45 files changed, 529 insertions, 309 deletions

diff --git a/net/802/tr.c b/net/802/tr.c
index 158150fee462..f47ae289d83b 100644
--- a/net/802/tr.c
+++ b/net/802/tr.c
@@ -668,3 +668,5 @@ module_init(rif_init);
 
 EXPORT_SYMBOL(tr_type_trans);
 EXPORT_SYMBOL(alloc_trdev);
+
+MODULE_LICENSE("GPL");
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index e9db889d6222..2886d2fb9ab5 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -1,12 +1,16 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
+#include <linux/netpoll.h>
 #include "vlan.h"
 
 /* VLAN rx hw acceleration helper.  This acts like netif_{rx,receive_skb}(). */
 int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
                       u16 vlan_tci, int polling)
 {
+        if (netpoll_rx(skb))
+                return NET_RX_DROP;
+
         if (skb_bond_should_drop(skb))
                 goto drop;
 
@@ -100,6 +104,9 @@ int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
 {
         int err = NET_RX_SUCCESS;
 
+        if (netpoll_receive_skb(skb))
+                return NET_RX_DROP;
+
         switch (vlan_gro_common(napi, grp, vlan_tci, skb)) {
         case -1:
                 return netif_receive_skb(skb);
@@ -126,6 +133,9 @@ int vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
         if (!skb)
                 goto out;
 
+        if (netpoll_receive_skb(skb))
+                goto out;
+
         err = NET_RX_SUCCESS;
 
         switch (vlan_gro_common(napi, grp, vlan_tci, skb)) {
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 4a19acd3a32b..1b34135cf990 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -553,7 +553,7 @@ static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa)
         int err = 0;
 
         if (netif_device_present(real_dev) && ops->ndo_neigh_setup)
-                err = ops->ndo_neigh_setup(dev, pa);
+                err = ops->ndo_neigh_setup(real_dev, pa);
 
         return err;
 }
@@ -639,6 +639,7 @@ static int vlan_dev_init(struct net_device *dev)
                 dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN;
                 dev->netdev_ops         = &vlan_netdev_ops;
         }
+        netdev_resync_ops(dev);
 
         if (is_vlan_dev(real_dev))
                 subclass = 1;
diff --git a/net/core/dev.c b/net/core/dev.c
index a17e00662363..e3fe5c705606 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2267,12 +2267,6 @@ int netif_receive_skb(struct sk_buff *skb)
 
         rcu_read_lock();
 
-        /* Don't receive packets in an exiting network namespace */
-        if (!net_alive(dev_net(skb->dev))) {
-                kfree_skb(skb);
-                goto out;
-        }
-
 #ifdef CONFIG_NET_CLS_ACT
         if (skb->tc_verd & TC_NCLS) {
                 skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
@@ -2488,6 +2482,9 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 
 int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
+        if (netpoll_receive_skb(skb))
+                return NET_RX_DROP;
+
         switch (__napi_gro_receive(napi, skb)) {
         case -1:
                 return netif_receive_skb(skb);
@@ -2558,6 +2555,9 @@ int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info)
         if (!skb)
                 goto out;
 
+        if (netpoll_receive_skb(skb))
+                goto out;
+
         err = NET_RX_SUCCESS;
 
         switch (__napi_gro_receive(napi, skb)) {
@@ -2588,9 +2588,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
                 local_irq_disable();
                 skb = __skb_dequeue(&queue->input_pkt_queue);
                 if (!skb) {
-                        __napi_complete(napi);
                         local_irq_enable();
-                        break;
+                        napi_complete(napi);
+                        goto out;
                 }
                 local_irq_enable();
 
@@ -2599,6 +2599,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
 
         napi_gro_flush(napi);
 
+out:
         return work;
 }
 
@@ -2671,7 +2672,7 @@ void netif_napi_del(struct napi_struct *napi)
         struct sk_buff *skb, *next;
 
         list_del_init(&napi->dev_list);
-        kfree(napi->skb);
+        kfree_skb(napi->skb);
 
         for (skb = napi->gro_list; skb; skb = next) {
                 next = skb->next;
@@ -4282,6 +4283,39 @@ unsigned long netdev_fix_features(unsigned long features, const char *name)
 }
 EXPORT_SYMBOL(netdev_fix_features);
 
+/* Some devices need to (re-)set their netdev_ops inside
+ * ->init() or similar.  If that happens, we have to setup
+ * the compat pointers again.
+ */
+void netdev_resync_ops(struct net_device *dev)
+{
+#ifdef CONFIG_COMPAT_NET_DEV_OPS
+        const struct net_device_ops *ops = dev->netdev_ops;
+
+        dev->init = ops->ndo_init;
+        dev->uninit = ops->ndo_uninit;
+        dev->open = ops->ndo_open;
+        dev->change_rx_flags = ops->ndo_change_rx_flags;
+        dev->set_rx_mode = ops->ndo_set_rx_mode;
+        dev->set_multicast_list = ops->ndo_set_multicast_list;
+        dev->set_mac_address = ops->ndo_set_mac_address;
+        dev->validate_addr = ops->ndo_validate_addr;
+        dev->do_ioctl = ops->ndo_do_ioctl;
+        dev->set_config = ops->ndo_set_config;
+        dev->change_mtu = ops->ndo_change_mtu;
+        dev->neigh_setup = ops->ndo_neigh_setup;
+        dev->tx_timeout = ops->ndo_tx_timeout;
+        dev->get_stats = ops->ndo_get_stats;
+        dev->vlan_rx_register = ops->ndo_vlan_rx_register;
+        dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid;
+        dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid;
+#ifdef CONFIG_NET_POLL_CONTROLLER
+        dev->poll_controller = ops->ndo_poll_controller;
+#endif
+#endif
+}
+EXPORT_SYMBOL(netdev_resync_ops);
+
 /**
  *      register_netdevice      - register a network device
  *      @dev: device to register
@@ -4326,27 +4360,7 @@ int register_netdevice(struct net_device *dev)
          * This is temporary until all network devices are converted.
          */
         if (dev->netdev_ops) {
-                const struct net_device_ops *ops = dev->netdev_ops;
-
-                dev->init = ops->ndo_init;
-                dev->uninit = ops->ndo_uninit;
-                dev->open = ops->ndo_open;
-                dev->change_rx_flags = ops->ndo_change_rx_flags;
-                dev->set_rx_mode = ops->ndo_set_rx_mode;
-                dev->set_multicast_list = ops->ndo_set_multicast_list;
-                dev->set_mac_address = ops->ndo_set_mac_address;
-                dev->validate_addr = ops->ndo_validate_addr;
-                dev->do_ioctl = ops->ndo_do_ioctl;
-                dev->set_config = ops->ndo_set_config;
-                dev->change_mtu = ops->ndo_change_mtu;
-                dev->tx_timeout = ops->ndo_tx_timeout;
-                dev->get_stats = ops->ndo_get_stats;
-                dev->vlan_rx_register = ops->ndo_vlan_rx_register;
-                dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid;
-                dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid;
-#ifdef CONFIG_NET_POLL_CONTROLLER
-                dev->poll_controller = ops->ndo_poll_controller;
-#endif
+                netdev_resync_ops(dev);
         } else {
                 char drivername[64];
                 pr_info("%s (%s): not using net_device_ops yet\n",
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 6ac29a46e23e..484f58750eba 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -77,7 +77,9 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
         if (endp == buf)
                 goto err;
 
-        rtnl_lock();
+        if (!rtnl_trylock())
+                return -ERESTARTSYS;
+
         if (dev_isalive(net)) {
                 if ((ret = (*set)(net, new)) == 0)
                         ret = len;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 55151faaf90c..e3bebd36f053 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -32,24 +32,14 @@ static __net_init int setup_net(struct net *net)
 {
         /* Must be called with net_mutex held */
         struct pernet_operations *ops;
-        int error;
-        struct net_generic *ng;
+        int error = 0;
 
         atomic_set(&net->count, 1);
+
 #ifdef NETNS_REFCNT_DEBUG
         atomic_set(&net->use_count, 0);
 #endif
 
-        error = -ENOMEM;
-        ng = kzalloc(sizeof(struct net_generic) +
-                        INITIAL_NET_GEN_PTRS * sizeof(void *), GFP_KERNEL);
-        if (ng == NULL)
-                goto out;
-
-        ng->len = INITIAL_NET_GEN_PTRS;
-        rcu_assign_pointer(net->gen, ng);
-
-        error = 0;
         list_for_each_entry(ops, &pernet_list, list) {
                 if (ops->init) {
                         error = ops->init(net);
@@ -70,24 +60,50 @@ out_undo:
         }
 
         rcu_barrier();
-        kfree(ng);
         goto out;
 }
 
+static struct net_generic *net_alloc_generic(void)
+{
+        struct net_generic *ng;
+        size_t generic_size = sizeof(struct net_generic) +
+                INITIAL_NET_GEN_PTRS * sizeof(void *);
+
+        ng = kzalloc(generic_size, GFP_KERNEL);
+        if (ng)
+                ng->len = INITIAL_NET_GEN_PTRS;
+
+        return ng;
+}
+
 #ifdef CONFIG_NET_NS
 static struct kmem_cache *net_cachep;
 static struct workqueue_struct *netns_wq;
 
 static struct net *net_alloc(void)
 {
-        return kmem_cache_zalloc(net_cachep, GFP_KERNEL);
+        struct net *net = NULL;
+        struct net_generic *ng;
+
+        ng = net_alloc_generic();
+        if (!ng)
+                goto out;
+
+        net = kmem_cache_zalloc(net_cachep, GFP_KERNEL);
+        if (!net)
+                goto out_free;
+
+        rcu_assign_pointer(net->gen, ng);
+out:
+        return net;
+
+out_free:
+        kfree(ng);
+        goto out;
 }
 
 static void net_free(struct net *net)
 {
-        if (!net)
-                return;
-
 #ifdef NETNS_REFCNT_DEBUG
         if (unlikely(atomic_read(&net->use_count) != 0)) {
                 printk(KERN_EMERG "network namespace not free! Usage: %d\n",
@@ -112,27 +128,28 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
         err = -ENOMEM;
         new_net = net_alloc();
         if (!new_net)
-                goto out;
+                goto out_err;
 
         mutex_lock(&net_mutex);
         err = setup_net(new_net);
-        if (err)
-                goto out_unlock;
-
-        rtnl_lock();
-        list_add_tail(&new_net->list, &net_namespace_list);
-        rtnl_unlock();
-
-
-out_unlock:
+        if (!err) {
+                rtnl_lock();
+                list_add_tail(&new_net->list, &net_namespace_list);
+                rtnl_unlock();
+        }
         mutex_unlock(&net_mutex);
+
+        if (err)
+                goto out_free;
 out:
         put_net(old_net);
-        if (err) {
-                net_free(new_net);
-                new_net = ERR_PTR(err);
-        }
         return new_net;
+
+out_free:
+        net_free(new_net);
+out_err:
+        new_net = ERR_PTR(err);
+        goto out;
 }
 
 static void cleanup_net(struct work_struct *work)
@@ -140,9 +157,6 @@ static void cleanup_net(struct work_struct *work)
         struct pernet_operations *ops;
         struct net *net;
 
-        /* Be very certain incoming network packets will not find us */
-        rcu_barrier();
-
         net = container_of(work, struct net, work);
 
         mutex_lock(&net_mutex);
@@ -188,6 +202,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 
 static int __init net_ns_init(void)
 {
+        struct net_generic *ng;
         int err;
 
         printk(KERN_INFO "net_namespace: %zd bytes\n", sizeof(struct net));
@@ -202,6 +217,12 @@ static int __init net_ns_init(void)
                 panic("Could not create netns workq");
 #endif
 
+        ng = net_alloc_generic();
+        if (!ng)
+                panic("Could not allocate generic netns");
+
+        rcu_assign_pointer(init_net.gen, ng);
+
         mutex_lock(&net_mutex);
         err = setup_net(&init_net);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index da74b844f4ea..c6a6b166f8d6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -143,14 +143,6 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here)
         BUG();
 }
 
-void skb_truesize_bug(struct sk_buff *skb)
-{
-        WARN(net_ratelimit(), KERN_ERR "SKB BUG: Invalid truesize (%u) "
-               "len=%u, sizeof(sk_buff)=%Zd\n",
-               skb->truesize, skb->len, sizeof(struct sk_buff));
-}
-EXPORT_SYMBOL(skb_truesize_bug);
-
 /*      Allocate a new skbuff. We do this ourselves so we can fill in a few
  *      'private' fields and also do memory statistics to find all the
  *      [BEEP] leaks.
diff --git a/net/core/sock.c b/net/core/sock.c
index 6f2e1337975d..5f97caa158e8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -696,7 +696,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
         if (len < 0)
                 return -EINVAL;
 
-        v.val = 0;
+        memset(&v, 0, sizeof(v));
 
         switch(optname) {
         case SO_DEBUG:
@@ -1137,7 +1137,6 @@ void sock_rfree(struct sk_buff *skb)
 {
         struct sock *sk = skb->sk;
 
-        skb_truesize_check(skb);
         atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
         sk_mem_uncharge(skb->sk, skb->truesize);
 }
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 6bb2635b5ded..7bc992976d29 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -3,11 +3,16 @@
  *
  * This is an implementation of the CIPSO 2.2 protocol as specified in
  * draft-ietf-cipso-ipsecurity-01.txt with additional tag types as found in
- * FIPS-188, copies of both documents can be found in the Documentation
- * directory.  While CIPSO never became a full IETF RFC standard many vendors
+ * FIPS-188.  While CIPSO never became a full IETF RFC standard many vendors
  * have chosen to adopt the protocol and over the years it has become a
  * de-facto standard for labeled networking.
  *
+ * The CIPSO draft specification can be found in the kernel's Documentation
+ * directory as well as the following URL:
+ *   http://netlabel.sourceforge.net/files/draft-ietf-cipso-ipsecurity-01.txt
+ * The FIPS-188 specification can be found at the following URL:
+ *   http://www.itl.nist.gov/fipspubs/fip188.htm
+ *
  * Author: Paul Moore <paul.moore@hp.com>
  *
  */
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 705b33b184a3..fc562d29cc46 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1205,7 +1205,7 @@ static struct pernet_operations __net_initdata icmp_sk_ops = {
 
 int __init icmp_init(void)
 {
-        return register_pernet_device(&icmp_sk_ops);
+        return register_pernet_subsys(&icmp_sk_ops);
 }
 
 EXPORT_SYMBOL(icmp_err_convert);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 6659ac000eeb..7985346653bd 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -463,6 +463,7 @@ err:
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
                          struct net_device *dev)
 {
+        struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
         struct iphdr *iph;
         struct sk_buff *fp, *head = qp->q.fragments;
         int len;
@@ -548,7 +549,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
         iph = ip_hdr(head);
         iph->frag_off = 0;
         iph->tot_len = htons(len);
-        IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_REASMOKS);
+        IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
         qp->q.fragments = NULL;
         return 0;
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a6961d75c7ea..c28976a7e596 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1374,7 +1374,8 @@ static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
 
 static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
                            struct tcp_sacktag_state *state,
-                           unsigned int pcount, int shifted, int mss)
+                           unsigned int pcount, int shifted, int mss,
+                           int dup_sack)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
@@ -1410,7 +1411,7 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
         }
 
         /* We discard results */
-        tcp_sacktag_one(skb, sk, state, 0, pcount);
+        tcp_sacktag_one(skb, sk, state, dup_sack, pcount);
 
         /* Difference in this won't matter, both ACKed by the same cumul. ACK */
         TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);
@@ -1561,7 +1562,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 
         if (!skb_shift(prev, skb, len))
                 goto fallback;
-        if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss))
+        if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
                 goto out;
 
         /* Hole filled allows collapsing with the next as well, this is very
@@ -1580,7 +1581,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
         len = skb->len;
         if (skb_shift(prev, skb, len)) {
                 pcount += tcp_skb_pcount(skb);
-                tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss);
+                tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
         }
 
 out:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 19d7b429a262..cf74c416831a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2443,7 +2443,7 @@ static struct pernet_operations __net_initdata tcp_sk_ops = {
 void __init tcp_v4_init(void)
 {
         inet_hashinfo_init(&tcp_hashinfo);
-        if (register_pernet_device(&tcp_sk_ops))
+        if (register_pernet_subsys(&tcp_sk_ops))
                 panic("Failed to create the TCP control socket.\n");
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index dda42f0bd7a3..da2c3b8794f2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2023,7 +2023,6 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
                 last_lost = tp->snd_una;
         }
 
-        /* First pass: retransmit lost packets. */
         tcp_for_write_queue_from(skb, sk) {
                 __u8 sacked = TCP_SKB_CB(skb)->sacked;
 
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 2747ec7bfb63..4660b088a8ce 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -1,6 +1,6 @@
 /* Tom Kelly's Scalable TCP
  *
- * See htt://www-lce.eng.cam.ac.uk/~ctk21/scalable/
+ * See http://www.deneholme.net/tom/scalable/
  *
  * John Heffner <jheffner@sc.edu>
  */
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f9afb452249c..1220e2c7831e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -493,15 +493,17 @@ static void addrconf_forward_change(struct net *net, __s32 newf)
         read_unlock(&dev_base_lock);
 }
 
-static void addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
+static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
 {
         struct net *net;
 
         net = (struct net *)table->extra2;
         if (p == &net->ipv6.devconf_dflt->forwarding)
-                return;
+                return 0;
+
+        if (!rtnl_trylock())
+                return -ERESTARTSYS;
 
-        rtnl_lock();
         if (p == &net->ipv6.devconf_all->forwarding) {
                 __s32 newf = net->ipv6.devconf_all->forwarding;
                 net->ipv6.devconf_dflt->forwarding = newf;
@@ -512,6 +514,7 @@ static void addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
 
         if (*p)
                 rt6_purge_dflt_routers(net);
+        return 1;
 }
 #endif
 
@@ -2608,9 +2611,6 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 
         ASSERT_RTNL();
 
-        if ((dev->flags & IFF_LOOPBACK) && how == 1)
-                how = 0;
-
         rt6_ifdown(net, dev);
         neigh_ifdown(&nd_tbl, dev);
 
@@ -3983,7 +3983,7 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write, struct file * filp,
         ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
 
         if (write)
-                addrconf_fixup_forwarding(ctl, valp, val);
+                ret = addrconf_fixup_forwarding(ctl, valp, val);
         return ret;
 }
 
@@ -4019,8 +4019,7 @@ static int addrconf_sysctl_forward_strategy(ctl_table *table,
         }
 
         *valp = new;
-        addrconf_fixup_forwarding(table, valp, val);
-        return 1;
+        return addrconf_fixup_forwarding(table, valp, val);
 }
 
 static struct addrconf_sysctl_table
@@ -4446,25 +4445,6 @@ int unregister_inet6addr_notifier(struct notifier_block *nb)
 
 EXPORT_SYMBOL(unregister_inet6addr_notifier);
 
-static void addrconf_net_exit(struct net *net)
-{
-        struct net_device *dev;
-
-        rtnl_lock();
-        /* clean dev list */
-        for_each_netdev(net, dev) {
-                if (__in6_dev_get(dev) == NULL)
-                        continue;
-                addrconf_ifdown(dev, 1);
-        }
-        addrconf_ifdown(net->loopback_dev, 2);
-        rtnl_unlock();
-}
-
-static struct pernet_operations addrconf_net_ops = {
-        .exit = addrconf_net_exit,
-};
-
 /*
  *      Init / cleanup code
  */
@@ -4506,10 +4486,6 @@ int __init addrconf_init(void)
         if (err)
                 goto errlo;
 
-        err = register_pernet_device(&addrconf_net_ops);
-        if (err)
-                return err;
-
         register_netdevice_notifier(&ipv6_dev_notf);
 
         addrconf_verify(0);
@@ -4539,15 +4515,22 @@ errlo:
 void addrconf_cleanup(void)
 {
         struct inet6_ifaddr *ifa;
+        struct net_device *dev;
         int i;
 
         unregister_netdevice_notifier(&ipv6_dev_notf);
-        unregister_pernet_device(&addrconf_net_ops);
-
         unregister_pernet_subsys(&addrconf_ops);
 
         rtnl_lock();
 
+        /* clean dev list */
+        for_each_netdev(&init_net, dev) {
+                if (__in6_dev_get(dev) == NULL)
+                        continue;
+                addrconf_ifdown(dev, 1);
+        }
+        addrconf_ifdown(init_net.loopback_dev, 2);
+
         /*
          *      Check hash table.
          */
@@ -4568,6 +4551,4 @@ void addrconf_cleanup(void)
 
         del_timer(&addr_chk_timer);
         rtnl_unlock();
-
-        unregister_pernet_subsys(&addrconf_net_ops);
 }
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c802bc1658a8..9c8309ed35cf 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -72,6 +72,10 @@ MODULE_LICENSE("GPL");
 static struct list_head inetsw6[SOCK_MAX];
 static DEFINE_SPINLOCK(inetsw6_lock);
 
+static int disable_ipv6 = 0;
+module_param_named(disable, disable_ipv6, int, 0);
+MODULE_PARM_DESC(disable, "Disable IPv6 such that it is non-functional");
+
 static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
 {
         const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
@@ -991,10 +995,21 @@ static int __init inet6_init(void)
 {
         struct sk_buff *dummy_skb;
         struct list_head *r;
-        int err;
+        int err = 0;
 
         BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb));
 
+        /* Register the socket-side information for inet6_create.  */
+        for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r)
+                INIT_LIST_HEAD(r);
+
+        if (disable_ipv6) {
+                printk(KERN_INFO
+                       "IPv6: Loaded, but administratively disabled, "
+                       "reboot required to enable\n");
+                goto out;
+        }
+
         err = proto_register(&tcpv6_prot, 1);
         if (err)
                 goto out;
@@ -1012,10 +1027,6 @@ static int __init inet6_init(void)
                 goto out_unregister_udplite_proto;
 
 
-        /* Register the socket-side information for inet6_create.  */
-        for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r)
-                INIT_LIST_HEAD(r);
-
         /* We MUST register RAW sockets before we create the ICMP6,
          * IGMP6, or NDISC control sockets.
          */
@@ -1181,6 +1192,9 @@ module_init(inet6_init);
 
 static void __exit inet6_exit(void)
 {
+        if (disable_ipv6)
+                return;
+
         /* First of all disallow new sockets creation. */
         sock_unregister(PF_INET6);
         /* Disallow any further netlink messages */
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 8fe267feb81e..1bcc3431859e 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -258,11 +258,11 @@ unique:
 
         if (twp != NULL) {
                 *twp = tw;
-                NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITRECYCLED);
+                NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED);
         } else if (tw != NULL) {
                 /* Silly. Should hash-dance instead... */
                 inet_twsk_deschedule(tw, death_row);
-                NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITRECYCLED);
+                NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED);
 
                 inet_twsk_put(tw);
         }
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index c323643ffcf9..72dbb6d1a6b3 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -201,8 +201,9 @@ icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff,
 
         if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
             nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) {
-                nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
-                              "nf_ct_icmpv6: ICMPv6 checksum failed\n");
+                if (LOG_INVALID(net, IPPROTO_ICMPV6))
+                        nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
+                                      "nf_ct_icmpv6: ICMPv6 checksum failed ");
                 return -NF_ACCEPT;
         }
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index ed4d79a9e4a6..058a5e4a60c3 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -528,14 +528,14 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
                 if (!ipv6_ext_hdr(nexthdr)) {
                         return -1;
                 }
-                if (len < (int)sizeof(struct ipv6_opt_hdr)) {
-                        pr_debug("too short\n");
-                        return -1;
-                }
                 if (nexthdr == NEXTHDR_NONE) {
                         pr_debug("next header is none\n");
                         return -1;
                 }
+                if (len < (int)sizeof(struct ipv6_opt_hdr)) {
+                        pr_debug("too short\n");
+                        return -1;
+                }
                 if (skb_copy_bits(skb, start, &hdr, sizeof(hdr)))
                         BUG();
                 if (nexthdr == NEXTHDR_AUTH)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 3c575118fca5..e9ac7a12f595 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -452,6 +452,7 @@ err:
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
                           struct net_device *dev)
 {
+        struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
         struct sk_buff *fp, *head = fq->q.fragments;
         int    payload_len;
         unsigned int nhoff;
@@ -551,8 +552,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
                                           head->csum);
 
         rcu_read_lock();
-        IP6_INC_STATS_BH(dev_net(dev),
-                         __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
+        IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
         rcu_read_unlock();
         fq->q.fragments = NULL;
         return 1;
@@ -566,8 +566,7 @@ out_oom:
                 printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
 out_fail:
         rcu_read_lock();
-        IP6_INC_STATS_BH(dev_net(dev),
-                         __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+        IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
         rcu_read_unlock();
         return -1;
 }
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index d3467e563f02..5cee2bcbcece 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -188,9 +188,9 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
         }
 
         nt = netdev_priv(dev);
-        ipip6_tunnel_init(dev);
 
         nt->parms = *parms;
+        ipip6_tunnel_init(dev);
 
         if (parms->i_flags & SIT_ISATAP)
                 dev->priv_flags |= IFF_ISATAP;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 94de5033f0b6..37e3d5ef7e3f 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -752,6 +752,8 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx)
                 skb_copy_queue_mapping(frag, first);
 
                 frag->do_not_encrypt = first->do_not_encrypt;
+                frag->dev = first->dev;
+                frag->iif = first->iif;
 
                 pos += copylen;
                 left -= copylen;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 90ce9ddb9451..f4935e344b61 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -726,7 +726,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
         NF_CT_ASSERT(skb->nfct);
 
         ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum);
-        if (ret < 0) {
+        if (ret <= 0) {
                 /* Invalid: inverse of the return code tells
                  * the netfilter core what to do */
                 pr_debug("nf_conntrack_in: Can't track with proto module\n");
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index cb78aa00399e..ed6d873ad384 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1780,6 +1780,7 @@ ctnetlink_create_expect(struct nlattr *cda[], u_int8_t u3, u32 pid, int report)
                 goto out;
         }
 
+        exp->class = 0;
         exp->expectfn = NULL;
         exp->flags = 0;
         exp->master = ct;
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index a1edb9c1adee..f3fd154d1ddd 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -859,7 +859,7 @@ static int tcp_packet(struct nf_conn *ct,
                          */
                         if (nf_ct_kill(ct))
                                 return -NF_REPEAT;
-                        return -NF_DROP;
+                        return NF_DROP;
                 }
                 /* Fall through */
         case TCP_CONNTRACK_IGNORE:
@@ -892,7 +892,7 @@ static int tcp_packet(struct nf_conn *ct,
                                 nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
                                           "nf_ct_tcp: killing out of sync session ");
                         nf_ct_kill(ct);
-                        return -NF_DROP;
+                        return NF_DROP;
                 }
                 ct->proto.tcp.last_index = index;
                 ct->proto.tcp.last_dir = dir;
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index fa49dc7fe100..c712e9fc6bba 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -39,7 +39,7 @@
 #endif
 
 #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE
-#define NFULNL_TIMEOUT_DEFAULT  HZ      /* every second */
+#define NFULNL_TIMEOUT_DEFAULT  100     /* every second */
 #define NFULNL_QTHRESH_DEFAULT  100     /* 100 packets */
 #define NFULNL_COPY_RANGE_MAX   0xFFFF  /* max packet size is limited by 16-bit struct nfattr nfa_len field */
 
@@ -590,8 +590,10 @@ nfulnl_log_packet(u_int8_t pf,
 
         qthreshold = inst->qthreshold;
         /* per-rule qthreshold overrides per-instance */
-        if (qthreshold > li->u.ulog.qthreshold)
-                qthreshold = li->u.ulog.qthreshold;
+        if (li->u.ulog.qthreshold)
+                if (qthreshold > li->u.ulog.qthreshold)
+                        qthreshold = li->u.ulog.qthreshold;
+
 
         switch (inst->copy_mode) {
         case NFULNL_COPY_META:
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index bfbf521f6ea5..5baccfa5a0de 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -827,59 +827,143 @@ static const struct file_operations xt_table_ops = {
         .release = seq_release_net,
 };
 
-static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos)
+/*
+ * Traverse state for ip{,6}_{tables,matches} for helping crossing
+ * the multi-AF mutexes.
+ */
+struct nf_mttg_trav {
+        struct list_head *head, *curr;
+        uint8_t class, nfproto;
+};
+
+enum {
+        MTTG_TRAV_INIT,
+        MTTG_TRAV_NFP_UNSPEC,
+        MTTG_TRAV_NFP_SPEC,
+        MTTG_TRAV_DONE,
+};
+
+static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos,
+    bool is_target)
 {
-        struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private;
-        u_int16_t af = (unsigned long)pde->data;
+        static const uint8_t next_class[] = {
+                [MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC,
+                [MTTG_TRAV_NFP_SPEC]   = MTTG_TRAV_DONE,
+        };
+        struct nf_mttg_trav *trav = seq->private;
+
+        switch (trav->class) {
+        case MTTG_TRAV_INIT:
+                trav->class = MTTG_TRAV_NFP_UNSPEC;
+                mutex_lock(&xt[NFPROTO_UNSPEC].mutex);
+                trav->head = trav->curr = is_target ?
+                        &xt[NFPROTO_UNSPEC].target : &xt[NFPROTO_UNSPEC].match;
+                break;
+        case MTTG_TRAV_NFP_UNSPEC:
+                trav->curr = trav->curr->next;
+                if (trav->curr != trav->head)
+                        break;
+                mutex_unlock(&xt[NFPROTO_UNSPEC].mutex);
+                mutex_lock(&xt[trav->nfproto].mutex);
+                trav->head = trav->curr = is_target ?
+                        &xt[trav->nfproto].target : &xt[trav->nfproto].match;
+                trav->class = next_class[trav->class];
+                break;
+        case MTTG_TRAV_NFP_SPEC:
+                trav->curr = trav->curr->next;
+                if (trav->curr != trav->head)
+                        break;
+                /* fallthru, _stop will unlock */
+        default:
+                return NULL;
+        }
 
-        mutex_lock(&xt[af].mutex);
-        return seq_list_start(&xt[af].match, *pos);
+        if (ppos != NULL)
+                ++*ppos;
+        return trav;
 }
 
-static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos,
+    bool is_target)
 {
-        struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private;
-        u_int16_t af = (unsigned long)pde->data;
+        struct nf_mttg_trav *trav = seq->private;
+        unsigned int j;
 
-        return seq_list_next(v, &xt[af].match, pos);
+        trav->class = MTTG_TRAV_INIT;
+        for (j = 0; j < *pos; ++j)
+                if (xt_mttg_seq_next(seq, NULL, NULL, is_target) == NULL)
+                        return NULL;
+        return trav;
 }
 
-static void xt_match_seq_stop(struct seq_file *seq, void *v)
+static void xt_mttg_seq_stop(struct seq_file *seq, void *v)
 {
-        struct proc_dir_entry *pde = seq->private;
-        u_int16_t af = (unsigned long)pde->data;
+        struct nf_mttg_trav *trav = seq->private;
+
+        switch (trav->class) {
+        case MTTG_TRAV_NFP_UNSPEC:
+                mutex_unlock(&xt[NFPROTO_UNSPEC].mutex);
+                break;
+        case MTTG_TRAV_NFP_SPEC:
+                mutex_unlock(&xt[trav->nfproto].mutex);
+                break;
+        }
+}
 
-        mutex_unlock(&xt[af].mutex);
+static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos)
+{
+        return xt_mttg_seq_start(seq, pos, false);
 }
 
-static int xt_match_seq_show(struct seq_file *seq, void *v)
+static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *ppos)
 {
-        struct xt_match *match = list_entry(v, struct xt_match, list);
+        return xt_mttg_seq_next(seq, v, ppos, false);
+}
 
-        if (strlen(match->name))
-                return seq_printf(seq, "%s\n", match->name);
-        else
-                return 0;
+static int xt_match_seq_show(struct seq_file *seq, void *v)
+{
+        const struct nf_mttg_trav *trav = seq->private;
+        const struct xt_match *match;
+
+        switch (trav->class) {
+        case MTTG_TRAV_NFP_UNSPEC:
+        case MTTG_TRAV_NFP_SPEC:
+                if (trav->curr == trav->head)
+                        return 0;
+                match = list_entry(trav->curr, struct xt_match, list);
+                return (*match->name == '\0') ? 0 :
+                       seq_printf(seq, "%s\n", match->name);
+        }
+        return 0;
 }
 
 static const struct seq_operations xt_match_seq_ops = {
         .start  = xt_match_seq_start,
         .next   = xt_match_seq_next,
-        .stop   = xt_match_seq_stop,
+        .stop   = xt_mttg_seq_stop,
         .show   = xt_match_seq_show,
 };
 
 static int xt_match_open(struct inode *inode, struct file *file)
 {
+        struct seq_file *seq;
+        struct nf_mttg_trav *trav;
         int ret;
 
-        ret = seq_open(file, &xt_match_seq_ops);
-        if (!ret) {
-                struct seq_file *seq = file->private_data;
+        trav = kmalloc(sizeof(*trav), GFP_KERNEL);
+        if (trav == NULL)
+                return -ENOMEM;
 
-                seq->private = PDE(inode);
+        ret = seq_open(file, &xt_match_seq_ops);
+        if (ret < 0) {
+                kfree(trav);
+                return ret;
         }
-        return ret;
+
+        seq = file->private_data;
+        seq->private = trav;
+        trav->nfproto = (unsigned long)PDE(inode)->data;
+        return 0;
 }
 
 static const struct file_operations xt_match_ops = {
@@ -887,62 +971,63 @@ static const struct file_operations xt_match_ops = {
         .open    = xt_match_open,
         .read    = seq_read,
         .llseek  = seq_lseek,
-        .release = seq_release,
+        .release = seq_release_private,
 };
 
 static void *xt_target_seq_start(struct seq_file *seq, loff_t *pos)
 {
-        struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private;
-        u_int16_t af = (unsigned long)pde->data;
-
-        mutex_lock(&xt[af].mutex);
-        return seq_list_start(&xt[af].target, *pos);
+        return xt_mttg_seq_start(seq, pos, true);
 }
 
-static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *ppos)
 {
-        struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private;
-        u_int16_t af = (unsigned long)pde->data;
-
-        return seq_list_next(v, &xt[af].target, pos);
-}
-
-static void xt_target_seq_stop(struct seq_file *seq, void *v)
-{
-        struct proc_dir_entry *pde = seq->private;
-        u_int16_t af = (unsigned long)pde->data;
-
-        mutex_unlock(&xt[af].mutex);
+        return xt_mttg_seq_next(seq, v, ppos, true);
 }
 
 static int xt_target_seq_show(struct seq_file *seq, void *v)
 {
-        struct xt_target *target = list_entry(v, struct xt_target, list);
-
-        if (strlen(target->name))
-                return seq_printf(seq, "%s\n", target->name);
-        else
-                return 0;
+        const struct nf_mttg_trav *trav = seq->private;
+        const struct xt_target *target;
+
+        switch (trav->class) {
+        case MTTG_TRAV_NFP_UNSPEC:
+        case MTTG_TRAV_NFP_SPEC:
+                if (trav->curr == trav->head)
+                        return 0;
+                target = list_entry(trav->curr, struct xt_target, list);
+                return (*target->name == '\0') ? 0 :
+                       seq_printf(seq, "%s\n", target->name);
+        }
+        return 0;
 }
 
 static const struct seq_operations xt_target_seq_ops = {
         .start  = xt_target_seq_start,
         .next   = xt_target_seq_next,
-        .stop   = xt_target_seq_stop,
+        .stop   = xt_mttg_seq_stop,
         .show   = xt_target_seq_show,
 };
 
 static int xt_target_open(struct inode *inode, struct file *file)
 {
+        struct seq_file *seq;
+        struct nf_mttg_trav *trav;
         int ret;
 
-        ret = seq_open(file, &xt_target_seq_ops);
-        if (!ret) {
-                struct seq_file *seq = file->private_data;
+        trav = kmalloc(sizeof(*trav), GFP_KERNEL);
+        if (trav == NULL)
+                return -ENOMEM;
 
-                seq->private = PDE(inode);
+        ret = seq_open(file, &xt_target_seq_ops);
+        if (ret < 0) {
+                kfree(trav);
+                return ret;
         }
-        return ret;
+
+        seq = file->private_data;
+        seq->private = trav;
+        trav->nfproto = (unsigned long)PDE(inode)->data;
+        return 0;
 }
 
 static const struct file_operations xt_target_ops = {
@@ -950,7 +1035,7 @@ static const struct file_operations xt_target_ops = {
         .open    = xt_target_open,
         .read    = seq_read,
         .llseek  = seq_lseek,
-        .release = seq_release,
+        .release = seq_release_private,
 };
 
 #define FORMAT_TABLES   "_tables_names"
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index fe80b614a400..791e030ea903 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -542,7 +542,7 @@ recent_mt_proc_write(struct file *file, const char __user *input,
         struct recent_entry *e;
         char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:5afe:c0de")];
         const char *c = buf;
-        union nf_inet_addr addr;
+        union nf_inet_addr addr = {};
         u_int16_t family;
         bool add, succ;
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 9eb895c7a2a9..3ae3cb816563 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1084,6 +1084,13 @@ out:
         return 0;
 }
 
+/**
+ * netlink_set_err - report error to broadcast listeners
+ * @ssk: the kernel netlink socket, as returned by netlink_kernel_create()
+ * @pid: the PID of a process that we want to skip (if any)
+ * @groups: the broadcast group that will notice the error
+ * @code: error code, must be negative (as usual in kernelspace)
+ */
 void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 {
         struct netlink_set_err_data info;
@@ -1093,7 +1100,8 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
         info.exclude_sk = ssk;
         info.pid = pid;
         info.group = group;
-        info.code = code;
+        /* sk->sk_err wants a positive error value */
+        info.code = -code;
 
         read_lock(&nl_table_lock);
 
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 5c72a116b1a4..f8f047b61245 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -183,13 +183,6 @@ override:
                 if (R_tab == NULL)
                         goto failure;
 
-                if (!est && (ret == ACT_P_CREATED ||
-                             !gen_estimator_active(&police->tcf_bstats,
-                                                   &police->tcf_rate_est))) {
-                        err = -EINVAL;
-                        goto failure;
-                }
-
                 if (parm->peakrate.rate) {
                         P_tab = qdisc_get_rtab(&parm->peakrate,
                                                tb[TCA_POLICE_PEAKRATE]);
@@ -205,6 +198,12 @@ override:
                                             &police->tcf_lock, est);
                 if (err)
                         goto failure_unlock;
+        } else if (tb[TCA_POLICE_AVRATE] &&
+                   (ret == ACT_P_CREATED ||
+                    !gen_estimator_active(&police->tcf_bstats,
+                                          &police->tcf_rate_est))) {
+                err = -EINVAL;
+                goto failure_unlock;
         }
 
         /* No failure allowed after this point */
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index f6b4fa97df70..e36e94ab4e10 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -66,11 +66,15 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 {
         struct drr_sched *q = qdisc_priv(sch);
         struct drr_class *cl = (struct drr_class *)*arg;
+        struct nlattr *opt = tca[TCA_OPTIONS];
         struct nlattr *tb[TCA_DRR_MAX + 1];
         u32 quantum;
         int err;
 
-        err = nla_parse_nested(tb, TCA_DRR_MAX, tca[TCA_OPTIONS], drr_policy);
+        if (!opt)
+                return -EINVAL;
+
+        err = nla_parse_nested(tb, TCA_DRR_MAX, opt, drr_policy);
         if (err < 0)
                 return err;
 
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 4c8d9f45ce09..905fda582b92 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -111,7 +111,8 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
                 if (sctp_addip_enable) {
                         auth_chunks->chunks[0] = SCTP_CID_ASCONF;
                         auth_chunks->chunks[1] = SCTP_CID_ASCONF_ACK;
-                        auth_chunks->param_hdr.length += htons(2);
+                        auth_chunks->param_hdr.length =
+                                        htons(sizeof(sctp_paramhdr_t) + 2);
                 }
         }
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index b78e3be69013..c4986d0f7419 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -717,15 +717,20 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
 static int sctp_ctl_sock_init(void)
 {
         int err;
-        sa_family_t family;
+        sa_family_t family = PF_INET;
 
         if (sctp_get_pf_specific(PF_INET6))
                 family = PF_INET6;
-        else
-                family = PF_INET;
 
         err = inet_ctl_sock_create(&sctp_ctl_sock, family,
                                    SOCK_SEQPACKET, IPPROTO_SCTP, &init_net);
+
+        /* If IPv6 socket could not be created, try the IPv4 socket */
+        if (err < 0 && family == PF_INET6)
+                err = inet_ctl_sock_create(&sctp_ctl_sock, AF_INET,
+                                           SOCK_SEQPACKET, IPPROTO_SCTP,
+                                           &init_net);
+
         if (err < 0) {
                 printk(KERN_ERR
                        "SCTP: Failed to create the SCTP control socket.\n");
@@ -1322,9 +1327,8 @@ SCTP_STATIC __init int sctp_init(void)
 out:
         return status;
 err_v6_add_protocol:
-        sctp_v6_del_protocol();
-err_add_protocol:
         sctp_v4_del_protocol();
+err_add_protocol:
         inet_ctl_sock_destroy(sctp_ctl_sock);
 err_ctl_sock_init:
         sctp_v6_protosw_exit();
@@ -1335,7 +1339,6 @@ err_protosw_init:
         sctp_v4_pf_exit();
         sctp_v6_pf_exit();
         sctp_sysctl_unregister();
-        list_del(&sctp_af_inet.list);
         free_pages((unsigned long)sctp_port_hashtable,
                    get_order(sctp_port_hashsize *
                              sizeof(struct sctp_bind_hashbucket)));
@@ -1383,7 +1386,6 @@ SCTP_STATIC __exit void sctp_exit(void)
         sctp_v4_pf_exit();
 
         sctp_sysctl_unregister();
-        list_del(&sctp_af_inet.list);
 
         free_pages((unsigned long)sctp_assoc_hashtable,
                    get_order(sctp_assoc_hashsize *
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index e1d6076b4f59..b5495aecab60 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -787,36 +787,48 @@ static void sctp_cmd_process_operr(sctp_cmd_seq_t *cmds,
                                    struct sctp_association *asoc,
                                    struct sctp_chunk *chunk)
 {
-        struct sctp_operr_chunk *operr_chunk;
         struct sctp_errhdr *err_hdr;
+        struct sctp_ulpevent *ev;
 
-        operr_chunk = (struct sctp_operr_chunk *)chunk->chunk_hdr;
-        err_hdr = &operr_chunk->err_hdr;
+        while (chunk->chunk_end > chunk->skb->data) {
+                err_hdr = (struct sctp_errhdr *)(chunk->skb->data);
 
-        switch (err_hdr->cause) {
-        case SCTP_ERROR_UNKNOWN_CHUNK:
-        {
-                struct sctp_chunkhdr *unk_chunk_hdr;
+                ev = sctp_ulpevent_make_remote_error(asoc, chunk, 0,
+                                                     GFP_ATOMIC);
+                if (!ev)
+                        return;
 
-                unk_chunk_hdr = (struct sctp_chunkhdr *)err_hdr->variable;
-                switch (unk_chunk_hdr->type) {
-                /* ADDIP 4.1 A9) If the peer responds to an ASCONF with an
-                 * ERROR chunk reporting that it did not recognized the ASCONF
-                 * chunk type, the sender of the ASCONF MUST NOT send any
-                 * further ASCONF chunks and MUST stop its T-4 timer.
-                 */
-                case SCTP_CID_ASCONF:
-                        asoc->peer.asconf_capable = 0;
-                        sctp_add_cmd_sf(cmds, SCTP_CMD_TIMER_STOP,
+                sctp_ulpq_tail_event(&asoc->ulpq, ev);
+
+                switch (err_hdr->cause) {
+                case SCTP_ERROR_UNKNOWN_CHUNK:
+                {
+                        sctp_chunkhdr_t *unk_chunk_hdr;
+
+                        unk_chunk_hdr = (sctp_chunkhdr_t *)err_hdr->variable;
+                        switch (unk_chunk_hdr->type) {
+                        /* ADDIP 4.1 A9) If the peer responds to an ASCONF with
+                         * an ERROR chunk reporting that it did not recognized
+                         * the ASCONF chunk type, the sender of the ASCONF MUST
+                         * NOT send any further ASCONF chunks and MUST stop its
+                         * T-4 timer.
+                         */
+                        case SCTP_CID_ASCONF:
+                                if (asoc->peer.asconf_capable == 0)
+                                        break;
+
+                                asoc->peer.asconf_capable = 0;
+                                sctp_add_cmd_sf(cmds, SCTP_CMD_TIMER_STOP,
                                         SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
+                                break;
+                        default:
+                                break;
+                        }
                         break;
+                }
                 default:
                         break;
                 }
-                break;
-        }
-        default:
-                break;
         }
 }
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 3a0cd075914f..f88dfded0e3a 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3163,7 +3163,6 @@ sctp_disposition_t sctp_sf_operr_notify(const struct sctp_endpoint *ep,
                                         sctp_cmd_seq_t *commands)
 {
         struct sctp_chunk *chunk = arg;
-        struct sctp_ulpevent *ev;
 
         if (!sctp_vtag_verify(chunk, asoc))
                 return sctp_sf_pdiscard(ep, asoc, type, arg, commands);
@@ -3173,21 +3172,10 @@ sctp_disposition_t sctp_sf_operr_notify(const struct sctp_endpoint *ep,
                 return sctp_sf_violation_chunklen(ep, asoc, type, arg,
                                                   commands);
 
-        while (chunk->chunk_end > chunk->skb->data) {
-                ev = sctp_ulpevent_make_remote_error(asoc, chunk, 0,
-                                                     GFP_ATOMIC);
-                if (!ev)
-                        goto nomem;
+        sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_OPERR,
+                        SCTP_CHUNK(chunk));
 
-                sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP,
-                                SCTP_ULPEVENT(ev));
-                sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_OPERR,
-                                SCTP_CHUNK(chunk));
-        }
         return SCTP_DISPOSITION_CONSUME;
-
-nomem:
-        return SCTP_DISPOSITION_NOMEM;
 }
 
 /*
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 385f427bedad..ff50a0546865 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -293,11 +293,6 @@ static void rpc_make_runnable(struct rpc_task *task)
         rpc_clear_queued(task);
         if (rpc_test_and_set_running(task))
                 return;
-        /* We might have raced */
-        if (RPC_IS_QUEUED(task)) {
-                rpc_clear_running(task);
-                return;
-        }
         if (RPC_IS_ASYNC(task)) {
                 int status;
 
@@ -607,7 +602,9 @@ void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata)
  */
 static void __rpc_execute(struct rpc_task *task)
 {
-        int             status = 0;
+        struct rpc_wait_queue *queue;
+        int task_is_async = RPC_IS_ASYNC(task);
+        int status = 0;
 
         dprintk("RPC: %5u __rpc_execute flags=0x%x\n",
                         task->tk_pid, task->tk_flags);
@@ -647,15 +644,25 @@ static void __rpc_execute(struct rpc_task *task)
                  */
                 if (!RPC_IS_QUEUED(task))
                         continue;
-                rpc_clear_running(task);
-                if (RPC_IS_ASYNC(task)) {
-                        /* Careful! we may have raced... */
-                        if (RPC_IS_QUEUED(task))
-                                return;
-                        if (rpc_test_and_set_running(task))
-                                return;
+                /*
+                 * The queue->lock protects against races with
+                 * rpc_make_runnable().
+                 *
+                 * Note that once we clear RPC_TASK_RUNNING on an asynchronous
+                 * rpc_task, rpc_make_runnable() can assign it to a
+                 * different workqueue. We therefore cannot assume that the
+                 * rpc_task pointer may still be dereferenced.
+                 */
+                queue = task->tk_waitqueue;
+                spin_lock_bh(&queue->lock);
+                if (!RPC_IS_QUEUED(task)) {
+                        spin_unlock_bh(&queue->lock);
                         continue;
                 }
+                rpc_clear_running(task);
+                spin_unlock_bh(&queue->lock);
+                if (task_is_async)
+                        return;
 
                 /* sync task: sleep here */
                 dprintk("RPC: %5u sync task going to sleep\n", task->tk_pid);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 29e401bb612e..62098d101a1f 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -663,7 +663,7 @@ void xprt_connect(struct rpc_task *task)
                         xprt, (xprt_connected(xprt) ? "is" : "is not"));
 
         if (!xprt_bound(xprt)) {
-                task->tk_status = -EIO;
+                task->tk_status = -EAGAIN;
                 return;
         }
         if (!xprt_lock_write(xprt, task))
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 5cbb404c4cdf..29c71e645b27 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -467,7 +467,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
         int err, sent = 0;
 
         if (unlikely(!sock))
-                return -ENOTCONN;
+                return -ENOTSOCK;
 
         clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
         if (base != 0) {
@@ -577,6 +577,8 @@ static int xs_udp_send_request(struct rpc_task *task)
                                 req->rq_svec->iov_base,
                                 req->rq_svec->iov_len);
 
+        if (!xprt_bound(xprt))
+                return -ENOTCONN;
         status = xs_sendpages(transport->sock,
                               xs_addr(xprt),
                               xprt->addrlen, xdr,
@@ -594,6 +596,10 @@ static int xs_udp_send_request(struct rpc_task *task)
         }
 
         switch (status) {
+        case -ENOTSOCK:
+                status = -ENOTCONN;
+                /* Should we call xs_close() here? */
+                break;
         case -EAGAIN:
                 xs_nospace(task);
                 break;
@@ -693,6 +699,10 @@ static int xs_tcp_send_request(struct rpc_task *task)
         }
 
         switch (status) {
+        case -ENOTSOCK:
+                status = -ENOTCONN;
+                /* Should we call xs_close() here? */
+                break;
         case -EAGAIN:
                 xs_nospace(task);
                 break;
@@ -1523,7 +1533,7 @@ static void xs_udp_connect_worker4(struct work_struct *work)
         struct socket *sock = transport->sock;
         int err, status = -EIO;
 
-        if (xprt->shutdown || !xprt_bound(xprt))
+        if (xprt->shutdown)
                 goto out;
 
         /* Start by resetting any existing state */
@@ -1564,7 +1574,7 @@ static void xs_udp_connect_worker6(struct work_struct *work)
         struct socket *sock = transport->sock;
         int err, status = -EIO;
 
-        if (xprt->shutdown || !xprt_bound(xprt))
+        if (xprt->shutdown)
                 goto out;
 
         /* Start by resetting any existing state */
@@ -1648,6 +1658,9 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
                 write_unlock_bh(&sk->sk_callback_lock);
         }
 
+        if (!xprt_bound(xprt))
+                return -ENOTCONN;
+
         /* Tell the socket layer to start connecting... */
         xprt->stat.connect_count++;
         xprt->stat.connect_start = jiffies;
@@ -1668,7 +1681,7 @@ static void xs_tcp_connect_worker4(struct work_struct *work)
         struct socket *sock = transport->sock;
         int err, status = -EIO;
 
-        if (xprt->shutdown || !xprt_bound(xprt))
+        if (xprt->shutdown)
                 goto out;
 
         if (!sock) {
@@ -1728,7 +1741,7 @@ static void xs_tcp_connect_worker6(struct work_struct *work)
         struct socket *sock = transport->sock;
         int err, status = -EIO;
 
-        if (xprt->shutdown || !xprt_bound(xprt))
+        if (xprt->shutdown)
                 goto out;
 
         if (!sock) {
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index e28e2b8fa436..092ae6faccca 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -102,3 +102,13 @@ config LIB80211_CRYPT_CCMP
 
 config LIB80211_CRYPT_TKIP
         tristate
+
+config LIB80211_DEBUG
+        bool "lib80211 debugging messages"
+        depends on LIB80211
+        default n
+        ---help---
+          You can enable this if you want verbose debugging messages
+          from lib80211.
+
+          If unsure, say N.
diff --git a/net/wireless/lib80211_crypt_ccmp.c b/net/wireless/lib80211_crypt_ccmp.c
index db428194c16a..2301dc1edc4c 100644
--- a/net/wireless/lib80211_crypt_ccmp.c
+++ b/net/wireless/lib80211_crypt_ccmp.c
@@ -337,6 +337,7 @@ static int lib80211_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
         pos += 8;
 
         if (ccmp_replay_check(pn, key->rx_pn)) {
+#ifdef CONFIG_LIB80211_DEBUG
                 if (net_ratelimit()) {
                         printk(KERN_DEBUG "CCMP: replay detected: STA=%pM "
                                  "previous PN %02x%02x%02x%02x%02x%02x "
@@ -346,6 +347,7 @@ static int lib80211_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
                                  key->rx_pn[3], key->rx_pn[4], key->rx_pn[5],
                                  pn[0], pn[1], pn[2], pn[3], pn[4], pn[5]);
                 }
+#endif
                 key->dot11RSNAStatsCCMPReplays++;
                 return -4;
         }
diff --git a/net/wireless/lib80211_crypt_tkip.c b/net/wireless/lib80211_crypt_tkip.c
index 7e8e22bfed90..c36287399d7e 100644
--- a/net/wireless/lib80211_crypt_tkip.c
+++ b/net/wireless/lib80211_crypt_tkip.c
@@ -465,12 +465,14 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
         pos += 8;
 
         if (tkip_replay_check(iv32, iv16, tkey->rx_iv32, tkey->rx_iv16)) {
+#ifdef CONFIG_LIB80211_DEBUG
                 if (net_ratelimit()) {
                         printk(KERN_DEBUG "TKIP: replay detected: STA=%pM"
                                " previous TSC %08x%04x received TSC "
                                "%08x%04x\n", hdr->addr2,
                                tkey->rx_iv32, tkey->rx_iv16, iv32, iv16);
                 }
+#endif
                 tkey->dot11RSNAStatsTKIPReplays++;
                 return -4;
         }
@@ -505,10 +507,12 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
                          * it needs to be recalculated for the next packet. */
                         tkey->rx_phase1_done = 0;
                 }
+#ifdef CONFIG_LIB80211_DEBUG
                 if (net_ratelimit()) {
                         printk(KERN_DEBUG "TKIP: ICV error detected: STA="
                                "%pM\n", hdr->addr2);
                 }
+#endif
                 tkey->dot11RSNAStatsTKIPICVErrors++;
                 return -5;
         }
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 1e728fff474e..31b807af3235 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1908,6 +1908,11 @@ static int nl80211_get_mesh_params(struct sk_buff *skb,
         if (err)
                 return err;
 
+        if (!drv->ops->get_mesh_params) {
+                err = -EOPNOTSUPP;
+                goto out;
+        }
+
         /* Get the mesh params */
         rtnl_lock();
         err = drv->ops->get_mesh_params(&drv->wiphy, dev, &cur_params);
@@ -2017,6 +2022,11 @@ static int nl80211_set_mesh_params(struct sk_buff *skb, struct genl_info *info)
         if (err)
                 return err;
 
+        if (!drv->ops->set_mesh_params) {
+                err = -EOPNOTSUPP;
+                goto out;
+        }
+
         /* This makes sure that there aren't more than 32 mesh config
          * parameters (otherwise our bitfield scheme would not work.) */
         BUILD_BUG_ON(NL80211_MESHCONF_ATTR_MAX > 32);
@@ -2061,6 +2071,7 @@ static int nl80211_set_mesh_params(struct sk_buff *skb, struct genl_info *info)
         err = drv->ops->set_mesh_params(&drv->wiphy, dev, &cfg, mask);
         rtnl_unlock();
 
+ out:
         /* cleanup */
         cfg80211_put_dev(drv);
         dev_put(dev);
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 85c9034c59b2..bd0a16c3de5e 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -380,7 +380,8 @@ static bool is_valid_reg_rule(const struct ieee80211_reg_rule *rule)
 
         freq_diff = freq_range->end_freq_khz - freq_range->start_freq_khz;
 
-        if (freq_diff <= 0 || freq_range->max_bandwidth_khz > freq_diff)
+        if (freq_range->end_freq_khz <= freq_range->start_freq_khz ||
+                        freq_range->max_bandwidth_khz > freq_diff)
                 return false;
 
         return true;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index e25ff62ab2a6..62a5425cc6aa 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -748,12 +748,51 @@ static void xfrm_hash_grow_check(struct net *net, int have_hash_collision)
                 schedule_work(&net->xfrm.state_hash_work);
 }
 
+static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
+                               struct flowi *fl, unsigned short family,
+                               xfrm_address_t *daddr, xfrm_address_t *saddr,
+                               struct xfrm_state **best, int *acq_in_progress,
+                               int *error)
+{
+        /* Resolution logic:
+         * 1. There is a valid state with matching selector. Done.
+         * 2. Valid state with inappropriate selector. Skip.
+         *
+         * Entering area of "sysdeps".
+         *
+         * 3. If state is not valid, selector is temporary, it selects
+         *    only session which triggered previous resolution. Key
+         *    manager will do something to install a state with proper
+         *    selector.
+         */
+        if (x->km.state == XFRM_STATE_VALID) {
+                if ((x->sel.family &&
+                     !xfrm_selector_match(&x->sel, fl, x->sel.family)) ||
+                    !security_xfrm_state_pol_flow_match(x, pol, fl))
+                        return;
+
+                if (!*best ||
+                    (*best)->km.dying > x->km.dying ||
+                    ((*best)->km.dying == x->km.dying &&
+                     (*best)->curlft.add_time < x->curlft.add_time))
+                        *best = x;
+        } else if (x->km.state == XFRM_STATE_ACQ) {
+                *acq_in_progress = 1;
+        } else if (x->km.state == XFRM_STATE_ERROR ||
+                   x->km.state == XFRM_STATE_EXPIRED) {
+                if (xfrm_selector_match(&x->sel, fl, x->sel.family) &&
+                    security_xfrm_state_pol_flow_match(x, pol, fl))
+                        *error = -ESRCH;
+        }
+}
+
 struct xfrm_state *
 xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
                 struct flowi *fl, struct xfrm_tmpl *tmpl,
                 struct xfrm_policy *pol, int *err,
                 unsigned short family)
 {
+        static xfrm_address_t saddr_wildcard = { };
         struct net *net = xp_net(pol);
         unsigned int h;
         struct hlist_node *entry;
@@ -773,40 +812,27 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr,
                     xfrm_state_addr_check(x, daddr, saddr, family) &&
                     tmpl->mode == x->props.mode &&
                     tmpl->id.proto == x->id.proto &&
-                    (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) {
-                        /* Resolution logic:
-                           1. There is a valid state with matching selector.
-                              Done.
-                           2. Valid state with inappropriate selector. Skip.
-
-                           Entering area of "sysdeps".
-
-                           3. If state is not valid, selector is temporary,
-                              it selects only session which triggered
-                              previous resolution. Key manager will do
-                              something to install a state with proper
-                              selector.
-                         */
-                        if (x->km.state == XFRM_STATE_VALID) {
-                                if ((x->sel.family && !xfrm_selector_match(&x->sel, fl, x->sel.family)) ||
-                                    !security_xfrm_state_pol_flow_match(x, pol, fl))
-                                        continue;
-                                if (!best ||
-                                    best->km.dying > x->km.dying ||
-                                    (best->km.dying == x->km.dying &&
-                                     best->curlft.add_time < x->curlft.add_time))
-                                        best = x;
-                        } else if (x->km.state == XFRM_STATE_ACQ) {
-                                acquire_in_progress = 1;
-                        } else if (x->km.state == XFRM_STATE_ERROR ||
-                                   x->km.state == XFRM_STATE_EXPIRED) {
-                                if (xfrm_selector_match(&x->sel, fl, x->sel.family) &&
-                                    security_xfrm_state_pol_flow_match(x, pol, fl))
-                                        error = -ESRCH;
-                        }
-                }
+                    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
+                        xfrm_state_look_at(pol, x, fl, family, daddr, saddr,
+                                           &best, &acquire_in_progress, &error);
+        }
+        if (best)
+                goto found;
+
+        h = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family);
+        hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) {
+                if (x->props.family == family &&
+                    x->props.reqid == tmpl->reqid &&
+                    !(x->props.flags & XFRM_STATE_WILDRECV) &&
+                    xfrm_state_addr_check(x, daddr, saddr, family) &&
+                    tmpl->mode == x->props.mode &&
+                    tmpl->id.proto == x->id.proto &&
+                    (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
+                        xfrm_state_look_at(pol, x, fl, family, daddr, saddr,
+                                           &best, &acquire_in_progress, &error);
         }
 
+found:
         x = best;
         if (!x && !error && !acquire_in_progress) {
                 if (tmpl->id.spi &&