18 files changed, 180 insertions, 96 deletions

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index c95cd93acf29..1940b4df7699 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -70,6 +70,7 @@
  *                                      bonding can change the skb before
  *                                      sending (e.g. insert 8021q tag).
  *              Harald Welte    :       convert to make use of jenkins hash
+ *              Jesper D. Brouer:       Proxy ARP PVLAN RFC 3069 support.
  */
 
 #include <linux/module.h>
@@ -524,12 +525,15 @@ int arp_bind_neighbour(struct dst_entry *dst)
 /*
  * Check if we can use proxy ARP for this path
  */
-
-static inline int arp_fwd_proxy(struct in_device *in_dev, struct rtable *rt)
+static inline int arp_fwd_proxy(struct in_device *in_dev,
+                                struct net_device *dev, struct rtable *rt)
 {
         struct in_device *out_dev;
         int imi, omi = -1;
 
+        if (rt->u.dst.dev == dev)
+                return 0;
+
         if (!IN_DEV_PROXY_ARP(in_dev))
                 return 0;
 
@@ -548,6 +552,43 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, struct rtable *rt)
 }
 
 /*
+ * Check for RFC3069 proxy arp private VLAN (allow to send back to same dev)
+ *
+ * RFC3069 supports proxy arp replies back to the same interface.  This
+ * is done to support (ethernet) switch features, like RFC 3069, where
+ * the individual ports are not allowed to communicate with each
+ * other, BUT they are allowed to talk to the upstream router.  As
+ * described in RFC 3069, it is possible to allow these hosts to
+ * communicate through the upstream router, by proxy_arp'ing.
+ *
+ * RFC 3069: "VLAN Aggregation for Efficient IP Address Allocation"
+ *
+ *  This technology is known by different names:
+ *    In RFC 3069 it is called VLAN Aggregation.
+ *    Cisco and Allied Telesyn call it Private VLAN.
+ *    Hewlett-Packard call it Source-Port filtering or port-isolation.
+ *    Ericsson call it MAC-Forced Forwarding (RFC Draft).
+ *
+ */
+static inline int arp_fwd_pvlan(struct in_device *in_dev,
+                                struct net_device *dev, struct rtable *rt,
+                                __be32 sip, __be32 tip)
+{
+        /* Private VLAN is only concerned about the same ethernet segment */
+        if (rt->u.dst.dev != dev)
+                return 0;
+
+        /* Don't reply on self probes (often done by windowz boxes)*/
+        if (sip == tip)
+                return 0;
+
+        if (IN_DEV_PROXY_ARP_PVLAN(in_dev))
+                return 1;
+        else
+                return 0;
+}
+
+/*
  *      Interface to link layer: send routine and receive handler.
  */
 
@@ -833,8 +874,11 @@ static int arp_process(struct sk_buff *skb)
                         }
                         goto out;
                 } else if (IN_DEV_FORWARD(in_dev)) {
-                            if (addr_type == RTN_UNICAST  && rt->u.dst.dev != dev &&
-                             (arp_fwd_proxy(in_dev, rt) || pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) {
+                        if (addr_type == RTN_UNICAST  &&
+                            (arp_fwd_proxy(in_dev, dev, rt) ||
+                             arp_fwd_pvlan(in_dev, dev, rt, sip, tip) ||
+                             pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))
+                        {
                                 n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
                                 if (n)
                                         neigh_release(n);
@@ -863,7 +907,8 @@ static int arp_process(struct sk_buff *skb)
                    devices (strip is candidate)
                  */
                 if (n == NULL &&
-                    arp->ar_op == htons(ARPOP_REPLY) &&
+                    (arp->ar_op == htons(ARPOP_REPLY) ||
+                     (arp->ar_op == htons(ARPOP_REQUEST) && tip == sip)) &&
                     inet_addr_type(net, sip) == RTN_UNICAST)
                         n = __neigh_lookup(&arp_tbl, &sip, dev, 1);
         }
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 040c4f05b653..cd71a3908391 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1408,6 +1408,7 @@ static struct devinet_sysctl_table {
                 DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"),
                 DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"),
                 DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"),
+                DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"),
 
                 DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"),
                 DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"),
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 82dbf711d6d0..9b3e28ed5240 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -883,7 +883,7 @@ static void nl_fib_input(struct sk_buff *skb)
         netlink_unicast(net->ipv4.fibnl, skb, pid, MSG_DONTWAIT);
 }
 
-static int nl_fib_lookup_init(struct net *net)
+static int __net_init nl_fib_lookup_init(struct net *net)
 {
         struct sock *sk;
         sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, 0,
@@ -1004,7 +1004,7 @@ fail:
         return err;
 }
 
-static void __net_exit ip_fib_net_exit(struct net *net)
+static void ip_fib_net_exit(struct net *net)
 {
         unsigned int i;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index ed19aa6919c2..96b21011a3e4 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -62,8 +62,8 @@ static DEFINE_SPINLOCK(fib_multipath_lock);
 #define for_nexthops(fi) { int nhsel; const struct fib_nh * nh; \
 for (nhsel=0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++)
 
-#define change_nexthops(fi) { int nhsel; struct fib_nh * nh; \
-for (nhsel=0, nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++)
+#define change_nexthops(fi) { int nhsel; struct fib_nh *nexthop_nh; \
+for (nhsel=0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nexthop_nh++, nhsel++)
 
 #else /* CONFIG_IP_ROUTE_MULTIPATH */
 
@@ -72,7 +72,7 @@ for (nhsel=0, nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++,
 #define for_nexthops(fi) { int nhsel = 0; const struct fib_nh * nh = (fi)->fib_nh; \
 for (nhsel=0; nhsel < 1; nhsel++)
 
-#define change_nexthops(fi) { int nhsel = 0; struct fib_nh * nh = (struct fib_nh *)((fi)->fib_nh); \
+#define change_nexthops(fi) { int nhsel = 0; struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \
 for (nhsel=0; nhsel < 1; nhsel++)
 
 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
@@ -145,9 +145,9 @@ void free_fib_info(struct fib_info *fi)
                 return;
         }
         change_nexthops(fi) {
-                if (nh->nh_dev)
-                        dev_put(nh->nh_dev);
-                nh->nh_dev = NULL;
+                if (nexthop_nh->nh_dev)
+                        dev_put(nexthop_nh->nh_dev);
+                nexthop_nh->nh_dev = NULL;
         } endfor_nexthops(fi);
         fib_info_cnt--;
         release_net(fi->fib_net);
@@ -162,9 +162,9 @@ void fib_release_info(struct fib_info *fi)
                 if (fi->fib_prefsrc)
                         hlist_del(&fi->fib_lhash);
                 change_nexthops(fi) {
-                        if (!nh->nh_dev)
+                        if (!nexthop_nh->nh_dev)
                                 continue;
-                        hlist_del(&nh->nh_hash);
+                        hlist_del(&nexthop_nh->nh_hash);
                 } endfor_nexthops(fi)
                 fi->fib_dead = 1;
                 fib_info_put(fi);
@@ -395,19 +395,20 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
                 if (!rtnh_ok(rtnh, remaining))
                         return -EINVAL;
 
-                nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
-                nh->nh_oif = rtnh->rtnh_ifindex;
-                nh->nh_weight = rtnh->rtnh_hops + 1;
+                nexthop_nh->nh_flags =
+                        (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
+                nexthop_nh->nh_oif = rtnh->rtnh_ifindex;
+                nexthop_nh->nh_weight = rtnh->rtnh_hops + 1;
 
                 attrlen = rtnh_attrlen(rtnh);
                 if (attrlen > 0) {
                         struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 
                         nla = nla_find(attrs, attrlen, RTA_GATEWAY);
-                        nh->nh_gw = nla ? nla_get_be32(nla) : 0;
+                        nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0;
 #ifdef CONFIG_NET_CLS_ROUTE
                         nla = nla_find(attrs, attrlen, RTA_FLOW);
-                        nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
+                        nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
 #endif
                 }
 
@@ -738,7 +739,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 
         fi->fib_nhs = nhs;
         change_nexthops(fi) {
-                nh->nh_parent = fi;
+                nexthop_nh->nh_parent = fi;
         } endfor_nexthops(fi)
 
         if (cfg->fc_mx) {
@@ -808,7 +809,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
                         goto failure;
         } else {
                 change_nexthops(fi) {
-                        if ((err = fib_check_nh(cfg, fi, nh)) != 0)
+                        if ((err = fib_check_nh(cfg, fi, nexthop_nh)) != 0)
                                 goto failure;
                 } endfor_nexthops(fi)
         }
@@ -843,11 +844,11 @@ link_it:
                 struct hlist_head *head;
                 unsigned int hash;
 
-                if (!nh->nh_dev)
+                if (!nexthop_nh->nh_dev)
                         continue;
-                hash = fib_devindex_hashfn(nh->nh_dev->ifindex);
+                hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex);
                 head = &fib_info_devhash[hash];
-                hlist_add_head(&nh->nh_hash, head);
+                hlist_add_head(&nexthop_nh->nh_hash, head);
         } endfor_nexthops(fi)
         spin_unlock_bh(&fib_info_lock);
         return fi;
@@ -1080,21 +1081,21 @@ int fib_sync_down_dev(struct net_device *dev, int force)
                 prev_fi = fi;
                 dead = 0;
                 change_nexthops(fi) {
-                        if (nh->nh_flags&RTNH_F_DEAD)
+                        if (nexthop_nh->nh_flags&RTNH_F_DEAD)
                                 dead++;
-                        else if (nh->nh_dev == dev &&
-                                        nh->nh_scope != scope) {
-                                nh->nh_flags |= RTNH_F_DEAD;
+                        else if (nexthop_nh->nh_dev == dev &&
+                                 nexthop_nh->nh_scope != scope) {
+                                nexthop_nh->nh_flags |= RTNH_F_DEAD;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
                                 spin_lock_bh(&fib_multipath_lock);
-                                fi->fib_power -= nh->nh_power;
-                                nh->nh_power = 0;
+                                fi->fib_power -= nexthop_nh->nh_power;
+                                nexthop_nh->nh_power = 0;
                                 spin_unlock_bh(&fib_multipath_lock);
 #endif
                                 dead++;
                         }
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-                        if (force > 1 && nh->nh_dev == dev) {
+                        if (force > 1 && nexthop_nh->nh_dev == dev) {
                                 dead = fi->fib_nhs;
                                 break;
                         }
@@ -1144,18 +1145,20 @@ int fib_sync_up(struct net_device *dev)
                 prev_fi = fi;
                 alive = 0;
                 change_nexthops(fi) {
-                        if (!(nh->nh_flags&RTNH_F_DEAD)) {
+                        if (!(nexthop_nh->nh_flags&RTNH_F_DEAD)) {
                                 alive++;
                                 continue;
                         }
-                        if (nh->nh_dev == NULL || !(nh->nh_dev->flags&IFF_UP))
+                        if (nexthop_nh->nh_dev == NULL ||
+                            !(nexthop_nh->nh_dev->flags&IFF_UP))
                                 continue;
-                        if (nh->nh_dev != dev || !__in_dev_get_rtnl(dev))
+                        if (nexthop_nh->nh_dev != dev ||
+                            !__in_dev_get_rtnl(dev))
                                 continue;
                         alive++;
                         spin_lock_bh(&fib_multipath_lock);
-                        nh->nh_power = 0;
-                        nh->nh_flags &= ~RTNH_F_DEAD;
+                        nexthop_nh->nh_power = 0;
+                        nexthop_nh->nh_flags &= ~RTNH_F_DEAD;
                         spin_unlock_bh(&fib_multipath_lock);
                 } endfor_nexthops(fi)
 
@@ -1182,9 +1185,9 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res)
         if (fi->fib_power <= 0) {
                 int power = 0;
                 change_nexthops(fi) {
-                        if (!(nh->nh_flags&RTNH_F_DEAD)) {
-                                power += nh->nh_weight;
-                                nh->nh_power = nh->nh_weight;
+                        if (!(nexthop_nh->nh_flags&RTNH_F_DEAD)) {
+                                power += nexthop_nh->nh_weight;
+                                nexthop_nh->nh_power = nexthop_nh->nh_weight;
                         }
                 } endfor_nexthops(fi);
                 fi->fib_power = power;
@@ -1204,9 +1207,10 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res)
         w = jiffies % fi->fib_power;
 
         change_nexthops(fi) {
-                if (!(nh->nh_flags&RTNH_F_DEAD) && nh->nh_power) {
-                        if ((w -= nh->nh_power) <= 0) {
-                                nh->nh_power--;
+                if (!(nexthop_nh->nh_flags&RTNH_F_DEAD) &&
+                    nexthop_nh->nh_power) {
+                        if ((w -= nexthop_nh->nh_power) <= 0) {
+                                nexthop_nh->nh_power--;
                                 fi->fib_power--;
                                 res->nh_sel = nhsel;
                                 spin_unlock_bh(&fib_multipath_lock);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 76c08402c933..8f5468393f01 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2603,7 +2603,7 @@ static const struct file_operations igmp_mcf_seq_fops = {
         .release        =       seq_release_net,
 };
 
-static int igmp_net_init(struct net *net)
+static int __net_init igmp_net_init(struct net *net)
 {
         struct proc_dir_entry *pde;
 
@@ -2621,7 +2621,7 @@ out_igmp:
         return -ENOMEM;
 }
 
-static void igmp_net_exit(struct net *net)
+static void __net_exit igmp_net_exit(struct net *net)
 {
         proc_net_remove(net, "mcfilter");
         proc_net_remove(net, "igmp");
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index ee16475f8fc3..8da6429269dd 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -529,6 +529,8 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
                                 syn_ack_recalc(req, thresh, max_retries,
                                                queue->rskq_defer_accept,
                                                &expire, &resend);
+                                if (req->rsk_ops->syn_ack_timeout)
+                                        req->rsk_ops->syn_ack_timeout(parent, req);
                                 if (!expire &&
                                     (!resend ||
                                      !req->rsk_ops->rtx_syn_ack(parent, req, NULL) ||
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 86964b353c31..891c72aea520 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -646,7 +646,7 @@ static struct ctl_table ip4_frags_ctl_table[] = {
         { }
 };
 
-static int ip4_frags_ns_ctl_register(struct net *net)
+static int __net_init ip4_frags_ns_ctl_register(struct net *net)
 {
         struct ctl_table *table;
         struct ctl_table_header *hdr;
@@ -676,7 +676,7 @@ err_alloc:
         return -ENOMEM;
 }
 
-static void ip4_frags_ns_ctl_unregister(struct net *net)
+static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net)
 {
         struct ctl_table *table;
 
@@ -704,7 +704,7 @@ static inline void ip4_frags_ctl_register(void)
 }
 #endif
 
-static int ipv4_frags_init_net(struct net *net)
+static int __net_init ipv4_frags_init_net(struct net *net)
 {
         /*
          * Fragment cache limits. We will commit 256K at one time. Should we
@@ -726,7 +726,7 @@ static int ipv4_frags_init_net(struct net *net)
         return ip4_frags_ns_ctl_register(net);
 }
 
-static void ipv4_frags_exit_net(struct net *net)
+static void __net_exit ipv4_frags_exit_net(struct net *net)
 {
         ip4_frags_ns_ctl_unregister(net);
         inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f36ce156cac6..7631b20490f5 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1307,7 +1307,7 @@ static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
         }
 }
 
-static int ipgre_init_net(struct net *net)
+static int __net_init ipgre_init_net(struct net *net)
 {
         struct ipgre_net *ign = net_generic(net, ipgre_net_id);
         int err;
@@ -1334,7 +1334,7 @@ err_alloc_dev:
         return err;
 }
 
-static void ipgre_exit_net(struct net *net)
+static void __net_exit ipgre_exit_net(struct net *net)
 {
         struct ipgre_net *ign;
         LIST_HEAD(list);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index cafad9baff03..644dc43a55de 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -451,7 +451,8 @@ static int do_ip_setsockopt(struct sock *sk, int level,
                              (1<<IP_TTL) | (1<<IP_HDRINCL) |
                              (1<<IP_MTU_DISCOVER) | (1<<IP_RECVERR) |
                              (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) |
-                             (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT))) ||
+                             (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) |
+                             (1<<IP_MINTTL))) ||
             optname == IP_MULTICAST_TTL ||
             optname == IP_MULTICAST_ALL ||
             optname == IP_MULTICAST_LOOP ||
@@ -936,6 +937,14 @@ mc_msf_out:
                 inet->transparent = !!val;
                 break;
 
+        case IP_MINTTL:
+                if (optlen < 1)
+                        goto e_inval;
+                if (val < 0 || val > 255)
+                        goto e_inval;
+                inet->min_ttl = val;
+                break;
+
         default:
                 err = -ENOPROTOOPT;
                 break;
@@ -1198,6 +1207,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
         case IP_TRANSPARENT:
                 val = inet->transparent;
                 break;
+        case IP_MINTTL:
+                val = inet->min_ttl;
+                break;
         default:
                 release_sock(sk);
                 return -ENOPROTOOPT;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index eda04fed3379..95db732e542b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -130,7 +130,6 @@ struct ipip_net {
         struct net_device *fb_tunnel_dev;
 };
 
-static void ipip_fb_tunnel_init(struct net_device *dev);
 static void ipip_tunnel_init(struct net_device *dev);
 static void ipip_tunnel_setup(struct net_device *dev);
 
@@ -730,7 +729,7 @@ static void ipip_tunnel_init(struct net_device *dev)
         ipip_tunnel_bind_dev(dev);
 }
 
-static void ipip_fb_tunnel_init(struct net_device *dev)
+static void __net_init ipip_fb_tunnel_init(struct net_device *dev)
 {
         struct ip_tunnel *tunnel = netdev_priv(dev);
         struct iphdr *iph = &tunnel->parms.iph;
@@ -773,7 +772,7 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
         }
 }
 
-static int ipip_init_net(struct net *net)
+static int __net_init ipip_init_net(struct net *net)
 {
         struct ipip_net *ipn = net_generic(net, ipip_net_id);
         int err;
@@ -806,7 +805,7 @@ err_alloc_dev:
         return err;
 }
 
-static void ipip_exit_net(struct net *net)
+static void __net_exit ipip_exit_net(struct net *net)
 {
         struct ipip_net *ipn = net_generic(net, ipip_net_id);
         LIST_HEAD(list);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d62b05d33384..b16dfadbe6d6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1990,8 +1990,13 @@ static int __mkroute_input(struct sk_buff *skb,
         if (skb->protocol != htons(ETH_P_IP)) {
                 /* Not IP (i.e. ARP). Do not create route, if it is
                  * invalid for proxy arp. DNAT routes are always valid.
+                 *
+                 * Proxy arp feature have been extended to allow, ARP
+                 * replies back to the same interface, to support
+                 * Private VLAN switch technologies. See arp.c.
                  */
-                if (out_dev == in_dev) {
+                if (out_dev == in_dev &&
+                    IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) {
                         err = -EINVAL;
                         goto cleanup;
                 }
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 66fd80ef2473..5c24db4a3c91 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -358,7 +358,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 
         tcp_select_initial_window(tcp_full_space(sk), req->mss,
                                   &req->rcv_wnd, &req->window_clamp,
-                                  ireq->wscale_ok, &rcv_wscale);
+                                  ireq->wscale_ok, &rcv_wscale,
+                                  dst_metric(&rt->u.dst, RTAX_INITRWND));
 
         ireq->rcv_wscale  = rcv_wscale;
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b0a26bb25e2e..d5d69ea8f249 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -536,8 +536,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
                 tp->nonagle &= ~TCP_NAGLE_PUSH;
 }
 
-static inline void tcp_mark_urg(struct tcp_sock *tp, int flags,
-                                struct sk_buff *skb)
+static inline void tcp_mark_urg(struct tcp_sock *tp, int flags)
 {
         if (flags & MSG_OOB)
                 tp->snd_up = tp->write_seq;
@@ -546,13 +545,13 @@ static inline void tcp_mark_urg(struct tcp_sock *tp, int flags,
 static inline void tcp_push(struct sock *sk, int flags, int mss_now,
                             int nonagle)
 {
-        struct tcp_sock *tp = tcp_sk(sk);
-
         if (tcp_send_head(sk)) {
-                struct sk_buff *skb = tcp_write_queue_tail(sk);
+                struct tcp_sock *tp = tcp_sk(sk);
+
                 if (!(flags & MSG_MORE) || forced_push(tp))
-                        tcp_mark_push(tp, skb);
-                tcp_mark_urg(tp, flags, skb);
+                        tcp_mark_push(tp, tcp_write_queue_tail(sk));
+
+                tcp_mark_urg(tp, flags);
                 __tcp_push_pending_frames(sk, mss_now,
                                           (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle);
         }
@@ -877,12 +876,12 @@ ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset,
 #define TCP_PAGE(sk)    (sk->sk_sndmsg_page)
 #define TCP_OFF(sk)     (sk->sk_sndmsg_off)
 
-static inline int select_size(struct sock *sk)
+static inline int select_size(struct sock *sk, int sg)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         int tmp = tp->mss_cache;
 
-        if (sk->sk_route_caps & NETIF_F_SG) {
+        if (sg) {
                 if (sk_can_gso(sk))
                         tmp = 0;
                 else {
@@ -906,7 +905,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
         struct sk_buff *skb;
         int iovlen, flags;
         int mss_now, size_goal;
-        int err, copied;
+        int sg, err, copied;
         long timeo;
 
         lock_sock(sk);
@@ -934,6 +933,8 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
         if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
                 goto out_err;
 
+        sg = sk->sk_route_caps & NETIF_F_SG;
+
         while (--iovlen >= 0) {
                 int seglen = iov->iov_len;
                 unsigned char __user *from = iov->iov_base;
@@ -959,8 +960,9 @@ new_segment:
                                 if (!sk_stream_memory_free(sk))
                                         goto wait_for_sndbuf;
 
-                                skb = sk_stream_alloc_skb(sk, select_size(sk),
-                                                sk->sk_allocation);
+                                skb = sk_stream_alloc_skb(sk,
+                                                          select_size(sk, sg),
+                                                          sk->sk_allocation);
                                 if (!skb)
                                         goto wait_for_memory;
 
@@ -997,9 +999,7 @@ new_segment:
                                         /* We can extend the last page
                                          * fragment. */
                                         merge = 1;
-                                } else if (i == MAX_SKB_FRAGS ||
-                                           (!i &&
-                                           !(sk->sk_route_caps & NETIF_F_SG))) {
+                                } else if (i == MAX_SKB_FRAGS || !sg) {
                                         /* Need to add new fragment and cannot
                                          * do this because interface is non-SG,
                                          * or because all the page slots are
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 65b8ebfd078a..c3588b4fd979 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -742,9 +742,9 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
  *      This still operates on a request_sock only, not on a big
  *      socket.
  */
-static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
-                                struct request_sock *req,
-                                struct request_values *rvp)
+static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
+                              struct request_sock *req,
+                              struct request_values *rvp)
 {
         const struct inet_request_sock *ireq = inet_rsk(req);
         int err = -1;
@@ -775,10 +775,11 @@ static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
         return err;
 }
 
-static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
+static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req,
                               struct request_values *rvp)
 {
-        return __tcp_v4_send_synack(sk, NULL, req, rvp);
+        TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+        return tcp_v4_send_synack(sk, NULL, req, rvp);
 }
 
 /*
@@ -1192,10 +1193,11 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb)
 struct request_sock_ops tcp_request_sock_ops __read_mostly = {
         .family         =       PF_INET,
         .obj_size       =       sizeof(struct tcp_request_sock),
-        .rtx_syn_ack    =       tcp_v4_send_synack,
+        .rtx_syn_ack    =       tcp_v4_rtx_synack,
         .send_ack       =       tcp_v4_reqsk_send_ack,
         .destructor     =       tcp_v4_reqsk_destructor,
         .send_reset     =       tcp_v4_send_reset,
+        .syn_ack_timeout =      tcp_syn_ack_timeout,
 };
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1373,8 +1375,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
         }
         tcp_rsk(req)->snt_isn = isn;
 
-        if (__tcp_v4_send_synack(sk, dst, req,
-                                 (struct request_values *)&tmp_ext) ||
+        if (tcp_v4_send_synack(sk, dst, req,
+                               (struct request_values *)&tmp_ext) ||
             want_cookie)
                 goto drop_and_free;
 
@@ -1649,6 +1651,9 @@ int tcp_v4_rcv(struct sk_buff *skb)
         if (!sk)
                 goto no_tcp_socket;
 
+        if (iph->ttl < inet_sk(sk)->min_ttl)
+                goto discard_and_relse;
+
 process:
         if (sk->sk_state == TCP_TIME_WAIT)
                 goto do_time_wait;
@@ -2425,12 +2430,12 @@ static struct tcp_seq_afinfo tcp4_seq_afinfo = {
         },
 };
 
-static int tcp4_proc_init_net(struct net *net)
+static int __net_init tcp4_proc_init_net(struct net *net)
 {
         return tcp_proc_register(net, &tcp4_seq_afinfo);
 }
 
-static void tcp4_proc_exit_net(struct net *net)
+static void __net_exit tcp4_proc_exit_net(struct net *net)
 {
         tcp_proc_unregister(net, &tcp4_seq_afinfo);
 }
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 383ce237640f..4a1605d3f909 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -183,7 +183,8 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
  */
 void tcp_select_initial_window(int __space, __u32 mss,
                                __u32 *rcv_wnd, __u32 *window_clamp,
-                               int wscale_ok, __u8 *rcv_wscale)
+                               int wscale_ok, __u8 *rcv_wscale,
+                               __u32 init_rcv_wnd)
 {
         unsigned int space = (__space < 0 ? 0 : __space);
 
@@ -232,7 +233,13 @@ void tcp_select_initial_window(int __space, __u32 mss,
                         init_cwnd = 2;
                 else if (mss > 1460)
                         init_cwnd = 3;
-                if (*rcv_wnd > init_cwnd * mss)
+                /* when initializing use the value from init_rcv_wnd
+                 * rather than the default from above
+                 */
+                if (init_rcv_wnd &&
+                    (*rcv_wnd > init_rcv_wnd * mss))
+                        *rcv_wnd = init_rcv_wnd * mss;
+                else if (*rcv_wnd > init_cwnd * mss)
                         *rcv_wnd = init_cwnd * mss;
         }
 
@@ -1794,11 +1801,6 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
                                int nonagle)
 {
-        struct sk_buff *skb = tcp_send_head(sk);
-
-        if (!skb)
-                return;
-
         /* If we are closed, the bytes will have to remain here.
          * In time closedown will finish, we empty the write queue and
          * all will be happy.
@@ -2422,7 +2424,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
                         &req->rcv_wnd,
                         &req->window_clamp,
                         ireq->wscale_ok,
-                        &rcv_wscale);
+                        &rcv_wscale,
+                        dst_metric(dst, RTAX_INITRWND));
                 ireq->rcv_wscale = rcv_wscale;
         }
 
@@ -2549,7 +2552,8 @@ static void tcp_connect_init(struct sock *sk)
                                   &tp->rcv_wnd,
                                   &tp->window_clamp,
                                   sysctl_tcp_window_scaling,
-                                  &rcv_wscale);
+                                  &rcv_wscale,
+                                  dst_metric(dst, RTAX_INITRWND));
 
         tp->rx_opt.rcv_wscale = rcv_wscale;
         tp->rcv_ssthresh = tp->rcv_wnd;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 8816a20c2597..de7d1bf9114f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -474,6 +474,12 @@ static void tcp_synack_timer(struct sock *sk)
                                    TCP_TIMEOUT_INIT, TCP_RTO_MAX);
 }
 
+void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req)
+{
+        NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEOUTS);
+}
+EXPORT_SYMBOL(tcp_syn_ack_timeout);
+
 void tcp_set_keepalive(struct sock *sk, int val)
 {
         if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f0126fdd7e04..4f7d2122d818 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2027,12 +2027,12 @@ static struct udp_seq_afinfo udp4_seq_afinfo = {
         },
 };
 
-static int udp4_proc_init_net(struct net *net)
+static int __net_init udp4_proc_init_net(struct net *net)
 {
         return udp_proc_register(net, &udp4_seq_afinfo);
 }
 
-static void udp4_proc_exit_net(struct net *net)
+static void __net_exit udp4_proc_exit_net(struct net *net)
 {
         udp_proc_unregister(net, &udp4_seq_afinfo);
 }
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 66f79513f4a5..6610bf76369f 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -81,12 +81,12 @@ static struct udp_seq_afinfo udplite4_seq_afinfo = {
         },
 };
 
-static int udplite4_proc_init_net(struct net *net)
+static int __net_init udplite4_proc_init_net(struct net *net)
 {
         return udp_proc_register(net, &udplite4_seq_afinfo);
 }
 
-static void udplite4_proc_exit_net(struct net *net)
+static void __net_exit udplite4_proc_exit_net(struct net *net)
 {
         udp_proc_unregister(net, &udplite4_seq_afinfo);
 }