) > 1)
 		goto drop;
 
-	req = tcp_openreq_alloc();
+	req = reqsk_alloc(&tcp_request_sock_ops);
 	if (!req)
 		goto drop;
 
@@ -1461,10 +1444,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 
 	tcp_openreq_init(req, &tmp_opt, skb);
 
-	req->af.v4_req.loc_addr = daddr;
-	req->af.v4_req.rmt_addr = saddr;
-	req->af.v4_req.opt = tcp_v4_save_options(sk, skb);
-	req->class = &or_ipv4;
+	ireq = inet_rsk(req);
+	ireq->loc_addr = daddr;
+	ireq->rmt_addr = saddr;
+	ireq->opt = tcp_v4_save_options(sk, skb);
 	if (!want_cookie)
 		TCP_ECN_create_request(req, skb->h.th);
 
@@ -1523,20 +1506,20 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 
 		isn = tcp_v4_init_sequence(sk, skb);
 	}
-	req->snt_isn = isn;
+	tcp_rsk(req)->snt_isn = isn;
 
 	if (tcp_v4_send_synack(sk, req, dst))
 		goto drop_and_free;
 
 	if (want_cookie) {
-	   	tcp_openreq_free(req);
+	   	reqsk_free(req);
 	} else {
 		tcp_v4_synq_add(sk, req);
 	}
 	return 0;
 
 drop_and_free:
-	tcp_openreq_free(req);
+	reqsk_free(req);
 drop:
 	TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
 	return 0;
@@ -1548,9 +1531,10 @@ drop:
  * now create the new socket.
  */
 struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
-				  struct open_request *req,
+				  struct request_sock *req,
 				  struct dst_entry *dst)
 {
+	struct inet_request_sock *ireq;
 	struct inet_sock *newinet;
 	struct tcp_sock *newtp;
 	struct sock *newsk;
@@ -1570,11 +1554,12 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	newtp		      = tcp_sk(newsk);
 	newinet		      = inet_sk(newsk);
-	newinet->daddr	      = req->af.v4_req.rmt_addr;
-	newinet->rcv_saddr    = req->af.v4_req.loc_addr;
-	newinet->saddr	      = req->af.v4_req.loc_addr;
-	newinet->opt	      = req->af.v4_req.opt;
-	req->af.v4_req.opt    = NULL;
+	ireq		      = inet_rsk(req);
+	newinet->daddr	      = ireq->rmt_addr;
+	newinet->rcv_saddr    = ireq->loc_addr;
+	newinet->saddr	      = ireq->loc_addr;
+	newinet->opt	      = ireq->opt;
+	ireq->opt	      = NULL;
 	newinet->mc_index     = tcp_v4_iif(skb);
 	newinet->mc_ttl	      = skb->nh.iph->ttl;
 	newtp->ext_header_len = 0;
@@ -1605,9 +1590,9 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 	struct iphdr *iph = skb->nh.iph;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sock *nsk;
-	struct open_request **prev;
+	struct request_sock **prev;
 	/* Find possible connection requests. */
-	struct open_request *req = tcp_v4_search_req(tp, &prev, th->source,
+	struct request_sock *req = tcp_v4_search_req(tp, &prev, th->source,
 						     iph->saddr, iph->daddr);
 	if (req)
 		return tcp_check_req(sk, skb, req, prev);
@@ -2144,13 +2129,13 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	++st->num;
 
 	if (st->state == TCP_SEQ_STATE_OPENREQ) {
-		struct open_request *req = cur;
+		struct request_sock *req = cur;
 
 	       	tp = tcp_sk(st->syn_wait_sk);
 		req = req->dl_next;
 		while (1) {
 			while (req) {
-				if (req->class->family == st->family) {
+				if (req->rsk_ops->family == st->family) {
 					cur = req;
 					goto out;
 				}
@@ -2159,17 +2144,17 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 			if (++st->sbucket >= TCP_SYNQ_HSIZE)
 				break;
 get_req:
-			req = tp->listen_opt->syn_table[st->sbucket];
+			req = tp->accept_queue.listen_opt->syn_table[st->sbucket];
 		}
 		sk	  = sk_next(st->syn_wait_sk);
 		st->state = TCP_SEQ_STATE_LISTENING;
-		read_unlock_bh(&tp->syn_wait_lock);
+		read_unlock_bh(&tp->accept_queue.syn_wait_lock);
 	} else {
 	       	tp = tcp_sk(sk);
-		read_lock_bh(&tp->syn_wait_lock);
-		if (tp->listen_opt && tp->listen_opt->qlen)
+		read_lock_bh(&tp->accept_queue.syn_wait_lock);
+		if (reqsk_queue_len(&tp->accept_queue))
 			goto start_req;
-		read_unlock_bh(&tp->syn_wait_lock);
+		read_unlock_bh(&tp->accept_queue.syn_wait_lock);
 		sk = sk_next(sk);
 	}
 get_sk:
@@ -2179,8 +2164,8 @@ get_sk:
 			goto out;
 		}
 	       	tp = tcp_sk(sk);
-		read_lock_bh(&tp->syn_wait_lock);
-		if (tp->listen_opt && tp->listen_opt->qlen) {
+		read_lock_bh(&tp->accept_queue.syn_wait_lock);
+		if (reqsk_queue_len(&tp->accept_queue)) {
 start_req:
 			st->uid		= sock_i_uid(sk);
 			st->syn_wait_sk = sk;
@@ -2188,7 +2173,7 @@ start_req:
 			st->sbucket	= 0;
 			goto get_req;
 		}
-		read_unlock_bh(&tp->syn_wait_lock);
+		read_unlock_bh(&tp->accept_queue.syn_wait_lock);
 	}
 	if (++st->bucket < TCP_LHTABLE_SIZE) {
 		sk = sk_head(&tcp_listening_hash[st->bucket]);
@@ -2375,7 +2360,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
 	case TCP_SEQ_STATE_OPENREQ:
 		if (v) {
 			struct tcp_sock *tp = tcp_sk(st->syn_wait_sk);
-			read_unlock_bh(&tp->syn_wait_lock);
+			read_unlock_bh(&tp->accept_queue.syn_wait_lock);
 		}
 	case TCP_SEQ_STATE_LISTENING:
 		if (v != SEQ_START_TOKEN)
@@ -2451,18 +2436,19 @@ void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo)
 	memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops)); 
 }
 
-static void get_openreq4(struct sock *sk, struct open_request *req,
+static void get_openreq4(struct sock *sk, struct request_sock *req,
 			 char *tmpbuf, int i, int uid)
 {
+	const struct inet_request_sock *ireq = inet_rsk(req);
 	int ttd = req->expires - jiffies;
 
 	sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
 		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p",
 		i,
-		req->af.v4_req.loc_addr,
+		ireq->loc_addr,
 		ntohs(inet_sk(sk)->sport),
-		req->af.v4_req.rmt_addr,
-		ntohs(req->rmt_port),
+		ireq->rmt_addr,
+		ntohs(ireq->rmt_port),
 		TCP_SYN_RECV,
 		0, 0, /* could print option size, but that is af dependent. */
 		1,    /* timers active (only the expire timer) */
@@ -2618,6 +2604,7 @@ struct proto tcp_prot = {
 	.sysctl_rmem		= sysctl_tcp_rmem,
 	.max_header		= MAX_TCP_HEADER,
 	.obj_size		= sizeof(struct tcp_sock),
+	.rsk_prot		= &tcp_request_sock_ops,
 };
 
 
@@ -2660,7 +2647,6 @@ EXPORT_SYMBOL(tcp_proc_register);
 EXPORT_SYMBOL(tcp_proc_unregister);
 #endif
 EXPORT_SYMBOL(sysctl_local_port_range);
-EXPORT_SYMBOL(sysctl_max_syn_backlog);
 EXPORT_SYMBOL(sysctl_tcp_low_latency);
 EXPORT_SYMBOL(sysctl_tcp_tw_reuse);
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index eea1a17a9ac..b3943e7562f 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -684,7 +684,7 @@ out:
  * Actually, we could lots of memory writes here. tp of listening
  * socket contains all necessary default parameters.
  */
-struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, struct sk_buff *skb)
+struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb)
 {
 	/* allocate the newsk from the same slab of the master sock,
 	 * if not, at sk_free time we'll try to free it from the wrong
@@ -692,6 +692,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req,
 	struct sock *newsk = sk_alloc(PF_INET, GFP_ATOMIC, sk->sk_prot, 0);
 
 	if(newsk != NULL) {
+		struct inet_request_sock *ireq = inet_rsk(req);
+		struct tcp_request_sock *treq = tcp_rsk(req);
 		struct tcp_sock *newtp;
 		struct sk_filter *filter;
 
@@ -703,7 +705,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req,
 		tcp_sk(newsk)->bind_hash = NULL;
 
 		/* Clone the TCP header template */
-		inet_sk(newsk)->dport = req->rmt_port;
+		inet_sk(newsk)->dport = ireq->rmt_port;
 
 		sock_lock_init(newsk);
 		bh_lock_sock(newsk);
@@ -739,14 +741,14 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req,
 		/* Now setup tcp_sock */
 		newtp = tcp_sk(newsk);
 		newtp->pred_flags = 0;
-		newtp->rcv_nxt = req->rcv_isn + 1;
-		newtp->snd_nxt = req->snt_isn + 1;
-		newtp->snd_una = req->snt_isn + 1;
-		newtp->snd_sml = req->snt_isn + 1;
+		newtp->rcv_nxt = treq->rcv_isn + 1;
+		newtp->snd_nxt = treq->snt_isn + 1;
+		newtp->snd_una = treq->snt_isn + 1;
+		newtp->snd_sml = treq->snt_isn + 1;
 
 		tcp_prequeue_init(newtp);
 
-		tcp_init_wl(newtp, req->snt_isn, req->rcv_isn);
+		tcp_init_wl(newtp, treq->snt_isn, treq->rcv_isn);
 
 		newtp->retransmits = 0;
 		newtp->backoff = 0;
@@ -775,10 +777,10 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req,
 		tcp_set_ca_state(newtp, TCP_CA_Open);
 		tcp_init_xmit_timers(newsk);
 		skb_queue_head_init(&newtp->out_of_order_queue);
-		newtp->rcv_wup = req->rcv_isn + 1;
-		newtp->write_seq = req->snt_isn + 1;
+		newtp->rcv_wup = treq->rcv_isn + 1;
+		newtp->write_seq = treq->snt_isn + 1;
 		newtp->pushed_seq = newtp->write_seq;
-		newtp->copied_seq = req->rcv_isn + 1;
+		newtp->copied_seq = treq->rcv_isn + 1;
 
 		newtp->rx_opt.saw_tstamp = 0;
 
@@ -788,10 +790,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req,
 		newtp->probes_out = 0;
 		newtp->rx_opt.num_sacks = 0;
 		newtp->urg_data = 0;
-		newtp->listen_opt = NULL;
-		newtp->accept_queue = newtp->accept_queue_tail = NULL;
-		/* Deinitialize syn_wait_lock to trap illegal accesses. */
-		memset(&newtp->syn_wait_lock, 0, sizeof(newtp->syn_wait_lock));
+		/* Deinitialize accept_queue to trap illegal accesses. */
+		memset(&newtp->accept_queue, 0, sizeof(newtp->accept_queue));
 
 		/* Back to base struct sock members. */
 		newsk->sk_err = 0;
@@ -808,18 +808,18 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req,
 		newsk->sk_socket = NULL;
 		newsk->sk_sleep = NULL;
 
-		newtp->rx_opt.tstamp_ok = req->tstamp_ok;
-		if((newtp->rx_opt.sack_ok = req->sack_ok) != 0) {
+		newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
+		if((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) {
 			if (sysctl_tcp_fack)
 				newtp->rx_opt.sack_ok |= 2;
 		}
 		newtp->window_clamp = req->window_clamp;
 		newtp->rcv_ssthresh = req->rcv_wnd;
 		newtp->rcv_wnd = req->rcv_wnd;
-		newtp->rx_opt.wscale_ok = req->wscale_ok;
+		newtp->rx_opt.wscale_ok = ireq->wscale_ok;
 		if (newtp->rx_opt.wscale_ok) {
-			newtp->rx_opt.snd_wscale = req->snd_wscale;
-			newtp->rx_opt.rcv_wscale = req->rcv_wscale;
+			newtp->rx_opt.snd_wscale = ireq->snd_wscale;
+			newtp->rx_opt.rcv_wscale = ireq->rcv_wscale;
 		} else {
 			newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0;
 			newtp->window_clamp = min(newtp->window_clamp, 65535U);
@@ -851,12 +851,12 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req,
 
 /* 
  *	Process an incoming packet for SYN_RECV sockets represented
- *	as an open_request.
+ *	as a request_sock.
  */
 
 struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
-			   struct open_request *req,
-			   struct open_request **prev)
+			   struct request_sock *req,
+			   struct request_sock **prev)
 {
 	struct tcphdr *th = skb->h.th;
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -881,7 +881,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 	}
 
 	/* Check for pure retransmitted SYN. */
-	if (TCP_SKB_CB(skb)->seq == req->rcv_isn &&
+	if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn &&
 	    flg == TCP_FLAG_SYN &&
 	    !paws_reject) {
 		/*
@@ -901,7 +901,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 		 * Enforce "SYN-ACK" according to figure 8, figure 6
 		 * of RFC793, fixed by RFC1122.
 		 */
-		req->class->rtx_syn_ack(sk, req, NULL);
+		req->rsk_ops->rtx_syn_ack(sk, req, NULL);
 		return NULL;
 	}
 
@@ -959,7 +959,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 	 * Invalid ACK: reset will be sent by listening socket
 	 */
 	if ((flg & TCP_FLAG_ACK) &&
-	    (TCP_SKB_CB(skb)->ack_seq != req->snt_isn+1))
+	    (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1))
 		return sk;
 
 	/* Also, it would be not so bad idea to check rcv_tsecr, which
@@ -970,10 +970,10 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 	/* RFC793: "first check sequence number". */
 
 	if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
-					  req->rcv_isn+1, req->rcv_isn+1+req->rcv_wnd)) {
+					  tcp_rsk(req)->rcv_isn + 1, tcp_rsk(req)->rcv_isn + 1 + req->rcv_wnd)) {
 		/* Out of window: send ACK and drop. */
 		if (!(flg & TCP_FLAG_RST))
-			req->class->send_ack(skb, req);
+			req->rsk_ops->send_ack(skb, req);
 		if (paws_reject)
 			NET_INC_STATS_BH(LINUX_MIB_PAWSESTABREJECTED);
 		return NULL;
@@ -981,12 +981,12 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 
 	/* In sequence, PAWS is OK. */
 
-	if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, req->rcv_isn+1))
+	if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_isn + 1))
 			req->ts_recent = tmp_opt.rcv_tsval;
 
-		if (TCP_SKB_CB(skb)->seq == req->rcv_isn) {
+		if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
 			/* Truncate SYN, it is out of window starting
-			   at req->rcv_isn+1. */
+			   at tcp_rsk(req)->rcv_isn + 1. */
 			flg &= ~TCP_FLAG_SYN;
 		}
 
@@ -1003,8 +1003,8 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 			return NULL;
 
 		/* If TCP_DEFER_ACCEPT is set, drop bare ACK. */
-		if (tp->defer_accept && TCP_SKB_CB(skb)->end_seq == req->rcv_isn+1) {
-			req->acked = 1;
+		if (tp->defer_accept && TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
+			inet_rsk(req)->acked = 1;
 			return NULL;
 		}
 
@@ -1026,14 +1026,14 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
 
 	listen_overflow:
 		if (!sysctl_tcp_abort_on_overflow) {
-			req->acked = 1;
+			inet_rsk(req)->acked = 1;
 			return NULL;
 		}
 
 	embryonic_reset:
 		NET_INC_STATS_BH(LINUX_MIB_EMBRYONICRSTS);
 		if (!(flg & TCP_FLAG_RST))
-			req->class->send_reset(skb);
+			req->rsk_ops->send_reset(skb);
 
 		tcp_synq_drop(sk, req, prev);
 		return NULL;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fa24e7ae1f4..f17c6577e33 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1356,8 +1356,9 @@ int tcp_send_synack(struct sock *sk)
  * Prepare a SYN-ACK.
  */
 struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
-				 struct open_request *req)
+				 struct request_sock *req)
 {
+	struct inet_request_sock *ireq = inet_rsk(req);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcphdr *th;
 	int tcp_header_size;
@@ -1373,47 +1374,47 @@ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	skb->dst = dst_clone(dst);
 
 	tcp_header_size = (sizeof(struct tcphdr) + TCPOLEN_MSS +
-			   (req->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) +
-			   (req->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) +
+			   (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) +
+			   (ireq->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) +
 			   /* SACK_PERM is in the place of NOP NOP of TS */
-			   ((req->sack_ok && !req->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0));
+			   ((ireq->sack_ok && !ireq->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0));
 	skb->h.th = th = (struct tcphdr *) skb_push(skb, tcp_header_size);
 
 	memset(th, 0, sizeof(struct tcphdr));
 	th->syn = 1;
 	th->ack = 1;
 	if (dst->dev->features&NETIF_F_TSO)
-		req->ecn_ok = 0;
+		ireq->ecn_ok = 0;
 	TCP_ECN_make_synack(req, th);
 	th->source = inet_sk(sk)->sport;
-	th->dest = req->rmt_port;
-	TCP_SKB_CB(skb)->seq = req->snt_isn;
+	th->dest = ireq->rmt_port;
+	TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn;
 	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
 	TCP_SKB_CB(skb)->sacked = 0;
 	skb_shinfo(skb)->tso_segs = 1;
 	skb_shinfo(skb)->tso_size = 0;
 	th->seq = htonl(TCP_SKB_CB(skb)->seq);
-	th->ack_seq = htonl(req->rcv_isn + 1);
+	th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
 	if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
 		__u8 rcv_wscale; 
 		/* Set this up on the first call only */
 		req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
 		/* tcp_full_space because it is guaranteed to be the first packet */
 		tcp_select_initial_window(tcp_full_space(sk), 
-			dst_metric(dst, RTAX_ADVMSS) - (req->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
+			dst_metric(dst, RTAX_ADVMSS) - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
 			&req->rcv_wnd,
 			&req->window_clamp,
-			req->wscale_ok,
+			ireq->wscale_ok,
 			&rcv_wscale);
-		req->rcv_wscale = rcv_wscale; 
+		ireq->rcv_wscale = rcv_wscale; 
 	}
 
 	/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
 	th->window = htons(req->rcv_wnd);
 
 	TCP_SKB_CB(skb)->when = tcp_time_stamp;
-	tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), req->tstamp_ok,
-			      req->sack_ok, req->wscale_ok, req->rcv_wscale,
+	tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok,
+			      ireq->sack_ok, ireq->wscale_ok, ireq->rcv_wscale,
 			      TCP_SKB_CB(skb)->when,
 			      req->ts_recent);
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 799ebe061e2..b127b449856 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -464,11 +464,11 @@ out_unlock:
 static void tcp_synack_timer(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp_listen_opt *lopt = tp->listen_opt;
+	struct listen_sock *lopt = tp->accept_queue.listen_opt;
 	int max_retries = tp->syn_retries ? : sysctl_tcp_synack_retries;
 	int thresh = max_retries;
 	unsigned long now = jiffies;
-	struct open_request **reqp, *req;
+	struct request_sock **reqp, *req;
 	int i, budget;
 
 	if (lopt == NULL || lopt->qlen == 0)
@@ -513,8 +513,8 @@ static void tcp_synack_timer(struct sock *sk)
 		while ((req = *reqp) != NULL) {
 			if (time_after_eq(now, req->expires)) {
 				if ((req->retrans < thresh ||
-				     (req->acked && req->retrans < max_retries))
-				    && !req->class->rtx_syn_ack(sk, req, NULL)) {
+				     (inet_rsk(req)->acked && req->retrans < max_retries))
+				    && !req->rsk_ops->rtx_syn_ack(sk, req, NULL)) {
 					unsigned long timeo;
 
 					if (req->retrans++ == 0)
@@ -527,13 +527,9 @@ static void tcp_synack_timer(struct sock *sk)
 				}
 
 				/* Drop this request */
-				write_lock(&tp->syn_wait_lock);
-				*reqp = req->dl_next;
-				write_unlock(&tp->syn_wait_lock);
-				lopt->qlen--;
-				if (req->retrans == 0)
-					lopt->qlen_young--;
-				tcp_openreq_free(req);
+				tcp_synq_unlink(tp, req, reqp);
+				reqsk_queue_removed(&tp->accept_queue, req);
+				reqsk_free(req);
 				continue;
 			}
 			reqp = &req->dl_next;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4a6952e3fee..7c24e64b443 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -738,7 +738,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 			unsigned long amount;
 
 			amount = 0;
-			spin_lock_irq(&sk->sk_receive_queue.lock);
+			spin_lock_bh(&sk->sk_receive_queue.lock);
 			skb = skb_peek(&sk->sk_receive_queue);
 			if (skb != NULL) {
 				/*
@@ -748,7 +748,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 				 */
 				amount = skb->len - sizeof(struct udphdr);
 			}
-			spin_unlock_irq(&sk->sk_receive_queue.lock);
+			spin_unlock_bh(&sk->sk_receive_queue.lock);
 			return put_user(amount, (int __user *)arg);
 		}
 
@@ -848,12 +848,12 @@ csum_copy_err:
 	/* Clear queue. */
 	if (flags&MSG_PEEK) {
 		int clear = 0;
-		spin_lock_irq(&sk->sk_receive_queue.lock);
+		spin_lock_bh(&sk->sk_receive_queue.lock);
 		if (skb == skb_peek(&sk->sk_receive_queue)) {
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			clear = 1;
 		}
-		spin_unlock_irq(&sk->sk_receive_queue.lock);
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		if (clear)
 			kfree_skb(skb);
 	}
@@ -1334,7 +1334,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		struct sk_buff_head *rcvq = &sk->sk_receive_queue;
 		struct sk_buff *skb;
 
-		spin_lock_irq(&rcvq->lock);
+		spin_lock_bh(&rcvq->lock);
 		while ((skb = skb_peek(rcvq)) != NULL) {
 			if (udp_checksum_complete(skb)) {
 				UDP_INC_STATS_BH(UDP_MIB_INERRORS);
@@ -1345,7 +1345,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 				break;
 			}
 		}
-		spin_unlock_irq(&rcvq->lock);
+		spin_unlock_bh(&rcvq->lock);
 
 		/* nothing to see, move along */
 		if (skb == NULL)
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index af2392ae576..66620a95942 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -33,6 +33,7 @@ static void xfrm4_encap(struct sk_buff *skb)
 	struct dst_entry *dst = skb->dst;
 	struct xfrm_state *x = dst->xfrm;
 	struct iphdr *iph, *top_iph;
+	int flags;
 
 	iph = skb->nh.iph;
 	skb->h.ipiph = iph;
@@ -51,10 +52,13 @@ static void xfrm4_encap(struct sk_buff *skb)
 
 	/* DS disclosed */
 	top_iph->tos = INET_ECN_encapsulate(iph->tos, iph->tos);
-	if (x->props.flags & XFRM_STATE_NOECN)
+
+	flags = x->props.flags;
+	if (flags & XFRM_STATE_NOECN)
 		IP_ECN_clear(top_iph);
 
-	top_iph->frag_off = iph->frag_off & htons(IP_DF);
+	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
+		0 : (iph->frag_off & htons(IP_DF));
 	if (!top_iph->frag_off)
 		__ip_select_ident(top_iph, dst, 0);
 
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 223a2e83853..050611d7a96 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -7,12 +7,20 @@
  *
  */
 
+#include <net/ip.h>
 #include <net/xfrm.h>
 #include <linux/pfkeyv2.h>
 #include <linux/ipsec.h>
 
 static struct xfrm_state_afinfo xfrm4_state_afinfo;
 
+static int xfrm4_init_flags(struct xfrm_state *x)
+{
+	if (ipv4_config.no_pmtu_disc)
+		x->props.flags |= XFRM_STATE_NOPMTUDISC;
+	return 0;
+}
+
 static void
 __xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl,
 		     struct xfrm_tmpl *tmpl,
@@ -109,6 +117,7 @@ __xfrm4_find_acq(u8 mode, u32 reqid, u8 proto,
 static struct xfrm_state_afinfo xfrm4_state_afinfo = {
 	.family			= AF_INET,
 	.lock			= RW_LOCK_UNLOCKED,
+	.init_flags		= xfrm4_init_flags,
 	.init_tempsel		= __xfrm4_init_tempsel,
 	.state_lookup		= __xfrm4_state_lookup,
 	.find_acq		= __xfrm4_find_acq,
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index 413191f585f..e1fe360ed27 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -84,7 +84,7 @@ static void ipip_err(struct sk_buff *skb, u32 info)
 		handler->err_handler(skb, &arg);
 }
 
-static int ipip_init_state(struct xfrm_state *x, void *args)
+static int ipip_init_state(struct xfrm_state *x)
 {
 	if (!x->props.mode)
 		return -EINVAL;