788 files changed, 50890 insertions, 25780 deletions

diff --git a/net/802/garp.c b/net/802/garp.c
index 5d9630a0eb9..b38ee6dcba4 100644
--- a/net/802/garp.c
+++ b/net/802/garp.c
@@ -397,7 +397,7 @@ static void garp_join_timer_arm(struct garp_applicant *app)
 {
 	unsigned long delay;
 
-	delay = (u64)msecs_to_jiffies(garp_join_time) * net_random() >> 32;
+	delay = (u64)msecs_to_jiffies(garp_join_time) * prandom_u32() >> 32;
 	mod_timer(&app->join_timer, jiffies + delay);
 }
 
diff --git a/net/802/hippi.c b/net/802/hippi.c
index a97a3bde77b..5ff2a718ddc 100644
--- a/net/802/hippi.c
+++ b/net/802/hippi.c
@@ -172,14 +172,14 @@ EXPORT_SYMBOL(hippi_mac_addr);
 int hippi_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p)
 {
 	/* Never send broadcast/multicast ARP messages */
-	NEIGH_VAR_SET(p, MCAST_PROBES, 0);
+	NEIGH_VAR_INIT(p, MCAST_PROBES, 0);
 
 	/* In IPv6 unicast probes are valid even on NBMA,
 	* because they are encapsulated in normal IPv6 protocol.
 	* Should be a generic flag.
 	*/
 	if (p->tbl->family != AF_INET6)
-		NEIGH_VAR_SET(p, UCAST_PROBES, 0);
+		NEIGH_VAR_INIT(p, UCAST_PROBES, 0);
 	return 0;
 }
 EXPORT_SYMBOL(hippi_neigh_setup_dev);
diff --git a/net/802/mrp.c b/net/802/mrp.c
index 3ed61621587..72db2785ef2 100644
--- a/net/802/mrp.c
+++ b/net/802/mrp.c
@@ -583,7 +583,7 @@ static void mrp_join_timer_arm(struct mrp_applicant *app)
 {
 	unsigned long delay;
 
-	delay = (u64)msecs_to_jiffies(mrp_join_time) * net_random() >> 32;
+	delay = (u64)msecs_to_jiffies(mrp_join_time) * prandom_u32() >> 32;
 	mod_timer(&app->join_timer, jiffies + delay);
 }
 
diff --git a/net/8021q/Kconfig b/net/8021q/Kconfig
index b85a91fa61f..42320180967 100644
--- a/net/8021q/Kconfig
+++ b/net/8021q/Kconfig
@@ -6,11 +6,11 @@ config VLAN_8021Q
 	tristate "802.1Q/802.1ad VLAN Support"
 	---help---
 	  Select this and you will be able to create 802.1Q VLAN interfaces
-	  on your ethernet interfaces.  802.1Q VLAN supports almost
-	  everything a regular ethernet interface does, including
-	  firewalling, bridging, and of course IP traffic.  You will need
-	  the 'vconfig' tool from the VLAN project in order to effectively
-	  use VLANs.  See the VLAN web page for more information:
+	  on your Ethernet interfaces. 802.1Q VLAN supports almost
+	  everything a regular Ethernet interface does, including
+	  firewalling, bridging, and of course IP traffic. You will need
+	  the 'ip' utility in order to effectively use VLANs.
+	  See the VLAN web page for more information:
 	  <http://www.candelatech.com/~greear/vlan.html>
 
 	  To compile this code as a module, choose M here: the module
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index b3d17d1c49c..44ebd5c2cd4 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -169,6 +169,7 @@ int register_vlan_dev(struct net_device *dev)
 	if (err < 0)
 		goto out_uninit_mvrp;
 
+	vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out_uninit_mvrp;
@@ -301,15 +302,17 @@ static void vlan_sync_address(struct net_device *dev,
 	    !ether_addr_equal(vlandev->dev_addr, dev->dev_addr))
 		dev_uc_add(dev, vlandev->dev_addr);
 
-	memcpy(vlan->real_dev_addr, dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(vlan->real_dev_addr, dev->dev_addr);
 }
 
 static void vlan_transfer_features(struct net_device *dev,
 				   struct net_device *vlandev)
 {
+	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
+
 	vlandev->gso_max_size = dev->gso_max_size;
 
-	if (dev->features & NETIF_F_HW_VLAN_CTAG_TX)
+	if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
 		vlandev->hard_header_len = dev->hard_header_len;
 	else
 		vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 5704ed9c3a2..9d010a09ab9 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -38,9 +38,9 @@ struct vlan_info {
 static inline unsigned int vlan_proto_idx(__be16 proto)
 {
 	switch (proto) {
-	case __constant_htons(ETH_P_8021Q):
+	case htons(ETH_P_8021Q):
 		return VLAN_PROTO_8021Q;
-	case __constant_htons(ETH_P_8021AD):
+	case htons(ETH_P_8021AD):
 		return VLAN_PROTO_8021AD;
 	default:
 		BUG();
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 6ee48aac776..75d42776399 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -22,11 +22,11 @@ bool vlan_do_receive(struct sk_buff **skbp)
 		return false;
 
 	skb->dev = vlan_dev;
-	if (skb->pkt_type == PACKET_OTHERHOST) {
+	if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) {
 		/* Our lower layer thinks this is not local, let's make sure.
 		 * This allows the VLAN to have a different MAC than the
 		 * underlying device, and still route correctly. */
-		if (ether_addr_equal(eth_hdr(skb)->h_dest, vlan_dev->dev_addr))
+		if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, vlan_dev->dev_addr))
 			skb->pkt_type = PACKET_HOST;
 	}
 
@@ -63,7 +63,7 @@ bool vlan_do_receive(struct sk_buff **skbp)
 }
 
 /* Must be invoked with rcu_read_lock. */
-struct net_device *__vlan_find_dev_deep(struct net_device *dev,
+struct net_device *__vlan_find_dev_deep_rcu(struct net_device *dev,
 					__be16 vlan_proto, u16 vlan_id)
 {
 	struct vlan_info *vlan_info = rcu_dereference(dev->vlan_info);
@@ -81,13 +81,13 @@ struct net_device *__vlan_find_dev_deep(struct net_device *dev,
 
 		upper_dev = netdev_master_upper_dev_get_rcu(dev);
 		if (upper_dev)
-			return __vlan_find_dev_deep(upper_dev,
+			return __vlan_find_dev_deep_rcu(upper_dev,
 						    vlan_proto, vlan_id);
 	}
 
 	return NULL;
 }
-EXPORT_SYMBOL(__vlan_find_dev_deep);
+EXPORT_SYMBOL(__vlan_find_dev_deep_rcu);
 
 struct net_device *vlan_dev_real_dev(const struct net_device *dev)
 {
@@ -106,10 +106,19 @@ u16 vlan_dev_vlan_id(const struct net_device *dev)
 }
 EXPORT_SYMBOL(vlan_dev_vlan_id);
 
+__be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->vlan_proto;
+}
+EXPORT_SYMBOL(vlan_dev_vlan_proto);
+
 static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
 {
-	if (skb_cow(skb, skb_headroom(skb)) < 0)
+	if (skb_cow(skb, skb_headroom(skb)) < 0) {
+		kfree_skb(skb);
 		return NULL;
+	}
+
 	memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
 	skb->mac_header += VLAN_HLEN;
 	return skb;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 762896ebfcf..dd11f612e03 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -61,7 +61,7 @@ static int vlan_dev_rebuild_header(struct sk_buff *skb)
 		pr_debug("%s: unable to resolve type %X addresses\n",
 			 dev->name, ntohs(veth->h_vlan_encapsulated_proto));
 
-		memcpy(veth->h_source, dev->dev_addr, ETH_ALEN);
+		ether_addr_copy(veth->h_source, dev->dev_addr);
 		break;
 	}
 
@@ -303,7 +303,7 @@ static int vlan_dev_open(struct net_device *dev)
 			goto clear_allmulti;
 	}
 
-	memcpy(vlan->real_dev_addr, real_dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(vlan->real_dev_addr, real_dev->dev_addr);
 
 	if (vlan->flags & VLAN_FLAG_GVRP)
 		vlan_gvrp_request_join(dev);
@@ -367,7 +367,7 @@ static int vlan_dev_set_mac_address(struct net_device *dev, void *p)
 		dev_uc_del(real_dev, dev->dev_addr);
 
 out:
-	memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
+	ether_addr_copy(dev->dev_addr, addr->sa_data);
 	return 0;
 }
 
@@ -524,12 +524,37 @@ static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass)
 	netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass);
 }
 
+static int vlan_dev_get_lock_subclass(struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->nest_level;
+}
+
 static const struct header_ops vlan_header_ops = {
 	.create	 = vlan_dev_hard_header,
 	.rebuild = vlan_dev_rebuild_header,
 	.parse	 = eth_header_parse,
 };
 
+static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev,
+				     unsigned short type,
+				     const void *daddr, const void *saddr,
+				     unsigned int len)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct net_device *real_dev = vlan->real_dev;
+
+	if (saddr == NULL)
+		saddr = dev->dev_addr;
+
+	return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
+}
+
+static const struct header_ops vlan_passthru_header_ops = {
+	.create	 = vlan_passthru_hard_header,
+	.rebuild = dev_rebuild_header,
+	.parse	 = eth_header_parse,
+};
+
 static struct device_type vlan_type = {
 	.name	= "vlan",
 };
@@ -539,7 +564,6 @@ static const struct net_device_ops vlan_netdev_ops;
 static int vlan_dev_init(struct net_device *dev)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
-	int subclass = 0, i;
 
 	netif_carrier_off(dev);
 
@@ -558,6 +582,9 @@ static int vlan_dev_init(struct net_device *dev)
 
 	dev->features |= real_dev->vlan_features | NETIF_F_LLTX;
 	dev->gso_max_size = real_dev->gso_max_size;
+	if (dev->features & NETIF_F_VLAN_FEATURES)
+		netdev_warn(real_dev, "VLAN features are set incorrectly.  Q-in-Q configurations may not work correctly.\n");
+
 
 	/* ipv6 shared card related stuff */
 	dev->dev_id = real_dev->dev_id;
@@ -572,8 +599,9 @@ static int vlan_dev_init(struct net_device *dev)
 #endif
 
 	dev->needed_headroom = real_dev->needed_headroom;
-	if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
-		dev->header_ops      = real_dev->header_ops;
+	if (vlan_hw_offload_capable(real_dev->features,
+				    vlan_dev_priv(dev)->vlan_proto)) {
+		dev->header_ops      = &vlan_passthru_header_ops;
 		dev->hard_header_len = real_dev->hard_header_len;
 	} else {
 		dev->header_ops      = &vlan_header_ops;
@@ -584,22 +612,12 @@ static int vlan_dev_init(struct net_device *dev)
 
 	SET_NETDEV_DEVTYPE(dev, &vlan_type);
 
-	if (is_vlan_dev(real_dev))
-		subclass = 1;
-
-	vlan_dev_set_lockdep_class(dev, subclass);
+	vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev));
 
-	vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
+	vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct vlan_pcpu_stats *vlan_stat;
-		vlan_stat = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
-		u64_stats_init(&vlan_stat->syncp);
-	}
-
-
 	return 0;
 }
 
@@ -609,8 +627,6 @@ static void vlan_dev_uninit(struct net_device *dev)
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	int i;
 
-	free_percpu(vlan->vlan_pcpu_stats);
-	vlan->vlan_pcpu_stats = NULL;
 	for (i = 0; i < ARRAY_SIZE(vlan->egress_priority_map); i++) {
 		while ((pm = vlan->egress_priority_map[i]) != NULL) {
 			vlan->egress_priority_map[i] = pm->next;
@@ -625,9 +641,9 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev,
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	netdev_features_t old_features = features;
 
-	features &= real_dev->vlan_features;
+	features = netdev_intersect_features(features, real_dev->vlan_features);
 	features |= NETIF_F_RXCSUM;
-	features &= real_dev->features;
+	features = netdev_intersect_features(features, real_dev->features);
 
 	features |= old_features & NETIF_F_SOFT_FEATURES;
 	features |= NETIF_F_LLTX;
@@ -653,38 +669,36 @@ static void vlan_ethtool_get_drvinfo(struct net_device *dev,
 
 static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
+	struct vlan_pcpu_stats *p;
+	u32 rx_errors = 0, tx_dropped = 0;
+	int i;
 
-	if (vlan_dev_priv(dev)->vlan_pcpu_stats) {
-		struct vlan_pcpu_stats *p;
-		u32 rx_errors = 0, tx_dropped = 0;
-		int i;
-
-		for_each_possible_cpu(i) {
-			u64 rxpackets, rxbytes, rxmulticast, txpackets, txbytes;
-			unsigned int start;
-
-			p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
-			do {
-				start = u64_stats_fetch_begin_bh(&p->syncp);
-				rxpackets	= p->rx_packets;
-				rxbytes		= p->rx_bytes;
-				rxmulticast	= p->rx_multicast;
-				txpackets	= p->tx_packets;
-				txbytes		= p->tx_bytes;
-			} while (u64_stats_fetch_retry_bh(&p->syncp, start));
-
-			stats->rx_packets	+= rxpackets;
-			stats->rx_bytes		+= rxbytes;
-			stats->multicast	+= rxmulticast;
-			stats->tx_packets	+= txpackets;
-			stats->tx_bytes		+= txbytes;
-			/* rx_errors & tx_dropped are u32 */
-			rx_errors	+= p->rx_errors;
-			tx_dropped	+= p->tx_dropped;
-		}
-		stats->rx_errors  = rx_errors;
-		stats->tx_dropped = tx_dropped;
+	for_each_possible_cpu(i) {
+		u64 rxpackets, rxbytes, rxmulticast, txpackets, txbytes;
+		unsigned int start;
+
+		p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
+		do {
+			start = u64_stats_fetch_begin_irq(&p->syncp);
+			rxpackets	= p->rx_packets;
+			rxbytes		= p->rx_bytes;
+			rxmulticast	= p->rx_multicast;
+			txpackets	= p->tx_packets;
+			txbytes		= p->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
+
+		stats->rx_packets	+= rxpackets;
+		stats->rx_bytes		+= rxbytes;
+		stats->multicast	+= rxmulticast;
+		stats->tx_packets	+= txpackets;
+		stats->tx_bytes		+= txbytes;
+		/* rx_errors & tx_dropped are u32 */
+		rx_errors	+= p->rx_errors;
+		tx_dropped	+= p->tx_dropped;
 	}
+	stats->rx_errors  = rx_errors;
+	stats->tx_dropped = tx_dropped;
+
 	return stats;
 }
 
@@ -694,20 +708,19 @@ static void vlan_dev_poll_controller(struct net_device *dev)
 	return;
 }
 
-static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo,
-				  gfp_t gfp)
+static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
 {
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
 	struct netpoll *netpoll;
 	int err = 0;
 
-	netpoll = kzalloc(sizeof(*netpoll), gfp);
+	netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
 	err = -ENOMEM;
 	if (!netpoll)
 		goto out;
 
-	err = __netpoll_setup(netpoll, real_dev, gfp);
+	err = __netpoll_setup(netpoll, real_dev);
 	if (err) {
 		kfree(netpoll);
 		goto out;
@@ -767,8 +780,18 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_netpoll_cleanup	= vlan_dev_netpoll_cleanup,
 #endif
 	.ndo_fix_features	= vlan_dev_fix_features,
+	.ndo_get_lock_subclass  = vlan_dev_get_lock_subclass,
 };
 
+static void vlan_dev_free(struct net_device *dev)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+
+	free_percpu(vlan->vlan_pcpu_stats);
+	vlan->vlan_pcpu_stats = NULL;
+	free_netdev(dev);
+}
+
 void vlan_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -778,7 +801,7 @@ void vlan_setup(struct net_device *dev)
 	dev->tx_queue_len	= 0;
 
 	dev->netdev_ops		= &vlan_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->destructor		= vlan_dev_free;
 	dev->ethtool_ops	= &vlan_ethtool_ops;
 
 	memset(dev->broadcast, 0, ETH_ALEN);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index c7e634af851..8ac8a5cc214 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -56,8 +56,8 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[])
 
 	if (data[IFLA_VLAN_PROTOCOL]) {
 		switch (nla_get_be16(data[IFLA_VLAN_PROTOCOL])) {
-		case __constant_htons(ETH_P_8021Q):
-		case __constant_htons(ETH_P_8021AD):
+		case htons(ETH_P_8021Q):
+		case htons(ETH_P_8021AD):
 			break;
 		default:
 			return -EPROTONOSUPPORT;
diff --git a/net/9p/client.c b/net/9p/client.c
index ee8fd6bd403..0004cbaac4a 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -204,7 +204,7 @@ free_and_return:
 	return ret;
 }
 
-struct p9_fcall *p9_fcall_alloc(int alloc_msize)
+static struct p9_fcall *p9_fcall_alloc(int alloc_msize)
 {
 	struct p9_fcall *fc;
 	fc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, GFP_NOFS);
@@ -415,9 +415,17 @@ static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
  * req: request received
  *
  */
-void p9_client_cb(struct p9_client *c, struct p9_req_t *req)
+void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
 {
 	p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc->tag);
+
+	/*
+	 * This barrier is needed to make sure any change made to req before
+	 * the other thread wakes up will indeed be seen by the waiting side.
+	 */
+	smp_wmb();
+	req->status = status;
+
 	wake_up(req->wq);
 	p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
 }
@@ -655,16 +663,13 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-
 	/*
 	 * if we haven't received a response for oldreq,
 	 * remove it from the list
 	 */
-	if (oldreq->status == REQ_STATUS_FLSH) {
-		spin_lock(&c->lock);
-		list_del(&oldreq->req_list);
-		spin_unlock(&c->lock);
-	}
+	if (oldreq->status == REQ_STATUS_SENT)
+		if (c->trans_mod->cancelled)
+			c->trans_mod->cancelled(c, oldreq);
 
 	p9_free_req(c, req);
 	return 0;
@@ -751,6 +756,12 @@ again:
 	err = wait_event_interruptible(*req->wq,
 				       req->status >= REQ_STATUS_RCVD);
 
+	/*
+	 * Make sure our req is coherent with regard to updates in other
+	 * threads - echoes to wmb() in the callback
+	 */
+	smp_rmb();
+
 	if ((err == -ERESTARTSYS) && (c->status == Connected)
 				  && (type == P9_TFLUSH)) {
 		sigpending = 1;
@@ -1012,9 +1023,6 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 		goto destroy_tagpool;
 
 	if (!clnt->trans_mod)
-		clnt->trans_mod = v9fs_get_trans_by_name("virtio");
-
-	if (!clnt->trans_mod)
 		clnt->trans_mod = v9fs_get_default_trans();
 
 	if (clnt->trans_mod == NULL) {
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 9321a776306..80d08f6664c 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -66,20 +66,6 @@ struct p9_fd_opts {
 	int privport;
 };
 
-/**
- * struct p9_trans_fd - transport state
- * @rd: reference to file to read from
- * @wr: reference of file to write to
- * @conn: connection state reference
- *
- */
-
-struct p9_trans_fd {
-	struct file *rd;
-	struct file *wr;
-	struct p9_conn *conn;
-};
-
 /*
   * Option Parsing (code inspired by NFS code)
   *  - a little lazy - parse all fd-transport options
@@ -159,6 +145,20 @@ struct p9_conn {
 	unsigned long wsched;
 };
 
+/**
+ * struct p9_trans_fd - transport state
+ * @rd: reference to file to read from
+ * @wr: reference of file to write to
+ * @conn: connection state reference
+ *
+ */
+
+struct p9_trans_fd {
+	struct file *rd;
+	struct file *wr;
+	struct p9_conn conn;
+};
+
 static void p9_poll_workfn(struct work_struct *work);
 
 static DEFINE_SPINLOCK(p9_poll_lock);
@@ -212,15 +212,9 @@ static void p9_conn_cancel(struct p9_conn *m, int err)
 	m->err = err;
 
 	list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) {
-		req->status = REQ_STATUS_ERROR;
-		if (!req->t_err)
-			req->t_err = err;
 		list_move(&req->req_list, &cancel_list);
 	}
 	list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) {
-		req->status = REQ_STATUS_ERROR;
-		if (!req->t_err)
-			req->t_err = err;
 		list_move(&req->req_list, &cancel_list);
 	}
 	spin_unlock_irqrestore(&m->client->lock, flags);
@@ -228,7 +222,9 @@ static void p9_conn_cancel(struct p9_conn *m, int err)
 	list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) {
 		p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req);
 		list_del(&req->req_list);
-		p9_client_cb(m->client, req);
+		if (!req->t_err)
+			req->t_err = err;
+		p9_client_cb(m->client, req, REQ_STATUS_ERROR);
 	}
 }
 
@@ -302,6 +298,7 @@ static void p9_read_work(struct work_struct *work)
 {
 	int n, err;
 	struct p9_conn *m;
+	int status = REQ_STATUS_ERROR;
 
 	m = container_of(work, struct p9_conn, rq);
 
@@ -348,8 +345,7 @@ static void p9_read_work(struct work_struct *work)
 			 "mux %p pkt: size: %d bytes tag: %d\n", m, n, tag);
 
 		m->req = p9_tag_lookup(m->client, tag);
-		if (!m->req || (m->req->status != REQ_STATUS_SENT &&
-					m->req->status != REQ_STATUS_FLSH)) {
+		if (!m->req || (m->req->status != REQ_STATUS_SENT)) {
 			p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n",
 				 tag);
 			err = -EIO;
@@ -375,10 +371,10 @@ static void p9_read_work(struct work_struct *work)
 		p9_debug(P9_DEBUG_TRANS, "got new packet\n");
 		spin_lock(&m->client->lock);
 		if (m->req->status != REQ_STATUS_ERROR)
-			m->req->status = REQ_STATUS_RCVD;
+			status = REQ_STATUS_RCVD;
 		list_del(&m->req->req_list);
 		spin_unlock(&m->client->lock);
-		p9_client_cb(m->client, m->req);
+		p9_client_cb(m->client, m->req, status);
 		m->rbuf = NULL;
 		m->rpos = 0;
 		m->rsize = 0;
@@ -573,21 +569,19 @@ p9_pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p)
 }
 
 /**
- * p9_conn_create - allocate and initialize the per-session mux data
+ * p9_conn_create - initialize the per-session mux data
  * @client: client instance
  *
  * Note: Creates the polling task if this is the first session.
  */
 
-static struct p9_conn *p9_conn_create(struct p9_client *client)
+static void p9_conn_create(struct p9_client *client)
 {
 	int n;
-	struct p9_conn *m;
+	struct p9_trans_fd *ts = client->trans;
+	struct p9_conn *m = &ts->conn;
 
 	p9_debug(P9_DEBUG_TRANS, "client %p msize %d\n", client, client->msize);
-	m = kzalloc(sizeof(struct p9_conn), GFP_KERNEL);
-	if (!m)
-		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&m->mux_list);
 	m->client = client;
@@ -609,8 +603,6 @@ static struct p9_conn *p9_conn_create(struct p9_client *client)
 		p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m);
 		set_bit(Wpending, &m->wsched);
 	}
-
-	return m;
 }
 
 /**
@@ -669,7 +661,7 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
 {
 	int n;
 	struct p9_trans_fd *ts = client->trans;
-	struct p9_conn *m = ts->conn;
+	struct p9_conn *m = &ts->conn;
 
 	p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n",
 		 m, current, req->tc, req->tc->id);
@@ -704,14 +696,26 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
 		list_del(&req->req_list);
 		req->status = REQ_STATUS_FLSHD;
 		ret = 0;
-	} else if (req->status == REQ_STATUS_SENT)
-		req->status = REQ_STATUS_FLSH;
-
+	}
 	spin_unlock(&client->lock);
 
 	return ret;
 }
 
+static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
+{
+	p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
+
+	/* we haven't received a response for oldreq,
+	 * remove it from the list.
+	 */
+	spin_lock(&client->lock);
+	list_del(&req->req_list);
+	spin_unlock(&client->lock);
+
+	return 0;
+}
+
 /**
  * parse_opts - parse mount options into p9_fd_opts structure
  * @params: options string passed from mount
@@ -780,7 +784,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts)
 
 static int p9_fd_open(struct p9_client *client, int rfd, int wfd)
 {
-	struct p9_trans_fd *ts = kmalloc(sizeof(struct p9_trans_fd),
+	struct p9_trans_fd *ts = kzalloc(sizeof(struct p9_trans_fd),
 					   GFP_KERNEL);
 	if (!ts)
 		return -ENOMEM;
@@ -806,9 +810,8 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket)
 {
 	struct p9_trans_fd *p;
 	struct file *file;
-	int ret;
 
-	p = kmalloc(sizeof(struct p9_trans_fd), GFP_KERNEL);
+	p = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 
@@ -829,20 +832,12 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket)
 
 	p->rd->f_flags |= O_NONBLOCK;
 
-	p->conn = p9_conn_create(client);
-	if (IS_ERR(p->conn)) {
-		ret = PTR_ERR(p->conn);
-		p->conn = NULL;
-		kfree(p);
-		sockfd_put(csocket);
-		sockfd_put(csocket);
-		return ret;
-	}
+	p9_conn_create(client);
 	return 0;
 }
 
 /**
- * p9_mux_destroy - cancels all pending requests and frees mux resources
+ * p9_mux_destroy - cancels all pending requests of mux
  * @m: mux to destroy
  *
  */
@@ -859,7 +854,6 @@ static void p9_conn_destroy(struct p9_conn *m)
 	p9_conn_cancel(m, -ECONNRESET);
 
 	m->client = NULL;
-	kfree(m);
 }
 
 /**
@@ -881,7 +875,7 @@ static void p9_fd_close(struct p9_client *client)
 
 	client->status = Disconnected;
 
-	p9_conn_destroy(ts->conn);
+	p9_conn_destroy(&ts->conn);
 
 	if (ts->rd)
 		fput(ts->rd);
@@ -1033,14 +1027,7 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args)
 		return err;
 
 	p = (struct p9_trans_fd *) client->trans;
-	p->conn = p9_conn_create(client);
-	if (IS_ERR(p->conn)) {
-		err = PTR_ERR(p->conn);
-		p->conn = NULL;
-		fput(p->rd);
-		fput(p->wr);
-		return err;
-	}
+	p9_conn_create(client);
 
 	return 0;
 }
@@ -1048,11 +1035,12 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args)
 static struct p9_trans_module p9_tcp_trans = {
 	.name = "tcp",
 	.maxsize = MAX_SOCK_BUF,
-	.def = 1,
+	.def = 0,
 	.create = p9_fd_create_tcp,
 	.close = p9_fd_close,
 	.request = p9_fd_request,
 	.cancel = p9_fd_cancel,
+	.cancelled = p9_fd_cancelled,
 	.owner = THIS_MODULE,
 };
 
@@ -1064,6 +1052,7 @@ static struct p9_trans_module p9_unix_trans = {
 	.close = p9_fd_close,
 	.request = p9_fd_request,
 	.cancel = p9_fd_cancel,
+	.cancelled = p9_fd_cancelled,
 	.owner = THIS_MODULE,
 };
 
@@ -1075,6 +1064,7 @@ static struct p9_trans_module p9_fd_trans = {
 	.close = p9_fd_close,
 	.request = p9_fd_request,
 	.cancel = p9_fd_cancel,
+	.cancelled = p9_fd_cancelled,
 	.owner = THIS_MODULE,
 };
 
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 8f68df5d297..14ad43b5cf8 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -193,6 +193,8 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts)
 		if (!*p)
 			continue;
 		token = match_token(p, tokens, args);
+		if (token == Opt_err)
+			continue;
 		r = match_int(&args[0], &option);
 		if (r < 0) {
 			p9_debug(P9_DEBUG_ERROR,
@@ -305,8 +307,7 @@ handle_recv(struct p9_client *client, struct p9_trans_rdma *rdma,
 	}
 
 	req->rc = c->rc;
-	req->status = REQ_STATUS_RCVD;
-	p9_client_cb(client, req);
+	p9_client_cb(client, req, REQ_STATUS_RCVD);
 
 	return;
 
@@ -511,6 +512,11 @@ dont_need_post_recv:
 		goto send_error;
 	}
 
+	/* Mark request as `sent' *before* we actually send it,
+	 * because doing if after could erase the REQ_STATUS_RCVD
+	 * status in case of a very fast reply.
+	 */
+	req->status = REQ_STATUS_SENT;
 	err = ib_post_send(rdma->qp, &wr, &bad_wr);
 	if (err)
 		goto send_error;
@@ -520,6 +526,7 @@ dont_need_post_recv:
 
  /* Handle errors that happened during or while preparing the send: */
  send_error:
+	req->status = REQ_STATUS_ERROR;
 	kfree(c);
 	p9_debug(P9_DEBUG_ERROR, "Error %d in rdma_request()\n", err);
 
@@ -582,12 +589,24 @@ static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts)
 	return rdma;
 }
 
-/* its not clear to me we can do anything after send has been posted */
 static int rdma_cancel(struct p9_client *client, struct p9_req_t *req)
 {
+	/* Nothing to do here.
+	 * We will take care of it (if we have to) in rdma_cancelled()
+	 */
 	return 1;
 }
 
+/* A request has been fully flushed without a reply.
+ * That means we have posted one buffer in excess.
+ */
+static int rdma_cancelled(struct p9_client *client, struct p9_req_t *req)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	atomic_inc(&rdma->excess_rc);
+	return 0;
+}
+
 /**
  * trans_create_rdma - Transport method for creating atransport instance
  * @client: client instance
@@ -721,6 +740,7 @@ static struct p9_trans_module p9_rdma_trans = {
 	.close = rdma_close,
 	.request = rdma_request,
 	.cancel = rdma_cancel,
+	.cancelled = rdma_cancelled,
 };
 
 /**
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 9c5a1aa34d1..6940d8fe897 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -164,8 +164,7 @@ static void req_done(struct virtqueue *vq)
 		p9_debug(P9_DEBUG_TRANS, ": rc %p\n", rc);
 		p9_debug(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag);
 		req = p9_tag_lookup(chan->client, rc->tag);
-		req->status = REQ_STATUS_RCVD;
-		p9_client_cb(chan->client, req);
+		p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
 	}
 }
 
@@ -340,7 +339,10 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
 		int count = nr_pages;
 		while (nr_pages) {
 			s = rest_of_page(data);
-			pages[index++] = kmap_to_page(data);
+			if (is_vmalloc_addr(data))
+				pages[index++] = vmalloc_to_page(data);
+			else
+				pages[index++] = kmap_to_page(data);
 			data += s;
 			nr_pages--;
 		}
@@ -698,7 +700,7 @@ static struct p9_trans_module p9_virtio_trans = {
 	 * page in zero copy.
 	 */
 	.maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3),
-	.def = 0,
+	.def = 1,
 	.owner = THIS_MODULE,
 };
 
diff --git a/net/Kconfig b/net/Kconfig
index d334678c0bd..d92afe4204d 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -89,8 +89,12 @@ config NETWORK_SECMARK
 	  to nfmark, but designated for security purposes.
 	  If you are unsure how to answer this question, answer N.
 
+config NET_PTP_CLASSIFY
+	def_bool n
+
 config NETWORK_PHY_TIMESTAMPING
 	bool "Timestamping in PHY devices"
+	select NET_PTP_CLASSIFY
 	help
 	  This allows timestamping of network packets by PHYs with
 	  hardware timestamping capabilities. This option adds some
@@ -238,12 +242,19 @@ config XPS
 	depends on SMP
 	default y
 
-config NETPRIO_CGROUP
-	tristate "Network priority cgroup"
+config CGROUP_NET_PRIO
+	bool "Network priority cgroup"
 	depends on CGROUPS
 	---help---
 	  Cgroup subsystem for use in assigning processes to network priorities on
-	  a per-interface basis
+	  a per-interface basis.
+
+config CGROUP_NET_CLASSID
+	boolean "Network classid cgroup"
+	depends on CGROUPS
+	---help---
+	  Cgroup subsystem for use as general purpose socket classid marker that is
+	  being used in cls_cgroup and for netfilter matching.
 
 config NET_RX_BUSY_POLL
 	boolean
diff --git a/net/Makefile b/net/Makefile
index 8fa2f91517f..cbbbe6d657c 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -57,7 +57,7 @@ obj-$(CONFIG_CAIF)		+= caif/
 ifneq ($(CONFIG_DCB),)
 obj-y				+= dcb/
 endif
-obj-$(CONFIG_IEEE802154)	+= ieee802154/
+obj-y				+= ieee802154/
 obj-$(CONFIG_MAC802154)		+= mac802154/
 
 ifeq ($(CONFIG_NET),y)
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index 690356fa52b..d1c55d8dd0a 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -40,6 +40,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/export.h>
+#include <linux/etherdevice.h>
 
 int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME;
 int sysctl_aarp_tick_time = AARP_TICK_TIME;
@@ -67,7 +68,7 @@ struct aarp_entry {
 	unsigned long		expires_at;
 	struct atalk_addr	target_addr;
 	struct net_device	*dev;
-	char			hwaddr[6];
+	char			hwaddr[ETH_ALEN];
 	unsigned short		xmit_count;
 	struct aarp_entry	*next;
 };
@@ -134,7 +135,7 @@ static void __aarp_send_query(struct aarp_entry *a)
 	eah->pa_len	 = AARP_PA_ALEN;
 	eah->function	 = htons(AARP_REQUEST);
 
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(eah->hw_src, dev->dev_addr);
 
 	eah->pa_src_zero = 0;
 	eah->pa_src_net	 = sat->s_net;
@@ -181,7 +182,7 @@ static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us,
 	eah->pa_len	 = AARP_PA_ALEN;
 	eah->function	 = htons(AARP_REPLY);
 
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(eah->hw_src, dev->dev_addr);
 
 	eah->pa_src_zero = 0;
 	eah->pa_src_net	 = us->s_net;
@@ -190,7 +191,7 @@ static void aarp_send_reply(struct net_device *dev, struct atalk_addr *us,
 	if (!sha)
 		memset(eah->hw_dst, '\0', ETH_ALEN);
 	else
-		memcpy(eah->hw_dst, sha, ETH_ALEN);
+		ether_addr_copy(eah->hw_dst, sha);
 
 	eah->pa_dst_zero = 0;
 	eah->pa_dst_net	 = them->s_net;
@@ -232,7 +233,7 @@ static void aarp_send_probe(struct net_device *dev, struct atalk_addr *us)
 	eah->pa_len	 = AARP_PA_ALEN;
 	eah->function	 = htons(AARP_PROBE);
 
-	memcpy(eah->hw_src, dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(eah->hw_src, dev->dev_addr);
 
 	eah->pa_src_zero = 0;
 	eah->pa_src_net	 = us->s_net;
@@ -790,7 +791,7 @@ static int aarp_rcv(struct sk_buff *skb, struct net_device *dev,
 			break;
 
 		/* We can fill one in - this is good. */
-		memcpy(a->hwaddr, ea->hw_src, ETH_ALEN);
+		ether_addr_copy(a->hwaddr, ea->hw_src);
 		__aarp_resolved(&unresolved[hash], a, hash);
 		if (!unresolved_count)
 			mod_timer(&aarp_timer,
@@ -925,7 +926,7 @@ static struct aarp_entry *iter_next(struct aarp_iter_state *iter, loff_t *pos)
 	struct aarp_entry *entry;
 
  rescan:
-	while(ct < AARP_HASH_SIZE) {
+	while (ct < AARP_HASH_SIZE) {
 		for (entry = table[ct]; entry; entry = entry->next) {
 			if (!pos || ++off == *pos) {
 				iter->table = table;
@@ -994,7 +995,7 @@ static const char *dt2str(unsigned long ticks)
 {
 	static char buf[32];
 
-	sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100 ) / HZ);
+	sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100) / HZ);
 
 	return buf;
 }
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 7d424ac6e76..bfcf6be1d66 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -293,7 +293,7 @@ static int atif_probe_device(struct atalk_iface *atif)
 
 /* Perform AARP probing for a proxy address */
 static int atif_proxy_probe_device(struct atalk_iface *atif,
-				   struct atalk_addr* proxy_addr)
+				   struct atalk_addr *proxy_addr)
 {
 	int netrange = ntohs(atif->nets.nr_lastnet) -
 			ntohs(atif->nets.nr_firstnet) + 1;
@@ -581,7 +581,7 @@ out:
 }
 
 /* Delete a route. Find it and discard it */
-static int atrtr_delete(struct atalk_addr * addr)
+static int atrtr_delete(struct atalk_addr *addr)
 {
 	struct atalk_route **r = &atalk_routes;
 	int retval = 0;
@@ -936,11 +936,11 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset,
 	int i, copy;
 
 	/* checksum stuff in header space */
-	if ( (copy = start - offset) > 0) {
+	if ((copy = start - offset) > 0) {
 		if (copy > len)
 			copy = len;
 		sum = atalk_sum_partial(skb->data + offset, copy, sum);
-		if ( (len -= copy) == 0)
+		if ((len -= copy) == 0)
 			return sum;
 
 		offset += copy;
@@ -1151,7 +1151,7 @@ static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 			goto out;
 
 		at->src_net  = addr->sat_addr.s_net = ap->s_net;
-		at->src_node = addr->sat_addr.s_node= ap->s_node;
+		at->src_node = addr->sat_addr.s_node = ap->s_node;
 	} else {
 		err = -EADDRNOTAVAIL;
 		if (!atalk_find_interface(addr->sat_addr.s_net,
@@ -1489,8 +1489,6 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto drop;
 
 	/* Queue packet (standard) */
-	skb->sk = sock;
-
 	if (sock_queue_rcv_skb(sock, skb) < 0)
 		goto drop;
 
@@ -1566,7 +1564,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 {
 	struct sock *sk = sock->sk;
 	struct atalk_sock *at = at_sk(sk);
-	struct sockaddr_at *usat = (struct sockaddr_at *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_at *, usat, msg->msg_name);
 	int flags = msg->msg_flags;
 	int loopback = 0;
 	struct sockaddr_at local_satalk, gsat;
@@ -1644,7 +1642,6 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 	if (!skb)
 		goto out;
 
-	skb->sk = sk;
 	skb_reserve(skb, ddp_dl->header_length);
 	skb_reserve(skb, dev->hard_header_len);
 	skb->dev = dev;
@@ -1669,7 +1666,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 		goto out;
 	}
 
-	if (sk->sk_no_check == 1)
+	if (sk->sk_no_check_tx)
 		ddp->deh_sum = 0;
 	else
 		ddp->deh_sum = atalk_checksum(skb, len + sizeof(*ddp));
@@ -1764,7 +1761,7 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
 
 	if (!err && msg->msg_name) {
-		struct sockaddr_at *sat = msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_at *, sat, msg->msg_name);
 		sat->sat_family      = AF_APPLETALK;
 		sat->sat_port        = ddp->deh_sport;
 		sat->sat_addr.s_node = ddp->deh_snode;
@@ -1790,53 +1787,53 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	void __user *argp = (void __user *)arg;
 
 	switch (cmd) {
-		/* Protocol layer */
-		case TIOCOUTQ: {
-			long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk);
+	/* Protocol layer */
+	case TIOCOUTQ: {
+		long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk);
 
-			if (amount < 0)
-				amount = 0;
-			rc = put_user(amount, (int __user *)argp);
-			break;
-		}
-		case TIOCINQ: {
-			/*
-			 * These two are safe on a single CPU system as only
-			 * user tasks fiddle here
-			 */
-			struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
-			long amount = 0;
+		if (amount < 0)
+			amount = 0;
+		rc = put_user(amount, (int __user *)argp);
+		break;
+	}
+	case TIOCINQ: {
+		/*
+		 * These two are safe on a single CPU system as only
+		 * user tasks fiddle here
+		 */
+		struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+		long amount = 0;
 
-			if (skb)
-				amount = skb->len - sizeof(struct ddpehdr);
-			rc = put_user(amount, (int __user *)argp);
-			break;
-		}
-		case SIOCGSTAMP:
-			rc = sock_get_timestamp(sk, argp);
-			break;
-		case SIOCGSTAMPNS:
-			rc = sock_get_timestampns(sk, argp);
-			break;
-		/* Routing */
-		case SIOCADDRT:
-		case SIOCDELRT:
-			rc = -EPERM;
-			if (capable(CAP_NET_ADMIN))
-				rc = atrtr_ioctl(cmd, argp);
-			break;
-		/* Interface */
-		case SIOCGIFADDR:
-		case SIOCSIFADDR:
-		case SIOCGIFBRDADDR:
-		case SIOCATALKDIFADDR:
-		case SIOCDIFADDR:
-		case SIOCSARP:		/* proxy AARP */
-		case SIOCDARP:		/* proxy AARP */
-			rtnl_lock();
-			rc = atif_ioctl(cmd, argp);
-			rtnl_unlock();
-			break;
+		if (skb)
+		amount = skb->len - sizeof(struct ddpehdr);
+		rc = put_user(amount, (int __user *)argp);
+		break;
+	}
+	case SIOCGSTAMP:
+		rc = sock_get_timestamp(sk, argp);
+		break;
+	case SIOCGSTAMPNS:
+		rc = sock_get_timestampns(sk, argp);
+		break;
+	/* Routing */
+	case SIOCADDRT:
+	case SIOCDELRT:
+		rc = -EPERM;
+		if (capable(CAP_NET_ADMIN))
+			rc = atrtr_ioctl(cmd, argp);
+		break;
+	/* Interface */
+	case SIOCGIFADDR:
+	case SIOCSIFADDR:
+	case SIOCGIFBRDADDR:
+	case SIOCATALKDIFADDR:
+	case SIOCDIFADDR:
+	case SIOCSARP:		/* proxy AARP */
+	case SIOCDARP:		/* proxy AARP */
+		rtnl_lock();
+		rc = atif_ioctl(cmd, argp);
+		rtnl_unlock();
+		break;
 	}
 
 	return rc;
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 8215f7cb170..ba291ce4bdf 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -68,7 +68,7 @@ static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip)
 
 	sk = sk_atm(atmarpd);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 	return 0;
 }
 
diff --git a/net/atm/lec.c b/net/atm/lec.c
index f23916be18f..4c5b8ba0f84 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -152,7 +152,7 @@ static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev)
 		atm_force_charge(priv->lecd, skb2->truesize);
 		sk = sk_atm(priv->lecd);
 		skb_queue_tail(&sk->sk_receive_queue, skb2);
-		sk->sk_data_ready(sk, skb2->len);
+		sk->sk_data_ready(sk);
 	}
 }
 #endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */
@@ -447,7 +447,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb)
 			atm_force_charge(priv->lecd, skb2->truesize);
 			sk = sk_atm(priv->lecd);
 			skb_queue_tail(&sk->sk_receive_queue, skb2);
-			sk->sk_data_ready(sk, skb2->len);
+			sk->sk_data_ready(sk);
 		}
 	}
 #endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */
@@ -521,7 +521,7 @@ send_to_lecd(struct lec_priv *priv, atmlec_msg_type type,
 	if (data != NULL)
 		mesg->sizeoftlvs = data->len;
 	if (mac_addr)
-		memcpy(&mesg->content.normal.mac_addr, mac_addr, ETH_ALEN);
+		ether_addr_copy(mesg->content.normal.mac_addr, mac_addr);
 	else
 		mesg->content.normal.targetless_le_arp = 1;
 	if (atm_addr)
@@ -530,13 +530,13 @@ send_to_lecd(struct lec_priv *priv, atmlec_msg_type type,
 	atm_force_charge(priv->lecd, skb->truesize);
 	sk = sk_atm(priv->lecd);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 
 	if (data != NULL) {
 		pr_debug("about to send %d bytes of data\n", data->len);
 		atm_force_charge(priv->lecd, data->truesize);
 		skb_queue_tail(&sk->sk_receive_queue, data);
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 	}
 
 	return 0;
@@ -616,7 +616,7 @@ static void lec_push(struct atm_vcc *vcc, struct sk_buff *skb)
 
 		pr_debug("%s: To daemon\n", dev->name);
 		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 	} else {		/* Data frame, queue to protocol handlers */
 		struct lec_arp_table *entry;
 		unsigned char *src, *dst;
@@ -1565,7 +1565,7 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv,
 		pr_info("LEC: Arp entry kmalloc failed\n");
 		return NULL;
 	}
-	memcpy(to_return->mac_addr, mac_addr, ETH_ALEN);
+	ether_addr_copy(to_return->mac_addr, mac_addr);
 	INIT_HLIST_NODE(&to_return->next);
 	setup_timer(&to_return->timer, lec_arp_expire_arp,
 			(unsigned long)to_return);
@@ -1887,7 +1887,8 @@ lec_arp_update(struct lec_priv *priv, const unsigned char *mac_addr,
 					entry = tmp;
 				} else {
 					entry->status = ESI_FORWARD_DIRECT;
-					memcpy(entry->mac_addr, mac_addr, ETH_ALEN);
+					ether_addr_copy(entry->mac_addr,
+							mac_addr);
 					entry->last_used = jiffies;
 					lec_arp_add(priv, entry);
 				}
@@ -2263,7 +2264,7 @@ lec_arp_check_empties(struct lec_priv *priv,
 				  &priv->lec_arp_empty_ones, next) {
 		if (vcc == entry->vcc) {
 			del_timer(&entry->timer);
-			memcpy(entry->mac_addr, src, ETH_ALEN);
+			ether_addr_copy(entry->mac_addr, src);
 			entry->status = ESI_FORWARD_DIRECT;
 			entry->last_used = jiffies;
 			/* We might have got an entry */
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 3af12755cd0..e8e0e7a8a23 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -478,7 +478,7 @@ static const uint8_t *copy_macs(struct mpoa_client *mpc,
 			return NULL;
 		}
 	}
-	memcpy(mpc->mps_macs, router_mac, ETH_ALEN);
+	ether_addr_copy(mpc->mps_macs, router_mac);
 	tlvs += 20; if (device_type == MPS_AND_MPC) tlvs += 20;
 	if (mps_macs > 0)
 		memcpy(mpc->mps_macs, tlvs, mps_macs*ETH_ALEN);
@@ -706,7 +706,7 @@ static void mpc_push(struct atm_vcc *vcc, struct sk_buff *skb)
 		dprintk("(%s) control packet arrived\n", dev->name);
 		/* Pass control packets to daemon */
 		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 		return;
 	}
 
@@ -992,7 +992,7 @@ int msg_to_mpoad(struct k_message *mesg, struct mpoa_client *mpc)
 
 	sk = sk_atm(mpc->mpoad_vcc);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 
 	return 0;
 }
@@ -1273,7 +1273,7 @@ static void purge_egress_shortcut(struct atm_vcc *vcc, eg_cache_entry *entry)
 
 	sk = sk_atm(vcc);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 	dprintk("exiting\n");
 }
 
@@ -1492,7 +1492,7 @@ static void __exit atm_mpoa_cleanup(void)
 
 	mpc_proc_clean();
 
-	del_timer(&mpc_timer);
+	del_timer_sync(&mpc_timer);
 	unregister_netdevice_notifier(&mpoa_notifier);
 	deregister_atm_ioctl(&atm_ioctl_ops);
 
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
index 8c93267ce96..c4e09846d1d 100644
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -252,7 +252,7 @@ static int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size)
 	 * we need to ensure there's a memory barrier after it. The bit
 	 * *must* be set before we do the atomic_inc() on pvcc->inflight.
 	 * There's no smp_mb__after_set_bit(), so it's this or abuse
-	 * smp_mb__after_clear_bit().
+	 * smp_mb__after_atomic().
 	 */
 	test_and_set_bit(BLOCKED, &pvcc->blocked);
 
diff --git a/net/atm/raw.c b/net/atm/raw.c
index b4f7b9ff3c7..2e17e97a7a8 100644
--- a/net/atm/raw.c
+++ b/net/atm/raw.c
@@ -25,7 +25,7 @@ static void atm_push_raw(struct atm_vcc *vcc, struct sk_buff *skb)
 		struct sock *sk = sk_atm(vcc);
 
 		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 	}
 }
 
diff --git a/net/atm/signaling.c b/net/atm/signaling.c
index 4176887e72e..523bce72f69 100644
--- a/net/atm/signaling.c
+++ b/net/atm/signaling.c
@@ -51,7 +51,7 @@ static void sigd_put_skb(struct sk_buff *skb)
 #endif
 	atm_force_charge(sigd, skb->truesize);
 	skb_queue_tail(&sk_atm(sigd)->sk_receive_queue, skb);
-	sk_atm(sigd)->sk_data_ready(sk_atm(sigd), skb->len);
+	sk_atm(sigd)->sk_data_ready(sk_atm(sigd));
 }
 
 static void modify_qos(struct atm_vcc *vcc, struct atmsvc_msg *msg)
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 1281049c135..d8e5d0c2ebb 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -263,17 +263,11 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr,
 			goto out;
 		}
 	}
-/*
- * Not supported yet
- *
- * #ifndef CONFIG_SINGLE_SIGITF
- */
+
 	vcc->qos.txtp.max_pcr = SELECT_TOP_PCR(vcc->qos.txtp);
 	vcc->qos.txtp.pcr = 0;
 	vcc->qos.txtp.min_pcr = 0;
-/*
- * #endif
- */
+
 	error = vcc_connect(sock, vcc->itf, vcc->vpi, vcc->vci);
 	if (!error)
 		sock->state = SS_CONNECTED;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 7bb1605bdfd..c35c3f48fc0 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1435,7 +1435,7 @@ out:
 static int ax25_sendmsg(struct kiocb *iocb, struct socket *sock,
 			struct msghdr *msg, size_t len)
 {
-	struct sockaddr_ax25 *usax = (struct sockaddr_ax25 *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_ax25 *, usax, msg->msg_name);
 	struct sock *sk = sock->sk;
 	struct sockaddr_ax25 sax;
 	struct sk_buff *skb;
@@ -1640,7 +1640,7 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock,
 		ax25_digi digi;
 		ax25_address src;
 		const unsigned char *mac = skb_mac_header(skb);
-		struct sockaddr_ax25 *sax = msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_ax25 *, sax, msg->msg_name);
 
 		memset(sax, 0, sizeof(struct full_sockaddr_ax25));
 		ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL,
diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c
index 96f4cab3a2f..7ed8ab72481 100644
--- a/net/ax25/ax25_in.c
+++ b/net/ax25/ax25_in.c
@@ -422,7 +422,7 @@ static int ax25_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	if (sk) {
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk, skb->len);
+			sk->sk_data_ready(sk);
 		sock_put(sk);
 	} else {
 free:
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index fa780b76630..11660a3aab5 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -50,6 +50,15 @@ config BATMAN_ADV_NC
 	  If you think that your network does not need this feature you
 	  can safely disable it and save some space.
 
+config BATMAN_ADV_MCAST
+	bool "Multicast optimisation"
+	depends on BATMAN_ADV
+	default n
+	help
+	  This option enables the multicast optimisation which aims to
+	  reduce the air overhead while improving the reliability of
+	  multicast messages.
+
 config BATMAN_ADV_DEBUG
 	bool "B.A.T.M.A.N. debugging"
 	depends on BATMAN_ADV
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index 4f4aabbd8ea..eb7d8c0388e 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -1,5 +1,5 @@
 #
-# Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+# Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
 #
 # Marek Lindner, Simon Wunderlich
 #
@@ -13,9 +13,7 @@
 # General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
-# 02110-1301, USA
+# along with this program; if not, see <http://www.gnu.org/licenses/>.
 #
 
 obj-$(CONFIG_BATMAN_ADV) += batman-adv.o
@@ -38,3 +36,4 @@ batman-adv-y += send.o
 batman-adv-y += soft-interface.o
 batman-adv-y += sysfs.o
 batman-adv-y += translation-table.o
+batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o
diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h
index a4808c29ea3..4e49666f8c6 100644
--- a/net/batman-adv/bat_algo.h
+++ b/net/batman-adv/bat_algo.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_BAT_ALGO_H_
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index a2b480a9087..f04224c3200 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -243,19 +241,19 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const uint8_t *addr)
 	size = bat_priv->num_ifaces * sizeof(uint8_t);
 	orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC);
 	if (!orig_node->bat_iv.bcast_own_sum)
-		goto free_bcast_own;
+		goto free_orig_node;
 
 	hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig,
 				     batadv_choose_orig, orig_node,
 				     &orig_node->hash_entry);
 	if (hash_added != 0)
-		goto free_bcast_own;
+		goto free_orig_node;
 
 	return orig_node;
 
-free_bcast_own:
-	kfree(orig_node->bat_iv.bcast_own);
 free_orig_node:
+	/* free twice, as batadv_orig_node_new sets refcount to 2 */
+	batadv_orig_node_free_ref(orig_node);
 	batadv_orig_node_free_ref(orig_node);
 
 	return NULL;
@@ -268,22 +266,39 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface,
 			struct batadv_orig_node *orig_neigh)
 {
 	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
-	struct batadv_neigh_node *neigh_node;
+	struct batadv_neigh_node *neigh_node, *tmp_neigh_node;
 
 	neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, orig_node);
 	if (!neigh_node)
 		goto out;
 
-	spin_lock_init(&neigh_node->bat_iv.lq_update_lock);
+	if (!atomic_inc_not_zero(&hard_iface->refcount)) {
+		kfree(neigh_node);
+		neigh_node = NULL;
+		goto out;
+	}
 
-	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-		   "Creating new neighbor %pM for orig_node %pM on interface %s\n",
-		   neigh_addr, orig_node->orig, hard_iface->net_dev->name);
+	neigh_node->orig_node = orig_neigh;
+	neigh_node->if_incoming = hard_iface;
 
 	spin_lock_bh(&orig_node->neigh_list_lock);
-	hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list);
+	tmp_neigh_node = batadv_neigh_node_get(orig_node, hard_iface,
+					       neigh_addr);
+	if (!tmp_neigh_node) {
+		hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list);
+	} else {
+		kfree(neigh_node);
+		batadv_hardif_free_ref(hard_iface);
+		neigh_node = tmp_neigh_node;
+	}
 	spin_unlock_bh(&orig_node->neigh_list_lock);
 
+	if (!tmp_neigh_node)
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "Creating new neighbor %pM for orig_node %pM on interface %s\n",
+			   neigh_addr, orig_node->orig,
+			   hard_iface->net_dev->name);
+
 out:
 	return neigh_node;
 }
@@ -307,9 +322,9 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
 	hard_iface->bat_iv.ogm_buff = ogm_buff;
 
 	batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
-	batadv_ogm_packet->header.packet_type = BATADV_IV_OGM;
-	batadv_ogm_packet->header.version = BATADV_COMPAT_VERSION;
-	batadv_ogm_packet->header.ttl = 2;
+	batadv_ogm_packet->packet_type = BATADV_IV_OGM;
+	batadv_ogm_packet->version = BATADV_COMPAT_VERSION;
+	batadv_ogm_packet->ttl = 2;
 	batadv_ogm_packet->flags = BATADV_NO_FLAGS;
 	batadv_ogm_packet->reserved = 0;
 	batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE;
@@ -332,10 +347,10 @@ static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface)
 	unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff;
 
 	batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
-	memcpy(batadv_ogm_packet->orig,
-	       hard_iface->net_dev->dev_addr, ETH_ALEN);
-	memcpy(batadv_ogm_packet->prev_sender,
-	       hard_iface->net_dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(batadv_ogm_packet->orig,
+			hard_iface->net_dev->dev_addr);
+	ether_addr_copy(batadv_ogm_packet->prev_sender,
+			hard_iface->net_dev->dev_addr);
 }
 
 static void
@@ -346,7 +361,7 @@ batadv_iv_ogm_primary_iface_set(struct batadv_hard_iface *hard_iface)
 
 	batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
 	batadv_ogm_packet->flags = BATADV_PRIMARIES_FIRST_HOP;
-	batadv_ogm_packet->header.ttl = BATADV_TTL;
+	batadv_ogm_packet->ttl = BATADV_TTL;
 }
 
 /* when do we schedule our own ogm to be sent */
@@ -435,7 +450,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet,
 			   fwd_str, (packet_num > 0 ? "aggregated " : ""),
 			   batadv_ogm_packet->orig,
 			   ntohl(batadv_ogm_packet->seqno),
-			   batadv_ogm_packet->tq, batadv_ogm_packet->header.ttl,
+			   batadv_ogm_packet->tq, batadv_ogm_packet->ttl,
 			   (batadv_ogm_packet->flags & BATADV_DIRECTLINK ?
 			    "on" : "off"),
 			   hard_iface->net_dev->name,
@@ -461,17 +476,9 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet,
 /* send a batman ogm packet */
 static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet)
 {
-	struct batadv_hard_iface *hard_iface;
 	struct net_device *soft_iface;
 	struct batadv_priv *bat_priv;
 	struct batadv_hard_iface *primary_if = NULL;
-	struct batadv_ogm_packet *batadv_ogm_packet;
-	unsigned char directlink;
-	uint8_t *packet_pos;
-
-	packet_pos = forw_packet->skb->data;
-	batadv_ogm_packet = (struct batadv_ogm_packet *)packet_pos;
-	directlink = (batadv_ogm_packet->flags & BATADV_DIRECTLINK ? 1 : 0);
 
 	if (!forw_packet->if_incoming) {
 		pr_err("Error - can't forward packet: incoming iface not specified\n");
@@ -481,59 +488,48 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet)
 	soft_iface = forw_packet->if_incoming->soft_iface;
 	bat_priv = netdev_priv(soft_iface);
 
-	if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE)
+	if (WARN_ON(!forw_packet->if_outgoing))
 		goto out;
 
-	primary_if = batadv_primary_if_get_selected(bat_priv);
-	if (!primary_if)
+	if (WARN_ON(forw_packet->if_outgoing->soft_iface != soft_iface))
 		goto out;
 
-	/* multihomed peer assumed
-	 * non-primary OGMs are only broadcasted on their interface
-	 */
-	if ((directlink && (batadv_ogm_packet->header.ttl == 1)) ||
-	    (forw_packet->own && (forw_packet->if_incoming != primary_if))) {
-		/* FIXME: what about aggregated packets ? */
-		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-			   "%s packet (originator %pM, seqno %u, TTL %d) on interface %s [%pM]\n",
-			   (forw_packet->own ? "Sending own" : "Forwarding"),
-			   batadv_ogm_packet->orig,
-			   ntohl(batadv_ogm_packet->seqno),
-			   batadv_ogm_packet->header.ttl,
-			   forw_packet->if_incoming->net_dev->name,
-			   forw_packet->if_incoming->net_dev->dev_addr);
-
-		/* skb is only used once and than forw_packet is free'd */
-		batadv_send_skb_packet(forw_packet->skb,
-				       forw_packet->if_incoming,
-				       batadv_broadcast_addr);
-		forw_packet->skb = NULL;
-
+	if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE)
 		goto out;
-	}
 
-	/* broadcast on every interface */
-	rcu_read_lock();
-	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->soft_iface != soft_iface)
-			continue;
+	primary_if = batadv_primary_if_get_selected(bat_priv);
+	if (!primary_if)
+		goto out;
 
-		batadv_iv_ogm_send_to_if(forw_packet, hard_iface);
-	}
-	rcu_read_unlock();
+	/* only for one specific outgoing interface */
+	batadv_iv_ogm_send_to_if(forw_packet, forw_packet->if_outgoing);
 
 out:
 	if (primary_if)
 		batadv_hardif_free_ref(primary_if);
 }
 
-/* return true if new_packet can be aggregated with forw_packet */
+/**
+ * batadv_iv_ogm_can_aggregate - find out if an OGM can be aggregated on an
+ *  existing forward packet
+ * @new_bat_ogm_packet: OGM packet to be aggregated
+ * @bat_priv: the bat priv with all the soft interface information
+ * @packet_len: (total) length of the OGM
+ * @send_time: timestamp (jiffies) when the packet is to be sent
+ * @direktlink: true if this is a direct link packet
+ * @if_incoming: interface where the packet was received
+ * @if_outgoing: interface for which the retransmission should be considered
+ * @forw_packet: the forwarded packet which should be checked
+ *
+ * Returns true if new_packet can be aggregated with forw_packet
+ */
 static bool
 batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 			    struct batadv_priv *bat_priv,
 			    int packet_len, unsigned long send_time,
 			    bool directlink,
 			    const struct batadv_hard_iface *if_incoming,
+			    const struct batadv_hard_iface *if_outgoing,
 			    const struct batadv_forw_packet *forw_packet)
 {
 	struct batadv_ogm_packet *batadv_ogm_packet;
@@ -567,12 +563,16 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 		if (!primary_if)
 			goto out;
 
+		/* packet is not leaving on the same interface. */
+		if (forw_packet->if_outgoing != if_outgoing)
+			goto out;
+
 		/* packets without direct link flag and high TTL
 		 * are flooded through the net
 		 */
 		if ((!directlink) &&
 		    (!(batadv_ogm_packet->flags & BATADV_DIRECTLINK)) &&
-		    (batadv_ogm_packet->header.ttl != 1) &&
+		    (batadv_ogm_packet->ttl != 1) &&
 
 		    /* own packets originating non-primary
 		     * interfaces leave only that interface
@@ -587,7 +587,7 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 		 * interface only - we still can aggregate
 		 */
 		if ((directlink) &&
-		    (new_bat_ogm_packet->header.ttl == 1) &&
+		    (new_bat_ogm_packet->ttl == 1) &&
 		    (forw_packet->if_incoming == if_incoming) &&
 
 		    /* packets from direct neighbors or
@@ -608,11 +608,22 @@ out:
 	return res;
 }
 
-/* create a new aggregated packet and add this packet to it */
+/**
+ * batadv_iv_ogm_aggregate_new - create a new aggregated packet and add this
+ *  packet to it.
+ * @packet_buff: pointer to the OGM
+ * @packet_len: (total) length of the OGM
+ * @send_time: timestamp (jiffies) when the packet is to be sent
+ * @direct_link: whether this OGM has direct link status
+ * @if_incoming: interface where the packet was received
+ * @if_outgoing: interface for which the retransmission should be considered
+ * @own_packet: true if it is a self-generated ogm
+ */
 static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
 					int packet_len, unsigned long send_time,
 					bool direct_link,
 					struct batadv_hard_iface *if_incoming,
+					struct batadv_hard_iface *if_outgoing,
 					int own_packet)
 {
 	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
@@ -623,6 +634,9 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
 	if (!atomic_inc_not_zero(&if_incoming->refcount))
 		return;
 
+	if (!atomic_inc_not_zero(&if_outgoing->refcount))
+		goto out_free_incoming;
+
 	/* own packet should always be scheduled */
 	if (!own_packet) {
 		if (!batadv_atomic_dec_not_zero(&bat_priv->batman_queue_left)) {
@@ -663,6 +677,7 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
 
 	forw_packet_aggr->own = own_packet;
 	forw_packet_aggr->if_incoming = if_incoming;
+	forw_packet_aggr->if_outgoing = if_outgoing;
 	forw_packet_aggr->num_packets = 0;
 	forw_packet_aggr->direct_link_flags = BATADV_NO_FLAGS;
 	forw_packet_aggr->send_time = send_time;
@@ -685,6 +700,8 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
 
 	return;
 out:
+	batadv_hardif_free_ref(if_outgoing);
+out_free_incoming:
 	batadv_hardif_free_ref(if_incoming);
 }
 
@@ -708,10 +725,21 @@ static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr,
 	}
 }
 
+/**
+ * batadv_iv_ogm_queue_add - queue up an OGM for transmission
+ * @bat_priv: the bat priv with all the soft interface information
+ * @packet_buff: pointer to the OGM
+ * @packet_len: (total) length of the OGM
+ * @if_incoming: interface where the packet was received
+ * @if_outgoing: interface for which the retransmission should be considered
+ * @own_packet: true if it is a self-generated ogm
+ * @send_time: timestamp (jiffies) when the packet is to be sent
+ */
 static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv,
 				    unsigned char *packet_buff,
 				    int packet_len,
 				    struct batadv_hard_iface *if_incoming,
+				    struct batadv_hard_iface *if_outgoing,
 				    int own_packet, unsigned long send_time)
 {
 	/* _aggr -> pointer to the packet we want to aggregate with
@@ -737,6 +765,7 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv,
 							bat_priv, packet_len,
 							send_time, direct_link,
 							if_incoming,
+							if_outgoing,
 							forw_packet_pos)) {
 				forw_packet_aggr = forw_packet_pos;
 				break;
@@ -760,7 +789,8 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv,
 
 		batadv_iv_ogm_aggregate_new(packet_buff, packet_len,
 					    send_time, direct_link,
-					    if_incoming, own_packet);
+					    if_incoming, if_outgoing,
+					    own_packet);
 	} else {
 		batadv_iv_ogm_aggregate(forw_packet_aggr, packet_buff,
 					packet_len, direct_link);
@@ -773,12 +803,13 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node,
 				  struct batadv_ogm_packet *batadv_ogm_packet,
 				  bool is_single_hop_neigh,
 				  bool is_from_best_next_hop,
-				  struct batadv_hard_iface *if_incoming)
+				  struct batadv_hard_iface *if_incoming,
+				  struct batadv_hard_iface *if_outgoing)
 {
 	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
 	uint16_t tvlv_len;
 
-	if (batadv_ogm_packet->header.ttl <= 1) {
+	if (batadv_ogm_packet->ttl <= 1) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "ttl exceeded\n");
 		return;
 	}
@@ -798,8 +829,8 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node,
 
 	tvlv_len = ntohs(batadv_ogm_packet->tvlv_len);
 
-	batadv_ogm_packet->header.ttl--;
-	memcpy(batadv_ogm_packet->prev_sender, ethhdr->h_source, ETH_ALEN);
+	batadv_ogm_packet->ttl--;
+	ether_addr_copy(batadv_ogm_packet->prev_sender, ethhdr->h_source);
 
 	/* apply hop penalty */
 	batadv_ogm_packet->tq = batadv_hop_penalty(batadv_ogm_packet->tq,
@@ -807,7 +838,7 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node,
 
 	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 		   "Forwarding packet: tq: %i, ttl: %i\n",
-		   batadv_ogm_packet->tq, batadv_ogm_packet->header.ttl);
+		   batadv_ogm_packet->tq, batadv_ogm_packet->ttl);
 
 	/* switch of primaries first hop flag when forwarding */
 	batadv_ogm_packet->flags &= ~BATADV_PRIMARIES_FIRST_HOP;
@@ -818,7 +849,8 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node,
 
 	batadv_iv_ogm_queue_add(bat_priv, (unsigned char *)batadv_ogm_packet,
 				BATADV_OGM_HLEN + tvlv_len,
-				if_incoming, 0, batadv_iv_ogm_fwd_send_time());
+				if_incoming, if_outgoing, 0,
+				batadv_iv_ogm_fwd_send_time());
 }
 
 /**
@@ -863,10 +895,11 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
 	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
 	unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff;
 	struct batadv_ogm_packet *batadv_ogm_packet;
-	struct batadv_hard_iface *primary_if;
+	struct batadv_hard_iface *primary_if, *tmp_hard_iface;
 	int *ogm_buff_len = &hard_iface->bat_iv.ogm_buff_len;
 	uint32_t seqno;
 	uint16_t tvlv_len = 0;
+	unsigned long send_time;
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 
@@ -889,23 +922,60 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
 	atomic_inc(&hard_iface->bat_iv.ogm_seqno);
 
 	batadv_iv_ogm_slide_own_bcast_window(hard_iface);
-	batadv_iv_ogm_queue_add(bat_priv, hard_iface->bat_iv.ogm_buff,
-				hard_iface->bat_iv.ogm_buff_len, hard_iface, 1,
-				batadv_iv_ogm_emit_send_time(bat_priv));
 
+	send_time = batadv_iv_ogm_emit_send_time(bat_priv);
+
+	if (hard_iface != primary_if) {
+		/* OGMs from secondary interfaces are only scheduled on their
+		 * respective interfaces.
+		 */
+		batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, *ogm_buff_len,
+					hard_iface, hard_iface, 1, send_time);
+		goto out;
+	}
+
+	/* OGMs from primary interfaces are scheduled on all
+	 * interfaces.
+	 */
+	rcu_read_lock();
+	list_for_each_entry_rcu(tmp_hard_iface, &batadv_hardif_list, list) {
+		if (tmp_hard_iface->soft_iface != hard_iface->soft_iface)
+				continue;
+		batadv_iv_ogm_queue_add(bat_priv, *ogm_buff,
+					*ogm_buff_len, hard_iface,
+					tmp_hard_iface, 1, send_time);
+	}
+	rcu_read_unlock();
+
+out:
 	if (primary_if)
 		batadv_hardif_free_ref(primary_if);
 }
 
+/**
+ * batadv_iv_ogm_orig_update - use OGM to update corresponding data in an
+ *  originator
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: the orig node who originally emitted the ogm packet
+ * @orig_ifinfo: ifinfo for the outgoing interface of the orig_node
+ * @ethhdr: Ethernet header of the OGM
+ * @batadv_ogm_packet: the ogm packet
+ * @if_incoming: interface where the packet was received
+ * @if_outgoing: interface for which the retransmission should be considered
+ * @dup_status: the duplicate status of this ogm packet.
+ */
 static void
 batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
 			  struct batadv_orig_node *orig_node,
+			  struct batadv_orig_ifinfo *orig_ifinfo,
 			  const struct ethhdr *ethhdr,
 			  const struct batadv_ogm_packet *batadv_ogm_packet,
 			  struct batadv_hard_iface *if_incoming,
-			  const unsigned char *tt_buff,
+			  struct batadv_hard_iface *if_outgoing,
 			  enum batadv_dup_status dup_status)
 {
+	struct batadv_neigh_ifinfo *neigh_ifinfo = NULL;
+	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
 	struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL;
 	struct batadv_neigh_node *router = NULL;
 	struct batadv_orig_node *orig_node_tmp;
@@ -933,12 +1003,21 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
 		if (dup_status != BATADV_NO_DUP)
 			continue;
 
-		spin_lock_bh(&tmp_neigh_node->bat_iv.lq_update_lock);
-		batadv_ring_buffer_set(tmp_neigh_node->bat_iv.tq_recv,
-				       &tmp_neigh_node->bat_iv.tq_index, 0);
-		tq_avg = batadv_ring_buffer_avg(tmp_neigh_node->bat_iv.tq_recv);
-		tmp_neigh_node->bat_iv.tq_avg = tq_avg;
-		spin_unlock_bh(&tmp_neigh_node->bat_iv.lq_update_lock);
+		/* only update the entry for this outgoing interface */
+		neigh_ifinfo = batadv_neigh_ifinfo_get(tmp_neigh_node,
+						       if_outgoing);
+		if (!neigh_ifinfo)
+			continue;
+
+		spin_lock_bh(&tmp_neigh_node->ifinfo_lock);
+		batadv_ring_buffer_set(neigh_ifinfo->bat_iv.tq_recv,
+				       &neigh_ifinfo->bat_iv.tq_index, 0);
+		tq_avg = batadv_ring_buffer_avg(neigh_ifinfo->bat_iv.tq_recv);
+		neigh_ifinfo->bat_iv.tq_avg = tq_avg;
+		spin_unlock_bh(&tmp_neigh_node->ifinfo_lock);
+
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
+		neigh_ifinfo = NULL;
 	}
 
 	if (!neigh_node) {
@@ -960,39 +1039,49 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
 			   "Updating existing last-hop neighbor of originator\n");
 
 	rcu_read_unlock();
+	neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing);
+	if (!neigh_ifinfo)
+		goto out;
 
 	neigh_node->last_seen = jiffies;
 
-	spin_lock_bh(&neigh_node->bat_iv.lq_update_lock);
-	batadv_ring_buffer_set(neigh_node->bat_iv.tq_recv,
-			       &neigh_node->bat_iv.tq_index,
+	spin_lock_bh(&neigh_node->ifinfo_lock);
+	batadv_ring_buffer_set(neigh_ifinfo->bat_iv.tq_recv,
+			       &neigh_ifinfo->bat_iv.tq_index,
 			       batadv_ogm_packet->tq);
-	tq_avg = batadv_ring_buffer_avg(neigh_node->bat_iv.tq_recv);
-	neigh_node->bat_iv.tq_avg = tq_avg;
-	spin_unlock_bh(&neigh_node->bat_iv.lq_update_lock);
+	tq_avg = batadv_ring_buffer_avg(neigh_ifinfo->bat_iv.tq_recv);
+	neigh_ifinfo->bat_iv.tq_avg = tq_avg;
+	spin_unlock_bh(&neigh_node->ifinfo_lock);
 
 	if (dup_status == BATADV_NO_DUP) {
-		orig_node->last_ttl = batadv_ogm_packet->header.ttl;
-		neigh_node->last_ttl = batadv_ogm_packet->header.ttl;
+		orig_ifinfo->last_ttl = batadv_ogm_packet->ttl;
+		neigh_ifinfo->last_ttl = batadv_ogm_packet->ttl;
 	}
 
-	batadv_bonding_candidate_add(bat_priv, orig_node, neigh_node);
-
 	/* if this neighbor already is our next hop there is nothing
 	 * to change
 	 */
-	router = batadv_orig_node_get_router(orig_node);
+	router = batadv_orig_router_get(orig_node, if_outgoing);
 	if (router == neigh_node)
 		goto out;
 
-	/* if this neighbor does not offer a better TQ we won't consider it */
-	if (router && (router->bat_iv.tq_avg > neigh_node->bat_iv.tq_avg))
-		goto out;
+	if (router) {
+		router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing);
+		if (!router_ifinfo)
+			goto out;
+
+		/* if this neighbor does not offer a better TQ we won't
+		 * consider it
+		 */
+		if (router_ifinfo->bat_iv.tq_avg > neigh_ifinfo->bat_iv.tq_avg)
+			goto out;
+	}
 
 	/* if the TQ is the same and the link not more symmetric we
 	 * won't consider it either
 	 */
-	if (router && (neigh_node->bat_iv.tq_avg == router->bat_iv.tq_avg)) {
+	if (router_ifinfo &&
+	    (neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg)) {
 		orig_node_tmp = router->orig_node;
 		spin_lock_bh(&orig_node_tmp->bat_iv.ogm_cnt_lock);
 		if_num = router->if_incoming->if_num;
@@ -1009,7 +1098,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
 			goto out;
 	}
 
-	batadv_update_route(bat_priv, orig_node, neigh_node);
+	batadv_update_route(bat_priv, orig_node, if_outgoing, neigh_node);
 	goto out;
 
 unlock:
@@ -1019,20 +1108,37 @@ out:
 		batadv_neigh_node_free_ref(neigh_node);
 	if (router)
 		batadv_neigh_node_free_ref(router);
+	if (neigh_ifinfo)
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
+	if (router_ifinfo)
+		batadv_neigh_ifinfo_free_ref(router_ifinfo);
 }
 
+/**
+ * batadv_iv_ogm_calc_tq - calculate tq for current received ogm packet
+ * @orig_node: the orig node who originally emitted the ogm packet
+ * @orig_neigh_node: the orig node struct of the neighbor who sent the packet
+ * @batadv_ogm_packet: the ogm packet
+ * @if_incoming: interface where the packet was received
+ * @if_outgoing: interface for which the retransmission should be considered
+ *
+ * Returns 1 if the link can be considered bidirectional, 0 otherwise
+ */
 static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node,
 				 struct batadv_orig_node *orig_neigh_node,
 				 struct batadv_ogm_packet *batadv_ogm_packet,
-				 struct batadv_hard_iface *if_incoming)
+				 struct batadv_hard_iface *if_incoming,
+				 struct batadv_hard_iface *if_outgoing)
 {
 	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
 	struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node;
+	struct batadv_neigh_ifinfo *neigh_ifinfo;
 	uint8_t total_count;
 	uint8_t orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own;
 	unsigned int neigh_rq_inv_cube, neigh_rq_max_cube;
 	int tq_asym_penalty, inv_asym_penalty, if_num, ret = 0;
 	unsigned int combined_tq;
+	int tq_iface_penalty;
 
 	/* find corresponding one hop neighbor */
 	rcu_read_lock();
@@ -1072,7 +1178,13 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node,
 	spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock);
 	if_num = if_incoming->if_num;
 	orig_eq_count = orig_neigh_node->bat_iv.bcast_own_sum[if_num];
-	neigh_rq_count = neigh_node->bat_iv.real_packet_count;
+	neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing);
+	if (neigh_ifinfo) {
+		neigh_rq_count = neigh_ifinfo->bat_iv.real_packet_count;
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
+	} else {
+		neigh_rq_count = 0;
+	}
 	spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock);
 
 	/* pay attention to not get a value bigger than 100 % */
@@ -1108,15 +1220,31 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node,
 	inv_asym_penalty /= neigh_rq_max_cube;
 	tq_asym_penalty = BATADV_TQ_MAX_VALUE - inv_asym_penalty;
 
-	combined_tq = batadv_ogm_packet->tq * tq_own * tq_asym_penalty;
-	combined_tq /= BATADV_TQ_MAX_VALUE * BATADV_TQ_MAX_VALUE;
+	/* penalize if the OGM is forwarded on the same interface. WiFi
+	 * interfaces and other half duplex devices suffer from throughput
+	 * drops as they can't send and receive at the same time.
+	 */
+	tq_iface_penalty = BATADV_TQ_MAX_VALUE;
+	if (if_outgoing && (if_incoming == if_outgoing) &&
+	    batadv_is_wifi_netdev(if_outgoing->net_dev))
+		tq_iface_penalty = batadv_hop_penalty(BATADV_TQ_MAX_VALUE,
+						      bat_priv);
+
+	combined_tq = batadv_ogm_packet->tq *
+		      tq_own *
+		      tq_asym_penalty *
+		      tq_iface_penalty;
+	combined_tq /= BATADV_TQ_MAX_VALUE *
+		       BATADV_TQ_MAX_VALUE *
+		       BATADV_TQ_MAX_VALUE;
 	batadv_ogm_packet->tq = combined_tq;
 
 	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-		   "bidirectional: orig = %-15pM neigh = %-15pM => own_bcast = %2i, real recv = %2i, local tq: %3i, asym_penalty: %3i, total tq: %3i\n",
+		   "bidirectional: orig = %-15pM neigh = %-15pM => own_bcast = %2i, real recv = %2i, local tq: %3i, asym_penalty: %3i, iface_penalty: %3i, total tq: %3i, if_incoming = %s, if_outgoing = %s\n",
 		   orig_node->orig, orig_neigh_node->orig, total_count,
-		   neigh_rq_count, tq_own,
-		   tq_asym_penalty, batadv_ogm_packet->tq);
+		   neigh_rq_count, tq_own, tq_asym_penalty, tq_iface_penalty,
+		   batadv_ogm_packet->tq, if_incoming->net_dev->name,
+		   if_outgoing ? if_outgoing->net_dev->name : "DEFAULT");
 
 	/* if link has the minimum required transmission quality
 	 * consider it bidirectional
@@ -1136,17 +1264,21 @@ out:
  * @ethhdr: ethernet header of the packet
  * @batadv_ogm_packet: OGM packet to be considered
  * @if_incoming: interface on which the OGM packet was received
+ * @if_outgoing: interface for which the retransmission should be considered
  *
  * Returns duplicate status as enum batadv_dup_status
  */
 static enum batadv_dup_status
 batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr,
 			    const struct batadv_ogm_packet *batadv_ogm_packet,
-			    const struct batadv_hard_iface *if_incoming)
+			    const struct batadv_hard_iface *if_incoming,
+			    struct batadv_hard_iface *if_outgoing)
 {
 	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
 	struct batadv_orig_node *orig_node;
-	struct batadv_neigh_node *tmp_neigh_node;
+	struct batadv_orig_ifinfo *orig_ifinfo = NULL;
+	struct batadv_neigh_node *neigh_node;
+	struct batadv_neigh_ifinfo *neigh_ifinfo;
 	int is_dup;
 	int32_t seq_diff;
 	int need_update = 0;
@@ -1161,27 +1293,37 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr,
 	if (!orig_node)
 		return BATADV_NO_DUP;
 
+	orig_ifinfo = batadv_orig_ifinfo_new(orig_node, if_outgoing);
+	if (WARN_ON(!orig_ifinfo)) {
+		batadv_orig_node_free_ref(orig_node);
+		return 0;
+	}
+
 	spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock);
-	seq_diff = seqno - orig_node->last_real_seqno;
+	seq_diff = seqno - orig_ifinfo->last_real_seqno;
 
 	/* signalize caller that the packet is to be dropped. */
 	if (!hlist_empty(&orig_node->neigh_list) &&
 	    batadv_window_protected(bat_priv, seq_diff,
-				    &orig_node->batman_seqno_reset)) {
+				    &orig_ifinfo->batman_seqno_reset)) {
 		ret = BATADV_PROTECTED;
 		goto out;
 	}
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(tmp_neigh_node,
-				 &orig_node->neigh_list, list) {
-		neigh_addr = tmp_neigh_node->addr;
-		is_dup = batadv_test_bit(tmp_neigh_node->bat_iv.real_bits,
-					 orig_node->last_real_seqno,
+	hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) {
+		neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node,
+						       if_outgoing);
+		if (!neigh_ifinfo)
+			continue;
+
+		neigh_addr = neigh_node->addr;
+		is_dup = batadv_test_bit(neigh_ifinfo->bat_iv.real_bits,
+					 orig_ifinfo->last_real_seqno,
 					 seqno);
 
 		if (batadv_compare_eth(neigh_addr, ethhdr->h_source) &&
-		    tmp_neigh_node->if_incoming == if_incoming) {
+		    neigh_node->if_incoming == if_incoming) {
 			set_mark = 1;
 			if (is_dup)
 				ret = BATADV_NEIGH_DUP;
@@ -1192,173 +1334,78 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr,
 		}
 
 		/* if the window moved, set the update flag. */
-		bitmap = tmp_neigh_node->bat_iv.real_bits;
+		bitmap = neigh_ifinfo->bat_iv.real_bits;
 		need_update |= batadv_bit_get_packet(bat_priv, bitmap,
 						     seq_diff, set_mark);
 
-		packet_count = bitmap_weight(tmp_neigh_node->bat_iv.real_bits,
+		packet_count = bitmap_weight(bitmap,
 					     BATADV_TQ_LOCAL_WINDOW_SIZE);
-		tmp_neigh_node->bat_iv.real_packet_count = packet_count;
+		neigh_ifinfo->bat_iv.real_packet_count = packet_count;
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
 	}
 	rcu_read_unlock();
 
 	if (need_update) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-			   "updating last_seqno: old %u, new %u\n",
-			   orig_node->last_real_seqno, seqno);
-		orig_node->last_real_seqno = seqno;
+			   "%s updating last_seqno: old %u, new %u\n",
+			   if_outgoing ? if_outgoing->net_dev->name : "DEFAULT",
+			   orig_ifinfo->last_real_seqno, seqno);
+		orig_ifinfo->last_real_seqno = seqno;
 	}
 
 out:
 	spin_unlock_bh(&orig_node->bat_iv.ogm_cnt_lock);
 	batadv_orig_node_free_ref(orig_node);
+	if (orig_ifinfo)
+		batadv_orig_ifinfo_free_ref(orig_ifinfo);
 	return ret;
 }
 
-static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
-				  struct batadv_ogm_packet *batadv_ogm_packet,
-				  const unsigned char *tt_buff,
-				  struct batadv_hard_iface *if_incoming)
+
+/**
+ * batadv_iv_ogm_process_per_outif - process a batman iv OGM for an outgoing if
+ * @skb: the skb containing the OGM
+ * @orig_node: the (cached) orig node for the originator of this OGM
+ * @if_incoming: the interface where this packet was received
+ * @if_outgoing: the interface for which the packet should be considered
+ */
+static void
+batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
+				struct batadv_orig_node *orig_node,
+				struct batadv_hard_iface *if_incoming,
+				struct batadv_hard_iface *if_outgoing)
 {
 	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
-	struct batadv_hard_iface *hard_iface;
-	struct batadv_orig_node *orig_neigh_node, *orig_node, *orig_node_tmp;
 	struct batadv_neigh_node *router = NULL, *router_router = NULL;
+	struct batadv_orig_node *orig_neigh_node;
+	struct batadv_orig_ifinfo *orig_ifinfo;
 	struct batadv_neigh_node *orig_neigh_router = NULL;
-	int has_directlink_flag;
-	int is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0;
-	int is_bidirect;
-	bool is_single_hop_neigh = false;
-	bool is_from_best_next_hop = false;
-	int sameseq, similar_ttl;
+	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
+	struct batadv_ogm_packet *ogm_packet;
 	enum batadv_dup_status dup_status;
-	uint32_t if_incoming_seqno;
+	bool is_from_best_next_hop = false;
+	bool is_single_hop_neigh = false;
+	bool sameseq, similar_ttl;
+	struct sk_buff *skb_priv;
+	struct ethhdr *ethhdr;
 	uint8_t *prev_sender;
+	int is_bidirect;
 
-	/* Silently drop when the batman packet is actually not a
-	 * correct packet.
-	 *
-	 * This might happen if a packet is padded (e.g. Ethernet has a
-	 * minimum frame length of 64 byte) and the aggregation interprets
-	 * it as an additional length.
-	 *
-	 * TODO: A more sane solution would be to have a bit in the
-	 * batadv_ogm_packet to detect whether the packet is the last
-	 * packet in an aggregation.  Here we expect that the padding
-	 * is always zero (or not 0x01)
+	/* create a private copy of the skb, as some functions change tq value
+	 * and/or flags.
 	 */
-	if (batadv_ogm_packet->header.packet_type != BATADV_IV_OGM)
+	skb_priv = skb_copy(skb, GFP_ATOMIC);
+	if (!skb_priv)
 		return;
 
-	/* could be changed by schedule_own_packet() */
-	if_incoming_seqno = atomic_read(&if_incoming->bat_iv.ogm_seqno);
-
-	if (batadv_ogm_packet->flags & BATADV_DIRECTLINK)
-		has_directlink_flag = 1;
-	else
-		has_directlink_flag = 0;
+	ethhdr = eth_hdr(skb_priv);
+	ogm_packet = (struct batadv_ogm_packet *)(skb_priv->data + ogm_offset);
 
-	if (batadv_compare_eth(ethhdr->h_source, batadv_ogm_packet->orig))
+	dup_status = batadv_iv_ogm_update_seqnos(ethhdr, ogm_packet,
+						 if_incoming, if_outgoing);
+	if (batadv_compare_eth(ethhdr->h_source, ogm_packet->orig))
 		is_single_hop_neigh = true;
 
-	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-		   "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, tq %d, TTL %d, V %d, IDF %d)\n",
-		   ethhdr->h_source, if_incoming->net_dev->name,
-		   if_incoming->net_dev->dev_addr, batadv_ogm_packet->orig,
-		   batadv_ogm_packet->prev_sender,
-		   ntohl(batadv_ogm_packet->seqno), batadv_ogm_packet->tq,
-		   batadv_ogm_packet->header.ttl,
-		   batadv_ogm_packet->header.version, has_directlink_flag);
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->if_status != BATADV_IF_ACTIVE)
-			continue;
-
-		if (hard_iface->soft_iface != if_incoming->soft_iface)
-			continue;
-
-		if (batadv_compare_eth(ethhdr->h_source,
-				       hard_iface->net_dev->dev_addr))
-			is_my_addr = 1;
-
-		if (batadv_compare_eth(batadv_ogm_packet->orig,
-				       hard_iface->net_dev->dev_addr))
-			is_my_orig = 1;
-
-		if (batadv_compare_eth(batadv_ogm_packet->prev_sender,
-				       hard_iface->net_dev->dev_addr))
-			is_my_oldorig = 1;
-	}
-	rcu_read_unlock();
-
-	if (is_my_addr) {
-		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-			   "Drop packet: received my own broadcast (sender: %pM)\n",
-			   ethhdr->h_source);
-		return;
-	}
-
-	if (is_my_orig) {
-		unsigned long *word;
-		int offset;
-		int32_t bit_pos;
-		int16_t if_num;
-		uint8_t *weight;
-
-		orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv,
-							 ethhdr->h_source);
-		if (!orig_neigh_node)
-			return;
-
-		/* neighbor has to indicate direct link and it has to
-		 * come via the corresponding interface
-		 * save packet seqno for bidirectional check
-		 */
-		if (has_directlink_flag &&
-		    batadv_compare_eth(if_incoming->net_dev->dev_addr,
-				       batadv_ogm_packet->orig)) {
-			if_num = if_incoming->if_num;
-			offset = if_num * BATADV_NUM_WORDS;
-
-			spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock);
-			word = &(orig_neigh_node->bat_iv.bcast_own[offset]);
-			bit_pos = if_incoming_seqno - 2;
-			bit_pos -= ntohl(batadv_ogm_packet->seqno);
-			batadv_set_bit(word, bit_pos);
-			weight = &orig_neigh_node->bat_iv.bcast_own_sum[if_num];
-			*weight = bitmap_weight(word,
-						BATADV_TQ_LOCAL_WINDOW_SIZE);
-			spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock);
-		}
-
-		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-			   "Drop packet: originator packet from myself (via neighbor)\n");
-		batadv_orig_node_free_ref(orig_neigh_node);
-		return;
-	}
-
-	if (is_my_oldorig) {
-		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-			   "Drop packet: ignoring all rebroadcast echos (sender: %pM)\n",
-			   ethhdr->h_source);
-		return;
-	}
-
-	if (batadv_ogm_packet->flags & BATADV_NOT_BEST_NEXT_HOP) {
-		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-			   "Drop packet: ignoring all packets not forwarded from the best next hop (sender: %pM)\n",
-			   ethhdr->h_source);
-		return;
-	}
-
-	orig_node = batadv_iv_ogm_orig_get(bat_priv, batadv_ogm_packet->orig);
-	if (!orig_node)
-		return;
-
-	dup_status = batadv_iv_ogm_update_seqnos(ethhdr, batadv_ogm_packet,
-						 if_incoming);
-
 	if (dup_status == BATADV_PROTECTED) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Drop packet: packet within seqno protection time (sender: %pM)\n",
@@ -1366,27 +1413,28 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
 		goto out;
 	}
 
-	if (batadv_ogm_packet->tq == 0) {
+	if (ogm_packet->tq == 0) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Drop packet: originator packet with tq equal 0\n");
 		goto out;
 	}
 
-	router = batadv_orig_node_get_router(orig_node);
+	router = batadv_orig_router_get(orig_node, if_outgoing);
 	if (router) {
-		orig_node_tmp = router->orig_node;
-		router_router = batadv_orig_node_get_router(orig_node_tmp);
+		router_router = batadv_orig_router_get(router->orig_node,
+						       if_outgoing);
+		router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing);
 	}
 
-	if ((router && router->bat_iv.tq_avg != 0) &&
+	if ((router_ifinfo && router_ifinfo->bat_iv.tq_avg != 0) &&
 	    (batadv_compare_eth(router->addr, ethhdr->h_source)))
 		is_from_best_next_hop = true;
 
-	prev_sender = batadv_ogm_packet->prev_sender;
+	prev_sender = ogm_packet->prev_sender;
 	/* avoid temporary routing loops */
 	if (router && router_router &&
 	    (batadv_compare_eth(router->addr, prev_sender)) &&
-	    !(batadv_compare_eth(batadv_ogm_packet->orig, prev_sender)) &&
+	    !(batadv_compare_eth(ogm_packet->orig, prev_sender)) &&
 	    (batadv_compare_eth(router->addr, router_router->addr))) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Drop packet: ignoring all rebroadcast packets that may make me loop (sender: %pM)\n",
@@ -1394,7 +1442,8 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
 		goto out;
 	}
 
-	batadv_tvlv_ogm_receive(bat_priv, batadv_ogm_packet, orig_node);
+	if (if_outgoing == BATADV_IF_DEFAULT)
+		batadv_tvlv_ogm_receive(bat_priv, ogm_packet, orig_node);
 
 	/* if sender is a direct neighbor the sender mac equals
 	 * originator mac
@@ -1410,9 +1459,10 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
 
 	/* Update nc_nodes of the originator */
 	batadv_nc_update_nc_node(bat_priv, orig_node, orig_neigh_node,
-				 batadv_ogm_packet, is_single_hop_neigh);
+				 ogm_packet, is_single_hop_neigh);
 
-	orig_neigh_router = batadv_orig_node_get_router(orig_neigh_node);
+	orig_neigh_router = batadv_orig_router_get(orig_neigh_node,
+						   if_outgoing);
 
 	/* drop packet if sender is not a direct neighbor and if we
 	 * don't route towards it
@@ -1424,28 +1474,48 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
 	}
 
 	is_bidirect = batadv_iv_ogm_calc_tq(orig_node, orig_neigh_node,
-					    batadv_ogm_packet, if_incoming);
-
-	batadv_bonding_save_primary(orig_node, orig_neigh_node,
-				    batadv_ogm_packet);
+					    ogm_packet, if_incoming,
+					    if_outgoing);
 
 	/* update ranking if it is not a duplicate or has the same
 	 * seqno and similar ttl as the non-duplicate
 	 */
-	sameseq = orig_node->last_real_seqno == ntohl(batadv_ogm_packet->seqno);
-	similar_ttl = orig_node->last_ttl - 3 <= batadv_ogm_packet->header.ttl;
+	orig_ifinfo = batadv_orig_ifinfo_new(orig_node, if_outgoing);
+	if (!orig_ifinfo)
+		goto out_neigh;
+
+	sameseq = orig_ifinfo->last_real_seqno == ntohl(ogm_packet->seqno);
+	similar_ttl = (orig_ifinfo->last_ttl - 3) <= ogm_packet->ttl;
+
 	if (is_bidirect && ((dup_status == BATADV_NO_DUP) ||
-			    (sameseq && similar_ttl)))
-		batadv_iv_ogm_orig_update(bat_priv, orig_node, ethhdr,
-					  batadv_ogm_packet, if_incoming,
-					  tt_buff, dup_status);
+			    (sameseq && similar_ttl))) {
+		batadv_iv_ogm_orig_update(bat_priv, orig_node,
+					  orig_ifinfo, ethhdr,
+					  ogm_packet, if_incoming,
+					  if_outgoing, dup_status);
+	}
+	batadv_orig_ifinfo_free_ref(orig_ifinfo);
+
+	/* only forward for specific interface, not for the default one. */
+	if (if_outgoing == BATADV_IF_DEFAULT)
+		goto out_neigh;
 
 	/* is single hop (direct) neighbor */
 	if (is_single_hop_neigh) {
+		/* OGMs from secondary interfaces should only scheduled once
+		 * per interface where it has been received, not multiple times
+		 */
+		if ((ogm_packet->ttl <= 2) &&
+		    (if_incoming != if_outgoing)) {
+			batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+				   "Drop packet: OGM from secondary interface and wrong outgoing interface\n");
+			goto out_neigh;
+		}
 		/* mark direct link on incoming interface */
-		batadv_iv_ogm_forward(orig_node, ethhdr, batadv_ogm_packet,
+		batadv_iv_ogm_forward(orig_node, ethhdr, ogm_packet,
 				      is_single_hop_neigh,
-				      is_from_best_next_hop, if_incoming);
+				      is_from_best_next_hop, if_incoming,
+				      if_outgoing);
 
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Forwarding packet: rebroadcast neighbor packet with direct link flag\n");
@@ -1467,14 +1537,16 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
 
 	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 		   "Forwarding packet: rebroadcast originator packet\n");
-	batadv_iv_ogm_forward(orig_node, ethhdr, batadv_ogm_packet,
+	batadv_iv_ogm_forward(orig_node, ethhdr, ogm_packet,
 			      is_single_hop_neigh, is_from_best_next_hop,
-			      if_incoming);
+			      if_incoming, if_outgoing);
 
 out_neigh:
 	if ((orig_neigh_node) && (!is_single_hop_neigh))
 		batadv_orig_node_free_ref(orig_neigh_node);
 out:
+	if (router_ifinfo)
+		batadv_neigh_ifinfo_free_ref(router_ifinfo);
 	if (router)
 		batadv_neigh_node_free_ref(router);
 	if (router_router)
@@ -1482,6 +1554,165 @@ out:
 	if (orig_neigh_router)
 		batadv_neigh_node_free_ref(orig_neigh_router);
 
+	kfree_skb(skb_priv);
+}
+
+/**
+ * batadv_iv_ogm_process - process an incoming batman iv OGM
+ * @skb: the skb containing the OGM
+ * @ogm_offset: offset to the OGM which should be processed (for aggregates)
+ * @if_incoming: the interface where this packet was receved
+ */
+static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset,
+				  struct batadv_hard_iface *if_incoming)
+{
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_orig_node *orig_neigh_node, *orig_node;
+	struct batadv_hard_iface *hard_iface;
+	struct batadv_ogm_packet *ogm_packet;
+	uint32_t if_incoming_seqno;
+	bool has_directlink_flag;
+	struct ethhdr *ethhdr;
+	bool is_my_oldorig = false;
+	bool is_my_addr = false;
+	bool is_my_orig = false;
+
+	ogm_packet = (struct batadv_ogm_packet *)(skb->data + ogm_offset);
+	ethhdr = eth_hdr(skb);
+
+	/* Silently drop when the batman packet is actually not a
+	 * correct packet.
+	 *
+	 * This might happen if a packet is padded (e.g. Ethernet has a
+	 * minimum frame length of 64 byte) and the aggregation interprets
+	 * it as an additional length.
+	 *
+	 * TODO: A more sane solution would be to have a bit in the
+	 * batadv_ogm_packet to detect whether the packet is the last
+	 * packet in an aggregation.  Here we expect that the padding
+	 * is always zero (or not 0x01)
+	 */
+	if (ogm_packet->packet_type != BATADV_IV_OGM)
+		return;
+
+	/* could be changed by schedule_own_packet() */
+	if_incoming_seqno = atomic_read(&if_incoming->bat_iv.ogm_seqno);
+
+	if (ogm_packet->flags & BATADV_DIRECTLINK)
+		has_directlink_flag = true;
+	else
+		has_directlink_flag = false;
+
+	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+		   "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, tq %d, TTL %d, V %d, IDF %d)\n",
+		   ethhdr->h_source, if_incoming->net_dev->name,
+		   if_incoming->net_dev->dev_addr, ogm_packet->orig,
+		   ogm_packet->prev_sender, ntohl(ogm_packet->seqno),
+		   ogm_packet->tq, ogm_packet->ttl,
+		   ogm_packet->version, has_directlink_flag);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
+		if (hard_iface->if_status != BATADV_IF_ACTIVE)
+			continue;
+
+		if (hard_iface->soft_iface != if_incoming->soft_iface)
+			continue;
+
+		if (batadv_compare_eth(ethhdr->h_source,
+				       hard_iface->net_dev->dev_addr))
+			is_my_addr = true;
+
+		if (batadv_compare_eth(ogm_packet->orig,
+				       hard_iface->net_dev->dev_addr))
+			is_my_orig = true;
+
+		if (batadv_compare_eth(ogm_packet->prev_sender,
+				       hard_iface->net_dev->dev_addr))
+			is_my_oldorig = true;
+	}
+	rcu_read_unlock();
+
+	if (is_my_addr) {
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "Drop packet: received my own broadcast (sender: %pM)\n",
+			   ethhdr->h_source);
+		return;
+	}
+
+	if (is_my_orig) {
+		unsigned long *word;
+		int offset;
+		int32_t bit_pos;
+		int16_t if_num;
+		uint8_t *weight;
+
+		orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv,
+							 ethhdr->h_source);
+		if (!orig_neigh_node)
+			return;
+
+		/* neighbor has to indicate direct link and it has to
+		 * come via the corresponding interface
+		 * save packet seqno for bidirectional check
+		 */
+		if (has_directlink_flag &&
+		    batadv_compare_eth(if_incoming->net_dev->dev_addr,
+				       ogm_packet->orig)) {
+			if_num = if_incoming->if_num;
+			offset = if_num * BATADV_NUM_WORDS;
+
+			spin_lock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock);
+			word = &(orig_neigh_node->bat_iv.bcast_own[offset]);
+			bit_pos = if_incoming_seqno - 2;
+			bit_pos -= ntohl(ogm_packet->seqno);
+			batadv_set_bit(word, bit_pos);
+			weight = &orig_neigh_node->bat_iv.bcast_own_sum[if_num];
+			*weight = bitmap_weight(word,
+						BATADV_TQ_LOCAL_WINDOW_SIZE);
+			spin_unlock_bh(&orig_neigh_node->bat_iv.ogm_cnt_lock);
+		}
+
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "Drop packet: originator packet from myself (via neighbor)\n");
+		batadv_orig_node_free_ref(orig_neigh_node);
+		return;
+	}
+
+	if (is_my_oldorig) {
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "Drop packet: ignoring all rebroadcast echos (sender: %pM)\n",
+			   ethhdr->h_source);
+		return;
+	}
+
+	if (ogm_packet->flags & BATADV_NOT_BEST_NEXT_HOP) {
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "Drop packet: ignoring all packets not forwarded from the best next hop (sender: %pM)\n",
+			   ethhdr->h_source);
+		return;
+	}
+
+	orig_node = batadv_iv_ogm_orig_get(bat_priv, ogm_packet->orig);
+	if (!orig_node)
+		return;
+
+	batadv_iv_ogm_process_per_outif(skb, ogm_offset, orig_node,
+					if_incoming, BATADV_IF_DEFAULT);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
+		if (hard_iface->if_status != BATADV_IF_ACTIVE)
+			continue;
+
+		if (hard_iface->soft_iface != bat_priv->soft_iface)
+			continue;
+
+		batadv_iv_ogm_process_per_outif(skb, ogm_offset, orig_node,
+						if_incoming, hard_iface);
+	}
+	rcu_read_unlock();
+
 	batadv_orig_node_free_ref(orig_node);
 }
 
@@ -1489,11 +1720,9 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb,
 				 struct batadv_hard_iface *if_incoming)
 {
 	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
-	struct batadv_ogm_packet *batadv_ogm_packet;
-	struct ethhdr *ethhdr;
-	int buff_pos = 0, packet_len;
-	unsigned char *tvlv_buff, *packet_buff;
+	struct batadv_ogm_packet *ogm_packet;
 	uint8_t *packet_pos;
+	int ogm_offset;
 	bool ret;
 
 	ret = batadv_check_management_packet(skb, if_incoming, BATADV_OGM_HLEN);
@@ -1510,24 +1739,19 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb,
 	batadv_add_counter(bat_priv, BATADV_CNT_MGMT_RX_BYTES,
 			   skb->len + ETH_HLEN);
 
-	packet_len = skb_headlen(skb);
-	ethhdr = eth_hdr(skb);
-	packet_buff = skb->data;
-	batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff;
+	ogm_offset = 0;
+	ogm_packet = (struct batadv_ogm_packet *)skb->data;
 
 	/* unpack the aggregated packets and process them one by one */
-	while (batadv_iv_ogm_aggr_packet(buff_pos, packet_len,
-					 batadv_ogm_packet->tvlv_len)) {
-		tvlv_buff = packet_buff + buff_pos + BATADV_OGM_HLEN;
+	while (batadv_iv_ogm_aggr_packet(ogm_offset, skb_headlen(skb),
+					 ogm_packet->tvlv_len)) {
+		batadv_iv_ogm_process(skb, ogm_offset, if_incoming);
 
-		batadv_iv_ogm_process(ethhdr, batadv_ogm_packet,
-				      tvlv_buff, if_incoming);
+		ogm_offset += BATADV_OGM_HLEN;
+		ogm_offset += ntohs(ogm_packet->tvlv_len);
 
-		buff_pos += BATADV_OGM_HLEN;
-		buff_pos += ntohs(batadv_ogm_packet->tvlv_len);
-
-		packet_pos = packet_buff + buff_pos;
-		batadv_ogm_packet = (struct batadv_ogm_packet *)packet_pos;
+		packet_pos = skb->data + ogm_offset;
+		ogm_packet = (struct batadv_ogm_packet *)packet_pos;
 	}
 
 	kfree_skb(skb);
@@ -1535,17 +1759,49 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb,
 }
 
 /**
+ * batadv_iv_ogm_orig_print_neigh - print neighbors for the originator table
+ * @orig_node: the orig_node for which the neighbors are printed
+ * @if_outgoing: outgoing interface for these entries
+ * @seq: debugfs table seq_file struct
+ *
+ * Must be called while holding an rcu lock.
+ */
+static void
+batadv_iv_ogm_orig_print_neigh(struct batadv_orig_node *orig_node,
+			       struct batadv_hard_iface *if_outgoing,
+			       struct seq_file *seq)
+{
+	struct batadv_neigh_node *neigh_node;
+	struct batadv_neigh_ifinfo *n_ifinfo;
+
+	hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) {
+		n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing);
+		if (!n_ifinfo)
+			continue;
+
+		seq_printf(seq, " %pM (%3i)",
+			   neigh_node->addr,
+			   n_ifinfo->bat_iv.tq_avg);
+
+		batadv_neigh_ifinfo_free_ref(n_ifinfo);
+	}
+}
+
+/**
  * batadv_iv_ogm_orig_print - print the originator table
  * @bat_priv: the bat priv with all the soft interface information
  * @seq: debugfs table seq_file struct
+ * @if_outgoing: the outgoing interface for which this should be printed
  */
 static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv,
-				     struct seq_file *seq)
+				     struct seq_file *seq,
+				     struct batadv_hard_iface *if_outgoing)
 {
-	struct batadv_neigh_node *neigh_node, *neigh_node_tmp;
+	struct batadv_neigh_node *neigh_node;
 	struct batadv_hashtable *hash = bat_priv->orig_hash;
 	int last_seen_msecs, last_seen_secs;
 	struct batadv_orig_node *orig_node;
+	struct batadv_neigh_ifinfo *n_ifinfo;
 	unsigned long last_seen_jiffies;
 	struct hlist_head *head;
 	int batman_count = 0;
@@ -1560,11 +1816,17 @@ static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv,
 
 		rcu_read_lock();
 		hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
-			neigh_node = batadv_orig_node_get_router(orig_node);
+			neigh_node = batadv_orig_router_get(orig_node,
+							    if_outgoing);
 			if (!neigh_node)
 				continue;
 
-			if (neigh_node->bat_iv.tq_avg == 0)
+			n_ifinfo = batadv_neigh_ifinfo_get(neigh_node,
+							   if_outgoing);
+			if (!n_ifinfo)
+				goto next;
+
+			if (n_ifinfo->bat_iv.tq_avg == 0)
 				goto next;
 
 			last_seen_jiffies = jiffies - orig_node->last_seen;
@@ -1574,22 +1836,19 @@ static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv,
 
 			seq_printf(seq, "%pM %4i.%03is   (%3i) %pM [%10s]:",
 				   orig_node->orig, last_seen_secs,
-				   last_seen_msecs, neigh_node->bat_iv.tq_avg,
+				   last_seen_msecs, n_ifinfo->bat_iv.tq_avg,
 				   neigh_node->addr,
 				   neigh_node->if_incoming->net_dev->name);
 
-			hlist_for_each_entry_rcu(neigh_node_tmp,
-						 &orig_node->neigh_list, list) {
-				seq_printf(seq, " %pM (%3i)",
-					   neigh_node_tmp->addr,
-					   neigh_node_tmp->bat_iv.tq_avg);
-			}
-
+			batadv_iv_ogm_orig_print_neigh(orig_node, if_outgoing,
+						       seq);
 			seq_puts(seq, "\n");
 			batman_count++;
 
 next:
 			batadv_neigh_node_free_ref(neigh_node);
+			if (n_ifinfo)
+				batadv_neigh_ifinfo_free_ref(n_ifinfo);
 		}
 		rcu_read_unlock();
 	}
@@ -1601,37 +1860,84 @@ next:
 /**
  * batadv_iv_ogm_neigh_cmp - compare the metrics of two neighbors
  * @neigh1: the first neighbor object of the comparison
+ * @if_outgoing1: outgoing interface for the first neighbor
  * @neigh2: the second neighbor object of the comparison
+ * @if_outgoing2: outgoing interface for the second neighbor
  *
  * Returns a value less, equal to or greater than 0 if the metric via neigh1 is
  * lower, the same as or higher than the metric via neigh2
  */
 static int batadv_iv_ogm_neigh_cmp(struct batadv_neigh_node *neigh1,
-				   struct batadv_neigh_node *neigh2)
+				   struct batadv_hard_iface *if_outgoing1,
+				   struct batadv_neigh_node *neigh2,
+				   struct batadv_hard_iface *if_outgoing2)
 {
+	struct batadv_neigh_ifinfo *neigh1_ifinfo, *neigh2_ifinfo;
 	uint8_t tq1, tq2;
+	int diff;
+
+	neigh1_ifinfo = batadv_neigh_ifinfo_get(neigh1, if_outgoing1);
+	neigh2_ifinfo = batadv_neigh_ifinfo_get(neigh2, if_outgoing2);
 
-	tq1 = neigh1->bat_iv.tq_avg;
-	tq2 = neigh2->bat_iv.tq_avg;
+	if (!neigh1_ifinfo || !neigh2_ifinfo) {
+		diff = 0;
+		goto out;
+	}
+
+	tq1 = neigh1_ifinfo->bat_iv.tq_avg;
+	tq2 = neigh2_ifinfo->bat_iv.tq_avg;
+	diff = tq1 - tq2;
 
-	return tq1 - tq2;
+out:
+	if (neigh1_ifinfo)
+		batadv_neigh_ifinfo_free_ref(neigh1_ifinfo);
+	if (neigh2_ifinfo)
+		batadv_neigh_ifinfo_free_ref(neigh2_ifinfo);
+
+	return diff;
 }
 
 /**
  * batadv_iv_ogm_neigh_is_eob - check if neigh1 is equally good or better than
  *  neigh2 from the metric prospective
  * @neigh1: the first neighbor object of the comparison
+ * @if_outgoing: outgoing interface for the first neighbor
  * @neigh2: the second neighbor object of the comparison
- *
- * Returns true if the metric via neigh1 is equally good or better than the
- * metric via neigh2, false otherwise.
+ * @if_outgoing2: outgoing interface for the second neighbor
+
+ * Returns true if the metric via neigh1 is equally good or better than
+ * the metric via neigh2, false otherwise.
  */
-static bool batadv_iv_ogm_neigh_is_eob(struct batadv_neigh_node *neigh1,
-				       struct batadv_neigh_node *neigh2)
+static bool
+batadv_iv_ogm_neigh_is_eob(struct batadv_neigh_node *neigh1,
+			   struct batadv_hard_iface *if_outgoing1,
+			   struct batadv_neigh_node *neigh2,
+			   struct batadv_hard_iface *if_outgoing2)
 {
-	int diff = batadv_iv_ogm_neigh_cmp(neigh1, neigh2);
+	struct batadv_neigh_ifinfo *neigh1_ifinfo, *neigh2_ifinfo;
+	uint8_t tq1, tq2;
+	bool ret;
+
+	neigh1_ifinfo = batadv_neigh_ifinfo_get(neigh1, if_outgoing1);
+	neigh2_ifinfo = batadv_neigh_ifinfo_get(neigh2, if_outgoing2);
+
+	/* we can't say that the metric is better */
+	if (!neigh1_ifinfo || !neigh2_ifinfo) {
+		ret = false;
+		goto out;
+	}
+
+	tq1 = neigh1_ifinfo->bat_iv.tq_avg;
+	tq2 = neigh2_ifinfo->bat_iv.tq_avg;
+	ret = (tq1 - tq2) > -BATADV_TQ_SIMILARITY_THRESHOLD;
 
-	return diff > -BATADV_TQ_SIMILARITY_THRESHOLD;
+out:
+	if (neigh1_ifinfo)
+		batadv_neigh_ifinfo_free_ref(neigh1_ifinfo);
+	if (neigh2_ifinfo)
+		batadv_neigh_ifinfo_free_ref(neigh2_ifinfo);
+
+	return ret;
 }
 
 static struct batadv_algo_ops batadv_batman_iv __read_mostly = {
diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c
index 973982414d5..9586750022f 100644
--- a/net/batman-adv/bitarray.c
+++ b/net/batman-adv/bitarray.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich, Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h
index a81b9322e38..cc2407351d3 100644
--- a/net/batman-adv/bitarray.h
+++ b/net/batman-adv/bitarray.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich, Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_BITARRAY_H_
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 28eb5e6d0a0..a957c814072 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -132,7 +130,9 @@ static void batadv_claim_free_ref(struct batadv_bla_claim *claim)
 		call_rcu(&claim->rcu, batadv_claim_free_rcu);
 }
 
-/* @bat_priv: the bat priv with all the soft interface information
+/**
+ * batadv_claim_hash_find
+ * @bat_priv: the bat priv with all the soft interface information
  * @data: search data (may be local/static data)
  *
  * looks for a claim in the hash, and returns it if found
@@ -191,7 +191,7 @@ batadv_backbone_hash_find(struct batadv_priv *bat_priv,
 	if (!hash)
 		return NULL;
 
-	memcpy(search_entry.orig, addr, ETH_ALEN);
+	ether_addr_copy(search_entry.orig, addr);
 	search_entry.vid = vid;
 
 	index = batadv_choose_backbone_gw(&search_entry, hash->size);
@@ -305,7 +305,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac,
 		/* normal claim frame
 		 * set Ethernet SRC to the clients mac
 		 */
-		memcpy(ethhdr->h_source, mac, ETH_ALEN);
+		ether_addr_copy(ethhdr->h_source, mac);
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_send_claim(): CLAIM %pM on vid %d\n", mac,
 			   BATADV_PRINT_VID(vid));
@@ -314,7 +314,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac,
 		/* unclaim frame
 		 * set HW SRC to the clients mac
 		 */
-		memcpy(hw_src, mac, ETH_ALEN);
+		ether_addr_copy(hw_src, mac);
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_send_claim(): UNCLAIM %pM on vid %d\n", mac,
 			   BATADV_PRINT_VID(vid));
@@ -323,7 +323,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac,
 		/* announcement frame
 		 * set HW SRC to the special mac containg the crc
 		 */
-		memcpy(hw_src, mac, ETH_ALEN);
+		ether_addr_copy(hw_src, mac);
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_send_claim(): ANNOUNCE of %pM on vid %d\n",
 			   ethhdr->h_source, BATADV_PRINT_VID(vid));
@@ -333,8 +333,8 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac,
 		 * set HW SRC and header destination to the receiving backbone
 		 * gws mac
 		 */
-		memcpy(hw_src, mac, ETH_ALEN);
-		memcpy(ethhdr->h_dest, mac, ETH_ALEN);
+		ether_addr_copy(hw_src, mac);
+		ether_addr_copy(ethhdr->h_dest, mac);
 		batadv_dbg(BATADV_DBG_BLA, bat_priv,
 			   "bla_send_claim(): REQUEST of %pM to %pM on vid %d\n",
 			   ethhdr->h_source, ethhdr->h_dest,
@@ -395,7 +395,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig,
 	entry->bat_priv = bat_priv;
 	atomic_set(&entry->request_sent, 0);
 	atomic_set(&entry->wait_periods, 0);
-	memcpy(entry->orig, orig, ETH_ALEN);
+	ether_addr_copy(entry->orig, orig);
 
 	/* one for the hash, one for returning */
 	atomic_set(&entry->refcount, 2);
@@ -451,7 +451,9 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv,
 	batadv_backbone_gw_free_ref(backbone_gw);
 }
 
-/* @bat_priv: the bat priv with all the soft interface information
+/**
+ * batadv_bla_answer_request - answer a bla request by sending own claims
+ * @bat_priv: the bat priv with all the soft interface information
  * @vid: the vid where the request came on
  *
  * Repeat all of our own claims, and finally send an ANNOUNCE frame
@@ -497,7 +499,9 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv,
 	batadv_backbone_gw_free_ref(backbone_gw);
 }
 
-/* @backbone_gw: the backbone gateway from whom we are out of sync
+/**
+ * batadv_bla_send_request - send a request to repeat claims
+ * @backbone_gw: the backbone gateway from whom we are out of sync
  *
  * When the crc is wrong, ask the backbone gateway for a full table update.
  * After the request, it will repeat all of his own claims and finally
@@ -522,7 +526,9 @@ static void batadv_bla_send_request(struct batadv_bla_backbone_gw *backbone_gw)
 	}
 }
 
-/* @bat_priv: the bat priv with all the soft interface information
+/**
+ * batadv_bla_send_announce
+ * @bat_priv: the bat priv with all the soft interface information
  * @backbone_gw: our backbone gateway which should be announced
  *
  * This function sends an announcement. It is called from multiple
@@ -557,7 +563,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
 	struct batadv_bla_claim search_claim;
 	int hash_added;
 
-	memcpy(search_claim.addr, mac, ETH_ALEN);
+	ether_addr_copy(search_claim.addr, mac);
 	search_claim.vid = vid;
 	claim = batadv_claim_hash_find(bat_priv, &search_claim);
 
@@ -567,7 +573,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
 		if (!claim)
 			return;
 
-		memcpy(claim->addr, mac, ETH_ALEN);
+		ether_addr_copy(claim->addr, mac);
 		claim->vid = vid;
 		claim->lasttime = jiffies;
 		claim->backbone_gw = backbone_gw;
@@ -618,7 +624,7 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
 {
 	struct batadv_bla_claim search_claim, *claim;
 
-	memcpy(search_claim.addr, mac, ETH_ALEN);
+	ether_addr_copy(search_claim.addr, mac);
 	search_claim.vid = vid;
 	claim = batadv_claim_hash_find(bat_priv, &search_claim);
 	if (!claim)
@@ -794,11 +800,6 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv,
 	bla_dst = (struct batadv_bla_claim_dst *)hw_dst;
 	bla_dst_own = &bat_priv->bla.claim_dest;
 
-	/* check if it is a claim packet in general */
-	if (memcmp(bla_dst->magic, bla_dst_own->magic,
-		   sizeof(bla_dst->magic)) != 0)
-		return 0;
-
 	/* if announcement packet, use the source,
 	 * otherwise assume it is in the hw_src
 	 */
@@ -846,7 +847,9 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv,
 }
 
 
-/* @bat_priv: the bat priv with all the soft interface information
+/**
+ * batadv_bla_process_claim
+ * @bat_priv: the bat priv with all the soft interface information
  * @skb: the frame to be checked
  *
  * Check if this is a claim frame, and process it accordingly.
@@ -858,12 +861,13 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
 				    struct batadv_hard_iface *primary_if,
 				    struct sk_buff *skb)
 {
-	struct batadv_bla_claim_dst *bla_dst;
+	struct batadv_bla_claim_dst *bla_dst, *bla_dst_own;
 	uint8_t *hw_src, *hw_dst;
-	struct vlan_ethhdr *vhdr;
+	struct vlan_hdr *vhdr, vhdr_buf;
 	struct ethhdr *ethhdr;
 	struct arphdr *arphdr;
 	unsigned short vid;
+	int vlan_depth = 0;
 	__be16 proto;
 	int headlen;
 	int ret;
@@ -874,9 +878,24 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
 	proto = ethhdr->h_proto;
 	headlen = ETH_HLEN;
 	if (vid & BATADV_VLAN_HAS_TAG) {
-		vhdr = (struct vlan_ethhdr *)ethhdr;
-		proto = vhdr->h_vlan_encapsulated_proto;
-		headlen += VLAN_HLEN;
+		/* Traverse the VLAN/Ethertypes.
+		 *
+		 * At this point it is known that the first protocol is a VLAN
+		 * header, so start checking at the encapsulated protocol.
+		 *
+		 * The depth of the VLAN headers is recorded to drop BLA claim
+		 * frames encapsulated into multiple VLAN headers (QinQ).
+		 */
+		do {
+			vhdr = skb_header_pointer(skb, headlen, VLAN_HLEN,
+						  &vhdr_buf);
+			if (!vhdr)
+				return 0;
+
+			proto = vhdr->h_vlan_encapsulated_proto;
+			headlen += VLAN_HLEN;
+			vlan_depth++;
+		} while (proto == htons(ETH_P_8021Q));
 	}
 
 	if (proto != htons(ETH_P_ARP))
@@ -906,6 +925,19 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
 	hw_src = (uint8_t *)arphdr + sizeof(struct arphdr);
 	hw_dst = hw_src + ETH_ALEN + 4;
 	bla_dst = (struct batadv_bla_claim_dst *)hw_dst;
+	bla_dst_own = &bat_priv->bla.claim_dest;
+
+	/* check if it is a claim frame in general */
+	if (memcmp(bla_dst->magic, bla_dst_own->magic,
+		   sizeof(bla_dst->magic)) != 0)
+		return 0;
+
+	/* check if there is a claim frame encapsulated deeper in (QinQ) and
+	 * drop that, as this is not supported by BLA but should also not be
+	 * sent via the mesh.
+	 */
+	if (vlan_depth > 1)
+		return 1;
 
 	/* check if it is a claim frame. */
 	ret = batadv_check_claim_group(bat_priv, primary_if, hw_src, hw_dst,
@@ -1095,8 +1127,8 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv,
 						oldif->net_dev->dev_addr))
 				continue;
 
-			memcpy(backbone_gw->orig,
-			       primary_if->net_dev->dev_addr, ETH_ALEN);
+			ether_addr_copy(backbone_gw->orig,
+					primary_if->net_dev->dev_addr);
 			/* send an announce frame so others will ask for our
 			 * claims and update their tables.
 			 */
@@ -1302,7 +1334,7 @@ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv,
 	entry = &bat_priv->bla.bcast_duplist[curr];
 	entry->crc = crc;
 	entry->entrytime = jiffies;
-	memcpy(entry->orig, bcast_packet->orig, ETH_ALEN);
+	ether_addr_copy(entry->orig, bcast_packet->orig);
 	bat_priv->bla.bcast_duplist_curr = curr;
 
 out:
@@ -1313,7 +1345,9 @@ out:
 
 
 
-/* @bat_priv: the bat priv with all the soft interface information
+/**
+ * batadv_bla_is_backbone_gw_orig
+ * @bat_priv: the bat priv with all the soft interface information
  * @orig: originator mac address
  * @vid: VLAN identifier
  *
@@ -1448,7 +1482,7 @@ int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast)
 			goto handled;
 
-	memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN);
+	ether_addr_copy(search_claim.addr, ethhdr->h_source);
 	search_claim.vid = vid;
 	claim = batadv_claim_hash_find(bat_priv, &search_claim);
 
@@ -1537,9 +1571,6 @@ int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 	if (!atomic_read(&bat_priv->bridge_loop_avoidance))
 		goto allow;
 
-	/* in VLAN case, the mac header might not be set. */
-	skb_reset_mac_header(skb);
-
 	if (batadv_bla_process_claim(bat_priv, primary_if, skb))
 		goto handled;
 
@@ -1550,7 +1581,7 @@ int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		if (is_multicast_ether_addr(ethhdr->h_dest))
 			goto handled;
 
-	memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN);
+	ether_addr_copy(search_claim.addr, ethhdr->h_source);
 	search_claim.vid = vid;
 
 	claim = batadv_claim_hash_find(bat_priv, &search_claim);
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index da173e760e7..43c985d92c3 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_BLA_H_
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index 049a7a2ac5b..a12e25efaf6 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -247,18 +245,35 @@ static int batadv_algorithms_open(struct inode *inode, struct file *file)
 static int batadv_originators_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_orig_seq_print_text, net_dev);
 }
 
+/**
+ * batadv_originators_hardif_open - handles debugfs output for the
+ *  originator table of an hard interface
+ * @inode: inode pointer to debugfs file
+ * @file: pointer to the seq_file
+ */
+static int batadv_originators_hardif_open(struct inode *inode,
+					  struct file *file)
+{
+	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
+	return single_open(file, batadv_orig_hardif_seq_print_text, net_dev);
+}
+
 static int batadv_gateways_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_gw_client_seq_print_text, net_dev);
 }
 
 static int batadv_transtable_global_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_tt_global_seq_print_text, net_dev);
 }
 
@@ -266,6 +281,7 @@ static int batadv_transtable_global_open(struct inode *inode, struct file *file)
 static int batadv_bla_claim_table_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_bla_claim_table_seq_print_text,
 			   net_dev);
 }
@@ -274,6 +290,7 @@ static int batadv_bla_backbone_table_open(struct inode *inode,
 					  struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_bla_backbone_table_seq_print_text,
 			   net_dev);
 }
@@ -289,6 +306,7 @@ static int batadv_bla_backbone_table_open(struct inode *inode,
 static int batadv_dat_cache_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_dat_cache_seq_print_text, net_dev);
 }
 #endif
@@ -296,6 +314,7 @@ static int batadv_dat_cache_open(struct inode *inode, struct file *file)
 static int batadv_transtable_local_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_tt_local_seq_print_text, net_dev);
 }
 
@@ -308,6 +327,7 @@ struct batadv_debuginfo {
 static int batadv_nc_nodes_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_nc_nodes_seq_print_text, net_dev);
 }
 #endif
@@ -322,7 +342,7 @@ struct batadv_debuginfo batadv_debuginfo_##_name = {	\
 		  .llseek = seq_lseek,			\
 		  .release = single_release,		\
 		}					\
-};
+}
 
 /* the following attributes are general and therefore they will be directly
  * placed in the BATADV_DEBUGFS_SUBDIR subdirectory of debugfs
@@ -371,6 +391,28 @@ static struct batadv_debuginfo *batadv_mesh_debuginfos[] = {
 	NULL,
 };
 
+#define BATADV_HARDIF_DEBUGINFO(_name, _mode, _open)		\
+struct batadv_debuginfo batadv_hardif_debuginfo_##_name = {	\
+	.attr = {						\
+		.name = __stringify(_name),			\
+		.mode = _mode,					\
+	},							\
+	.fops = {						\
+		.owner = THIS_MODULE,				\
+		.open = _open,					\
+		.read	= seq_read,				\
+		.llseek = seq_lseek,				\
+		.release = single_release,			\
+	},							\
+}
+static BATADV_HARDIF_DEBUGINFO(originators, S_IRUGO,
+			       batadv_originators_hardif_open);
+
+static struct batadv_debuginfo *batadv_hardif_debuginfos[] = {
+	&batadv_hardif_debuginfo_originators,
+	NULL,
+};
+
 void batadv_debugfs_init(void)
 {
 	struct batadv_debuginfo **bat_debug;
@@ -398,6 +440,7 @@ void batadv_debugfs_init(void)
 	return;
 err:
 	debugfs_remove_recursive(batadv_debugfs);
+	batadv_debugfs = NULL;
 }
 
 void batadv_debugfs_destroy(void)
@@ -406,6 +449,59 @@ void batadv_debugfs_destroy(void)
 	batadv_debugfs = NULL;
 }
 
+/**
+ * batadv_debugfs_add_hardif - creates the base directory for a hard interface
+ *  in debugfs.
+ * @hard_iface: hard interface which should be added.
+ */
+int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
+{
+	struct batadv_debuginfo **bat_debug;
+	struct dentry *file;
+
+	if (!batadv_debugfs)
+		goto out;
+
+	hard_iface->debug_dir = debugfs_create_dir(hard_iface->net_dev->name,
+						   batadv_debugfs);
+	if (!hard_iface->debug_dir)
+		goto out;
+
+	for (bat_debug = batadv_hardif_debuginfos; *bat_debug; ++bat_debug) {
+		file = debugfs_create_file(((*bat_debug)->attr).name,
+					   S_IFREG | ((*bat_debug)->attr).mode,
+					   hard_iface->debug_dir,
+					   hard_iface->net_dev,
+					   &(*bat_debug)->fops);
+		if (!file)
+			goto rem_attr;
+	}
+
+	return 0;
+rem_attr:
+	debugfs_remove_recursive(hard_iface->debug_dir);
+	hard_iface->debug_dir = NULL;
+out:
+#ifdef CONFIG_DEBUG_FS
+	return -ENOMEM;
+#else
+	return 0;
+#endif /* CONFIG_DEBUG_FS */
+}
+
+/**
+ * batadv_debugfs_del_hardif - delete the base directory for a hard interface
+ *  in debugfs.
+ * @hard_iface: hard interface which is deleted.
+ */
+void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface)
+{
+	if (batadv_debugfs) {
+		debugfs_remove_recursive(hard_iface->debug_dir);
+		hard_iface->debug_dir = NULL;
+	}
+}
+
 int batadv_debugfs_add_meshif(struct net_device *dev)
 {
 	struct batadv_priv *bat_priv = netdev_priv(dev);
diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h
index f8c3849edff..37c4d6ddd04 100644
--- a/net/batman-adv/debugfs.h
+++ b/net/batman-adv/debugfs.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_DEBUGFS_H_
@@ -26,5 +24,7 @@ void batadv_debugfs_init(void);
 void batadv_debugfs_destroy(void);
 int batadv_debugfs_add_meshif(struct net_device *dev);
 void batadv_debugfs_del_meshif(struct net_device *dev);
+int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface);
+void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface);
 
 #endif /* _NET_BATMAN_ADV_DEBUGFS_H_ */
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 6c8c3934bd7..f2c066b2171 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors:
  *
  * Antonio Quartulli
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/if_ether.h>
@@ -141,7 +139,7 @@ static int batadv_compare_dat(const struct hlist_node *node, const void *data2)
 	const void *data1 = container_of(node, struct batadv_dat_entry,
 					 hash_entry);
 
-	return (memcmp(data1, data2, sizeof(__be32)) == 0 ? 1 : 0);
+	return memcmp(data1, data2, sizeof(__be32)) == 0 ? 1 : 0;
 }
 
 /**
@@ -279,7 +277,7 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip,
 	/* if this entry is already known, just update it */
 	if (dat_entry) {
 		if (!batadv_compare_eth(dat_entry->mac_addr, mac_addr))
-			memcpy(dat_entry->mac_addr, mac_addr, ETH_ALEN);
+			ether_addr_copy(dat_entry->mac_addr, mac_addr);
 		dat_entry->last_update = jiffies;
 		batadv_dbg(BATADV_DBG_DAT, bat_priv,
 			   "Entry updated: %pI4 %pM (vid: %d)\n",
@@ -294,7 +292,7 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip,
 
 	dat_entry->ip = ip;
 	dat_entry->vid = vid;
-	memcpy(dat_entry->mac_addr, mac_addr, ETH_ALEN);
+	ether_addr_copy(dat_entry->mac_addr, mac_addr);
 	dat_entry->last_update = jiffies;
 	atomic_set(&dat_entry->refcount, 2);
 
@@ -349,7 +347,7 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 	unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
 
-	switch (unicast_4addr_packet->u.header.packet_type) {
+	switch (unicast_4addr_packet->u.packet_type) {
 	case BATADV_UNICAST:
 		batadv_dbg(BATADV_DBG_DAT, bat_priv,
 			   "* encapsulated within a UNICAST packet\n");
@@ -374,7 +372,7 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb,
 			break;
 		default:
 			batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: Unknown (%u)!\n",
-				   unicast_4addr_packet->u.header.packet_type);
+				   unicast_4addr_packet->u.packet_type);
 		}
 		break;
 	case BATADV_BCAST:
@@ -387,7 +385,7 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb,
 	default:
 		batadv_dbg(BATADV_DBG_DAT, bat_priv,
 			   "* encapsulated within an unknown packet type (0x%x)\n",
-			   unicast_4addr_packet->u.header.packet_type);
+			   unicast_4addr_packet->u.packet_type);
 	}
 }
 
@@ -591,11 +589,12 @@ static bool batadv_dat_send_data(struct batadv_priv *bat_priv,
 		if (cand[i].type == BATADV_DAT_CANDIDATE_NOT_FOUND)
 			continue;
 
-		neigh_node = batadv_orig_node_get_router(cand[i].orig_node);
+		neigh_node = batadv_orig_router_get(cand[i].orig_node,
+						    BATADV_IF_DEFAULT);
 		if (!neigh_node)
 			goto free_orig;
 
-		tmp_skb = pskb_copy(skb, GFP_ATOMIC);
+		tmp_skb = pskb_copy_for_clone(skb, GFP_ATOMIC);
 		if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, tmp_skb,
 							   cand[i].orig_node,
 							   packet_subtype)) {
@@ -663,6 +662,7 @@ static void batadv_dat_tvlv_container_update(struct batadv_priv *bat_priv)
 void batadv_dat_status_update(struct net_device *net_dev)
 {
 	struct batadv_priv *bat_priv = netdev_priv(net_dev);
+
 	batadv_dat_tvlv_container_update(bat_priv);
 }
 
@@ -941,8 +941,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 		 * additional DAT answer may trigger kernel warnings about
 		 * a packet coming from the wrong port.
 		 */
-		if (batadv_is_my_client(bat_priv, dat_entry->mac_addr,
-					BATADV_NO_FLAGS)) {
+		if (batadv_is_my_client(bat_priv, dat_entry->mac_addr, vid)) {
 			ret = true;
 			goto out;
 		}
@@ -1028,6 +1027,11 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
 	if (!skb_new)
 		goto out;
 
+	/* the rest of the TX path assumes that the mac_header offset pointing
+	 * to the inner Ethernet header has been set, therefore reset it now.
+	 */
+	skb_reset_mac_header(skb_new);
+
 	if (vid & BATADV_VLAN_HAS_TAG)
 		skb_new = vlan_insert_tag(skb_new, htons(ETH_P_8021Q),
 					  vid & VLAN_VID_MASK);
@@ -1039,9 +1043,9 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
 	if (hdr_size == sizeof(struct batadv_unicast_4addr_packet))
 		err = batadv_send_skb_via_tt_4addr(bat_priv, skb_new,
 						   BATADV_P_DAT_CACHE_REPLY,
-						   vid);
+						   NULL, vid);
 	else
-		err = batadv_send_skb_via_tt(bat_priv, skb_new, vid);
+		err = batadv_send_skb_via_tt(bat_priv, skb_new, NULL, vid);
 
 	if (err != NET_XMIT_DROP) {
 		batadv_inc_counter(bat_priv, BATADV_CNT_DAT_CACHED_REPLY_TX);
diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h
index 60d853beb8d..d76e1d06c5b 100644
--- a/net/batman-adv/distributed-arp-table.h
+++ b/net/batman-adv/distributed-arp-table.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2014 B.A.T.M.A.N. contributors:
  *
  * Antonio Quartulli
  *
@@ -12,13 +12,11 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
-#ifndef _NET_BATMAN_ADV_ARP_H_
-#define _NET_BATMAN_ADV_ARP_H_
+#ifndef _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_
+#define _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_
 
 #ifdef CONFIG_BATMAN_ADV_DAT
 
@@ -27,6 +25,9 @@
 
 #include <linux/if_arp.h>
 
+/**
+ * BATADV_DAT_ADDR_MAX - maximum address value in the DHT space
+ */
 #define BATADV_DAT_ADDR_MAX ((batadv_dat_addr_t)~(batadv_dat_addr_t)0)
 
 void batadv_dat_status_update(struct net_device *net_dev);
@@ -169,4 +170,4 @@ static inline void batadv_dat_inc_counter(struct batadv_priv *bat_priv,
 
 #endif /* CONFIG_BATMAN_ADV_DAT */
 
-#endif /* _NET_BATMAN_ADV_ARP_H_ */
+#endif /* _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_ */
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 271d321b3a0..f14e54a0569 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors:
  *
  * Martin Hundebøll <martin@hundeboll.net>
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -355,7 +353,7 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
 		batadv_add_counter(bat_priv, BATADV_CNT_FRAG_FWD_BYTES,
 				   skb->len + ETH_HLEN);
 
-		packet->header.ttl--;
+		packet->ttl--;
 		batadv_send_skb_packet(skb, neigh_node->if_incoming,
 				       neigh_node->addr);
 		ret = true;
@@ -420,12 +418,13 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 			     struct batadv_neigh_node *neigh_node)
 {
 	struct batadv_priv *bat_priv;
-	struct batadv_hard_iface *primary_if;
+	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_frag_packet frag_header;
 	struct sk_buff *skb_fragment;
 	unsigned mtu = neigh_node->if_incoming->net_dev->mtu;
 	unsigned header_size = sizeof(frag_header);
 	unsigned max_fragment_size, max_packet_size;
+	bool ret = false;
 
 	/* To avoid merge and refragmentation at next-hops we never send
 	 * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE
@@ -444,15 +443,15 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 		goto out_err;
 
 	/* Create one header to be copied to all fragments */
-	frag_header.header.packet_type = BATADV_UNICAST_FRAG;
-	frag_header.header.version = BATADV_COMPAT_VERSION;
-	frag_header.header.ttl = BATADV_TTL;
+	frag_header.packet_type = BATADV_UNICAST_FRAG;
+	frag_header.version = BATADV_COMPAT_VERSION;
+	frag_header.ttl = BATADV_TTL;
 	frag_header.seqno = htons(atomic_inc_return(&bat_priv->frag_seqno));
 	frag_header.reserved = 0;
 	frag_header.no = 0;
 	frag_header.total_size = htons(skb->len);
-	memcpy(frag_header.orig, primary_if->net_dev->dev_addr, ETH_ALEN);
-	memcpy(frag_header.dest, orig_node->orig, ETH_ALEN);
+	ether_addr_copy(frag_header.orig, primary_if->net_dev->dev_addr);
+	ether_addr_copy(frag_header.dest, orig_node->orig);
 
 	/* Eat and send fragments from the tail of skb */
 	while (skb->len > max_fragment_size) {
@@ -485,7 +484,11 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 			   skb->len + ETH_HLEN);
 	batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
 
-	return true;
+	ret = true;
+
 out_err:
-	return false;
+	if (primary_if)
+		batadv_hardif_free_ref(primary_if);
+
+	return ret;
 }
diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h
index ca029e2676e..5d7a0e66a22 100644
--- a/net/batman-adv/fragmentation.h
+++ b/net/batman-adv/fragmentation.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2014 B.A.T.M.A.N. contributors:
  *
  * Martin Hundebøll <martin@hundeboll.net>
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_FRAGMENTATION_H_
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 2449afaa763..90cff585b37 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -30,16 +28,24 @@
 #include <linux/udp.h>
 #include <linux/if_vlan.h>
 
-/* This is the offset of the options field in a dhcp packet starting at
- * the beginning of the dhcp header
+/* These are the offsets of the "hw type" and "hw address length" in the dhcp
+ * packet starting at the beginning of the dhcp header
  */
-#define BATADV_DHCP_OPTIONS_OFFSET 240
-#define BATADV_DHCP_REQUEST 3
+#define BATADV_DHCP_HTYPE_OFFSET	1
+#define BATADV_DHCP_HLEN_OFFSET		2
+/* Value of htype representing Ethernet */
+#define BATADV_DHCP_HTYPE_ETHERNET	0x01
+/* This is the offset of the "chaddr" field in the dhcp packet starting at the
+ * beginning of the dhcp header
+ */
+#define BATADV_DHCP_CHADDR_OFFSET	28
 
 static void batadv_gw_node_free_ref(struct batadv_gw_node *gw_node)
 {
-	if (atomic_dec_and_test(&gw_node->refcount))
+	if (atomic_dec_and_test(&gw_node->refcount)) {
+		batadv_orig_node_free_ref(gw_node->orig_node);
 		kfree_rcu(gw_node, rcu);
+	}
 }
 
 static struct batadv_gw_node *
@@ -105,7 +111,18 @@ static void batadv_gw_select(struct batadv_priv *bat_priv,
 	spin_unlock_bh(&bat_priv->gw.list_lock);
 }
 
-void batadv_gw_deselect(struct batadv_priv *bat_priv)
+/**
+ * batadv_gw_reselect - force a gateway reselection
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Set a flag to remind the GW component to perform a new gateway reselection.
+ * However this function does not ensure that the current gateway is going to be
+ * deselected. The reselection mechanism may elect the same gateway once again.
+ *
+ * This means that invoking batadv_gw_reselect() does not guarantee a gateway
+ * change and therefore a uevent is not necessarily expected.
+ */
+void batadv_gw_reselect(struct batadv_priv *bat_priv)
 {
 	atomic_set(&bat_priv->gw.reselect, 1);
 }
@@ -114,6 +131,7 @@ static struct batadv_gw_node *
 batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv)
 {
 	struct batadv_neigh_node *router;
+	struct batadv_neigh_ifinfo *router_ifinfo;
 	struct batadv_gw_node *gw_node, *curr_gw = NULL;
 	uint32_t max_gw_factor = 0, tmp_gw_factor = 0;
 	uint32_t gw_divisor;
@@ -130,14 +148,19 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv)
 			continue;
 
 		orig_node = gw_node->orig_node;
-		router = batadv_orig_node_get_router(orig_node);
+		router = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT);
 		if (!router)
 			continue;
 
+		router_ifinfo = batadv_neigh_ifinfo_get(router,
+							BATADV_IF_DEFAULT);
+		if (!router_ifinfo)
+			goto next;
+
 		if (!atomic_inc_not_zero(&gw_node->refcount))
 			goto next;
 
-		tq_avg = router->bat_iv.tq_avg;
+		tq_avg = router_ifinfo->bat_iv.tq_avg;
 
 		switch (atomic_read(&bat_priv->gw_sel_class)) {
 		case 1: /* fast connection */
@@ -182,6 +205,8 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv)
 
 next:
 		batadv_neigh_node_free_ref(router);
+		if (router_ifinfo)
+			batadv_neigh_ifinfo_free_ref(router_ifinfo);
 	}
 	rcu_read_unlock();
 
@@ -207,6 +232,11 @@ void batadv_gw_check_client_stop(struct batadv_priv *bat_priv)
 	if (!curr_gw)
 		return;
 
+	/* deselect the current gateway so that next time that client mode is
+	 * enabled a proper GW_ADD event can be sent
+	 */
+	batadv_gw_select(bat_priv, NULL);
+
 	/* if batman-adv is switching the gw client mode off and a gateway was
 	 * already selected, send a DEL uevent
 	 */
@@ -219,6 +249,7 @@ void batadv_gw_election(struct batadv_priv *bat_priv)
 {
 	struct batadv_gw_node *curr_gw = NULL, *next_gw = NULL;
 	struct batadv_neigh_node *router = NULL;
+	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
 	char gw_addr[18] = { '\0' };
 
 	if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_CLIENT)
@@ -237,9 +268,17 @@ void batadv_gw_election(struct batadv_priv *bat_priv)
 	if (next_gw) {
 		sprintf(gw_addr, "%pM", next_gw->orig_node->orig);
 
-		router = batadv_orig_node_get_router(next_gw->orig_node);
+		router = batadv_orig_router_get(next_gw->orig_node,
+						BATADV_IF_DEFAULT);
 		if (!router) {
-			batadv_gw_deselect(bat_priv);
+			batadv_gw_reselect(bat_priv);
+			goto out;
+		}
+
+		router_ifinfo = batadv_neigh_ifinfo_get(router,
+							BATADV_IF_DEFAULT);
+		if (!router_ifinfo) {
+			batadv_gw_reselect(bat_priv);
 			goto out;
 		}
 	}
@@ -256,7 +295,8 @@ void batadv_gw_election(struct batadv_priv *bat_priv)
 			   next_gw->bandwidth_down / 10,
 			   next_gw->bandwidth_down % 10,
 			   next_gw->bandwidth_up / 10,
-			   next_gw->bandwidth_up % 10, router->bat_iv.tq_avg);
+			   next_gw->bandwidth_up % 10,
+			   router_ifinfo->bat_iv.tq_avg);
 		batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_ADD,
 				    gw_addr);
 	} else {
@@ -266,7 +306,8 @@ void batadv_gw_election(struct batadv_priv *bat_priv)
 			   next_gw->bandwidth_down / 10,
 			   next_gw->bandwidth_down % 10,
 			   next_gw->bandwidth_up / 10,
-			   next_gw->bandwidth_up % 10, router->bat_iv.tq_avg);
+			   next_gw->bandwidth_up % 10,
+			   router_ifinfo->bat_iv.tq_avg);
 		batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_CHANGE,
 				    gw_addr);
 	}
@@ -280,33 +321,47 @@ out:
 		batadv_gw_node_free_ref(next_gw);
 	if (router)
 		batadv_neigh_node_free_ref(router);
+	if (router_ifinfo)
+		batadv_neigh_ifinfo_free_ref(router_ifinfo);
 }
 
 void batadv_gw_check_election(struct batadv_priv *bat_priv,
 			      struct batadv_orig_node *orig_node)
 {
+	struct batadv_neigh_ifinfo *router_orig_tq = NULL;
+	struct batadv_neigh_ifinfo *router_gw_tq = NULL;
 	struct batadv_orig_node *curr_gw_orig;
 	struct batadv_neigh_node *router_gw = NULL, *router_orig = NULL;
 	uint8_t gw_tq_avg, orig_tq_avg;
 
 	curr_gw_orig = batadv_gw_get_selected_orig(bat_priv);
 	if (!curr_gw_orig)
-		goto deselect;
+		goto reselect;
 
-	router_gw = batadv_orig_node_get_router(curr_gw_orig);
+	router_gw = batadv_orig_router_get(curr_gw_orig, BATADV_IF_DEFAULT);
 	if (!router_gw)
-		goto deselect;
+		goto reselect;
+
+	router_gw_tq = batadv_neigh_ifinfo_get(router_gw,
+					       BATADV_IF_DEFAULT);
+	if (!router_gw_tq)
+		goto reselect;
 
 	/* this node already is the gateway */
 	if (curr_gw_orig == orig_node)
 		goto out;
 
-	router_orig = batadv_orig_node_get_router(orig_node);
+	router_orig = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT);
 	if (!router_orig)
 		goto out;
 
-	gw_tq_avg = router_gw->bat_iv.tq_avg;
-	orig_tq_avg = router_orig->bat_iv.tq_avg;
+	router_orig_tq = batadv_neigh_ifinfo_get(router_orig,
+						 BATADV_IF_DEFAULT);
+	if (!router_orig_tq)
+		goto out;
+
+	gw_tq_avg = router_gw_tq->bat_iv.tq_avg;
+	orig_tq_avg = router_orig_tq->bat_iv.tq_avg;
 
 	/* the TQ value has to be better */
 	if (orig_tq_avg < gw_tq_avg)
@@ -323,8 +378,8 @@ void batadv_gw_check_election(struct batadv_priv *bat_priv,
 		   "Restarting gateway selection: better gateway found (tq curr: %i, tq new: %i)\n",
 		   gw_tq_avg, orig_tq_avg);
 
-deselect:
-	batadv_gw_deselect(bat_priv);
+reselect:
+	batadv_gw_reselect(bat_priv);
 out:
 	if (curr_gw_orig)
 		batadv_orig_node_free_ref(curr_gw_orig);
@@ -332,8 +387,10 @@ out:
 		batadv_neigh_node_free_ref(router_gw);
 	if (router_orig)
 		batadv_neigh_node_free_ref(router_orig);
-
-	return;
+	if (router_gw_tq)
+		batadv_neigh_ifinfo_free_ref(router_gw_tq);
+	if (router_orig_tq)
+		batadv_neigh_ifinfo_free_ref(router_orig_tq);
 }
 
 /**
@@ -351,9 +408,14 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv,
 	if (gateway->bandwidth_down == 0)
 		return;
 
+	if (!atomic_inc_not_zero(&orig_node->refcount))
+		return;
+
 	gw_node = kzalloc(sizeof(*gw_node), GFP_ATOMIC);
-	if (!gw_node)
+	if (!gw_node) {
+		batadv_orig_node_free_ref(orig_node);
 		return;
+	}
 
 	INIT_HLIST_NODE(&gw_node->list);
 	gw_node->orig_node = orig_node;
@@ -454,7 +516,7 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv,
 		 */
 		curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
 		if (gw_node == curr_gw)
-			batadv_gw_deselect(bat_priv);
+			batadv_gw_reselect(bat_priv);
 	}
 
 out:
@@ -480,7 +542,7 @@ void batadv_gw_node_purge(struct batadv_priv *bat_priv)
 	struct batadv_gw_node *gw_node, *curr_gw;
 	struct hlist_node *node_tmp;
 	unsigned long timeout = msecs_to_jiffies(2 * BATADV_PURGE_TIMEOUT);
-	int do_deselect = 0;
+	int do_reselect = 0;
 
 	curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
 
@@ -494,7 +556,7 @@ void batadv_gw_node_purge(struct batadv_priv *bat_priv)
 			continue;
 
 		if (curr_gw == gw_node)
-			do_deselect = 1;
+			do_reselect = 1;
 
 		hlist_del_rcu(&gw_node->list);
 		batadv_gw_node_free_ref(gw_node);
@@ -502,9 +564,9 @@ void batadv_gw_node_purge(struct batadv_priv *bat_priv)
 
 	spin_unlock_bh(&bat_priv->gw.list_lock);
 
-	/* gw_deselect() needs to acquire the gw_list_lock */
-	if (do_deselect)
-		batadv_gw_deselect(bat_priv);
+	/* gw_reselect() needs to acquire the gw_list_lock */
+	if (do_reselect)
+		batadv_gw_reselect(bat_priv);
 
 	if (curr_gw)
 		batadv_gw_node_free_ref(curr_gw);
@@ -517,28 +579,36 @@ static int batadv_write_buffer_text(struct batadv_priv *bat_priv,
 {
 	struct batadv_gw_node *curr_gw;
 	struct batadv_neigh_node *router;
+	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
 	int ret = -1;
 
-	router = batadv_orig_node_get_router(gw_node->orig_node);
+	router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT);
 	if (!router)
 		goto out;
 
+	router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT);
+	if (!router_ifinfo)
+		goto out;
+
 	curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
 
 	ret = seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %u.%u/%u.%u MBit\n",
 			 (curr_gw == gw_node ? "=>" : "  "),
 			 gw_node->orig_node->orig,
-			 router->bat_iv.tq_avg, router->addr,
+			 router_ifinfo->bat_iv.tq_avg, router->addr,
 			 router->if_incoming->net_dev->name,
 			 gw_node->bandwidth_down / 10,
 			 gw_node->bandwidth_down % 10,
 			 gw_node->bandwidth_up / 10,
 			 gw_node->bandwidth_up % 10);
 
-	batadv_neigh_node_free_ref(router);
 	if (curr_gw)
 		batadv_gw_node_free_ref(curr_gw);
 out:
+	if (router_ifinfo)
+		batadv_neigh_ifinfo_free_ref(router_ifinfo);
+	if (router)
+		batadv_neigh_node_free_ref(router);
 	return ret;
 }
 
@@ -582,90 +652,49 @@ out:
 	return 0;
 }
 
-/* this call might reallocate skb data */
-static bool batadv_is_type_dhcprequest(struct sk_buff *skb, int header_len)
-{
-	int ret = false;
-	unsigned char *p;
-	int pkt_len;
-
-	if (skb_linearize(skb) < 0)
-		goto out;
-
-	pkt_len = skb_headlen(skb);
-
-	if (pkt_len < header_len + BATADV_DHCP_OPTIONS_OFFSET + 1)
-		goto out;
-
-	p = skb->data + header_len + BATADV_DHCP_OPTIONS_OFFSET;
-	pkt_len -= header_len + BATADV_DHCP_OPTIONS_OFFSET + 1;
-
-	/* Access the dhcp option lists. Each entry is made up by:
-	 * - octet 1: option type
-	 * - octet 2: option data len (only if type != 255 and 0)
-	 * - octet 3: option data
-	 */
-	while (*p != 255 && !ret) {
-		/* p now points to the first octet: option type */
-		if (*p == 53) {
-			/* type 53 is the message type option.
-			 * Jump the len octet and go to the data octet
-			 */
-			if (pkt_len < 2)
-				goto out;
-			p += 2;
-
-			/* check if the message type is what we need */
-			if (*p == BATADV_DHCP_REQUEST)
-				ret = true;
-			break;
-		} else if (*p == 0) {
-			/* option type 0 (padding), just go forward */
-			if (pkt_len < 1)
-				goto out;
-			pkt_len--;
-			p++;
-		} else {
-			/* This is any other option. So we get the length... */
-			if (pkt_len < 1)
-				goto out;
-			pkt_len--;
-			p++;
-
-			/* ...and then we jump over the data */
-			if (pkt_len < 1 + (*p))
-				goto out;
-			pkt_len -= 1 + (*p);
-			p += 1 + (*p);
-		}
-	}
-out:
-	return ret;
-}
-
-/* this call might reallocate skb data */
-bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len)
+/**
+ * batadv_gw_dhcp_recipient_get - check if a packet is a DHCP message
+ * @skb: the packet to check
+ * @header_len: a pointer to the batman-adv header size
+ * @chaddr: buffer where the client address will be stored. Valid
+ *  only if the function returns BATADV_DHCP_TO_CLIENT
+ *
+ * Returns:
+ * - BATADV_DHCP_NO if the packet is not a dhcp message or if there was an error
+ *   while parsing it
+ * - BATADV_DHCP_TO_SERVER if this is a message going to the DHCP server
+ * - BATADV_DHCP_TO_CLIENT if this is a message going to a DHCP client
+ *
+ * This function may re-allocate the data buffer of the skb passed as argument.
+ */
+enum batadv_dhcp_recipient
+batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len,
+			     uint8_t *chaddr)
 {
+	enum batadv_dhcp_recipient ret = BATADV_DHCP_NO;
 	struct ethhdr *ethhdr;
 	struct iphdr *iphdr;
 	struct ipv6hdr *ipv6hdr;
 	struct udphdr *udphdr;
 	struct vlan_ethhdr *vhdr;
+	int chaddr_offset;
 	__be16 proto;
+	uint8_t *p;
 
 	/* check for ethernet header */
 	if (!pskb_may_pull(skb, *header_len + ETH_HLEN))
-		return false;
-	ethhdr = (struct ethhdr *)skb->data;
+		return BATADV_DHCP_NO;
+
+	ethhdr = eth_hdr(skb);
 	proto = ethhdr->h_proto;
 	*header_len += ETH_HLEN;
 
 	/* check for initial vlan header */
 	if (proto == htons(ETH_P_8021Q)) {
 		if (!pskb_may_pull(skb, *header_len + VLAN_HLEN))
-			return false;
+			return BATADV_DHCP_NO;
 
-		vhdr = (struct vlan_ethhdr *)skb->data;
+		vhdr = vlan_eth_hdr(skb);
 		proto = vhdr->h_vlan_encapsulated_proto;
 		*header_len += VLAN_HLEN;
 	}
@@ -674,35 +703,37 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len)
 	switch (proto) {
 	case htons(ETH_P_IP):
 		if (!pskb_may_pull(skb, *header_len + sizeof(*iphdr)))
-			return false;
+			return BATADV_DHCP_NO;
+
 		iphdr = (struct iphdr *)(skb->data + *header_len);
 		*header_len += iphdr->ihl * 4;
 
 		/* check for udp header */
 		if (iphdr->protocol != IPPROTO_UDP)
-			return false;
+			return BATADV_DHCP_NO;
 
 		break;
 	case htons(ETH_P_IPV6):
 		if (!pskb_may_pull(skb, *header_len + sizeof(*ipv6hdr)))
-			return false;
+			return BATADV_DHCP_NO;
+
 		ipv6hdr = (struct ipv6hdr *)(skb->data + *header_len);
 		*header_len += sizeof(*ipv6hdr);
 
 		/* check for udp header */
 		if (ipv6hdr->nexthdr != IPPROTO_UDP)
-			return false;
+			return BATADV_DHCP_NO;
 
 		break;
 	default:
-		return false;
+		return BATADV_DHCP_NO;
 	}
 
 	if (!pskb_may_pull(skb, *header_len + sizeof(*udphdr)))
-		return false;
+		return BATADV_DHCP_NO;
 
 	/* skb->data might have been reallocated by pskb_may_pull() */
-	ethhdr = (struct ethhdr *)skb->data;
+	ethhdr = eth_hdr(skb);
 	if (ntohs(ethhdr->h_proto) == ETH_P_8021Q)
 		ethhdr = (struct ethhdr *)(skb->data + VLAN_HLEN);
 
@@ -710,17 +741,40 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len)
 	*header_len += sizeof(*udphdr);
 
 	/* check for bootp port */
-	if ((proto == htons(ETH_P_IP)) &&
-	    (udphdr->dest != htons(67)))
-		return false;
+	switch (proto) {
+	case htons(ETH_P_IP):
+		if (udphdr->dest == htons(67))
+			ret = BATADV_DHCP_TO_SERVER;
+		else if (udphdr->source == htons(67))
+			ret = BATADV_DHCP_TO_CLIENT;
+		break;
+	case htons(ETH_P_IPV6):
+		if (udphdr->dest == htons(547))
+			ret = BATADV_DHCP_TO_SERVER;
+		else if (udphdr->source == htons(547))
+			ret = BATADV_DHCP_TO_CLIENT;
+		break;
+	}
 
-	if ((proto == htons(ETH_P_IPV6)) &&
-	    (udphdr->dest != htons(547)))
-		return false;
+	chaddr_offset = *header_len + BATADV_DHCP_CHADDR_OFFSET;
+	/* store the client address if the message is going to a client */
+	if (ret == BATADV_DHCP_TO_CLIENT &&
+	    pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) {
+		/* check if the DHCP packet carries an Ethernet DHCP */
+		p = skb->data + *header_len + BATADV_DHCP_HTYPE_OFFSET;
+		if (*p != BATADV_DHCP_HTYPE_ETHERNET)
+			return BATADV_DHCP_NO;
+
+		/* check if the DHCP packet carries a valid Ethernet address */
+		p = skb->data + *header_len + BATADV_DHCP_HLEN_OFFSET;
+		if (*p != ETH_ALEN)
+			return BATADV_DHCP_NO;
+
+		ether_addr_copy(chaddr, skb->data + chaddr_offset);
+	}
 
-	return true;
+	return ret;
 }
-
 /**
  * batadv_gw_out_of_range - check if the dhcp request destination is the best gw
  * @bat_priv: the bat priv with all the soft interface information
@@ -734,6 +788,7 @@ bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len)
  * false otherwise.
  *
  * This call might reallocate skb data.
+ * Must be invoked only when the DHCP packet is going TO a DHCP SERVER.
  */
 bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 			    struct sk_buff *skb)
@@ -741,19 +796,14 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 	struct batadv_neigh_node *neigh_curr = NULL, *neigh_old = NULL;
 	struct batadv_orig_node *orig_dst_node = NULL;
 	struct batadv_gw_node *gw_node = NULL, *curr_gw = NULL;
-	struct ethhdr *ethhdr;
-	bool ret, out_of_range = false;
-	unsigned int header_len = 0;
+	struct batadv_neigh_ifinfo *curr_ifinfo, *old_ifinfo;
+	struct ethhdr *ethhdr = (struct ethhdr *)skb->data;
+	bool out_of_range = false;
 	uint8_t curr_tq_avg;
 	unsigned short vid;
 
 	vid = batadv_get_vid(skb, 0);
 
-	ret = batadv_gw_is_dhcp_target(skb, &header_len);
-	if (!ret)
-		goto out;
-
-	ethhdr = (struct ethhdr *)skb->data;
 	orig_dst_node = batadv_transtable_search(bat_priv, ethhdr->h_source,
 						 ethhdr->h_dest, vid);
 	if (!orig_dst_node)
@@ -763,10 +813,6 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 	if (!gw_node->bandwidth_down == 0)
 		goto out;
 
-	ret = batadv_is_type_dhcprequest(skb, header_len);
-	if (!ret)
-		goto out;
-
 	switch (atomic_read(&bat_priv->gw_mode)) {
 	case BATADV_GW_MODE_SERVER:
 		/* If we are a GW then we are our best GW. We can artificially
@@ -792,7 +838,14 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 		if (!neigh_curr)
 			goto out;
 
-		curr_tq_avg = neigh_curr->bat_iv.tq_avg;
+		curr_ifinfo = batadv_neigh_ifinfo_get(neigh_curr,
+						      BATADV_IF_DEFAULT);
+		if (!curr_ifinfo)
+			goto out;
+
+		curr_tq_avg = curr_ifinfo->bat_iv.tq_avg;
+		batadv_neigh_ifinfo_free_ref(curr_ifinfo);
+
 		break;
 	case BATADV_GW_MODE_OFF:
 	default:
@@ -803,8 +856,13 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
 	if (!neigh_old)
 		goto out;
 
-	if (curr_tq_avg - neigh_old->bat_iv.tq_avg > BATADV_GW_THRESHOLD)
+	old_ifinfo = batadv_neigh_ifinfo_get(neigh_old, BATADV_IF_DEFAULT);
+	if (!old_ifinfo)
+		goto out;
+
+	if ((curr_tq_avg - old_ifinfo->bat_iv.tq_avg) > BATADV_GW_THRESHOLD)
 		out_of_range = true;
+	batadv_neigh_ifinfo_free_ref(old_ifinfo);
 
 out:
 	if (orig_dst_node)
diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h
index d95c2d23195..7ee53bb7d50 100644
--- a/net/batman-adv/gateway_client.h
+++ b/net/batman-adv/gateway_client.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,16 +12,14 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_GATEWAY_CLIENT_H_
 #define _NET_BATMAN_ADV_GATEWAY_CLIENT_H_
 
 void batadv_gw_check_client_stop(struct batadv_priv *bat_priv);
-void batadv_gw_deselect(struct batadv_priv *bat_priv);
+void batadv_gw_reselect(struct batadv_priv *bat_priv);
 void batadv_gw_election(struct batadv_priv *bat_priv);
 struct batadv_orig_node *
 batadv_gw_get_selected_orig(struct batadv_priv *bat_priv);
@@ -34,7 +32,9 @@ void batadv_gw_node_delete(struct batadv_priv *bat_priv,
 			   struct batadv_orig_node *orig_node);
 void batadv_gw_node_purge(struct batadv_priv *bat_priv);
 int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset);
-bool batadv_gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len);
 bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct sk_buff *skb);
+enum batadv_dhcp_recipient
+batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len,
+			     uint8_t *chaddr);
 
 #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index b211b0f9cb7..6f5e621f220 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -164,7 +162,7 @@ ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff,
 	if ((down_curr == down_new) && (up_curr == up_new))
 		return count;
 
-	batadv_gw_deselect(bat_priv);
+	batadv_gw_reselect(bat_priv);
 	batadv_info(net_dev,
 		    "Changing gateway bandwidth from: '%u.%u/%u.%u MBit' to: '%u.%u/%u.%u MBit'\n",
 		    down_curr / 10, down_curr % 10, up_curr / 10, up_curr % 10,
diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h
index 56384a4cd18..aa511656194 100644
--- a/net/batman-adv/gateway_common.h
+++ b/net/batman-adv/gateway_common.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_GATEWAY_COMMON_H_
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 57c2a19dcb5..fbda6b54baf 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -25,6 +23,7 @@
 #include "translation-table.h"
 #include "routing.h"
 #include "sysfs.h"
+#include "debugfs.h"
 #include "originator.h"
 #include "hash.h"
 #include "bridge_loop_avoidance.h"
@@ -84,19 +83,17 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
 		return true;
 
 	/* no more parents..stop recursion */
-	if (net_dev->iflink == net_dev->ifindex)
+	if (net_dev->iflink == 0 || net_dev->iflink == net_dev->ifindex)
 		return false;
 
 	/* recurse over the parent device */
-	parent_dev = dev_get_by_index(&init_net, net_dev->iflink);
+	parent_dev = __dev_get_by_index(&init_net, net_dev->iflink);
 	/* if we got a NULL parent_dev there is something broken.. */
 	if (WARN(!parent_dev, "Cannot find parent device"))
 		return false;
 
 	ret = batadv_is_on_batman_iface(parent_dev);
 
-	if (parent_dev)
-		dev_put(parent_dev);
 	return ret;
 }
 
@@ -244,7 +241,7 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
 {
 	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
 	const struct batadv_hard_iface *hard_iface;
-	int min_mtu = ETH_DATA_LEN;
+	int min_mtu = INT_MAX;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
@@ -259,8 +256,6 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
 	}
 	rcu_read_unlock();
 
-	atomic_set(&bat_priv->packet_size_max, min_mtu);
-
 	if (atomic_read(&bat_priv->fragmentation) == 0)
 		goto out;
 
@@ -271,13 +266,21 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
 	min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE);
 	min_mtu -= sizeof(struct batadv_frag_packet);
 	min_mtu *= BATADV_FRAG_MAX_FRAGMENTS;
-	atomic_set(&bat_priv->packet_size_max, min_mtu);
-
-	/* with fragmentation enabled we can fragment external packets easily */
-	min_mtu = min_t(int, min_mtu, ETH_DATA_LEN);
 
 out:
-	return min_mtu - batadv_max_header_len();
+	/* report to the other components the maximum amount of bytes that
+	 * batman-adv can send over the wire (without considering the payload
+	 * overhead). For example, this value is used by TT to compute the
+	 * maximum local table table size
+	 */
+	atomic_set(&bat_priv->packet_size_max, min_mtu);
+
+	/* the real soft-interface MTU is computed by removing the payload
+	 * overhead from the maximum amount of bytes that was just computed.
+	 *
+	 * However batman-adv does not support MTUs bigger than ETH_DATA_LEN
+	 */
+	return min_t(int, min_mtu - batadv_max_header_len(), ETH_DATA_LEN);
 }
 
 /* adjusts the MTU if a new interface with a smaller MTU appeared. */
@@ -541,6 +544,7 @@ static void batadv_hardif_remove_interface_finish(struct work_struct *work)
 	hard_iface = container_of(work, struct batadv_hard_iface,
 				  cleanup_work);
 
+	batadv_debugfs_del_hardif(hard_iface);
 	batadv_sysfs_del_hardif(&hard_iface->hardif_obj);
 	batadv_hardif_free_ref(hard_iface);
 }
@@ -571,6 +575,11 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 	hard_iface->net_dev = net_dev;
 	hard_iface->soft_iface = NULL;
 	hard_iface->if_status = BATADV_IF_NOT_IN_USE;
+
+	ret = batadv_debugfs_add_hardif(hard_iface);
+	if (ret)
+		goto free_sysfs;
+
 	INIT_LIST_HEAD(&hard_iface->list);
 	INIT_WORK(&hard_iface->cleanup_work,
 		  batadv_hardif_remove_interface_finish);
@@ -587,6 +596,8 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 
 	return hard_iface;
 
+free_sysfs:
+	batadv_sysfs_del_hardif(&hard_iface->hardif_obj);
 free_if:
 	kfree(hard_iface);
 release_dev:
diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index df4c8bd45c4..1918cd50b62 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_HARD_INTERFACE_H_
@@ -42,6 +40,7 @@ enum batadv_hard_if_cleanup {
 extern struct notifier_block batadv_hard_if_notifier;
 
 bool batadv_is_wifi_netdev(struct net_device *net_device);
+bool batadv_is_wifi_iface(int ifindex);
 struct batadv_hard_iface*
 batadv_hardif_get_by_netdev(const struct net_device *net_dev);
 int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
@@ -53,6 +52,11 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface);
 void batadv_update_min_mtu(struct net_device *soft_iface);
 void batadv_hardif_free_rcu(struct rcu_head *rcu);
 
+/**
+ * batadv_hardif_free_ref - decrement the hard interface refcounter and
+ *  possibly free it
+ * @hard_iface: the hard interface to free
+ */
 static inline void
 batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface)
 {
@@ -60,6 +64,18 @@ batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface)
 		call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu);
 }
 
+/**
+ * batadv_hardif_free_ref_now - decrement the hard interface refcounter and
+ *  possibly free it (without rcu callback)
+ * @hard_iface: the hard interface to free
+ */
+static inline void
+batadv_hardif_free_ref_now(struct batadv_hard_iface *hard_iface)
+{
+	if (atomic_dec_and_test(&hard_iface->refcount))
+		batadv_hardif_free_rcu(&hard_iface->rcu);
+}
+
 static inline struct batadv_hard_iface *
 batadv_primary_if_get_selected(struct batadv_priv *bat_priv)
 {
diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c
index 7198dafd3bf..63bdf7e94f1 100644
--- a/net/batman-adv/hash.c
+++ b/net/batman-adv/hash.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich, Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h
index 1b4da72f209..539fc126679 100644
--- a/net/batman-adv/hash.h
+++ b/net/batman-adv/hash.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2014 B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich, Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_HASH_H_
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 29ae4efe354..161ef8f17d2 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -160,6 +158,7 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff,
 	struct batadv_orig_node *orig_node = NULL;
 	struct batadv_neigh_node *neigh_node = NULL;
 	size_t packet_len = sizeof(struct batadv_icmp_packet);
+	uint8_t *addr;
 
 	if (len < sizeof(struct batadv_icmp_header)) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
@@ -194,7 +193,7 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff,
 		goto free_skb;
 	}
 
-	if (icmp_header->header.packet_type != BATADV_ICMP) {
+	if (icmp_header->packet_type != BATADV_ICMP) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Error - can't send packet from char device: got bogus packet type (expected: BAT_ICMP)\n");
 		len = -EINVAL;
@@ -217,7 +216,8 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff,
 		if (!orig_node)
 			goto dst_unreach;
 
-		neigh_node = batadv_orig_node_get_router(orig_node);
+		neigh_node = batadv_orig_router_get(orig_node,
+						    BATADV_IF_DEFAULT);
 		if (!neigh_node)
 			goto dst_unreach;
 
@@ -228,10 +228,10 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff,
 			goto dst_unreach;
 
 		icmp_packet_rr = (struct batadv_icmp_packet_rr *)icmp_header;
-		if (packet_len == sizeof(*icmp_packet_rr))
-			memcpy(icmp_packet_rr->rr,
-			       neigh_node->if_incoming->net_dev->dev_addr,
-			       ETH_ALEN);
+		if (packet_len == sizeof(*icmp_packet_rr)) {
+			addr = neigh_node->if_incoming->net_dev->dev_addr;
+			ether_addr_copy(icmp_packet_rr->rr[0], addr);
+		}
 
 		break;
 	default:
@@ -243,15 +243,15 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff,
 
 	icmp_header->uid = socket_client->index;
 
-	if (icmp_header->header.version != BATADV_COMPAT_VERSION) {
+	if (icmp_header->version != BATADV_COMPAT_VERSION) {
 		icmp_header->msg_type = BATADV_PARAMETER_PROBLEM;
-		icmp_header->header.version = BATADV_COMPAT_VERSION;
+		icmp_header->version = BATADV_COMPAT_VERSION;
 		batadv_socket_add_packet(socket_client, icmp_header,
 					 packet_len);
 		goto free_skb;
 	}
 
-	memcpy(icmp_header->orig, primary_if->net_dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(icmp_header->orig, primary_if->net_dev->dev_addr);
 
 	batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
 	goto out;
diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h
index 6665080dff7..0c33950aa4a 100644
--- a/net/batman-adv/icmp_socket.h
+++ b/net/batman-adv/icmp_socket.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_ICMP_SOCKET_H_
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index c51a5e568f0..d1183e88216 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/crc32c.h>
@@ -36,6 +34,7 @@
 #include "gateway_client.h"
 #include "bridge_loop_avoidance.h"
 #include "distributed-arp-table.h"
+#include "multicast.h"
 #include "gateway_common.h"
 #include "hash.h"
 #include "bat_algo.h"
@@ -112,6 +111,9 @@ int batadv_mesh_init(struct net_device *soft_iface)
 	spin_lock_init(&bat_priv->tt.last_changeset_lock);
 	spin_lock_init(&bat_priv->tt.commit_lock);
 	spin_lock_init(&bat_priv->gw.list_lock);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	spin_lock_init(&bat_priv->mcast.want_lists_lock);
+#endif
 	spin_lock_init(&bat_priv->tvlv.container_list_lock);
 	spin_lock_init(&bat_priv->tvlv.handler_list_lock);
 	spin_lock_init(&bat_priv->softif_vlan_list_lock);
@@ -119,9 +121,17 @@ int batadv_mesh_init(struct net_device *soft_iface)
 	INIT_HLIST_HEAD(&bat_priv->forw_bat_list);
 	INIT_HLIST_HEAD(&bat_priv->forw_bcast_list);
 	INIT_HLIST_HEAD(&bat_priv->gw.list);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	INIT_HLIST_HEAD(&bat_priv->mcast.want_all_unsnoopables_list);
+	INIT_HLIST_HEAD(&bat_priv->mcast.want_all_ipv4_list);
+	INIT_HLIST_HEAD(&bat_priv->mcast.want_all_ipv6_list);
+#endif
 	INIT_LIST_HEAD(&bat_priv->tt.changes_list);
 	INIT_LIST_HEAD(&bat_priv->tt.req_list);
 	INIT_LIST_HEAD(&bat_priv->tt.roam_list);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	INIT_HLIST_HEAD(&bat_priv->mcast.mla_list);
+#endif
 	INIT_HLIST_HEAD(&bat_priv->tvlv.container_list);
 	INIT_HLIST_HEAD(&bat_priv->tvlv.handler_list);
 	INIT_HLIST_HEAD(&bat_priv->softif_vlan_list);
@@ -147,6 +157,7 @@ int batadv_mesh_init(struct net_device *soft_iface)
 		goto err;
 
 	batadv_gw_init(bat_priv);
+	batadv_mcast_init(bat_priv);
 
 	atomic_set(&bat_priv->gw.reselect, 0);
 	atomic_set(&bat_priv->mesh_state, BATADV_MESH_ACTIVE);
@@ -171,6 +182,8 @@ void batadv_mesh_free(struct net_device *soft_iface)
 	batadv_dat_free(bat_priv);
 	batadv_bla_free(bat_priv);
 
+	batadv_mcast_free(bat_priv);
+
 	/* Free the TT and the originator tables only after having terminated
 	 * all the other depending components which may use these structures for
 	 * their purposes.
@@ -277,7 +290,7 @@ int batadv_max_header_len(void)
 			   sizeof(struct batadv_coded_packet));
 #endif
 
-	return header_len;
+	return header_len + ETH_HLEN;
 }
 
 /**
@@ -383,17 +396,17 @@ int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev,
 
 	batadv_ogm_packet = (struct batadv_ogm_packet *)skb->data;
 
-	if (batadv_ogm_packet->header.version != BATADV_COMPAT_VERSION) {
+	if (batadv_ogm_packet->version != BATADV_COMPAT_VERSION) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Drop packet: incompatible batman version (%i)\n",
-			   batadv_ogm_packet->header.version);
+			   batadv_ogm_packet->version);
 		goto err_free;
 	}
 
 	/* all receive handlers return whether they received or reused
 	 * the supplied skb. if not, we have to free the skb.
 	 */
-	idx = batadv_ogm_packet->header.packet_type;
+	idx = batadv_ogm_packet->packet_type;
 	ret = (*batadv_rx_handler[idx])(skb, hard_iface);
 
 	if (ret == NET_RX_DROP)
@@ -421,13 +434,23 @@ static void batadv_recv_handler_init(void)
 	for (i = BATADV_UNICAST_MIN; i <= BATADV_UNICAST_MAX; i++)
 		batadv_rx_handler[i] = batadv_recv_unhandled_unicast_packet;
 
-	/* compile time checks for struct member offsets */
-	BUILD_BUG_ON(offsetof(struct batadv_unicast_4addr_packet, src) != 10);
-	BUILD_BUG_ON(offsetof(struct batadv_unicast_packet, dest) != 4);
-	BUILD_BUG_ON(offsetof(struct batadv_unicast_tvlv_packet, dst) != 4);
-	BUILD_BUG_ON(offsetof(struct batadv_frag_packet, dest) != 4);
-	BUILD_BUG_ON(offsetof(struct batadv_icmp_packet, icmph.dst) != 4);
-	BUILD_BUG_ON(offsetof(struct batadv_icmp_packet_rr, icmph.dst) != 4);
+	/* compile time checks for sizes */
+	BUILD_BUG_ON(sizeof(struct batadv_bla_claim_dst) != 6);
+	BUILD_BUG_ON(sizeof(struct batadv_ogm_packet) != 24);
+	BUILD_BUG_ON(sizeof(struct batadv_icmp_header) != 20);
+	BUILD_BUG_ON(sizeof(struct batadv_icmp_packet) != 20);
+	BUILD_BUG_ON(sizeof(struct batadv_icmp_packet_rr) != 116);
+	BUILD_BUG_ON(sizeof(struct batadv_unicast_packet) != 10);
+	BUILD_BUG_ON(sizeof(struct batadv_unicast_4addr_packet) != 18);
+	BUILD_BUG_ON(sizeof(struct batadv_frag_packet) != 20);
+	BUILD_BUG_ON(sizeof(struct batadv_bcast_packet) != 14);
+	BUILD_BUG_ON(sizeof(struct batadv_coded_packet) != 46);
+	BUILD_BUG_ON(sizeof(struct batadv_unicast_tvlv_packet) != 20);
+	BUILD_BUG_ON(sizeof(struct batadv_tvlv_hdr) != 4);
+	BUILD_BUG_ON(sizeof(struct batadv_tvlv_gateway_data) != 8);
+	BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_vlan_data) != 8);
+	BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_change) != 12);
+	BUILD_BUG_ON(sizeof(struct batadv_tvlv_roam_adv) != 8);
 
 	/* broadcast packet */
 	batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet;
@@ -1119,14 +1142,14 @@ void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, uint8_t *src,
 	skb_reserve(skb, ETH_HLEN);
 	tvlv_buff = skb_put(skb, sizeof(*unicast_tvlv_packet) + tvlv_len);
 	unicast_tvlv_packet = (struct batadv_unicast_tvlv_packet *)tvlv_buff;
-	unicast_tvlv_packet->header.packet_type = BATADV_UNICAST_TVLV;
-	unicast_tvlv_packet->header.version = BATADV_COMPAT_VERSION;
-	unicast_tvlv_packet->header.ttl = BATADV_TTL;
+	unicast_tvlv_packet->packet_type = BATADV_UNICAST_TVLV;
+	unicast_tvlv_packet->version = BATADV_COMPAT_VERSION;
+	unicast_tvlv_packet->ttl = BATADV_TTL;
 	unicast_tvlv_packet->reserved = 0;
 	unicast_tvlv_packet->tvlv_len = htons(tvlv_len);
 	unicast_tvlv_packet->align = 0;
-	memcpy(unicast_tvlv_packet->src, src, ETH_ALEN);
-	memcpy(unicast_tvlv_packet->dst, dst, ETH_ALEN);
+	ether_addr_copy(unicast_tvlv_packet->src, src);
+	ether_addr_copy(unicast_tvlv_packet->dst, dst);
 
 	tvlv_buff = (unsigned char *)(unicast_tvlv_packet + 1);
 	tvlv_hdr = (struct batadv_tvlv_hdr *)tvlv_buff;
@@ -1173,6 +1196,32 @@ unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len)
 	return vid;
 }
 
+/**
+ * batadv_vlan_ap_isola_get - return the AP isolation status for the given vlan
+ * @bat_priv: the bat priv with all the soft interface information
+ * @vid: the VLAN identifier for which the AP isolation attributed as to be
+ *  looked up
+ *
+ * Returns true if AP isolation is on for the VLAN idenfied by vid, false
+ * otherwise
+ */
+bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid)
+{
+	bool ap_isolation_enabled = false;
+	struct batadv_softif_vlan *vlan;
+
+	/* if the AP isolation is requested on a VLAN, then check for its
+	 * setting in the proper VLAN private data structure
+	 */
+	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	if (vlan) {
+		ap_isolation_enabled = atomic_read(&vlan->ap_isolation);
+		batadv_softif_vlan_free_ref(vlan);
+	}
+
+	return ap_isolation_enabled;
+}
+
 static int batadv_param_set_ra(const char *val, const struct kernel_param *kp)
 {
 	struct batadv_algo_ops *bat_algo_ops;
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index f94f287b867..118b990bae2 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_MAIN_H_
@@ -26,7 +24,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2013.5.0"
+#define BATADV_SOURCE_VERSION "2014.3.0"
 #endif
 
 /* B.A.T.M.A.N. parameters */
@@ -72,6 +70,14 @@
 
 #define BATADV_NULL_IFINDEX 0 /* dummy ifindex used to avoid iface checks */
 
+#define BATADV_NO_MARK 0
+
+/* default interface for multi interface operation. The default interface is
+ * used for communication which originated locally (i.e. is not forwarded)
+ * or where special forwarding is not desired/necessary.
+ */
+#define BATADV_IF_DEFAULT	((struct batadv_hard_iface *)NULL)
+
 #define BATADV_NUM_WORDS BITS_TO_LONGS(BATADV_TQ_LOCAL_WINDOW_SIZE)
 
 #define BATADV_LOG_BUF_LEN 8192	  /* has to be a power of 2 */
@@ -170,6 +176,8 @@ enum batadv_uev_type {
 #include <linux/percpu.h>
 #include <linux/slab.h>
 #include <net/sock.h>		/* struct sock */
+#include <net/addrconf.h>	/* ipv6 address stuff */
+#include <linux/ip.h>
 #include <net/rtnetlink.h>
 #include <linux/jiffies.h>
 #include <linux/seq_file.h>
@@ -266,7 +274,7 @@ static inline void batadv_dbg(int type __always_unused,
  */
 static inline int batadv_compare_eth(const void *data1, const void *data2)
 {
-	return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0);
+	return ether_addr_equal_unaligned(data1, data2);
 }
 
 /**
@@ -369,5 +377,6 @@ void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, uint8_t *src,
 			      uint8_t *dst, uint8_t type, uint8_t version,
 			      void *tvlv_value, uint16_t tvlv_value_len);
 unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len);
+bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid);
 
 #endif /* _NET_BATMAN_ADV_MAIN_H_ */
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
new file mode 100644
index 00000000000..96b66fd30f9
--- /dev/null
+++ b/net/batman-adv/multicast.c
@@ -0,0 +1,748 @@
+/* Copyright (C) 2014 B.A.T.M.A.N. contributors:
+ *
+ * Linus Lüssing
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "main.h"
+#include "multicast.h"
+#include "originator.h"
+#include "hard-interface.h"
+#include "translation-table.h"
+#include "multicast.h"
+
+/**
+ * batadv_mcast_mla_softif_get - get softif multicast listeners
+ * @dev: the device to collect multicast addresses from
+ * @mcast_list: a list to put found addresses into
+ *
+ * Collect multicast addresses of the local multicast listeners
+ * on the given soft interface, dev, in the given mcast_list.
+ *
+ * Returns -ENOMEM on memory allocation error or the number of
+ * items added to the mcast_list otherwise.
+ */
+static int batadv_mcast_mla_softif_get(struct net_device *dev,
+				       struct hlist_head *mcast_list)
+{
+	struct netdev_hw_addr *mc_list_entry;
+	struct batadv_hw_addr *new;
+	int ret = 0;
+
+	netif_addr_lock_bh(dev);
+	netdev_for_each_mc_addr(mc_list_entry, dev) {
+		new = kmalloc(sizeof(*new), GFP_ATOMIC);
+		if (!new) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		ether_addr_copy(new->addr, mc_list_entry->addr);
+		hlist_add_head(&new->list, mcast_list);
+		ret++;
+	}
+	netif_addr_unlock_bh(dev);
+
+	return ret;
+}
+
+/**
+ * batadv_mcast_mla_is_duplicate - check whether an address is in a list
+ * @mcast_addr: the multicast address to check
+ * @mcast_list: the list with multicast addresses to search in
+ *
+ * Returns true if the given address is already in the given list.
+ * Otherwise returns false.
+ */
+static bool batadv_mcast_mla_is_duplicate(uint8_t *mcast_addr,
+					  struct hlist_head *mcast_list)
+{
+	struct batadv_hw_addr *mcast_entry;
+
+	hlist_for_each_entry(mcast_entry, mcast_list, list)
+		if (batadv_compare_eth(mcast_entry->addr, mcast_addr))
+			return true;
+
+	return false;
+}
+
+/**
+ * batadv_mcast_mla_list_free - free a list of multicast addresses
+ * @mcast_list: the list to free
+ *
+ * Removes and frees all items in the given mcast_list.
+ */
+static void batadv_mcast_mla_list_free(struct hlist_head *mcast_list)
+{
+	struct batadv_hw_addr *mcast_entry;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) {
+		hlist_del(&mcast_entry->list);
+		kfree(mcast_entry);
+	}
+}
+
+/**
+ * batadv_mcast_mla_tt_retract - clean up multicast listener announcements
+ * @bat_priv: the bat priv with all the soft interface information
+ * @mcast_list: a list of addresses which should _not_ be removed
+ *
+ * Retracts the announcement of any multicast listener from the
+ * translation table except the ones listed in the given mcast_list.
+ *
+ * If mcast_list is NULL then all are retracted.
+ */
+static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv,
+					struct hlist_head *mcast_list)
+{
+	struct batadv_hw_addr *mcast_entry;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry_safe(mcast_entry, tmp, &bat_priv->mcast.mla_list,
+				  list) {
+		if (mcast_list &&
+		    batadv_mcast_mla_is_duplicate(mcast_entry->addr,
+						  mcast_list))
+			continue;
+
+		batadv_tt_local_remove(bat_priv, mcast_entry->addr,
+				       BATADV_NO_FLAGS,
+				       "mcast TT outdated", false);
+
+		hlist_del(&mcast_entry->list);
+		kfree(mcast_entry);
+	}
+}
+
+/**
+ * batadv_mcast_mla_tt_add - add multicast listener announcements
+ * @bat_priv: the bat priv with all the soft interface information
+ * @mcast_list: a list of addresses which are going to get added
+ *
+ * Adds multicast listener announcements from the given mcast_list to the
+ * translation table if they have not been added yet.
+ */
+static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv,
+				    struct hlist_head *mcast_list)
+{
+	struct batadv_hw_addr *mcast_entry;
+	struct hlist_node *tmp;
+
+	if (!mcast_list)
+		return;
+
+	hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) {
+		if (batadv_mcast_mla_is_duplicate(mcast_entry->addr,
+						  &bat_priv->mcast.mla_list))
+			continue;
+
+		if (!batadv_tt_local_add(bat_priv->soft_iface,
+					 mcast_entry->addr, BATADV_NO_FLAGS,
+					 BATADV_NULL_IFINDEX, BATADV_NO_MARK))
+			continue;
+
+		hlist_del(&mcast_entry->list);
+		hlist_add_head(&mcast_entry->list, &bat_priv->mcast.mla_list);
+	}
+}
+
+/**
+ * batadv_mcast_has_bridge - check whether the soft-iface is bridged
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Checks whether there is a bridge on top of our soft interface. Returns
+ * true if so, false otherwise.
+ */
+static bool batadv_mcast_has_bridge(struct batadv_priv *bat_priv)
+{
+	struct net_device *upper = bat_priv->soft_iface;
+
+	rcu_read_lock();
+	do {
+		upper = netdev_master_upper_dev_get_rcu(upper);
+	} while (upper && !(upper->priv_flags & IFF_EBRIDGE));
+	rcu_read_unlock();
+
+	return upper;
+}
+
+/**
+ * batadv_mcast_mla_tvlv_update - update multicast tvlv
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Updates the own multicast tvlv with our current multicast related settings,
+ * capabilities and inabilities.
+ *
+ * Returns true if the tvlv container is registered afterwards. Otherwise
+ * returns false.
+ */
+static bool batadv_mcast_mla_tvlv_update(struct batadv_priv *bat_priv)
+{
+	struct batadv_tvlv_mcast_data mcast_data;
+
+	mcast_data.flags = BATADV_NO_FLAGS;
+	memset(mcast_data.reserved, 0, sizeof(mcast_data.reserved));
+
+	/* Avoid attaching MLAs, if there is a bridge on top of our soft
+	 * interface, we don't support that yet (TODO)
+	 */
+	if (batadv_mcast_has_bridge(bat_priv)) {
+		if (bat_priv->mcast.enabled) {
+			batadv_tvlv_container_unregister(bat_priv,
+							 BATADV_TVLV_MCAST, 1);
+			bat_priv->mcast.enabled = false;
+		}
+
+		return false;
+	}
+
+	if (!bat_priv->mcast.enabled ||
+	    mcast_data.flags != bat_priv->mcast.flags) {
+		batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 1,
+					       &mcast_data, sizeof(mcast_data));
+		bat_priv->mcast.flags = mcast_data.flags;
+		bat_priv->mcast.enabled = true;
+	}
+
+	return true;
+}
+
+/**
+ * batadv_mcast_mla_update - update the own MLAs
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Updates the own multicast listener announcements in the translation
+ * table as well as the own, announced multicast tvlv container.
+ */
+void batadv_mcast_mla_update(struct batadv_priv *bat_priv)
+{
+	struct net_device *soft_iface = bat_priv->soft_iface;
+	struct hlist_head mcast_list = HLIST_HEAD_INIT;
+	int ret;
+
+	if (!batadv_mcast_mla_tvlv_update(bat_priv))
+		goto update;
+
+	ret = batadv_mcast_mla_softif_get(soft_iface, &mcast_list);
+	if (ret < 0)
+		goto out;
+
+update:
+	batadv_mcast_mla_tt_retract(bat_priv, &mcast_list);
+	batadv_mcast_mla_tt_add(bat_priv, &mcast_list);
+
+out:
+	batadv_mcast_mla_list_free(&mcast_list);
+}
+
+/**
+ * batadv_mcast_forw_mode_check_ipv4 - check for optimized forwarding potential
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the IPv4 packet to check
+ * @is_unsnoopable: stores whether the destination is snoopable
+ *
+ * Checks whether the given IPv4 packet has the potential to be forwarded with a
+ * mode more optimal than classic flooding.
+ *
+ * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM in case of
+ * memory allocation failure.
+ */
+static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
+					     struct sk_buff *skb,
+					     bool *is_unsnoopable)
+{
+	struct iphdr *iphdr;
+
+	/* We might fail due to out-of-memory -> drop it */
+	if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*iphdr)))
+		return -ENOMEM;
+
+	iphdr = ip_hdr(skb);
+
+	/* TODO: Implement Multicast Router Discovery (RFC4286),
+	 * then allow scope > link local, too
+	 */
+	if (!ipv4_is_local_multicast(iphdr->daddr))
+		return -EINVAL;
+
+	/* link-local multicast listeners behind a bridge are
+	 * not snoopable (see RFC4541, section 2.1.2.2)
+	 */
+	*is_unsnoopable = true;
+
+	return 0;
+}
+
+/**
+ * batadv_mcast_forw_mode_check_ipv6 - check for optimized forwarding potential
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the IPv6 packet to check
+ * @is_unsnoopable: stores whether the destination is snoopable
+ *
+ * Checks whether the given IPv6 packet has the potential to be forwarded with a
+ * mode more optimal than classic flooding.
+ *
+ * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM if we are out
+ * of memory.
+ */
+static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
+					     struct sk_buff *skb,
+					     bool *is_unsnoopable)
+{
+	struct ipv6hdr *ip6hdr;
+
+	/* We might fail due to out-of-memory -> drop it */
+	if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*ip6hdr)))
+		return -ENOMEM;
+
+	ip6hdr = ipv6_hdr(skb);
+
+	/* TODO: Implement Multicast Router Discovery (RFC4286),
+	 * then allow scope > link local, too
+	 */
+	if (IPV6_ADDR_MC_SCOPE(&ip6hdr->daddr) != IPV6_ADDR_SCOPE_LINKLOCAL)
+		return -EINVAL;
+
+	/* link-local-all-nodes multicast listeners behind a bridge are
+	 * not snoopable (see RFC4541, section 3, paragraph 3)
+	 */
+	if (ipv6_addr_is_ll_all_nodes(&ip6hdr->daddr))
+		*is_unsnoopable = true;
+
+	return 0;
+}
+
+/**
+ * batadv_mcast_forw_mode_check - check for optimized forwarding potential
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast frame to check
+ * @is_unsnoopable: stores whether the destination is snoopable
+ *
+ * Checks whether the given multicast ethernet frame has the potential to be
+ * forwarded with a mode more optimal than classic flooding.
+ *
+ * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM if we are out
+ * of memory.
+ */
+static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv,
+					struct sk_buff *skb,
+					bool *is_unsnoopable)
+{
+	struct ethhdr *ethhdr = eth_hdr(skb);
+
+	if (!atomic_read(&bat_priv->multicast_mode))
+		return -EINVAL;
+
+	if (atomic_read(&bat_priv->mcast.num_disabled))
+		return -EINVAL;
+
+	switch (ntohs(ethhdr->h_proto)) {
+	case ETH_P_IP:
+		return batadv_mcast_forw_mode_check_ipv4(bat_priv, skb,
+							 is_unsnoopable);
+	case ETH_P_IPV6:
+		return batadv_mcast_forw_mode_check_ipv6(bat_priv, skb,
+							 is_unsnoopable);
+	default:
+		return -EINVAL;
+	}
+}
+
+/**
+ * batadv_mcast_want_all_ip_count - count nodes with unspecific mcast interest
+ * @bat_priv: the bat priv with all the soft interface information
+ * @ethhdr: ethernet header of a packet
+ *
+ * Returns the number of nodes which want all IPv4 multicast traffic if the
+ * given ethhdr is from an IPv4 packet or the number of nodes which want all
+ * IPv6 traffic if it matches an IPv6 packet.
+ */
+static int batadv_mcast_forw_want_all_ip_count(struct batadv_priv *bat_priv,
+					       struct ethhdr *ethhdr)
+{
+	switch (ntohs(ethhdr->h_proto)) {
+	case ETH_P_IP:
+		return atomic_read(&bat_priv->mcast.num_want_all_ipv4);
+	case ETH_P_IPV6:
+		return atomic_read(&bat_priv->mcast.num_want_all_ipv6);
+	default:
+		/* we shouldn't be here... */
+		return 0;
+	}
+}
+
+/**
+ * batadv_mcast_forw_tt_node_get - get a multicast tt node
+ * @bat_priv: the bat priv with all the soft interface information
+ * @ethhdr: the ether header containing the multicast destination
+ *
+ * Returns an orig_node matching the multicast address provided by ethhdr
+ * via a translation table lookup. This increases the returned nodes refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_tt_node_get(struct batadv_priv *bat_priv,
+			      struct ethhdr *ethhdr)
+{
+	return batadv_transtable_search(bat_priv, ethhdr->h_source,
+					ethhdr->h_dest, BATADV_NO_FLAGS);
+}
+
+/**
+ * batadv_mcast_want_forw_ipv4_node_get - get a node with an ipv4 flag
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 flag set and
+ * increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_ipv4_node_get(struct batadv_priv *bat_priv)
+{
+	struct batadv_orig_node *tmp_orig_node, *orig_node = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp_orig_node,
+				 &bat_priv->mcast.want_all_ipv4_list,
+				 mcast_want_all_ipv4_node) {
+		if (!atomic_inc_not_zero(&tmp_orig_node->refcount))
+			continue;
+
+		orig_node = tmp_orig_node;
+		break;
+	}
+	rcu_read_unlock();
+
+	return orig_node;
+}
+
+/**
+ * batadv_mcast_want_forw_ipv6_node_get - get a node with an ipv6 flag
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV6 flag set
+ * and increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_ipv6_node_get(struct batadv_priv *bat_priv)
+{
+	struct batadv_orig_node *tmp_orig_node, *orig_node = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp_orig_node,
+				 &bat_priv->mcast.want_all_ipv6_list,
+				 mcast_want_all_ipv6_node) {
+		if (!atomic_inc_not_zero(&tmp_orig_node->refcount))
+			continue;
+
+		orig_node = tmp_orig_node;
+		break;
+	}
+	rcu_read_unlock();
+
+	return orig_node;
+}
+
+/**
+ * batadv_mcast_want_forw_ip_node_get - get a node with an ipv4/ipv6 flag
+ * @bat_priv: the bat priv with all the soft interface information
+ * @ethhdr: an ethernet header to determine the protocol family from
+ *
+ * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 or
+ * BATADV_MCAST_WANT_ALL_IPV6 flag, depending on the provided ethhdr, set and
+ * increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_ip_node_get(struct batadv_priv *bat_priv,
+			      struct ethhdr *ethhdr)
+{
+	switch (ntohs(ethhdr->h_proto)) {
+	case ETH_P_IP:
+		return batadv_mcast_forw_ipv4_node_get(bat_priv);
+	case ETH_P_IPV6:
+		return batadv_mcast_forw_ipv6_node_get(bat_priv);
+	default:
+		/* we shouldn't be here... */
+		return NULL;
+	}
+}
+
+/**
+ * batadv_mcast_want_forw_unsnoop_node_get - get a node with an unsnoopable flag
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag
+ * set and increases its refcount.
+ */
+static struct batadv_orig_node *
+batadv_mcast_forw_unsnoop_node_get(struct batadv_priv *bat_priv)
+{
+	struct batadv_orig_node *tmp_orig_node, *orig_node = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp_orig_node,
+				 &bat_priv->mcast.want_all_unsnoopables_list,
+				 mcast_want_all_unsnoopables_node) {
+		if (!atomic_inc_not_zero(&tmp_orig_node->refcount))
+			continue;
+
+		orig_node = tmp_orig_node;
+		break;
+	}
+	rcu_read_unlock();
+
+	return orig_node;
+}
+
+/**
+ * batadv_mcast_forw_mode - check on how to forward a multicast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: The multicast packet to check
+ * @orig: an originator to be set to forward the skb to
+ *
+ * Returns the forwarding mode as enum batadv_forw_mode and in case of
+ * BATADV_FORW_SINGLE set the orig to the single originator the skb
+ * should be forwarded to.
+ */
+enum batadv_forw_mode
+batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
+		       struct batadv_orig_node **orig)
+{
+	int ret, tt_count, ip_count, unsnoop_count, total_count;
+	bool is_unsnoopable = false;
+	struct ethhdr *ethhdr;
+
+	ret = batadv_mcast_forw_mode_check(bat_priv, skb, &is_unsnoopable);
+	if (ret == -ENOMEM)
+		return BATADV_FORW_NONE;
+	else if (ret < 0)
+		return BATADV_FORW_ALL;
+
+	ethhdr = eth_hdr(skb);
+
+	tt_count = batadv_tt_global_hash_count(bat_priv, ethhdr->h_dest,
+					       BATADV_NO_FLAGS);
+	ip_count = batadv_mcast_forw_want_all_ip_count(bat_priv, ethhdr);
+	unsnoop_count = !is_unsnoopable ? 0 :
+			atomic_read(&bat_priv->mcast.num_want_all_unsnoopables);
+
+	total_count = tt_count + ip_count + unsnoop_count;
+
+	switch (total_count) {
+	case 1:
+		if (tt_count)
+			*orig = batadv_mcast_forw_tt_node_get(bat_priv, ethhdr);
+		else if (ip_count)
+			*orig = batadv_mcast_forw_ip_node_get(bat_priv, ethhdr);
+		else if (unsnoop_count)
+			*orig = batadv_mcast_forw_unsnoop_node_get(bat_priv);
+
+		if (*orig)
+			return BATADV_FORW_SINGLE;
+
+		/* fall through */
+	case 0:
+		return BATADV_FORW_NONE;
+	default:
+		return BATADV_FORW_ALL;
+	}
+}
+
+/**
+ * batadv_mcast_want_unsnoop_update - update unsnoop counter and list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node which multicast state might have changed of
+ * @mcast_flags: flags indicating the new multicast state
+ *
+ * If the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag of this originator,
+ * orig, has toggled then this method updates counter and list accordingly.
+ */
+static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv,
+					     struct batadv_orig_node *orig,
+					     uint8_t mcast_flags)
+{
+	/* switched from flag unset to set */
+	if (mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
+	    !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)) {
+		atomic_inc(&bat_priv->mcast.num_want_all_unsnoopables);
+
+		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+		hlist_add_head_rcu(&orig->mcast_want_all_unsnoopables_node,
+				   &bat_priv->mcast.want_all_unsnoopables_list);
+		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+	/* switched from flag set to unset */
+	} else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) &&
+		   orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) {
+		atomic_dec(&bat_priv->mcast.num_want_all_unsnoopables);
+
+		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+		hlist_del_rcu(&orig->mcast_want_all_unsnoopables_node);
+		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+	}
+}
+
+/**
+ * batadv_mcast_want_ipv4_update - update want-all-ipv4 counter and list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node which multicast state might have changed of
+ * @mcast_flags: flags indicating the new multicast state
+ *
+ * If the BATADV_MCAST_WANT_ALL_IPV4 flag of this originator, orig, has
+ * toggled then this method updates counter and list accordingly.
+ */
+static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv,
+					  struct batadv_orig_node *orig,
+					  uint8_t mcast_flags)
+{
+	/* switched from flag unset to set */
+	if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV4 &&
+	    !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4)) {
+		atomic_inc(&bat_priv->mcast.num_want_all_ipv4);
+
+		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+		hlist_add_head_rcu(&orig->mcast_want_all_ipv4_node,
+				   &bat_priv->mcast.want_all_ipv4_list);
+		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+	/* switched from flag set to unset */
+	} else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) &&
+		   orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) {
+		atomic_dec(&bat_priv->mcast.num_want_all_ipv4);
+
+		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+		hlist_del_rcu(&orig->mcast_want_all_ipv4_node);
+		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+	}
+}
+
+/**
+ * batadv_mcast_want_ipv6_update - update want-all-ipv6 counter and list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node which multicast state might have changed of
+ * @mcast_flags: flags indicating the new multicast state
+ *
+ * If the BATADV_MCAST_WANT_ALL_IPV6 flag of this originator, orig, has
+ * toggled then this method updates counter and list accordingly.
+ */
+static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv,
+					  struct batadv_orig_node *orig,
+					  uint8_t mcast_flags)
+{
+	/* switched from flag unset to set */
+	if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV6 &&
+	    !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6)) {
+		atomic_inc(&bat_priv->mcast.num_want_all_ipv6);
+
+		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+		hlist_add_head_rcu(&orig->mcast_want_all_ipv6_node,
+				   &bat_priv->mcast.want_all_ipv6_list);
+		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+	/* switched from flag set to unset */
+	} else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) &&
+		   orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) {
+		atomic_dec(&bat_priv->mcast.num_want_all_ipv6);
+
+		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
+		hlist_del_rcu(&orig->mcast_want_all_ipv6_node);
+		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
+	}
+}
+
+/**
+ * batadv_mcast_tvlv_ogm_handler_v1 - process incoming multicast tvlv container
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig: the orig_node of the ogm
+ * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags)
+ * @tvlv_value: tvlv buffer containing the multicast data
+ * @tvlv_value_len: tvlv buffer length
+ */
+static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
+					     struct batadv_orig_node *orig,
+					     uint8_t flags,
+					     void *tvlv_value,
+					     uint16_t tvlv_value_len)
+{
+	bool orig_mcast_enabled = !(flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
+	uint8_t mcast_flags = BATADV_NO_FLAGS;
+	bool orig_initialized;
+
+	orig_initialized = orig->capa_initialized & BATADV_ORIG_CAPA_HAS_MCAST;
+
+	/* If mcast support is turned on decrease the disabled mcast node
+	 * counter only if we had increased it for this node before. If this
+	 * is a completely new orig_node no need to decrease the counter.
+	 */
+	if (orig_mcast_enabled &&
+	    !(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST)) {
+		if (orig_initialized)
+			atomic_dec(&bat_priv->mcast.num_disabled);
+		orig->capabilities |= BATADV_ORIG_CAPA_HAS_MCAST;
+	/* If mcast support is being switched off increase the disabled
+	 * mcast node counter.
+	 */
+	} else if (!orig_mcast_enabled &&
+		   orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST) {
+		atomic_inc(&bat_priv->mcast.num_disabled);
+		orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_MCAST;
+	}
+
+	orig->capa_initialized |= BATADV_ORIG_CAPA_HAS_MCAST;
+
+	if (orig_mcast_enabled && tvlv_value &&
+	    (tvlv_value_len >= sizeof(mcast_flags)))
+		mcast_flags = *(uint8_t *)tvlv_value;
+
+	batadv_mcast_want_unsnoop_update(bat_priv, orig, mcast_flags);
+	batadv_mcast_want_ipv4_update(bat_priv, orig, mcast_flags);
+	batadv_mcast_want_ipv6_update(bat_priv, orig, mcast_flags);
+
+	orig->mcast_flags = mcast_flags;
+}
+
+/**
+ * batadv_mcast_init - initialize the multicast optimizations structures
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+void batadv_mcast_init(struct batadv_priv *bat_priv)
+{
+	batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler_v1,
+				     NULL, BATADV_TVLV_MCAST, 1,
+				     BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
+}
+
+/**
+ * batadv_mcast_free - free the multicast optimizations structures
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+void batadv_mcast_free(struct batadv_priv *bat_priv)
+{
+	batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 1);
+	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 1);
+
+	batadv_mcast_mla_tt_retract(bat_priv, NULL);
+}
+
+/**
+ * batadv_mcast_purge_orig - reset originator global mcast state modifications
+ * @orig: the originator which is going to get purged
+ */
+void batadv_mcast_purge_orig(struct batadv_orig_node *orig)
+{
+	struct batadv_priv *bat_priv = orig->bat_priv;
+
+	if (!(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST))
+		atomic_dec(&bat_priv->mcast.num_disabled);
+
+	batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS);
+	batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS);
+	batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS);
+}
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
new file mode 100644
index 00000000000..73b5d45819c
--- /dev/null
+++ b/net/batman-adv/multicast.h
@@ -0,0 +1,80 @@
+/* Copyright (C) 2014 B.A.T.M.A.N. contributors:
+ *
+ * Linus Lüssing
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _NET_BATMAN_ADV_MULTICAST_H_
+#define _NET_BATMAN_ADV_MULTICAST_H_
+
+/**
+ * batadv_forw_mode - the way a packet should be forwarded as
+ * @BATADV_FORW_ALL: forward the packet to all nodes (currently via classic
+ *  flooding)
+ * @BATADV_FORW_SINGLE: forward the packet to a single node (currently via the
+ *  BATMAN unicast routing protocol)
+ * @BATADV_FORW_NONE: don't forward, drop it
+ */
+enum batadv_forw_mode {
+	BATADV_FORW_ALL,
+	BATADV_FORW_SINGLE,
+	BATADV_FORW_NONE,
+};
+
+#ifdef CONFIG_BATMAN_ADV_MCAST
+
+void batadv_mcast_mla_update(struct batadv_priv *bat_priv);
+
+enum batadv_forw_mode
+batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
+		       struct batadv_orig_node **mcast_single_orig);
+
+void batadv_mcast_init(struct batadv_priv *bat_priv);
+
+void batadv_mcast_free(struct batadv_priv *bat_priv);
+
+void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node);
+
+#else
+
+static inline void batadv_mcast_mla_update(struct batadv_priv *bat_priv)
+{
+	return;
+}
+
+static inline enum batadv_forw_mode
+batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
+		       struct batadv_orig_node **mcast_single_orig)
+{
+	return BATADV_FORW_ALL;
+}
+
+static inline int batadv_mcast_init(struct batadv_priv *bat_priv)
+{
+	return 0;
+}
+
+static inline void batadv_mcast_free(struct batadv_priv *bat_priv)
+{
+	return;
+}
+
+static inline void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node)
+{
+	return;
+}
+
+#endif /* CONFIG_BATMAN_ADV_MCAST */
+
+#endif /* _NET_BATMAN_ADV_MULTICAST_H_ */
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 351e199bc0a..8d04d174669 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2012-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors:
  *
  * Martin Hundebøll, Jeppe Ledet-Pedersen
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/debugfs.h>
@@ -88,6 +86,7 @@ static void batadv_nc_tvlv_container_update(struct batadv_priv *bat_priv)
 void batadv_nc_status_update(struct net_device *net_dev)
 {
 	struct batadv_priv *bat_priv = netdev_priv(net_dev);
+
 	batadv_nc_tvlv_container_update(bat_priv);
 }
 
@@ -720,9 +719,21 @@ static bool batadv_can_nc_with_orig(struct batadv_priv *bat_priv,
 				    struct batadv_orig_node *orig_node,
 				    struct batadv_ogm_packet *ogm_packet)
 {
-	if (orig_node->last_real_seqno != ntohl(ogm_packet->seqno))
+	struct batadv_orig_ifinfo *orig_ifinfo;
+	uint32_t last_real_seqno;
+	uint8_t last_ttl;
+
+	orig_ifinfo = batadv_orig_ifinfo_get(orig_node, BATADV_IF_DEFAULT);
+	if (!orig_ifinfo)
+		return false;
+
+	last_ttl = orig_ifinfo->last_ttl;
+	last_real_seqno = orig_ifinfo->last_real_seqno;
+	batadv_orig_ifinfo_free_ref(orig_ifinfo);
+
+	if (last_real_seqno != ntohl(ogm_packet->seqno))
 		return false;
-	if (orig_node->last_ttl != ogm_packet->header.ttl + 1)
+	if (last_ttl != ogm_packet->ttl + 1)
 		return false;
 	if (!batadv_compare_eth(ogm_packet->orig, ogm_packet->prev_sender))
 		return false;
@@ -809,7 +820,7 @@ static struct batadv_nc_node
 
 	/* Initialize nc_node */
 	INIT_LIST_HEAD(&nc_node->list);
-	memcpy(nc_node->addr, orig_node->orig, ETH_ALEN);
+	ether_addr_copy(nc_node->addr, orig_node->orig);
 	nc_node->orig_node = orig_neigh_node;
 	atomic_set(&nc_node->refcount, 2);
 
@@ -931,8 +942,8 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv,
 	spin_lock_init(&nc_path->packet_list_lock);
 	atomic_set(&nc_path->refcount, 2);
 	nc_path->last_valid = jiffies;
-	memcpy(nc_path->next_hop, dst, ETH_ALEN);
-	memcpy(nc_path->prev_hop, src, ETH_ALEN);
+	ether_addr_copy(nc_path->next_hop, dst);
+	ether_addr_copy(nc_path->prev_hop, src);
 
 	batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_path %pM -> %pM\n",
 		   nc_path->prev_hop,
@@ -1010,6 +1021,8 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv,
 	struct batadv_coded_packet *coded_packet;
 	struct batadv_neigh_node *neigh_tmp, *router_neigh;
 	struct batadv_neigh_node *router_coding = NULL;
+	struct batadv_neigh_ifinfo *router_neigh_ifinfo = NULL;
+	struct batadv_neigh_ifinfo *router_coding_ifinfo = NULL;
 	uint8_t *first_source, *first_dest, *second_source, *second_dest;
 	__be32 packet_id1, packet_id2;
 	size_t count;
@@ -1019,19 +1032,34 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv,
 	int coded_size = sizeof(*coded_packet);
 	int header_add = coded_size - unicast_size;
 
-	router_neigh = batadv_orig_node_get_router(neigh_node->orig_node);
+	/* TODO: do we need to consider the outgoing interface for
+	 * coded packets?
+	 */
+	router_neigh = batadv_orig_router_get(neigh_node->orig_node,
+					      BATADV_IF_DEFAULT);
 	if (!router_neigh)
 		goto out;
 
+	router_neigh_ifinfo = batadv_neigh_ifinfo_get(router_neigh,
+						      BATADV_IF_DEFAULT);
+	if (!router_neigh_ifinfo)
+		goto out;
+
 	neigh_tmp = nc_packet->neigh_node;
-	router_coding = batadv_orig_node_get_router(neigh_tmp->orig_node);
+	router_coding = batadv_orig_router_get(neigh_tmp->orig_node,
+					       BATADV_IF_DEFAULT);
 	if (!router_coding)
 		goto out;
 
-	tq_tmp = batadv_nc_random_weight_tq(router_neigh->bat_iv.tq_avg);
-	tq_weighted_neigh = tq_tmp;
-	tq_tmp = batadv_nc_random_weight_tq(router_coding->bat_iv.tq_avg);
-	tq_weighted_coding = tq_tmp;
+	router_coding_ifinfo = batadv_neigh_ifinfo_get(router_coding,
+						       BATADV_IF_DEFAULT);
+	if (!router_coding_ifinfo)
+		goto out;
+
+	tq_tmp = router_neigh_ifinfo->bat_iv.tq_avg;
+	tq_weighted_neigh = batadv_nc_random_weight_tq(tq_tmp);
+	tq_tmp = router_coding_ifinfo->bat_iv.tq_avg;
+	tq_weighted_coding = batadv_nc_random_weight_tq(tq_tmp);
 
 	/* Select one destination for the MAC-header dst-field based on
 	 * weighted TQ-values.
@@ -1082,22 +1110,22 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv,
 	coded_packet = (struct batadv_coded_packet *)skb_dest->data;
 	skb_reset_mac_header(skb_dest);
 
-	coded_packet->header.packet_type = BATADV_CODED;
-	coded_packet->header.version = BATADV_COMPAT_VERSION;
-	coded_packet->header.ttl = packet1->header.ttl;
+	coded_packet->packet_type = BATADV_CODED;
+	coded_packet->version = BATADV_COMPAT_VERSION;
+	coded_packet->ttl = packet1->ttl;
 
 	/* Info about first unicast packet */
-	memcpy(coded_packet->first_source, first_source, ETH_ALEN);
-	memcpy(coded_packet->first_orig_dest, packet1->dest, ETH_ALEN);
+	ether_addr_copy(coded_packet->first_source, first_source);
+	ether_addr_copy(coded_packet->first_orig_dest, packet1->dest);
 	coded_packet->first_crc = packet_id1;
 	coded_packet->first_ttvn = packet1->ttvn;
 
 	/* Info about second unicast packet */
-	memcpy(coded_packet->second_dest, second_dest, ETH_ALEN);
-	memcpy(coded_packet->second_source, second_source, ETH_ALEN);
-	memcpy(coded_packet->second_orig_dest, packet2->dest, ETH_ALEN);
+	ether_addr_copy(coded_packet->second_dest, second_dest);
+	ether_addr_copy(coded_packet->second_source, second_source);
+	ether_addr_copy(coded_packet->second_orig_dest, packet2->dest);
 	coded_packet->second_crc = packet_id2;
-	coded_packet->second_ttl = packet2->header.ttl;
+	coded_packet->second_ttl = packet2->ttl;
 	coded_packet->second_ttvn = packet2->ttvn;
 	coded_packet->coded_len = htons(coding_len);
 
@@ -1155,6 +1183,10 @@ out:
 		batadv_neigh_node_free_ref(router_neigh);
 	if (router_coding)
 		batadv_neigh_node_free_ref(router_coding);
+	if (router_neigh_ifinfo)
+		batadv_neigh_ifinfo_free_ref(router_neigh_ifinfo);
+	if (router_coding_ifinfo)
+		batadv_neigh_ifinfo_free_ref(router_coding_ifinfo);
 	return res;
 }
 
@@ -1312,14 +1344,14 @@ static void batadv_nc_skb_store_before_coding(struct batadv_priv *bat_priv,
 	struct ethhdr *ethhdr;
 
 	/* Copy skb header to change the mac header */
-	skb = pskb_copy(skb, GFP_ATOMIC);
+	skb = pskb_copy_for_clone(skb, GFP_ATOMIC);
 	if (!skb)
 		return;
 
 	/* Set the mac header as if we actually sent the packet uncoded */
 	ethhdr = eth_hdr(skb);
-	memcpy(ethhdr->h_source, ethhdr->h_dest, ETH_ALEN);
-	memcpy(ethhdr->h_dest, eth_dst_new, ETH_ALEN);
+	ether_addr_copy(ethhdr->h_source, ethhdr->h_dest);
+	ether_addr_copy(ethhdr->h_dest, eth_dst_new);
 
 	/* Set data pointer to MAC header to mimic packets from our tx path */
 	skb_push(skb, ETH_HLEN);
@@ -1452,7 +1484,7 @@ bool batadv_nc_skb_forward(struct sk_buff *skb,
 	/* We only handle unicast packets */
 	payload = skb_network_header(skb);
 	packet = (struct batadv_unicast_packet *)payload;
-	if (packet->header.packet_type != BATADV_UNICAST)
+	if (packet->packet_type != BATADV_UNICAST)
 		goto out;
 
 	/* Try to find a coding opportunity and send the skb if one is found */
@@ -1505,7 +1537,7 @@ void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
 	/* Check for supported packet type */
 	payload = skb_network_header(skb);
 	packet = (struct batadv_unicast_packet *)payload;
-	if (packet->header.packet_type != BATADV_UNICAST)
+	if (packet->packet_type != BATADV_UNICAST)
 		goto out;
 
 	/* Find existing nc_path or create a new */
@@ -1605,7 +1637,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 	/* Reconstruct original mac header */
 	ethhdr = eth_hdr(skb);
-	memcpy(ethhdr, &ethhdr_tmp, sizeof(*ethhdr));
+	*ethhdr = ethhdr_tmp;
 
 	/* Select the correct unicast header information based on the location
 	 * of our mac address in the coded_packet header
@@ -1615,7 +1647,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		 * so the Ethernet address must be copied to h_dest and
 		 * pkt_type changed from PACKET_OTHERHOST to PACKET_HOST
 		 */
-		memcpy(ethhdr->h_dest, coded_packet_tmp.second_dest, ETH_ALEN);
+		ether_addr_copy(ethhdr->h_dest, coded_packet_tmp.second_dest);
 		skb->pkt_type = PACKET_HOST;
 
 		orig_dest = coded_packet_tmp.second_orig_dest;
@@ -1623,7 +1655,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		ttvn = coded_packet_tmp.second_ttvn;
 	} else {
 		orig_dest = coded_packet_tmp.first_orig_dest;
-		ttl = coded_packet_tmp.header.ttl;
+		ttl = coded_packet_tmp.ttl;
 		ttvn = coded_packet_tmp.first_ttvn;
 	}
 
@@ -1648,10 +1680,10 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 	/* Create decoded unicast packet */
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
-	unicast_packet->header.packet_type = BATADV_UNICAST;
-	unicast_packet->header.version = BATADV_COMPAT_VERSION;
-	unicast_packet->header.ttl = ttl;
-	memcpy(unicast_packet->dest, orig_dest, ETH_ALEN);
+	unicast_packet->packet_type = BATADV_UNICAST;
+	unicast_packet->version = BATADV_COMPAT_VERSION;
+	unicast_packet->ttl = ttl;
+	ether_addr_copy(unicast_packet->dest, orig_dest);
 	unicast_packet->ttvn = ttvn;
 
 	batadv_nc_packet_free(nc_packet);
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
index d4fd315b526..358c0d686ab 100644
--- a/net/batman-adv/network-coding.h
+++ b/net/batman-adv/network-coding.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2012-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2012-2014 B.A.T.M.A.N. contributors:
  *
  * Martin Hundebøll, Jeppe Ledet-Pedersen
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_NETWORK_CODING_H_
@@ -64,7 +62,6 @@ static inline int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
 
 static inline void batadv_nc_mesh_free(struct batadv_priv *bat_priv)
 {
-	return;
 }
 
 static inline void
@@ -74,7 +71,6 @@ batadv_nc_update_nc_node(struct batadv_priv *bat_priv,
 			 struct batadv_ogm_packet *ogm_packet,
 			 int is_single_hop_neigh)
 {
-	return;
 }
 
 static inline void
@@ -83,17 +79,14 @@ batadv_nc_purge_orig(struct batadv_priv *bat_priv,
 		     bool (*to_purge)(struct batadv_priv *,
 				      struct batadv_nc_node *))
 {
-	return;
 }
 
 static inline void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv)
 {
-	return;
 }
 
 static inline void batadv_nc_init_orig(struct batadv_orig_node *orig_node)
 {
-	return;
 }
 
 static inline bool batadv_nc_skb_forward(struct sk_buff *skb,
@@ -106,14 +99,12 @@ static inline void
 batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
 				 struct sk_buff *skb)
 {
-	return;
 }
 
 static inline void
 batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
 				    struct sk_buff *skb)
 {
-	return;
 }
 
 static inline int batadv_nc_nodes_seq_print_text(struct seq_file *seq,
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 8ab14340d10..6a484514cd3 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -29,6 +27,7 @@
 #include "bridge_loop_avoidance.h"
 #include "network-coding.h"
 #include "fragmentation.h"
+#include "multicast.h"
 
 /* hash class keys */
 static struct lock_class_key batadv_orig_hash_lock_class_key;
@@ -41,7 +40,7 @@ int batadv_compare_orig(const struct hlist_node *node, const void *data2)
 	const void *data1 = container_of(node, struct batadv_orig_node,
 					 hash_entry);
 
-	return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0);
+	return batadv_compare_eth(data1, data2);
 }
 
 /**
@@ -150,20 +149,114 @@ err:
 	return -ENOMEM;
 }
 
+/**
+ * batadv_neigh_ifinfo_free_rcu - free the neigh_ifinfo object
+ * @rcu: rcu pointer of the neigh_ifinfo object
+ */
+static void batadv_neigh_ifinfo_free_rcu(struct rcu_head *rcu)
+{
+	struct batadv_neigh_ifinfo *neigh_ifinfo;
+
+	neigh_ifinfo = container_of(rcu, struct batadv_neigh_ifinfo, rcu);
+
+	if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
+		batadv_hardif_free_ref_now(neigh_ifinfo->if_outgoing);
+
+	kfree(neigh_ifinfo);
+}
+
+/**
+ * batadv_neigh_ifinfo_free_now - decrement the refcounter and possibly free
+ *  the neigh_ifinfo (without rcu callback)
+ * @neigh_ifinfo: the neigh_ifinfo object to release
+ */
+static void
+batadv_neigh_ifinfo_free_ref_now(struct batadv_neigh_ifinfo *neigh_ifinfo)
+{
+	if (atomic_dec_and_test(&neigh_ifinfo->refcount))
+		batadv_neigh_ifinfo_free_rcu(&neigh_ifinfo->rcu);
+}
+
+/**
+ * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly free
+ *  the neigh_ifinfo
+ * @neigh_ifinfo: the neigh_ifinfo object to release
+ */
+void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo)
+{
+	if (atomic_dec_and_test(&neigh_ifinfo->refcount))
+		call_rcu(&neigh_ifinfo->rcu, batadv_neigh_ifinfo_free_rcu);
+}
+
+/**
+ * batadv_neigh_node_free_rcu - free the neigh_node
+ * @rcu: rcu pointer of the neigh_node
+ */
+static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
+{
+	struct hlist_node *node_tmp;
+	struct batadv_neigh_node *neigh_node;
+	struct batadv_neigh_ifinfo *neigh_ifinfo;
+
+	neigh_node = container_of(rcu, struct batadv_neigh_node, rcu);
+
+	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
+				  &neigh_node->ifinfo_list, list) {
+		batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo);
+	}
+	batadv_hardif_free_ref_now(neigh_node->if_incoming);
+
+	kfree(neigh_node);
+}
+
+/**
+ * batadv_neigh_node_free_ref_now - decrement the neighbors refcounter
+ *  and possibly free it (without rcu callback)
+ * @neigh_node: neigh neighbor to free
+ */
+static void
+batadv_neigh_node_free_ref_now(struct batadv_neigh_node *neigh_node)
+{
+	if (atomic_dec_and_test(&neigh_node->refcount))
+		batadv_neigh_node_free_rcu(&neigh_node->rcu);
+}
+
+/**
+ * batadv_neigh_node_free_ref - decrement the neighbors refcounter
+ *  and possibly free it
+ * @neigh_node: neigh neighbor to free
+ */
 void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node)
 {
 	if (atomic_dec_and_test(&neigh_node->refcount))
-		kfree_rcu(neigh_node, rcu);
+		call_rcu(&neigh_node->rcu, batadv_neigh_node_free_rcu);
 }
 
-/* increases the refcounter of a found router */
+/**
+ * batadv_orig_node_get_router - router to the originator depending on iface
+ * @orig_node: the orig node for the router
+ * @if_outgoing: the interface where the payload packet has been received or
+ *  the OGM should be sent to
+ *
+ * Returns the neighbor which should be router for this orig_node/iface.
+ *
+ * The object is returned with refcounter increased by 1.
+ */
 struct batadv_neigh_node *
-batadv_orig_node_get_router(struct batadv_orig_node *orig_node)
+batadv_orig_router_get(struct batadv_orig_node *orig_node,
+		       const struct batadv_hard_iface *if_outgoing)
 {
-	struct batadv_neigh_node *router;
+	struct batadv_orig_ifinfo *orig_ifinfo;
+	struct batadv_neigh_node *router = NULL;
 
 	rcu_read_lock();
-	router = rcu_dereference(orig_node->router);
+	hlist_for_each_entry_rcu(orig_ifinfo, &orig_node->ifinfo_list, list) {
+		if (orig_ifinfo->if_outgoing != if_outgoing)
+			continue;
+
+		router = rcu_dereference(orig_ifinfo->router);
+		break;
+	}
 
 	if (router && !atomic_inc_not_zero(&router->refcount))
 		router = NULL;
@@ -173,6 +266,164 @@ batadv_orig_node_get_router(struct batadv_orig_node *orig_node)
 }
 
 /**
+ * batadv_orig_ifinfo_get - find the ifinfo from an orig_node
+ * @orig_node: the orig node to be queried
+ * @if_outgoing: the interface for which the ifinfo should be acquired
+ *
+ * Returns the requested orig_ifinfo or NULL if not found.
+ *
+ * The object is returned with refcounter increased by 1.
+ */
+struct batadv_orig_ifinfo *
+batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node,
+		       struct batadv_hard_iface *if_outgoing)
+{
+	struct batadv_orig_ifinfo *tmp, *orig_ifinfo = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp, &orig_node->ifinfo_list,
+				 list) {
+		if (tmp->if_outgoing != if_outgoing)
+			continue;
+
+		if (!atomic_inc_not_zero(&tmp->refcount))
+			continue;
+
+		orig_ifinfo = tmp;
+		break;
+	}
+	rcu_read_unlock();
+
+	return orig_ifinfo;
+}
+
+/**
+ * batadv_orig_ifinfo_new - search and possibly create an orig_ifinfo object
+ * @orig_node: the orig node to be queried
+ * @if_outgoing: the interface for which the ifinfo should be acquired
+ *
+ * Returns NULL in case of failure or the orig_ifinfo object for the if_outgoing
+ * interface otherwise. The object is created and added to the list
+ * if it does not exist.
+ *
+ * The object is returned with refcounter increased by 1.
+ */
+struct batadv_orig_ifinfo *
+batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node,
+		       struct batadv_hard_iface *if_outgoing)
+{
+	struct batadv_orig_ifinfo *orig_ifinfo = NULL;
+	unsigned long reset_time;
+
+	spin_lock_bh(&orig_node->neigh_list_lock);
+
+	orig_ifinfo = batadv_orig_ifinfo_get(orig_node, if_outgoing);
+	if (orig_ifinfo)
+		goto out;
+
+	orig_ifinfo = kzalloc(sizeof(*orig_ifinfo), GFP_ATOMIC);
+	if (!orig_ifinfo)
+		goto out;
+
+	if (if_outgoing != BATADV_IF_DEFAULT &&
+	    !atomic_inc_not_zero(&if_outgoing->refcount)) {
+		kfree(orig_ifinfo);
+		orig_ifinfo = NULL;
+		goto out;
+	}
+
+	reset_time = jiffies - 1;
+	reset_time -= msecs_to_jiffies(BATADV_RESET_PROTECTION_MS);
+	orig_ifinfo->batman_seqno_reset = reset_time;
+	orig_ifinfo->if_outgoing = if_outgoing;
+	INIT_HLIST_NODE(&orig_ifinfo->list);
+	atomic_set(&orig_ifinfo->refcount, 2);
+	hlist_add_head_rcu(&orig_ifinfo->list,
+			   &orig_node->ifinfo_list);
+out:
+	spin_unlock_bh(&orig_node->neigh_list_lock);
+	return orig_ifinfo;
+}
+
+/**
+ * batadv_neigh_ifinfo_get - find the ifinfo from an neigh_node
+ * @neigh_node: the neigh node to be queried
+ * @if_outgoing: the interface for which the ifinfo should be acquired
+ *
+ * The object is returned with refcounter increased by 1.
+ *
+ * Returns the requested neigh_ifinfo or NULL if not found
+ */
+struct batadv_neigh_ifinfo *
+batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh,
+			struct batadv_hard_iface *if_outgoing)
+{
+	struct batadv_neigh_ifinfo *neigh_ifinfo = NULL,
+				   *tmp_neigh_ifinfo;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp_neigh_ifinfo, &neigh->ifinfo_list,
+				 list) {
+		if (tmp_neigh_ifinfo->if_outgoing != if_outgoing)
+			continue;
+
+		if (!atomic_inc_not_zero(&tmp_neigh_ifinfo->refcount))
+			continue;
+
+		neigh_ifinfo = tmp_neigh_ifinfo;
+		break;
+	}
+	rcu_read_unlock();
+
+	return neigh_ifinfo;
+}
+
+/**
+ * batadv_neigh_ifinfo_new - search and possibly create an neigh_ifinfo object
+ * @neigh_node: the neigh node to be queried
+ * @if_outgoing: the interface for which the ifinfo should be acquired
+ *
+ * Returns NULL in case of failure or the neigh_ifinfo object for the
+ * if_outgoing interface otherwise. The object is created and added to the list
+ * if it does not exist.
+ *
+ * The object is returned with refcounter increased by 1.
+ */
+struct batadv_neigh_ifinfo *
+batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh,
+			struct batadv_hard_iface *if_outgoing)
+{
+	struct batadv_neigh_ifinfo *neigh_ifinfo;
+
+	spin_lock_bh(&neigh->ifinfo_lock);
+
+	neigh_ifinfo = batadv_neigh_ifinfo_get(neigh, if_outgoing);
+	if (neigh_ifinfo)
+		goto out;
+
+	neigh_ifinfo = kzalloc(sizeof(*neigh_ifinfo), GFP_ATOMIC);
+	if (!neigh_ifinfo)
+		goto out;
+
+	if (if_outgoing && !atomic_inc_not_zero(&if_outgoing->refcount)) {
+		kfree(neigh_ifinfo);
+		neigh_ifinfo = NULL;
+		goto out;
+	}
+
+	INIT_HLIST_NODE(&neigh_ifinfo->list);
+	atomic_set(&neigh_ifinfo->refcount, 2);
+	neigh_ifinfo->if_outgoing = if_outgoing;
+
+	hlist_add_head_rcu(&neigh_ifinfo->list, &neigh->ifinfo_list);
+
+out:
+	spin_unlock_bh(&neigh->ifinfo_lock);
+
+	return neigh_ifinfo;
+}
+
+/**
  * batadv_neigh_node_new - create and init a new neigh_node object
  * @hard_iface: the interface where the neighbour is connected to
  * @neigh_addr: the mac address of the neighbour interface
@@ -193,13 +444,13 @@ batadv_neigh_node_new(struct batadv_hard_iface *hard_iface,
 		goto out;
 
 	INIT_HLIST_NODE(&neigh_node->list);
+	INIT_HLIST_HEAD(&neigh_node->ifinfo_list);
+	spin_lock_init(&neigh_node->ifinfo_lock);
 
-	memcpy(neigh_node->addr, neigh_addr, ETH_ALEN);
+	ether_addr_copy(neigh_node->addr, neigh_addr);
 	neigh_node->if_incoming = hard_iface;
 	neigh_node->orig_node = orig_node;
 
-	INIT_LIST_HEAD(&neigh_node->bonding_list);
-
 	/* extra reference for return */
 	atomic_set(&neigh_node->refcount, 2);
 
@@ -207,32 +458,113 @@ out:
 	return neigh_node;
 }
 
+/**
+ * batadv_neigh_node_get - retrieve a neighbour from the list
+ * @orig_node: originator which the neighbour belongs to
+ * @hard_iface: the interface where this neighbour is connected to
+ * @addr: the address of the neighbour
+ *
+ * Looks for and possibly returns a neighbour belonging to this originator list
+ * which is connected through the provided hard interface.
+ * Returns NULL if the neighbour is not found.
+ */
+struct batadv_neigh_node *
+batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
+		      const struct batadv_hard_iface *hard_iface,
+		      const uint8_t *addr)
+{
+	struct batadv_neigh_node *tmp_neigh_node, *res = NULL;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) {
+		if (!batadv_compare_eth(tmp_neigh_node->addr, addr))
+			continue;
+
+		if (tmp_neigh_node->if_incoming != hard_iface)
+			continue;
+
+		if (!atomic_inc_not_zero(&tmp_neigh_node->refcount))
+			continue;
+
+		res = tmp_neigh_node;
+		break;
+	}
+	rcu_read_unlock();
+
+	return res;
+}
+
+/**
+ * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object
+ * @rcu: rcu pointer of the orig_ifinfo object
+ */
+static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
+{
+	struct batadv_orig_ifinfo *orig_ifinfo;
+	struct batadv_neigh_node *router;
+
+	orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu);
+
+	if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
+		batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing);
+
+	/* this is the last reference to this object */
+	router = rcu_dereference_protected(orig_ifinfo->router, true);
+	if (router)
+		batadv_neigh_node_free_ref_now(router);
+	kfree(orig_ifinfo);
+}
+
+/**
+ * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free
+ *  the orig_ifinfo (without rcu callback)
+ * @orig_ifinfo: the orig_ifinfo object to release
+ */
+static void
+batadv_orig_ifinfo_free_ref_now(struct batadv_orig_ifinfo *orig_ifinfo)
+{
+	if (atomic_dec_and_test(&orig_ifinfo->refcount))
+		batadv_orig_ifinfo_free_rcu(&orig_ifinfo->rcu);
+}
+
+/**
+ * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free
+ *  the orig_ifinfo
+ * @orig_ifinfo: the orig_ifinfo object to release
+ */
+void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo)
+{
+	if (atomic_dec_and_test(&orig_ifinfo->refcount))
+		call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu);
+}
+
 static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
 {
 	struct hlist_node *node_tmp;
-	struct batadv_neigh_node *neigh_node, *tmp_neigh_node;
+	struct batadv_neigh_node *neigh_node;
 	struct batadv_orig_node *orig_node;
+	struct batadv_orig_ifinfo *orig_ifinfo;
 
 	orig_node = container_of(rcu, struct batadv_orig_node, rcu);
 
 	spin_lock_bh(&orig_node->neigh_list_lock);
 
-	/* for all bonding members ... */
-	list_for_each_entry_safe(neigh_node, tmp_neigh_node,
-				 &orig_node->bond_list, bonding_list) {
-		list_del_rcu(&neigh_node->bonding_list);
-		batadv_neigh_node_free_ref(neigh_node);
-	}
-
 	/* for all neighbors towards this originator ... */
 	hlist_for_each_entry_safe(neigh_node, node_tmp,
 				  &orig_node->neigh_list, list) {
 		hlist_del_rcu(&neigh_node->list);
-		batadv_neigh_node_free_ref(neigh_node);
+		batadv_neigh_node_free_ref_now(neigh_node);
 	}
 
+	hlist_for_each_entry_safe(orig_ifinfo, node_tmp,
+				  &orig_node->ifinfo_list, list) {
+		hlist_del_rcu(&orig_ifinfo->list);
+		batadv_orig_ifinfo_free_ref_now(orig_ifinfo);
+	}
 	spin_unlock_bh(&orig_node->neigh_list_lock);
 
+	batadv_mcast_purge_orig(orig_node);
+
 	/* Free nc_nodes */
 	batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL);
 
@@ -327,8 +659,8 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 		return NULL;
 
 	INIT_HLIST_HEAD(&orig_node->neigh_list);
-	INIT_LIST_HEAD(&orig_node->bond_list);
 	INIT_LIST_HEAD(&orig_node->vlan_list);
+	INIT_HLIST_HEAD(&orig_node->ifinfo_list);
 	spin_lock_init(&orig_node->bcast_seqno_lock);
 	spin_lock_init(&orig_node->neigh_list_lock);
 	spin_lock_init(&orig_node->tt_buff_lock);
@@ -340,19 +672,17 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 	/* extra reference for return */
 	atomic_set(&orig_node->refcount, 2);
 
-	orig_node->tt_initialised = false;
 	orig_node->bat_priv = bat_priv;
-	memcpy(orig_node->orig, addr, ETH_ALEN);
+	ether_addr_copy(orig_node->orig, addr);
 	batadv_dat_init_orig_node_addr(orig_node);
-	orig_node->router = NULL;
 	atomic_set(&orig_node->last_ttvn, 0);
 	orig_node->tt_buff = NULL;
 	orig_node->tt_buff_len = 0;
 	reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS);
 	orig_node->bcast_seqno_reset = reset_time;
-	orig_node->batman_seqno_reset = reset_time;
-
-	atomic_set(&orig_node->bond_candidates, 0);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	orig_node->mcast_flags = BATADV_NO_FLAGS;
+#endif
 
 	/* create a vlan object for the "untagged" LAN */
 	vlan = batadv_orig_node_vlan_new(orig_node, BATADV_NO_FLAGS);
@@ -376,20 +706,117 @@ free_orig_node:
 	return NULL;
 }
 
+/**
+ * batadv_purge_neigh_ifinfo - purge obsolete ifinfo entries from neighbor
+ * @bat_priv: the bat priv with all the soft interface information
+ * @neigh: orig node which is to be checked
+ */
+static void
+batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv,
+			  struct batadv_neigh_node *neigh)
+{
+	struct batadv_neigh_ifinfo *neigh_ifinfo;
+	struct batadv_hard_iface *if_outgoing;
+	struct hlist_node *node_tmp;
+
+	spin_lock_bh(&neigh->ifinfo_lock);
+
+	/* for all ifinfo objects for this neighinator */
+	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
+				  &neigh->ifinfo_list, list) {
+		if_outgoing = neigh_ifinfo->if_outgoing;
+
+		/* always keep the default interface */
+		if (if_outgoing == BATADV_IF_DEFAULT)
+			continue;
+
+		/* don't purge if the interface is not (going) down */
+		if ((if_outgoing->if_status != BATADV_IF_INACTIVE) &&
+		    (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) &&
+		    (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED))
+			continue;
+
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "neighbor/ifinfo purge: neighbor %pM, iface: %s\n",
+			   neigh->addr, if_outgoing->net_dev->name);
+
+		hlist_del_rcu(&neigh_ifinfo->list);
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
+	}
+
+	spin_unlock_bh(&neigh->ifinfo_lock);
+}
+
+/**
+ * batadv_purge_orig_ifinfo - purge obsolete ifinfo entries from originator
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: orig node which is to be checked
+ *
+ * Returns true if any ifinfo entry was purged, false otherwise.
+ */
+static bool
+batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv,
+			 struct batadv_orig_node *orig_node)
+{
+	struct batadv_orig_ifinfo *orig_ifinfo;
+	struct batadv_hard_iface *if_outgoing;
+	struct hlist_node *node_tmp;
+	bool ifinfo_purged = false;
+
+	spin_lock_bh(&orig_node->neigh_list_lock);
+
+	/* for all ifinfo objects for this originator */
+	hlist_for_each_entry_safe(orig_ifinfo, node_tmp,
+				  &orig_node->ifinfo_list, list) {
+		if_outgoing = orig_ifinfo->if_outgoing;
+
+		/* always keep the default interface */
+		if (if_outgoing == BATADV_IF_DEFAULT)
+			continue;
+
+		/* don't purge if the interface is not (going) down */
+		if ((if_outgoing->if_status != BATADV_IF_INACTIVE) &&
+		    (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) &&
+		    (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED))
+			continue;
+
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "router/ifinfo purge: originator %pM, iface: %s\n",
+			   orig_node->orig, if_outgoing->net_dev->name);
+
+		ifinfo_purged = true;
+
+		hlist_del_rcu(&orig_ifinfo->list);
+		batadv_orig_ifinfo_free_ref(orig_ifinfo);
+		if (orig_node->last_bonding_candidate == orig_ifinfo) {
+			orig_node->last_bonding_candidate = NULL;
+			batadv_orig_ifinfo_free_ref(orig_ifinfo);
+		}
+	}
+
+	spin_unlock_bh(&orig_node->neigh_list_lock);
+
+	return ifinfo_purged;
+}
+
+
+/**
+ * batadv_purge_orig_neighbors - purges neighbors from originator
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: orig node which is to be checked
+ *
+ * Returns true if any neighbor was purged, false otherwise
+ */
 static bool
 batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
-			    struct batadv_orig_node *orig_node,
-			    struct batadv_neigh_node **best_neigh)
+			    struct batadv_orig_node *orig_node)
 {
-	struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
 	struct hlist_node *node_tmp;
 	struct batadv_neigh_node *neigh_node;
 	bool neigh_purged = false;
 	unsigned long last_seen;
 	struct batadv_hard_iface *if_incoming;
 
-	*best_neigh = NULL;
-
 	spin_lock_bh(&orig_node->neigh_list_lock);
 
 	/* for all neighbors towards this originator ... */
@@ -418,15 +845,12 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
 			neigh_purged = true;
 
 			hlist_del_rcu(&neigh_node->list);
-			batadv_bonding_candidate_del(orig_node, neigh_node);
 			batadv_neigh_node_free_ref(neigh_node);
 		} else {
-			/* store the best_neighbour if this is the first
-			 * iteration or if a better neighbor has been found
+			/* only necessary if not the whole neighbor is to be
+			 * deleted, but some interface has been removed.
 			 */
-			if (!*best_neigh ||
-			    bao->bat_neigh_cmp(neigh_node, *best_neigh) > 0)
-				*best_neigh = neigh_node;
+			batadv_purge_neigh_ifinfo(bat_priv, neigh_node);
 		}
 	}
 
@@ -434,10 +858,57 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
 	return neigh_purged;
 }
 
+/**
+ * batadv_find_best_neighbor - finds the best neighbor after purging
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: orig node which is to be checked
+ * @if_outgoing: the interface for which the metric should be compared
+ *
+ * Returns the current best neighbor, with refcount increased.
+ */
+static struct batadv_neigh_node *
+batadv_find_best_neighbor(struct batadv_priv *bat_priv,
+			  struct batadv_orig_node *orig_node,
+			  struct batadv_hard_iface *if_outgoing)
+{
+	struct batadv_neigh_node *best = NULL, *neigh;
+	struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(neigh, &orig_node->neigh_list, list) {
+		if (best && (bao->bat_neigh_cmp(neigh, if_outgoing,
+						best, if_outgoing) <= 0))
+			continue;
+
+		if (!atomic_inc_not_zero(&neigh->refcount))
+			continue;
+
+		if (best)
+			batadv_neigh_node_free_ref(best);
+
+		best = neigh;
+	}
+	rcu_read_unlock();
+
+	return best;
+}
+
+/**
+ * batadv_purge_orig_node - purges obsolete information from an orig_node
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: orig node which is to be checked
+ *
+ * This function checks if the orig_node or substructures of it have become
+ * obsolete, and purges this information if that's the case.
+ *
+ * Returns true if the orig_node is to be removed, false otherwise.
+ */
 static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 				   struct batadv_orig_node *orig_node)
 {
 	struct batadv_neigh_node *best_neigh_node;
+	struct batadv_hard_iface *hard_iface;
+	bool changed_ifinfo, changed_neigh;
 
 	if (batadv_has_timed_out(orig_node->last_seen,
 				 2 * BATADV_PURGE_TIMEOUT)) {
@@ -446,12 +917,39 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 			   orig_node->orig,
 			   jiffies_to_msecs(orig_node->last_seen));
 		return true;
-	} else {
-		if (batadv_purge_orig_neighbors(bat_priv, orig_node,
-						&best_neigh_node))
-			batadv_update_route(bat_priv, orig_node,
-					    best_neigh_node);
 	}
+	changed_ifinfo = batadv_purge_orig_ifinfo(bat_priv, orig_node);
+	changed_neigh = batadv_purge_orig_neighbors(bat_priv, orig_node);
+
+	if (!changed_ifinfo && !changed_neigh)
+		return false;
+
+	/* first for NULL ... */
+	best_neigh_node = batadv_find_best_neighbor(bat_priv, orig_node,
+						    BATADV_IF_DEFAULT);
+	batadv_update_route(bat_priv, orig_node, BATADV_IF_DEFAULT,
+			    best_neigh_node);
+	if (best_neigh_node)
+		batadv_neigh_node_free_ref(best_neigh_node);
+
+	/* ... then for all other interfaces. */
+	rcu_read_lock();
+	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
+		if (hard_iface->if_status != BATADV_IF_ACTIVE)
+			continue;
+
+		if (hard_iface->soft_iface != bat_priv->soft_iface)
+			continue;
+
+		best_neigh_node = batadv_find_best_neighbor(bat_priv,
+							    orig_node,
+							    hard_iface);
+		batadv_update_route(bat_priv, orig_node, hard_iface,
+				    best_neigh_node);
+		if (best_neigh_node)
+			batadv_neigh_node_free_ref(best_neigh_node);
+	}
+	rcu_read_unlock();
 
 	return false;
 }
@@ -534,11 +1032,58 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset)
 		return 0;
 	}
 
-	bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq);
+	bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq,
+					       BATADV_IF_DEFAULT);
 
 	return 0;
 }
 
+/**
+ * batadv_orig_hardif_seq_print_text - writes originator infos for a specific
+ *  outgoing interface
+ * @seq: debugfs table seq_file struct
+ * @offset: not used
+ *
+ * Returns 0
+ */
+int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
+{
+	struct net_device *net_dev = (struct net_device *)seq->private;
+	struct batadv_hard_iface *hard_iface;
+	struct batadv_priv *bat_priv;
+
+	hard_iface = batadv_hardif_get_by_netdev(net_dev);
+
+	if (!hard_iface || !hard_iface->soft_iface) {
+		seq_puts(seq, "Interface not known to B.A.T.M.A.N.\n");
+		goto out;
+	}
+
+	bat_priv = netdev_priv(hard_iface->soft_iface);
+	if (!bat_priv->bat_algo_ops->bat_orig_print) {
+		seq_puts(seq,
+			 "No printing function for this routing protocol\n");
+		goto out;
+	}
+
+	if (hard_iface->if_status != BATADV_IF_ACTIVE) {
+		seq_puts(seq, "Interface not active\n");
+		goto out;
+	}
+
+	seq_printf(seq, "[B.A.T.M.A.N. adv %s, IF/MAC: %s/%pM (%s %s)]\n",
+		   BATADV_SOURCE_VERSION, hard_iface->net_dev->name,
+		   hard_iface->net_dev->dev_addr,
+		   hard_iface->soft_iface->name, bat_priv->bat_algo_ops->name);
+
+	bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface);
+
+out:
+	if (hard_iface)
+		batadv_hardif_free_ref(hard_iface);
+	return 0;
+}
+
 int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface,
 			    int max_if_num)
 {
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index 6f77d808a91..db3a9ed734c 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_ORIGINATOR_H_
@@ -31,13 +29,35 @@ void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node);
 struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 					      const uint8_t *addr);
 struct batadv_neigh_node *
+batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
+		      const struct batadv_hard_iface *hard_iface,
+		      const uint8_t *addr);
+struct batadv_neigh_node *
 batadv_neigh_node_new(struct batadv_hard_iface *hard_iface,
 		      const uint8_t *neigh_addr,
 		      struct batadv_orig_node *orig_node);
 void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node);
 struct batadv_neigh_node *
-batadv_orig_node_get_router(struct batadv_orig_node *orig_node);
+batadv_orig_router_get(struct batadv_orig_node *orig_node,
+		       const struct batadv_hard_iface *if_outgoing);
+struct batadv_neigh_ifinfo *
+batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh,
+			struct batadv_hard_iface *if_outgoing);
+struct batadv_neigh_ifinfo *
+batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh,
+			struct batadv_hard_iface *if_outgoing);
+void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo);
+
+struct batadv_orig_ifinfo *
+batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node,
+		       struct batadv_hard_iface *if_outgoing);
+struct batadv_orig_ifinfo *
+batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node,
+		       struct batadv_hard_iface *if_outgoing);
+void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo);
+
 int batadv_orig_seq_print_text(struct seq_file *seq, void *offset);
+int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset);
 int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface,
 			    int max_if_num);
 int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface,
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 207459b6296..34e096d2dce 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_PACKET_H_
@@ -91,6 +89,19 @@ enum batadv_icmp_packettype {
 	BATADV_PARAMETER_PROBLEM       = 12,
 };
 
+/**
+ * enum batadv_mcast_flags - flags for multicast capabilities and settings
+ * @BATADV_MCAST_WANT_ALL_UNSNOOPABLES: we want all packets destined for
+ *  224.0.0.0/24 or ff02::1
+ * @BATADV_MCAST_WANT_ALL_IPV4: we want all IPv4 multicast packets
+ * @BATADV_MCAST_WANT_ALL_IPV6: we want all IPv6 multicast packets
+ */
+enum batadv_mcast_flags {
+	BATADV_MCAST_WANT_ALL_UNSNOOPABLES	= BIT(0),
+	BATADV_MCAST_WANT_ALL_IPV4		= BIT(1),
+	BATADV_MCAST_WANT_ALL_IPV6		= BIT(2),
+};
+
 /* tt data subtypes */
 #define BATADV_TT_DATA_TYPE_MASK 0x0F
 
@@ -108,15 +119,36 @@ enum batadv_tt_data_flags {
 	BATADV_TT_FULL_TABLE = BIT(4),
 };
 
-/* BATADV_TT_CLIENT flags.
- * Flags from BIT(0) to BIT(7) are sent on the wire, while flags from BIT(8) to
- * BIT(15) are used for local computation only.
- * Flags from BIT(4) to BIT(7) are kept in sync with the rest of the network.
+/**
+ * enum batadv_tt_client_flags - TT client specific flags
+ * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table
+ * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and the new
+ *  update telling its new real location has not been received/sent yet
+ * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi interface.
+ *  This information is used by the "AP Isolation" feature
+ * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This
+ *  information is used by the Extended Isolation feature
+ * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from the table
+ * @BATADV_TT_CLIENT_NEW: this client has been added to the local table but has
+ *  not been announced yet
+ * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it is kept
+ *  in the table for one more originator interval for consistency purposes
+ * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be part of
+ *  the network but no nnode has already announced it
+ *
+ * Bits from 0 to 7 are called _remote flags_ because they are sent on the wire.
+ * Bits from 8 to 15 are called _local flags_ because they are used for local
+ * computations only.
+ *
+ * Bits from 4 to 7 - a subset of remote flags - are ensured to be in sync with
+ * the other nodes in the network. To achieve this goal these flags are included
+ * in the TT CRC computation.
  */
 enum batadv_tt_client_flags {
 	BATADV_TT_CLIENT_DEL     = BIT(0),
 	BATADV_TT_CLIENT_ROAM    = BIT(1),
 	BATADV_TT_CLIENT_WIFI    = BIT(4),
+	BATADV_TT_CLIENT_ISOLA	 = BIT(5),
 	BATADV_TT_CLIENT_NOPURGE = BIT(8),
 	BATADV_TT_CLIENT_NEW     = BIT(9),
 	BATADV_TT_CLIENT_PENDING = BIT(10),
@@ -146,6 +178,7 @@ enum batadv_bla_claimframe {
  * @BATADV_TVLV_NC: network coding tvlv
  * @BATADV_TVLV_TT: translation table tvlv
  * @BATADV_TVLV_ROAM: roaming advertisement tvlv
+ * @BATADV_TVLV_MCAST: multicast capability tvlv
  */
 enum batadv_tvlv_type {
 	BATADV_TVLV_GW		= 0x01,
@@ -153,8 +186,10 @@ enum batadv_tvlv_type {
 	BATADV_TVLV_NC		= 0x03,
 	BATADV_TVLV_TT		= 0x04,
 	BATADV_TVLV_ROAM	= 0x05,
+	BATADV_TVLV_MCAST	= 0x06,
 };
 
+#pragma pack(2)
 /* the destination hardware field in the ARP frame is used to
  * transport the claim type and the group id
  */
@@ -163,24 +198,20 @@ struct batadv_bla_claim_dst {
 	uint8_t type;		/* bla_claimframe */
 	__be16 group;		/* group id */
 };
-
-struct batadv_header {
-	uint8_t  packet_type;
-	uint8_t  version;  /* batman version field */
-	uint8_t  ttl;
-	/* the parent struct has to add a byte after the header to make
-	 * everything 4 bytes aligned again
-	 */
-};
+#pragma pack()
 
 /**
  * struct batadv_ogm_packet - ogm (routing protocol) packet
- * @header: common batman packet header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
  * @flags: contains routing relevant flags - see enum batadv_iv_flags
  * @tvlv_len: length of tvlv data following the ogm header
  */
 struct batadv_ogm_packet {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;
+	uint8_t  ttl;
 	uint8_t  flags;
 	__be32   seqno;
 	uint8_t  orig[ETH_ALEN];
@@ -196,29 +227,51 @@ struct batadv_ogm_packet {
 #define BATADV_OGM_HLEN sizeof(struct batadv_ogm_packet)
 
 /**
- * batadv_icmp_header - common ICMP header
- * @header: common batman header
+ * batadv_icmp_header - common members among all the ICMP packets
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
  * @msg_type: ICMP packet type
  * @dst: address of the destination node
  * @orig: address of the source node
  * @uid: local ICMP socket identifier
+ * @align: not used - useful for alignment purposes only
+ *
+ * This structure is used for ICMP packets parsing only and it is never sent
+ * over the wire. The alignment field at the end is there to ensure that
+ * members are padded the same way as they are in real packets.
  */
 struct batadv_icmp_header {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;
+	uint8_t  ttl;
 	uint8_t  msg_type; /* see ICMP message types above */
 	uint8_t  dst[ETH_ALEN];
 	uint8_t  orig[ETH_ALEN];
 	uint8_t  uid;
+	uint8_t  align[3];
 };
 
 /**
  * batadv_icmp_packet - ICMP packet
- * @icmph: common ICMP header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @msg_type: ICMP packet type
+ * @dst: address of the destination node
+ * @orig: address of the source node
+ * @uid: local ICMP socket identifier
  * @reserved: not used - useful for alignment
  * @seqno: ICMP sequence number
  */
 struct batadv_icmp_packet {
-	struct batadv_icmp_header icmph;
+	uint8_t  packet_type;
+	uint8_t  version;
+	uint8_t  ttl;
+	uint8_t  msg_type; /* see ICMP message types above */
+	uint8_t  dst[ETH_ALEN];
+	uint8_t  orig[ETH_ALEN];
+	uint8_t  uid;
 	uint8_t  reserved;
 	__be16   seqno;
 };
@@ -227,13 +280,25 @@ struct batadv_icmp_packet {
 
 /**
  * batadv_icmp_packet_rr - ICMP RouteRecord packet
- * @icmph: common ICMP header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @msg_type: ICMP packet type
+ * @dst: address of the destination node
+ * @orig: address of the source node
+ * @uid: local ICMP socket identifier
  * @rr_cur: number of entries the rr array
  * @seqno: ICMP sequence number
  * @rr: route record array
  */
 struct batadv_icmp_packet_rr {
-	struct batadv_icmp_header icmph;
+	uint8_t  packet_type;
+	uint8_t  version;
+	uint8_t  ttl;
+	uint8_t  msg_type; /* see ICMP message types above */
+	uint8_t  dst[ETH_ALEN];
+	uint8_t  orig[ETH_ALEN];
+	uint8_t  uid;
 	uint8_t  rr_cur;
 	__be16   seqno;
 	uint8_t  rr[BATADV_RR_LEN][ETH_ALEN];
@@ -253,8 +318,18 @@ struct batadv_icmp_packet_rr {
  */
 #pragma pack(2)
 
+/**
+ * struct batadv_unicast_packet - unicast packet for network payload
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @ttvn: translation table version number
+ * @dest: originator destination of the unicast packet
+ */
 struct batadv_unicast_packet {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;
+	uint8_t  ttl;
 	uint8_t  ttvn; /* destination translation table version number */
 	uint8_t  dest[ETH_ALEN];
 	/* "4 bytes boundary + 2 bytes" long to make the payload after the
@@ -280,7 +355,9 @@ struct batadv_unicast_4addr_packet {
 
 /**
  * struct batadv_frag_packet - fragmented packet
- * @header: common batman packet header with type, compatversion, and ttl
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
  * @dest: final destination used when routing fragments
  * @orig: originator of the fragment used when merging the packet
  * @no: fragment number within this sequence
@@ -289,7 +366,9 @@ struct batadv_unicast_4addr_packet {
  * @total_size: size of the merged packet
  */
 struct batadv_frag_packet {
-	struct  batadv_header header;
+	uint8_t packet_type;
+	uint8_t version;  /* batman version field */
+	uint8_t ttl;
 #if defined(__BIG_ENDIAN_BITFIELD)
 	uint8_t no:4;
 	uint8_t reserved:4;
@@ -305,8 +384,19 @@ struct batadv_frag_packet {
 	__be16  total_size;
 };
 
+/**
+ * struct batadv_bcast_packet - broadcast packet for network payload
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @reserved: reserved byte for alignment
+ * @seqno: sequence identification
+ * @orig: originator of the broadcast packet
+ */
 struct batadv_bcast_packet {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;  /* batman version field */
+	uint8_t  ttl;
 	uint8_t  reserved;
 	__be32   seqno;
 	uint8_t  orig[ETH_ALEN];
@@ -315,11 +405,11 @@ struct batadv_bcast_packet {
 	 */
 };
 
-#pragma pack()
-
 /**
  * struct batadv_coded_packet - network coded packet
- * @header: common batman packet header and ttl of first included packet
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
  * @reserved: Align following fields to 2-byte boundaries
  * @first_source: original source of first included packet
  * @first_orig_dest: original destinal of first included packet
@@ -334,7 +424,9 @@ struct batadv_bcast_packet {
  * @coded_len: length of network coded part of the payload
  */
 struct batadv_coded_packet {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;  /* batman version field */
+	uint8_t  ttl;
 	uint8_t  first_ttvn;
 	/* uint8_t  first_dest[ETH_ALEN]; - saved in mac header destination */
 	uint8_t  first_source[ETH_ALEN];
@@ -349,9 +441,13 @@ struct batadv_coded_packet {
 	__be16   coded_len;
 };
 
+#pragma pack()
+
 /**
  * struct batadv_unicast_tvlv - generic unicast packet with tvlv payload
- * @header: common batman packet header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
  * @reserved: reserved field (for packet alignment)
  * @src: address of the source
  * @dst: address of the destination
@@ -359,7 +455,9 @@ struct batadv_coded_packet {
  * @align: 2 bytes to align the header to a 4 byte boundry
  */
 struct batadv_unicast_tvlv_packet {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;  /* batman version field */
+	uint8_t  ttl;
 	uint8_t  reserved;
 	uint8_t  dst[ETH_ALEN];
 	uint8_t  src[ETH_ALEN];
@@ -420,13 +518,13 @@ struct batadv_tvlv_tt_vlan_data {
  * struct batadv_tvlv_tt_change - translation table diff data
  * @flags: status indicators concerning the non-mesh client (see
  *  batadv_tt_client_flags)
- * @reserved: reserved field
+ * @reserved: reserved field - useful for alignment purposes only
  * @addr: mac address of non-mesh client that triggered this tt change
  * @vid: VLAN identifier
  */
 struct batadv_tvlv_tt_change {
 	uint8_t flags;
-	uint8_t reserved;
+	uint8_t reserved[3];
 	uint8_t addr[ETH_ALEN];
 	__be16 vid;
 };
@@ -441,4 +539,14 @@ struct batadv_tvlv_roam_adv {
 	__be16 vid;
 };
 
+/**
+ * struct batadv_tvlv_mcast_data - payload of a multicast tvlv
+ * @flags: multicast flags announced by the orig node
+ * @reserved: reserved field
+ */
+struct batadv_tvlv_mcast_data {
+	uint8_t	flags;
+	uint8_t reserved[3];
+};
+
 #endif /* _NET_BATMAN_ADV_PACKET_H_ */
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index d4114d775ad..35141534938 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -35,13 +33,32 @@
 static int batadv_route_unicast_packet(struct sk_buff *skb,
 				       struct batadv_hard_iface *recv_if);
 
+/**
+ * _batadv_update_route - set the router for this originator
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: orig node which is to be configured
+ * @recv_if: the receive interface for which this route is set
+ * @neigh_node: neighbor which should be the next router
+ *
+ * This function does not perform any error checks
+ */
 static void _batadv_update_route(struct batadv_priv *bat_priv,
 				 struct batadv_orig_node *orig_node,
+				 struct batadv_hard_iface *recv_if,
 				 struct batadv_neigh_node *neigh_node)
 {
+	struct batadv_orig_ifinfo *orig_ifinfo;
 	struct batadv_neigh_node *curr_router;
 
-	curr_router = batadv_orig_node_get_router(orig_node);
+	orig_ifinfo = batadv_orig_ifinfo_get(orig_node, recv_if);
+	if (!orig_ifinfo)
+		return;
+
+	rcu_read_lock();
+	curr_router = rcu_dereference(orig_ifinfo->router);
+	if (curr_router && !atomic_inc_not_zero(&curr_router->refcount))
+		curr_router = NULL;
+	rcu_read_unlock();
 
 	/* route deleted */
 	if ((curr_router) && (!neigh_node)) {
@@ -71,16 +88,25 @@ static void _batadv_update_route(struct batadv_priv *bat_priv,
 		neigh_node = NULL;
 
 	spin_lock_bh(&orig_node->neigh_list_lock);
-	rcu_assign_pointer(orig_node->router, neigh_node);
+	rcu_assign_pointer(orig_ifinfo->router, neigh_node);
 	spin_unlock_bh(&orig_node->neigh_list_lock);
+	batadv_orig_ifinfo_free_ref(orig_ifinfo);
 
 	/* decrease refcount of previous best neighbor */
 	if (curr_router)
 		batadv_neigh_node_free_ref(curr_router);
 }
 
+/**
+ * batadv_update_route - set the router for this originator
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: orig node which is to be configured
+ * @recv_if: the receive interface for which this route is set
+ * @neigh_node: neighbor which should be the next router
+ */
 void batadv_update_route(struct batadv_priv *bat_priv,
 			 struct batadv_orig_node *orig_node,
+			 struct batadv_hard_iface *recv_if,
 			 struct batadv_neigh_node *neigh_node)
 {
 	struct batadv_neigh_node *router = NULL;
@@ -88,125 +114,16 @@ void batadv_update_route(struct batadv_priv *bat_priv,
 	if (!orig_node)
 		goto out;
 
-	router = batadv_orig_node_get_router(orig_node);
+	router = batadv_orig_router_get(orig_node, recv_if);
 
 	if (router != neigh_node)
-		_batadv_update_route(bat_priv, orig_node, neigh_node);
-
-out:
-	if (router)
-		batadv_neigh_node_free_ref(router);
-}
-
-/* caller must hold the neigh_list_lock */
-void batadv_bonding_candidate_del(struct batadv_orig_node *orig_node,
-				  struct batadv_neigh_node *neigh_node)
-{
-	/* this neighbor is not part of our candidate list */
-	if (list_empty(&neigh_node->bonding_list))
-		goto out;
-
-	list_del_rcu(&neigh_node->bonding_list);
-	INIT_LIST_HEAD(&neigh_node->bonding_list);
-	batadv_neigh_node_free_ref(neigh_node);
-	atomic_dec(&orig_node->bond_candidates);
-
-out:
-	return;
-}
-
-/**
- * batadv_bonding_candidate_add - consider a new link for bonding mode towards
- *  the given originator
- * @bat_priv: the bat priv with all the soft interface information
- * @orig_node: the target node
- * @neigh_node: the neighbor representing the new link to consider for bonding
- *  mode
- */
-void batadv_bonding_candidate_add(struct batadv_priv *bat_priv,
-				  struct batadv_orig_node *orig_node,
-				  struct batadv_neigh_node *neigh_node)
-{
-	struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
-	struct batadv_neigh_node *tmp_neigh_node, *router = NULL;
-	uint8_t interference_candidate = 0;
-
-	spin_lock_bh(&orig_node->neigh_list_lock);
-
-	/* only consider if it has the same primary address ...  */
-	if (!batadv_compare_eth(orig_node->orig,
-				neigh_node->orig_node->primary_addr))
-		goto candidate_del;
-
-	router = batadv_orig_node_get_router(orig_node);
-	if (!router)
-		goto candidate_del;
-
-
-	/* ... and is good enough to be considered */
-	if (bao->bat_neigh_is_equiv_or_better(neigh_node, router))
-		goto candidate_del;
-
-	/* check if we have another candidate with the same mac address or
-	 * interface. If we do, we won't select this candidate because of
-	 * possible interference.
-	 */
-	hlist_for_each_entry_rcu(tmp_neigh_node,
-				 &orig_node->neigh_list, list) {
-		if (tmp_neigh_node == neigh_node)
-			continue;
-
-		/* we only care if the other candidate is even
-		 * considered as candidate.
-		 */
-		if (list_empty(&tmp_neigh_node->bonding_list))
-			continue;
-
-		if ((neigh_node->if_incoming == tmp_neigh_node->if_incoming) ||
-		    (batadv_compare_eth(neigh_node->addr,
-					tmp_neigh_node->addr))) {
-			interference_candidate = 1;
-			break;
-		}
-	}
-
-	/* don't care further if it is an interference candidate */
-	if (interference_candidate)
-		goto candidate_del;
-
-	/* this neighbor already is part of our candidate list */
-	if (!list_empty(&neigh_node->bonding_list))
-		goto out;
-
-	if (!atomic_inc_not_zero(&neigh_node->refcount))
-		goto out;
-
-	list_add_rcu(&neigh_node->bonding_list, &orig_node->bond_list);
-	atomic_inc(&orig_node->bond_candidates);
-	goto out;
-
-candidate_del:
-	batadv_bonding_candidate_del(orig_node, neigh_node);
+		_batadv_update_route(bat_priv, orig_node, recv_if, neigh_node);
 
 out:
-	spin_unlock_bh(&orig_node->neigh_list_lock);
-
 	if (router)
 		batadv_neigh_node_free_ref(router);
 }
 
-/* copy primary address for bonding */
-void
-batadv_bonding_save_primary(const struct batadv_orig_node *orig_node,
-			    struct batadv_orig_node *orig_neigh_node,
-			    const struct batadv_ogm_packet *batman_ogm_packet)
-{
-	if (!(batman_ogm_packet->flags & BATADV_PRIMARIES_FIRST_HOP))
-		return;
-
-	memcpy(orig_neigh_node->primary_addr, orig_node->orig, ETH_ALEN);
-}
-
 /* checks whether the host restarted and is in the protection time.
  * returns:
  *  0 if the packet is to be accepted
@@ -305,10 +222,10 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv,
 
 		icmph = (struct batadv_icmp_header *)skb->data;
 
-		memcpy(icmph->dst, icmph->orig, ETH_ALEN);
-		memcpy(icmph->orig, primary_if->net_dev->dev_addr, ETH_ALEN);
+		ether_addr_copy(icmph->dst, icmph->orig);
+		ether_addr_copy(icmph->orig, primary_if->net_dev->dev_addr);
 		icmph->msg_type = BATADV_ECHO_REPLY;
-		icmph->header.ttl = BATADV_TTL;
+		icmph->ttl = BATADV_TTL;
 
 		res = batadv_send_skb_to_orig(skb, orig_node, NULL);
 		if (res != NET_XMIT_DROP)
@@ -338,9 +255,9 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
 	icmp_packet = (struct batadv_icmp_packet *)skb->data;
 
 	/* send TTL exceeded if packet is an echo request (traceroute) */
-	if (icmp_packet->icmph.msg_type != BATADV_ECHO_REQUEST) {
+	if (icmp_packet->msg_type != BATADV_ECHO_REQUEST) {
 		pr_debug("Warning - can't forward icmp packet from %pM to %pM: ttl exceeded\n",
-			 icmp_packet->icmph.orig, icmp_packet->icmph.dst);
+			 icmp_packet->orig, icmp_packet->dst);
 		goto out;
 	}
 
@@ -349,7 +266,7 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
 		goto out;
 
 	/* get routing information */
-	orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->icmph.orig);
+	orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->orig);
 	if (!orig_node)
 		goto out;
 
@@ -359,11 +276,10 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
 
 	icmp_packet = (struct batadv_icmp_packet *)skb->data;
 
-	memcpy(icmp_packet->icmph.dst, icmp_packet->icmph.orig, ETH_ALEN);
-	memcpy(icmp_packet->icmph.orig, primary_if->net_dev->dev_addr,
-	       ETH_ALEN);
-	icmp_packet->icmph.msg_type = BATADV_TTL_EXCEEDED;
-	icmp_packet->icmph.header.ttl = BATADV_TTL;
+	ether_addr_copy(icmp_packet->dst, icmp_packet->orig);
+	ether_addr_copy(icmp_packet->orig, primary_if->net_dev->dev_addr);
+	icmp_packet->msg_type = BATADV_TTL_EXCEEDED;
+	icmp_packet->ttl = BATADV_TTL;
 
 	if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
 		ret = NET_RX_SUCCESS;
@@ -424,8 +340,8 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
 		if (icmp_packet_rr->rr_cur >= BATADV_RR_LEN)
 			goto out;
 
-		memcpy(&(icmp_packet_rr->rr[icmp_packet_rr->rr_cur]),
-		       ethhdr->h_dest, ETH_ALEN);
+		ether_addr_copy(icmp_packet_rr->rr[icmp_packet_rr->rr_cur],
+				ethhdr->h_dest);
 		icmp_packet_rr->rr_cur++;
 	}
 
@@ -434,7 +350,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
 		return batadv_recv_my_icmp_packet(bat_priv, skb);
 
 	/* TTL exceeded */
-	if (icmph->header.ttl < 2)
+	if (icmph->ttl < 2)
 		return batadv_recv_icmp_ttl_exceeded(bat_priv, skb);
 
 	/* get routing information */
@@ -449,7 +365,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
 	icmph = (struct batadv_icmp_header *)skb->data;
 
 	/* decrement ttl */
-	icmph->header.ttl--;
+	icmph->ttl--;
 
 	/* route it */
 	if (batadv_send_skb_to_orig(skb, orig_node, recv_if) != NET_XMIT_DROP)
@@ -461,114 +377,6 @@ out:
 	return ret;
 }
 
-/* In the bonding case, send the packets in a round
- * robin fashion over the remaining interfaces.
- *
- * This method rotates the bonding list and increases the
- * returned router's refcount.
- */
-static struct batadv_neigh_node *
-batadv_find_bond_router(struct batadv_orig_node *primary_orig,
-			const struct batadv_hard_iface *recv_if)
-{
-	struct batadv_neigh_node *tmp_neigh_node;
-	struct batadv_neigh_node *router = NULL, *first_candidate = NULL;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list,
-				bonding_list) {
-		if (!first_candidate)
-			first_candidate = tmp_neigh_node;
-
-		/* recv_if == NULL on the first node. */
-		if (tmp_neigh_node->if_incoming == recv_if)
-			continue;
-
-		if (!atomic_inc_not_zero(&tmp_neigh_node->refcount))
-			continue;
-
-		router = tmp_neigh_node;
-		break;
-	}
-
-	/* use the first candidate if nothing was found. */
-	if (!router && first_candidate &&
-	    atomic_inc_not_zero(&first_candidate->refcount))
-		router = first_candidate;
-
-	if (!router)
-		goto out;
-
-	/* selected should point to the next element
-	 * after the current router
-	 */
-	spin_lock_bh(&primary_orig->neigh_list_lock);
-	/* this is a list_move(), which unfortunately
-	 * does not exist as rcu version
-	 */
-	list_del_rcu(&primary_orig->bond_list);
-	list_add_rcu(&primary_orig->bond_list,
-		     &router->bonding_list);
-	spin_unlock_bh(&primary_orig->neigh_list_lock);
-
-out:
-	rcu_read_unlock();
-	return router;
-}
-
-/**
- * batadv_find_ifalter_router - find the best of the remaining candidates which
- *  are not using this interface
- * @bat_priv: the bat priv with all the soft interface information
- * @primary_orig: the destination
- * @recv_if: the interface that the router returned by this function has to not
- *  use
- *
- * Returns the best candidate towards primary_orig that is not using recv_if.
- * Increases the returned neighbor's refcount
- */
-static struct batadv_neigh_node *
-batadv_find_ifalter_router(struct batadv_priv *bat_priv,
-			   struct batadv_orig_node *primary_orig,
-			   const struct batadv_hard_iface *recv_if)
-{
-	struct batadv_neigh_node *router = NULL, *first_candidate = NULL;
-	struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
-	struct batadv_neigh_node *tmp_neigh_node;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(tmp_neigh_node, &primary_orig->bond_list,
-				bonding_list) {
-		if (!first_candidate)
-			first_candidate = tmp_neigh_node;
-
-		/* recv_if == NULL on the first node. */
-		if (tmp_neigh_node->if_incoming == recv_if)
-			continue;
-
-		if (router && bao->bat_neigh_cmp(tmp_neigh_node, router))
-			continue;
-
-		if (!atomic_inc_not_zero(&tmp_neigh_node->refcount))
-			continue;
-
-		/* decrement refcount of previously selected router */
-		if (router)
-			batadv_neigh_node_free_ref(router);
-
-		/* we found a better router (or at least one valid router) */
-		router = tmp_neigh_node;
-	}
-
-	/* use the first candidate if nothing was found. */
-	if (!router && first_candidate &&
-	    atomic_inc_not_zero(&first_candidate->refcount))
-		router = first_candidate;
-
-	rcu_read_unlock();
-	return router;
-}
-
 /**
  * batadv_check_unicast_packet - Check for malformed unicast packets
  * @bat_priv: the bat priv with all the soft interface information
@@ -606,95 +414,141 @@ static int batadv_check_unicast_packet(struct batadv_priv *bat_priv,
 	return 0;
 }
 
-/* find a suitable router for this originator, and use
- * bonding if possible. increases the found neighbors
- * refcount.
+/**
+ * batadv_find_router - find a suitable router for this originator
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_node: the destination node
+ * @recv_if: pointer to interface this packet was received on
+ *
+ * Returns the router which should be used for this orig_node on
+ * this interface, or NULL if not available.
  */
 struct batadv_neigh_node *
 batadv_find_router(struct batadv_priv *bat_priv,
 		   struct batadv_orig_node *orig_node,
-		   const struct batadv_hard_iface *recv_if)
+		   struct batadv_hard_iface *recv_if)
 {
-	struct batadv_orig_node *primary_orig_node;
-	struct batadv_orig_node *router_orig;
-	struct batadv_neigh_node *router;
-	static uint8_t zero_mac[ETH_ALEN] = {0, 0, 0, 0, 0, 0};
-	int bonding_enabled;
-	uint8_t *primary_addr;
+	struct batadv_algo_ops *bao = bat_priv->bat_algo_ops;
+	struct batadv_neigh_node *first_candidate_router = NULL;
+	struct batadv_neigh_node *next_candidate_router = NULL;
+	struct batadv_neigh_node *router, *cand_router = NULL;
+	struct batadv_neigh_node *last_cand_router = NULL;
+	struct batadv_orig_ifinfo *cand, *first_candidate = NULL;
+	struct batadv_orig_ifinfo *next_candidate = NULL;
+	struct batadv_orig_ifinfo *last_candidate;
+	bool last_candidate_found = false;
 
 	if (!orig_node)
 		return NULL;
 
-	router = batadv_orig_node_get_router(orig_node);
-	if (!router)
-		goto err;
+	router = batadv_orig_router_get(orig_node, recv_if);
 
-	/* without bonding, the first node should
-	 * always choose the default router.
+	/* only consider bonding for recv_if == BATADV_IF_DEFAULT (first hop)
+	 * and if activated.
+	 */
+	if (recv_if == BATADV_IF_DEFAULT || !atomic_read(&bat_priv->bonding) ||
+	    !router)
+		return router;
+
+	/* bonding: loop through the list of possible routers found
+	 * for the various outgoing interfaces and find a candidate after
+	 * the last chosen bonding candidate (next_candidate). If no such
+	 * router is found, use the first candidate found (the previously
+	 * chosen bonding candidate might have been the last one in the list).
+	 * If this can't be found either, return the previously choosen
+	 * router - obviously there are no other candidates.
 	 */
-	bonding_enabled = atomic_read(&bat_priv->bonding);
-
 	rcu_read_lock();
-	/* select default router to output */
-	router_orig = router->orig_node;
-	if (!router_orig)
-		goto err_unlock;
+	last_candidate = orig_node->last_bonding_candidate;
+	if (last_candidate)
+		last_cand_router = rcu_dereference(last_candidate->router);
 
-	if ((!recv_if) && (!bonding_enabled))
-		goto return_router;
+	hlist_for_each_entry_rcu(cand, &orig_node->ifinfo_list, list) {
+		/* acquire some structures and references ... */
+		if (!atomic_inc_not_zero(&cand->refcount))
+			continue;
 
-	primary_addr = router_orig->primary_addr;
+		cand_router = rcu_dereference(cand->router);
+		if (!cand_router)
+			goto next;
 
-	/* if we have something in the primary_addr, we can search
-	 * for a potential bonding candidate.
-	 */
-	if (batadv_compare_eth(primary_addr, zero_mac))
-		goto return_router;
+		if (!atomic_inc_not_zero(&cand_router->refcount)) {
+			cand_router = NULL;
+			goto next;
+		}
 
-	/* find the orig_node which has the primary interface. might
-	 * even be the same as our router_orig in many cases
-	 */
-	if (batadv_compare_eth(primary_addr, router_orig->orig)) {
-		primary_orig_node = router_orig;
-	} else {
-		primary_orig_node = batadv_orig_hash_find(bat_priv,
-							  primary_addr);
-		if (!primary_orig_node)
-			goto return_router;
+		/* alternative candidate should be good enough to be
+		 * considered
+		 */
+		if (!bao->bat_neigh_is_equiv_or_better(cand_router,
+						       cand->if_outgoing,
+						       router, recv_if))
+			goto next;
+
+		/* don't use the same router twice */
+		if (last_cand_router == cand_router)
+			goto next;
+
+		/* mark the first possible candidate */
+		if (!first_candidate) {
+			atomic_inc(&cand_router->refcount);
+			atomic_inc(&cand->refcount);
+			first_candidate = cand;
+			first_candidate_router = cand_router;
+		}
+
+		/* check if the loop has already passed the previously selected
+		 * candidate ... this function should select the next candidate
+		 * AFTER the previously used bonding candidate.
+		 */
+		if (!last_candidate || last_candidate_found) {
+			next_candidate = cand;
+			next_candidate_router = cand_router;
+			break;
+		}
 
-		batadv_orig_node_free_ref(primary_orig_node);
+		if (last_candidate == cand)
+			last_candidate_found = true;
+next:
+		/* free references */
+		if (cand_router) {
+			batadv_neigh_node_free_ref(cand_router);
+			cand_router = NULL;
+		}
+		batadv_orig_ifinfo_free_ref(cand);
 	}
+	rcu_read_unlock();
 
-	/* with less than 2 candidates, we can't do any
-	 * bonding and prefer the original router.
-	 */
-	if (atomic_read(&primary_orig_node->bond_candidates) < 2)
-		goto return_router;
+	/* last_bonding_candidate is reset below, remove the old reference. */
+	if (orig_node->last_bonding_candidate)
+		batadv_orig_ifinfo_free_ref(orig_node->last_bonding_candidate);
 
-	/* all nodes between should choose a candidate which
-	 * is is not on the interface where the packet came
-	 * in.
+	/* After finding candidates, handle the three cases:
+	 * 1) there is a next candidate, use that
+	 * 2) there is no next candidate, use the first of the list
+	 * 3) there is no candidate at all, return the default router
 	 */
-	batadv_neigh_node_free_ref(router);
+	if (next_candidate) {
+		batadv_neigh_node_free_ref(router);
 
-	if (bonding_enabled)
-		router = batadv_find_bond_router(primary_orig_node, recv_if);
-	else
-		router = batadv_find_ifalter_router(bat_priv, primary_orig_node,
-						    recv_if);
+		/* remove references to first candidate, we don't need it. */
+		if (first_candidate) {
+			batadv_neigh_node_free_ref(first_candidate_router);
+			batadv_orig_ifinfo_free_ref(first_candidate);
+		}
+		router = next_candidate_router;
+		orig_node->last_bonding_candidate = next_candidate;
+	} else if (first_candidate) {
+		batadv_neigh_node_free_ref(router);
 
-return_router:
-	if (router && router->if_incoming->if_status != BATADV_IF_ACTIVE)
-		goto err_unlock;
+		/* refcounting has already been done in the loop above. */
+		router = first_candidate_router;
+		orig_node->last_bonding_candidate = first_candidate;
+	} else {
+		orig_node->last_bonding_candidate = NULL;
+	}
 
-	rcu_read_unlock();
 	return router;
-err_unlock:
-	rcu_read_unlock();
-err:
-	if (router)
-		batadv_neigh_node_free_ref(router);
-	return NULL;
 }
 
 static int batadv_route_unicast_packet(struct sk_buff *skb,
@@ -709,7 +563,7 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
 
 	/* TTL exceeded */
-	if (unicast_packet->header.ttl < 2) {
+	if (unicast_packet->ttl < 2) {
 		pr_debug("Warning - can't forward unicast packet from %pM to %pM: ttl exceeded\n",
 			 ethhdr->h_source, unicast_packet->dest);
 		goto out;
@@ -727,9 +581,9 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
 
 	/* decrement ttl */
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
-	unicast_packet->header.ttl--;
+	unicast_packet->ttl--;
 
-	switch (unicast_packet->header.packet_type) {
+	switch (unicast_packet->packet_type) {
 	case BATADV_UNICAST_4ADDR:
 		hdr_len = sizeof(struct batadv_unicast_4addr_packet);
 		break;
@@ -809,7 +663,7 @@ batadv_reroute_unicast_packet(struct batadv_priv *bat_priv,
 	}
 
 	/* update the packet header */
-	memcpy(unicast_packet->dest, orig_addr, ETH_ALEN);
+	ether_addr_copy(unicast_packet->dest, orig_addr);
 	unicast_packet->ttvn = orig_ttvn;
 
 	ret = true;
@@ -833,7 +687,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv,
 	int is_old_ttvn;
 
 	/* check if there is enough data before accessing it */
-	if (pskb_may_pull(skb, hdr_len + ETH_HLEN) < 0)
+	if (!pskb_may_pull(skb, hdr_len + ETH_HLEN))
 		return 0;
 
 	/* create a copy of the skb (in case of for re-routing) to modify it. */
@@ -919,7 +773,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv,
 	if (!primary_if)
 		return 0;
 
-	memcpy(unicast_packet->dest, primary_if->net_dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(unicast_packet->dest, primary_if->net_dev->dev_addr);
 
 	batadv_hardif_free_ref(primary_if);
 
@@ -970,7 +824,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
 	unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
 
-	is4addr = unicast_packet->header.packet_type == BATADV_UNICAST_4ADDR;
+	is4addr = unicast_packet->packet_type == BATADV_UNICAST_4ADDR;
 	/* the caller function should have already pulled 2 bytes */
 	if (is4addr)
 		hdr_size = sizeof(*unicast_4addr_packet);
@@ -1063,6 +917,8 @@ int batadv_recv_unicast_tvlv(struct sk_buff *skb,
 
 	if (ret != NET_RX_SUCCESS)
 		ret = batadv_route_unicast_packet(skb, recv_if);
+	else
+		consume_skb(skb);
 
 	return ret;
 }
@@ -1135,6 +991,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 	int hdr_size = sizeof(*bcast_packet);
 	int ret = NET_RX_DROP;
 	int32_t seq_diff;
+	uint32_t seqno;
 
 	/* drop packet if it has not necessary minimum size */
 	if (unlikely(!pskb_may_pull(skb, hdr_size)))
@@ -1160,7 +1017,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 	if (batadv_is_my_mac(bat_priv, bcast_packet->orig))
 		goto out;
 
-	if (bcast_packet->header.ttl < 2)
+	if (bcast_packet->ttl < 2)
 		goto out;
 
 	orig_node = batadv_orig_hash_find(bat_priv, bcast_packet->orig);
@@ -1170,12 +1027,13 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 
 	spin_lock_bh(&orig_node->bcast_seqno_lock);
 
+	seqno = ntohl(bcast_packet->seqno);
 	/* check whether the packet is a duplicate */
 	if (batadv_test_bit(orig_node->bcast_bits, orig_node->last_bcast_seqno,
-			    ntohl(bcast_packet->seqno)))
+			    seqno))
 		goto spin_unlock;
 
-	seq_diff = ntohl(bcast_packet->seqno) - orig_node->last_bcast_seqno;
+	seq_diff = seqno - orig_node->last_bcast_seqno;
 
 	/* check whether the packet is old and the host just restarted. */
 	if (batadv_window_protected(bat_priv, seq_diff,
@@ -1186,7 +1044,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 	 * if required.
 	 */
 	if (batadv_bit_get_packet(bat_priv, orig_node->bcast_bits, seq_diff, 1))
-		orig_node->last_bcast_seqno = ntohl(bcast_packet->seqno);
+		orig_node->last_bcast_seqno = seqno;
 
 	spin_unlock_bh(&orig_node->bcast_seqno_lock);
 
diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h
index 19544ddb81b..557d3d12a9a 100644
--- a/net/batman-adv/routing.h
+++ b/net/batman-adv/routing.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_ROUTING_H_
@@ -25,6 +23,7 @@ bool batadv_check_management_packet(struct sk_buff *skb,
 				    int header_len);
 void batadv_update_route(struct batadv_priv *bat_priv,
 			 struct batadv_orig_node *orig_node,
+			 struct batadv_hard_iface *recv_if,
 			 struct batadv_neigh_node *neigh_node);
 int batadv_recv_icmp_packet(struct sk_buff *skb,
 			    struct batadv_hard_iface *recv_if);
@@ -45,16 +44,7 @@ int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb,
 struct batadv_neigh_node *
 batadv_find_router(struct batadv_priv *bat_priv,
 		   struct batadv_orig_node *orig_node,
-		   const struct batadv_hard_iface *recv_if);
-void batadv_bonding_candidate_del(struct batadv_orig_node *orig_node,
-				  struct batadv_neigh_node *neigh_node);
-void batadv_bonding_candidate_add(struct batadv_priv *bat_priv,
-				  struct batadv_orig_node *orig_node,
-				  struct batadv_neigh_node *neigh_node);
-void batadv_bonding_save_primary(const struct batadv_orig_node *orig_node,
-				 struct batadv_orig_node *orig_neigh_node,
-				 const struct batadv_ogm_packet
-				 *batman_ogm_packet);
+		   struct batadv_hard_iface *recv_if);
 int batadv_window_protected(struct batadv_priv *bat_priv, int32_t seq_num_diff,
 			    unsigned long *last_reset);
 
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index c83be5ebaa2..3d64ed20c39 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -29,6 +27,7 @@
 #include "originator.h"
 #include "network-coding.h"
 #include "fragmentation.h"
+#include "multicast.h"
 
 static void batadv_send_outstanding_bcast_packet(struct work_struct *work);
 
@@ -61,8 +60,8 @@ int batadv_send_skb_packet(struct sk_buff *skb,
 	skb_reset_mac_header(skb);
 
 	ethhdr = eth_hdr(skb);
-	memcpy(ethhdr->h_source, hard_iface->net_dev->dev_addr, ETH_ALEN);
-	memcpy(ethhdr->h_dest, dst_addr, ETH_ALEN);
+	ether_addr_copy(ethhdr->h_source, hard_iface->net_dev->dev_addr);
+	ether_addr_copy(ethhdr->h_dest, dst_addr);
 	ethhdr->h_proto = htons(ETH_P_BATMAN);
 
 	skb_set_network_header(skb, ETH_HLEN);
@@ -161,13 +160,13 @@ batadv_send_skb_push_fill_unicast(struct sk_buff *skb, int hdr_size,
 		return false;
 
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
-	unicast_packet->header.version = BATADV_COMPAT_VERSION;
+	unicast_packet->version = BATADV_COMPAT_VERSION;
 	/* batman packet type: unicast */
-	unicast_packet->header.packet_type = BATADV_UNICAST;
+	unicast_packet->packet_type = BATADV_UNICAST;
 	/* set unicast ttl */
-	unicast_packet->header.ttl = BATADV_TTL;
+	unicast_packet->ttl = BATADV_TTL;
 	/* copy the destination for faster routing */
-	memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN);
+	ether_addr_copy(unicast_packet->dest, orig_node->orig);
 	/* set the destination tt version number */
 	unicast_packet->ttvn = ttvn;
 
@@ -221,8 +220,8 @@ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv,
 		goto out;
 
 	uc_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
-	uc_4addr_packet->u.header.packet_type = BATADV_UNICAST_4ADDR;
-	memcpy(uc_4addr_packet->src, primary_if->net_dev->dev_addr, ETH_ALEN);
+	uc_4addr_packet->u.packet_type = BATADV_UNICAST_4ADDR;
+	ether_addr_copy(uc_4addr_packet->src, primary_if->net_dev->dev_addr);
 	uc_4addr_packet->subtype = packet_subtype;
 	uc_4addr_packet->reserved = 0;
 
@@ -250,13 +249,13 @@ out:
  *
  * Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
  */
-static int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
-				   struct sk_buff *skb, int packet_type,
-				   int packet_subtype,
-				   struct batadv_orig_node *orig_node,
-				   unsigned short vid)
+int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
+			    struct sk_buff *skb, int packet_type,
+			    int packet_subtype,
+			    struct batadv_orig_node *orig_node,
+			    unsigned short vid)
 {
-	struct ethhdr *ethhdr = (struct ethhdr *)skb->data;
+	struct ethhdr *ethhdr;
 	struct batadv_unicast_packet *unicast_packet;
 	int ret = NET_XMIT_DROP;
 
@@ -281,6 +280,10 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
 		goto out;
 	}
 
+	/* skb->data might have been reallocated by
+	 * batadv_send_skb_prepare_unicast{,_4addr}()
+	 */
+	ethhdr = eth_hdr(skb);
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
 
 	/* inform the destination node that we are still missing a correct route
@@ -309,6 +312,7 @@ out:
  * @packet_type: the batman unicast packet type to use
  * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast
  *  4addr packets)
+ * @dst_hint: can be used to override the destination contained in the skb
  * @vid: the vid to be used to search the translation table
  *
  * Look up the recipient node for the destination address in the ethernet
@@ -321,13 +325,23 @@ out:
  */
 int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv,
 				   struct sk_buff *skb, int packet_type,
-				   int packet_subtype, unsigned short vid)
+				   int packet_subtype, uint8_t *dst_hint,
+				   unsigned short vid)
 {
 	struct ethhdr *ethhdr = (struct ethhdr *)skb->data;
 	struct batadv_orig_node *orig_node;
+	uint8_t *src, *dst;
+
+	src = ethhdr->h_source;
+	dst = ethhdr->h_dest;
+
+	/* if we got an hint! let's send the packet to this client (if any) */
+	if (dst_hint) {
+		src = NULL;
+		dst = dst_hint;
+	}
+	orig_node = batadv_transtable_search(bat_priv, src, dst, vid);
 
-	orig_node = batadv_transtable_search(bat_priv, ethhdr->h_source,
-					     ethhdr->h_dest, vid);
 	return batadv_send_skb_unicast(bat_priv, skb, packet_type,
 				       packet_subtype, orig_node, vid);
 }
@@ -379,6 +393,8 @@ static void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet)
 		kfree_skb(forw_packet->skb);
 	if (forw_packet->if_incoming)
 		batadv_hardif_free_ref(forw_packet->if_incoming);
+	if (forw_packet->if_outgoing)
+		batadv_hardif_free_ref(forw_packet->if_outgoing);
 	kfree(forw_packet);
 }
 
@@ -436,12 +452,13 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
 
 	/* as we have a copy now, it is safe to decrease the TTL */
 	bcast_packet = (struct batadv_bcast_packet *)newskb->data;
-	bcast_packet->header.ttl--;
+	bcast_packet->ttl--;
 
 	skb_reset_mac_header(newskb);
 
 	forw_packet->skb = newskb;
 	forw_packet->if_incoming = primary_if;
+	forw_packet->if_outgoing = NULL;
 
 	/* how often did we send the bcast packet ? */
 	forw_packet->num_packets = 0;
@@ -537,11 +554,16 @@ void batadv_send_outstanding_bat_ogm_packet(struct work_struct *work)
 
 	bat_priv->bat_algo_ops->bat_ogm_emit(forw_packet);
 
-	/* we have to have at least one packet in the queue
-	 * to determine the queues wake up time unless we are
-	 * shutting down
+	/* we have to have at least one packet in the queue to determine the
+	 * queues wake up time unless we are shutting down.
+	 *
+	 * only re-schedule if this is the "original" copy, e.g. the OGM of the
+	 * primary interface should only be rescheduled once per period, but
+	 * this function will be called for the forw_packet instances of the
+	 * other secondary interfaces as well.
 	 */
-	if (forw_packet->own)
+	if (forw_packet->own &&
+	    forw_packet->if_incoming == forw_packet->if_outgoing)
 		batadv_schedule_bat_ogm(forw_packet->if_incoming);
 
 out:
@@ -602,7 +624,8 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv,
 		 * we delete only packets belonging to the given interface
 		 */
 		if ((hard_iface) &&
-		    (forw_packet->if_incoming != hard_iface))
+		    (forw_packet->if_incoming != hard_iface) &&
+		    (forw_packet->if_outgoing != hard_iface))
 			continue;
 
 		spin_unlock_bh(&bat_priv->forw_bat_list_lock);
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index aa2e2537a73..38d0ec1833a 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_SEND_H_
@@ -38,9 +36,15 @@ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv,
 					   struct sk_buff *skb,
 					   struct batadv_orig_node *orig_node,
 					   int packet_subtype);
+int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
+			    struct sk_buff *skb, int packet_type,
+			    int packet_subtype,
+			    struct batadv_orig_node *orig_node,
+			    unsigned short vid);
 int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv,
 				   struct sk_buff *skb, int packet_type,
-				   int packet_subtype, unsigned short vid);
+				   int packet_subtype, uint8_t *dst_hint,
+				   unsigned short vid);
 int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb,
 			   unsigned short vid);
 
@@ -48,6 +52,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb,
  * batadv_send_skb_via_tt - send an skb via TT lookup
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: the payload to send
+ * @dst_hint: can be used to override the destination contained in the skb
  * @vid: the vid to be used to search the translation table
  *
  * Look up the recipient node for the destination address in the ethernet
@@ -57,11 +62,11 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb,
  * Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
  */
 static inline int batadv_send_skb_via_tt(struct batadv_priv *bat_priv,
-					 struct sk_buff *skb,
+					 struct sk_buff *skb, uint8_t *dst_hint,
 					 unsigned short vid)
 {
 	return batadv_send_skb_via_tt_generic(bat_priv, skb, BATADV_UNICAST, 0,
-					      vid);
+					      dst_hint, vid);
 }
 
 /**
@@ -69,6 +74,7 @@ static inline int batadv_send_skb_via_tt(struct batadv_priv *bat_priv,
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: the payload to send
  * @packet_subtype: the unicast 4addr packet subtype to use
+ * @dst_hint: can be used to override the destination contained in the skb
  * @vid: the vid to be used to search the translation table
  *
  * Look up the recipient node for the destination address in the ethernet
@@ -81,11 +87,12 @@ static inline int batadv_send_skb_via_tt(struct batadv_priv *bat_priv,
 static inline int batadv_send_skb_via_tt_4addr(struct batadv_priv *bat_priv,
 					       struct sk_buff *skb,
 					       int packet_subtype,
+					       uint8_t *dst_hint,
 					       unsigned short vid)
 {
 	return batadv_send_skb_via_tt_generic(bat_priv, skb,
 					      BATADV_UNICAST_4ADDR,
-					      packet_subtype, vid);
+					      packet_subtype, dst_hint, vid);
 }
 
 #endif /* _NET_BATMAN_ADV_SEND_H_ */
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 36f050876f8..cbd677f48c0 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -34,6 +32,7 @@
 #include <linux/ethtool.h>
 #include <linux/etherdevice.h>
 #include <linux/if_vlan.h>
+#include "multicast.h"
 #include "bridge_loop_avoidance.h"
 #include "network-coding.h"
 
@@ -113,15 +112,15 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	memcpy(old_addr, dev->dev_addr, ETH_ALEN);
-	memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
+	ether_addr_copy(old_addr, dev->dev_addr);
+	ether_addr_copy(dev->dev_addr, addr->sa_data);
 
 	/* only modify transtable if it has been initialized before */
 	if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE) {
 		batadv_tt_local_remove(bat_priv, old_addr, BATADV_NO_FLAGS,
 				       "mac address changed", false);
 		batadv_tt_local_add(dev, addr->sa_data, BATADV_NO_FLAGS,
-				    BATADV_NULL_IFINDEX);
+				    BATADV_NULL_IFINDEX, BATADV_NO_MARK);
 	}
 
 	return 0;
@@ -162,6 +161,8 @@ static int batadv_interface_tx(struct sk_buff *skb,
 						   0x00, 0x00};
 	static const uint8_t ectp_addr[ETH_ALEN] = {0xCF, 0x00, 0x00, 0x00,
 						    0x00, 0x00};
+	enum batadv_dhcp_recipient dhcp_rcp = BATADV_DHCP_NO;
+	uint8_t *dst_hint = NULL, chaddr[ETH_ALEN];
 	struct vlan_ethhdr *vhdr;
 	unsigned int header_len = 0;
 	int data_len = skb->len, ret;
@@ -169,17 +170,20 @@ static int batadv_interface_tx(struct sk_buff *skb,
 	bool do_bcast = false, client_added;
 	unsigned short vid;
 	uint32_t seqno;
+	int gw_mode;
+	enum batadv_forw_mode forw_mode;
+	struct batadv_orig_node *mcast_single_orig = NULL;
 
 	if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
 		goto dropped;
 
 	soft_iface->trans_start = jiffies;
 	vid = batadv_get_vid(skb, 0);
-	ethhdr = (struct ethhdr *)skb->data;
+	ethhdr = eth_hdr(skb);
 
 	switch (ntohs(ethhdr->h_proto)) {
 	case ETH_P_8021Q:
-		vhdr = (struct vlan_ethhdr *)skb->data;
+		vhdr = vlan_eth_hdr(skb);
 
 		if (vhdr->h_vlan_encapsulated_proto != ethertype)
 			break;
@@ -193,12 +197,13 @@ static int batadv_interface_tx(struct sk_buff *skb,
 		goto dropped;
 
 	/* skb->data might have been reallocated by batadv_bla_tx() */
-	ethhdr = (struct ethhdr *)skb->data;
+	ethhdr = eth_hdr(skb);
 
 	/* Register the client MAC in the transtable */
 	if (!is_multicast_ether_addr(ethhdr->h_source)) {
 		client_added = batadv_tt_local_add(soft_iface, ethhdr->h_source,
-						   vid, skb->skb_iif);
+						   vid, skb->skb_iif,
+						   skb->mark);
 		if (!client_added)
 			goto dropped;
 	}
@@ -215,34 +220,47 @@ static int batadv_interface_tx(struct sk_buff *skb,
 	if (batadv_compare_eth(ethhdr->h_dest, ectp_addr))
 		goto dropped;
 
+	gw_mode = atomic_read(&bat_priv->gw_mode);
 	if (is_multicast_ether_addr(ethhdr->h_dest)) {
-		do_bcast = true;
+		/* if gw mode is off, broadcast every packet */
+		if (gw_mode == BATADV_GW_MODE_OFF) {
+			do_bcast = true;
+			goto send;
+		}
 
-		switch (atomic_read(&bat_priv->gw_mode)) {
-		case BATADV_GW_MODE_SERVER:
-			/* gateway servers should not send dhcp
-			 * requests into the mesh
+		dhcp_rcp = batadv_gw_dhcp_recipient_get(skb, &header_len,
+							chaddr);
+		/* skb->data may have been modified by
+		 * batadv_gw_dhcp_recipient_get()
+		 */
+		ethhdr = eth_hdr(skb);
+		/* if gw_mode is on, broadcast any non-DHCP message.
+		 * All the DHCP packets are going to be sent as unicast
+		 */
+		if (dhcp_rcp == BATADV_DHCP_NO) {
+			do_bcast = true;
+			goto send;
+		}
+
+		if (dhcp_rcp == BATADV_DHCP_TO_CLIENT)
+			dst_hint = chaddr;
+		else if ((gw_mode == BATADV_GW_MODE_SERVER) &&
+			 (dhcp_rcp == BATADV_DHCP_TO_SERVER))
+			/* gateways should not forward any DHCP message if
+			 * directed to a DHCP server
 			 */
-			ret = batadv_gw_is_dhcp_target(skb, &header_len);
-			if (ret)
+			goto dropped;
+
+send:
+		if (do_bcast && !is_broadcast_ether_addr(ethhdr->h_dest)) {
+			forw_mode = batadv_mcast_forw_mode(bat_priv, skb,
+							   &mcast_single_orig);
+			if (forw_mode == BATADV_FORW_NONE)
 				goto dropped;
-			break;
-		case BATADV_GW_MODE_CLIENT:
-			/* gateway clients should send dhcp requests
-			 * via unicast to their gateway
-			 */
-			ret = batadv_gw_is_dhcp_target(skb, &header_len);
-			if (ret)
+
+			if (forw_mode == BATADV_FORW_SINGLE)
 				do_bcast = false;
-			break;
-		case BATADV_GW_MODE_OFF:
-		default:
-			break;
 		}
-
-		/* reminder: ethhdr might have become unusable from here on
-		 * (batadv_gw_is_dhcp_target() might have reallocated skb data)
-		 */
 	}
 
 	batadv_skb_set_priority(skb, 0);
@@ -264,18 +282,18 @@ static int batadv_interface_tx(struct sk_buff *skb,
 			goto dropped;
 
 		bcast_packet = (struct batadv_bcast_packet *)skb->data;
-		bcast_packet->header.version = BATADV_COMPAT_VERSION;
-		bcast_packet->header.ttl = BATADV_TTL;
+		bcast_packet->version = BATADV_COMPAT_VERSION;
+		bcast_packet->ttl = BATADV_TTL;
 
 		/* batman packet type: broadcast */
-		bcast_packet->header.packet_type = BATADV_BCAST;
+		bcast_packet->packet_type = BATADV_BCAST;
 		bcast_packet->reserved = 0;
 
 		/* hw address of first interface is the orig mac because only
 		 * this mac is known throughout the mesh
 		 */
-		memcpy(bcast_packet->orig,
-		       primary_if->net_dev->dev_addr, ETH_ALEN);
+		ether_addr_copy(bcast_packet->orig,
+				primary_if->net_dev->dev_addr);
 
 		/* set broadcast sequence number */
 		seqno = atomic_inc_return(&bat_priv->bcast_seqno);
@@ -290,22 +308,26 @@ static int batadv_interface_tx(struct sk_buff *skb,
 
 	/* unicast packet */
 	} else {
-		if (atomic_read(&bat_priv->gw_mode) != BATADV_GW_MODE_OFF) {
+		/* DHCP packets going to a server will use the GW feature */
+		if (dhcp_rcp == BATADV_DHCP_TO_SERVER) {
 			ret = batadv_gw_out_of_range(bat_priv, skb);
 			if (ret)
 				goto dropped;
-		}
-
-		if (batadv_dat_snoop_outgoing_arp_request(bat_priv, skb))
-			goto dropped;
-
-		batadv_dat_snoop_outgoing_arp_reply(bat_priv, skb);
-
-		if (is_multicast_ether_addr(ethhdr->h_dest))
 			ret = batadv_send_skb_via_gw(bat_priv, skb, vid);
-		else
-			ret = batadv_send_skb_via_tt(bat_priv, skb, vid);
+		} else if (mcast_single_orig) {
+			ret = batadv_send_skb_unicast(bat_priv, skb,
+						      BATADV_UNICAST, 0,
+						      mcast_single_orig, vid);
+		} else {
+			if (batadv_dat_snoop_outgoing_arp_request(bat_priv,
+								  skb))
+				goto dropped;
+
+			batadv_dat_snoop_outgoing_arp_reply(bat_priv, skb);
 
+			ret = batadv_send_skb_via_tt(bat_priv, skb, dst_hint,
+						     vid);
+		}
 		if (ret == NET_XMIT_DROP)
 			goto dropped_freed;
 	}
@@ -328,7 +350,7 @@ void batadv_interface_rx(struct net_device *soft_iface,
 			 struct sk_buff *skb, struct batadv_hard_iface *recv_if,
 			 int hdr_size, struct batadv_orig_node *orig_node)
 {
-	struct batadv_header *batadv_header = (struct batadv_header *)skb->data;
+	struct batadv_bcast_packet *batadv_bcast_packet;
 	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
 	__be16 ethertype = htons(ETH_P_BATMAN);
 	struct vlan_ethhdr *vhdr;
@@ -336,7 +358,8 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	unsigned short vid;
 	bool is_bcast;
 
-	is_bcast = (batadv_header->packet_type == BATADV_BCAST);
+	batadv_bcast_packet = (struct batadv_bcast_packet *)skb->data;
+	is_bcast = (batadv_bcast_packet->packet_type == BATADV_BCAST);
 
 	/* check if enough space is available for pulling, and pull */
 	if (!pskb_may_pull(skb, hdr_size))
@@ -345,7 +368,12 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	skb_pull_rcsum(skb, hdr_size);
 	skb_reset_mac_header(skb);
 
-	vid = batadv_get_vid(skb, hdr_size);
+	/* clean the netfilter state now that the batman-adv header has been
+	 * removed
+	 */
+	nf_reset(skb);
+
+	vid = batadv_get_vid(skb, 0);
 	ethhdr = eth_hdr(skb);
 
 	switch (ntohs(ethhdr->h_proto)) {
@@ -388,9 +416,23 @@ void batadv_interface_rx(struct net_device *soft_iface,
 		batadv_tt_add_temporary_global_entry(bat_priv, orig_node,
 						     ethhdr->h_source, vid);
 
-	if (batadv_is_ap_isolated(bat_priv, ethhdr->h_source, ethhdr->h_dest,
-				  vid))
+	if (is_multicast_ether_addr(ethhdr->h_dest)) {
+		/* set the mark on broadcast packets if AP isolation is ON and
+		 * the packet is coming from an "isolated" client
+		 */
+		if (batadv_vlan_ap_isola_get(bat_priv, vid) &&
+		    batadv_tt_global_is_isolated(bat_priv, ethhdr->h_source,
+						 vid)) {
+			/* save bits in skb->mark not covered by the mask and
+			 * apply the mark on the rest
+			 */
+			skb->mark &= ~bat_priv->isolation_mark_mask;
+			skb->mark |= bat_priv->isolation_mark;
+		}
+	} else if (batadv_is_ap_isolated(bat_priv, ethhdr->h_source,
+					 ethhdr->h_dest, vid)) {
 		goto dropped;
+	}
 
 	netif_rx(skb);
 	goto out;
@@ -406,10 +448,15 @@ out:
  *  possibly free it
  * @softif_vlan: the vlan object to release
  */
-void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *softif_vlan)
+void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *vlan)
 {
-	if (atomic_dec_and_test(&softif_vlan->refcount))
-		kfree_rcu(softif_vlan, rcu);
+	if (atomic_dec_and_test(&vlan->refcount)) {
+		spin_lock_bh(&vlan->bat_priv->softif_vlan_list_lock);
+		hlist_del_rcu(&vlan->list);
+		spin_unlock_bh(&vlan->bat_priv->softif_vlan_list_lock);
+
+		kfree_rcu(vlan, rcu);
+	}
 }
 
 /**
@@ -463,6 +510,7 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 	if (!vlan)
 		return -ENOMEM;
 
+	vlan->bat_priv = bat_priv;
 	vlan->vid = vid;
 	atomic_set(&vlan->refcount, 1);
 
@@ -474,16 +522,16 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 		return err;
 	}
 
+	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
+	hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list);
+	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
+
 	/* add a new TT local entry. This one will be marked with the NOPURGE
 	 * flag
 	 */
 	batadv_tt_local_add(bat_priv->soft_iface,
 			    bat_priv->soft_iface->dev_addr, vid,
-			    BATADV_NULL_IFINDEX);
-
-	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
-	hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list);
-	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
+			    BATADV_NULL_IFINDEX, BATADV_NO_MARK);
 
 	return 0;
 }
@@ -496,18 +544,13 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 static void batadv_softif_destroy_vlan(struct batadv_priv *bat_priv,
 				       struct batadv_softif_vlan *vlan)
 {
-	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
-	hlist_del_rcu(&vlan->list);
-	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
-
-	batadv_sysfs_del_vlan(bat_priv, vlan);
-
 	/* explicitly remove the associated TT local entry because it is marked
 	 * with the NOPURGE flag
 	 */
 	batadv_tt_local_remove(bat_priv, bat_priv->soft_iface->dev_addr,
 			       vlan->vid, "vlan interface destroyed", false);
 
+	batadv_sysfs_del_vlan(bat_priv, vlan);
 	batadv_softif_vlan_free_ref(vlan);
 }
 
@@ -525,6 +568,8 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto,
 				    unsigned short vid)
 {
 	struct batadv_priv *bat_priv = netdev_priv(dev);
+	struct batadv_softif_vlan *vlan;
+	int ret;
 
 	/* only 802.1Q vlans are supported.
 	 * batman-adv does not know how to handle other types
@@ -534,7 +579,36 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto,
 
 	vid |= BATADV_VLAN_HAS_TAG;
 
-	return batadv_softif_create_vlan(bat_priv, vid);
+	/* if a new vlan is getting created and it already exists, it means that
+	 * it was not deleted yet. batadv_softif_vlan_get() increases the
+	 * refcount in order to revive the object.
+	 *
+	 * if it does not exist then create it.
+	 */
+	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	if (!vlan)
+		return batadv_softif_create_vlan(bat_priv, vid);
+
+	/* recreate the sysfs object if it was already destroyed (and it should
+	 * be since we received a kill_vid() for this vlan
+	 */
+	if (!vlan->kobj) {
+		ret = batadv_sysfs_add_vlan(bat_priv->soft_iface, vlan);
+		if (ret) {
+			batadv_softif_vlan_free_ref(vlan);
+			return ret;
+		}
+	}
+
+	/* add a new TT local entry. This one will be marked with the NOPURGE
+	 * flag. This must be added again, even if the vlan object already
+	 * exists, because the entry was deleted by kill_vid()
+	 */
+	batadv_tt_local_add(bat_priv->soft_iface,
+			    bat_priv->soft_iface->dev_addr, vid,
+			    BATADV_NULL_IFINDEX, BATADV_NO_MARK);
+
+	return 0;
 }
 
 /**
@@ -627,10 +701,7 @@ static void batadv_softif_destroy_finish(struct work_struct *work)
 	}
 
 	batadv_sysfs_del_meshif(soft_iface);
-
-	rtnl_lock();
-	unregister_netdevice(soft_iface);
-	rtnl_unlock();
+	unregister_netdev(soft_iface);
 }
 
 /**
@@ -667,12 +738,20 @@ static int batadv_softif_init_late(struct net_device *dev)
 #ifdef CONFIG_BATMAN_ADV_DAT
 	atomic_set(&bat_priv->distributed_arp_table, 1);
 #endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	bat_priv->mcast.flags = BATADV_NO_FLAGS;
+	atomic_set(&bat_priv->multicast_mode, 1);
+	atomic_set(&bat_priv->mcast.num_disabled, 0);
+	atomic_set(&bat_priv->mcast.num_want_all_unsnoopables, 0);
+	atomic_set(&bat_priv->mcast.num_want_all_ipv4, 0);
+	atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0);
+#endif
 	atomic_set(&bat_priv->gw_mode, BATADV_GW_MODE_OFF);
 	atomic_set(&bat_priv->gw_sel_class, 20);
 	atomic_set(&bat_priv->gw.bandwidth_down, 100);
 	atomic_set(&bat_priv->gw.bandwidth_up, 20);
 	atomic_set(&bat_priv->orig_interval, 1000);
-	atomic_set(&bat_priv->hop_penalty, 30);
+	atomic_set(&bat_priv->hop_penalty, 15);
 #ifdef CONFIG_BATMAN_ADV_DEBUG
 	atomic_set(&bat_priv->log_level, 0);
 #endif
@@ -691,6 +770,8 @@ static int batadv_softif_init_late(struct net_device *dev)
 #endif
 	bat_priv->tt.last_changeset = NULL;
 	bat_priv->tt.last_changeset_len = 0;
+	bat_priv->isolation_mark = 0;
+	bat_priv->isolation_mark_mask = 0;
 
 	/* randomize initial seqno to avoid collision */
 	get_random_bytes(&random_seqno, sizeof(random_seqno));
@@ -835,7 +916,7 @@ static void batadv_softif_init_early(struct net_device *dev)
 	/* generate random address */
 	eth_hw_addr_random(dev);
 
-	SET_ETHTOOL_OPS(dev, &batadv_ethtool_ops);
+	dev->ethtool_ops = &batadv_ethtool_ops;
 
 	memset(priv, 0, sizeof(*priv));
 }
diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h
index 06fc91ff5a0..dbab22fd89a 100644
--- a/net/batman-adv/soft-interface.h
+++ b/net/batman-adv/soft-interface.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_SOFT_INTERFACE_H_
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 6335433310a..fc47baa888c 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -31,12 +29,14 @@
 static struct net_device *batadv_kobj_to_netdev(struct kobject *obj)
 {
 	struct device *dev = container_of(obj->parent, struct device, kobj);
+
 	return to_net_dev(dev);
 }
 
 static struct batadv_priv *batadv_kobj_to_batpriv(struct kobject *obj)
 {
 	struct net_device *net_dev = batadv_kobj_to_netdev(obj);
+
 	return netdev_priv(net_dev);
 }
 
@@ -108,7 +108,7 @@ struct batadv_attribute batadv_attr_vlan_##_name = {	\
 		 .mode = _mode },			\
 	.show   = _show,				\
 	.store  = _store,				\
-};
+}
 
 /* Use this, if you have customized show and store functions */
 #define BATADV_ATTR(_name, _mode, _show, _store)	\
@@ -117,7 +117,7 @@ struct batadv_attribute batadv_attr_##_name = {		\
 		 .mode = _mode },			\
 	.show   = _show,				\
 	.store  = _store,				\
-};
+}
 
 #define BATADV_ATTR_SIF_STORE_BOOL(_name, _post_func)			\
 ssize_t batadv_store_##_name(struct kobject *kobj,			\
@@ -126,6 +126,7 @@ ssize_t batadv_store_##_name(struct kobject *kobj,			\
 {									\
 	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);	\
 	struct batadv_priv *bat_priv = netdev_priv(net_dev);		\
+									\
 	return __batadv_store_bool_attr(buff, count, _post_func, attr,	\
 					&bat_priv->_name, net_dev);	\
 }
@@ -135,6 +136,7 @@ ssize_t batadv_show_##_name(struct kobject *kobj,			\
 			    struct attribute *attr, char *buff)		\
 {									\
 	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);	\
+									\
 	return sprintf(buff, "%s\n",					\
 		       atomic_read(&bat_priv->_name) == 0 ?		\
 		       "disabled" : "enabled");				\
@@ -157,6 +159,7 @@ ssize_t batadv_store_##_name(struct kobject *kobj,			\
 {									\
 	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);	\
 	struct batadv_priv *bat_priv = netdev_priv(net_dev);		\
+									\
 	return __batadv_store_uint_attr(buff, count, _min, _max,	\
 					_post_func, attr,		\
 					&bat_priv->_name, net_dev);	\
@@ -167,6 +170,7 @@ ssize_t batadv_show_##_name(struct kobject *kobj,			\
 			    struct attribute *attr, char *buff)		\
 {									\
 	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);	\
+									\
 	return sprintf(buff, "%i\n", atomic_read(&bat_priv->_name));	\
 }									\
 
@@ -190,6 +194,7 @@ ssize_t batadv_store_vlan_##_name(struct kobject *kobj,			\
 	size_t res = __batadv_store_bool_attr(buff, count, _post_func,	\
 					      attr, &vlan->_name,	\
 					      bat_priv->soft_iface);	\
+									\
 	batadv_softif_vlan_free_ref(vlan);				\
 	return res;							\
 }
@@ -204,6 +209,7 @@ ssize_t batadv_show_vlan_##_name(struct kobject *kobj,			\
 	size_t res = sprintf(buff, "%s\n",				\
 			     atomic_read(&vlan->_name) == 0 ?		\
 			     "disabled" : "enabled");			\
+									\
 	batadv_softif_vlan_free_ref(vlan);				\
 	return res;							\
 }
@@ -326,13 +332,15 @@ static ssize_t batadv_show_bat_algo(struct kobject *kobj,
 				    struct attribute *attr, char *buff)
 {
 	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
+
 	return sprintf(buff, "%s\n", bat_priv->bat_algo_ops->name);
 }
 
-static void batadv_post_gw_deselect(struct net_device *net_dev)
+static void batadv_post_gw_reselect(struct net_device *net_dev)
 {
 	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	batadv_gw_deselect(bat_priv);
+
+	batadv_gw_reselect(bat_priv);
 }
 
 static ssize_t batadv_show_gw_mode(struct kobject *kobj, struct attribute *attr,
@@ -408,7 +416,16 @@ static ssize_t batadv_store_gw_mode(struct kobject *kobj,
 	batadv_info(net_dev, "Changing gw mode from: %s to: %s\n",
 		    curr_gw_mode_str, buff);
 
-	batadv_gw_deselect(bat_priv);
+	/* Invoking batadv_gw_reselect() is not enough to really de-select the
+	 * current GW. It will only instruct the gateway client code to perform
+	 * a re-election the next time that this is needed.
+	 *
+	 * When gw client mode is being switched off the current GW must be
+	 * de-selected explicitly otherwise no GW_ADD uevent is thrown on
+	 * client mode re-activation. This is operation is performed in
+	 * batadv_gw_check_client_stop().
+	 */
+	batadv_gw_reselect(bat_priv);
 	/* always call batadv_gw_check_client_stop() before changing the gateway
 	 * state
 	 */
@@ -443,6 +460,74 @@ static ssize_t batadv_store_gw_bwidth(struct kobject *kobj,
 	return batadv_gw_bandwidth_set(net_dev, buff, count);
 }
 
+/**
+ * batadv_show_isolation_mark - print the current isolation mark/mask
+ * @kobj: kobject representing the private mesh sysfs directory
+ * @attr: the batman-adv attribute the user is interacting with
+ * @buff: the buffer that will contain the data to send back to the user
+ *
+ * Returns the number of bytes written into 'buff' on success or a negative
+ * error code in case of failure
+ */
+static ssize_t batadv_show_isolation_mark(struct kobject *kobj,
+					  struct attribute *attr, char *buff)
+{
+	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
+
+	return sprintf(buff, "%#.8x/%#.8x\n", bat_priv->isolation_mark,
+		       bat_priv->isolation_mark_mask);
+}
+
+/**
+ * batadv_store_isolation_mark - parse and store the isolation mark/mask entered
+ *  by the user
+ * @kobj: kobject representing the private mesh sysfs directory
+ * @attr: the batman-adv attribute the user is interacting with
+ * @buff: the buffer containing the user data
+ * @count: number of bytes in the buffer
+ *
+ * Returns 'count' on success or a negative error code in case of failure
+ */
+static ssize_t batadv_store_isolation_mark(struct kobject *kobj,
+					   struct attribute *attr, char *buff,
+					   size_t count)
+{
+	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
+	struct batadv_priv *bat_priv = netdev_priv(net_dev);
+	uint32_t mark, mask;
+	char *mask_ptr;
+
+	/* parse the mask if it has been specified, otherwise assume the mask is
+	 * the biggest possible
+	 */
+	mask = 0xFFFFFFFF;
+	mask_ptr = strchr(buff, '/');
+	if (mask_ptr) {
+		*mask_ptr = '\0';
+		mask_ptr++;
+
+		/* the mask must be entered in hex base as it is going to be a
+		 * bitmask and not a prefix length
+		 */
+		if (kstrtou32(mask_ptr, 16, &mask) < 0)
+			return -EINVAL;
+	}
+
+	/* the mark can be entered in any base */
+	if (kstrtou32(buff, 0, &mark) < 0)
+		return -EINVAL;
+
+	bat_priv->isolation_mark_mask = mask;
+	/* erase bits not covered by the mask */
+	bat_priv->isolation_mark = mark & bat_priv->isolation_mark_mask;
+
+	batadv_info(net_dev,
+		    "New skb mark for extended isolation: %#.8x/%#.8x\n",
+		    bat_priv->isolation_mark, bat_priv->isolation_mark_mask);
+
+	return count;
+}
+
 BATADV_ATTR_SIF_BOOL(aggregated_ogms, S_IRUGO | S_IWUSR, NULL);
 BATADV_ATTR_SIF_BOOL(bonding, S_IRUGO | S_IWUSR, NULL);
 #ifdef CONFIG_BATMAN_ADV_BLA
@@ -461,9 +546,12 @@ BATADV_ATTR_SIF_UINT(orig_interval, S_IRUGO | S_IWUSR, 2 * BATADV_JITTER,
 BATADV_ATTR_SIF_UINT(hop_penalty, S_IRUGO | S_IWUSR, 0, BATADV_TQ_MAX_VALUE,
 		     NULL);
 BATADV_ATTR_SIF_UINT(gw_sel_class, S_IRUGO | S_IWUSR, 1, BATADV_TQ_MAX_VALUE,
-		     batadv_post_gw_deselect);
+		     batadv_post_gw_reselect);
 static BATADV_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, batadv_show_gw_bwidth,
 		   batadv_store_gw_bwidth);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+BATADV_ATTR_SIF_BOOL(multicast_mode, S_IRUGO | S_IWUSR, NULL);
+#endif
 #ifdef CONFIG_BATMAN_ADV_DEBUG
 BATADV_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, BATADV_DBG_ALL, NULL);
 #endif
@@ -471,6 +559,8 @@ BATADV_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, BATADV_DBG_ALL, NULL);
 BATADV_ATTR_SIF_BOOL(network_coding, S_IRUGO | S_IWUSR,
 		     batadv_nc_status_update);
 #endif
+static BATADV_ATTR(isolation_mark, S_IRUGO | S_IWUSR,
+		   batadv_show_isolation_mark, batadv_store_isolation_mark);
 
 static struct batadv_attribute *batadv_mesh_attrs[] = {
 	&batadv_attr_aggregated_ogms,
@@ -481,6 +571,9 @@ static struct batadv_attribute *batadv_mesh_attrs[] = {
 #ifdef CONFIG_BATMAN_ADV_DAT
 	&batadv_attr_distributed_arp_table,
 #endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	&batadv_attr_multicast_mode,
+#endif
 	&batadv_attr_fragmentation,
 	&batadv_attr_routing_algo,
 	&batadv_attr_gw_mode,
@@ -494,6 +587,7 @@ static struct batadv_attribute *batadv_mesh_attrs[] = {
 #ifdef CONFIG_BATMAN_ADV_NC
 	&batadv_attr_network_coding,
 #endif
+	&batadv_attr_isolation_mark,
 	NULL,
 };
 
diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h
index c7d725de50a..b715b60db7c 100644
--- a/net/batman-adv/sysfs.h
+++ b/net/batman-adv/sysfs.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_SYSFS_H_
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 4add57d4857..5f59e7f899a 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich, Antonio Quartulli
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
@@ -26,6 +24,7 @@
 #include "originator.h"
 #include "routing.h"
 #include "bridge_loop_avoidance.h"
+#include "multicast.h"
 
 #include <linux/crc32c.h>
 
@@ -51,7 +50,7 @@ static int batadv_compare_tt(const struct hlist_node *node, const void *data2)
 	const void *data1 = container_of(node, struct batadv_tt_common_entry,
 					 hash_entry);
 
-	return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0);
+	return batadv_compare_eth(data1, data2);
 }
 
 /**
@@ -98,7 +97,7 @@ batadv_tt_hash_find(struct batadv_hashtable *hash, const uint8_t *addr,
 	if (!hash)
 		return NULL;
 
-	memcpy(to_search.addr, addr, ETH_ALEN);
+	ether_addr_copy(to_search.addr, addr);
 	to_search.vid = vid;
 
 	index = batadv_choose_tt(&to_search, hash->size);
@@ -194,6 +193,31 @@ batadv_tt_global_entry_free_ref(struct batadv_tt_global_entry *tt_global_entry)
 	}
 }
 
+/**
+ * batadv_tt_global_hash_count - count the number of orig entries
+ * @hash: hash table containing the tt entries
+ * @addr: the mac address of the client to count entries for
+ * @vid: VLAN identifier
+ *
+ * Return the number of originators advertising the given address/data
+ * (excluding ourself).
+ */
+int batadv_tt_global_hash_count(struct batadv_priv *bat_priv,
+				const uint8_t *addr, unsigned short vid)
+{
+	struct batadv_tt_global_entry *tt_global_entry;
+	int count;
+
+	tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr, vid);
+	if (!tt_global_entry)
+		return 0;
+
+	count = atomic_read(&tt_global_entry->orig_list_count);
+	batadv_tt_global_entry_free_ref(tt_global_entry);
+
+	return count;
+}
+
 static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu)
 {
 	struct batadv_tt_orig_list_entry *orig_entry;
@@ -333,8 +357,9 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv,
 		return;
 
 	tt_change_node->change.flags = flags;
-	tt_change_node->change.reserved = 0;
-	memcpy(tt_change_node->change.addr, common->addr, ETH_ALEN);
+	memset(tt_change_node->change.reserved, 0,
+	       sizeof(tt_change_node->change.reserved));
+	ether_addr_copy(tt_change_node->change.addr, common->addr);
 	tt_change_node->change.vid = htons(common->vid);
 
 	del_op_requested = flags & BATADV_TT_CLIENT_DEL;
@@ -475,27 +500,33 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv,
  * @vid: VLAN identifier
  * @ifindex: index of the interface where the client is connected to (useful to
  *  identify wireless clients)
+ * @mark: the value contained in the skb->mark field of the received packet (if
+ *  any)
  *
  * Returns true if the client was successfully added, false otherwise.
  */
 bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
-			 unsigned short vid, int ifindex)
+			 unsigned short vid, int ifindex, uint32_t mark)
 {
 	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
 	struct batadv_tt_local_entry *tt_local;
-	struct batadv_tt_global_entry *tt_global;
+	struct batadv_tt_global_entry *tt_global = NULL;
+	struct batadv_softif_vlan *vlan;
 	struct net_device *in_dev = NULL;
 	struct hlist_head *head;
 	struct batadv_tt_orig_list_entry *orig_entry;
 	int hash_added, table_size, packet_size_max;
 	bool ret = false, roamed_back = false;
 	uint8_t remote_flags;
+	uint32_t match_mark;
 
 	if (ifindex != BATADV_NULL_IFINDEX)
 		in_dev = dev_get_by_index(&init_net, ifindex);
 
 	tt_local = batadv_tt_local_hash_find(bat_priv, addr, vid);
-	tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid);
+
+	if (!is_multicast_ether_addr(addr))
+		tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid);
 
 	if (tt_local) {
 		tt_local->last_seen = jiffies;
@@ -542,12 +573,15 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
 	if (!tt_local)
 		goto out;
 
+	/* increase the refcounter of the related vlan */
+	vlan = batadv_softif_vlan_get(bat_priv, vid);
+
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Creating new local tt entry: %pM (vid: %d, ttvn: %d)\n",
 		   addr, BATADV_PRINT_VID(vid),
 		   (uint8_t)atomic_read(&bat_priv->tt.vn));
 
-	memcpy(tt_local->common.addr, addr, ETH_ALEN);
+	ether_addr_copy(tt_local->common.addr, addr);
 	/* The local entry has to be marked as NEW to avoid to send it in
 	 * a full table response going out before the next ttvn increment
 	 * (consistency check)
@@ -560,8 +594,11 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
 	tt_local->last_seen = jiffies;
 	tt_local->common.added_at = tt_local->last_seen;
 
-	/* the batman interface mac address should never be purged */
-	if (batadv_compare_eth(addr, soft_iface->dev_addr))
+	/* the batman interface mac and multicast addresses should never be
+	 * purged
+	 */
+	if (batadv_compare_eth(addr, soft_iface->dev_addr) ||
+	    is_multicast_ether_addr(addr))
 		tt_local->common.flags |= BATADV_TT_CLIENT_NOPURGE;
 
 	hash_added = batadv_hash_add(bat_priv->tt.local_hash, batadv_compare_tt,
@@ -571,6 +608,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
 	if (unlikely(hash_added != 0)) {
 		/* remove the reference for the hash */
 		batadv_tt_local_entry_free_ref(tt_local);
+		batadv_softif_vlan_free_ref(vlan);
 		goto out;
 	}
 
@@ -614,6 +652,17 @@ check_roaming:
 	else
 		tt_local->common.flags &= ~BATADV_TT_CLIENT_WIFI;
 
+	/* check the mark in the skb: if it's equal to the configured
+	 * isolation_mark, it means the packet is coming from an isolated
+	 * non-mesh client
+	 */
+	match_mark = (mark & bat_priv->isolation_mark_mask);
+	if (bat_priv->isolation_mark_mask &&
+	    match_mark == bat_priv->isolation_mark)
+		tt_local->common.flags |= BATADV_TT_CLIENT_ISOLA;
+	else
+		tt_local->common.flags &= ~BATADV_TT_CLIENT_ISOLA;
+
 	/* if any "dynamic" flag has been modified, resend an ADD event for this
 	 * entry so that all the nodes can get the new flags
 	 */
@@ -874,7 +923,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
 	seq_printf(seq,
 		   "Locally retrieved addresses (from %s) announced via TT (TTVN: %u):\n",
 		   net_dev->name, (uint8_t)atomic_read(&bat_priv->tt.vn));
-	seq_printf(seq, "       %-13s  %s %-7s %-9s (%-10s)\n", "Client", "VID",
+	seq_printf(seq, "       %-13s  %s %-8s %-9s (%-10s)\n", "Client", "VID",
 		   "Flags", "Last seen", "CRC");
 
 	for (i = 0; i < hash->size; i++) {
@@ -902,7 +951,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
 			}
 
 			seq_printf(seq,
-				   " * %pM %4i [%c%c%c%c%c] %3u.%03u   (%#.8x)\n",
+				   " * %pM %4i [%c%c%c%c%c%c] %3u.%03u   (%#.8x)\n",
 				   tt_common_entry->addr,
 				   BATADV_PRINT_VID(tt_common_entry->vid),
 				   (tt_common_entry->flags &
@@ -914,6 +963,8 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
 				    BATADV_TT_CLIENT_PENDING ? 'X' : '.'),
 				   (tt_common_entry->flags &
 				    BATADV_TT_CLIENT_WIFI ? 'W' : '.'),
+				   (tt_common_entry->flags &
+				    BATADV_TT_CLIENT_ISOLA ? 'I' : '.'),
 				   no_purge ? 0 : last_seen_secs,
 				   no_purge ? 0 : last_seen_msecs,
 				   vlan->tt.crc);
@@ -963,6 +1014,7 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv,
 {
 	struct batadv_tt_local_entry *tt_local_entry;
 	uint16_t flags, curr_flags = BATADV_NO_FLAGS;
+	struct batadv_softif_vlan *vlan;
 
 	tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid);
 	if (!tt_local_entry)
@@ -993,6 +1045,11 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv,
 	hlist_del_rcu(&tt_local_entry->common.hash_entry);
 	batadv_tt_local_entry_free_ref(tt_local_entry);
 
+	/* decrease the reference held for this vlan */
+	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	batadv_softif_vlan_free_ref(vlan);
+	batadv_softif_vlan_free_ref(vlan);
+
 out:
 	if (tt_local_entry)
 		batadv_tt_local_entry_free_ref(tt_local_entry);
@@ -1065,6 +1122,7 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv)
 	spinlock_t *list_lock; /* protects write access to the hash lists */
 	struct batadv_tt_common_entry *tt_common_entry;
 	struct batadv_tt_local_entry *tt_local;
+	struct batadv_softif_vlan *vlan;
 	struct hlist_node *node_tmp;
 	struct hlist_head *head;
 	uint32_t i;
@@ -1085,6 +1143,13 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv)
 			tt_local = container_of(tt_common_entry,
 						struct batadv_tt_local_entry,
 						common);
+
+			/* decrease the reference held for this vlan */
+			vlan = batadv_softif_vlan_get(bat_priv,
+						      tt_common_entry->vid);
+			batadv_softif_vlan_free_ref(vlan);
+			batadv_softif_vlan_free_ref(vlan);
+
 			batadv_tt_local_entry_free_ref(tt_local);
 		}
 		spin_unlock_bh(list_lock);
@@ -1204,6 +1269,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global,
 	hlist_add_head_rcu(&orig_entry->list,
 			   &tt_global->orig_list);
 	spin_unlock_bh(&tt_global->list_lock);
+	atomic_inc(&tt_global->orig_list_count);
+
 out:
 	if (orig_entry)
 		batadv_tt_orig_list_entry_free_ref(orig_entry);
@@ -1262,7 +1329,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
 			goto out;
 
 		common = &tt_global_entry->common;
-		memcpy(common->addr, tt_addr, ETH_ALEN);
+		ether_addr_copy(common->addr, tt_addr);
 		common->vid = vid;
 
 		common->flags = flags;
@@ -1277,6 +1344,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
 		common->added_at = jiffies;
 
 		INIT_HLIST_HEAD(&tt_global_entry->orig_list);
+		atomic_set(&tt_global_entry->orig_list_count, 0);
 		spin_lock_init(&tt_global_entry->list_lock);
 
 		hash_added = batadv_hash_add(bat_priv->tt.global_hash,
@@ -1346,6 +1414,11 @@ add_orig_entry:
 	ret = true;
 
 out_remove:
+	/* Do not remove multicast addresses from the local hash on
+	 * global additions
+	 */
+	if (is_multicast_ether_addr(tt_addr))
+		goto out;
 
 	/* remove address from local hash if present */
 	local_flags = batadv_tt_local_remove(bat_priv, tt_addr, vid,
@@ -1367,7 +1440,8 @@ out:
 	return ret;
 }
 
-/* batadv_transtable_best_orig - Get best originator list entry from tt entry
+/**
+ * batadv_transtable_best_orig - Get best originator list entry from tt entry
  * @bat_priv: the bat priv with all the soft interface information
  * @tt_global_entry: global translation table entry to be analyzed
  *
@@ -1385,12 +1459,14 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv,
 
 	head = &tt_global_entry->orig_list;
 	hlist_for_each_entry_rcu(orig_entry, head, list) {
-		router = batadv_orig_node_get_router(orig_entry->orig_node);
+		router = batadv_orig_router_get(orig_entry->orig_node,
+						BATADV_IF_DEFAULT);
 		if (!router)
 			continue;
 
 		if (best_router &&
-		    bao->bat_neigh_cmp(router, best_router) <= 0) {
+		    bao->bat_neigh_cmp(router, BATADV_IF_DEFAULT,
+				       best_router, BATADV_IF_DEFAULT) <= 0) {
 			batadv_neigh_node_free_ref(router);
 			continue;
 		}
@@ -1409,8 +1485,9 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv,
 	return best_entry;
 }
 
-/* batadv_tt_global_print_entry - print all orig nodes who announce the address
- * for this global entry
+/**
+ * batadv_tt_global_print_entry - print all orig nodes who announce the address
+ *  for this global entry
  * @bat_priv: the bat priv with all the soft interface information
  * @tt_global_entry: global translation table entry to be printed
  * @seq: debugfs table seq_file struct
@@ -1446,13 +1523,14 @@ batadv_tt_global_print_entry(struct batadv_priv *bat_priv,
 
 		last_ttvn = atomic_read(&best_entry->orig_node->last_ttvn);
 		seq_printf(seq,
-			   " %c %pM %4i   (%3u) via %pM     (%3u)   (%#.8x) [%c%c%c]\n",
+			   " %c %pM %4i   (%3u) via %pM     (%3u)   (%#.8x) [%c%c%c%c]\n",
 			   '*', tt_global_entry->common.addr,
 			   BATADV_PRINT_VID(tt_global_entry->common.vid),
 			   best_entry->ttvn, best_entry->orig_node->orig,
 			   last_ttvn, vlan->tt.crc,
 			   (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'),
 			   (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'),
+			   (flags & BATADV_TT_CLIENT_ISOLA ? 'I' : '.'),
 			   (flags & BATADV_TT_CLIENT_TEMP ? 'T' : '.'));
 
 		batadv_orig_node_vlan_free_ref(vlan);
@@ -1477,13 +1555,14 @@ print_list:
 
 		last_ttvn = atomic_read(&orig_entry->orig_node->last_ttvn);
 		seq_printf(seq,
-			   " %c %pM %4d   (%3u) via %pM     (%3u)   (%#.8x) [%c%c%c]\n",
+			   " %c %pM %4d   (%3u) via %pM     (%3u)   (%#.8x) [%c%c%c%c]\n",
 			   '+', tt_global_entry->common.addr,
 			   BATADV_PRINT_VID(tt_global_entry->common.vid),
 			   orig_entry->ttvn, orig_entry->orig_node->orig,
 			   last_ttvn, vlan->tt.crc,
 			   (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'),
 			   (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'),
+			   (flags & BATADV_TT_CLIENT_ISOLA ? 'I' : '.'),
 			   (flags & BATADV_TT_CLIENT_TEMP ? 'T' : '.'));
 
 		batadv_orig_node_vlan_free_ref(vlan);
@@ -1531,6 +1610,25 @@ out:
 	return 0;
 }
 
+/**
+ * batadv_tt_global_del_orig_entry - remove and free an orig_entry
+ * @tt_global_entry: the global entry to remove the orig_entry from
+ * @orig_entry: the orig entry to remove and free
+ *
+ * Remove an orig_entry from its list in the given tt_global_entry and
+ * free this orig_entry afterwards.
+ */
+static void
+batadv_tt_global_del_orig_entry(struct batadv_tt_global_entry *tt_global_entry,
+				struct batadv_tt_orig_list_entry *orig_entry)
+{
+	batadv_tt_global_size_dec(orig_entry->orig_node,
+				  tt_global_entry->common.vid);
+	atomic_dec(&tt_global_entry->orig_list_count);
+	hlist_del_rcu(&orig_entry->list);
+	batadv_tt_orig_list_entry_free_ref(orig_entry);
+}
+
 /* deletes the orig list of a tt_global_entry */
 static void
 batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry)
@@ -1541,20 +1639,26 @@ batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry)
 
 	spin_lock_bh(&tt_global_entry->list_lock);
 	head = &tt_global_entry->orig_list;
-	hlist_for_each_entry_safe(orig_entry, safe, head, list) {
-		hlist_del_rcu(&orig_entry->list);
-		batadv_tt_global_size_dec(orig_entry->orig_node,
-					  tt_global_entry->common.vid);
-		batadv_tt_orig_list_entry_free_ref(orig_entry);
-	}
+	hlist_for_each_entry_safe(orig_entry, safe, head, list)
+		batadv_tt_global_del_orig_entry(tt_global_entry, orig_entry);
 	spin_unlock_bh(&tt_global_entry->list_lock);
 }
 
+/**
+ * batadv_tt_global_del_orig_node - remove orig_node from a global tt entry
+ * @bat_priv: the bat priv with all the soft interface information
+ * @tt_global_entry: the global entry to remove the orig_node from
+ * @orig_node: the originator announcing the client
+ * @message: message to append to the log on deletion
+ *
+ * Remove the given orig_node and its according orig_entry from the given
+ * global tt entry.
+ */
 static void
-batadv_tt_global_del_orig_entry(struct batadv_priv *bat_priv,
-				struct batadv_tt_global_entry *tt_global_entry,
-				struct batadv_orig_node *orig_node,
-				const char *message)
+batadv_tt_global_del_orig_node(struct batadv_priv *bat_priv,
+			       struct batadv_tt_global_entry *tt_global_entry,
+			       struct batadv_orig_node *orig_node,
+			       const char *message)
 {
 	struct hlist_head *head;
 	struct hlist_node *safe;
@@ -1571,10 +1675,8 @@ batadv_tt_global_del_orig_entry(struct batadv_priv *bat_priv,
 				   orig_node->orig,
 				   tt_global_entry->common.addr,
 				   BATADV_PRINT_VID(vid), message);
-			hlist_del_rcu(&orig_entry->list);
-			batadv_tt_global_size_dec(orig_node,
-						  tt_global_entry->common.vid);
-			batadv_tt_orig_list_entry_free_ref(orig_entry);
+			batadv_tt_global_del_orig_entry(tt_global_entry,
+							orig_entry);
 		}
 	}
 	spin_unlock_bh(&tt_global_entry->list_lock);
@@ -1616,8 +1718,8 @@ batadv_tt_global_del_roaming(struct batadv_priv *bat_priv,
 		/* there is another entry, we can simply delete this
 		 * one and can still use the other one.
 		 */
-		batadv_tt_global_del_orig_entry(bat_priv, tt_global_entry,
-						orig_node, message);
+		batadv_tt_global_del_orig_node(bat_priv, tt_global_entry,
+					       orig_node, message);
 }
 
 /**
@@ -1643,8 +1745,8 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv,
 		goto out;
 
 	if (!roaming) {
-		batadv_tt_global_del_orig_entry(bat_priv, tt_global_entry,
-						orig_node, message);
+		batadv_tt_global_del_orig_node(bat_priv, tt_global_entry,
+					       orig_node, message);
 
 		if (hlist_empty(&tt_global_entry->orig_list))
 			batadv_tt_global_free(bat_priv, tt_global_entry,
@@ -1727,8 +1829,8 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
 						 struct batadv_tt_global_entry,
 						 common);
 
-			batadv_tt_global_del_orig_entry(bat_priv, tt_global,
-							orig_node, message);
+			batadv_tt_global_del_orig_node(bat_priv, tt_global,
+						       orig_node, message);
 
 			if (hlist_empty(&tt_global->orig_list)) {
 				vid = tt_global->common.vid;
@@ -1742,7 +1844,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
 		}
 		spin_unlock_bh(list_lock);
 	}
-	orig_node->tt_initialised = false;
+	orig_node->capa_initialized &= ~BATADV_ORIG_CAPA_HAS_TT;
 }
 
 static bool batadv_tt_global_to_purge(struct batadv_tt_global_entry *tt_global,
@@ -1852,6 +1954,11 @@ _batadv_is_ap_isolated(struct batadv_tt_local_entry *tt_local_entry,
 	    tt_global_entry->common.flags & BATADV_TT_CLIENT_WIFI)
 		ret = true;
 
+	/* check if the two clients are marked as isolated */
+	if (tt_local_entry->common.flags & BATADV_TT_CLIENT_ISOLA &&
+	    tt_global_entry->common.flags & BATADV_TT_CLIENT_ISOLA)
+		ret = true;
+
 	return ret;
 }
 
@@ -1878,19 +1985,8 @@ struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv,
 	struct batadv_tt_global_entry *tt_global_entry = NULL;
 	struct batadv_orig_node *orig_node = NULL;
 	struct batadv_tt_orig_list_entry *best_entry;
-	bool ap_isolation_enabled = false;
-	struct batadv_softif_vlan *vlan;
-
-	/* if the AP isolation is requested on a VLAN, then check for its
-	 * setting in the proper VLAN private data structure
-	 */
-	vlan = batadv_softif_vlan_get(bat_priv, vid);
-	if (vlan) {
-		ap_isolation_enabled = atomic_read(&vlan->ap_isolation);
-		batadv_softif_vlan_free_ref(vlan);
-	}
 
-	if (src && ap_isolation_enabled) {
+	if (src && batadv_vlan_ap_isola_get(bat_priv, vid)) {
 		tt_local_entry = batadv_tt_local_hash_find(bat_priv, src, vid);
 		if (!tt_local_entry ||
 		    (tt_local_entry->common.flags & BATADV_TT_CLIENT_PENDING))
@@ -1960,6 +2056,7 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv,
 	struct hlist_head *head;
 	uint32_t i, crc_tmp, crc = 0;
 	uint8_t flags;
+	__be16 tmp_vid;
 
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
@@ -1996,8 +2093,11 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv,
 							     orig_node))
 				continue;
 
-			crc_tmp = crc32c(0, &tt_common->vid,
-					 sizeof(tt_common->vid));
+			/* use network order to read the VID: this ensures that
+			 * every node reads the bytes in the same order.
+			 */
+			tmp_vid = htons(tt_common->vid);
+			crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid));
 
 			/* compute the CRC on flags that have to be kept in sync
 			 * among nodes
@@ -2031,6 +2131,7 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv,
 	struct hlist_head *head;
 	uint32_t i, crc_tmp, crc = 0;
 	uint8_t flags;
+	__be16 tmp_vid;
 
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
@@ -2049,8 +2150,11 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv,
 			if (tt_common->flags & BATADV_TT_CLIENT_NEW)
 				continue;
 
-			crc_tmp = crc32c(0, &tt_common->vid,
-					 sizeof(tt_common->vid));
+			/* use network order to read the VID: this ensures that
+			 * every node reads the bytes in the same order.
+			 */
+			tmp_vid = htons(tt_common->vid);
+			crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid));
 
 			/* compute the CRC on flags that have to be kept in sync
 			 * among nodes
@@ -2137,7 +2241,7 @@ batadv_new_tt_req_node(struct batadv_priv *bat_priv,
 	if (!tt_req_node)
 		goto unlock;
 
-	memcpy(tt_req_node->addr, orig_node->orig, ETH_ALEN);
+	ether_addr_copy(tt_req_node->addr, orig_node->orig);
 	tt_req_node->issued_at = jiffies;
 
 	list_add(&tt_req_node->list, &bat_priv->tt.req_list);
@@ -2217,11 +2321,11 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv,
 			if ((valid_cb) && (!valid_cb(tt_common_entry, cb_data)))
 				continue;
 
-			memcpy(tt_change->addr, tt_common_entry->addr,
-			       ETH_ALEN);
+			ether_addr_copy(tt_change->addr, tt_common_entry->addr);
 			tt_change->flags = tt_common_entry->flags;
 			tt_change->vid = htons(tt_common_entry->vid);
-			tt_change->reserved = 0;
+			memset(tt_change->reserved, 0,
+			       sizeof(tt_change->reserved));
 
 			tt_num_entries++;
 			tt_change++;
@@ -2246,6 +2350,7 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node,
 {
 	struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp;
 	struct batadv_orig_node_vlan *vlan;
+	uint32_t crc;
 	int i;
 
 	/* check if each received CRC matches the locally stored one */
@@ -2265,7 +2370,10 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node,
 		if (!vlan)
 			return false;
 
-		if (vlan->tt.crc != ntohl(tt_vlan_tmp->crc))
+		crc = vlan->tt.crc;
+		batadv_orig_node_vlan_free_ref(vlan);
+
+		if (crc != ntohl(tt_vlan_tmp->crc))
 			return false;
 	}
 
@@ -2696,7 +2804,7 @@ static void _batadv_tt_update_changes(struct batadv_priv *bat_priv,
 				return;
 		}
 	}
-	orig_node->tt_initialised = true;
+	orig_node->capa_initialized |= BATADV_ORIG_CAPA_HAS_TT;
 }
 
 static void batadv_tt_fill_gtable(struct batadv_priv *bat_priv,
@@ -2904,7 +3012,7 @@ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv,
 		tt_roam_node->first_time = jiffies;
 		atomic_set(&tt_roam_node->counter,
 			   BATADV_ROAMING_MAX_COUNT - 1);
-		memcpy(tt_roam_node->addr, client, ETH_ALEN);
+		ether_addr_copy(tt_roam_node->addr, client);
 
 		list_add(&tt_roam_node->list, &bat_priv->tt.roam_list);
 		ret = true;
@@ -3050,6 +3158,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv)
 	struct batadv_hashtable *hash = bat_priv->tt.local_hash;
 	struct batadv_tt_common_entry *tt_common;
 	struct batadv_tt_local_entry *tt_local;
+	struct batadv_softif_vlan *vlan;
 	struct hlist_node *node_tmp;
 	struct hlist_head *head;
 	spinlock_t *list_lock; /* protects write access to the hash lists */
@@ -3078,6 +3187,12 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv)
 			tt_local = container_of(tt_common,
 						struct batadv_tt_local_entry,
 						common);
+
+			/* decrease the reference held for this vlan */
+			vlan = batadv_softif_vlan_get(bat_priv, tt_common->vid);
+			batadv_softif_vlan_free_ref(vlan);
+			batadv_softif_vlan_free_ref(vlan);
+
 			batadv_tt_local_entry_free_ref(tt_local);
 		}
 		spin_unlock_bh(list_lock);
@@ -3093,6 +3208,9 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv)
  */
 static void batadv_tt_local_commit_changes_nolock(struct batadv_priv *bat_priv)
 {
+	/* Update multicast addresses in local translation table */
+	batadv_mcast_mla_update(bat_priv);
+
 	if (atomic_read(&bat_priv->tt.local_changes) < 1) {
 		if (!batadv_atomic_dec_not_zero(&bat_priv->tt.ogm_append_cnt))
 			batadv_tt_tvlv_container_update(bat_priv);
@@ -3183,13 +3301,15 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv,
 	uint8_t orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn);
 	struct batadv_tvlv_tt_vlan_data *tt_vlan;
 	bool full_table = true;
+	bool has_tt_init;
 
 	tt_vlan = (struct batadv_tvlv_tt_vlan_data *)tt_buff;
+	has_tt_init = orig_node->capa_initialized & BATADV_ORIG_CAPA_HAS_TT;
+
 	/* orig table not initialised AND first diff is in the OGM OR the ttvn
 	 * increased by one -> we can apply the attached changes
 	 */
-	if ((!orig_node->tt_initialised && ttvn == 1) ||
-	    ttvn - orig_ttvn == 1) {
+	if ((!has_tt_init && ttvn == 1) || ttvn - orig_ttvn == 1) {
 		/* the OGM could not contain the changes due to their size or
 		 * because they have already been sent BATADV_TT_OGM_APPEND_MAX
 		 * times.
@@ -3202,7 +3322,6 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv,
 
 		spin_lock_bh(&orig_node->tt_lock);
 
-		tt_change = (struct batadv_tvlv_tt_change *)tt_buff;
 		batadv_tt_update_changes(bat_priv, orig_node, tt_num_changes,
 					 ttvn, tt_change);
 
@@ -3230,7 +3349,7 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv,
 		/* if we missed more than one change or our tables are not
 		 * in sync anymore -> request fresh tt data
 		 */
-		if (!orig_node->tt_initialised || ttvn != orig_ttvn ||
+		if (!has_tt_init || ttvn != orig_ttvn ||
 		    !batadv_tt_global_check_crc(orig_node, tt_vlan,
 						tt_num_vlan)) {
 request_table:
@@ -3565,3 +3684,29 @@ int batadv_tt_init(struct batadv_priv *bat_priv)
 
 	return 1;
 }
+
+/**
+ * batadv_tt_global_is_isolated - check if a client is marked as isolated
+ * @bat_priv: the bat priv with all the soft interface information
+ * @addr: the mac address of the client
+ * @vid: the identifier of the VLAN where this client is connected
+ *
+ * Returns true if the client is marked with the TT_CLIENT_ISOLA flag, false
+ * otherwise
+ */
+bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv,
+				  const uint8_t *addr, unsigned short vid)
+{
+	struct batadv_tt_global_entry *tt;
+	bool ret;
+
+	tt = batadv_tt_global_hash_find(bat_priv, addr, vid);
+	if (!tt)
+		return false;
+
+	ret = tt->common.flags & BATADV_TT_CLIENT_ISOLA;
+
+	batadv_tt_global_entry_free_ref(tt);
+
+	return ret;
+}
diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h
index 026b1ffa674..ad84d7b89e3 100644
--- a/net/batman-adv/translation-table.h
+++ b/net/batman-adv/translation-table.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich, Antonio Quartulli
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_TRANSLATION_TABLE_H_
@@ -22,7 +20,7 @@
 
 int batadv_tt_init(struct batadv_priv *bat_priv);
 bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
-			 unsigned short vid, int ifindex);
+			 unsigned short vid, int ifindex, uint32_t mark);
 uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv,
 				const uint8_t *addr, unsigned short vid,
 				const char *message, bool roaming);
@@ -31,6 +29,8 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset);
 void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
 			       struct batadv_orig_node *orig_node,
 			       int32_t match_vid, const char *message);
+int batadv_tt_global_hash_count(struct batadv_priv *bat_priv,
+				const uint8_t *addr, unsigned short vid);
 struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv,
 						  const uint8_t *src,
 						  const uint8_t *addr,
@@ -50,5 +50,7 @@ bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv,
 					  struct batadv_orig_node *orig_node,
 					  const unsigned char *addr,
 					  unsigned short vid);
+bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv,
+				  const uint8_t *addr, unsigned short vid);
 
 #endif /* _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ */
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 91dd369b0ff..8854c05622a 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1,4 +1,4 @@
-/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2014 B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
  *
@@ -12,9 +12,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_TYPES_H_
@@ -26,8 +24,9 @@
 
 #ifdef CONFIG_BATMAN_ADV_DAT
 
-/* batadv_dat_addr_t is the type used for all DHT addresses. If it is changed,
- * BATADV_DAT_ADDR_MAX is changed as well.
+/**
+ * batadv_dat_addr_t - it is the type used for all DHT addresses. If it is
+ *  changed, BATADV_DAT_ADDR_MAX is changed as well.
  *
  * *Please be careful: batadv_dat_addr_t must be UNSIGNED*
  */
@@ -36,6 +35,18 @@
 #endif /* CONFIG_BATMAN_ADV_DAT */
 
 /**
+ * enum batadv_dhcp_recipient - dhcp destination
+ * @BATADV_DHCP_NO: packet is not a dhcp message
+ * @BATADV_DHCP_TO_SERVER: dhcp message is directed to a server
+ * @BATADV_DHCP_TO_CLIENT: dhcp message is directed to a client
+ */
+enum batadv_dhcp_recipient {
+	BATADV_DHCP_NO = 0,
+	BATADV_DHCP_TO_SERVER,
+	BATADV_DHCP_TO_CLIENT,
+};
+
+/**
  * BATADV_TT_REMOTE_MASK - bitmask selecting the flags that are sent over the
  *  wire only
  */
@@ -74,6 +85,7 @@ struct batadv_hard_iface_bat_iv {
  * @rcu: struct used for freeing in an RCU-safe manner
  * @bat_iv: BATMAN IV specific per hard interface data
  * @cleanup_work: work queue callback item for hard interface deinit
+ * @debug_dir: dentry for nc subdir in batman-adv directory in debugfs
  */
 struct batadv_hard_iface {
 	struct list_head list;
@@ -88,6 +100,29 @@ struct batadv_hard_iface {
 	struct rcu_head rcu;
 	struct batadv_hard_iface_bat_iv bat_iv;
 	struct work_struct cleanup_work;
+	struct dentry *debug_dir;
+};
+
+/**
+ * struct batadv_orig_ifinfo - originator info per outgoing interface
+ * @list: list node for orig_node::ifinfo_list
+ * @if_outgoing: pointer to outgoing hard interface
+ * @router: router that should be used to reach this originator
+ * @last_real_seqno: last and best known sequence number
+ * @last_ttl: ttl of last received packet
+ * @batman_seqno_reset: time when the batman seqno window was reset
+ * @refcount: number of contexts the object is used
+ * @rcu: struct used for freeing in an RCU-safe manner
+ */
+struct batadv_orig_ifinfo {
+	struct hlist_node list;
+	struct batadv_hard_iface *if_outgoing;
+	struct batadv_neigh_node __rcu *router; /* rcu protected pointer */
+	uint32_t last_real_seqno;
+	uint8_t last_ttl;
+	unsigned long batman_seqno_reset;
+	atomic_t refcount;
+	struct rcu_head rcu;
 };
 
 /**
@@ -129,7 +164,7 @@ struct batadv_vlan_tt {
 };
 
 /**
- * batadv_orig_node_vlan - VLAN specific data per orig_node
+ * struct batadv_orig_node_vlan - VLAN specific data per orig_node
  * @vid: the VLAN identifier
  * @tt: VLAN specific TT attributes
  * @list: list node for orig_node::vlan_list
@@ -165,36 +200,36 @@ struct batadv_orig_bat_iv {
  * struct batadv_orig_node - structure for orig_list maintaining nodes of mesh
  * @orig: originator ethernet address
  * @primary_addr: hosts primary interface address
- * @router: router that should be used to reach this originator
+ * @ifinfo_list: list for routers per outgoing interface
+ * @last_bonding_candidate: pointer to last ifinfo of last used router
  * @batadv_dat_addr_t:  address of the orig node in the distributed hash
  * @last_seen: time when last packet from this node was received
  * @bcast_seqno_reset: time when the broadcast seqno window was reset
- * @batman_seqno_reset: time when the batman seqno window was reset
+ * @mcast_flags: multicast flags announced by the orig node
+ * @mcast_want_all_unsnoop_node: a list node for the
+ *  mcast.want_all_unsnoopables list
+ * @mcast_want_all_ipv4_node: a list node for the mcast.want_all_ipv4 list
+ * @mcast_want_all_ipv6_node: a list node for the mcast.want_all_ipv6 list
  * @capabilities: announced capabilities of this originator
+ * @capa_initialized: bitfield to remember whether a capability was initialized
  * @last_ttvn: last seen translation table version number
  * @tt_buff: last tt changeset this node received from the orig node
  * @tt_buff_len: length of the last tt changeset this node received from the
  *  orig node
  * @tt_buff_lock: lock that protects tt_buff and tt_buff_len
- * @tt_initialised: bool keeping track of whether or not this node have received
- *  any translation table information from the orig node yet
  * @tt_lock: prevents from updating the table while reading it. Table update is
  *  made up by two operations (data structure update and metdata -CRC/TTVN-
  *  recalculation) and they have to be executed atomically in order to avoid
  *  another thread to read the table/metadata between those.
- * @last_real_seqno: last and best known sequence number
- * @last_ttl: ttl of last received packet
  * @bcast_bits: bitfield containing the info which payload broadcast originated
  *  from this orig node this host already has seen (relative to
  *  last_bcast_seqno)
  * @last_bcast_seqno: last broadcast sequence number received by this host
  * @neigh_list: list of potential next hop neighbor towards this orig node
- * @neigh_list_lock: lock protecting neigh_list, router and bonding_list
+ * @neigh_list_lock: lock protecting neigh_list and router
  * @hash_entry: hlist node for batadv_priv::orig_hash
  * @bat_priv: pointer to soft_iface this orig node belongs to
  * @bcast_seqno_lock: lock protecting bcast_bits & last_bcast_seqno
- * @bond_candidates: how many candidates are available
- * @bond_list: list of bonding candidates
  * @refcount: number of contexts the object is used
  * @rcu: struct used for freeing in an RCU-safe manner
  * @in_coding_list: list of nodes this orig can hear
@@ -210,34 +245,36 @@ struct batadv_orig_bat_iv {
 struct batadv_orig_node {
 	uint8_t orig[ETH_ALEN];
 	uint8_t primary_addr[ETH_ALEN];
-	struct batadv_neigh_node __rcu *router; /* rcu protected pointer */
+	struct hlist_head ifinfo_list;
+	struct batadv_orig_ifinfo *last_bonding_candidate;
 #ifdef CONFIG_BATMAN_ADV_DAT
 	batadv_dat_addr_t dat_addr;
 #endif
 	unsigned long last_seen;
 	unsigned long bcast_seqno_reset;
-	unsigned long batman_seqno_reset;
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	uint8_t mcast_flags;
+	struct hlist_node mcast_want_all_unsnoopables_node;
+	struct hlist_node mcast_want_all_ipv4_node;
+	struct hlist_node mcast_want_all_ipv6_node;
+#endif
 	uint8_t capabilities;
+	uint8_t capa_initialized;
 	atomic_t last_ttvn;
 	unsigned char *tt_buff;
 	int16_t tt_buff_len;
 	spinlock_t tt_buff_lock; /* protects tt_buff & tt_buff_len */
-	bool tt_initialised;
 	/* prevents from changing the table while reading it */
 	spinlock_t tt_lock;
-	uint32_t last_real_seqno;
-	uint8_t last_ttl;
 	DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE);
 	uint32_t last_bcast_seqno;
 	struct hlist_head neigh_list;
-	/* neigh_list_lock protects: neigh_list, router & bonding_list */
+	/* neigh_list_lock protects: neigh_list and router */
 	spinlock_t neigh_list_lock;
 	struct hlist_node hash_entry;
 	struct batadv_priv *bat_priv;
 	/* bcast_seqno_lock protects: bcast_bits & last_bcast_seqno */
 	spinlock_t bcast_seqno_lock;
-	atomic_t bond_candidates;
-	struct list_head bond_list;
 	atomic_t refcount;
 	struct rcu_head rcu;
 #ifdef CONFIG_BATMAN_ADV_NC
@@ -256,10 +293,15 @@ struct batadv_orig_node {
  * enum batadv_orig_capabilities - orig node capabilities
  * @BATADV_ORIG_CAPA_HAS_DAT: orig node has distributed arp table enabled
  * @BATADV_ORIG_CAPA_HAS_NC: orig node has network coding enabled
+ * @BATADV_ORIG_CAPA_HAS_TT: orig node has tt capability
+ * @BATADV_ORIG_CAPA_HAS_MCAST: orig node has some multicast capability
+ *  (= orig node announces a tvlv of type BATADV_TVLV_MCAST)
  */
 enum batadv_orig_capabilities {
 	BATADV_ORIG_CAPA_HAS_DAT = BIT(0),
 	BATADV_ORIG_CAPA_HAS_NC = BIT(1),
+	BATADV_ORIG_CAPA_HAS_TT = BIT(2),
+	BATADV_ORIG_CAPA_HAS_MCAST = BIT(3),
 };
 
 /**
@@ -283,49 +325,64 @@ struct batadv_gw_node {
 };
 
 /**
- * struct batadv_neigh_bat_iv - B.A.T.M.A.N. IV specific structure for single
- *  hop neighbors
+ * struct batadv_neigh_node - structure for single hops neighbors
+ * @list: list node for batadv_orig_node::neigh_list
+ * @orig_node: pointer to corresponding orig_node
+ * @addr: the MAC address of the neighboring interface
+ * @ifinfo_list: list for routing metrics per outgoing interface
+ * @ifinfo_lock: lock protecting private ifinfo members and list
+ * @if_incoming: pointer to incoming hard interface
+ * @last_seen: when last packet via this neighbor was received
+ * @last_ttl: last received ttl from this neigh node
+ * @rcu: struct used for freeing in an RCU-safe manner
+ * @bat_iv: B.A.T.M.A.N. IV private structure
+ */
+struct batadv_neigh_node {
+	struct hlist_node list;
+	struct batadv_orig_node *orig_node;
+	uint8_t addr[ETH_ALEN];
+	struct hlist_head ifinfo_list;
+	spinlock_t ifinfo_lock;	/* protects ifinfo_list and its members */
+	struct batadv_hard_iface *if_incoming;
+	unsigned long last_seen;
+	atomic_t refcount;
+	struct rcu_head rcu;
+};
+
+/**
+ * struct batadv_neigh_ifinfo_bat_iv - neighbor information per outgoing
+ *  interface for BATMAN IV
  * @tq_recv: ring buffer of received TQ values from this neigh node
  * @tq_index: ring buffer index
  * @tq_avg: averaged tq of all tq values in the ring buffer (tq_recv)
  * @real_bits: bitfield containing the number of OGMs received from this neigh
  *  node (relative to orig_node->last_real_seqno)
  * @real_packet_count: counted result of real_bits
- * @lq_update_lock: lock protecting tq_recv & tq_index
  */
-struct batadv_neigh_bat_iv {
+struct batadv_neigh_ifinfo_bat_iv {
 	uint8_t tq_recv[BATADV_TQ_GLOBAL_WINDOW_SIZE];
 	uint8_t tq_index;
 	uint8_t tq_avg;
 	DECLARE_BITMAP(real_bits, BATADV_TQ_LOCAL_WINDOW_SIZE);
 	uint8_t real_packet_count;
-	spinlock_t lq_update_lock; /* protects tq_recv & tq_index */
 };
 
 /**
- * struct batadv_neigh_node - structure for single hops neighbors
- * @list: list node for batadv_orig_node::neigh_list
- * @orig_node: pointer to corresponding orig_node
- * @addr: the MAC address of the neighboring interface
- * @if_incoming: pointer to incoming hard interface
- * @last_seen: when last packet via this neighbor was received
+ * struct batadv_neigh_ifinfo - neighbor information per outgoing interface
+ * @list: list node for batadv_neigh_node::ifinfo_list
+ * @if_outgoing: pointer to outgoing hard interface
+ * @bat_iv: B.A.T.M.A.N. IV private structure
  * @last_ttl: last received ttl from this neigh node
- * @bonding_list: list node for batadv_orig_node::bond_list
  * @refcount: number of contexts the object is used
- * @rcu: struct used for freeing in an RCU-safe manner
- * @bat_iv: B.A.T.M.A.N. IV private structure
+ * @rcu: struct used for freeing in a RCU-safe manner
  */
-struct batadv_neigh_node {
+struct batadv_neigh_ifinfo {
 	struct hlist_node list;
-	struct batadv_orig_node *orig_node;
-	uint8_t addr[ETH_ALEN];
-	struct batadv_hard_iface *if_incoming;
-	unsigned long last_seen;
+	struct batadv_hard_iface *if_outgoing;
+	struct batadv_neigh_ifinfo_bat_iv bat_iv;
 	uint8_t last_ttl;
-	struct list_head bonding_list;
 	atomic_t refcount;
 	struct rcu_head rcu;
-	struct batadv_neigh_bat_iv bat_iv;
 };
 
 /**
@@ -503,7 +560,7 @@ struct batadv_priv_bla {
 #endif
 
 /**
- * struct batadv_debug_log - debug logging data
+ * struct batadv_priv_debug_log - debug logging data
  * @log_buff: buffer holding the logs (ring bufer)
  * @log_start: index of next character to read
  * @log_end: index of next character to write
@@ -566,6 +623,39 @@ struct batadv_priv_dat {
 };
 #endif
 
+#ifdef CONFIG_BATMAN_ADV_MCAST
+/**
+ * struct batadv_priv_mcast - per mesh interface mcast data
+ * @mla_list: list of multicast addresses we are currently announcing via TT
+ * @want_all_unsnoopables_list: a list of orig_nodes wanting all unsnoopable
+ *  multicast traffic
+ * @want_all_ipv4_list: a list of orig_nodes wanting all IPv4 multicast traffic
+ * @want_all_ipv6_list: a list of orig_nodes wanting all IPv6 multicast traffic
+ * @flags: the flags we have last sent in our mcast tvlv
+ * @enabled: whether the multicast tvlv is currently enabled
+ * @num_disabled: number of nodes that have no mcast tvlv
+ * @num_want_all_unsnoopables: number of nodes wanting unsnoopable IP traffic
+ * @num_want_all_ipv4: counter for items in want_all_ipv4_list
+ * @num_want_all_ipv6: counter for items in want_all_ipv6_list
+ * @want_lists_lock: lock for protecting modifications to mcast want lists
+ *  (traversals are rcu-locked)
+ */
+struct batadv_priv_mcast {
+	struct hlist_head mla_list;
+	struct hlist_head want_all_unsnoopables_list;
+	struct hlist_head want_all_ipv4_list;
+	struct hlist_head want_all_ipv6_list;
+	uint8_t flags;
+	bool enabled;
+	atomic_t num_disabled;
+	atomic_t num_want_all_unsnoopables;
+	atomic_t num_want_all_ipv4;
+	atomic_t num_want_all_ipv6;
+	/* protects want_all_{unsnoopables,ipv4,ipv6}_list */
+	spinlock_t want_lists_lock;
+};
+#endif
+
 /**
  * struct batadv_priv_nc - per mesh interface network coding private data
  * @work: work queue callback item for cleanup
@@ -597,6 +687,7 @@ struct batadv_priv_nc {
 
 /**
  * struct batadv_softif_vlan - per VLAN attributes set
+ * @bat_priv: pointer to the mesh object
  * @vid: VLAN identifier
  * @kobj: kobject for sysfs vlan subdirectory
  * @ap_isolation: AP isolation state
@@ -606,6 +697,7 @@ struct batadv_priv_nc {
  * @rcu: struct used for freeing in a RCU-safe manner
  */
 struct batadv_softif_vlan {
+	struct batadv_priv *bat_priv;
 	unsigned short vid;
 	struct kobject *kobj;
 	atomic_t ap_isolation;		/* boolean */
@@ -631,6 +723,8 @@ struct batadv_softif_vlan {
  *  enabled
  * @distributed_arp_table: bool indicating whether distributed ARP table is
  *  enabled
+ * @multicast_mode: Enable or disable multicast optimizations on this node's
+ *  sender/originating side
  * @gw_mode: gateway operation: off, client or server (see batadv_gw_modes)
  * @gw_sel_class: gateway selection class (applies if gw_mode client)
  * @orig_interval: OGM broadcast interval in milliseconds
@@ -661,6 +755,7 @@ struct batadv_softif_vlan {
  * @tt: translation table data
  * @tvlv: type-version-length-value data
  * @dat: distributed arp table data
+ * @mcast: multicast data
  * @network_coding: bool indicating whether network coding is enabled
  * @batadv_priv_nc: network coding data
  */
@@ -680,6 +775,9 @@ struct batadv_priv {
 #ifdef CONFIG_BATMAN_ADV_DAT
 	atomic_t distributed_arp_table;
 #endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	atomic_t multicast_mode;
+#endif
 	atomic_t gw_mode;
 	atomic_t gw_sel_class;
 	atomic_t orig_interval;
@@ -687,6 +785,8 @@ struct batadv_priv {
 #ifdef CONFIG_BATMAN_ADV_DEBUG
 	atomic_t log_level;
 #endif
+	uint32_t isolation_mark;
+	uint32_t isolation_mark_mask;
 	atomic_t bcast_seqno;
 	atomic_t bcast_queue_left;
 	atomic_t batman_queue_left;
@@ -716,6 +816,9 @@ struct batadv_priv {
 #ifdef CONFIG_BATMAN_ADV_DAT
 	struct batadv_priv_dat dat;
 #endif
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	struct batadv_priv_mcast mcast;
+#endif
 #ifdef CONFIG_BATMAN_ADV_NC
 	atomic_t network_coding;
 	struct batadv_priv_nc nc;
@@ -838,12 +941,14 @@ struct batadv_tt_local_entry {
  * struct batadv_tt_global_entry - translation table global entry data
  * @common: general translation table data
  * @orig_list: list of orig nodes announcing this non-mesh client
+ * @orig_list_count: number of items in the orig_list
  * @list_lock: lock protecting orig_list
  * @roam_at: time at which TT_GLOBAL_ROAM was set
  */
 struct batadv_tt_global_entry {
 	struct batadv_tt_common_entry common;
 	struct hlist_head orig_list;
+	atomic_t orig_list_count;
 	spinlock_t list_lock;	/* protects orig_list */
 	unsigned long roam_at;
 };
@@ -961,8 +1066,8 @@ struct batadv_nc_packet {
 };
 
 /**
- * batadv_skb_cb - control buffer structure used to store private data relevant
- *  to batman-adv in the skb->cb buffer in skbs.
+ * struct batadv_skb_cb - control buffer structure used to store private data
+ *  relevant to batman-adv in the skb->cb buffer in skbs.
  * @decoded: Marks a skb as decoded, which is checked when searching for coding
  *  opportunities in network-coding.c
  */
@@ -981,8 +1086,10 @@ struct batadv_skb_cb {
  * @direct_link_flags: direct link flags for aggregated OGM packets
  * @num_packets: counter for bcast packet retransmission
  * @delayed_work: work queue callback item for packet sending
- * @if_incoming: pointer incoming hard-iface or primary iface if locally
- *  generated packet
+ * @if_incoming: pointer to incoming hard-iface or primary iface if
+ *  locally generated packet
+ * @if_outgoing: packet where the packet should be sent to, or NULL if
+ *  unspecified
  */
 struct batadv_forw_packet {
 	struct hlist_node list;
@@ -994,6 +1101,7 @@ struct batadv_forw_packet {
 	uint8_t num_packets;
 	struct delayed_work delayed_work;
 	struct batadv_hard_iface *if_incoming;
+	struct batadv_hard_iface *if_outgoing;
 };
 
 /**
@@ -1007,9 +1115,11 @@ struct batadv_forw_packet {
  * @bat_primary_iface_set: called when primary interface is selected / changed
  * @bat_ogm_schedule: prepare a new outgoing OGM for the send queue
  * @bat_ogm_emit: send scheduled OGM
- * @bat_neigh_cmp: compare the metrics of two neighbors
- * @bat_neigh_is_equiv_or_better: check if neigh1 is equally good or
- *  better than neigh2 from the metric prospective
+ * @bat_neigh_cmp: compare the metrics of two neighbors for their respective
+ *  outgoing interfaces
+ * @bat_neigh_is_equiv_or_better: check if neigh1 is equally good or better
+ *  than neigh2 for their respective outgoing interface from the metric
+ *  prospective
  * @bat_orig_print: print the originator table (optional)
  * @bat_orig_free: free the resources allocated by the routing algorithm for an
  *  orig_node object
@@ -1028,11 +1138,17 @@ struct batadv_algo_ops {
 	void (*bat_ogm_schedule)(struct batadv_hard_iface *hard_iface);
 	void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet);
 	int (*bat_neigh_cmp)(struct batadv_neigh_node *neigh1,
-			     struct batadv_neigh_node *neigh2);
-	bool (*bat_neigh_is_equiv_or_better)(struct batadv_neigh_node *neigh1,
-					     struct batadv_neigh_node *neigh2);
+			     struct batadv_hard_iface *if_outgoing1,
+			     struct batadv_neigh_node *neigh2,
+			     struct batadv_hard_iface *if_outgoing2);
+	bool (*bat_neigh_is_equiv_or_better)
+		(struct batadv_neigh_node *neigh1,
+		 struct batadv_hard_iface *if_outgoing1,
+		 struct batadv_neigh_node *neigh2,
+		 struct batadv_hard_iface *if_outgoing2);
 	/* orig_node handling API */
-	void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq);
+	void (*bat_orig_print)(struct batadv_priv *priv, struct seq_file *seq,
+			       struct batadv_hard_iface *hard_iface);
 	void (*bat_orig_free)(struct batadv_orig_node *orig_node);
 	int (*bat_orig_add_if)(struct batadv_orig_node *orig_node,
 			       int max_if_num);
@@ -1062,6 +1178,16 @@ struct batadv_dat_entry {
 };
 
 /**
+ * struct batadv_hw_addr - a list entry for a MAC address
+ * @list: list node for the linking of entries
+ * @addr: the MAC address of this list entry
+ */
+struct batadv_hw_addr {
+	struct hlist_node list;
+	unsigned char addr[ETH_ALEN];
+};
+
+/**
  * struct batadv_dat_candidate - candidate destination for DAT operations
  * @type: the type of the selected candidate. It can one of the following:
  *	  - BATADV_DAT_CANDIDATE_NOT_FOUND
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
new file mode 100644
index 00000000000..8796ffa08b4
--- /dev/null
+++ b/net/bluetooth/6lowpan.c
@@ -0,0 +1,865 @@
+/*
+   Copyright (c) 2013 Intel Corp.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 2 and
+   only version 2 as published by the Free Software Foundation.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+*/
+
+#include <linux/if_arp.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+
+#include <net/af_ieee802154.h> /* to get the address type */
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/l2cap.h>
+
+#include "6lowpan.h"
+
+#include <net/6lowpan.h> /* for the compression support */
+
+#define IFACE_NAME_TEMPLATE "bt%d"
+#define EUI64_ADDR_LEN 8
+
+struct skb_cb {
+	struct in6_addr addr;
+	struct l2cap_conn *conn;
+};
+#define lowpan_cb(skb) ((struct skb_cb *)((skb)->cb))
+
+/* The devices list contains those devices that we are acting
+ * as a proxy. The BT 6LoWPAN device is a virtual device that
+ * connects to the Bluetooth LE device. The real connection to
+ * BT device is done via l2cap layer. There exists one
+ * virtual device / one BT 6LoWPAN network (=hciX device).
+ * The list contains struct lowpan_dev elements.
+ */
+static LIST_HEAD(bt_6lowpan_devices);
+static DEFINE_RWLOCK(devices_lock);
+
+struct lowpan_peer {
+	struct list_head list;
+	struct l2cap_conn *conn;
+
+	/* peer addresses in various formats */
+	unsigned char eui64_addr[EUI64_ADDR_LEN];
+	struct in6_addr peer_addr;
+};
+
+struct lowpan_dev {
+	struct list_head list;
+
+	struct hci_dev *hdev;
+	struct net_device *netdev;
+	struct list_head peers;
+	atomic_t peer_count; /* number of items in peers list */
+
+	struct work_struct delete_netdev;
+	struct delayed_work notify_peers;
+};
+
+static inline struct lowpan_dev *lowpan_dev(const struct net_device *netdev)
+{
+	return netdev_priv(netdev);
+}
+
+static inline void peer_add(struct lowpan_dev *dev, struct lowpan_peer *peer)
+{
+	list_add(&peer->list, &dev->peers);
+	atomic_inc(&dev->peer_count);
+}
+
+static inline bool peer_del(struct lowpan_dev *dev, struct lowpan_peer *peer)
+{
+	list_del(&peer->list);
+
+	if (atomic_dec_and_test(&dev->peer_count)) {
+		BT_DBG("last peer");
+		return true;
+	}
+
+	return false;
+}
+
+static inline struct lowpan_peer *peer_lookup_ba(struct lowpan_dev *dev,
+						 bdaddr_t *ba, __u8 type)
+{
+	struct lowpan_peer *peer, *tmp;
+
+	BT_DBG("peers %d addr %pMR type %d", atomic_read(&dev->peer_count),
+	       ba, type);
+
+	list_for_each_entry_safe(peer, tmp, &dev->peers, list) {
+		BT_DBG("addr %pMR type %d",
+		       &peer->conn->hcon->dst, peer->conn->hcon->dst_type);
+
+		if (bacmp(&peer->conn->hcon->dst, ba))
+			continue;
+
+		if (type == peer->conn->hcon->dst_type)
+			return peer;
+	}
+
+	return NULL;
+}
+
+static inline struct lowpan_peer *peer_lookup_conn(struct lowpan_dev *dev,
+						   struct l2cap_conn *conn)
+{
+	struct lowpan_peer *peer, *tmp;
+
+	list_for_each_entry_safe(peer, tmp, &dev->peers, list) {
+		if (peer->conn == conn)
+			return peer;
+	}
+
+	return NULL;
+}
+
+static struct lowpan_peer *lookup_peer(struct l2cap_conn *conn)
+{
+	struct lowpan_dev *entry, *tmp;
+	struct lowpan_peer *peer = NULL;
+	unsigned long flags;
+
+	read_lock_irqsave(&devices_lock, flags);
+
+	list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) {
+		peer = peer_lookup_conn(entry, conn);
+		if (peer)
+			break;
+	}
+
+	read_unlock_irqrestore(&devices_lock, flags);
+
+	return peer;
+}
+
+static struct lowpan_dev *lookup_dev(struct l2cap_conn *conn)
+{
+	struct lowpan_dev *entry, *tmp;
+	struct lowpan_dev *dev = NULL;
+	unsigned long flags;
+
+	read_lock_irqsave(&devices_lock, flags);
+
+	list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) {
+		if (conn->hcon->hdev == entry->hdev) {
+			dev = entry;
+			break;
+		}
+	}
+
+	read_unlock_irqrestore(&devices_lock, flags);
+
+	return dev;
+}
+
+static int give_skb_to_upper(struct sk_buff *skb, struct net_device *dev)
+{
+	struct sk_buff *skb_cp;
+	int ret;
+
+	skb_cp = skb_copy(skb, GFP_ATOMIC);
+	if (!skb_cp)
+		return -ENOMEM;
+
+	ret = netif_rx(skb_cp);
+
+	BT_DBG("receive skb %d", ret);
+	if (ret < 0)
+		return NET_RX_DROP;
+
+	return ret;
+}
+
+static int process_data(struct sk_buff *skb, struct net_device *netdev,
+			struct l2cap_conn *conn)
+{
+	const u8 *saddr, *daddr;
+	u8 iphc0, iphc1;
+	struct lowpan_dev *dev;
+	struct lowpan_peer *peer;
+	unsigned long flags;
+
+	dev = lowpan_dev(netdev);
+
+	read_lock_irqsave(&devices_lock, flags);
+	peer = peer_lookup_conn(dev, conn);
+	read_unlock_irqrestore(&devices_lock, flags);
+	if (!peer)
+		goto drop;
+
+	saddr = peer->eui64_addr;
+	daddr = dev->netdev->dev_addr;
+
+	/* at least two bytes will be used for the encoding */
+	if (skb->len < 2)
+		goto drop;
+
+	if (lowpan_fetch_skb_u8(skb, &iphc0))
+		goto drop;
+
+	if (lowpan_fetch_skb_u8(skb, &iphc1))
+		goto drop;
+
+	return lowpan_process_data(skb, netdev,
+				   saddr, IEEE802154_ADDR_LONG, EUI64_ADDR_LEN,
+				   daddr, IEEE802154_ADDR_LONG, EUI64_ADDR_LEN,
+				   iphc0, iphc1, give_skb_to_upper);
+
+drop:
+	kfree_skb(skb);
+	return -EINVAL;
+}
+
+static int recv_pkt(struct sk_buff *skb, struct net_device *dev,
+		    struct l2cap_conn *conn)
+{
+	struct sk_buff *local_skb;
+	int ret;
+
+	if (!netif_running(dev))
+		goto drop;
+
+	if (dev->type != ARPHRD_6LOWPAN)
+		goto drop;
+
+	/* check that it's our buffer */
+	if (skb->data[0] == LOWPAN_DISPATCH_IPV6) {
+		/* Copy the packet so that the IPv6 header is
+		 * properly aligned.
+		 */
+		local_skb = skb_copy_expand(skb, NET_SKB_PAD - 1,
+					    skb_tailroom(skb), GFP_ATOMIC);
+		if (!local_skb)
+			goto drop;
+
+		local_skb->protocol = htons(ETH_P_IPV6);
+		local_skb->pkt_type = PACKET_HOST;
+
+		skb_reset_network_header(local_skb);
+		skb_set_transport_header(local_skb, sizeof(struct ipv6hdr));
+
+		if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) {
+			kfree_skb(local_skb);
+			goto drop;
+		}
+
+		dev->stats.rx_bytes += skb->len;
+		dev->stats.rx_packets++;
+
+		kfree_skb(local_skb);
+		kfree_skb(skb);
+	} else {
+		switch (skb->data[0] & 0xe0) {
+		case LOWPAN_DISPATCH_IPHC:	/* ipv6 datagram */
+			local_skb = skb_clone(skb, GFP_ATOMIC);
+			if (!local_skb)
+				goto drop;
+
+			ret = process_data(local_skb, dev, conn);
+			if (ret != NET_RX_SUCCESS)
+				goto drop;
+
+			dev->stats.rx_bytes += skb->len;
+			dev->stats.rx_packets++;
+
+			kfree_skb(skb);
+			break;
+		default:
+			break;
+		}
+	}
+
+	return NET_RX_SUCCESS;
+
+drop:
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
+
+/* Packet from BT LE device */
+int bt_6lowpan_recv(struct l2cap_conn *conn, struct sk_buff *skb)
+{
+	struct lowpan_dev *dev;
+	struct lowpan_peer *peer;
+	int err;
+
+	peer = lookup_peer(conn);
+	if (!peer)
+		return -ENOENT;
+
+	dev = lookup_dev(conn);
+	if (!dev || !dev->netdev)
+		return -ENOENT;
+
+	err = recv_pkt(skb, dev->netdev, conn);
+	BT_DBG("recv pkt %d", err);
+
+	return err;
+}
+
+static inline int skbuff_copy(void *msg, int len, int count, int mtu,
+			      struct sk_buff *skb, struct net_device *dev)
+{
+	struct sk_buff **frag;
+	int sent = 0;
+
+	memcpy(skb_put(skb, count), msg, count);
+
+	sent += count;
+	msg  += count;
+	len  -= count;
+
+	dev->stats.tx_bytes += count;
+	dev->stats.tx_packets++;
+
+	raw_dump_table(__func__, "Sending", skb->data, skb->len);
+
+	/* Continuation fragments (no L2CAP header) */
+	frag = &skb_shinfo(skb)->frag_list;
+	while (len > 0) {
+		struct sk_buff *tmp;
+
+		count = min_t(unsigned int, mtu, len);
+
+		tmp = bt_skb_alloc(count, GFP_ATOMIC);
+		if (!tmp)
+			return -ENOMEM;
+
+		*frag = tmp;
+
+		memcpy(skb_put(*frag, count), msg, count);
+
+		raw_dump_table(__func__, "Sending fragment",
+			       (*frag)->data, count);
+
+		(*frag)->priority = skb->priority;
+
+		sent += count;
+		msg  += count;
+		len  -= count;
+
+		skb->len += (*frag)->len;
+		skb->data_len += (*frag)->len;
+
+		frag = &(*frag)->next;
+
+		dev->stats.tx_bytes += count;
+		dev->stats.tx_packets++;
+	}
+
+	return sent;
+}
+
+static struct sk_buff *create_pdu(struct l2cap_conn *conn, void *msg,
+				  size_t len, u32 priority,
+				  struct net_device *dev)
+{
+	struct sk_buff *skb;
+	int err, count;
+	struct l2cap_hdr *lh;
+
+	/* FIXME: This mtu check should be not needed and atm is only used for
+	 * testing purposes
+	 */
+	if (conn->mtu > (L2CAP_LE_MIN_MTU + L2CAP_HDR_SIZE))
+		conn->mtu = L2CAP_LE_MIN_MTU + L2CAP_HDR_SIZE;
+
+	count = min_t(unsigned int, (conn->mtu - L2CAP_HDR_SIZE), len);
+
+	BT_DBG("conn %p len %zu mtu %d count %d", conn, len, conn->mtu, count);
+
+	skb = bt_skb_alloc(count + L2CAP_HDR_SIZE, GFP_ATOMIC);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	skb->priority = priority;
+
+	lh = (struct l2cap_hdr *)skb_put(skb, L2CAP_HDR_SIZE);
+	lh->cid = cpu_to_le16(L2CAP_FC_6LOWPAN);
+	lh->len = cpu_to_le16(len);
+
+	err = skbuff_copy(msg, len, count, conn->mtu, skb, dev);
+	if (unlikely(err < 0)) {
+		kfree_skb(skb);
+		BT_DBG("skbuff copy %d failed", err);
+		return ERR_PTR(err);
+	}
+
+	return skb;
+}
+
+static int conn_send(struct l2cap_conn *conn,
+		     void *msg, size_t len, u32 priority,
+		     struct net_device *dev)
+{
+	struct sk_buff *skb;
+
+	skb = create_pdu(conn, msg, len, priority, dev);
+	if (IS_ERR(skb))
+		return -EINVAL;
+
+	BT_DBG("conn %p skb %p len %d priority %u", conn, skb, skb->len,
+	       skb->priority);
+
+	hci_send_acl(conn->hchan, skb, ACL_START);
+
+	return 0;
+}
+
+static u8 get_addr_type_from_eui64(u8 byte)
+{
+	/* Is universal(0) or local(1) bit,  */
+	if (byte & 0x02)
+		return ADDR_LE_DEV_RANDOM;
+
+	return ADDR_LE_DEV_PUBLIC;
+}
+
+static void copy_to_bdaddr(struct in6_addr *ip6_daddr, bdaddr_t *addr)
+{
+	u8 *eui64 = ip6_daddr->s6_addr + 8;
+
+	addr->b[0] = eui64[7];
+	addr->b[1] = eui64[6];
+	addr->b[2] = eui64[5];
+	addr->b[3] = eui64[2];
+	addr->b[4] = eui64[1];
+	addr->b[5] = eui64[0];
+}
+
+static void convert_dest_bdaddr(struct in6_addr *ip6_daddr,
+				bdaddr_t *addr, u8 *addr_type)
+{
+	copy_to_bdaddr(ip6_daddr, addr);
+
+	/* We need to toggle the U/L bit that we got from IPv6 address
+	 * so that we get the proper address and type of the BD address.
+	 */
+	addr->b[5] ^= 0x02;
+
+	*addr_type = get_addr_type_from_eui64(addr->b[5]);
+}
+
+static int header_create(struct sk_buff *skb, struct net_device *netdev,
+		         unsigned short type, const void *_daddr,
+		         const void *_saddr, unsigned int len)
+{
+	struct ipv6hdr *hdr;
+	struct lowpan_dev *dev;
+	struct lowpan_peer *peer;
+	bdaddr_t addr, *any = BDADDR_ANY;
+	u8 *saddr, *daddr = any->b;
+	u8 addr_type;
+
+	if (type != ETH_P_IPV6)
+		return -EINVAL;
+
+	hdr = ipv6_hdr(skb);
+
+	dev = lowpan_dev(netdev);
+
+	if (ipv6_addr_is_multicast(&hdr->daddr)) {
+		memcpy(&lowpan_cb(skb)->addr, &hdr->daddr,
+		       sizeof(struct in6_addr));
+		lowpan_cb(skb)->conn = NULL;
+	} else {
+		unsigned long flags;
+
+		/* Get destination BT device from skb.
+		 * If there is no such peer then discard the packet.
+		 */
+		convert_dest_bdaddr(&hdr->daddr, &addr, &addr_type);
+
+		BT_DBG("dest addr %pMR type %s IP %pI6c", &addr,
+		       addr_type == ADDR_LE_DEV_PUBLIC ? "PUBLIC" : "RANDOM",
+		       &hdr->daddr);
+
+		read_lock_irqsave(&devices_lock, flags);
+		peer = peer_lookup_ba(dev, &addr, addr_type);
+		read_unlock_irqrestore(&devices_lock, flags);
+
+		if (!peer) {
+			BT_DBG("no such peer %pMR found", &addr);
+			return -ENOENT;
+		}
+
+		daddr = peer->eui64_addr;
+
+		memcpy(&lowpan_cb(skb)->addr, &hdr->daddr,
+		       sizeof(struct in6_addr));
+		lowpan_cb(skb)->conn = peer->conn;
+	}
+
+	saddr = dev->netdev->dev_addr;
+
+	return lowpan_header_compress(skb, netdev, type, daddr, saddr, len);
+}
+
+/* Packet to BT LE device */
+static int send_pkt(struct l2cap_conn *conn, const void *saddr,
+		    const void *daddr, struct sk_buff *skb,
+		    struct net_device *netdev)
+{
+	raw_dump_table(__func__, "raw skb data dump before fragmentation",
+		       skb->data, skb->len);
+
+	return conn_send(conn, skb->data, skb->len, 0, netdev);
+}
+
+static void send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct sk_buff *local_skb;
+	struct lowpan_dev *entry, *tmp;
+	unsigned long flags;
+
+	read_lock_irqsave(&devices_lock, flags);
+
+	list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) {
+		struct lowpan_peer *pentry, *ptmp;
+		struct lowpan_dev *dev;
+
+		if (entry->netdev != netdev)
+			continue;
+
+		dev = lowpan_dev(entry->netdev);
+
+		list_for_each_entry_safe(pentry, ptmp, &dev->peers, list) {
+			local_skb = skb_clone(skb, GFP_ATOMIC);
+
+			send_pkt(pentry->conn, netdev->dev_addr,
+				 pentry->eui64_addr, local_skb, netdev);
+
+			kfree_skb(local_skb);
+		}
+	}
+
+	read_unlock_irqrestore(&devices_lock, flags);
+}
+
+static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	int err = 0;
+	unsigned char *eui64_addr;
+	struct lowpan_dev *dev;
+	struct lowpan_peer *peer;
+	bdaddr_t addr;
+	u8 addr_type;
+
+	if (ipv6_addr_is_multicast(&lowpan_cb(skb)->addr)) {
+		/* We need to send the packet to every device
+		 * behind this interface.
+		 */
+		send_mcast_pkt(skb, netdev);
+	} else {
+		unsigned long flags;
+
+		convert_dest_bdaddr(&lowpan_cb(skb)->addr, &addr, &addr_type);
+		eui64_addr = lowpan_cb(skb)->addr.s6_addr + 8;
+		dev = lowpan_dev(netdev);
+
+		read_lock_irqsave(&devices_lock, flags);
+		peer = peer_lookup_ba(dev, &addr, addr_type);
+		read_unlock_irqrestore(&devices_lock, flags);
+
+		BT_DBG("xmit %s to %pMR type %s IP %pI6c peer %p",
+		       netdev->name, &addr,
+		       addr_type == ADDR_LE_DEV_PUBLIC ? "PUBLIC" : "RANDOM",
+		       &lowpan_cb(skb)->addr, peer);
+
+		if (peer && peer->conn)
+			err = send_pkt(peer->conn, netdev->dev_addr,
+				       eui64_addr, skb, netdev);
+	}
+	dev_kfree_skb(skb);
+
+	if (err)
+		BT_DBG("ERROR: xmit failed (%d)", err);
+
+	return (err < 0) ? NET_XMIT_DROP : err;
+}
+
+static const struct net_device_ops netdev_ops = {
+	.ndo_start_xmit		= bt_xmit,
+};
+
+static struct header_ops header_ops = {
+	.create	= header_create,
+};
+
+static void netdev_setup(struct net_device *dev)
+{
+	dev->addr_len		= EUI64_ADDR_LEN;
+	dev->type		= ARPHRD_6LOWPAN;
+
+	dev->hard_header_len	= 0;
+	dev->needed_tailroom	= 0;
+	dev->mtu		= IPV6_MIN_MTU;
+	dev->tx_queue_len	= 0;
+	dev->flags		= IFF_RUNNING | IFF_POINTOPOINT;
+	dev->watchdog_timeo	= 0;
+
+	dev->netdev_ops		= &netdev_ops;
+	dev->header_ops		= &header_ops;
+	dev->destructor		= free_netdev;
+}
+
+static struct device_type bt_type = {
+	.name	= "bluetooth",
+};
+
+static void set_addr(u8 *eui, u8 *addr, u8 addr_type)
+{
+	/* addr is the BT address in little-endian format */
+	eui[0] = addr[5];
+	eui[1] = addr[4];
+	eui[2] = addr[3];
+	eui[3] = 0xFF;
+	eui[4] = 0xFE;
+	eui[5] = addr[2];
+	eui[6] = addr[1];
+	eui[7] = addr[0];
+
+	/* Universal/local bit set, BT 6lowpan draft ch. 3.2.1 */
+	if (addr_type == ADDR_LE_DEV_PUBLIC)
+		eui[0] &= ~0x02;
+	else
+		eui[0] |= 0x02;
+
+	BT_DBG("type %d addr %*phC", addr_type, 8, eui);
+}
+
+static void set_dev_addr(struct net_device *netdev, bdaddr_t *addr,
+		         u8 addr_type)
+{
+	netdev->addr_assign_type = NET_ADDR_PERM;
+	set_addr(netdev->dev_addr, addr->b, addr_type);
+}
+
+static void ifup(struct net_device *netdev)
+{
+	int err;
+
+	rtnl_lock();
+	err = dev_open(netdev);
+	if (err < 0)
+		BT_INFO("iface %s cannot be opened (%d)", netdev->name, err);
+	rtnl_unlock();
+}
+
+static void do_notify_peers(struct work_struct *work)
+{
+	struct lowpan_dev *dev = container_of(work, struct lowpan_dev,
+					      notify_peers.work);
+
+	netdev_notify_peers(dev->netdev); /* send neighbour adv at startup */
+}
+
+static bool is_bt_6lowpan(struct hci_conn *hcon)
+{
+	if (hcon->type != LE_LINK)
+		return false;
+
+	return test_bit(HCI_CONN_6LOWPAN, &hcon->flags);
+}
+
+static int add_peer_conn(struct l2cap_conn *conn, struct lowpan_dev *dev)
+{
+	struct lowpan_peer *peer;
+	unsigned long flags;
+
+	peer = kzalloc(sizeof(*peer), GFP_ATOMIC);
+	if (!peer)
+		return -ENOMEM;
+
+	peer->conn = conn;
+	memset(&peer->peer_addr, 0, sizeof(struct in6_addr));
+
+	/* RFC 2464 ch. 5 */
+	peer->peer_addr.s6_addr[0] = 0xFE;
+	peer->peer_addr.s6_addr[1] = 0x80;
+	set_addr((u8 *)&peer->peer_addr.s6_addr + 8, conn->hcon->dst.b,
+	         conn->hcon->dst_type);
+
+	memcpy(&peer->eui64_addr, (u8 *)&peer->peer_addr.s6_addr + 8,
+	       EUI64_ADDR_LEN);
+
+	write_lock_irqsave(&devices_lock, flags);
+	INIT_LIST_HEAD(&peer->list);
+	peer_add(dev, peer);
+	write_unlock_irqrestore(&devices_lock, flags);
+
+	/* Notifying peers about us needs to be done without locks held */
+	INIT_DELAYED_WORK(&dev->notify_peers, do_notify_peers);
+	schedule_delayed_work(&dev->notify_peers, msecs_to_jiffies(100));
+
+	return 0;
+}
+
+/* This gets called when BT LE 6LoWPAN device is connected. We then
+ * create network device that acts as a proxy between BT LE device
+ * and kernel network stack.
+ */
+int bt_6lowpan_add_conn(struct l2cap_conn *conn)
+{
+	struct lowpan_peer *peer = NULL;
+	struct lowpan_dev *dev;
+	struct net_device *netdev;
+	int err = 0;
+	unsigned long flags;
+
+	if (!is_bt_6lowpan(conn->hcon))
+		return 0;
+
+	peer = lookup_peer(conn);
+	if (peer)
+		return -EEXIST;
+
+	dev = lookup_dev(conn);
+	if (dev)
+		return add_peer_conn(conn, dev);
+
+	netdev = alloc_netdev(sizeof(*dev), IFACE_NAME_TEMPLATE, netdev_setup);
+	if (!netdev)
+		return -ENOMEM;
+
+	set_dev_addr(netdev, &conn->hcon->src, conn->hcon->src_type);
+
+	netdev->netdev_ops = &netdev_ops;
+	SET_NETDEV_DEV(netdev, &conn->hcon->dev);
+	SET_NETDEV_DEVTYPE(netdev, &bt_type);
+
+	err = register_netdev(netdev);
+	if (err < 0) {
+		BT_INFO("register_netdev failed %d", err);
+		free_netdev(netdev);
+		goto out;
+	}
+
+	BT_DBG("ifindex %d peer bdaddr %pMR my addr %pMR",
+	       netdev->ifindex, &conn->hcon->dst, &conn->hcon->src);
+	set_bit(__LINK_STATE_PRESENT, &netdev->state);
+
+	dev = netdev_priv(netdev);
+	dev->netdev = netdev;
+	dev->hdev = conn->hcon->hdev;
+	INIT_LIST_HEAD(&dev->peers);
+
+	write_lock_irqsave(&devices_lock, flags);
+	INIT_LIST_HEAD(&dev->list);
+	list_add(&dev->list, &bt_6lowpan_devices);
+	write_unlock_irqrestore(&devices_lock, flags);
+
+	ifup(netdev);
+
+	return add_peer_conn(conn, dev);
+
+out:
+	return err;
+}
+
+static void delete_netdev(struct work_struct *work)
+{
+	struct lowpan_dev *entry = container_of(work, struct lowpan_dev,
+						delete_netdev);
+
+	unregister_netdev(entry->netdev);
+
+	/* The entry pointer is deleted in device_event() */
+}
+
+int bt_6lowpan_del_conn(struct l2cap_conn *conn)
+{
+	struct lowpan_dev *entry, *tmp;
+	struct lowpan_dev *dev = NULL;
+	struct lowpan_peer *peer;
+	int err = -ENOENT;
+	unsigned long flags;
+	bool last = false;
+
+	if (!conn || !is_bt_6lowpan(conn->hcon))
+		return 0;
+
+	write_lock_irqsave(&devices_lock, flags);
+
+	list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices, list) {
+		dev = lowpan_dev(entry->netdev);
+		peer = peer_lookup_conn(dev, conn);
+		if (peer) {
+			last = peer_del(dev, peer);
+			err = 0;
+			break;
+		}
+	}
+
+	if (!err && last && dev && !atomic_read(&dev->peer_count)) {
+		write_unlock_irqrestore(&devices_lock, flags);
+
+		cancel_delayed_work_sync(&dev->notify_peers);
+
+		/* bt_6lowpan_del_conn() is called with hci dev lock held which
+		 * means that we must delete the netdevice in worker thread.
+		 */
+		INIT_WORK(&entry->delete_netdev, delete_netdev);
+		schedule_work(&entry->delete_netdev);
+	} else {
+		write_unlock_irqrestore(&devices_lock, flags);
+	}
+
+	return err;
+}
+
+static int device_event(struct notifier_block *unused,
+			unsigned long event, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct lowpan_dev *entry, *tmp;
+	unsigned long flags;
+
+	if (netdev->type != ARPHRD_6LOWPAN)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_UNREGISTER:
+		write_lock_irqsave(&devices_lock, flags);
+		list_for_each_entry_safe(entry, tmp, &bt_6lowpan_devices,
+					 list) {
+			if (entry->netdev == netdev) {
+				list_del(&entry->list);
+				kfree(entry);
+				break;
+			}
+		}
+		write_unlock_irqrestore(&devices_lock, flags);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block bt_6lowpan_dev_notifier = {
+	.notifier_call = device_event,
+};
+
+int bt_6lowpan_init(void)
+{
+	return register_netdevice_notifier(&bt_6lowpan_dev_notifier);
+}
+
+void bt_6lowpan_cleanup(void)
+{
+	unregister_netdevice_notifier(&bt_6lowpan_dev_notifier);
+}
diff --git a/net/bluetooth/6lowpan.h b/net/bluetooth/6lowpan.h
new file mode 100644
index 00000000000..5d281f1eaf5
--- /dev/null
+++ b/net/bluetooth/6lowpan.h
@@ -0,0 +1,47 @@
+/*
+   Copyright (c) 2013 Intel Corp.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 2 and
+   only version 2 as published by the Free Software Foundation.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+*/
+
+#ifndef __6LOWPAN_H
+#define __6LOWPAN_H
+
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/bluetooth/l2cap.h>
+
+#if IS_ENABLED(CONFIG_BT_6LOWPAN)
+int bt_6lowpan_recv(struct l2cap_conn *conn, struct sk_buff *skb);
+int bt_6lowpan_add_conn(struct l2cap_conn *conn);
+int bt_6lowpan_del_conn(struct l2cap_conn *conn);
+int bt_6lowpan_init(void);
+void bt_6lowpan_cleanup(void);
+#else
+static int bt_6lowpan_recv(struct l2cap_conn *conn, struct sk_buff *skb)
+{
+	return -EOPNOTSUPP;
+}
+static int bt_6lowpan_add_conn(struct l2cap_conn *conn)
+{
+	return -EOPNOTSUPP;
+}
+int bt_6lowpan_del_conn(struct l2cap_conn *conn)
+{
+	return -EOPNOTSUPP;
+}
+static int bt_6lowpan_init(void)
+{
+	return -EOPNOTSUPP;
+}
+static void bt_6lowpan_cleanup(void) { }
+#endif
+
+#endif /* __6LOWPAN_H */
diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig
index d3f3f7b1d32..06ec14499ca 100644
--- a/net/bluetooth/Kconfig
+++ b/net/bluetooth/Kconfig
@@ -6,6 +6,7 @@ menuconfig BT
 	tristate "Bluetooth subsystem support"
 	depends on NET && !S390
 	depends on RFKILL || !RFKILL
+	select 6LOWPAN_IPHC if BT_6LOWPAN
 	select CRC16
 	select CRYPTO
 	select CRYPTO_BLKCIPHER
@@ -39,6 +40,12 @@ menuconfig BT
 	  to Bluetooth kernel modules are provided in the BlueZ packages.  For
 	  more information, see <http://www.bluez.org/>.
 
+config BT_6LOWPAN
+	bool "Bluetooth 6LoWPAN support"
+	depends on BT && IPV6
+	help
+	  IPv6 compression over Bluetooth.
+
 source "net/bluetooth/rfcomm/Kconfig"
 
 source "net/bluetooth/bnep/Kconfig"
diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile
index 6a791e73e39..ca51246b101 100644
--- a/net/bluetooth/Makefile
+++ b/net/bluetooth/Makefile
@@ -11,5 +11,6 @@ obj-$(CONFIG_BT_HIDP)	+= hidp/
 bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \
 	hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o sco.o lib.o \
 	a2mp.o amp.o
+bluetooth-$(CONFIG_BT_6LOWPAN) += 6lowpan.o
 
 subdir-ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index efcd108822c..9514cc9e850 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -162,7 +162,7 @@ static int a2mp_discover_req(struct amp_mgr *mgr, struct sk_buff *skb,
 		return -ENOMEM;
 	}
 
-	rsp->mtu = __constant_cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU);
+	rsp->mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU);
 	rsp->ext_feat = 0;
 
 	__a2mp_add_cl(mgr, rsp->cl);
@@ -235,7 +235,7 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 			BT_DBG("chan %p state %s", chan,
 			       state_to_string(chan->state));
 
-			if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP)
+			if (chan->scid == L2CAP_CID_A2MP)
 				continue;
 
 			l2cap_chan_lock(chan);
@@ -649,7 +649,7 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
 	if (err) {
 		struct a2mp_cmd_rej rej;
 
-		rej.reason = __constant_cpu_to_le16(0);
+		rej.reason = cpu_to_le16(0);
 		hdr = (void *) skb->data;
 
 		BT_DBG("Send A2MP Rej: cmd 0x%2.2x err %d", hdr->code, err);
@@ -695,7 +695,13 @@ static void a2mp_chan_state_change_cb(struct l2cap_chan *chan, int state,
 static struct sk_buff *a2mp_chan_alloc_skb_cb(struct l2cap_chan *chan,
 					      unsigned long len, int nb)
 {
-	return bt_skb_alloc(len, GFP_KERNEL);
+	struct sk_buff *skb;
+
+	skb = bt_skb_alloc(len, GFP_KERNEL);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	return skb;
 }
 
 static struct l2cap_ops a2mp_chan_ops = {
@@ -726,7 +732,11 @@ static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked)
 
 	BT_DBG("chan %p", chan);
 
-	chan->chan_type = L2CAP_CHAN_CONN_FIX_A2MP;
+	chan->chan_type = L2CAP_CHAN_FIXED;
+	chan->scid = L2CAP_CID_A2MP;
+	chan->dcid = L2CAP_CID_A2MP;
+	chan->omtu = L2CAP_A2MP_DEFAULT_MTU;
+	chan->imtu = L2CAP_A2MP_DEFAULT_MTU;
 	chan->flush_to = L2CAP_DEFAULT_FLUSH_TO;
 
 	chan->ops = &a2mp_chan_ops;
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 56ca494621c..2021c481cdb 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -31,7 +31,7 @@
 #include <net/bluetooth/bluetooth.h>
 #include <linux/proc_fs.h>
 
-#define VERSION "2.17"
+#define VERSION "2.19"
 
 /* Bluetooth sockets */
 #define BT_MAX_PROTO	8
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index ba5366c320d..a7a27bc2c0b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -28,6 +28,7 @@
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/l2cap.h>
 
 #include "smp.h"
 #include "a2mp.h"
@@ -82,7 +83,7 @@ static void hci_acl_create_connection(struct hci_conn *conn)
 			cp.pscan_rep_mode = ie->data.pscan_rep_mode;
 			cp.pscan_mode     = ie->data.pscan_mode;
 			cp.clock_offset   = ie->data.clock_offset |
-					    __constant_cpu_to_le16(0x8000);
+					    cpu_to_le16(0x8000);
 		}
 
 		memcpy(conn->dev_class, ie->data.dev_class, 3);
@@ -182,8 +183,8 @@ bool hci_setup_sync(struct hci_conn *conn, __u16 handle)
 
 	cp.handle   = cpu_to_le16(handle);
 
-	cp.tx_bandwidth   = __constant_cpu_to_le32(0x00001f40);
-	cp.rx_bandwidth   = __constant_cpu_to_le32(0x00001f40);
+	cp.tx_bandwidth   = cpu_to_le32(0x00001f40);
+	cp.rx_bandwidth   = cpu_to_le32(0x00001f40);
 	cp.voice_setting  = cpu_to_le16(conn->setting);
 
 	switch (conn->setting & SCO_AIRMODE_MASK) {
@@ -225,13 +226,13 @@ void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max,
 	cp.conn_interval_max	= cpu_to_le16(max);
 	cp.conn_latency		= cpu_to_le16(latency);
 	cp.supervision_timeout	= cpu_to_le16(to_multiplier);
-	cp.min_ce_len		= __constant_cpu_to_le16(0x0001);
-	cp.max_ce_len		= __constant_cpu_to_le16(0x0001);
+	cp.min_ce_len		= cpu_to_le16(0x0000);
+	cp.max_ce_len		= cpu_to_le16(0x0000);
 
 	hci_send_cmd(hdev, HCI_OP_LE_CONN_UPDATE, sizeof(cp), &cp);
 }
 
-void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8],
+void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand,
 		      __u8 ltk[16])
 {
 	struct hci_dev *hdev = conn->hdev;
@@ -242,9 +243,9 @@ void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8],
 	memset(&cp, 0, sizeof(cp));
 
 	cp.handle = cpu_to_le16(conn->handle);
-	memcpy(cp.ltk, ltk, sizeof(cp.ltk));
+	cp.rand = rand;
 	cp.ediv = ediv;
-	memcpy(cp.rand, rand, sizeof(cp.rand));
+	memcpy(cp.ltk, ltk, sizeof(cp.ltk));
 
 	hci_send_cmd(hdev, HCI_OP_LE_START_ENC, sizeof(cp), &cp);
 }
@@ -288,10 +289,20 @@ static void hci_conn_timeout(struct work_struct *work)
 {
 	struct hci_conn *conn = container_of(work, struct hci_conn,
 					     disc_work.work);
+	int refcnt = atomic_read(&conn->refcnt);
 
 	BT_DBG("hcon %p state %s", conn, state_to_string(conn->state));
 
-	if (atomic_read(&conn->refcnt))
+	WARN_ON(refcnt < 0);
+
+	/* FIXME: It was observed that in pairing failed scenario, refcnt
+	 * drops below 0. Probably this is because l2cap_conn_del calls
+	 * l2cap_chan_del for each channel, and inside l2cap_chan_del conn is
+	 * dropped. After that loop hci_chan_del is called which also drops
+	 * conn. For now make sure that ACL is alive if refcnt is higher then 0,
+	 * otherwise drop it.
+	 */
+	if (refcnt > 0)
 		return;
 
 	switch (conn->state) {
@@ -337,9 +348,9 @@ static void hci_conn_idle(struct work_struct *work)
 	if (lmp_sniffsubr_capable(hdev) && lmp_sniffsubr_capable(conn)) {
 		struct hci_cp_sniff_subrate cp;
 		cp.handle             = cpu_to_le16(conn->handle);
-		cp.max_latency        = __constant_cpu_to_le16(0);
-		cp.min_remote_timeout = __constant_cpu_to_le16(0);
-		cp.min_local_timeout  = __constant_cpu_to_le16(0);
+		cp.max_latency        = cpu_to_le16(0);
+		cp.min_remote_timeout = cpu_to_le16(0);
+		cp.min_local_timeout  = cpu_to_le16(0);
 		hci_send_cmd(hdev, HCI_OP_SNIFF_SUBRATE, sizeof(cp), &cp);
 	}
 
@@ -348,8 +359,8 @@ static void hci_conn_idle(struct work_struct *work)
 		cp.handle       = cpu_to_le16(conn->handle);
 		cp.max_interval = cpu_to_le16(hdev->sniff_max_interval);
 		cp.min_interval = cpu_to_le16(hdev->sniff_min_interval);
-		cp.attempt      = __constant_cpu_to_le16(4);
-		cp.timeout      = __constant_cpu_to_le16(1);
+		cp.attempt      = cpu_to_le16(4);
+		cp.timeout      = cpu_to_le16(1);
 		hci_send_cmd(hdev, HCI_OP_SNIFF_MODE, sizeof(cp), &cp);
 	}
 }
@@ -363,6 +374,30 @@ static void hci_conn_auto_accept(struct work_struct *work)
 		     &conn->dst);
 }
 
+static void le_conn_timeout(struct work_struct *work)
+{
+	struct hci_conn *conn = container_of(work, struct hci_conn,
+					     le_conn_timeout.work);
+	struct hci_dev *hdev = conn->hdev;
+
+	BT_DBG("");
+
+	/* We could end up here due to having done directed advertising,
+	 * so clean up the state if necessary. This should however only
+	 * happen with broken hardware or if low duty cycle was used
+	 * (which doesn't have a timeout of its own).
+	 */
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
+		u8 enable = 0x00;
+		hci_send_cmd(hdev, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable),
+			     &enable);
+		hci_le_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT);
+		return;
+	}
+
+	hci_le_create_connection_cancel(conn);
+}
+
 struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
 {
 	struct hci_conn *conn;
@@ -383,6 +418,8 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
 	conn->io_capability = hdev->io_capability;
 	conn->remote_auth = 0xff;
 	conn->key_type = 0xff;
+	conn->tx_power = HCI_TX_POWER_INVALID;
+	conn->max_tx_power = HCI_TX_POWER_INVALID;
 
 	set_bit(HCI_CONN_POWER_SAVE, &conn->flags);
 	conn->disc_timeout = HCI_DISCONN_TIMEOUT;
@@ -391,6 +428,10 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
 	case ACL_LINK:
 		conn->pkt_type = hdev->pkt_type & ACL_PTYPE_MASK;
 		break;
+	case LE_LINK:
+		/* conn->src should reflect the local identity address */
+		hci_copy_identity_address(hdev, &conn->src, &conn->src_type);
+		break;
 	case SCO_LINK:
 		if (lmp_esco_capable(hdev))
 			conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) |
@@ -410,6 +451,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
 	INIT_DELAYED_WORK(&conn->disc_work, hci_conn_timeout);
 	INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept);
 	INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle);
+	INIT_DELAYED_WORK(&conn->le_conn_timeout, le_conn_timeout);
 
 	atomic_set(&conn->refcnt, 0);
 
@@ -442,6 +484,8 @@ int hci_conn_del(struct hci_conn *conn)
 		/* Unacked frames */
 		hdev->acl_cnt += conn->sent;
 	} else if (conn->type == LE_LINK) {
+		cancel_delayed_work_sync(&conn->le_conn_timeout);
+
 		if (hdev->le_pkts)
 			hdev->le_cnt += conn->sent;
 		else
@@ -514,6 +558,31 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src)
 }
 EXPORT_SYMBOL(hci_get_route);
 
+/* This function requires the caller holds hdev->lock */
+void hci_le_conn_failed(struct hci_conn *conn, u8 status)
+{
+	struct hci_dev *hdev = conn->hdev;
+
+	conn->state = BT_CLOSED;
+
+	mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type,
+			    status);
+
+	hci_proto_connect_cfm(conn, status);
+
+	hci_conn_del(conn);
+
+	/* Since we may have temporarily stopped the background scanning in
+	 * favor of connection establishment, we should restart it.
+	 */
+	hci_update_background_scan(hdev);
+
+	/* Re-enable advertising in case this was a failed connection
+	 * attempt as a peripheral.
+	 */
+	mgmt_reenable_advertising(hdev);
+}
+
 static void create_le_conn_complete(struct hci_dev *hdev, u8 status)
 {
 	struct hci_conn *conn;
@@ -530,60 +599,91 @@ static void create_le_conn_complete(struct hci_dev *hdev, u8 status)
 	if (!conn)
 		goto done;
 
-	conn->state = BT_CLOSED;
-
-	mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type,
-			    status);
-
-	hci_proto_connect_cfm(conn, status);
-
-	hci_conn_del(conn);
+	hci_le_conn_failed(conn, status);
 
 done:
 	hci_dev_unlock(hdev);
 }
 
-static int hci_create_le_conn(struct hci_conn *conn)
+static void hci_req_add_le_create_conn(struct hci_request *req,
+				       struct hci_conn *conn)
 {
-	struct hci_dev *hdev = conn->hdev;
 	struct hci_cp_le_create_conn cp;
-	struct hci_request req;
-	int err;
-
-	hci_req_init(&req, hdev);
+	struct hci_dev *hdev = conn->hdev;
+	u8 own_addr_type;
 
 	memset(&cp, 0, sizeof(cp));
+
+	/* Update random address, but set require_privacy to false so
+	 * that we never connect with an unresolvable address.
+	 */
+	if (hci_update_random_address(req, false, &own_addr_type))
+		return;
+
 	cp.scan_interval = cpu_to_le16(hdev->le_scan_interval);
 	cp.scan_window = cpu_to_le16(hdev->le_scan_window);
 	bacpy(&cp.peer_addr, &conn->dst);
 	cp.peer_addr_type = conn->dst_type;
-	cp.own_address_type = conn->src_type;
-	cp.conn_interval_min = cpu_to_le16(hdev->le_conn_min_interval);
-	cp.conn_interval_max = cpu_to_le16(hdev->le_conn_max_interval);
-	cp.supervision_timeout = __constant_cpu_to_le16(0x002a);
-	cp.min_ce_len = __constant_cpu_to_le16(0x0000);
-	cp.max_ce_len = __constant_cpu_to_le16(0x0000);
+	cp.own_address_type = own_addr_type;
+	cp.conn_interval_min = cpu_to_le16(conn->le_conn_min_interval);
+	cp.conn_interval_max = cpu_to_le16(conn->le_conn_max_interval);
+	cp.supervision_timeout = cpu_to_le16(0x002a);
+	cp.min_ce_len = cpu_to_le16(0x0000);
+	cp.max_ce_len = cpu_to_le16(0x0000);
 
-	hci_req_add(&req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp);
+	hci_req_add(req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp);
 
-	err = hci_req_run(&req, create_le_conn_complete);
-	if (err) {
-		hci_conn_del(conn);
-		return err;
-	}
+	conn->state = BT_CONNECT;
+}
 
-	return 0;
+static void hci_req_directed_advertising(struct hci_request *req,
+					 struct hci_conn *conn)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_cp_le_set_adv_param cp;
+	u8 own_addr_type;
+	u8 enable;
+
+	enable = 0x00;
+	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
+
+	/* Clear the HCI_ADVERTISING bit temporarily so that the
+	 * hci_update_random_address knows that it's safe to go ahead
+	 * and write a new random address. The flag will be set back on
+	 * as soon as the SET_ADV_ENABLE HCI command completes.
+	 */
+	clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
+
+	/* Set require_privacy to false so that the remote device has a
+	 * chance of identifying us.
+	 */
+	if (hci_update_random_address(req, false, &own_addr_type) < 0)
+		return;
+
+	memset(&cp, 0, sizeof(cp));
+	cp.type = LE_ADV_DIRECT_IND;
+	cp.own_address_type = own_addr_type;
+	cp.direct_addr_type = conn->dst_type;
+	bacpy(&cp.direct_addr, &conn->dst);
+	cp.channel_map = hdev->le_adv_channel_map;
+
+	hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp);
+
+	enable = 0x01;
+	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
+
+	conn->state = BT_CONNECT;
 }
 
-static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
-				    u8 dst_type, u8 sec_level, u8 auth_type)
+struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
+				u8 dst_type, u8 sec_level, u8 auth_type)
 {
+	struct hci_conn_params *params;
 	struct hci_conn *conn;
+	struct smp_irk *irk;
+	struct hci_request req;
 	int err;
 
-	if (test_bit(HCI_ADVERTISING, &hdev->flags))
-		return ERR_PTR(-ENOTSUPP);
-
 	/* Some devices send ATT messages as soon as the physical link is
 	 * established. To be able to handle these ATT messages, the user-
 	 * space first establishes the connection and then starts the pairing
@@ -607,35 +707,80 @@ static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	if (conn)
 		return ERR_PTR(-EBUSY);
 
+	/* When given an identity address with existing identity
+	 * resolving key, the connection needs to be established
+	 * to a resolvable random address.
+	 *
+	 * This uses the cached random resolvable address from
+	 * a previous scan. When no cached address is available,
+	 * try connecting to the identity address instead.
+	 *
+	 * Storing the resolvable random address is required here
+	 * to handle connection failures. The address will later
+	 * be resolved back into the original identity address
+	 * from the connect request.
+	 */
+	irk = hci_find_irk_by_addr(hdev, dst, dst_type);
+	if (irk && bacmp(&irk->rpa, BDADDR_ANY)) {
+		dst = &irk->rpa;
+		dst_type = ADDR_LE_DEV_RANDOM;
+	}
+
 	conn = hci_conn_add(hdev, LE_LINK, dst);
 	if (!conn)
 		return ERR_PTR(-ENOMEM);
 
-	if (dst_type == BDADDR_LE_PUBLIC)
-		conn->dst_type = ADDR_LE_DEV_PUBLIC;
-	else
-		conn->dst_type = ADDR_LE_DEV_RANDOM;
+	conn->dst_type = dst_type;
+	conn->sec_level = BT_SECURITY_LOW;
+	conn->pending_sec_level = sec_level;
+	conn->auth_type = auth_type;
 
-	conn->src_type = hdev->own_addr_type;
+	hci_req_init(&req, hdev);
+
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
+		hci_req_directed_advertising(&req, conn);
+		goto create_conn;
+	}
 
-	conn->state = BT_CONNECT;
 	conn->out = true;
 	conn->link_mode |= HCI_LM_MASTER;
-	conn->sec_level = BT_SECURITY_LOW;
-	conn->pending_sec_level = sec_level;
-	conn->auth_type = auth_type;
 
-	err = hci_create_le_conn(conn);
-	if (err)
+	params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type);
+	if (params) {
+		conn->le_conn_min_interval = params->conn_min_interval;
+		conn->le_conn_max_interval = params->conn_max_interval;
+	} else {
+		conn->le_conn_min_interval = hdev->le_conn_min_interval;
+		conn->le_conn_max_interval = hdev->le_conn_max_interval;
+	}
+
+	/* If controller is scanning, we stop it since some controllers are
+	 * not able to scan and connect at the same time. Also set the
+	 * HCI_LE_SCAN_INTERRUPTED flag so that the command complete
+	 * handler for scan disabling knows to set the correct discovery
+	 * state.
+	 */
+	if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) {
+		hci_req_add_le_scan_disable(&req);
+		set_bit(HCI_LE_SCAN_INTERRUPTED, &hdev->dev_flags);
+	}
+
+	hci_req_add_le_create_conn(&req, conn);
+
+create_conn:
+	err = hci_req_run(&req, create_le_conn_complete);
+	if (err) {
+		hci_conn_del(conn);
 		return ERR_PTR(err);
+	}
 
 done:
 	hci_conn_hold(conn);
 	return conn;
 }
 
-static struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
-						u8 sec_level, u8 auth_type)
+struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
+				 u8 sec_level, u8 auth_type)
 {
 	struct hci_conn *acl;
 
@@ -704,27 +849,22 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst,
 	return sco;
 }
 
-/* Create SCO, ACL or LE connection. */
-struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst,
-			     __u8 dst_type, __u8 sec_level, __u8 auth_type)
-{
-	BT_DBG("%s dst %pMR type 0x%x", hdev->name, dst, type);
-
-	switch (type) {
-	case LE_LINK:
-		return hci_connect_le(hdev, dst, dst_type, sec_level, auth_type);
-	case ACL_LINK:
-		return hci_connect_acl(hdev, dst, sec_level, auth_type);
-	}
-
-	return ERR_PTR(-EINVAL);
-}
-
 /* Check link security requirement */
 int hci_conn_check_link_mode(struct hci_conn *conn)
 {
 	BT_DBG("hcon %p", conn);
 
+	/* In Secure Connections Only mode, it is required that Secure
+	 * Connections is used and the link is encrypted with AES-CCM
+	 * using a P-256 authenticated combination key.
+	 */
+	if (test_bit(HCI_SC_ONLY, &conn->hdev->flags)) {
+		if (!hci_conn_sc_enabled(conn) ||
+		    !test_bit(HCI_CONN_AES_CCM, &conn->flags) ||
+		    conn->key_type != HCI_LK_AUTH_COMBINATION_P256)
+			return 0;
+	}
+
 	if (hci_conn_ssp_enabled(conn) && !(conn->link_mode & HCI_LM_ENCRYPT))
 		return 0;
 
@@ -752,14 +892,17 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 	if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
 		struct hci_cp_auth_requested cp;
 
-		/* encrypt must be pending if auth is also pending */
-		set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
-
 		cp.handle = cpu_to_le16(conn->handle);
 		hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED,
 			     sizeof(cp), &cp);
-		if (conn->key_type != 0xff)
+
+		/* If we're already encrypted set the REAUTH_PEND flag,
+		 * otherwise set the ENCRYPT_PEND.
+		 */
+		if (conn->link_mode & HCI_LM_ENCRYPT)
 			set_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
+		else
+			set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
 	}
 
 	return 0;
@@ -800,14 +943,23 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 	if (!(conn->link_mode & HCI_LM_AUTH))
 		goto auth;
 
-	/* An authenticated combination key has sufficient security for any
-	   security level. */
-	if (conn->key_type == HCI_LK_AUTH_COMBINATION)
+	/* An authenticated FIPS approved combination key has sufficient
+	 * security for security level 4. */
+	if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256 &&
+	    sec_level == BT_SECURITY_FIPS)
+		goto encrypt;
+
+	/* An authenticated combination key has sufficient security for
+	   security level 3. */
+	if ((conn->key_type == HCI_LK_AUTH_COMBINATION_P192 ||
+	     conn->key_type == HCI_LK_AUTH_COMBINATION_P256) &&
+	    sec_level == BT_SECURITY_HIGH)
 		goto encrypt;
 
 	/* An unauthenticated combination key has sufficient security for
 	   security level 1 and 2. */
-	if (conn->key_type == HCI_LK_UNAUTH_COMBINATION &&
+	if ((conn->key_type == HCI_LK_UNAUTH_COMBINATION_P192 ||
+	     conn->key_type == HCI_LK_UNAUTH_COMBINATION_P256) &&
 	    (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW))
 		goto encrypt;
 
@@ -816,7 +968,8 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 	   is generated using maximum PIN code length (16).
 	   For pre 2.1 units. */
 	if (conn->key_type == HCI_LK_COMBINATION &&
-	    (sec_level != BT_SECURITY_HIGH || conn->pin_length == 16))
+	    (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW ||
+	     conn->pin_length == 16))
 		goto encrypt;
 
 auth:
@@ -840,13 +993,17 @@ int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level)
 {
 	BT_DBG("hcon %p", conn);
 
-	if (sec_level != BT_SECURITY_HIGH)
-		return 1; /* Accept if non-secure is required */
+	/* Accept if non-secure or higher security level is required */
+	if (sec_level != BT_SECURITY_HIGH && sec_level != BT_SECURITY_FIPS)
+		return 1;
 
-	if (conn->sec_level == BT_SECURITY_HIGH)
+	/* Accept if secure or higher security level is already present */
+	if (conn->sec_level == BT_SECURITY_HIGH ||
+	    conn->sec_level == BT_SECURITY_FIPS)
 		return 1;
 
-	return 0; /* Reject not secure link */
+	/* Reject not secure link */
+	return 0;
 }
 EXPORT_SYMBOL(hci_conn_check_secure);
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 6ccc4eb9e55..0a43cce9a91 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -29,10 +29,14 @@
 #include <linux/idr.h>
 #include <linux/rfkill.h>
 #include <linux/debugfs.h>
+#include <linux/crypto.h>
 #include <asm/unaligned.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/l2cap.h>
+
+#include "smp.h"
 
 static void hci_rx_work(struct work_struct *work);
 static void hci_cmd_work(struct work_struct *work);
@@ -285,24 +289,6 @@ static const struct file_operations link_keys_fops = {
 	.release	= single_release,
 };
 
-static ssize_t use_debug_keys_read(struct file *file, char __user *user_buf,
-				   size_t count, loff_t *ppos)
-{
-	struct hci_dev *hdev = file->private_data;
-	char buf[3];
-
-	buf[0] = test_bit(HCI_DEBUG_KEYS, &hdev->dev_flags) ? 'Y': 'N';
-	buf[1] = '\n';
-	buf[2] = '\0';
-	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
-}
-
-static const struct file_operations use_debug_keys_fops = {
-	.open		= simple_open,
-	.read		= use_debug_keys_read,
-	.llseek		= default_llseek,
-};
-
 static int dev_class_show(struct seq_file *f, void *ptr)
 {
 	struct hci_dev *hdev = f->private;
@@ -415,6 +401,70 @@ static int ssp_debug_mode_get(void *data, u64 *val)
 DEFINE_SIMPLE_ATTRIBUTE(ssp_debug_mode_fops, ssp_debug_mode_get,
 			ssp_debug_mode_set, "%llu\n");
 
+static ssize_t force_sc_support_read(struct file *file, char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[3];
+
+	buf[0] = test_bit(HCI_FORCE_SC, &hdev->dev_flags) ? 'Y': 'N';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t force_sc_support_write(struct file *file,
+				      const char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[32];
+	size_t buf_size = min(count, (sizeof(buf)-1));
+	bool enable;
+
+	if (test_bit(HCI_UP, &hdev->flags))
+		return -EBUSY;
+
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+	if (strtobool(buf, &enable))
+		return -EINVAL;
+
+	if (enable == test_bit(HCI_FORCE_SC, &hdev->dev_flags))
+		return -EALREADY;
+
+	change_bit(HCI_FORCE_SC, &hdev->dev_flags);
+
+	return count;
+}
+
+static const struct file_operations force_sc_support_fops = {
+	.open		= simple_open,
+	.read		= force_sc_support_read,
+	.write		= force_sc_support_write,
+	.llseek		= default_llseek,
+};
+
+static ssize_t sc_only_mode_read(struct file *file, char __user *user_buf,
+				 size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[3];
+
+	buf[0] = test_bit(HCI_SC_ONLY, &hdev->dev_flags) ? 'Y': 'N';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static const struct file_operations sc_only_mode_fops = {
+	.open		= simple_open,
+	.read		= sc_only_mode_read,
+	.llseek		= default_llseek,
+};
+
 static int idle_timeout_set(void *data, u64 val)
 {
 	struct hci_dev *hdev = data;
@@ -443,6 +493,37 @@ static int idle_timeout_get(void *data, u64 *val)
 DEFINE_SIMPLE_ATTRIBUTE(idle_timeout_fops, idle_timeout_get,
 			idle_timeout_set, "%llu\n");
 
+static int rpa_timeout_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	/* Require the RPA timeout to be at least 30 seconds and at most
+	 * 24 hours.
+	 */
+	if (val < 30 || val > (60 * 60 * 24))
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->rpa_timeout = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int rpa_timeout_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->rpa_timeout;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(rpa_timeout_fops, rpa_timeout_get,
+			rpa_timeout_set, "%llu\n");
+
 static int sniff_min_interval_set(void *data, u64 val)
 {
 	struct hci_dev *hdev = data;
@@ -499,6 +580,115 @@ static int sniff_max_interval_get(void *data, u64 *val)
 DEFINE_SIMPLE_ATTRIBUTE(sniff_max_interval_fops, sniff_max_interval_get,
 			sniff_max_interval_set, "%llu\n");
 
+static int conn_info_min_age_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val == 0 || val > hdev->conn_info_max_age)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->conn_info_min_age = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int conn_info_min_age_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->conn_info_min_age;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(conn_info_min_age_fops, conn_info_min_age_get,
+			conn_info_min_age_set, "%llu\n");
+
+static int conn_info_max_age_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val == 0 || val < hdev->conn_info_min_age)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->conn_info_max_age = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int conn_info_max_age_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->conn_info_max_age;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(conn_info_max_age_fops, conn_info_max_age_get,
+			conn_info_max_age_set, "%llu\n");
+
+static int identity_show(struct seq_file *f, void *p)
+{
+	struct hci_dev *hdev = f->private;
+	bdaddr_t addr;
+	u8 addr_type;
+
+	hci_dev_lock(hdev);
+
+	hci_copy_identity_address(hdev, &addr, &addr_type);
+
+	seq_printf(f, "%pMR (type %u) %*phN %pMR\n", &addr, addr_type,
+		   16, hdev->irk, &hdev->rpa);
+
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int identity_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, identity_show, inode->i_private);
+}
+
+static const struct file_operations identity_fops = {
+	.open		= identity_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int random_address_show(struct seq_file *f, void *p)
+{
+	struct hci_dev *hdev = f->private;
+
+	hci_dev_lock(hdev);
+	seq_printf(f, "%pMR\n", &hdev->random_addr);
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int random_address_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, random_address_show, inode->i_private);
+}
+
+static const struct file_operations random_address_fops = {
+	.open		= random_address_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static int static_address_show(struct seq_file *f, void *p)
 {
 	struct hci_dev *hdev = f->private;
@@ -522,33 +712,107 @@ static const struct file_operations static_address_fops = {
 	.release	= single_release,
 };
 
-static int own_address_type_set(void *data, u64 val)
+static ssize_t force_static_address_read(struct file *file,
+					 char __user *user_buf,
+					 size_t count, loff_t *ppos)
 {
-	struct hci_dev *hdev = data;
+	struct hci_dev *hdev = file->private_data;
+	char buf[3];
 
-	if (val != 0 && val != 1)
+	buf[0] = test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) ? 'Y': 'N';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t force_static_address_write(struct file *file,
+					  const char __user *user_buf,
+					  size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[32];
+	size_t buf_size = min(count, (sizeof(buf)-1));
+	bool enable;
+
+	if (test_bit(HCI_UP, &hdev->flags))
+		return -EBUSY;
+
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+	if (strtobool(buf, &enable))
 		return -EINVAL;
 
+	if (enable == test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags))
+		return -EALREADY;
+
+	change_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags);
+
+	return count;
+}
+
+static const struct file_operations force_static_address_fops = {
+	.open		= simple_open,
+	.read		= force_static_address_read,
+	.write		= force_static_address_write,
+	.llseek		= default_llseek,
+};
+
+static int white_list_show(struct seq_file *f, void *ptr)
+{
+	struct hci_dev *hdev = f->private;
+	struct bdaddr_list *b;
+
 	hci_dev_lock(hdev);
-	hdev->own_addr_type = val;
+	list_for_each_entry(b, &hdev->le_white_list, list)
+		seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type);
 	hci_dev_unlock(hdev);
 
 	return 0;
 }
 
-static int own_address_type_get(void *data, u64 *val)
+static int white_list_open(struct inode *inode, struct file *file)
 {
-	struct hci_dev *hdev = data;
+	return single_open(file, white_list_show, inode->i_private);
+}
+
+static const struct file_operations white_list_fops = {
+	.open		= white_list_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int identity_resolving_keys_show(struct seq_file *f, void *ptr)
+{
+	struct hci_dev *hdev = f->private;
+	struct list_head *p, *n;
 
 	hci_dev_lock(hdev);
-	*val = hdev->own_addr_type;
+	list_for_each_safe(p, n, &hdev->identity_resolving_keys) {
+		struct smp_irk *irk = list_entry(p, struct smp_irk, list);
+		seq_printf(f, "%pMR (type %u) %*phN %pMR\n",
+			   &irk->bdaddr, irk->addr_type,
+			   16, irk->val, &irk->rpa);
+	}
 	hci_dev_unlock(hdev);
 
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(own_address_type_fops, own_address_type_get,
-			own_address_type_set, "%llu\n");
+static int identity_resolving_keys_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, identity_resolving_keys_show,
+			   inode->i_private);
+}
+
+static const struct file_operations identity_resolving_keys_fops = {
+	.open		= identity_resolving_keys_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
 
 static int long_term_keys_show(struct seq_file *f, void *ptr)
 {
@@ -556,12 +820,12 @@ static int long_term_keys_show(struct seq_file *f, void *ptr)
 	struct list_head *p, *n;
 
 	hci_dev_lock(hdev);
-	list_for_each_safe(p, n, &hdev->link_keys) {
+	list_for_each_safe(p, n, &hdev->long_term_keys) {
 		struct smp_ltk *ltk = list_entry(p, struct smp_ltk, list);
-		seq_printf(f, "%pMR (type %u) %u %u %u %.4x %*phN %*phN\\n",
+		seq_printf(f, "%pMR (type %u) %u 0x%02x %u %.4x %.16llx %*phN\n",
 			   &ltk->bdaddr, ltk->bdaddr_type, ltk->authenticated,
 			   ltk->type, ltk->enc_size, __le16_to_cpu(ltk->ediv),
-			   8, ltk->rand, 16, ltk->val);
+			   __le64_to_cpu(ltk->rand), 16, ltk->val);
 	}
 	hci_dev_unlock(hdev);
 
@@ -636,6 +900,181 @@ static int conn_max_interval_get(void *data, u64 *val)
 DEFINE_SIMPLE_ATTRIBUTE(conn_max_interval_fops, conn_max_interval_get,
 			conn_max_interval_set, "%llu\n");
 
+static int adv_channel_map_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val < 0x01 || val > 0x07)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->le_adv_channel_map = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int adv_channel_map_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->le_adv_channel_map;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(adv_channel_map_fops, adv_channel_map_get,
+			adv_channel_map_set, "%llu\n");
+
+static ssize_t lowpan_read(struct file *file, char __user *user_buf,
+			   size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[3];
+
+	buf[0] = test_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags) ? 'Y' : 'N';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t lowpan_write(struct file *fp, const char __user *user_buffer,
+			    size_t count, loff_t *position)
+{
+	struct hci_dev *hdev = fp->private_data;
+	bool enable;
+	char buf[32];
+	size_t buf_size = min(count, (sizeof(buf)-1));
+
+	if (copy_from_user(buf, user_buffer, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+
+	if (strtobool(buf, &enable) < 0)
+		return -EINVAL;
+
+	if (enable == test_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags))
+		return -EALREADY;
+
+	change_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags);
+
+	return count;
+}
+
+static const struct file_operations lowpan_debugfs_fops = {
+	.open		= simple_open,
+	.read		= lowpan_read,
+	.write		= lowpan_write,
+	.llseek		= default_llseek,
+};
+
+static int le_auto_conn_show(struct seq_file *sf, void *ptr)
+{
+	struct hci_dev *hdev = sf->private;
+	struct hci_conn_params *p;
+
+	hci_dev_lock(hdev);
+
+	list_for_each_entry(p, &hdev->le_conn_params, list) {
+		seq_printf(sf, "%pMR %u %u\n", &p->addr, p->addr_type,
+			   p->auto_connect);
+	}
+
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int le_auto_conn_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, le_auto_conn_show, inode->i_private);
+}
+
+static ssize_t le_auto_conn_write(struct file *file, const char __user *data,
+				  size_t count, loff_t *offset)
+{
+	struct seq_file *sf = file->private_data;
+	struct hci_dev *hdev = sf->private;
+	u8 auto_connect = 0;
+	bdaddr_t addr;
+	u8 addr_type;
+	char *buf;
+	int err = 0;
+	int n;
+
+	/* Don't allow partial write */
+	if (*offset != 0)
+		return -EINVAL;
+
+	if (count < 3)
+		return -EINVAL;
+
+	buf = memdup_user(data, count);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
+	if (memcmp(buf, "add", 3) == 0) {
+		n = sscanf(&buf[4], "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu %hhu",
+			   &addr.b[5], &addr.b[4], &addr.b[3], &addr.b[2],
+			   &addr.b[1], &addr.b[0], &addr_type,
+			   &auto_connect);
+
+		if (n < 7) {
+			err = -EINVAL;
+			goto done;
+		}
+
+		hci_dev_lock(hdev);
+		err = hci_conn_params_add(hdev, &addr, addr_type, auto_connect,
+					  hdev->le_conn_min_interval,
+					  hdev->le_conn_max_interval);
+		hci_dev_unlock(hdev);
+
+		if (err)
+			goto done;
+	} else if (memcmp(buf, "del", 3) == 0) {
+		n = sscanf(&buf[4], "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu",
+			   &addr.b[5], &addr.b[4], &addr.b[3], &addr.b[2],
+			   &addr.b[1], &addr.b[0], &addr_type);
+
+		if (n < 7) {
+			err = -EINVAL;
+			goto done;
+		}
+
+		hci_dev_lock(hdev);
+		hci_conn_params_del(hdev, &addr, addr_type);
+		hci_dev_unlock(hdev);
+	} else if (memcmp(buf, "clr", 3) == 0) {
+		hci_dev_lock(hdev);
+		hci_conn_params_clear(hdev);
+		hci_pend_le_conns_clear(hdev);
+		hci_update_background_scan(hdev);
+		hci_dev_unlock(hdev);
+	} else {
+		err = -EINVAL;
+	}
+
+done:
+	kfree(buf);
+
+	if (err)
+		return err;
+	else
+		return count;
+}
+
+static const struct file_operations le_auto_conn_fops = {
+	.open		= le_auto_conn_open,
+	.read		= seq_read,
+	.write		= le_auto_conn_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 /* ---- HCI requests ---- */
 
 static void hci_req_sync_complete(struct hci_dev *hdev, u8 result)
@@ -962,7 +1401,7 @@ static void bredr_setup(struct hci_request *req)
 	hci_req_add(req, HCI_OP_SET_EVENT_FLT, 1, &flt_type);
 
 	/* Connection accept timeout ~20 secs */
-	param = __constant_cpu_to_le16(0x7d00);
+	param = cpu_to_le16(0x7d00);
 	hci_req_add(req, HCI_OP_WRITE_CA_TIMEOUT, 2, &param);
 
 	/* AVM Berlin (31), aka "BlueFRITZ!", reports version 1.2,
@@ -984,14 +1423,17 @@ static void le_setup(struct hci_request *req)
 	/* Read LE Local Supported Features */
 	hci_req_add(req, HCI_OP_LE_READ_LOCAL_FEATURES, 0, NULL);
 
+	/* Read LE Supported States */
+	hci_req_add(req, HCI_OP_LE_READ_SUPPORTED_STATES, 0, NULL);
+
 	/* Read LE Advertising Channel TX Power */
 	hci_req_add(req, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL);
 
 	/* Read LE White List Size */
 	hci_req_add(req, HCI_OP_LE_READ_WHITE_LIST_SIZE, 0, NULL);
 
-	/* Read LE Supported States */
-	hci_req_add(req, HCI_OP_LE_READ_SUPPORTED_STATES, 0, NULL);
+	/* Clear LE White List */
+	hci_req_add(req, HCI_OP_LE_CLEAR_WHITE_LIST, 0, NULL);
 
 	/* LE-only controllers have LE implicitly enabled */
 	if (!lmp_bredr_capable(hdev))
@@ -1228,7 +1670,7 @@ static void hci_set_event_mask_page_2(struct hci_request *req)
 	/* If Connectionless Slave Broadcast master role is supported
 	 * enable all necessary events for it.
 	 */
-	if (hdev->features[2][0] & 0x01) {
+	if (lmp_csb_master_capable(hdev)) {
 		events[1] |= 0x40;	/* Triggered Clock Capture */
 		events[1] |= 0x80;	/* Synchronization Train Complete */
 		events[2] |= 0x10;	/* Slave Page Response Timeout */
@@ -1238,13 +1680,17 @@ static void hci_set_event_mask_page_2(struct hci_request *req)
 	/* If Connectionless Slave Broadcast slave role is supported
 	 * enable all necessary events for it.
 	 */
-	if (hdev->features[2][0] & 0x02) {
+	if (lmp_csb_slave_capable(hdev)) {
 		events[2] |= 0x01;	/* Synchronization Train Received */
 		events[2] |= 0x02;	/* CSB Receive */
 		events[2] |= 0x04;	/* CSB Timeout */
 		events[2] |= 0x08;	/* Truncated Page Complete */
 	}
 
+	/* Enable Authenticated Payload Timeout Expired event if supported */
+	if (lmp_ping_capable(hdev))
+		events[2] |= 0x80;
+
 	hci_req_add(req, HCI_OP_SET_EVENT_MASK_PAGE_2, sizeof(events), events);
 }
 
@@ -1261,8 +1707,13 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
 	 * as supported send it. If not supported assume that the controller
 	 * does not have actual support for stored link keys which makes this
 	 * command redundant anyway.
+	 *
+	 * Some controllers indicate that they support handling deleting
+	 * stored link keys, but they don't. The quirk lets a driver
+	 * just disable this command.
 	 */
-	if (hdev->commands[6] & 0x80) {
+	if (hdev->commands[6] & 0x80 &&
+	    !test_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks)) {
 		struct hci_cp_delete_stored_link_key cp;
 
 		bacpy(&cp.bdaddr, BDADDR_ANY);
@@ -1274,19 +1725,8 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
 	if (hdev->commands[5] & 0x10)
 		hci_setup_link_policy(req);
 
-	if (lmp_le_capable(hdev)) {
-		/* If the controller has a public BD_ADDR, then by
-		 * default use that one. If this is a LE only
-		 * controller without one, default to the random
-		 * address.
-		 */
-		if (bacmp(&hdev->bdaddr, BDADDR_ANY))
-			hdev->own_addr_type = ADDR_LE_DEV_PUBLIC;
-		else
-			hdev->own_addr_type = ADDR_LE_DEV_RANDOM;
-
+	if (lmp_le_capable(hdev))
 		hci_set_le_support(req);
-	}
 
 	/* Read features beyond page 1 if available */
 	for (p = 2; p < HCI_MAX_PAGES && p <= hdev->max_page; p++) {
@@ -1307,8 +1747,17 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt)
 		hci_set_event_mask_page_2(req);
 
 	/* Check for Synchronization Train support */
-	if (hdev->features[2][0] & 0x04)
+	if (lmp_sync_train_capable(hdev))
 		hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL);
+
+	/* Enable Secure Connections if supported and configured */
+	if ((lmp_sc_capable(hdev) ||
+	     test_bit(HCI_FORCE_SC, &hdev->dev_flags)) &&
+	    test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) {
+		u8 support = 0x01;
+		hci_req_add(req, HCI_OP_WRITE_SC_SUPPORT,
+			    sizeof(support), &support);
+	}
 }
 
 static int __hci_init(struct hci_dev *hdev)
@@ -1362,13 +1811,16 @@ static int __hci_init(struct hci_dev *hdev)
 			    &blacklist_fops);
 	debugfs_create_file("uuids", 0444, hdev->debugfs, hdev, &uuids_fops);
 
+	debugfs_create_file("conn_info_min_age", 0644, hdev->debugfs, hdev,
+			    &conn_info_min_age_fops);
+	debugfs_create_file("conn_info_max_age", 0644, hdev->debugfs, hdev,
+			    &conn_info_max_age_fops);
+
 	if (lmp_bredr_capable(hdev)) {
 		debugfs_create_file("inquiry_cache", 0444, hdev->debugfs,
 				    hdev, &inquiry_cache_fops);
 		debugfs_create_file("link_keys", 0400, hdev->debugfs,
 				    hdev, &link_keys_fops);
-		debugfs_create_file("use_debug_keys", 0444, hdev->debugfs,
-				    hdev, &use_debug_keys_fops);
 		debugfs_create_file("dev_class", 0444, hdev->debugfs,
 				    hdev, &dev_class_fops);
 		debugfs_create_file("voice_setting", 0444, hdev->debugfs,
@@ -1380,6 +1832,10 @@ static int __hci_init(struct hci_dev *hdev)
 				    hdev, &auto_accept_delay_fops);
 		debugfs_create_file("ssp_debug_mode", 0644, hdev->debugfs,
 				    hdev, &ssp_debug_mode_fops);
+		debugfs_create_file("force_sc_support", 0644, hdev->debugfs,
+				    hdev, &force_sc_support_fops);
+		debugfs_create_file("sc_only_mode", 0444, hdev->debugfs,
+				    hdev, &sc_only_mode_fops);
 	}
 
 	if (lmp_sniff_capable(hdev)) {
@@ -1392,18 +1848,46 @@ static int __hci_init(struct hci_dev *hdev)
 	}
 
 	if (lmp_le_capable(hdev)) {
+		debugfs_create_file("identity", 0400, hdev->debugfs,
+				    hdev, &identity_fops);
+		debugfs_create_file("rpa_timeout", 0644, hdev->debugfs,
+				    hdev, &rpa_timeout_fops);
+		debugfs_create_file("random_address", 0444, hdev->debugfs,
+				    hdev, &random_address_fops);
+		debugfs_create_file("static_address", 0444, hdev->debugfs,
+				    hdev, &static_address_fops);
+
+		/* For controllers with a public address, provide a debug
+		 * option to force the usage of the configured static
+		 * address. By default the public address is used.
+		 */
+		if (bacmp(&hdev->bdaddr, BDADDR_ANY))
+			debugfs_create_file("force_static_address", 0644,
+					    hdev->debugfs, hdev,
+					    &force_static_address_fops);
+
 		debugfs_create_u8("white_list_size", 0444, hdev->debugfs,
 				  &hdev->le_white_list_size);
-		debugfs_create_file("static_address", 0444, hdev->debugfs,
-				   hdev, &static_address_fops);
-		debugfs_create_file("own_address_type", 0644, hdev->debugfs,
-				    hdev, &own_address_type_fops);
+		debugfs_create_file("white_list", 0444, hdev->debugfs, hdev,
+				    &white_list_fops);
+		debugfs_create_file("identity_resolving_keys", 0400,
+				    hdev->debugfs, hdev,
+				    &identity_resolving_keys_fops);
 		debugfs_create_file("long_term_keys", 0400, hdev->debugfs,
 				    hdev, &long_term_keys_fops);
 		debugfs_create_file("conn_min_interval", 0644, hdev->debugfs,
 				    hdev, &conn_min_interval_fops);
 		debugfs_create_file("conn_max_interval", 0644, hdev->debugfs,
 				    hdev, &conn_max_interval_fops);
+		debugfs_create_file("adv_channel_map", 0644, hdev->debugfs,
+				    hdev, &adv_channel_map_fops);
+		debugfs_create_file("6lowpan", 0644, hdev->debugfs, hdev,
+				    &lowpan_debugfs_fops);
+		debugfs_create_file("le_auto_conn", 0644, hdev->debugfs, hdev,
+				    &le_auto_conn_fops);
+		debugfs_create_u16("discov_interleaved_timeout", 0644,
+				   hdev->debugfs,
+				   &hdev->discov_interleaved_timeout);
 	}
 
 	return 0;
@@ -1496,6 +1980,8 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state)
 
 	switch (state) {
 	case DISCOVERY_STOPPED:
+		hci_update_background_scan(hdev);
+
 		if (hdev->discovery.state != DISCOVERY_STARTING)
 			mgmt_discovering(hdev, 0);
 		break;
@@ -1607,12 +2093,11 @@ bool hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data,
 
 	hci_remove_remote_oob_data(hdev, &data->bdaddr);
 
-	if (ssp)
-		*ssp = data->ssp_mode;
+	*ssp = data->ssp_mode;
 
 	ie = hci_inquiry_cache_lookup(hdev, &data->bdaddr);
 	if (ie) {
-		if (ie->data.ssp_mode && ssp)
+		if (ie->data.ssp_mode)
 			*ssp = true;
 
 		if (ie->name_state == NAME_NEEDED &&
@@ -1824,10 +2309,15 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 		 * be able to determine if there is a public address
 		 * or not.
 		 *
+		 * In case of user channel usage, it is not important
+		 * if a public address or static random address is
+		 * available.
+		 *
 		 * This check is only valid for BR/EDR controllers
 		 * since AMP controllers do not have an address.
 		 */
-		if (hdev->dev_type == HCI_BREDR &&
+		if (!test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) &&
+		    hdev->dev_type == HCI_BREDR &&
 		    !bacmp(&hdev->bdaddr, BDADDR_ANY) &&
 		    !bacmp(&hdev->static_addr, BDADDR_ANY)) {
 			ret = -EADDRNOTAVAIL;
@@ -1864,6 +2354,7 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 
 	if (!ret) {
 		hci_dev_hold(hdev);
+		set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
 		set_bit(HCI_UP, &hdev->flags);
 		hci_notify(hdev, HCI_DEV_UP);
 		if (!test_bit(HCI_SETUP, &hdev->dev_flags) &&
@@ -1962,9 +2453,13 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 
 	cancel_delayed_work_sync(&hdev->le_scan_disable);
 
+	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+		cancel_delayed_work_sync(&hdev->rpa_expired);
+
 	hci_dev_lock(hdev);
 	hci_inquiry_cache_flush(hdev);
 	hci_conn_hash_flush(hdev);
+	hci_pend_le_conns_clear(hdev);
 	hci_dev_unlock(hdev);
 
 	hci_notify(hdev, HCI_DEV_DOWN);
@@ -2022,6 +2517,7 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 
 	memset(hdev->eir, 0, sizeof(hdev->eir));
 	memset(hdev->dev_class, 0, sizeof(hdev->dev_class));
+	bacpy(&hdev->random_addr, BDADDR_ANY);
 
 	hci_req_unlock(hdev);
 
@@ -2385,7 +2881,7 @@ static void hci_discov_off(struct work_struct *work)
 	mgmt_discoverable_timeout(hdev);
 }
 
-int hci_uuids_clear(struct hci_dev *hdev)
+void hci_uuids_clear(struct hci_dev *hdev)
 {
 	struct bt_uuid *uuid, *tmp;
 
@@ -2393,11 +2889,9 @@ int hci_uuids_clear(struct hci_dev *hdev)
 		list_del(&uuid->list);
 		kfree(uuid);
 	}
-
-	return 0;
 }
 
-int hci_link_keys_clear(struct hci_dev *hdev)
+void hci_link_keys_clear(struct hci_dev *hdev)
 {
 	struct list_head *p, *n;
 
@@ -2409,11 +2903,9 @@ int hci_link_keys_clear(struct hci_dev *hdev)
 		list_del(p);
 		kfree(key);
 	}
-
-	return 0;
 }
 
-int hci_smp_ltks_clear(struct hci_dev *hdev)
+void hci_smp_ltks_clear(struct hci_dev *hdev)
 {
 	struct smp_ltk *k, *tmp;
 
@@ -2421,8 +2913,16 @@ int hci_smp_ltks_clear(struct hci_dev *hdev)
 		list_del(&k->list);
 		kfree(k);
 	}
+}
 
-	return 0;
+void hci_smp_irks_clear(struct hci_dev *hdev)
+{
+	struct smp_irk *k, *tmp;
+
+	list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) {
+		list_del(&k->list);
+		kfree(k);
+	}
 }
 
 struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
@@ -2472,13 +2972,24 @@ static bool hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn,
 	return false;
 }
 
-struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, u8 rand[8])
+static bool ltk_type_master(u8 type)
+{
+	if (type == HCI_SMP_STK || type == HCI_SMP_LTK)
+		return true;
+
+	return false;
+}
+
+struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, __le64 rand,
+			     bool master)
 {
 	struct smp_ltk *k;
 
 	list_for_each_entry(k, &hdev->long_term_keys, list) {
-		if (k->ediv != ediv ||
-		    memcmp(rand, k->rand, sizeof(k->rand)))
+		if (k->ediv != ediv || k->rand != rand)
+			continue;
+
+		if (ltk_type_master(k->type) != master)
 			continue;
 
 		return k;
@@ -2488,18 +2999,56 @@ struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, u8 rand[8])
 }
 
 struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				     u8 addr_type)
+				     u8 addr_type, bool master)
 {
 	struct smp_ltk *k;
 
 	list_for_each_entry(k, &hdev->long_term_keys, list)
 		if (addr_type == k->bdaddr_type &&
-		    bacmp(bdaddr, &k->bdaddr) == 0)
+		    bacmp(bdaddr, &k->bdaddr) == 0 &&
+		    ltk_type_master(k->type) == master)
 			return k;
 
 	return NULL;
 }
 
+struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa)
+{
+	struct smp_irk *irk;
+
+	list_for_each_entry(irk, &hdev->identity_resolving_keys, list) {
+		if (!bacmp(&irk->rpa, rpa))
+			return irk;
+	}
+
+	list_for_each_entry(irk, &hdev->identity_resolving_keys, list) {
+		if (smp_irk_matches(hdev->tfm_aes, irk->val, rpa)) {
+			bacpy(&irk->rpa, rpa);
+			return irk;
+		}
+	}
+
+	return NULL;
+}
+
+struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr,
+				     u8 addr_type)
+{
+	struct smp_irk *irk;
+
+	/* Identity Address must be public or static random */
+	if (addr_type == ADDR_LE_DEV_RANDOM && (bdaddr->b[5] & 0xc0) != 0xc0)
+		return NULL;
+
+	list_for_each_entry(irk, &hdev->identity_resolving_keys, list) {
+		if (addr_type == irk->addr_type &&
+		    bacmp(bdaddr, &irk->bdaddr) == 0)
+			return irk;
+	}
+
+	return NULL;
+}
+
 int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key,
 		     bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len)
 {
@@ -2513,7 +3062,7 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key,
 		key = old_key;
 	} else {
 		old_key_type = conn ? conn->key_type : 0xff;
-		key = kzalloc(sizeof(*key), GFP_ATOMIC);
+		key = kzalloc(sizeof(*key), GFP_KERNEL);
 		if (!key)
 			return -ENOMEM;
 		list_add(&key->list, &hdev->link_keys);
@@ -2553,22 +3102,20 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key,
 	return 0;
 }
 
-int hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type,
-		int new_key, u8 authenticated, u8 tk[16], u8 enc_size, __le16
-		ediv, u8 rand[8])
+struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			    u8 addr_type, u8 type, u8 authenticated,
+			    u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand)
 {
 	struct smp_ltk *key, *old_key;
+	bool master = ltk_type_master(type);
 
-	if (!(type & HCI_SMP_STK) && !(type & HCI_SMP_LTK))
-		return 0;
-
-	old_key = hci_find_ltk_by_addr(hdev, bdaddr, addr_type);
+	old_key = hci_find_ltk_by_addr(hdev, bdaddr, addr_type, master);
 	if (old_key)
 		key = old_key;
 	else {
-		key = kzalloc(sizeof(*key), GFP_ATOMIC);
+		key = kzalloc(sizeof(*key), GFP_KERNEL);
 		if (!key)
-			return -ENOMEM;
+			return NULL;
 		list_add(&key->list, &hdev->long_term_keys);
 	}
 
@@ -2577,17 +3124,34 @@ int hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type,
 	memcpy(key->val, tk, sizeof(key->val));
 	key->authenticated = authenticated;
 	key->ediv = ediv;
+	key->rand = rand;
 	key->enc_size = enc_size;
 	key->type = type;
-	memcpy(key->rand, rand, sizeof(key->rand));
 
-	if (!new_key)
-		return 0;
+	return key;
+}
 
-	if (type & HCI_SMP_LTK)
-		mgmt_new_ltk(hdev, key, 1);
+struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			    u8 addr_type, u8 val[16], bdaddr_t *rpa)
+{
+	struct smp_irk *irk;
 
-	return 0;
+	irk = hci_find_irk_by_addr(hdev, bdaddr, addr_type);
+	if (!irk) {
+		irk = kzalloc(sizeof(*irk), GFP_KERNEL);
+		if (!irk)
+			return NULL;
+
+		bacpy(&irk->bdaddr, bdaddr);
+		irk->addr_type = addr_type;
+
+		list_add(&irk->list, &hdev->identity_resolving_keys);
+	}
+
+	memcpy(irk->val, val, 16);
+	bacpy(&irk->rpa, rpa);
+
+	return irk;
 }
 
 int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
@@ -2606,21 +3170,38 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr)
 	return 0;
 }
 
-int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr)
+int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type)
 {
 	struct smp_ltk *k, *tmp;
+	int removed = 0;
 
 	list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) {
-		if (bacmp(bdaddr, &k->bdaddr))
+		if (bacmp(bdaddr, &k->bdaddr) || k->bdaddr_type != bdaddr_type)
 			continue;
 
 		BT_DBG("%s removing %pMR", hdev->name, bdaddr);
 
 		list_del(&k->list);
 		kfree(k);
+		removed++;
 	}
 
-	return 0;
+	return removed ? 0 : -ENOENT;
+}
+
+void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type)
+{
+	struct smp_irk *k, *tmp;
+
+	list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) {
+		if (bacmp(bdaddr, &k->bdaddr) || k->addr_type != addr_type)
+			continue;
+
+		BT_DBG("%s removing %pMR", hdev->name, bdaddr);
+
+		list_del(&k->list);
+		kfree(k);
+	}
 }
 
 /* HCI command timer function */
@@ -2669,7 +3250,7 @@ int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr)
 	return 0;
 }
 
-int hci_remote_oob_data_clear(struct hci_dev *hdev)
+void hci_remote_oob_data_clear(struct hci_dev *hdev)
 {
 	struct oob_data *data, *n;
 
@@ -2677,19 +3258,43 @@ int hci_remote_oob_data_clear(struct hci_dev *hdev)
 		list_del(&data->list);
 		kfree(data);
 	}
+}
+
+int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			    u8 *hash, u8 *randomizer)
+{
+	struct oob_data *data;
+
+	data = hci_find_remote_oob_data(hdev, bdaddr);
+	if (!data) {
+		data = kmalloc(sizeof(*data), GFP_KERNEL);
+		if (!data)
+			return -ENOMEM;
+
+		bacpy(&data->bdaddr, bdaddr);
+		list_add(&data->list, &hdev->remote_oob_data);
+	}
+
+	memcpy(data->hash192, hash, sizeof(data->hash192));
+	memcpy(data->randomizer192, randomizer, sizeof(data->randomizer192));
+
+	memset(data->hash256, 0, sizeof(data->hash256));
+	memset(data->randomizer256, 0, sizeof(data->randomizer256));
+
+	BT_DBG("%s for %pMR", hdev->name, bdaddr);
 
 	return 0;
 }
 
-int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash,
-			    u8 *randomizer)
+int hci_add_remote_oob_ext_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
+				u8 *hash192, u8 *randomizer192,
+				u8 *hash256, u8 *randomizer256)
 {
 	struct oob_data *data;
 
 	data = hci_find_remote_oob_data(hdev, bdaddr);
-
 	if (!data) {
-		data = kmalloc(sizeof(*data), GFP_ATOMIC);
+		data = kmalloc(sizeof(*data), GFP_KERNEL);
 		if (!data)
 			return -ENOMEM;
 
@@ -2697,8 +3302,11 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash,
 		list_add(&data->list, &hdev->remote_oob_data);
 	}
 
-	memcpy(data->hash, hash, sizeof(data->hash));
-	memcpy(data->randomizer, randomizer, sizeof(data->randomizer));
+	memcpy(data->hash192, hash192, sizeof(data->hash192));
+	memcpy(data->randomizer192, randomizer192, sizeof(data->randomizer192));
+
+	memcpy(data->hash256, hash256, sizeof(data->hash256));
+	memcpy(data->randomizer256, randomizer256, sizeof(data->randomizer256));
 
 	BT_DBG("%s for %pMR", hdev->name, bdaddr);
 
@@ -2718,7 +3326,7 @@ struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev,
 	return NULL;
 }
 
-int hci_blacklist_clear(struct hci_dev *hdev)
+static void hci_blacklist_clear(struct hci_dev *hdev)
 {
 	struct list_head *p, *n;
 
@@ -2728,8 +3336,6 @@ int hci_blacklist_clear(struct hci_dev *hdev)
 		list_del(p);
 		kfree(b);
 	}
-
-	return 0;
 }
 
 int hci_blacklist_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
@@ -2758,8 +3364,10 @@ int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
 {
 	struct bdaddr_list *entry;
 
-	if (!bacmp(bdaddr, BDADDR_ANY))
-		return hci_blacklist_clear(hdev);
+	if (!bacmp(bdaddr, BDADDR_ANY)) {
+		hci_blacklist_clear(hdev);
+		return 0;
+	}
 
 	entry = hci_blacklist_lookup(hdev, bdaddr, type);
 	if (!entry)
@@ -2771,6 +3379,262 @@ int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
 	return mgmt_device_unblocked(hdev, bdaddr, type);
 }
 
+struct bdaddr_list *hci_white_list_lookup(struct hci_dev *hdev,
+					  bdaddr_t *bdaddr, u8 type)
+{
+	struct bdaddr_list *b;
+
+	list_for_each_entry(b, &hdev->le_white_list, list) {
+		if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type)
+			return b;
+	}
+
+	return NULL;
+}
+
+void hci_white_list_clear(struct hci_dev *hdev)
+{
+	struct list_head *p, *n;
+
+	list_for_each_safe(p, n, &hdev->le_white_list) {
+		struct bdaddr_list *b = list_entry(p, struct bdaddr_list, list);
+
+		list_del(p);
+		kfree(b);
+	}
+}
+
+int hci_white_list_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
+{
+	struct bdaddr_list *entry;
+
+	if (!bacmp(bdaddr, BDADDR_ANY))
+		return -EBADF;
+
+	entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	bacpy(&entry->bdaddr, bdaddr);
+	entry->bdaddr_type = type;
+
+	list_add(&entry->list, &hdev->le_white_list);
+
+	return 0;
+}
+
+int hci_white_list_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
+{
+	struct bdaddr_list *entry;
+
+	if (!bacmp(bdaddr, BDADDR_ANY))
+		return -EBADF;
+
+	entry = hci_white_list_lookup(hdev, bdaddr, type);
+	if (!entry)
+		return -ENOENT;
+
+	list_del(&entry->list);
+	kfree(entry);
+
+	return 0;
+}
+
+/* This function requires the caller holds hdev->lock */
+struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev,
+					       bdaddr_t *addr, u8 addr_type)
+{
+	struct hci_conn_params *params;
+
+	list_for_each_entry(params, &hdev->le_conn_params, list) {
+		if (bacmp(&params->addr, addr) == 0 &&
+		    params->addr_type == addr_type) {
+			return params;
+		}
+	}
+
+	return NULL;
+}
+
+static bool is_connected(struct hci_dev *hdev, bdaddr_t *addr, u8 type)
+{
+	struct hci_conn *conn;
+
+	conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, addr);
+	if (!conn)
+		return false;
+
+	if (conn->dst_type != type)
+		return false;
+
+	if (conn->state != BT_CONNECTED)
+		return false;
+
+	return true;
+}
+
+static bool is_identity_address(bdaddr_t *addr, u8 addr_type)
+{
+	if (addr_type == ADDR_LE_DEV_PUBLIC)
+		return true;
+
+	/* Check for Random Static address type */
+	if ((addr->b[5] & 0xc0) == 0xc0)
+		return true;
+
+	return false;
+}
+
+/* This function requires the caller holds hdev->lock */
+int hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type,
+			u8 auto_connect, u16 conn_min_interval,
+			u16 conn_max_interval)
+{
+	struct hci_conn_params *params;
+
+	if (!is_identity_address(addr, addr_type))
+		return -EINVAL;
+
+	params = hci_conn_params_lookup(hdev, addr, addr_type);
+	if (params)
+		goto update;
+
+	params = kzalloc(sizeof(*params), GFP_KERNEL);
+	if (!params) {
+		BT_ERR("Out of memory");
+		return -ENOMEM;
+	}
+
+	bacpy(&params->addr, addr);
+	params->addr_type = addr_type;
+
+	list_add(&params->list, &hdev->le_conn_params);
+
+update:
+	params->conn_min_interval = conn_min_interval;
+	params->conn_max_interval = conn_max_interval;
+	params->auto_connect = auto_connect;
+
+	switch (auto_connect) {
+	case HCI_AUTO_CONN_DISABLED:
+	case HCI_AUTO_CONN_LINK_LOSS:
+		hci_pend_le_conn_del(hdev, addr, addr_type);
+		break;
+	case HCI_AUTO_CONN_ALWAYS:
+		if (!is_connected(hdev, addr, addr_type))
+			hci_pend_le_conn_add(hdev, addr, addr_type);
+		break;
+	}
+
+	BT_DBG("addr %pMR (type %u) auto_connect %u conn_min_interval 0x%.4x "
+	       "conn_max_interval 0x%.4x", addr, addr_type, auto_connect,
+	       conn_min_interval, conn_max_interval);
+
+	return 0;
+}
+
+/* This function requires the caller holds hdev->lock */
+void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type)
+{
+	struct hci_conn_params *params;
+
+	params = hci_conn_params_lookup(hdev, addr, addr_type);
+	if (!params)
+		return;
+
+	hci_pend_le_conn_del(hdev, addr, addr_type);
+
+	list_del(&params->list);
+	kfree(params);
+
+	BT_DBG("addr %pMR (type %u)", addr, addr_type);
+}
+
+/* This function requires the caller holds hdev->lock */
+void hci_conn_params_clear(struct hci_dev *hdev)
+{
+	struct hci_conn_params *params, *tmp;
+
+	list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) {
+		list_del(&params->list);
+		kfree(params);
+	}
+
+	BT_DBG("All LE connection parameters were removed");
+}
+
+/* This function requires the caller holds hdev->lock */
+struct bdaddr_list *hci_pend_le_conn_lookup(struct hci_dev *hdev,
+					    bdaddr_t *addr, u8 addr_type)
+{
+	struct bdaddr_list *entry;
+
+	list_for_each_entry(entry, &hdev->pend_le_conns, list) {
+		if (bacmp(&entry->bdaddr, addr) == 0 &&
+		    entry->bdaddr_type == addr_type)
+			return entry;
+	}
+
+	return NULL;
+}
+
+/* This function requires the caller holds hdev->lock */
+void hci_pend_le_conn_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type)
+{
+	struct bdaddr_list *entry;
+
+	entry = hci_pend_le_conn_lookup(hdev, addr, addr_type);
+	if (entry)
+		goto done;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		BT_ERR("Out of memory");
+		return;
+	}
+
+	bacpy(&entry->bdaddr, addr);
+	entry->bdaddr_type = addr_type;
+
+	list_add(&entry->list, &hdev->pend_le_conns);
+
+	BT_DBG("addr %pMR (type %u)", addr, addr_type);
+
+done:
+	hci_update_background_scan(hdev);
+}
+
+/* This function requires the caller holds hdev->lock */
+void hci_pend_le_conn_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type)
+{
+	struct bdaddr_list *entry;
+
+	entry = hci_pend_le_conn_lookup(hdev, addr, addr_type);
+	if (!entry)
+		goto done;
+
+	list_del(&entry->list);
+	kfree(entry);
+
+	BT_DBG("addr %pMR (type %u)", addr, addr_type);
+
+done:
+	hci_update_background_scan(hdev);
+}
+
+/* This function requires the caller holds hdev->lock */
+void hci_pend_le_conns_clear(struct hci_dev *hdev)
+{
+	struct bdaddr_list *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, &hdev->pend_le_conns, list) {
+		list_del(&entry->list);
+		kfree(entry);
+	}
+
+	BT_DBG("All LE pending connections cleared");
+}
+
 static void inquiry_complete(struct hci_dev *hdev, u8 status)
 {
 	if (status) {
@@ -2830,7 +3694,6 @@ static void le_scan_disable_work(struct work_struct *work)
 {
 	struct hci_dev *hdev = container_of(work, struct hci_dev,
 					    le_scan_disable.work);
-	struct hci_cp_le_set_scan_enable cp;
 	struct hci_request req;
 	int err;
 
@@ -2838,15 +3701,128 @@ static void le_scan_disable_work(struct work_struct *work)
 
 	hci_req_init(&req, hdev);
 
-	memset(&cp, 0, sizeof(cp));
-	cp.enable = LE_SCAN_DISABLE;
-	hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+	hci_req_add_le_scan_disable(&req);
 
 	err = hci_req_run(&req, le_scan_disable_work_complete);
 	if (err)
 		BT_ERR("Disable LE scanning request failed: err %d", err);
 }
 
+static void set_random_addr(struct hci_request *req, bdaddr_t *rpa)
+{
+	struct hci_dev *hdev = req->hdev;
+
+	/* If we're advertising or initiating an LE connection we can't
+	 * go ahead and change the random address at this time. This is
+	 * because the eventual initiator address used for the
+	 * subsequently created connection will be undefined (some
+	 * controllers use the new address and others the one we had
+	 * when the operation started).
+	 *
+	 * In this kind of scenario skip the update and let the random
+	 * address be updated at the next cycle.
+	 */
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags) ||
+	    hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) {
+		BT_DBG("Deferring random address update");
+		return;
+	}
+
+	hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, rpa);
+}
+
+int hci_update_random_address(struct hci_request *req, bool require_privacy,
+			      u8 *own_addr_type)
+{
+	struct hci_dev *hdev = req->hdev;
+	int err;
+
+	/* If privacy is enabled use a resolvable private address. If
+	 * current RPA has expired or there is something else than
+	 * the current RPA in use, then generate a new one.
+	 */
+	if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) {
+		int to;
+
+		*own_addr_type = ADDR_LE_DEV_RANDOM;
+
+		if (!test_and_clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags) &&
+		    !bacmp(&hdev->random_addr, &hdev->rpa))
+			return 0;
+
+		err = smp_generate_rpa(hdev->tfm_aes, hdev->irk, &hdev->rpa);
+		if (err < 0) {
+			BT_ERR("%s failed to generate new RPA", hdev->name);
+			return err;
+		}
+
+		set_random_addr(req, &hdev->rpa);
+
+		to = msecs_to_jiffies(hdev->rpa_timeout * 1000);
+		queue_delayed_work(hdev->workqueue, &hdev->rpa_expired, to);
+
+		return 0;
+	}
+
+	/* In case of required privacy without resolvable private address,
+	 * use an unresolvable private address. This is useful for active
+	 * scanning and non-connectable advertising.
+	 */
+	if (require_privacy) {
+		bdaddr_t urpa;
+
+		get_random_bytes(&urpa, 6);
+		urpa.b[5] &= 0x3f;	/* Clear two most significant bits */
+
+		*own_addr_type = ADDR_LE_DEV_RANDOM;
+		set_random_addr(req, &urpa);
+		return 0;
+	}
+
+	/* If forcing static address is in use or there is no public
+	 * address use the static address as random address (but skip
+	 * the HCI command if the current random address is already the
+	 * static one.
+	 */
+	if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) ||
+	    !bacmp(&hdev->bdaddr, BDADDR_ANY)) {
+		*own_addr_type = ADDR_LE_DEV_RANDOM;
+		if (bacmp(&hdev->static_addr, &hdev->random_addr))
+			hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6,
+				    &hdev->static_addr);
+		return 0;
+	}
+
+	/* Neither privacy nor static address is being used so use a
+	 * public address.
+	 */
+	*own_addr_type = ADDR_LE_DEV_PUBLIC;
+
+	return 0;
+}
+
+/* Copy the Identity Address of the controller.
+ *
+ * If the controller has a public BD_ADDR, then by default use that one.
+ * If this is a LE only controller without a public address, default to
+ * the static random address.
+ *
+ * For debugging purposes it is possible to force controllers with a
+ * public address to use the static random address instead.
+ */
+void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			       u8 *bdaddr_type)
+{
+	if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) ||
+	    !bacmp(&hdev->bdaddr, BDADDR_ANY)) {
+		bacpy(bdaddr, &hdev->static_addr);
+		*bdaddr_type = ADDR_LE_DEV_RANDOM;
+	} else {
+		bacpy(bdaddr, &hdev->bdaddr);
+		*bdaddr_type = ADDR_LE_DEV_PUBLIC;
+	}
+}
+
 /* Alloc HCI device */
 struct hci_dev *hci_alloc_dev(void)
 {
@@ -2867,11 +3843,17 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->sniff_max_interval = 800;
 	hdev->sniff_min_interval = 80;
 
+	hdev->le_adv_channel_map = 0x07;
 	hdev->le_scan_interval = 0x0060;
 	hdev->le_scan_window = 0x0030;
 	hdev->le_conn_min_interval = 0x0028;
 	hdev->le_conn_max_interval = 0x0038;
 
+	hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT;
+	hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT;
+	hdev->conn_info_min_age = DEFAULT_CONN_INFO_MIN_AGE;
+	hdev->conn_info_max_age = DEFAULT_CONN_INFO_MAX_AGE;
+
 	mutex_init(&hdev->lock);
 	mutex_init(&hdev->req_lock);
 
@@ -2880,7 +3862,11 @@ struct hci_dev *hci_alloc_dev(void)
 	INIT_LIST_HEAD(&hdev->uuids);
 	INIT_LIST_HEAD(&hdev->link_keys);
 	INIT_LIST_HEAD(&hdev->long_term_keys);
+	INIT_LIST_HEAD(&hdev->identity_resolving_keys);
 	INIT_LIST_HEAD(&hdev->remote_oob_data);
+	INIT_LIST_HEAD(&hdev->le_white_list);
+	INIT_LIST_HEAD(&hdev->le_conn_params);
+	INIT_LIST_HEAD(&hdev->pend_le_conns);
 	INIT_LIST_HEAD(&hdev->conn_hash.list);
 
 	INIT_WORK(&hdev->rx_work, hci_rx_work);
@@ -2965,9 +3951,18 @@ int hci_register_dev(struct hci_dev *hdev)
 
 	dev_set_name(&hdev->dev, "%s", hdev->name);
 
+	hdev->tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0,
+					       CRYPTO_ALG_ASYNC);
+	if (IS_ERR(hdev->tfm_aes)) {
+		BT_ERR("Unable to create crypto context");
+		error = PTR_ERR(hdev->tfm_aes);
+		hdev->tfm_aes = NULL;
+		goto err_wqueue;
+	}
+
 	error = device_add(&hdev->dev);
 	if (error < 0)
-		goto err_wqueue;
+		goto err_tfm;
 
 	hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev,
 				    RFKILL_TYPE_BLUETOOTH, &hci_rfkill_ops,
@@ -3003,6 +3998,8 @@ int hci_register_dev(struct hci_dev *hdev)
 
 	return id;
 
+err_tfm:
+	crypto_free_blkcipher(hdev->tfm_aes);
 err_wqueue:
 	destroy_workqueue(hdev->workqueue);
 	destroy_workqueue(hdev->req_workqueue);
@@ -3053,6 +4050,9 @@ void hci_unregister_dev(struct hci_dev *hdev)
 		rfkill_destroy(hdev->rfkill);
 	}
 
+	if (hdev->tfm_aes)
+		crypto_free_blkcipher(hdev->tfm_aes);
+
 	device_del(&hdev->dev);
 
 	debugfs_remove_recursive(hdev->debugfs);
@@ -3065,7 +4065,11 @@ void hci_unregister_dev(struct hci_dev *hdev)
 	hci_uuids_clear(hdev);
 	hci_link_keys_clear(hdev);
 	hci_smp_ltks_clear(hdev);
+	hci_smp_irks_clear(hdev);
 	hci_remote_oob_data_clear(hdev);
+	hci_white_list_clear(hdev);
+	hci_conn_params_clear(hdev);
+	hci_pend_le_conns_clear(hdev);
 	hci_dev_unlock(hdev);
 
 	hci_dev_put(hdev);
@@ -4293,3 +5297,104 @@ static void hci_cmd_work(struct work_struct *work)
 		}
 	}
 }
+
+void hci_req_add_le_scan_disable(struct hci_request *req)
+{
+	struct hci_cp_le_set_scan_enable cp;
+
+	memset(&cp, 0, sizeof(cp));
+	cp.enable = LE_SCAN_DISABLE;
+	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+}
+
+void hci_req_add_le_passive_scan(struct hci_request *req)
+{
+	struct hci_cp_le_set_scan_param param_cp;
+	struct hci_cp_le_set_scan_enable enable_cp;
+	struct hci_dev *hdev = req->hdev;
+	u8 own_addr_type;
+
+	/* Set require_privacy to true to avoid identification from
+	 * unknown peer devices. Since this is passive scanning, no
+	 * SCAN_REQ using the local identity should be sent. Mandating
+	 * privacy is just an extra precaution.
+	 */
+	if (hci_update_random_address(req, true, &own_addr_type))
+		return;
+
+	memset(&param_cp, 0, sizeof(param_cp));
+	param_cp.type = LE_SCAN_PASSIVE;
+	param_cp.interval = cpu_to_le16(hdev->le_scan_interval);
+	param_cp.window = cpu_to_le16(hdev->le_scan_window);
+	param_cp.own_address_type = own_addr_type;
+	hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
+		    &param_cp);
+
+	memset(&enable_cp, 0, sizeof(enable_cp));
+	enable_cp.enable = LE_SCAN_ENABLE;
+	enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
+	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp),
+		    &enable_cp);
+}
+
+static void update_background_scan_complete(struct hci_dev *hdev, u8 status)
+{
+	if (status)
+		BT_DBG("HCI request failed to update background scanning: "
+		       "status 0x%2.2x", status);
+}
+
+/* This function controls the background scanning based on hdev->pend_le_conns
+ * list. If there are pending LE connection we start the background scanning,
+ * otherwise we stop it.
+ *
+ * This function requires the caller holds hdev->lock.
+ */
+void hci_update_background_scan(struct hci_dev *hdev)
+{
+	struct hci_request req;
+	struct hci_conn *conn;
+	int err;
+
+	hci_req_init(&req, hdev);
+
+	if (list_empty(&hdev->pend_le_conns)) {
+		/* If there is no pending LE connections, we should stop
+		 * the background scanning.
+		 */
+
+		/* If controller is not scanning we are done. */
+		if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags))
+			return;
+
+		hci_req_add_le_scan_disable(&req);
+
+		BT_DBG("%s stopping background scanning", hdev->name);
+	} else {
+		/* If there is at least one pending LE connection, we should
+		 * keep the background scan running.
+		 */
+
+		/* If controller is connecting, we should not start scanning
+		 * since some controllers are not able to scan and connect at
+		 * the same time.
+		 */
+		conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT);
+		if (conn)
+			return;
+
+		/* If controller is currently scanning, we stop it to ensure we
+		 * don't miss any advertising (due to duplicates filter).
+		 */
+		if (test_bit(HCI_LE_SCAN, &hdev->dev_flags))
+			hci_req_add_le_scan_disable(&req);
+
+		hci_req_add_le_passive_scan(&req);
+
+		BT_DBG("%s starting background scanning", hdev->name);
+	}
+
+	err = hci_req_run(&req, update_background_scan_complete);
+	if (err)
+		BT_ERR("Failed to run HCI request: err %d", err);
+}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 5935f748c0f..640c54ec1bd 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -45,9 +45,13 @@ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb)
 		return;
 
 	clear_bit(HCI_INQUIRY, &hdev->flags);
-	smp_mb__after_clear_bit(); /* wake_up_bit advises about this barrier */
+	smp_mb__after_atomic(); /* wake_up_bit advises about this barrier */
 	wake_up_bit(&hdev->flags, HCI_INQUIRY);
 
+	hci_dev_lock(hdev);
+	hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+	hci_dev_unlock(hdev);
+
 	hci_conn_check_pending(hdev);
 }
 
@@ -199,6 +203,8 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb)
 	memset(hdev->scan_rsp_data, 0, sizeof(hdev->scan_rsp_data));
 	hdev->scan_rsp_data_len = 0;
 
+	hdev->le_scan_type = LE_SCAN_PASSIVE;
+
 	hdev->ssp_debug_mode = 0;
 }
 
@@ -461,6 +467,34 @@ static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 }
 
+static void hci_cc_write_sc_support(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	u8 status = *((u8 *) skb->data);
+	struct hci_cp_write_sc_support *sent;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SC_SUPPORT);
+	if (!sent)
+		return;
+
+	if (!status) {
+		if (sent->support)
+			hdev->features[1][0] |= LMP_HOST_SC;
+		else
+			hdev->features[1][0] &= ~LMP_HOST_SC;
+	}
+
+	if (test_bit(HCI_MGMT, &hdev->dev_flags))
+		mgmt_sc_enable_complete(hdev, sent->support, status);
+	else if (!status) {
+		if (sent->support)
+			set_bit(HCI_SC_ENABLED, &hdev->dev_flags);
+		else
+			clear_bit(HCI_SC_ENABLED, &hdev->dev_flags);
+	}
+}
+
 static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_rp_read_local_version *rp = (void *) skb->data;
@@ -486,7 +520,10 @@ static void hci_cc_read_local_commands(struct hci_dev *hdev,
 
 	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
 
-	if (!rp->status)
+	if (rp->status)
+		return;
+
+	if (test_bit(HCI_SETUP, &hdev->dev_flags))
 		memcpy(hdev->commands, rp->commands, sizeof(hdev->commands));
 }
 
@@ -538,12 +575,6 @@ static void hci_cc_read_local_features(struct hci_dev *hdev,
 
 	if (hdev->features[0][5] & LMP_EDR_3S_ESCO)
 		hdev->esco_type |= (ESCO_2EV5 | ESCO_3EV5);
-
-	BT_DBG("%s features 0x%.2x%.2x%.2x%.2x%.2x%.2x%.2x%.2x", hdev->name,
-	       hdev->features[0][0], hdev->features[0][1],
-	       hdev->features[0][2], hdev->features[0][3],
-	       hdev->features[0][4], hdev->features[0][5],
-	       hdev->features[0][6], hdev->features[0][7]);
 }
 
 static void hci_cc_read_local_ext_features(struct hci_dev *hdev,
@@ -907,16 +938,50 @@ static void hci_cc_user_passkey_neg_reply(struct hci_dev *hdev,
 	hci_dev_unlock(hdev);
 }
 
-static void hci_cc_read_local_oob_data_reply(struct hci_dev *hdev,
-					     struct sk_buff *skb)
+static void hci_cc_read_local_oob_data(struct hci_dev *hdev,
+				       struct sk_buff *skb)
 {
 	struct hci_rp_read_local_oob_data *rp = (void *) skb->data;
 
 	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
 
 	hci_dev_lock(hdev);
-	mgmt_read_local_oob_data_reply_complete(hdev, rp->hash,
-						rp->randomizer, rp->status);
+	mgmt_read_local_oob_data_complete(hdev, rp->hash, rp->randomizer,
+					  NULL, NULL, rp->status);
+	hci_dev_unlock(hdev);
+}
+
+static void hci_cc_read_local_oob_ext_data(struct hci_dev *hdev,
+					   struct sk_buff *skb)
+{
+	struct hci_rp_read_local_oob_ext_data *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	hci_dev_lock(hdev);
+	mgmt_read_local_oob_data_complete(hdev, rp->hash192, rp->randomizer192,
+					  rp->hash256, rp->randomizer256,
+					  rp->status);
+	hci_dev_unlock(hdev);
+}
+
+
+static void hci_cc_le_set_random_addr(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	__u8 status = *((__u8 *) skb->data);
+	bdaddr_t *sent;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_RANDOM_ADDR);
+	if (!sent)
+		return;
+
+	hci_dev_lock(hdev);
+
+	if (!status)
+		bacpy(&hdev->random_addr, sent);
+
 	hci_dev_unlock(hdev);
 }
 
@@ -930,18 +995,75 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!sent)
 		return;
 
+	if (status)
+		return;
+
 	hci_dev_lock(hdev);
 
-	if (!status) {
-		if (*sent)
-			set_bit(HCI_ADVERTISING, &hdev->dev_flags);
-		else
-			clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
+	/* If we're doing connection initation as peripheral. Set a
+	 * timeout in case something goes wrong.
+	 */
+	if (*sent) {
+		struct hci_conn *conn;
+
+		conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT);
+		if (conn)
+			queue_delayed_work(hdev->workqueue,
+					   &conn->le_conn_timeout,
+					   HCI_LE_CONN_TIMEOUT);
 	}
 
+	mgmt_advertising(hdev, *sent);
+
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_cp_le_set_scan_param *cp;
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_PARAM);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+
+	if (!status)
+		hdev->le_scan_type = cp->type;
+
+	hci_dev_unlock(hdev);
+}
+
+static bool has_pending_adv_report(struct hci_dev *hdev)
+{
+	struct discovery_state *d = &hdev->discovery;
+
+	return bacmp(&d->last_adv_addr, BDADDR_ANY);
+}
+
+static void clear_pending_adv_report(struct hci_dev *hdev)
+{
+	struct discovery_state *d = &hdev->discovery;
+
+	bacpy(&d->last_adv_addr, BDADDR_ANY);
+	d->last_adv_data_len = 0;
+}
+
+static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr,
+				     u8 bdaddr_type, s8 rssi, u8 *data, u8 len)
+{
+	struct discovery_state *d = &hdev->discovery;
+
+	bacpy(&d->last_adv_addr, bdaddr);
+	d->last_adv_addr_type = bdaddr_type;
+	d->last_adv_rssi = rssi;
+	memcpy(d->last_adv_data, data, len);
+	d->last_adv_data_len = len;
+}
+
 static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 				      struct sk_buff *skb)
 {
@@ -960,10 +1082,38 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 	switch (cp->enable) {
 	case LE_SCAN_ENABLE:
 		set_bit(HCI_LE_SCAN, &hdev->dev_flags);
+		if (hdev->le_scan_type == LE_SCAN_ACTIVE)
+			clear_pending_adv_report(hdev);
 		break;
 
 	case LE_SCAN_DISABLE:
+		/* We do this here instead of when setting DISCOVERY_STOPPED
+		 * since the latter would potentially require waiting for
+		 * inquiry to stop too.
+		 */
+		if (has_pending_adv_report(hdev)) {
+			struct discovery_state *d = &hdev->discovery;
+
+			mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK,
+					  d->last_adv_addr_type, NULL,
+					  d->last_adv_rssi, 0, 1,
+					  d->last_adv_data,
+					  d->last_adv_data_len, NULL, 0);
+		}
+
+		/* Cancel this timer so that we don't try to disable scanning
+		 * when it's already disabled.
+		 */
+		cancel_delayed_work(&hdev->le_scan_disable);
+
 		clear_bit(HCI_LE_SCAN, &hdev->dev_flags);
+		/* The HCI_LE_SCAN_INTERRUPTED flag indicates that we
+		 * interrupted scanning due to a connect request. Mark
+		 * therefore discovery as stopped.
+		 */
+		if (test_and_clear_bit(HCI_LE_SCAN_INTERRUPTED,
+				       &hdev->dev_flags))
+			hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
 		break;
 
 	default:
@@ -983,6 +1133,49 @@ static void hci_cc_le_read_white_list_size(struct hci_dev *hdev,
 		hdev->le_white_list_size = rp->size;
 }
 
+static void hci_cc_le_clear_white_list(struct hci_dev *hdev,
+				       struct sk_buff *skb)
+{
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (!status)
+		hci_white_list_clear(hdev);
+}
+
+static void hci_cc_le_add_to_white_list(struct hci_dev *hdev,
+					struct sk_buff *skb)
+{
+	struct hci_cp_le_add_to_white_list *sent;
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_WHITE_LIST);
+	if (!sent)
+		return;
+
+	if (!status)
+		hci_white_list_add(hdev, &sent->bdaddr, sent->bdaddr_type);
+}
+
+static void hci_cc_le_del_from_white_list(struct hci_dev *hdev,
+					  struct sk_buff *skb)
+{
+	struct hci_cp_le_del_from_white_list *sent;
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_LE_DEL_FROM_WHITE_LIST);
+	if (!sent)
+		return;
+
+	if (!status)
+		hci_white_list_del(hdev, &sent->bdaddr, sent->bdaddr_type);
+}
+
 static void hci_cc_le_read_supported_states(struct hci_dev *hdev,
 					    struct sk_buff *skb)
 {
@@ -1023,6 +1216,25 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev,
 	}
 }
 
+static void hci_cc_set_adv_param(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_cp_le_set_adv_param *cp;
+	u8 status = *((u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_PARAM);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+	hdev->adv_addr_type = cp->own_address_type;
+	hci_dev_unlock(hdev);
+}
+
 static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev,
 					  struct sk_buff *skb)
 {
@@ -1037,6 +1249,59 @@ static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev,
 	amp_write_rem_assoc_continue(hdev, rp->phy_handle);
 }
 
+static void hci_cc_read_rssi(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_rp_read_rssi *rp = (void *) skb->data;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle));
+	if (conn)
+		conn->rssi = rp->rssi;
+
+	hci_dev_unlock(hdev);
+}
+
+static void hci_cc_read_tx_power(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_cp_read_tx_power *sent;
+	struct hci_rp_read_tx_power *rp = (void *) skb->data;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_READ_TX_POWER);
+	if (!sent)
+		return;
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle));
+	if (!conn)
+		goto unlock;
+
+	switch (sent->type) {
+	case 0x00:
+		conn->tx_power = rp->tx_power;
+		break;
+	case 0x01:
+		conn->max_tx_power = rp->tx_power;
+		break;
+	}
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 {
 	BT_DBG("%s status 0x%2.2x", hdev->name, status);
@@ -1188,9 +1453,13 @@ static int hci_outgoing_auth_needed(struct hci_dev *hdev,
 		return 0;
 
 	/* Only request authentication for SSP connections or non-SSP
-	 * devices with sec_level HIGH or if MITM protection is requested */
+	 * devices with sec_level MEDIUM or HIGH or if MITM protection
+	 * is requested.
+	 */
 	if (!hci_conn_ssp_enabled(conn) && !(conn->auth_type & 0x01) &&
-	    conn->pending_sec_level != BT_SECURITY_HIGH)
+	    conn->pending_sec_level != BT_SECURITY_FIPS &&
+	    conn->pending_sec_level != BT_SECURITY_HIGH &&
+	    conn->pending_sec_level != BT_SECURITY_MEDIUM)
 		return 0;
 
 	return 1;
@@ -1521,6 +1790,87 @@ static void hci_cs_accept_phylink(struct hci_dev *hdev, u8 status)
 	amp_write_remote_assoc(hdev, cp->phy_handle);
 }
 
+static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status)
+{
+	struct hci_cp_le_create_conn *cp;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	/* All connection failure handling is taken care of by the
+	 * hci_le_conn_failed function which is triggered by the HCI
+	 * request completion callbacks used for connecting.
+	 */
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_CREATE_CONN);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->peer_addr);
+	if (!conn)
+		goto unlock;
+
+	/* Store the initiator and responder address information which
+	 * is needed for SMP. These values will not change during the
+	 * lifetime of the connection.
+	 */
+	conn->init_addr_type = cp->own_address_type;
+	if (cp->own_address_type == ADDR_LE_DEV_RANDOM)
+		bacpy(&conn->init_addr, &hdev->random_addr);
+	else
+		bacpy(&conn->init_addr, &hdev->bdaddr);
+
+	conn->resp_addr_type = cp->peer_addr_type;
+	bacpy(&conn->resp_addr, &cp->peer_addr);
+
+	/* We don't want the connection attempt to stick around
+	 * indefinitely since LE doesn't have a page timeout concept
+	 * like BR/EDR. Set a timer for any connection that doesn't use
+	 * the white list for connecting.
+	 */
+	if (cp->filter_policy == HCI_LE_USE_PEER_ADDR)
+		queue_delayed_work(conn->hdev->workqueue,
+				   &conn->le_conn_timeout,
+				   HCI_LE_CONN_TIMEOUT);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
+static void hci_cs_le_start_enc(struct hci_dev *hdev, u8 status)
+{
+	struct hci_cp_le_start_enc *cp;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (!status)
+		return;
+
+	hci_dev_lock(hdev);
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_START_ENC);
+	if (!cp)
+		goto unlock;
+
+	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle));
+	if (!conn)
+		goto unlock;
+
+	if (conn->state != BT_CONNECTED)
+		goto unlock;
+
+	hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE);
+	hci_conn_drop(conn);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 status = *((__u8 *) skb->data);
@@ -1534,7 +1884,7 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!test_and_clear_bit(HCI_INQUIRY, &hdev->flags))
 		return;
 
-	smp_mb__after_clear_bit(); /* wake_up_bit advises about this barrier */
+	smp_mb__after_atomic(); /* wake_up_bit advises about this barrier */
 	wake_up_bit(&hdev->flags, HCI_INQUIRY);
 
 	if (!test_bit(HCI_MGMT, &hdev->dev_flags))
@@ -1593,7 +1943,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		name_known = hci_inquiry_cache_update(hdev, &data, false, &ssp);
 		mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00,
 				  info->dev_class, 0, !name_known, ssp, NULL,
-				  0);
+				  0, NULL, 0);
 	}
 
 	hci_dev_unlock(hdev);
@@ -1662,7 +2012,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	} else {
 		conn->state = BT_CLOSED;
 		if (conn->type == ACL_LINK)
-			mgmt_connect_failed(hdev, &ev->bdaddr, conn->type,
+			mgmt_connect_failed(hdev, &conn->dst, conn->type,
 					    conn->dst_type, ev->status);
 	}
 
@@ -1741,9 +2091,9 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			bacpy(&cp.bdaddr, &ev->bdaddr);
 			cp.pkt_type = cpu_to_le16(conn->pkt_type);
 
-			cp.tx_bandwidth   = __constant_cpu_to_le32(0x00001f40);
-			cp.rx_bandwidth   = __constant_cpu_to_le32(0x00001f40);
-			cp.max_latency    = __constant_cpu_to_le16(0xffff);
+			cp.tx_bandwidth   = cpu_to_le32(0x00001f40);
+			cp.rx_bandwidth   = cpu_to_le32(0x00001f40);
+			cp.max_latency    = cpu_to_le16(0xffff);
 			cp.content_format = cpu_to_le16(hdev->voice_setting);
 			cp.retrans_effort = 0xff;
 
@@ -1782,7 +2132,11 @@ static u8 hci_to_mgmt_reason(u8 err)
 static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_disconn_complete *ev = (void *) skb->data;
+	u8 reason = hci_to_mgmt_reason(ev->reason);
+	struct hci_conn_params *params;
 	struct hci_conn *conn;
+	bool mgmt_connected;
+	u8 type;
 
 	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
 
@@ -1792,43 +2146,55 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!conn)
 		goto unlock;
 
-	if (ev->status == 0)
-		conn->state = BT_CLOSED;
+	if (ev->status) {
+		mgmt_disconnect_failed(hdev, &conn->dst, conn->type,
+				       conn->dst_type, ev->status);
+		goto unlock;
+	}
 
-	if (test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags) &&
-	    (conn->type == ACL_LINK || conn->type == LE_LINK)) {
-		if (ev->status) {
-			mgmt_disconnect_failed(hdev, &conn->dst, conn->type,
-					       conn->dst_type, ev->status);
-		} else {
-			u8 reason = hci_to_mgmt_reason(ev->reason);
+	conn->state = BT_CLOSED;
+
+	mgmt_connected = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags);
+	mgmt_device_disconnected(hdev, &conn->dst, conn->type, conn->dst_type,
+				reason, mgmt_connected);
+
+	if (conn->type == ACL_LINK && conn->flush_key)
+		hci_remove_link_key(hdev, &conn->dst);
+
+	params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type);
+	if (params) {
+		switch (params->auto_connect) {
+		case HCI_AUTO_CONN_LINK_LOSS:
+			if (ev->reason != HCI_ERROR_CONNECTION_TIMEOUT)
+				break;
+			/* Fall through */
 
-			mgmt_device_disconnected(hdev, &conn->dst, conn->type,
-						 conn->dst_type, reason);
+		case HCI_AUTO_CONN_ALWAYS:
+			hci_pend_le_conn_add(hdev, &conn->dst, conn->dst_type);
+			break;
+
+		default:
+			break;
 		}
 	}
 
-	if (ev->status == 0) {
-		u8 type = conn->type;
+	type = conn->type;
 
-		if (type == ACL_LINK && conn->flush_key)
-			hci_remove_link_key(hdev, &conn->dst);
-		hci_proto_disconn_cfm(conn, ev->reason);
-		hci_conn_del(conn);
+	hci_proto_disconn_cfm(conn, ev->reason);
+	hci_conn_del(conn);
 
-		/* Re-enable advertising if necessary, since it might
-		 * have been disabled by the connection. From the
-		 * HCI_LE_Set_Advertise_Enable command description in
-		 * the core specification (v4.0):
-		 * "The Controller shall continue advertising until the Host
-		 * issues an LE_Set_Advertise_Enable command with
-		 * Advertising_Enable set to 0x00 (Advertising is disabled)
-		 * or until a connection is created or until the Advertising
-		 * is timed out due to Directed Advertising."
-		 */
-		if (type == LE_LINK)
-			mgmt_reenable_advertising(hdev);
-	}
+	/* Re-enable advertising if necessary, since it might
+	 * have been disabled by the connection. From the
+	 * HCI_LE_Set_Advertise_Enable command description in
+	 * the core specification (v4.0):
+	 * "The Controller shall continue advertising until the Host
+	 * issues an LE_Set_Advertise_Enable command with
+	 * Advertising_Enable set to 0x00 (Advertising is disabled)
+	 * or until a connection is created or until the Advertising
+	 * is timed out due to Directed Advertising."
+	 */
+	if (type == LE_LINK)
+		mgmt_reenable_advertising(hdev);
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -1949,34 +2315,57 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_lock(hdev);
 
 	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle));
-	if (conn) {
-		if (!ev->status) {
-			if (ev->encrypt) {
-				/* Encryption implies authentication */
-				conn->link_mode |= HCI_LM_AUTH;
-				conn->link_mode |= HCI_LM_ENCRYPT;
-				conn->sec_level = conn->pending_sec_level;
-			} else
-				conn->link_mode &= ~HCI_LM_ENCRYPT;
+	if (!conn)
+		goto unlock;
+
+	if (!ev->status) {
+		if (ev->encrypt) {
+			/* Encryption implies authentication */
+			conn->link_mode |= HCI_LM_AUTH;
+			conn->link_mode |= HCI_LM_ENCRYPT;
+			conn->sec_level = conn->pending_sec_level;
+
+			/* P-256 authentication key implies FIPS */
+			if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256)
+				conn->link_mode |= HCI_LM_FIPS;
+
+			if ((conn->type == ACL_LINK && ev->encrypt == 0x02) ||
+			    conn->type == LE_LINK)
+				set_bit(HCI_CONN_AES_CCM, &conn->flags);
+		} else {
+			conn->link_mode &= ~HCI_LM_ENCRYPT;
+			clear_bit(HCI_CONN_AES_CCM, &conn->flags);
 		}
+	}
 
-		clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
+	clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
 
-		if (ev->status && conn->state == BT_CONNECTED) {
-			hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE);
+	if (ev->status && conn->state == BT_CONNECTED) {
+		hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE);
+		hci_conn_drop(conn);
+		goto unlock;
+	}
+
+	if (conn->state == BT_CONFIG) {
+		if (!ev->status)
+			conn->state = BT_CONNECTED;
+
+		/* In Secure Connections Only mode, do not allow any
+		 * connections that are not encrypted with AES-CCM
+		 * using a P-256 authenticated combination key.
+		 */
+		if (test_bit(HCI_SC_ONLY, &hdev->dev_flags) &&
+		    (!test_bit(HCI_CONN_AES_CCM, &conn->flags) ||
+		     conn->key_type != HCI_LK_AUTH_COMBINATION_P256)) {
+			hci_proto_connect_cfm(conn, HCI_ERROR_AUTH_FAILURE);
 			hci_conn_drop(conn);
 			goto unlock;
 		}
 
-		if (conn->state == BT_CONFIG) {
-			if (!ev->status)
-				conn->state = BT_CONNECTED;
-
-			hci_proto_connect_cfm(conn, ev->status);
-			hci_conn_drop(conn);
-		} else
-			hci_encrypt_cfm(conn, ev->status, ev->encrypt);
-	}
+		hci_proto_connect_cfm(conn, ev->status);
+		hci_conn_drop(conn);
+	} else
+		hci_encrypt_cfm(conn, ev->status, ev->encrypt);
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -2150,6 +2539,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_write_ssp_mode(hdev, skb);
 		break;
 
+	case HCI_OP_WRITE_SC_SUPPORT:
+		hci_cc_write_sc_support(hdev, skb);
+		break;
+
 	case HCI_OP_READ_LOCAL_VERSION:
 		hci_cc_read_local_version(hdev, skb);
 		break;
@@ -2219,7 +2612,11 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		break;
 
 	case HCI_OP_READ_LOCAL_OOB_DATA:
-		hci_cc_read_local_oob_data_reply(hdev, skb);
+		hci_cc_read_local_oob_data(hdev, skb);
+		break;
+
+	case HCI_OP_READ_LOCAL_OOB_EXT_DATA:
+		hci_cc_read_local_oob_ext_data(hdev, skb);
 		break;
 
 	case HCI_OP_LE_READ_BUFFER_SIZE:
@@ -2250,10 +2647,18 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_user_passkey_neg_reply(hdev, skb);
 		break;
 
+	case HCI_OP_LE_SET_RANDOM_ADDR:
+		hci_cc_le_set_random_addr(hdev, skb);
+		break;
+
 	case HCI_OP_LE_SET_ADV_ENABLE:
 		hci_cc_le_set_adv_enable(hdev, skb);
 		break;
 
+	case HCI_OP_LE_SET_SCAN_PARAM:
+		hci_cc_le_set_scan_param(hdev, skb);
+		break;
+
 	case HCI_OP_LE_SET_SCAN_ENABLE:
 		hci_cc_le_set_scan_enable(hdev, skb);
 		break;
@@ -2262,6 +2667,18 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_le_read_white_list_size(hdev, skb);
 		break;
 
+	case HCI_OP_LE_CLEAR_WHITE_LIST:
+		hci_cc_le_clear_white_list(hdev, skb);
+		break;
+
+	case HCI_OP_LE_ADD_TO_WHITE_LIST:
+		hci_cc_le_add_to_white_list(hdev, skb);
+		break;
+
+	case HCI_OP_LE_DEL_FROM_WHITE_LIST:
+		hci_cc_le_del_from_white_list(hdev, skb);
+		break;
+
 	case HCI_OP_LE_READ_SUPPORTED_STATES:
 		hci_cc_le_read_supported_states(hdev, skb);
 		break;
@@ -2270,10 +2687,22 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_write_le_host_supported(hdev, skb);
 		break;
 
+	case HCI_OP_LE_SET_ADV_PARAM:
+		hci_cc_set_adv_param(hdev, skb);
+		break;
+
 	case HCI_OP_WRITE_REMOTE_AMP_ASSOC:
 		hci_cc_write_remote_amp_assoc(hdev, skb);
 		break;
 
+	case HCI_OP_READ_RSSI:
+		hci_cc_read_rssi(hdev, skb);
+		break;
+
+	case HCI_OP_READ_TX_POWER:
+		hci_cc_read_tx_power(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode);
 		break;
@@ -2357,6 +2786,14 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cs_accept_phylink(hdev, ev->status);
 		break;
 
+	case HCI_OP_LE_CREATE_CONN:
+		hci_cs_le_create_conn(hdev, ev->status);
+		break;
+
+	case HCI_OP_LE_START_ENC:
+		hci_cs_le_start_enc(hdev, ev->status);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode);
 		break;
@@ -2636,14 +3073,16 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
 	if (conn) {
-		if (key->type == HCI_LK_UNAUTH_COMBINATION &&
+		if ((key->type == HCI_LK_UNAUTH_COMBINATION_P192 ||
+		     key->type == HCI_LK_UNAUTH_COMBINATION_P256) &&
 		    conn->auth_type != 0xff && (conn->auth_type & 0x01)) {
 			BT_DBG("%s ignoring unauthenticated key", hdev->name);
 			goto not_found;
 		}
 
 		if (key->type == HCI_LK_COMBINATION && key->pin_len < 16 &&
-		    conn->pending_sec_level == BT_SECURITY_HIGH) {
+		    (conn->pending_sec_level == BT_SECURITY_HIGH ||
+		     conn->pending_sec_level == BT_SECURITY_FIPS)) {
 			BT_DBG("%s ignoring key unauthenticated for high security",
 			       hdev->name);
 			goto not_found;
@@ -2788,7 +3227,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 							      false, &ssp);
 			mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00,
 					  info->dev_class, info->rssi,
-					  !name_known, ssp, NULL, 0);
+					  !name_known, ssp, NULL, 0, NULL, 0);
 		}
 	} else {
 		struct inquiry_info_with_rssi *info = (void *) (skb->data + 1);
@@ -2806,7 +3245,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 							      false, &ssp);
 			mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00,
 					  info->dev_class, info->rssi,
-					  !name_known, ssp, NULL, 0);
+					  !name_known, ssp, NULL, 0, NULL, 0);
 		}
 	}
 
@@ -2850,6 +3289,9 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev,
 			 * features do not indicate SSP support */
 			clear_bit(HCI_CONN_SSP_ENABLED, &conn->flags);
 		}
+
+		if (ev->features[0] & LMP_HOST_SC)
+			set_bit(HCI_CONN_SC_ENABLED, &conn->flags);
 	}
 
 	if (conn->state != BT_CONFIG)
@@ -2911,6 +3353,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev,
 	case 0x1c:	/* SCO interval rejected */
 	case 0x1a:	/* Unsupported Remote Feature */
 	case 0x1f:	/* Unspecified error */
+	case 0x20:	/* Unsupported LMP Parameter value */
 		if (conn->out) {
 			conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) |
 					(hdev->esco_type & EDR_ESCO_MASK);
@@ -2991,7 +3434,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev,
 		eir_len = eir_get_length(info->data, sizeof(info->data));
 		mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00,
 				  info->dev_class, info->rssi, !name_known,
-				  ssp, info->data, eir_len);
+				  ssp, info->data, eir_len, NULL, 0);
 	}
 
 	hci_dev_unlock(hdev);
@@ -3012,6 +3455,12 @@ static void hci_key_refresh_complete_evt(struct hci_dev *hdev,
 	if (!conn)
 		goto unlock;
 
+	/* For BR/EDR the necessary steps are taken through the
+	 * auth_complete event.
+	 */
+	if (conn->type != LE_LINK)
+		goto unlock;
+
 	if (!ev->status)
 		conn->sec_level = conn->pending_sec_level;
 
@@ -3043,24 +3492,20 @@ unlock:
 
 static u8 hci_get_auth_req(struct hci_conn *conn)
 {
-	/* If remote requests dedicated bonding follow that lead */
-	if (conn->remote_auth == HCI_AT_DEDICATED_BONDING ||
-	    conn->remote_auth == HCI_AT_DEDICATED_BONDING_MITM) {
-		/* If both remote and local IO capabilities allow MITM
-		 * protection then require it, otherwise don't */
-		if (conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT ||
-		    conn->io_capability == HCI_IO_NO_INPUT_OUTPUT)
-			return HCI_AT_DEDICATED_BONDING;
-		else
-			return HCI_AT_DEDICATED_BONDING_MITM;
-	}
-
 	/* If remote requests no-bonding follow that lead */
 	if (conn->remote_auth == HCI_AT_NO_BONDING ||
 	    conn->remote_auth == HCI_AT_NO_BONDING_MITM)
 		return conn->remote_auth | (conn->auth_type & 0x01);
 
-	return conn->auth_type;
+	/* If both remote and local have enough IO capabilities, require
+	 * MITM protection
+	 */
+	if (conn->remote_cap != HCI_IO_NO_INPUT_OUTPUT &&
+	    conn->io_capability != HCI_IO_NO_INPUT_OUTPUT)
+		return conn->remote_auth | 0x01;
+
+	/* No MITM protection possible so ignore remote requirement */
+	return (conn->remote_auth & ~0x01) | (conn->auth_type & 0x01);
 }
 
 static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
@@ -3090,8 +3535,25 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		 * to DisplayYesNo as it is not supported by BT spec. */
 		cp.capability = (conn->io_capability == 0x04) ?
 				HCI_IO_DISPLAY_YESNO : conn->io_capability;
-		conn->auth_type = hci_get_auth_req(conn);
-		cp.authentication = conn->auth_type;
+
+		/* If we are initiators, there is no remote information yet */
+		if (conn->remote_auth == 0xff) {
+			cp.authentication = conn->auth_type;
+
+			/* Request MITM protection if our IO caps allow it
+			 * except for the no-bonding case.
+			 * conn->auth_type is not updated here since
+			 * that might cause the user confirmation to be
+			 * rejected in case the remote doesn't have the
+			 * IO capabilities for MITM.
+			 */
+			if (conn->io_capability != HCI_IO_NO_INPUT_OUTPUT &&
+			    cp.authentication != HCI_AT_NO_BONDING)
+				cp.authentication |= 0x01;
+		} else {
+			conn->auth_type = hci_get_auth_req(conn);
+			cp.authentication = conn->auth_type;
+		}
 
 		if (hci_find_remote_oob_data(hdev, &conn->dst) &&
 		    (conn->out || test_bit(HCI_CONN_REMOTE_OOB, &conn->flags)))
@@ -3159,12 +3621,9 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev,
 	rem_mitm = (conn->remote_auth & 0x01);
 
 	/* If we require MITM but the remote device can't provide that
-	 * (it has NoInputNoOutput) then reject the confirmation
-	 * request. The only exception is when we're dedicated bonding
-	 * initiators (connect_cfm_cb set) since then we always have the MITM
-	 * bit set. */
-	if (!conn->connect_cfm_cb && loc_mitm &&
-	    conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT) {
+	 * (it has NoInputNoOutput) then reject the confirmation request
+	 */
+	if (loc_mitm && conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT) {
 		BT_DBG("Rejecting request: remote device can't provide MITM");
 		hci_send_cmd(hdev, HCI_OP_USER_CONFIRM_NEG_REPLY,
 			     sizeof(ev->bdaddr), &ev->bdaddr);
@@ -3177,8 +3636,11 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev,
 
 		/* If we're not the initiators request authorization to
 		 * proceed from user space (mgmt_user_confirm with
-		 * confirm_hint set to 1). */
-		if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
+		 * confirm_hint set to 1). The exception is if neither
+		 * side had MITM in which case we do auto-accept.
+		 */
+		if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) &&
+		    (loc_mitm || rem_mitm)) {
 			BT_DBG("Confirming auto-accept as acceptor");
 			confirm_hint = 1;
 			goto confirm;
@@ -3200,8 +3662,8 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev,
 	}
 
 confirm:
-	mgmt_user_confirm_request(hdev, &ev->bdaddr, ACL_LINK, 0, ev->passkey,
-				  confirm_hint);
+	mgmt_user_confirm_request(hdev, &ev->bdaddr, ACL_LINK, 0,
+				  le32_to_cpu(ev->passkey), confirm_hint);
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -3343,20 +3805,36 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev,
 
 	data = hci_find_remote_oob_data(hdev, &ev->bdaddr);
 	if (data) {
-		struct hci_cp_remote_oob_data_reply cp;
+		if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) {
+			struct hci_cp_remote_oob_ext_data_reply cp;
 
-		bacpy(&cp.bdaddr, &ev->bdaddr);
-		memcpy(cp.hash, data->hash, sizeof(cp.hash));
-		memcpy(cp.randomizer, data->randomizer, sizeof(cp.randomizer));
+			bacpy(&cp.bdaddr, &ev->bdaddr);
+			memcpy(cp.hash192, data->hash192, sizeof(cp.hash192));
+			memcpy(cp.randomizer192, data->randomizer192,
+			       sizeof(cp.randomizer192));
+			memcpy(cp.hash256, data->hash256, sizeof(cp.hash256));
+			memcpy(cp.randomizer256, data->randomizer256,
+			       sizeof(cp.randomizer256));
+
+			hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_EXT_DATA_REPLY,
+				     sizeof(cp), &cp);
+		} else {
+			struct hci_cp_remote_oob_data_reply cp;
+
+			bacpy(&cp.bdaddr, &ev->bdaddr);
+			memcpy(cp.hash, data->hash192, sizeof(cp.hash));
+			memcpy(cp.randomizer, data->randomizer192,
+			       sizeof(cp.randomizer));
 
-		hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY, sizeof(cp),
-			     &cp);
+			hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY,
+				     sizeof(cp), &cp);
+		}
 	} else {
 		struct hci_cp_remote_oob_data_neg_reply cp;
 
 		bacpy(&cp.bdaddr, &ev->bdaddr);
-		hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY, sizeof(cp),
-			     &cp);
+		hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY,
+			     sizeof(cp), &cp);
 	}
 
 unlock:
@@ -3490,6 +3968,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_le_conn_complete *ev = (void *) skb->data;
 	struct hci_conn *conn;
+	struct smp_irk *irk;
 
 	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
 
@@ -3505,63 +3984,223 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 		conn->dst_type = ev->bdaddr_type;
 
-		/* The advertising parameters for own address type
-		 * define which source address and source address
-		 * type this connections has.
-		 */
-		if (bacmp(&conn->src, BDADDR_ANY)) {
-			conn->src_type = ADDR_LE_DEV_PUBLIC;
-		} else {
-			bacpy(&conn->src, &hdev->static_addr);
-			conn->src_type = ADDR_LE_DEV_RANDOM;
-		}
-
 		if (ev->role == LE_CONN_ROLE_MASTER) {
 			conn->out = true;
 			conn->link_mode |= HCI_LM_MASTER;
 		}
+
+		/* If we didn't have a hci_conn object previously
+		 * but we're in master role this must be something
+		 * initiated using a white list. Since white list based
+		 * connections are not "first class citizens" we don't
+		 * have full tracking of them. Therefore, we go ahead
+		 * with a "best effort" approach of determining the
+		 * initiator address based on the HCI_PRIVACY flag.
+		 */
+		if (conn->out) {
+			conn->resp_addr_type = ev->bdaddr_type;
+			bacpy(&conn->resp_addr, &ev->bdaddr);
+			if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) {
+				conn->init_addr_type = ADDR_LE_DEV_RANDOM;
+				bacpy(&conn->init_addr, &hdev->rpa);
+			} else {
+				hci_copy_identity_address(hdev,
+							  &conn->init_addr,
+							  &conn->init_addr_type);
+			}
+		}
+	} else {
+		cancel_delayed_work(&conn->le_conn_timeout);
+	}
+
+	if (!conn->out) {
+		/* Set the responder (our side) address type based on
+		 * the advertising address type.
+		 */
+		conn->resp_addr_type = hdev->adv_addr_type;
+		if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM)
+			bacpy(&conn->resp_addr, &hdev->random_addr);
+		else
+			bacpy(&conn->resp_addr, &hdev->bdaddr);
+
+		conn->init_addr_type = ev->bdaddr_type;
+		bacpy(&conn->init_addr, &ev->bdaddr);
+	}
+
+	/* Lookup the identity address from the stored connection
+	 * address and address type.
+	 *
+	 * When establishing connections to an identity address, the
+	 * connection procedure will store the resolvable random
+	 * address first. Now if it can be converted back into the
+	 * identity address, start using the identity address from
+	 * now on.
+	 */
+	irk = hci_get_irk(hdev, &conn->dst, conn->dst_type);
+	if (irk) {
+		bacpy(&conn->dst, &irk->bdaddr);
+		conn->dst_type = irk->addr_type;
 	}
 
 	if (ev->status) {
-		mgmt_connect_failed(hdev, &conn->dst, conn->type,
-				    conn->dst_type, ev->status);
-		hci_proto_connect_cfm(conn, ev->status);
-		conn->state = BT_CLOSED;
-		hci_conn_del(conn);
+		hci_le_conn_failed(conn, ev->status);
 		goto unlock;
 	}
 
 	if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
-		mgmt_device_connected(hdev, &ev->bdaddr, conn->type,
+		mgmt_device_connected(hdev, &conn->dst, conn->type,
 				      conn->dst_type, 0, NULL, 0, NULL);
 
 	conn->sec_level = BT_SECURITY_LOW;
 	conn->handle = __le16_to_cpu(ev->handle);
 	conn->state = BT_CONNECTED;
 
+	if (test_bit(HCI_6LOWPAN_ENABLED, &hdev->dev_flags))
+		set_bit(HCI_CONN_6LOWPAN, &conn->flags);
+
 	hci_conn_add_sysfs(conn);
 
 	hci_proto_connect_cfm(conn, ev->status);
 
+	hci_pend_le_conn_del(hdev, &conn->dst, conn->dst_type);
+
 unlock:
 	hci_dev_unlock(hdev);
 }
 
+/* This function requires the caller holds hdev->lock */
+static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
+				  u8 addr_type)
+{
+	struct hci_conn *conn;
+	struct smp_irk *irk;
+
+	/* If this is a resolvable address, we should resolve it and then
+	 * update address and address type variables.
+	 */
+	irk = hci_get_irk(hdev, addr, addr_type);
+	if (irk) {
+		addr = &irk->bdaddr;
+		addr_type = irk->addr_type;
+	}
+
+	if (!hci_pend_le_conn_lookup(hdev, addr, addr_type))
+		return;
+
+	conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW,
+			      HCI_AT_NO_BONDING);
+	if (!IS_ERR(conn))
+		return;
+
+	switch (PTR_ERR(conn)) {
+	case -EBUSY:
+		/* If hci_connect() returns -EBUSY it means there is already
+		 * an LE connection attempt going on. Since controllers don't
+		 * support more than one connection attempt at the time, we
+		 * don't consider this an error case.
+		 */
+		break;
+	default:
+		BT_DBG("Failed to connect: err %ld", PTR_ERR(conn));
+	}
+}
+
+static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
+			       u8 bdaddr_type, s8 rssi, u8 *data, u8 len)
+{
+	struct discovery_state *d = &hdev->discovery;
+	bool match;
+
+	/* Passive scanning shouldn't trigger any device found events */
+	if (hdev->le_scan_type == LE_SCAN_PASSIVE) {
+		if (type == LE_ADV_IND || type == LE_ADV_DIRECT_IND)
+			check_pending_le_conn(hdev, bdaddr, bdaddr_type);
+		return;
+	}
+
+	/* If there's nothing pending either store the data from this
+	 * event or send an immediate device found event if the data
+	 * should not be stored for later.
+	 */
+	if (!has_pending_adv_report(hdev)) {
+		/* If the report will trigger a SCAN_REQ store it for
+		 * later merging.
+		 */
+		if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) {
+			store_pending_adv_report(hdev, bdaddr, bdaddr_type,
+						 rssi, data, len);
+			return;
+		}
+
+		mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL,
+				  rssi, 0, 1, data, len, NULL, 0);
+		return;
+	}
+
+	/* Check if the pending report is for the same device as the new one */
+	match = (!bacmp(bdaddr, &d->last_adv_addr) &&
+		 bdaddr_type == d->last_adv_addr_type);
+
+	/* If the pending data doesn't match this report or this isn't a
+	 * scan response (e.g. we got a duplicate ADV_IND) then force
+	 * sending of the pending data.
+	 */
+	if (type != LE_ADV_SCAN_RSP || !match) {
+		/* Send out whatever is in the cache, but skip duplicates */
+		if (!match)
+			mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK,
+					  d->last_adv_addr_type, NULL,
+					  d->last_adv_rssi, 0, 1,
+					  d->last_adv_data,
+					  d->last_adv_data_len, NULL, 0);
+
+		/* If the new report will trigger a SCAN_REQ store it for
+		 * later merging.
+		 */
+		if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) {
+			store_pending_adv_report(hdev, bdaddr, bdaddr_type,
+						 rssi, data, len);
+			return;
+		}
+
+		/* The advertising reports cannot be merged, so clear
+		 * the pending report and send out a device found event.
+		 */
+		clear_pending_adv_report(hdev);
+		mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL,
+				  rssi, 0, 1, data, len, NULL, 0);
+		return;
+	}
+
+	/* If we get here we've got a pending ADV_IND or ADV_SCAN_IND and
+	 * the new event is a SCAN_RSP. We can therefore proceed with
+	 * sending a merged device found event.
+	 */
+	mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK,
+			  d->last_adv_addr_type, NULL, rssi, 0, 1, data, len,
+			  d->last_adv_data, d->last_adv_data_len);
+	clear_pending_adv_report(hdev);
+}
+
 static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	u8 num_reports = skb->data[0];
 	void *ptr = &skb->data[1];
-	s8 rssi;
+
+	hci_dev_lock(hdev);
 
 	while (num_reports--) {
 		struct hci_ev_le_advertising_info *ev = ptr;
+		s8 rssi;
 
 		rssi = ev->data[ev->length];
-		mgmt_device_found(hdev, &ev->bdaddr, LE_LINK, ev->bdaddr_type,
-				  NULL, rssi, 0, 1, ev->data, ev->length);
+		process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
+				   ev->bdaddr_type, rssi, ev->data, ev->length);
 
 		ptr += sizeof(*ev) + ev->length + 1;
 	}
+
+	hci_dev_unlock(hdev);
 }
 
 static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
@@ -3580,7 +4219,7 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	if (conn == NULL)
 		goto not_found;
 
-	ltk = hci_find_ltk(hdev, ev->ediv, ev->random);
+	ltk = hci_find_ltk(hdev, ev->ediv, ev->rand, conn->out);
 	if (ltk == NULL)
 		goto not_found;
 
@@ -3596,7 +4235,13 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp);
 
-	if (ltk->type & HCI_SMP_STK) {
+	/* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a
+	 * temporary key used to encrypt a connection following
+	 * pairing. It is used during the Encrypted Session Setup to
+	 * distribute the keys. Later, security can be re-established
+	 * using a distributed LTK.
+	 */
+	if (ltk->type == HCI_SMP_STK_SLAVE) {
 		list_del(&ltk->list);
 		kfree(ltk);
 	}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 6a6c8bb4fd7..80d25c150a6 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -143,7 +143,7 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
 
 		if (!skb_copy) {
 			/* Create a private copy with headroom */
-			skb_copy = __pskb_copy(skb, 1, GFP_ATOMIC);
+			skb_copy = __pskb_copy_fclone(skb, 1, GFP_ATOMIC, true);
 			if (!skb_copy)
 				continue;
 
@@ -211,22 +211,22 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb)
 
 	switch (bt_cb(skb)->pkt_type) {
 	case HCI_COMMAND_PKT:
-		opcode = __constant_cpu_to_le16(HCI_MON_COMMAND_PKT);
+		opcode = cpu_to_le16(HCI_MON_COMMAND_PKT);
 		break;
 	case HCI_EVENT_PKT:
-		opcode = __constant_cpu_to_le16(HCI_MON_EVENT_PKT);
+		opcode = cpu_to_le16(HCI_MON_EVENT_PKT);
 		break;
 	case HCI_ACLDATA_PKT:
 		if (bt_cb(skb)->incoming)
-			opcode = __constant_cpu_to_le16(HCI_MON_ACL_RX_PKT);
+			opcode = cpu_to_le16(HCI_MON_ACL_RX_PKT);
 		else
-			opcode = __constant_cpu_to_le16(HCI_MON_ACL_TX_PKT);
+			opcode = cpu_to_le16(HCI_MON_ACL_TX_PKT);
 		break;
 	case HCI_SCODATA_PKT:
 		if (bt_cb(skb)->incoming)
-			opcode = __constant_cpu_to_le16(HCI_MON_SCO_RX_PKT);
+			opcode = cpu_to_le16(HCI_MON_SCO_RX_PKT);
 		else
-			opcode = __constant_cpu_to_le16(HCI_MON_SCO_TX_PKT);
+			opcode = cpu_to_le16(HCI_MON_SCO_TX_PKT);
 		break;
 	default:
 		return;
@@ -247,8 +247,8 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb)
 			struct hci_mon_hdr *hdr;
 
 			/* Create a private copy with headroom */
-			skb_copy = __pskb_copy(skb, HCI_MON_HDR_SIZE,
-					       GFP_ATOMIC);
+			skb_copy = __pskb_copy_fclone(skb, HCI_MON_HDR_SIZE,
+						      GFP_ATOMIC, true);
 			if (!skb_copy)
 				continue;
 
@@ -319,7 +319,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event)
 		bacpy(&ni->bdaddr, &hdev->bdaddr);
 		memcpy(ni->name, hdev->name, 8);
 
-		opcode = __constant_cpu_to_le16(HCI_MON_NEW_INDEX);
+		opcode = cpu_to_le16(HCI_MON_NEW_INDEX);
 		break;
 
 	case HCI_DEV_UNREG:
@@ -327,7 +327,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event)
 		if (!skb)
 			return NULL;
 
-		opcode = __constant_cpu_to_le16(HCI_MON_DEL_INDEX);
+		opcode = cpu_to_le16(HCI_MON_DEL_INDEX);
 		break;
 
 	default:
@@ -524,16 +524,7 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
 	case HCISETRAW:
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
-
-		if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
-			return -EPERM;
-
-		if (arg)
-			set_bit(HCI_RAW, &hdev->flags);
-		else
-			clear_bit(HCI_RAW, &hdev->flags);
-
-		return 0;
+		return -EOPNOTSUPP;
 
 	case HCIGETCONNINFO:
 		return hci_get_conn_info(hdev, (void __user *) arg);
@@ -716,6 +707,7 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
 		err = hci_dev_open(hdev->id);
 		if (err) {
 			clear_bit(HCI_USER_CHANNEL, &hdev->dev_flags);
+			mgmt_index_added(hdev);
 			hci_dev_put(hdev);
 			goto done;
 		}
@@ -940,8 +932,22 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	bt_cb(skb)->pkt_type = *((unsigned char *) skb->data);
 	skb_pull(skb, 1);
 
-	if (hci_pi(sk)->channel == HCI_CHANNEL_RAW &&
-	    bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
+	if (hci_pi(sk)->channel == HCI_CHANNEL_USER) {
+		/* No permission check is needed for user channel
+		 * since that gets enforced when binding the socket.
+		 *
+		 * However check that the packet type is valid.
+		 */
+		if (bt_cb(skb)->pkt_type != HCI_COMMAND_PKT &&
+		    bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
+		    bt_cb(skb)->pkt_type != HCI_SCODATA_PKT) {
+			err = -EINVAL;
+			goto drop;
+		}
+
+		skb_queue_tail(&hdev->raw_q, skb);
+		queue_work(hdev->workqueue, &hdev->tx_work);
+	} else if (bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
 		u16 opcode = get_unaligned_le16(skb->data);
 		u16 ogf = hci_opcode_ogf(opcode);
 		u16 ocf = hci_opcode_ocf(opcode);
@@ -972,14 +978,6 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 			goto drop;
 		}
 
-		if (hci_pi(sk)->channel == HCI_CHANNEL_USER &&
-		    bt_cb(skb)->pkt_type != HCI_COMMAND_PKT &&
-		    bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
-		    bt_cb(skb)->pkt_type != HCI_SCODATA_PKT) {
-			err = -EINVAL;
-			goto drop;
-		}
-
 		skb_queue_tail(&hdev->raw_q, skb);
 		queue_work(hdev->workqueue, &hdev->tx_work);
 	}
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index 0b61250cfdf..555982a78a5 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -49,14 +49,7 @@ static struct attribute *bt_link_attrs[] = {
 	NULL
 };
 
-static struct attribute_group bt_link_group = {
-	.attrs = bt_link_attrs,
-};
-
-static const struct attribute_group *bt_link_groups[] = {
-	&bt_link_group,
-	NULL
-};
+ATTRIBUTE_GROUPS(bt_link);
 
 static void bt_link_release(struct device *dev)
 {
@@ -182,14 +175,7 @@ static struct attribute *bt_host_attrs[] = {
 	NULL
 };
 
-static struct attribute_group bt_host_group = {
-	.attrs = bt_host_attrs,
-};
-
-static const struct attribute_group *bt_host_groups[] = {
-	&bt_host_group,
-	NULL
-};
+ATTRIBUTE_GROUPS(bt_host);
 
 static void bt_host_release(struct device *dev)
 {
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 292e619db89..8181ea4bc2f 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -223,51 +223,6 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb)
 	input_sync(dev);
 }
 
-static int hidp_send_report(struct hidp_session *session, struct hid_report *report)
-{
-	unsigned char hdr;
-	u8 *buf;
-	int rsize, ret;
-
-	buf = hid_alloc_report_buf(report, GFP_ATOMIC);
-	if (!buf)
-		return -EIO;
-
-	hid_output_report(report, buf);
-	hdr = HIDP_TRANS_DATA | HIDP_DATA_RTYPE_OUPUT;
-
-	rsize = ((report->size - 1) >> 3) + 1 + (report->id > 0);
-	ret = hidp_send_intr_message(session, hdr, buf, rsize);
-
-	kfree(buf);
-	return ret;
-}
-
-static int hidp_hidinput_event(struct input_dev *dev, unsigned int type,
-			       unsigned int code, int value)
-{
-	struct hid_device *hid = input_get_drvdata(dev);
-	struct hidp_session *session = hid->driver_data;
-	struct hid_field *field;
-	int offset;
-
-	BT_DBG("session %p type %d code %d value %d",
-	       session, type, code, value);
-
-	if (type != EV_LED)
-		return -1;
-
-	offset = hidinput_find_field(hid, type, code, &field);
-	if (offset == -1) {
-		hid_warn(dev, "event field not found\n");
-		return -1;
-	}
-
-	hid_set_field(field, offset, value);
-
-	return hidp_send_report(session, field->report);
-}
-
 static int hidp_get_raw_report(struct hid_device *hid,
 		unsigned char report_number,
 		unsigned char *data, size_t count,
@@ -353,17 +308,24 @@ err:
 	return ret;
 }
 
-static int hidp_output_raw_report(struct hid_device *hid, unsigned char *data, size_t count,
-		unsigned char report_type)
+static int hidp_set_raw_report(struct hid_device *hid, unsigned char reportnum,
+			       unsigned char *data, size_t count,
+			       unsigned char report_type)
 {
 	struct hidp_session *session = hid->driver_data;
 	int ret;
 
-	if (report_type == HID_OUTPUT_REPORT) {
-		report_type = HIDP_TRANS_DATA | HIDP_DATA_RTYPE_OUPUT;
-		return hidp_send_intr_message(session, report_type,
-					      data, count);
-	} else if (report_type != HID_FEATURE_REPORT) {
+	switch (report_type) {
+	case HID_FEATURE_REPORT:
+		report_type = HIDP_TRANS_SET_REPORT | HIDP_DATA_RTYPE_FEATURE;
+		break;
+	case HID_INPUT_REPORT:
+		report_type = HIDP_TRANS_SET_REPORT | HIDP_DATA_RTYPE_INPUT;
+		break;
+	case HID_OUTPUT_REPORT:
+		report_type = HIDP_TRANS_SET_REPORT | HIDP_DATA_RTYPE_OUPUT;
+		break;
+	default:
 		return -EINVAL;
 	}
 
@@ -371,8 +333,8 @@ static int hidp_output_raw_report(struct hid_device *hid, unsigned char *data, s
 		return -ERESTARTSYS;
 
 	/* Set up our wait, and send the report request to the device. */
+	data[0] = reportnum;
 	set_bit(HIDP_WAITING_FOR_SEND_ACK, &session->flags);
-	report_type = HIDP_TRANS_SET_REPORT | HIDP_DATA_RTYPE_FEATURE;
 	ret = hidp_send_ctrl_message(session, report_type, data, count);
 	if (ret)
 		goto err;
@@ -411,6 +373,29 @@ err:
 	return ret;
 }
 
+static int hidp_output_report(struct hid_device *hid, __u8 *data, size_t count)
+{
+	struct hidp_session *session = hid->driver_data;
+
+	return hidp_send_intr_message(session,
+				      HIDP_TRANS_DATA | HIDP_DATA_RTYPE_OUPUT,
+				      data, count);
+}
+
+static int hidp_raw_request(struct hid_device *hid, unsigned char reportnum,
+			    __u8 *buf, size_t len, unsigned char rtype,
+			    int reqtype)
+{
+	switch (reqtype) {
+	case HID_REQ_GET_REPORT:
+		return hidp_get_raw_report(hid, reportnum, buf, len, rtype);
+	case HID_REQ_SET_REPORT:
+		return hidp_set_raw_report(hid, reportnum, buf, len, rtype);
+	default:
+		return -EIO;
+	}
+}
+
 static void hidp_idle_timeout(unsigned long arg)
 {
 	struct hidp_session *session = (struct hidp_session *) arg;
@@ -430,6 +415,16 @@ static void hidp_del_timer(struct hidp_session *session)
 		del_timer(&session->timer);
 }
 
+static void hidp_process_report(struct hidp_session *session,
+				int type, const u8 *data, int len, int intr)
+{
+	if (len > HID_MAX_BUFFER_SIZE)
+		len = HID_MAX_BUFFER_SIZE;
+
+	memcpy(session->input_buf, data, len);
+	hid_input_report(session->hid, type, session->input_buf, len, intr);
+}
+
 static void hidp_process_handshake(struct hidp_session *session,
 					unsigned char param)
 {
@@ -502,7 +497,8 @@ static int hidp_process_data(struct hidp_session *session, struct sk_buff *skb,
 			hidp_input_report(session, skb);
 
 		if (session->hid)
-			hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 0);
+			hidp_process_report(session, HID_INPUT_REPORT,
+					    skb->data, skb->len, 0);
 		break;
 
 	case HIDP_DATA_RTYPE_OTHER:
@@ -584,7 +580,8 @@ static void hidp_recv_intr_frame(struct hidp_session *session,
 			hidp_input_report(session, skb);
 
 		if (session->hid) {
-			hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 1);
+			hidp_process_report(session, HID_INPUT_REPORT,
+					    skb->data, skb->len, 1);
 			BT_DBG("report len %d", skb->len);
 		}
 	} else {
@@ -727,7 +724,8 @@ static struct hid_ll_driver hidp_hid_driver = {
 	.stop = hidp_stop,
 	.open  = hidp_open,
 	.close = hidp_close,
-	.hidinput_input_event = hidp_hidinput_event,
+	.raw_request = hidp_raw_request,
+	.output_report = hidp_output_report,
 };
 
 /* This function sets up the hid device. It does not add it
@@ -769,15 +767,15 @@ static int hidp_setup_hid(struct hidp_session *session,
 	snprintf(hid->phys, sizeof(hid->phys), "%pMR",
 		 &l2cap_pi(session->ctrl_sock->sk)->chan->src);
 
+	/* NOTE: Some device modules depend on the dst address being stored in
+	 * uniq. Please be aware of this before making changes to this behavior.
+	 */
 	snprintf(hid->uniq, sizeof(hid->uniq), "%pMR",
 		 &l2cap_pi(session->ctrl_sock->sk)->chan->dst);
 
 	hid->dev.parent = &session->conn->hcon->dev;
 	hid->ll_driver = &hidp_hid_driver;
 
-	hid->hid_get_raw_report = hidp_get_raw_report;
-	hid->hid_output_raw_report = hidp_output_raw_report;
-
 	/* True if device is blacklisted in drivers/hid/hid-core.c */
 	if (hid_ignore(hid)) {
 		hid_destroy_device(session->hid);
diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h
index ab5241400cf..8798492a6e9 100644
--- a/net/bluetooth/hidp/hidp.h
+++ b/net/bluetooth/hidp/hidp.h
@@ -24,6 +24,7 @@
 #define __HIDP_H
 
 #include <linux/types.h>
+#include <linux/hid.h>
 #include <linux/kref.h>
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/l2cap.h>
@@ -179,6 +180,9 @@ struct hidp_session {
 
 	/* Used in hidp_output_raw_report() */
 	int output_report_success; /* boolean */
+
+	/* temporary input buffer */
+	u8 input_buf[HID_MAX_BUFFER_SIZE];
 };
 
 /* HIDP init defines */
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 4af3821df88..323f23cd2c3 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -40,6 +40,9 @@
 #include "smp.h"
 #include "a2mp.h"
 #include "amp.h"
+#include "6lowpan.h"
+
+#define LE_FLOWCTL_MAX_CREDITS 65535
 
 bool disable_ertm;
 
@@ -49,6 +52,9 @@ static u8 l2cap_fixed_chan[8] = { L2CAP_FC_L2CAP | L2CAP_FC_CONNLESS, };
 static LIST_HEAD(chan_list);
 static DEFINE_RWLOCK(chan_list_lock);
 
+static u16 le_max_credits = L2CAP_LE_MAX_CREDITS;
+static u16 le_default_mps = L2CAP_LE_DEFAULT_MPS;
+
 static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn,
 				       u8 code, u8 ident, u16 dlen, void *data);
 static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len,
@@ -213,9 +219,14 @@ int l2cap_add_scid(struct l2cap_chan *chan,  __u16 scid)
 
 static u16 l2cap_alloc_cid(struct l2cap_conn *conn)
 {
-	u16 cid = L2CAP_CID_DYN_START;
+	u16 cid, dyn_end;
+
+	if (conn->hcon->type == LE_LINK)
+		dyn_end = L2CAP_CID_LE_DYN_END;
+	else
+		dyn_end = L2CAP_CID_DYN_END;
 
-	for (; cid < L2CAP_CID_DYN_END; cid++) {
+	for (cid = L2CAP_CID_DYN_START; cid < dyn_end; cid++) {
 		if (!__l2cap_get_chan_by_scid(conn, cid))
 			return cid;
 	}
@@ -321,44 +332,20 @@ static inline bool l2cap_seq_list_contains(struct l2cap_seq_list *seq_list,
 	return seq_list->list[seq & seq_list->mask] != L2CAP_SEQ_LIST_CLEAR;
 }
 
-static u16 l2cap_seq_list_remove(struct l2cap_seq_list *seq_list, u16 seq)
+static inline u16 l2cap_seq_list_pop(struct l2cap_seq_list *seq_list)
 {
+	u16 seq = seq_list->head;
 	u16 mask = seq_list->mask;
 
-	if (seq_list->head == L2CAP_SEQ_LIST_CLEAR) {
-		/* In case someone tries to pop the head of an empty list */
-		return L2CAP_SEQ_LIST_CLEAR;
-	} else if (seq_list->head == seq) {
-		/* Head can be removed in constant time */
-		seq_list->head = seq_list->list[seq & mask];
-		seq_list->list[seq & mask] = L2CAP_SEQ_LIST_CLEAR;
-
-		if (seq_list->head == L2CAP_SEQ_LIST_TAIL) {
-			seq_list->head = L2CAP_SEQ_LIST_CLEAR;
-			seq_list->tail = L2CAP_SEQ_LIST_CLEAR;
-		}
-	} else {
-		/* Walk the list to find the sequence number */
-		u16 prev = seq_list->head;
-		while (seq_list->list[prev & mask] != seq) {
-			prev = seq_list->list[prev & mask];
-			if (prev == L2CAP_SEQ_LIST_TAIL)
-				return L2CAP_SEQ_LIST_CLEAR;
-		}
+	seq_list->head = seq_list->list[seq & mask];
+	seq_list->list[seq & mask] = L2CAP_SEQ_LIST_CLEAR;
 
-		/* Unlink the number from the list and clear it */
-		seq_list->list[prev & mask] = seq_list->list[seq & mask];
-		seq_list->list[seq & mask] = L2CAP_SEQ_LIST_CLEAR;
-		if (seq_list->tail == seq)
-			seq_list->tail = prev;
+	if (seq_list->head == L2CAP_SEQ_LIST_TAIL) {
+		seq_list->head = L2CAP_SEQ_LIST_CLEAR;
+		seq_list->tail = L2CAP_SEQ_LIST_CLEAR;
 	}
-	return seq;
-}
 
-static inline u16 l2cap_seq_list_pop(struct l2cap_seq_list *seq_list)
-{
-	/* Remove the head in constant time */
-	return l2cap_seq_list_remove(seq_list, seq_list->head);
+	return seq;
 }
 
 static void l2cap_seq_list_clear(struct l2cap_seq_list *seq_list)
@@ -484,12 +471,30 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan)
 	chan->max_tx = L2CAP_DEFAULT_MAX_TX;
 	chan->tx_win = L2CAP_DEFAULT_TX_WINDOW;
 	chan->tx_win_max = L2CAP_DEFAULT_TX_WINDOW;
+	chan->remote_max_tx = chan->max_tx;
+	chan->remote_tx_win = chan->tx_win;
 	chan->ack_win = L2CAP_DEFAULT_TX_WINDOW;
 	chan->sec_level = BT_SECURITY_LOW;
+	chan->flush_to = L2CAP_DEFAULT_FLUSH_TO;
+	chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO;
+	chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO;
+	chan->conf_state = 0;
 
 	set_bit(FLAG_FORCE_ACTIVE, &chan->flags);
 }
 
+static void l2cap_le_flowctl_init(struct l2cap_chan *chan)
+{
+	chan->sdu = NULL;
+	chan->sdu_last_frag = NULL;
+	chan->sdu_len = 0;
+	chan->tx_credits = 0;
+	chan->rx_credits = le_max_credits;
+	chan->mps = min_t(u16, chan->imtu, le_default_mps);
+
+	skb_queue_head_init(&chan->tx_q);
+}
+
 void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
 {
 	BT_DBG("conn %p, psm 0x%2.2x, dcid 0x%4.4x", conn,
@@ -501,18 +506,10 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
 
 	switch (chan->chan_type) {
 	case L2CAP_CHAN_CONN_ORIENTED:
-		if (conn->hcon->type == LE_LINK) {
-			/* LE connection */
-			chan->omtu = L2CAP_DEFAULT_MTU;
-			if (chan->dcid == L2CAP_CID_ATT)
-				chan->scid = L2CAP_CID_ATT;
-			else
-				chan->scid = l2cap_alloc_cid(conn);
-		} else {
-			/* Alloc CID for connection-oriented socket */
-			chan->scid = l2cap_alloc_cid(conn);
+		/* Alloc CID for connection-oriented socket */
+		chan->scid = l2cap_alloc_cid(conn);
+		if (conn->hcon->type == ACL_LINK)
 			chan->omtu = L2CAP_DEFAULT_MTU;
-		}
 		break;
 
 	case L2CAP_CHAN_CONN_LESS:
@@ -522,11 +519,8 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
 		chan->omtu = L2CAP_DEFAULT_MTU;
 		break;
 
-	case L2CAP_CHAN_CONN_FIX_A2MP:
-		chan->scid = L2CAP_CID_A2MP;
-		chan->dcid = L2CAP_CID_A2MP;
-		chan->omtu = L2CAP_A2MP_DEFAULT_MTU;
-		chan->imtu = L2CAP_A2MP_DEFAULT_MTU;
+	case L2CAP_CHAN_FIXED:
+		/* Caller will set CID and CID specific MTU values */
 		break;
 
 	default:
@@ -574,7 +568,7 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err)
 
 		chan->conn = NULL;
 
-		if (chan->chan_type != L2CAP_CHAN_CONN_FIX_A2MP)
+		if (chan->scid != L2CAP_CID_A2MP)
 			hci_conn_drop(conn->hcon);
 
 		if (mgr && mgr->bredr_chan == chan)
@@ -597,6 +591,10 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err)
 	case L2CAP_MODE_BASIC:
 		break;
 
+	case L2CAP_MODE_LE_FLOWCTL:
+		skb_queue_purge(&chan->tx_q);
+		break;
+
 	case L2CAP_MODE_ERTM:
 		__clear_retrans_timer(chan);
 		__clear_monitor_timer(chan);
@@ -617,6 +615,67 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err)
 	return;
 }
 
+void l2cap_conn_update_id_addr(struct hci_conn *hcon)
+{
+	struct l2cap_conn *conn = hcon->l2cap_data;
+	struct l2cap_chan *chan;
+
+	mutex_lock(&conn->chan_lock);
+
+	list_for_each_entry(chan, &conn->chan_l, list) {
+		l2cap_chan_lock(chan);
+		bacpy(&chan->dst, &hcon->dst);
+		chan->dst_type = bdaddr_type(hcon, hcon->dst_type);
+		l2cap_chan_unlock(chan);
+	}
+
+	mutex_unlock(&conn->chan_lock);
+}
+
+static void l2cap_chan_le_connect_reject(struct l2cap_chan *chan)
+{
+	struct l2cap_conn *conn = chan->conn;
+	struct l2cap_le_conn_rsp rsp;
+	u16 result;
+
+	if (test_bit(FLAG_DEFER_SETUP, &chan->flags))
+		result = L2CAP_CR_AUTHORIZATION;
+	else
+		result = L2CAP_CR_BAD_PSM;
+
+	l2cap_state_change(chan, BT_DISCONN);
+
+	rsp.dcid    = cpu_to_le16(chan->scid);
+	rsp.mtu     = cpu_to_le16(chan->imtu);
+	rsp.mps     = cpu_to_le16(chan->mps);
+	rsp.credits = cpu_to_le16(chan->rx_credits);
+	rsp.result  = cpu_to_le16(result);
+
+	l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CONN_RSP, sizeof(rsp),
+		       &rsp);
+}
+
+static void l2cap_chan_connect_reject(struct l2cap_chan *chan)
+{
+	struct l2cap_conn *conn = chan->conn;
+	struct l2cap_conn_rsp rsp;
+	u16 result;
+
+	if (test_bit(FLAG_DEFER_SETUP, &chan->flags))
+		result = L2CAP_CR_SEC_BLOCK;
+	else
+		result = L2CAP_CR_BAD_PSM;
+
+	l2cap_state_change(chan, BT_DISCONN);
+
+	rsp.scid   = cpu_to_le16(chan->dcid);
+	rsp.dcid   = cpu_to_le16(chan->scid);
+	rsp.result = cpu_to_le16(result);
+	rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
+
+	l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp);
+}
+
 void l2cap_chan_close(struct l2cap_chan *chan, int reason)
 {
 	struct l2cap_conn *conn = chan->conn;
@@ -630,8 +689,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason)
 
 	case BT_CONNECTED:
 	case BT_CONFIG:
-		if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED &&
-		    conn->hcon->type == ACL_LINK) {
+		if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED) {
 			__set_chan_timer(chan, chan->ops->get_sndtimeo(chan));
 			l2cap_send_disconn_req(chan, reason);
 		} else
@@ -639,24 +697,11 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason)
 		break;
 
 	case BT_CONNECT2:
-		if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED &&
-		    conn->hcon->type == ACL_LINK) {
-			struct l2cap_conn_rsp rsp;
-			__u16 result;
-
-			if (test_bit(FLAG_DEFER_SETUP, &chan->flags))
-				result = L2CAP_CR_SEC_BLOCK;
-			else
-				result = L2CAP_CR_BAD_PSM;
-
-			l2cap_state_change(chan, BT_DISCONN);
-
-			rsp.scid   = cpu_to_le16(chan->dcid);
-			rsp.dcid   = cpu_to_le16(chan->scid);
-			rsp.result = cpu_to_le16(result);
-			rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO);
-			l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP,
-				       sizeof(rsp), &rsp);
+		if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED) {
+			if (conn->hcon->type == ACL_LINK)
+				l2cap_chan_connect_reject(chan);
+			else if (conn->hcon->type == LE_LINK)
+				l2cap_chan_le_connect_reject(chan);
 		}
 
 		l2cap_chan_del(chan, reason);
@@ -679,6 +724,7 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan)
 	case L2CAP_CHAN_RAW:
 		switch (chan->sec_level) {
 		case BT_SECURITY_HIGH:
+		case BT_SECURITY_FIPS:
 			return HCI_AT_DEDICATED_BONDING_MITM;
 		case BT_SECURITY_MEDIUM:
 			return HCI_AT_DEDICATED_BONDING;
@@ -687,21 +733,23 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan)
 		}
 		break;
 	case L2CAP_CHAN_CONN_LESS:
-		if (chan->psm == __constant_cpu_to_le16(L2CAP_PSM_3DSP)) {
+		if (chan->psm == cpu_to_le16(L2CAP_PSM_3DSP)) {
 			if (chan->sec_level == BT_SECURITY_LOW)
 				chan->sec_level = BT_SECURITY_SDP;
 		}
-		if (chan->sec_level == BT_SECURITY_HIGH)
+		if (chan->sec_level == BT_SECURITY_HIGH ||
+		    chan->sec_level == BT_SECURITY_FIPS)
 			return HCI_AT_NO_BONDING_MITM;
 		else
 			return HCI_AT_NO_BONDING;
 		break;
 	case L2CAP_CHAN_CONN_ORIENTED:
-		if (chan->psm == __constant_cpu_to_le16(L2CAP_PSM_SDP)) {
+		if (chan->psm == cpu_to_le16(L2CAP_PSM_SDP)) {
 			if (chan->sec_level == BT_SECURITY_LOW)
 				chan->sec_level = BT_SECURITY_SDP;
 
-			if (chan->sec_level == BT_SECURITY_HIGH)
+			if (chan->sec_level == BT_SECURITY_HIGH ||
+			    chan->sec_level == BT_SECURITY_FIPS)
 				return HCI_AT_NO_BONDING_MITM;
 			else
 				return HCI_AT_NO_BONDING;
@@ -710,6 +758,7 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan)
 	default:
 		switch (chan->sec_level) {
 		case BT_SECURITY_HIGH:
+		case BT_SECURITY_FIPS:
 			return HCI_AT_GENERAL_BONDING_MITM;
 		case BT_SECURITY_MEDIUM:
 			return HCI_AT_GENERAL_BONDING;
@@ -726,6 +775,9 @@ int l2cap_chan_check_security(struct l2cap_chan *chan)
 	struct l2cap_conn *conn = chan->conn;
 	__u8 auth_type;
 
+	if (conn->hcon->type == LE_LINK)
+		return smp_conn_security(conn->hcon, chan->sec_level);
+
 	auth_type = l2cap_get_auth_type(chan);
 
 	return hci_conn_security(conn->hcon, chan->sec_level, auth_type);
@@ -1152,16 +1204,57 @@ static void l2cap_chan_ready(struct l2cap_chan *chan)
 	chan->conf_state = 0;
 	__clear_chan_timer(chan);
 
+	if (chan->mode == L2CAP_MODE_LE_FLOWCTL && !chan->tx_credits)
+		chan->ops->suspend(chan);
+
 	chan->state = BT_CONNECTED;
 
 	chan->ops->ready(chan);
 }
 
+static void l2cap_le_connect(struct l2cap_chan *chan)
+{
+	struct l2cap_conn *conn = chan->conn;
+	struct l2cap_le_conn_req req;
+
+	if (test_and_set_bit(FLAG_LE_CONN_REQ_SENT, &chan->flags))
+		return;
+
+	req.psm     = chan->psm;
+	req.scid    = cpu_to_le16(chan->scid);
+	req.mtu     = cpu_to_le16(chan->imtu);
+	req.mps     = cpu_to_le16(chan->mps);
+	req.credits = cpu_to_le16(chan->rx_credits);
+
+	chan->ident = l2cap_get_ident(conn);
+
+	l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CONN_REQ,
+		       sizeof(req), &req);
+}
+
+static void l2cap_le_start(struct l2cap_chan *chan)
+{
+	struct l2cap_conn *conn = chan->conn;
+
+	if (!smp_conn_security(conn->hcon, chan->sec_level))
+		return;
+
+	if (!chan->psm) {
+		l2cap_chan_ready(chan);
+		return;
+	}
+
+	if (chan->state == BT_CONNECT)
+		l2cap_le_connect(chan);
+}
+
 static void l2cap_start_connection(struct l2cap_chan *chan)
 {
 	if (__amp_capable(chan)) {
 		BT_DBG("chan %p AMP capable: discover AMPs", chan);
 		a2mp_discover_amp(chan);
+	} else if (chan->conn->hcon->type == LE_LINK) {
+		l2cap_le_start(chan);
 	} else {
 		l2cap_send_conn_req(chan);
 	}
@@ -1172,7 +1265,7 @@ static void l2cap_do_start(struct l2cap_chan *chan)
 	struct l2cap_conn *conn = chan->conn;
 
 	if (conn->hcon->type == LE_LINK) {
-		l2cap_chan_ready(chan);
+		l2cap_le_start(chan);
 		return;
 	}
 
@@ -1186,7 +1279,7 @@ static void l2cap_do_start(struct l2cap_chan *chan)
 		}
 	} else {
 		struct l2cap_info_req req;
-		req.type = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK);
+		req.type = cpu_to_le16(L2CAP_IT_FEAT_MASK);
 
 		conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_SENT;
 		conn->info_ident = l2cap_get_ident(conn);
@@ -1228,7 +1321,7 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err)
 		__clear_ack_timer(chan);
 	}
 
-	if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) {
+	if (chan->scid == L2CAP_CID_A2MP) {
 		l2cap_state_change(chan, BT_DISCONN);
 		return;
 	}
@@ -1283,18 +1376,18 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
 
 			if (l2cap_chan_check_security(chan)) {
 				if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) {
-					rsp.result = __constant_cpu_to_le16(L2CAP_CR_PEND);
-					rsp.status = __constant_cpu_to_le16(L2CAP_CS_AUTHOR_PEND);
+					rsp.result = cpu_to_le16(L2CAP_CR_PEND);
+					rsp.status = cpu_to_le16(L2CAP_CS_AUTHOR_PEND);
 					chan->ops->defer(chan);
 
 				} else {
 					l2cap_state_change(chan, BT_CONFIG);
-					rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS);
-					rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO);
+					rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS);
+					rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
 				}
 			} else {
-				rsp.result = __constant_cpu_to_le16(L2CAP_CR_PEND);
-				rsp.status = __constant_cpu_to_le16(L2CAP_CS_AUTHEN_PEND);
+				rsp.result = cpu_to_le16(L2CAP_CR_PEND);
+				rsp.status = cpu_to_le16(L2CAP_CS_AUTHEN_PEND);
 			}
 
 			l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP,
@@ -1367,6 +1460,8 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn)
 
 	BT_DBG("");
 
+	bt_6lowpan_add_conn(conn);
+
 	/* Check if we have socket listening on cid */
 	pchan = l2cap_global_chan_by_scid(BT_LISTEN, L2CAP_CID_ATT,
 					  &hcon->src, &hcon->dst);
@@ -1389,8 +1484,6 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn)
 	if (!chan)
 		goto clean;
 
-	chan->dcid = L2CAP_CID_ATT;
-
 	bacpy(&chan->src, &hcon->src);
 	bacpy(&chan->dst, &hcon->dst);
 	chan->src_type = bdaddr_type(hcon, hcon->src_type);
@@ -1424,15 +1517,13 @@ static void l2cap_conn_ready(struct l2cap_conn *conn)
 
 		l2cap_chan_lock(chan);
 
-		if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) {
+		if (chan->scid == L2CAP_CID_A2MP) {
 			l2cap_chan_unlock(chan);
 			continue;
 		}
 
 		if (hcon->type == LE_LINK) {
-			if (smp_conn_security(hcon, chan->sec_level))
-				l2cap_chan_ready(chan);
-
+			l2cap_le_start(chan);
 		} else if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) {
 			l2cap_chan_ready(chan);
 
@@ -1444,6 +1535,8 @@ static void l2cap_conn_ready(struct l2cap_conn *conn)
 	}
 
 	mutex_unlock(&conn->chan_lock);
+
+	queue_work(hcon->hdev->workqueue, &conn->pending_rx_work);
 }
 
 /* Notify sockets that we cannot guaranty reliability anymore */
@@ -1569,6 +1662,15 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 
 	kfree_skb(conn->rx_skb);
 
+	skb_queue_purge(&conn->pending_rx);
+
+	/* We can not call flush_work(&conn->pending_rx_work) here since we
+	 * might block if we are running on a worker from the same workqueue
+	 * pending_rx_work is waiting on.
+	 */
+	if (work_pending(&conn->pending_rx_work))
+		cancel_work_sync(&conn->pending_rx_work);
+
 	l2cap_unregister_all_users(conn);
 
 	mutex_lock(&conn->chan_lock);
@@ -1616,66 +1718,6 @@ static void security_timeout(struct work_struct *work)
 	}
 }
 
-static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
-{
-	struct l2cap_conn *conn = hcon->l2cap_data;
-	struct hci_chan *hchan;
-
-	if (conn)
-		return conn;
-
-	hchan = hci_chan_create(hcon);
-	if (!hchan)
-		return NULL;
-
-	conn = kzalloc(sizeof(struct l2cap_conn), GFP_KERNEL);
-	if (!conn) {
-		hci_chan_del(hchan);
-		return NULL;
-	}
-
-	kref_init(&conn->ref);
-	hcon->l2cap_data = conn;
-	conn->hcon = hcon;
-	hci_conn_get(conn->hcon);
-	conn->hchan = hchan;
-
-	BT_DBG("hcon %p conn %p hchan %p", hcon, conn, hchan);
-
-	switch (hcon->type) {
-	case LE_LINK:
-		if (hcon->hdev->le_mtu) {
-			conn->mtu = hcon->hdev->le_mtu;
-			break;
-		}
-		/* fall through */
-	default:
-		conn->mtu = hcon->hdev->acl_mtu;
-		break;
-	}
-
-	conn->feat_mask = 0;
-
-	if (hcon->type == ACL_LINK)
-		conn->hs_enabled = test_bit(HCI_HS_ENABLED,
-					    &hcon->hdev->dev_flags);
-
-	spin_lock_init(&conn->lock);
-	mutex_init(&conn->chan_lock);
-
-	INIT_LIST_HEAD(&conn->chan_l);
-	INIT_LIST_HEAD(&conn->users);
-
-	if (hcon->type == LE_LINK)
-		INIT_DELAYED_WORK(&conn->security_timer, security_timeout);
-	else
-		INIT_DELAYED_WORK(&conn->info_timer, l2cap_info_timeout);
-
-	conn->disc_reason = HCI_ERROR_REMOTE_USER_TERM;
-
-	return conn;
-}
-
 static void l2cap_conn_free(struct kref *ref)
 {
 	struct l2cap_conn *conn = container_of(ref, struct l2cap_conn, ref);
@@ -1703,7 +1745,8 @@ EXPORT_SYMBOL(l2cap_conn_put);
  */
 static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
 						   bdaddr_t *src,
-						   bdaddr_t *dst)
+						   bdaddr_t *dst,
+						   u8 link_type)
 {
 	struct l2cap_chan *c, *c1 = NULL;
 
@@ -1713,6 +1756,12 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
 		if (state && c->state != state)
 			continue;
 
+		if (link_type == ACL_LINK && c->src_type != BDADDR_BREDR)
+			continue;
+
+		if (link_type == LE_LINK && c->src_type == BDADDR_BREDR)
+			continue;
+
 		if (c->psm == psm) {
 			int src_match, dst_match;
 			int src_any, dst_any;
@@ -1739,140 +1788,6 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
 	return c1;
 }
 
-int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
-		       bdaddr_t *dst, u8 dst_type)
-{
-	struct l2cap_conn *conn;
-	struct hci_conn *hcon;
-	struct hci_dev *hdev;
-	__u8 auth_type;
-	int err;
-
-	BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", &chan->src, dst,
-	       dst_type, __le16_to_cpu(psm));
-
-	hdev = hci_get_route(dst, &chan->src);
-	if (!hdev)
-		return -EHOSTUNREACH;
-
-	hci_dev_lock(hdev);
-
-	l2cap_chan_lock(chan);
-
-	/* PSM must be odd and lsb of upper byte must be 0 */
-	if ((__le16_to_cpu(psm) & 0x0101) != 0x0001 && !cid &&
-	    chan->chan_type != L2CAP_CHAN_RAW) {
-		err = -EINVAL;
-		goto done;
-	}
-
-	if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && !(psm || cid)) {
-		err = -EINVAL;
-		goto done;
-	}
-
-	switch (chan->mode) {
-	case L2CAP_MODE_BASIC:
-		break;
-	case L2CAP_MODE_ERTM:
-	case L2CAP_MODE_STREAMING:
-		if (!disable_ertm)
-			break;
-		/* fall through */
-	default:
-		err = -ENOTSUPP;
-		goto done;
-	}
-
-	switch (chan->state) {
-	case BT_CONNECT:
-	case BT_CONNECT2:
-	case BT_CONFIG:
-		/* Already connecting */
-		err = 0;
-		goto done;
-
-	case BT_CONNECTED:
-		/* Already connected */
-		err = -EISCONN;
-		goto done;
-
-	case BT_OPEN:
-	case BT_BOUND:
-		/* Can connect */
-		break;
-
-	default:
-		err = -EBADFD;
-		goto done;
-	}
-
-	/* Set destination address and psm */
-	bacpy(&chan->dst, dst);
-	chan->dst_type = dst_type;
-
-	chan->psm = psm;
-	chan->dcid = cid;
-
-	auth_type = l2cap_get_auth_type(chan);
-
-	if (bdaddr_type_is_le(dst_type))
-		hcon = hci_connect(hdev, LE_LINK, dst, dst_type,
-				   chan->sec_level, auth_type);
-	else
-		hcon = hci_connect(hdev, ACL_LINK, dst, dst_type,
-				   chan->sec_level, auth_type);
-
-	if (IS_ERR(hcon)) {
-		err = PTR_ERR(hcon);
-		goto done;
-	}
-
-	conn = l2cap_conn_add(hcon);
-	if (!conn) {
-		hci_conn_drop(hcon);
-		err = -ENOMEM;
-		goto done;
-	}
-
-	if (cid && __l2cap_get_chan_by_dcid(conn, cid)) {
-		hci_conn_drop(hcon);
-		err = -EBUSY;
-		goto done;
-	}
-
-	/* Update source addr of the socket */
-	bacpy(&chan->src, &hcon->src);
-	chan->src_type = bdaddr_type(hcon, hcon->src_type);
-
-	l2cap_chan_unlock(chan);
-	l2cap_chan_add(conn, chan);
-	l2cap_chan_lock(chan);
-
-	/* l2cap_chan_add takes its own ref so we can drop this one */
-	hci_conn_drop(hcon);
-
-	l2cap_state_change(chan, BT_CONNECT);
-	__set_chan_timer(chan, chan->ops->get_sndtimeo(chan));
-
-	if (hcon->state == BT_CONNECTED) {
-		if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) {
-			__clear_chan_timer(chan);
-			if (l2cap_chan_check_security(chan))
-				l2cap_state_change(chan, BT_CONNECTED);
-		} else
-			l2cap_do_start(chan);
-	}
-
-	err = 0;
-
-done:
-	l2cap_chan_unlock(chan);
-	hci_dev_unlock(hdev);
-	hci_dev_put(hdev);
-	return err;
-}
-
 static void l2cap_monitor_timeout(struct work_struct *work)
 {
 	struct l2cap_chan *chan = container_of(work, struct l2cap_chan,
@@ -2432,6 +2347,89 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan,
 	return 0;
 }
 
+static struct sk_buff *l2cap_create_le_flowctl_pdu(struct l2cap_chan *chan,
+						   struct msghdr *msg,
+						   size_t len, u16 sdulen)
+{
+	struct l2cap_conn *conn = chan->conn;
+	struct sk_buff *skb;
+	int err, count, hlen;
+	struct l2cap_hdr *lh;
+
+	BT_DBG("chan %p len %zu", chan, len);
+
+	if (!conn)
+		return ERR_PTR(-ENOTCONN);
+
+	hlen = L2CAP_HDR_SIZE;
+
+	if (sdulen)
+		hlen += L2CAP_SDULEN_SIZE;
+
+	count = min_t(unsigned int, (conn->mtu - hlen), len);
+
+	skb = chan->ops->alloc_skb(chan, count + hlen,
+				   msg->msg_flags & MSG_DONTWAIT);
+	if (IS_ERR(skb))
+		return skb;
+
+	/* Create L2CAP header */
+	lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE);
+	lh->cid = cpu_to_le16(chan->dcid);
+	lh->len = cpu_to_le16(len + (hlen - L2CAP_HDR_SIZE));
+
+	if (sdulen)
+		put_unaligned_le16(sdulen, skb_put(skb, L2CAP_SDULEN_SIZE));
+
+	err = l2cap_skbuff_fromiovec(chan, msg, len, count, skb);
+	if (unlikely(err < 0)) {
+		kfree_skb(skb);
+		return ERR_PTR(err);
+	}
+
+	return skb;
+}
+
+static int l2cap_segment_le_sdu(struct l2cap_chan *chan,
+				struct sk_buff_head *seg_queue,
+				struct msghdr *msg, size_t len)
+{
+	struct sk_buff *skb;
+	size_t pdu_len;
+	u16 sdu_len;
+
+	BT_DBG("chan %p, msg %p, len %zu", chan, msg, len);
+
+	pdu_len = chan->conn->mtu - L2CAP_HDR_SIZE;
+
+	pdu_len = min_t(size_t, pdu_len, chan->remote_mps);
+
+	sdu_len = len;
+	pdu_len -= L2CAP_SDULEN_SIZE;
+
+	while (len > 0) {
+		if (len <= pdu_len)
+			pdu_len = len;
+
+		skb = l2cap_create_le_flowctl_pdu(chan, msg, pdu_len, sdu_len);
+		if (IS_ERR(skb)) {
+			__skb_queue_purge(seg_queue);
+			return PTR_ERR(skb);
+		}
+
+		__skb_queue_tail(seg_queue, skb);
+
+		len -= pdu_len;
+
+		if (sdu_len) {
+			sdu_len = 0;
+			pdu_len += L2CAP_SDULEN_SIZE;
+		}
+	}
+
+	return 0;
+}
+
 int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len,
 		    u32 priority)
 {
@@ -2448,11 +2446,53 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len,
 		if (IS_ERR(skb))
 			return PTR_ERR(skb);
 
+		/* Channel lock is released before requesting new skb and then
+		 * reacquired thus we need to recheck channel state.
+		 */
+		if (chan->state != BT_CONNECTED) {
+			kfree_skb(skb);
+			return -ENOTCONN;
+		}
+
 		l2cap_do_send(chan, skb);
 		return len;
 	}
 
 	switch (chan->mode) {
+	case L2CAP_MODE_LE_FLOWCTL:
+		/* Check outgoing MTU */
+		if (len > chan->omtu)
+			return -EMSGSIZE;
+
+		if (!chan->tx_credits)
+			return -EAGAIN;
+
+		__skb_queue_head_init(&seg_queue);
+
+		err = l2cap_segment_le_sdu(chan, &seg_queue, msg, len);
+
+		if (chan->state != BT_CONNECTED) {
+			__skb_queue_purge(&seg_queue);
+			err = -ENOTCONN;
+		}
+
+		if (err)
+			return err;
+
+		skb_queue_splice_tail_init(&seg_queue, &chan->tx_q);
+
+		while (chan->tx_credits && !skb_queue_empty(&chan->tx_q)) {
+			l2cap_do_send(chan, skb_dequeue(&chan->tx_q));
+			chan->tx_credits--;
+		}
+
+		if (!chan->tx_credits)
+			chan->ops->suspend(chan);
+
+		err = len;
+
+		break;
+
 	case L2CAP_MODE_BASIC:
 		/* Check outgoing MTU */
 		if (len > chan->omtu)
@@ -2463,6 +2503,14 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len,
 		if (IS_ERR(skb))
 			return PTR_ERR(skb);
 
+		/* Channel lock is released before requesting new skb and then
+		 * reacquired thus we need to recheck channel state.
+		 */
+		if (chan->state != BT_CONNECTED) {
+			kfree_skb(skb);
+			return -ENOTCONN;
+		}
+
 		l2cap_do_send(chan, skb);
 		err = len;
 		break;
@@ -2859,9 +2907,9 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code,
 	lh->len = cpu_to_le16(L2CAP_CMD_HDR_SIZE + dlen);
 
 	if (conn->hcon->type == LE_LINK)
-		lh->cid = __constant_cpu_to_le16(L2CAP_CID_LE_SIGNALING);
+		lh->cid = cpu_to_le16(L2CAP_CID_LE_SIGNALING);
 	else
-		lh->cid = __constant_cpu_to_le16(L2CAP_CID_SIGNALING);
+		lh->cid = cpu_to_le16(L2CAP_CID_SIGNALING);
 
 	cmd = (struct l2cap_cmd_hdr *) skb_put(skb, L2CAP_CMD_HDR_SIZE);
 	cmd->code  = code;
@@ -2974,8 +3022,8 @@ static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan)
 		efs.stype	= chan->local_stype;
 		efs.msdu	= cpu_to_le16(chan->local_msdu);
 		efs.sdu_itime	= cpu_to_le32(chan->local_sdu_itime);
-		efs.acc_lat	= __constant_cpu_to_le32(L2CAP_DEFAULT_ACC_LAT);
-		efs.flush_to	= __constant_cpu_to_le32(L2CAP_EFS_DEFAULT_FLUSH_TO);
+		efs.acc_lat	= cpu_to_le32(L2CAP_DEFAULT_ACC_LAT);
+		efs.flush_to	= cpu_to_le32(L2CAP_EFS_DEFAULT_FLUSH_TO);
 		break;
 
 	case L2CAP_MODE_STREAMING:
@@ -3116,8 +3164,8 @@ static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan,
 		rfc->retrans_timeout = cpu_to_le16((u16) ertm_to);
 		rfc->monitor_timeout = rfc->retrans_timeout;
 	} else {
-		rfc->retrans_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO);
-		rfc->monitor_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO);
+		rfc->retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO);
+		rfc->monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO);
 	}
 }
 
@@ -3249,7 +3297,7 @@ done:
 	}
 
 	req->dcid  = cpu_to_le16(chan->dcid);
-	req->flags = __constant_cpu_to_le16(0);
+	req->flags = cpu_to_le16(0);
 
 	return ptr - data;
 }
@@ -3463,7 +3511,7 @@ done:
 	}
 	rsp->scid   = cpu_to_le16(chan->dcid);
 	rsp->result = cpu_to_le16(result);
-	rsp->flags  = __constant_cpu_to_le16(0);
+	rsp->flags  = cpu_to_le16(0);
 
 	return ptr - data;
 }
@@ -3572,7 +3620,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len,
 	}
 
 	req->dcid   = cpu_to_le16(chan->dcid);
-	req->flags  = __constant_cpu_to_le16(0);
+	req->flags  = cpu_to_le16(0);
 
 	return ptr - data;
 }
@@ -3592,6 +3640,23 @@ static int l2cap_build_conf_rsp(struct l2cap_chan *chan, void *data,
 	return ptr - data;
 }
 
+void __l2cap_le_connect_rsp_defer(struct l2cap_chan *chan)
+{
+	struct l2cap_le_conn_rsp rsp;
+	struct l2cap_conn *conn = chan->conn;
+
+	BT_DBG("chan %p", chan);
+
+	rsp.dcid    = cpu_to_le16(chan->scid);
+	rsp.mtu     = cpu_to_le16(chan->imtu);
+	rsp.mps     = cpu_to_le16(chan->mps);
+	rsp.credits = cpu_to_le16(chan->rx_credits);
+	rsp.result  = cpu_to_le16(L2CAP_CR_SUCCESS);
+
+	l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CONN_RSP, sizeof(rsp),
+		       &rsp);
+}
+
 void __l2cap_connect_rsp_defer(struct l2cap_chan *chan)
 {
 	struct l2cap_conn_rsp rsp;
@@ -3601,8 +3666,8 @@ void __l2cap_connect_rsp_defer(struct l2cap_chan *chan)
 
 	rsp.scid   = cpu_to_le16(chan->dcid);
 	rsp.dcid   = cpu_to_le16(chan->scid);
-	rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS);
-	rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO);
+	rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS);
+	rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
 
 	if (chan->hs_hcon)
 		rsp_code = L2CAP_CREATE_CHAN_RSP;
@@ -3631,8 +3696,8 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len)
 	u16 txwin_ext = chan->ack_win;
 	struct l2cap_conf_rfc rfc = {
 		.mode = chan->mode,
-		.retrans_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO),
-		.monitor_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO),
+		.retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO),
+		.monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO),
 		.max_pdu_size = cpu_to_le16(chan->imtu),
 		.txwin_size = min_t(u16, chan->ack_win, L2CAP_DEFAULT_TX_WINDOW),
 	};
@@ -3713,7 +3778,7 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn,
 
 	/* Check if we have socket listening on psm */
 	pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src,
-					 &conn->hcon->dst);
+					 &conn->hcon->dst, ACL_LINK);
 	if (!pchan) {
 		result = L2CAP_CR_BAD_PSM;
 		goto sendresp;
@@ -3723,7 +3788,7 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn,
 	l2cap_chan_lock(pchan);
 
 	/* Check if the ACL is secure enough (if not SDP) */
-	if (psm != __constant_cpu_to_le16(L2CAP_PSM_SDP) &&
+	if (psm != cpu_to_le16(L2CAP_PSM_SDP) &&
 	    !hci_conn_check_link_mode(conn->hcon)) {
 		conn->disc_reason = HCI_ERROR_AUTH_FAILURE;
 		result = L2CAP_CR_SEC_BLOCK;
@@ -3808,7 +3873,7 @@ sendresp:
 
 	if (result == L2CAP_CR_PEND && status == L2CAP_CS_NO_INFO) {
 		struct l2cap_info_req info;
-		info.type = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK);
+		info.type = cpu_to_le16(L2CAP_IT_FEAT_MASK);
 
 		conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_SENT;
 		conn->info_ident = l2cap_get_ident(conn);
@@ -3957,7 +4022,7 @@ static void cmd_reject_invalid_cid(struct l2cap_conn *conn, u8 ident,
 {
 	struct l2cap_cmd_rej_cid rej;
 
-	rej.reason = __constant_cpu_to_le16(L2CAP_REJ_INVALID_CID);
+	rej.reason = cpu_to_le16(L2CAP_REJ_INVALID_CID);
 	rej.scid = __cpu_to_le16(scid);
 	rej.dcid = __cpu_to_le16(dcid);
 
@@ -4289,8 +4354,8 @@ static inline int l2cap_information_req(struct l2cap_conn *conn,
 		u8 buf[8];
 		u32 feat_mask = l2cap_feat_mask;
 		struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) buf;
-		rsp->type   = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK);
-		rsp->result = __constant_cpu_to_le16(L2CAP_IR_SUCCESS);
+		rsp->type   = cpu_to_le16(L2CAP_IT_FEAT_MASK);
+		rsp->result = cpu_to_le16(L2CAP_IR_SUCCESS);
 		if (!disable_ertm)
 			feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING
 				| L2CAP_FEAT_FCS;
@@ -4310,15 +4375,15 @@ static inline int l2cap_information_req(struct l2cap_conn *conn,
 		else
 			l2cap_fixed_chan[0] &= ~L2CAP_FC_A2MP;
 
-		rsp->type   = __constant_cpu_to_le16(L2CAP_IT_FIXED_CHAN);
-		rsp->result = __constant_cpu_to_le16(L2CAP_IR_SUCCESS);
+		rsp->type   = cpu_to_le16(L2CAP_IT_FIXED_CHAN);
+		rsp->result = cpu_to_le16(L2CAP_IR_SUCCESS);
 		memcpy(rsp->data, l2cap_fixed_chan, sizeof(l2cap_fixed_chan));
 		l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf),
 			       buf);
 	} else {
 		struct l2cap_info_rsp rsp;
 		rsp.type   = cpu_to_le16(type);
-		rsp.result = __constant_cpu_to_le16(L2CAP_IR_NOTSUPP);
+		rsp.result = cpu_to_le16(L2CAP_IR_NOTSUPP);
 		l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(rsp),
 			       &rsp);
 	}
@@ -4363,7 +4428,7 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn,
 
 		if (conn->feat_mask & L2CAP_FEAT_FIXED_CHAN) {
 			struct l2cap_info_req req;
-			req.type = __constant_cpu_to_le16(L2CAP_IT_FIXED_CHAN);
+			req.type = cpu_to_le16(L2CAP_IT_FIXED_CHAN);
 
 			conn->info_ident = l2cap_get_ident(conn);
 
@@ -4457,8 +4522,8 @@ static int l2cap_create_channel_req(struct l2cap_conn *conn,
 error:
 	rsp.dcid = 0;
 	rsp.scid = cpu_to_le16(scid);
-	rsp.result = __constant_cpu_to_le16(L2CAP_CR_BAD_AMP);
-	rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO);
+	rsp.result = cpu_to_le16(L2CAP_CR_BAD_AMP);
+	rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
 
 	l2cap_send_cmd(conn, cmd->ident, L2CAP_CREATE_CHAN_RSP,
 		       sizeof(rsp), &rsp);
@@ -4522,7 +4587,7 @@ static void l2cap_send_move_chan_cfm_icid(struct l2cap_conn *conn, u16 icid)
 	BT_DBG("conn %p, icid 0x%4.4x", conn, icid);
 
 	cfm.icid = cpu_to_le16(icid);
-	cfm.result = __constant_cpu_to_le16(L2CAP_MC_UNCONFIRMED);
+	cfm.result = cpu_to_le16(L2CAP_MC_UNCONFIRMED);
 
 	l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_MOVE_CHAN_CFM,
 		       sizeof(cfm), &cfm);
@@ -4705,12 +4770,12 @@ static void l2cap_do_create(struct l2cap_chan *chan, int result,
 
 		if (result == L2CAP_CR_SUCCESS) {
 			/* Send successful response */
-			rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS);
-			rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO);
+			rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS);
+			rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
 		} else {
 			/* Send negative response */
-			rsp.result = __constant_cpu_to_le16(L2CAP_CR_NO_MEM);
-			rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO);
+			rsp.result = cpu_to_le16(L2CAP_CR_NO_MEM);
+			rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
 		}
 
 		l2cap_send_cmd(chan->conn, chan->ident, L2CAP_CREATE_CHAN_RSP,
@@ -4838,7 +4903,7 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn,
 	chan = l2cap_get_chan_by_dcid(conn, icid);
 	if (!chan) {
 		rsp.icid = cpu_to_le16(icid);
-		rsp.result = __constant_cpu_to_le16(L2CAP_MR_NOT_ALLOWED);
+		rsp.result = cpu_to_le16(L2CAP_MR_NOT_ALLOWED);
 		l2cap_send_cmd(conn, cmd->ident, L2CAP_MOVE_CHAN_RSP,
 			       sizeof(rsp), &rsp);
 		return 0;
@@ -5155,18 +5220,17 @@ static inline int l2cap_check_conn_param(u16 min, u16 max, u16 latency,
 
 static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
 					      struct l2cap_cmd_hdr *cmd,
-					      u8 *data)
+					      u16 cmd_len, u8 *data)
 {
 	struct hci_conn *hcon = conn->hcon;
 	struct l2cap_conn_param_update_req *req;
 	struct l2cap_conn_param_update_rsp rsp;
-	u16 min, max, latency, to_multiplier, cmd_len;
+	u16 min, max, latency, to_multiplier;
 	int err;
 
 	if (!(hcon->link_mode & HCI_LM_MASTER))
 		return -EINVAL;
 
-	cmd_len = __le16_to_cpu(cmd->len);
 	if (cmd_len != sizeof(struct l2cap_conn_param_update_req))
 		return -EPROTO;
 
@@ -5183,9 +5247,9 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
 
 	err = l2cap_check_conn_param(min, max, latency, to_multiplier);
 	if (err)
-		rsp.result = __constant_cpu_to_le16(L2CAP_CONN_PARAM_REJECTED);
+		rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED);
 	else
-		rsp.result = __constant_cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED);
+		rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED);
 
 	l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_PARAM_UPDATE_RSP,
 		       sizeof(rsp), &rsp);
@@ -5196,6 +5260,65 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
 	return 0;
 }
 
+static int l2cap_le_connect_rsp(struct l2cap_conn *conn,
+				struct l2cap_cmd_hdr *cmd, u16 cmd_len,
+				u8 *data)
+{
+	struct l2cap_le_conn_rsp *rsp = (struct l2cap_le_conn_rsp *) data;
+	u16 dcid, mtu, mps, credits, result;
+	struct l2cap_chan *chan;
+	int err;
+
+	if (cmd_len < sizeof(*rsp))
+		return -EPROTO;
+
+	dcid    = __le16_to_cpu(rsp->dcid);
+	mtu     = __le16_to_cpu(rsp->mtu);
+	mps     = __le16_to_cpu(rsp->mps);
+	credits = __le16_to_cpu(rsp->credits);
+	result  = __le16_to_cpu(rsp->result);
+
+	if (result == L2CAP_CR_SUCCESS && (mtu < 23 || mps < 23))
+		return -EPROTO;
+
+	BT_DBG("dcid 0x%4.4x mtu %u mps %u credits %u result 0x%2.2x",
+	       dcid, mtu, mps, credits, result);
+
+	mutex_lock(&conn->chan_lock);
+
+	chan = __l2cap_get_chan_by_ident(conn, cmd->ident);
+	if (!chan) {
+		err = -EBADSLT;
+		goto unlock;
+	}
+
+	err = 0;
+
+	l2cap_chan_lock(chan);
+
+	switch (result) {
+	case L2CAP_CR_SUCCESS:
+		chan->ident = 0;
+		chan->dcid = dcid;
+		chan->omtu = mtu;
+		chan->remote_mps = mps;
+		chan->tx_credits = credits;
+		l2cap_chan_ready(chan);
+		break;
+
+	default:
+		l2cap_chan_del(chan, ECONNREFUSED);
+		break;
+	}
+
+	l2cap_chan_unlock(chan);
+
+unlock:
+	mutex_unlock(&conn->chan_lock);
+
+	return err;
+}
+
 static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn,
 				      struct l2cap_cmd_hdr *cmd, u16 cmd_len,
 				      u8 *data)
@@ -5276,23 +5399,235 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn,
 	return err;
 }
 
+static int l2cap_le_connect_req(struct l2cap_conn *conn,
+				struct l2cap_cmd_hdr *cmd, u16 cmd_len,
+				u8 *data)
+{
+	struct l2cap_le_conn_req *req = (struct l2cap_le_conn_req *) data;
+	struct l2cap_le_conn_rsp rsp;
+	struct l2cap_chan *chan, *pchan;
+	u16 dcid, scid, credits, mtu, mps;
+	__le16 psm;
+	u8 result;
+
+	if (cmd_len != sizeof(*req))
+		return -EPROTO;
+
+	scid = __le16_to_cpu(req->scid);
+	mtu  = __le16_to_cpu(req->mtu);
+	mps  = __le16_to_cpu(req->mps);
+	psm  = req->psm;
+	dcid = 0;
+	credits = 0;
+
+	if (mtu < 23 || mps < 23)
+		return -EPROTO;
+
+	BT_DBG("psm 0x%2.2x scid 0x%4.4x mtu %u mps %u", __le16_to_cpu(psm),
+	       scid, mtu, mps);
+
+	/* Check if we have socket listening on psm */
+	pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src,
+					 &conn->hcon->dst, LE_LINK);
+	if (!pchan) {
+		result = L2CAP_CR_BAD_PSM;
+		chan = NULL;
+		goto response;
+	}
+
+	mutex_lock(&conn->chan_lock);
+	l2cap_chan_lock(pchan);
+
+	if (!smp_sufficient_security(conn->hcon, pchan->sec_level)) {
+		result = L2CAP_CR_AUTHENTICATION;
+		chan = NULL;
+		goto response_unlock;
+	}
+
+	/* Check if we already have channel with that dcid */
+	if (__l2cap_get_chan_by_dcid(conn, scid)) {
+		result = L2CAP_CR_NO_MEM;
+		chan = NULL;
+		goto response_unlock;
+	}
+
+	chan = pchan->ops->new_connection(pchan);
+	if (!chan) {
+		result = L2CAP_CR_NO_MEM;
+		goto response_unlock;
+	}
+
+	l2cap_le_flowctl_init(chan);
+
+	bacpy(&chan->src, &conn->hcon->src);
+	bacpy(&chan->dst, &conn->hcon->dst);
+	chan->src_type = bdaddr_type(conn->hcon, conn->hcon->src_type);
+	chan->dst_type = bdaddr_type(conn->hcon, conn->hcon->dst_type);
+	chan->psm  = psm;
+	chan->dcid = scid;
+	chan->omtu = mtu;
+	chan->remote_mps = mps;
+	chan->tx_credits = __le16_to_cpu(req->credits);
+
+	__l2cap_chan_add(conn, chan);
+	dcid = chan->scid;
+	credits = chan->rx_credits;
+
+	__set_chan_timer(chan, chan->ops->get_sndtimeo(chan));
+
+	chan->ident = cmd->ident;
+
+	if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) {
+		l2cap_state_change(chan, BT_CONNECT2);
+		result = L2CAP_CR_PEND;
+		chan->ops->defer(chan);
+	} else {
+		l2cap_chan_ready(chan);
+		result = L2CAP_CR_SUCCESS;
+	}
+
+response_unlock:
+	l2cap_chan_unlock(pchan);
+	mutex_unlock(&conn->chan_lock);
+
+	if (result == L2CAP_CR_PEND)
+		return 0;
+
+response:
+	if (chan) {
+		rsp.mtu = cpu_to_le16(chan->imtu);
+		rsp.mps = cpu_to_le16(chan->mps);
+	} else {
+		rsp.mtu = 0;
+		rsp.mps = 0;
+	}
+
+	rsp.dcid    = cpu_to_le16(dcid);
+	rsp.credits = cpu_to_le16(credits);
+	rsp.result  = cpu_to_le16(result);
+
+	l2cap_send_cmd(conn, cmd->ident, L2CAP_LE_CONN_RSP, sizeof(rsp), &rsp);
+
+	return 0;
+}
+
+static inline int l2cap_le_credits(struct l2cap_conn *conn,
+				   struct l2cap_cmd_hdr *cmd, u16 cmd_len,
+				   u8 *data)
+{
+	struct l2cap_le_credits *pkt;
+	struct l2cap_chan *chan;
+	u16 cid, credits, max_credits;
+
+	if (cmd_len != sizeof(*pkt))
+		return -EPROTO;
+
+	pkt = (struct l2cap_le_credits *) data;
+	cid	= __le16_to_cpu(pkt->cid);
+	credits	= __le16_to_cpu(pkt->credits);
+
+	BT_DBG("cid 0x%4.4x credits 0x%4.4x", cid, credits);
+
+	chan = l2cap_get_chan_by_dcid(conn, cid);
+	if (!chan)
+		return -EBADSLT;
+
+	max_credits = LE_FLOWCTL_MAX_CREDITS - chan->tx_credits;
+	if (credits > max_credits) {
+		BT_ERR("LE credits overflow");
+		l2cap_send_disconn_req(chan, ECONNRESET);
+
+		/* Return 0 so that we don't trigger an unnecessary
+		 * command reject packet.
+		 */
+		return 0;
+	}
+
+	chan->tx_credits += credits;
+
+	while (chan->tx_credits && !skb_queue_empty(&chan->tx_q)) {
+		l2cap_do_send(chan, skb_dequeue(&chan->tx_q));
+		chan->tx_credits--;
+	}
+
+	if (chan->tx_credits)
+		chan->ops->resume(chan);
+
+	l2cap_chan_unlock(chan);
+
+	return 0;
+}
+
+static inline int l2cap_le_command_rej(struct l2cap_conn *conn,
+				       struct l2cap_cmd_hdr *cmd, u16 cmd_len,
+				       u8 *data)
+{
+	struct l2cap_cmd_rej_unk *rej = (struct l2cap_cmd_rej_unk *) data;
+	struct l2cap_chan *chan;
+
+	if (cmd_len < sizeof(*rej))
+		return -EPROTO;
+
+	mutex_lock(&conn->chan_lock);
+
+	chan = __l2cap_get_chan_by_ident(conn, cmd->ident);
+	if (!chan)
+		goto done;
+
+	l2cap_chan_lock(chan);
+	l2cap_chan_del(chan, ECONNREFUSED);
+	l2cap_chan_unlock(chan);
+
+done:
+	mutex_unlock(&conn->chan_lock);
+	return 0;
+}
+
 static inline int l2cap_le_sig_cmd(struct l2cap_conn *conn,
-				   struct l2cap_cmd_hdr *cmd, u8 *data)
+				   struct l2cap_cmd_hdr *cmd, u16 cmd_len,
+				   u8 *data)
 {
+	int err = 0;
+
 	switch (cmd->code) {
 	case L2CAP_COMMAND_REJ:
-		return 0;
+		l2cap_le_command_rej(conn, cmd, cmd_len, data);
+		break;
 
 	case L2CAP_CONN_PARAM_UPDATE_REQ:
-		return l2cap_conn_param_update_req(conn, cmd, data);
+		err = l2cap_conn_param_update_req(conn, cmd, cmd_len, data);
+		break;
 
 	case L2CAP_CONN_PARAM_UPDATE_RSP:
-		return 0;
+		break;
+
+	case L2CAP_LE_CONN_RSP:
+		l2cap_le_connect_rsp(conn, cmd, cmd_len, data);
+		break;
+
+	case L2CAP_LE_CONN_REQ:
+		err = l2cap_le_connect_req(conn, cmd, cmd_len, data);
+		break;
+
+	case L2CAP_LE_CREDITS:
+		err = l2cap_le_credits(conn, cmd, cmd_len, data);
+		break;
+
+	case L2CAP_DISCONN_REQ:
+		err = l2cap_disconnect_req(conn, cmd, cmd_len, data);
+		break;
+
+	case L2CAP_DISCONN_RSP:
+		l2cap_disconnect_rsp(conn, cmd, cmd_len, data);
+		break;
 
 	default:
 		BT_ERR("Unknown LE signaling command 0x%2.2x", cmd->code);
-		return -EINVAL;
+		err = -EINVAL;
+		break;
 	}
+
+	return err;
 }
 
 static inline void l2cap_le_sig_channel(struct l2cap_conn *conn,
@@ -5321,13 +5656,13 @@ static inline void l2cap_le_sig_channel(struct l2cap_conn *conn,
 		goto drop;
 	}
 
-	err = l2cap_le_sig_cmd(conn, cmd, skb->data);
+	err = l2cap_le_sig_cmd(conn, cmd, len, skb->data);
 	if (err) {
 		struct l2cap_cmd_rej_unk rej;
 
 		BT_ERR("Wrong link type (%d)", err);
 
-		rej.reason = __constant_cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
+		rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
 		l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ,
 			       sizeof(rej), &rej);
 	}
@@ -5372,7 +5707,7 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn,
 
 			BT_ERR("Wrong link type (%d)", err);
 
-			rej.reason = __constant_cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
+			rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD);
 			l2cap_send_cmd(conn, cmd.ident, L2CAP_COMMAND_REJ,
 				       sizeof(rej), &rej);
 		}
@@ -6312,6 +6647,122 @@ drop:
 	return 0;
 }
 
+static void l2cap_chan_le_send_credits(struct l2cap_chan *chan)
+{
+	struct l2cap_conn *conn = chan->conn;
+	struct l2cap_le_credits pkt;
+	u16 return_credits;
+
+	/* We return more credits to the sender only after the amount of
+	 * credits falls below half of the initial amount.
+	 */
+	if (chan->rx_credits >= (le_max_credits + 1) / 2)
+		return;
+
+	return_credits = le_max_credits - chan->rx_credits;
+
+	BT_DBG("chan %p returning %u credits to sender", chan, return_credits);
+
+	chan->rx_credits += return_credits;
+
+	pkt.cid     = cpu_to_le16(chan->scid);
+	pkt.credits = cpu_to_le16(return_credits);
+
+	chan->ident = l2cap_get_ident(conn);
+
+	l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CREDITS, sizeof(pkt), &pkt);
+}
+
+static int l2cap_le_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
+{
+	int err;
+
+	if (!chan->rx_credits) {
+		BT_ERR("No credits to receive LE L2CAP data");
+		l2cap_send_disconn_req(chan, ECONNRESET);
+		return -ENOBUFS;
+	}
+
+	if (chan->imtu < skb->len) {
+		BT_ERR("Too big LE L2CAP PDU");
+		return -ENOBUFS;
+	}
+
+	chan->rx_credits--;
+	BT_DBG("rx_credits %u -> %u", chan->rx_credits + 1, chan->rx_credits);
+
+	l2cap_chan_le_send_credits(chan);
+
+	err = 0;
+
+	if (!chan->sdu) {
+		u16 sdu_len;
+
+		sdu_len = get_unaligned_le16(skb->data);
+		skb_pull(skb, L2CAP_SDULEN_SIZE);
+
+		BT_DBG("Start of new SDU. sdu_len %u skb->len %u imtu %u",
+		       sdu_len, skb->len, chan->imtu);
+
+		if (sdu_len > chan->imtu) {
+			BT_ERR("Too big LE L2CAP SDU length received");
+			err = -EMSGSIZE;
+			goto failed;
+		}
+
+		if (skb->len > sdu_len) {
+			BT_ERR("Too much LE L2CAP data received");
+			err = -EINVAL;
+			goto failed;
+		}
+
+		if (skb->len == sdu_len)
+			return chan->ops->recv(chan, skb);
+
+		chan->sdu = skb;
+		chan->sdu_len = sdu_len;
+		chan->sdu_last_frag = skb;
+
+		return 0;
+	}
+
+	BT_DBG("SDU fragment. chan->sdu->len %u skb->len %u chan->sdu_len %u",
+	       chan->sdu->len, skb->len, chan->sdu_len);
+
+	if (chan->sdu->len + skb->len > chan->sdu_len) {
+		BT_ERR("Too much LE L2CAP data received");
+		err = -EINVAL;
+		goto failed;
+	}
+
+	append_skb_frag(chan->sdu, skb, &chan->sdu_last_frag);
+	skb = NULL;
+
+	if (chan->sdu->len == chan->sdu_len) {
+		err = chan->ops->recv(chan, chan->sdu);
+		if (!err) {
+			chan->sdu = NULL;
+			chan->sdu_last_frag = NULL;
+			chan->sdu_len = 0;
+		}
+	}
+
+failed:
+	if (err) {
+		kfree_skb(skb);
+		kfree_skb(chan->sdu);
+		chan->sdu = NULL;
+		chan->sdu_last_frag = NULL;
+		chan->sdu_len = 0;
+	}
+
+	/* We can't return an error here since we took care of the skb
+	 * freeing internally. An error return would cause the caller to
+	 * do a double-free of the skb.
+	 */
+	return 0;
+}
+
 static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid,
 			       struct sk_buff *skb)
 {
@@ -6341,14 +6792,22 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid,
 		goto drop;
 
 	switch (chan->mode) {
+	case L2CAP_MODE_LE_FLOWCTL:
+		if (l2cap_le_data_rcv(chan, skb) < 0)
+			goto drop;
+
+		goto done;
+
 	case L2CAP_MODE_BASIC:
 		/* If socket recv buffers overflows we drop data here
 		 * which is *bad* because L2CAP has to be reliable.
 		 * But we don't have any other choice. L2CAP doesn't
 		 * provide flow control mechanism. */
 
-		if (chan->imtu < skb->len)
+		if (chan->imtu < skb->len) {
+			BT_ERR("Dropping L2CAP data: receive buffer overflow");
 			goto drop;
+		}
 
 		if (!chan->ops->recv(chan, skb))
 			goto done;
@@ -6380,7 +6839,8 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
 	if (hcon->type != ACL_LINK)
 		goto drop;
 
-	chan = l2cap_global_chan_by_psm(0, psm, &hcon->src, &hcon->dst);
+	chan = l2cap_global_chan_by_psm(0, psm, &hcon->src, &hcon->dst,
+					ACL_LINK);
 	if (!chan)
 		goto drop;
 
@@ -6435,9 +6895,16 @@ drop:
 static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct l2cap_hdr *lh = (void *) skb->data;
+	struct hci_conn *hcon = conn->hcon;
 	u16 cid, len;
 	__le16 psm;
 
+	if (hcon->state != BT_CONNECTED) {
+		BT_DBG("queueing pending rx skb");
+		skb_queue_tail(&conn->pending_rx, skb);
+		return;
+	}
+
 	skb_pull(skb, L2CAP_HDR_SIZE);
 	cid = __le16_to_cpu(lh->cid);
 	len = __le16_to_cpu(lh->len);
@@ -6473,12 +6940,257 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb)
 			l2cap_conn_del(conn->hcon, EACCES);
 		break;
 
+	case L2CAP_FC_6LOWPAN:
+		bt_6lowpan_recv(conn, skb);
+		break;
+
 	default:
 		l2cap_data_channel(conn, cid, skb);
 		break;
 	}
 }
 
+static void process_pending_rx(struct work_struct *work)
+{
+	struct l2cap_conn *conn = container_of(work, struct l2cap_conn,
+					       pending_rx_work);
+	struct sk_buff *skb;
+
+	BT_DBG("");
+
+	while ((skb = skb_dequeue(&conn->pending_rx)))
+		l2cap_recv_frame(conn, skb);
+}
+
+static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
+{
+	struct l2cap_conn *conn = hcon->l2cap_data;
+	struct hci_chan *hchan;
+
+	if (conn)
+		return conn;
+
+	hchan = hci_chan_create(hcon);
+	if (!hchan)
+		return NULL;
+
+	conn = kzalloc(sizeof(struct l2cap_conn), GFP_KERNEL);
+	if (!conn) {
+		hci_chan_del(hchan);
+		return NULL;
+	}
+
+	kref_init(&conn->ref);
+	hcon->l2cap_data = conn;
+	conn->hcon = hcon;
+	hci_conn_get(conn->hcon);
+	conn->hchan = hchan;
+
+	BT_DBG("hcon %p conn %p hchan %p", hcon, conn, hchan);
+
+	switch (hcon->type) {
+	case LE_LINK:
+		if (hcon->hdev->le_mtu) {
+			conn->mtu = hcon->hdev->le_mtu;
+			break;
+		}
+		/* fall through */
+	default:
+		conn->mtu = hcon->hdev->acl_mtu;
+		break;
+	}
+
+	conn->feat_mask = 0;
+
+	if (hcon->type == ACL_LINK)
+		conn->hs_enabled = test_bit(HCI_HS_ENABLED,
+					    &hcon->hdev->dev_flags);
+
+	spin_lock_init(&conn->lock);
+	mutex_init(&conn->chan_lock);
+
+	INIT_LIST_HEAD(&conn->chan_l);
+	INIT_LIST_HEAD(&conn->users);
+
+	if (hcon->type == LE_LINK)
+		INIT_DELAYED_WORK(&conn->security_timer, security_timeout);
+	else
+		INIT_DELAYED_WORK(&conn->info_timer, l2cap_info_timeout);
+
+	skb_queue_head_init(&conn->pending_rx);
+	INIT_WORK(&conn->pending_rx_work, process_pending_rx);
+
+	conn->disc_reason = HCI_ERROR_REMOTE_USER_TERM;
+
+	return conn;
+}
+
+static bool is_valid_psm(u16 psm, u8 dst_type) {
+	if (!psm)
+		return false;
+
+	if (bdaddr_type_is_le(dst_type))
+		return (psm <= 0x00ff);
+
+	/* PSM must be odd and lsb of upper byte must be 0 */
+	return ((psm & 0x0101) == 0x0001);
+}
+
+int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
+		       bdaddr_t *dst, u8 dst_type)
+{
+	struct l2cap_conn *conn;
+	struct hci_conn *hcon;
+	struct hci_dev *hdev;
+	__u8 auth_type;
+	int err;
+
+	BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", &chan->src, dst,
+	       dst_type, __le16_to_cpu(psm));
+
+	hdev = hci_get_route(dst, &chan->src);
+	if (!hdev)
+		return -EHOSTUNREACH;
+
+	hci_dev_lock(hdev);
+
+	l2cap_chan_lock(chan);
+
+	if (!is_valid_psm(__le16_to_cpu(psm), dst_type) && !cid &&
+	    chan->chan_type != L2CAP_CHAN_RAW) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && !psm) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	if (chan->chan_type == L2CAP_CHAN_FIXED && !cid) {
+		err = -EINVAL;
+		goto done;
+	}
+
+	switch (chan->mode) {
+	case L2CAP_MODE_BASIC:
+		break;
+	case L2CAP_MODE_LE_FLOWCTL:
+		l2cap_le_flowctl_init(chan);
+		break;
+	case L2CAP_MODE_ERTM:
+	case L2CAP_MODE_STREAMING:
+		if (!disable_ertm)
+			break;
+		/* fall through */
+	default:
+		err = -ENOTSUPP;
+		goto done;
+	}
+
+	switch (chan->state) {
+	case BT_CONNECT:
+	case BT_CONNECT2:
+	case BT_CONFIG:
+		/* Already connecting */
+		err = 0;
+		goto done;
+
+	case BT_CONNECTED:
+		/* Already connected */
+		err = -EISCONN;
+		goto done;
+
+	case BT_OPEN:
+	case BT_BOUND:
+		/* Can connect */
+		break;
+
+	default:
+		err = -EBADFD;
+		goto done;
+	}
+
+	/* Set destination address and psm */
+	bacpy(&chan->dst, dst);
+	chan->dst_type = dst_type;
+
+	chan->psm = psm;
+	chan->dcid = cid;
+
+	auth_type = l2cap_get_auth_type(chan);
+
+	if (bdaddr_type_is_le(dst_type)) {
+		/* Convert from L2CAP channel address type to HCI address type
+		 */
+		if (dst_type == BDADDR_LE_PUBLIC)
+			dst_type = ADDR_LE_DEV_PUBLIC;
+		else
+			dst_type = ADDR_LE_DEV_RANDOM;
+
+		hcon = hci_connect_le(hdev, dst, dst_type, chan->sec_level,
+				      auth_type);
+	} else {
+		hcon = hci_connect_acl(hdev, dst, chan->sec_level, auth_type);
+	}
+
+	if (IS_ERR(hcon)) {
+		err = PTR_ERR(hcon);
+		goto done;
+	}
+
+	conn = l2cap_conn_add(hcon);
+	if (!conn) {
+		hci_conn_drop(hcon);
+		err = -ENOMEM;
+		goto done;
+	}
+
+	if (cid && __l2cap_get_chan_by_dcid(conn, cid)) {
+		hci_conn_drop(hcon);
+		err = -EBUSY;
+		goto done;
+	}
+
+	/* Update source addr of the socket */
+	bacpy(&chan->src, &hcon->src);
+	chan->src_type = bdaddr_type(hcon, hcon->src_type);
+
+	l2cap_chan_unlock(chan);
+	l2cap_chan_add(conn, chan);
+	l2cap_chan_lock(chan);
+
+	/* l2cap_chan_add takes its own ref so we can drop this one */
+	hci_conn_drop(hcon);
+
+	l2cap_state_change(chan, BT_CONNECT);
+	__set_chan_timer(chan, chan->ops->get_sndtimeo(chan));
+
+	/* Release chan->sport so that it can be reused by other
+	 * sockets (as it's only used for listening sockets).
+	 */
+	write_lock(&chan_list_lock);
+	chan->sport = 0;
+	write_unlock(&chan_list_lock);
+
+	if (hcon->state == BT_CONNECTED) {
+		if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) {
+			__clear_chan_timer(chan);
+			if (l2cap_chan_check_security(chan))
+				l2cap_state_change(chan, BT_CONNECTED);
+		} else
+			l2cap_do_start(chan);
+	}
+
+	err = 0;
+
+done:
+	l2cap_chan_unlock(chan);
+	hci_dev_unlock(hdev);
+	hci_dev_put(hdev);
+	return err;
+}
+
 /* ---- L2CAP interface with lower layer (HCI) ---- */
 
 int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr)
@@ -6540,6 +7252,8 @@ void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason)
 {
 	BT_DBG("hcon %p reason %d", hcon, reason);
 
+	bt_6lowpan_del_conn(hcon->l2cap_data);
+
 	l2cap_conn_del(hcon, bt_to_errno(reason));
 }
 
@@ -6551,7 +7265,8 @@ static inline void l2cap_check_encryption(struct l2cap_chan *chan, u8 encrypt)
 	if (encrypt == 0x00) {
 		if (chan->sec_level == BT_SECURITY_MEDIUM) {
 			__set_chan_timer(chan, L2CAP_ENC_TIMEOUT);
-		} else if (chan->sec_level == BT_SECURITY_HIGH)
+		} else if (chan->sec_level == BT_SECURITY_HIGH ||
+			   chan->sec_level == BT_SECURITY_FIPS)
 			l2cap_chan_close(chan, ECONNREFUSED);
 	} else {
 		if (chan->sec_level == BT_SECURITY_MEDIUM)
@@ -6571,7 +7286,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 
 	if (hcon->type == LE_LINK) {
 		if (!status && encrypt)
-			smp_distribute_keys(conn, 0);
+			smp_distribute_keys(conn);
 		cancel_delayed_work(&conn->security_timer);
 	}
 
@@ -6583,7 +7298,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 		BT_DBG("chan %p scid 0x%4.4x state %s", chan, chan->scid,
 		       state_to_string(chan->state));
 
-		if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) {
+		if (chan->scid == L2CAP_CID_A2MP) {
 			l2cap_chan_unlock(chan);
 			continue;
 		}
@@ -6612,11 +7327,10 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 		}
 
 		if (chan->state == BT_CONNECT) {
-			if (!status) {
+			if (!status)
 				l2cap_start_connection(chan);
-			} else {
+			else
 				__set_chan_timer(chan, L2CAP_DISC_TIMEOUT);
-			}
 		} else if (chan->state == BT_CONNECT2) {
 			struct l2cap_conn_rsp rsp;
 			__u16 res, stat;
@@ -6817,11 +7531,19 @@ int __init l2cap_init(void)
 	l2cap_debugfs = debugfs_create_file("l2cap", 0444, bt_debugfs,
 					    NULL, &l2cap_debugfs_fops);
 
+	debugfs_create_u16("l2cap_le_max_credits", 0644, bt_debugfs,
+			   &le_max_credits);
+	debugfs_create_u16("l2cap_le_default_mps", 0644, bt_debugfs,
+			   &le_default_mps);
+
+	bt_6lowpan_init();
+
 	return 0;
 }
 
 void l2cap_exit(void)
 {
+	bt_6lowpan_cleanup();
 	debugfs_remove(l2cap_debugfs);
 	l2cap_cleanup_sockets();
 }
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 7cc24d263ca..e1378693cc9 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -27,6 +27,7 @@
 
 /* Bluetooth L2CAP sockets. */
 
+#include <linux/module.h>
 #include <linux/export.h>
 
 #include <net/bluetooth/bluetooth.h>
@@ -50,6 +51,32 @@ bool l2cap_is_socket(struct socket *sock)
 }
 EXPORT_SYMBOL(l2cap_is_socket);
 
+static int l2cap_validate_bredr_psm(u16 psm)
+{
+	/* PSM must be odd and lsb of upper byte must be 0 */
+	if ((psm & 0x0101) != 0x0001)
+		return -EINVAL;
+
+	/* Restrict usage of well-known PSMs */
+	if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE))
+		return -EACCES;
+
+	return 0;
+}
+
+static int l2cap_validate_le_psm(u16 psm)
+{
+	/* Valid LE_PSM ranges are defined only until 0x00ff */
+	if (psm > 0x00ff)
+		return -EINVAL;
+
+	/* Restrict fixed, SIG assigned PSM values to CAP_NET_BIND_SERVICE */
+	if (psm <= 0x007f && !capable(CAP_NET_BIND_SERVICE))
+		return -EACCES;
+
+	return 0;
+}
+
 static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 {
 	struct sock *sk = sock->sk;
@@ -72,12 +99,19 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 	if (!bdaddr_type_is_valid(la.l2_bdaddr_type))
 		return -EINVAL;
 
+	if (la.l2_cid) {
+		/* When the socket gets created it defaults to
+		 * CHAN_CONN_ORIENTED, so we need to overwrite the
+		 * default here.
+		 */
+		chan->chan_type = L2CAP_CHAN_FIXED;
+		chan->omtu = L2CAP_DEFAULT_MTU;
+	}
+
 	if (bdaddr_type_is_le(la.l2_bdaddr_type)) {
-		/* Connection oriented channels are not supported on LE */
-		if (la.l2_psm)
-			return -EINVAL;
 		/* We only allow ATT user space socket */
-		if (la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT))
+		if (la.l2_cid &&
+		    la.l2_cid != cpu_to_le16(L2CAP_CID_ATT))
 			return -EINVAL;
 	}
 
@@ -91,17 +125,13 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 	if (la.l2_psm) {
 		__u16 psm = __le16_to_cpu(la.l2_psm);
 
-		/* PSM must be odd and lsb of upper byte must be 0 */
-		if ((psm & 0x0101) != 0x0001) {
-			err = -EINVAL;
-			goto done;
-		}
+		if (la.l2_bdaddr_type == BDADDR_BREDR)
+			err = l2cap_validate_bredr_psm(psm);
+		else
+			err = l2cap_validate_le_psm(psm);
 
-		/* Restrict usage of well-known PSMs */
-		if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE)) {
-			err = -EACCES;
+		if (err)
 			goto done;
-		}
 	}
 
 	if (la.l2_cid)
@@ -122,11 +152,17 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 		    __le16_to_cpu(la.l2_psm) == L2CAP_PSM_RFCOMM)
 			chan->sec_level = BT_SECURITY_SDP;
 		break;
+	case L2CAP_CHAN_RAW:
+		chan->sec_level = BT_SECURITY_SDP;
+		break;
 	}
 
 	bacpy(&chan->src, &la.l2_bdaddr);
 	chan->src_type = la.l2_bdaddr_type;
 
+	if (chan->psm && bdaddr_type_is_le(chan->src_type))
+		chan->mode = L2CAP_MODE_LE_FLOWCTL;
+
 	chan->state = BT_BOUND;
 	sk->sk_state = BT_BOUND;
 
@@ -173,7 +209,7 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr,
 		 * ATT. Anything else is an invalid combination.
 		 */
 		if (chan->scid != L2CAP_CID_ATT ||
-		    la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT))
+		    la.l2_cid != cpu_to_le16(L2CAP_CID_ATT))
 			return -EINVAL;
 
 		/* We don't have the hdev available here to make a
@@ -189,14 +225,15 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr,
 		return -EINVAL;
 
 	if (bdaddr_type_is_le(la.l2_bdaddr_type)) {
-		/* Connection oriented channels are not supported on LE */
-		if (la.l2_psm)
-			return -EINVAL;
 		/* We only allow ATT user space socket */
-		if (la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT))
+		if (la.l2_cid &&
+		    la.l2_cid != cpu_to_le16(L2CAP_CID_ATT))
 			return -EINVAL;
 	}
 
+	if (chan->psm && bdaddr_type_is_le(chan->src_type))
+		chan->mode = L2CAP_MODE_LE_FLOWCTL;
+
 	err = l2cap_chan_connect(chan, la.l2_psm, __le16_to_cpu(la.l2_cid),
 				 &la.l2_bdaddr, la.l2_bdaddr_type);
 	if (err)
@@ -234,6 +271,7 @@ static int l2cap_sock_listen(struct socket *sock, int backlog)
 
 	switch (chan->mode) {
 	case L2CAP_MODE_BASIC:
+	case L2CAP_MODE_LE_FLOWCTL:
 		break;
 	case L2CAP_MODE_ERTM:
 	case L2CAP_MODE_STREAMING:
@@ -322,17 +360,21 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr,
 
 	BT_DBG("sock %p, sk %p", sock, sk);
 
+	if (peer && sk->sk_state != BT_CONNECTED &&
+	    sk->sk_state != BT_CONNECT && sk->sk_state != BT_CONNECT2)
+		return -ENOTCONN;
+
 	memset(la, 0, sizeof(struct sockaddr_l2));
 	addr->sa_family = AF_BLUETOOTH;
 	*len = sizeof(struct sockaddr_l2);
 
+	la->l2_psm = chan->psm;
+
 	if (peer) {
-		la->l2_psm = chan->psm;
 		bacpy(&la->l2_bdaddr, &chan->dst);
 		la->l2_cid = cpu_to_le16(chan->dcid);
 		la->l2_bdaddr_type = chan->dst_type;
 	} else {
-		la->l2_psm = chan->sport;
 		bacpy(&la->l2_bdaddr, &chan->src);
 		la->l2_cid = cpu_to_le16(chan->scid);
 		la->l2_bdaddr_type = chan->src_type;
@@ -360,6 +402,16 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname,
 
 	switch (optname) {
 	case L2CAP_OPTIONS:
+		/* LE sockets should use BT_SNDMTU/BT_RCVMTU, but since
+		 * legacy ATT code depends on getsockopt for
+		 * L2CAP_OPTIONS we need to let this pass.
+		 */
+		if (bdaddr_type_is_le(chan->src_type) &&
+		    chan->scid != L2CAP_CID_ATT) {
+			err = -EINVAL;
+			break;
+		}
+
 		memset(&opts, 0, sizeof(opts));
 		opts.imtu     = chan->imtu;
 		opts.omtu     = chan->omtu;
@@ -387,6 +439,10 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname,
 			opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT |
 			      L2CAP_LM_SECURE;
 			break;
+		case BT_SECURITY_FIPS:
+			opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT |
+			      L2CAP_LM_SECURE | L2CAP_LM_FIPS;
+			break;
 		default:
 			opt = 0;
 			break;
@@ -400,6 +456,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname,
 
 		if (put_user(opt, (u32 __user *) optval))
 			err = -EFAULT;
+
 		break;
 
 	case L2CAP_CONNINFO:
@@ -454,6 +511,7 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname,
 	switch (optname) {
 	case BT_SECURITY:
 		if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED &&
+		    chan->chan_type != L2CAP_CHAN_FIXED &&
 		    chan->chan_type != L2CAP_CHAN_RAW) {
 			err = -EINVAL;
 			break;
@@ -514,6 +572,31 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname,
 			err = -EFAULT;
 		break;
 
+	case BT_SNDMTU:
+		if (!bdaddr_type_is_le(chan->src_type)) {
+			err = -EINVAL;
+			break;
+		}
+
+		if (sk->sk_state != BT_CONNECTED) {
+			err = -ENOTCONN;
+			break;
+		}
+
+		if (put_user(chan->omtu, (u16 __user *) optval))
+			err = -EFAULT;
+		break;
+
+	case BT_RCVMTU:
+		if (!bdaddr_type_is_le(chan->src_type)) {
+			err = -EINVAL;
+			break;
+		}
+
+		if (put_user(chan->imtu, (u16 __user *) optval))
+			err = -EFAULT;
+		break;
+
 	default:
 		err = -ENOPROTOOPT;
 		break;
@@ -554,6 +637,11 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
 
 	switch (optname) {
 	case L2CAP_OPTIONS:
+		if (bdaddr_type_is_le(chan->src_type)) {
+			err = -EINVAL;
+			break;
+		}
+
 		if (sk->sk_state == BT_CONNECTED) {
 			err = -EINVAL;
 			break;
@@ -585,6 +673,8 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
 
 		chan->mode = opts.mode;
 		switch (chan->mode) {
+		case L2CAP_MODE_LE_FLOWCTL:
+			break;
 		case L2CAP_MODE_BASIC:
 			clear_bit(CONF_STATE2_DEVICE, &chan->conf_state);
 			break;
@@ -612,6 +702,11 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
 			break;
 		}
 
+		if (opt & L2CAP_LM_FIPS) {
+			err = -EINVAL;
+			break;
+		}
+
 		if (opt & L2CAP_LM_AUTH)
 			chan->sec_level = BT_SECURITY_LOW;
 		if (opt & L2CAP_LM_ENCRYPT)
@@ -663,6 +758,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 	switch (optname) {
 	case BT_SECURITY:
 		if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED &&
+		    chan->chan_type != L2CAP_CHAN_FIXED &&
 		    chan->chan_type != L2CAP_CHAN_RAW) {
 			err = -EINVAL;
 			break;
@@ -691,11 +787,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 
 		/*change security for LE channels */
 		if (chan->scid == L2CAP_CID_ATT) {
-			if (!conn->hcon->out) {
-				err = -EINVAL;
-				break;
-			}
-
 			if (smp_conn_security(conn->hcon, sec.level))
 				break;
 			sk->sk_state = BT_CONFIG;
@@ -807,6 +898,37 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 
 		break;
 
+	case BT_SNDMTU:
+		if (!bdaddr_type_is_le(chan->src_type)) {
+			err = -EINVAL;
+			break;
+		}
+
+		/* Setting is not supported as it's the remote side that
+		 * decides this.
+		 */
+		err = -EPERM;
+		break;
+
+	case BT_RCVMTU:
+		if (!bdaddr_type_is_le(chan->src_type)) {
+			err = -EINVAL;
+			break;
+		}
+
+		if (sk->sk_state == BT_CONNECTED) {
+			err = -EISCONN;
+			break;
+		}
+
+		if (get_user(opt, (u32 __user *) optval)) {
+			err = -EFAULT;
+			break;
+		}
+
+		chan->imtu = opt;
+		break;
+
 	default:
 		err = -ENOPROTOOPT;
 		break;
@@ -859,10 +981,16 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	if (sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP,
 						    &bt_sk(sk)->flags)) {
-		sk->sk_state = BT_CONFIG;
-		pi->chan->state = BT_CONFIG;
+		if (bdaddr_type_is_le(pi->chan->src_type)) {
+			sk->sk_state = BT_CONNECTED;
+			pi->chan->state = BT_CONNECTED;
+			__l2cap_le_connect_rsp_defer(pi->chan);
+		} else {
+			sk->sk_state = BT_CONFIG;
+			pi->chan->state = BT_CONFIG;
+			__l2cap_connect_rsp_defer(pi->chan);
+		}
 
-		__l2cap_connect_rsp_defer(pi->chan);
 		err = 0;
 		goto done;
 	}
@@ -1047,13 +1175,16 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan)
 	/* Check for backlog size */
 	if (sk_acceptq_is_full(parent)) {
 		BT_DBG("backlog full %d", parent->sk_ack_backlog);
+		release_sock(parent);
 		return NULL;
 	}
 
 	sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP,
 			      GFP_ATOMIC);
-	if (!sk)
+	if (!sk) {
+		release_sock(parent);
 		return NULL;
+        }
 
 	bt_sock_reclassify_lock(sk, BTPROTO_L2CAP);
 
@@ -1138,7 +1269,7 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err)
 
 		if (parent) {
 			bt_accept_unlink(sk);
-			parent->sk_data_ready(parent, 0);
+			parent->sk_data_ready(parent);
 		} else {
 			sk->sk_state_change(sk);
 		}
@@ -1194,7 +1325,7 @@ static void l2cap_sock_ready_cb(struct l2cap_chan *chan)
 	sk->sk_state_change(sk);
 
 	if (parent)
-		parent->sk_data_ready(parent, 0);
+		parent->sk_data_ready(parent);
 
 	release_sock(sk);
 }
@@ -1207,7 +1338,7 @@ static void l2cap_sock_defer_cb(struct l2cap_chan *chan)
 
 	parent = bt_sk(sk)->parent;
 	if (parent)
-		parent->sk_data_ready(parent, 0);
+		parent->sk_data_ready(parent);
 
 	release_sock(sk);
 }
@@ -1236,6 +1367,14 @@ static long l2cap_sock_get_sndtimeo_cb(struct l2cap_chan *chan)
 	return sk->sk_sndtimeo;
 }
 
+static void l2cap_sock_suspend_cb(struct l2cap_chan *chan)
+{
+	struct sock *sk = chan->data;
+
+	set_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags);
+	sk->sk_state_change(sk);
+}
+
 static struct l2cap_ops l2cap_chan_ops = {
 	.name		= "L2CAP Socket Interface",
 	.new_connection	= l2cap_sock_new_connection_cb,
@@ -1246,6 +1385,7 @@ static struct l2cap_ops l2cap_chan_ops = {
 	.ready		= l2cap_sock_ready_cb,
 	.defer		= l2cap_sock_defer_cb,
 	.resume		= l2cap_sock_resume_cb,
+	.suspend	= l2cap_sock_suspend_cb,
 	.set_shutdown	= l2cap_sock_set_shutdown_cb,
 	.get_sndtimeo	= l2cap_sock_get_sndtimeo_cb,
 	.alloc_skb	= l2cap_sock_alloc_skb_cb,
@@ -1270,7 +1410,7 @@ static void l2cap_sock_destruct(struct sock *sk)
 static void l2cap_skb_msg_name(struct sk_buff *skb, void *msg_name,
 			       int *msg_namelen)
 {
-	struct sockaddr_l2 *la = (struct sockaddr_l2 *) msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_l2 *, la, msg_name);
 
 	memset(la, 0, sizeof(struct sockaddr_l2));
 	la->l2_family = AF_BLUETOOTH;
@@ -1303,6 +1443,13 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
 		chan->tx_win_max = pchan->tx_win_max;
 		chan->sec_level = pchan->sec_level;
 		chan->flags = pchan->flags;
+		chan->tx_credits = pchan->tx_credits;
+		chan->rx_credits = pchan->rx_credits;
+
+		if (chan->chan_type == L2CAP_CHAN_FIXED) {
+			chan->scid = pchan->scid;
+			chan->dcid = pchan->scid;
+		}
 
 		security_sk_clone(parent, sk);
 	} else {
diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c
index b3fbc73516c..941ad7530ed 100644
--- a/net/bluetooth/lib.c
+++ b/net/bluetooth/lib.c
@@ -58,6 +58,7 @@ int bt_to_errno(__u16 code)
 		return EIO;
 
 	case 0x04:
+	case 0x3c:
 		return EHOSTDOWN;
 
 	case 0x05:
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 074d83690a4..af8e0a6243b 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -29,12 +29,13 @@
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/mgmt.h>
 
 #include "smp.h"
 
 #define MGMT_VERSION	1
-#define MGMT_REVISION	4
+#define MGMT_REVISION	6
 
 static const u16 mgmt_commands[] = {
 	MGMT_OP_READ_INDEX_LIST,
@@ -79,6 +80,11 @@ static const u16 mgmt_commands[] = {
 	MGMT_OP_SET_BREDR,
 	MGMT_OP_SET_STATIC_ADDRESS,
 	MGMT_OP_SET_SCAN_PARAMS,
+	MGMT_OP_SET_SECURE_CONN,
+	MGMT_OP_SET_DEBUG_KEYS,
+	MGMT_OP_SET_PRIVACY,
+	MGMT_OP_LOAD_IRKS,
+	MGMT_OP_GET_CONN_INFO,
 };
 
 static const u16 mgmt_events[] = {
@@ -103,6 +109,8 @@ static const u16 mgmt_events[] = {
 	MGMT_EV_DEVICE_UNBLOCKED,
 	MGMT_EV_DEVICE_UNPAIRED,
 	MGMT_EV_PASSKEY_NOTIFY,
+	MGMT_EV_NEW_IRK,
+	MGMT_EV_NEW_CSRK,
 };
 
 #define CACHE_TIMEOUT	msecs_to_jiffies(2 * 1000)
@@ -127,7 +135,7 @@ static u8 mgmt_status_table[] = {
 	MGMT_STATUS_FAILED,		/* Hardware Failure */
 	MGMT_STATUS_CONNECT_FAILED,	/* Page Timeout */
 	MGMT_STATUS_AUTH_FAILED,	/* Authentication Failed */
-	MGMT_STATUS_NOT_PAIRED,		/* PIN or Key Missing */
+	MGMT_STATUS_AUTH_FAILED,	/* PIN or Key Missing */
 	MGMT_STATUS_NO_RESOURCES,	/* Memory Full */
 	MGMT_STATUS_TIMEOUT,		/* Connection Timeout */
 	MGMT_STATUS_NO_RESOURCES,	/* Max Number of Connections */
@@ -207,7 +215,7 @@ static int cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status)
 
 	hdr = (void *) skb_put(skb, sizeof(*hdr));
 
-	hdr->opcode = __constant_cpu_to_le16(MGMT_EV_CMD_STATUS);
+	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_STATUS);
 	hdr->index = cpu_to_le16(index);
 	hdr->len = cpu_to_le16(sizeof(*ev));
 
@@ -238,7 +246,7 @@ static int cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status,
 
 	hdr = (void *) skb_put(skb, sizeof(*hdr));
 
-	hdr->opcode = __constant_cpu_to_le16(MGMT_EV_CMD_COMPLETE);
+	hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE);
 	hdr->index = cpu_to_le16(index);
 	hdr->len = cpu_to_le16(sizeof(*ev) + rp_len);
 
@@ -264,7 +272,7 @@ static int read_version(struct sock *sk, struct hci_dev *hdev, void *data,
 	BT_DBG("sock %p", sk);
 
 	rp.version = MGMT_VERSION;
-	rp.revision = __constant_cpu_to_le16(MGMT_REVISION);
+	rp.revision = cpu_to_le16(MGMT_REVISION);
 
 	return cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_VERSION, 0, &rp,
 			    sizeof(rp));
@@ -288,8 +296,8 @@ static int read_commands(struct sock *sk, struct hci_dev *hdev, void *data,
 	if (!rp)
 		return -ENOMEM;
 
-	rp->num_commands = __constant_cpu_to_le16(num_commands);
-	rp->num_events = __constant_cpu_to_le16(num_events);
+	rp->num_commands = cpu_to_le16(num_commands);
+	rp->num_events = cpu_to_le16(num_events);
 
 	for (i = 0, opcode = rp->opcodes; i < num_commands; i++, opcode++)
 		put_unaligned_le16(mgmt_commands[i], opcode);
@@ -363,6 +371,7 @@ static u32 get_supported_settings(struct hci_dev *hdev)
 
 	settings |= MGMT_SETTING_POWERED;
 	settings |= MGMT_SETTING_PAIRABLE;
+	settings |= MGMT_SETTING_DEBUG_KEYS;
 
 	if (lmp_bredr_capable(hdev)) {
 		settings |= MGMT_SETTING_CONNECTABLE;
@@ -376,11 +385,16 @@ static u32 get_supported_settings(struct hci_dev *hdev)
 			settings |= MGMT_SETTING_SSP;
 			settings |= MGMT_SETTING_HS;
 		}
+
+		if (lmp_sc_capable(hdev) ||
+		    test_bit(HCI_FORCE_SC, &hdev->dev_flags))
+			settings |= MGMT_SETTING_SECURE_CONN;
 	}
 
 	if (lmp_le_capable(hdev)) {
 		settings |= MGMT_SETTING_LE;
 		settings |= MGMT_SETTING_ADVERTISING;
+		settings |= MGMT_SETTING_PRIVACY;
 	}
 
 	return settings;
@@ -423,6 +437,15 @@ static u32 get_current_settings(struct hci_dev *hdev)
 	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
 		settings |= MGMT_SETTING_ADVERTISING;
 
+	if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags))
+		settings |= MGMT_SETTING_SECURE_CONN;
+
+	if (test_bit(HCI_DEBUG_KEYS, &hdev->dev_flags))
+		settings |= MGMT_SETTING_DEBUG_KEYS;
+
+	if (test_bit(HCI_PRIVACY, &hdev->dev_flags))
+		settings |= MGMT_SETTING_PRIVACY;
+
 	return settings;
 }
 
@@ -629,14 +652,8 @@ static u8 create_adv_data(struct hci_dev *hdev, u8 *ptr)
 
 	flags |= get_adv_discov_flags(hdev);
 
-	if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
-		if (lmp_le_br_capable(hdev))
-			flags |= LE_AD_SIM_LE_BREDR_CTRL;
-		if (lmp_host_le_br_capable(hdev))
-			flags |= LE_AD_SIM_LE_BREDR_HOST;
-	} else {
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
 		flags |= LE_AD_NO_BREDR;
-	}
 
 	if (flags) {
 		BT_DBG("adv flags 0x%02x", flags);
@@ -803,6 +820,64 @@ static void update_class(struct hci_request *req)
 	hci_req_add(req, HCI_OP_WRITE_CLASS_OF_DEV, sizeof(cod), cod);
 }
 
+static bool get_connectable(struct hci_dev *hdev)
+{
+	struct pending_cmd *cmd;
+
+	/* If there's a pending mgmt command the flag will not yet have
+	 * it's final value, so check for this first.
+	 */
+	cmd = mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev);
+	if (cmd) {
+		struct mgmt_mode *cp = cmd->param;
+		return cp->val;
+	}
+
+	return test_bit(HCI_CONNECTABLE, &hdev->dev_flags);
+}
+
+static void enable_advertising(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_cp_le_set_adv_param cp;
+	u8 own_addr_type, enable = 0x01;
+	bool connectable;
+
+	/* Clear the HCI_ADVERTISING bit temporarily so that the
+	 * hci_update_random_address knows that it's safe to go ahead
+	 * and write a new random address. The flag will be set back on
+	 * as soon as the SET_ADV_ENABLE HCI command completes.
+	 */
+	clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
+
+	connectable = get_connectable(hdev);
+
+	/* Set require_privacy to true only when non-connectable
+	 * advertising is used. In that case it is fine to use a
+	 * non-resolvable private address.
+	 */
+	if (hci_update_random_address(req, !connectable, &own_addr_type) < 0)
+		return;
+
+	memset(&cp, 0, sizeof(cp));
+	cp.min_interval = cpu_to_le16(0x0800);
+	cp.max_interval = cpu_to_le16(0x0800);
+	cp.type = connectable ? LE_ADV_IND : LE_ADV_NONCONN_IND;
+	cp.own_address_type = own_addr_type;
+	cp.channel_map = hdev->le_adv_channel_map;
+
+	hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp);
+
+	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
+}
+
+static void disable_advertising(struct hci_request *req)
+{
+	u8 enable = 0x00;
+
+	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
+}
+
 static void service_cache_off(struct work_struct *work)
 {
 	struct hci_dev *hdev = container_of(work, struct hci_dev,
@@ -824,12 +899,39 @@ static void service_cache_off(struct work_struct *work)
 	hci_req_run(&req, NULL);
 }
 
+static void rpa_expired(struct work_struct *work)
+{
+	struct hci_dev *hdev = container_of(work, struct hci_dev,
+					    rpa_expired.work);
+	struct hci_request req;
+
+	BT_DBG("");
+
+	set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
+
+	if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags) ||
+	    hci_conn_num(hdev, LE_LINK) > 0)
+		return;
+
+	/* The generation of a new RPA and programming it into the
+	 * controller happens in the enable_advertising() function.
+	 */
+
+	hci_req_init(&req, hdev);
+
+	disable_advertising(&req);
+	enable_advertising(&req);
+
+	hci_req_run(&req, NULL);
+}
+
 static void mgmt_init_hdev(struct sock *sk, struct hci_dev *hdev)
 {
 	if (test_and_set_bit(HCI_MGMT, &hdev->dev_flags))
 		return;
 
 	INIT_DELAYED_WORK(&hdev->service_cache, service_cache_off);
+	INIT_DELAYED_WORK(&hdev->rpa_expired, rpa_expired);
 
 	/* Non-mgmt controlled devices get this bit set
 	 * implicitly so that pairing works for them, however
@@ -935,6 +1037,106 @@ static int send_settings_rsp(struct sock *sk, u16 opcode, struct hci_dev *hdev)
 			    sizeof(settings));
 }
 
+static void clean_up_hci_complete(struct hci_dev *hdev, u8 status)
+{
+	BT_DBG("%s status 0x%02x", hdev->name, status);
+
+	if (hci_conn_count(hdev) == 0) {
+		cancel_delayed_work(&hdev->power_off);
+		queue_work(hdev->req_workqueue, &hdev->power_off.work);
+	}
+}
+
+static void hci_stop_discovery(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_cp_remote_name_req_cancel cp;
+	struct inquiry_entry *e;
+
+	switch (hdev->discovery.state) {
+	case DISCOVERY_FINDING:
+		if (test_bit(HCI_INQUIRY, &hdev->flags)) {
+			hci_req_add(req, HCI_OP_INQUIRY_CANCEL, 0, NULL);
+		} else {
+			cancel_delayed_work(&hdev->le_scan_disable);
+			hci_req_add_le_scan_disable(req);
+		}
+
+		break;
+
+	case DISCOVERY_RESOLVING:
+		e = hci_inquiry_cache_lookup_resolve(hdev, BDADDR_ANY,
+						     NAME_PENDING);
+		if (!e)
+			return;
+
+		bacpy(&cp.bdaddr, &e->data.bdaddr);
+		hci_req_add(req, HCI_OP_REMOTE_NAME_REQ_CANCEL, sizeof(cp),
+			    &cp);
+
+		break;
+
+	default:
+		/* Passive scanning */
+		if (test_bit(HCI_LE_SCAN, &hdev->dev_flags))
+			hci_req_add_le_scan_disable(req);
+		break;
+	}
+}
+
+static int clean_up_hci_state(struct hci_dev *hdev)
+{
+	struct hci_request req;
+	struct hci_conn *conn;
+
+	hci_req_init(&req, hdev);
+
+	if (test_bit(HCI_ISCAN, &hdev->flags) ||
+	    test_bit(HCI_PSCAN, &hdev->flags)) {
+		u8 scan = 0x00;
+		hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
+	}
+
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
+		disable_advertising(&req);
+
+	hci_stop_discovery(&req);
+
+	list_for_each_entry(conn, &hdev->conn_hash.list, list) {
+		struct hci_cp_disconnect dc;
+		struct hci_cp_reject_conn_req rej;
+
+		switch (conn->state) {
+		case BT_CONNECTED:
+		case BT_CONFIG:
+			dc.handle = cpu_to_le16(conn->handle);
+			dc.reason = 0x15; /* Terminated due to Power Off */
+			hci_req_add(&req, HCI_OP_DISCONNECT, sizeof(dc), &dc);
+			break;
+		case BT_CONNECT:
+			if (conn->type == LE_LINK)
+				hci_req_add(&req, HCI_OP_LE_CREATE_CONN_CANCEL,
+					    0, NULL);
+			else if (conn->type == ACL_LINK)
+				hci_req_add(&req, HCI_OP_CREATE_CONN_CANCEL,
+					    6, &conn->dst);
+			break;
+		case BT_CONNECT2:
+			bacpy(&rej.bdaddr, &conn->dst);
+			rej.reason = 0x15; /* Terminated due to Power Off */
+			if (conn->type == ACL_LINK)
+				hci_req_add(&req, HCI_OP_REJECT_CONN_REQ,
+					    sizeof(rej), &rej);
+			else if (conn->type == SCO_LINK)
+				hci_req_add(&req, HCI_OP_REJECT_SYNC_CONN_REQ,
+					    sizeof(rej), &rej);
+			break;
+		}
+	}
+
+	return hci_req_run(&req, clean_up_hci_complete);
+}
+
 static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data,
 		       u16 len)
 {
@@ -978,12 +1180,23 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto failed;
 	}
 
-	if (cp->val)
+	if (cp->val) {
 		queue_work(hdev->req_workqueue, &hdev->power_on);
-	else
-		queue_work(hdev->req_workqueue, &hdev->power_off.work);
-
-	err = 0;
+		err = 0;
+	} else {
+		/* Disconnect connections, stop scans, etc */
+		err = clean_up_hci_state(hdev);
+		if (!err)
+			queue_delayed_work(hdev->req_workqueue, &hdev->power_off,
+					   HCI_POWER_OFF_TIMEOUT);
+
+		/* ENODATA means there were no HCI commands queued */
+		if (err == -ENODATA) {
+			cancel_delayed_work(&hdev->power_off);
+			queue_work(hdev->req_workqueue, &hdev->power_off.work);
+			err = 0;
+		}
+	}
 
 failed:
 	hci_dev_unlock(hdev);
@@ -1005,7 +1218,7 @@ static int mgmt_event(u16 event, struct hci_dev *hdev, void *data, u16 data_len,
 	if (hdev)
 		hdr->index = cpu_to_le16(hdev->id);
 	else
-		hdr->index = __constant_cpu_to_le16(MGMT_INDEX_NONE);
+		hdr->index = cpu_to_le16(MGMT_INDEX_NONE);
 	hdr->len = cpu_to_le16(data_len);
 
 	if (data)
@@ -1264,7 +1477,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
 
 		if (cp->val == 0x02) {
 			/* Limited discoverable mode */
-			hci_cp.num_iac = 2;
+			hci_cp.num_iac = min_t(u8, hdev->num_iac, 2);
 			hci_cp.iac_lap[0] = 0x00;	/* LIAC */
 			hci_cp.iac_lap[1] = 0x8b;
 			hci_cp.iac_lap[2] = 0x9e;
@@ -1317,15 +1530,15 @@ static void write_fast_connectable(struct hci_request *req, bool enable)
 		type = PAGE_SCAN_TYPE_INTERLACED;
 
 		/* 160 msec page scan interval */
-		acp.interval = __constant_cpu_to_le16(0x0100);
+		acp.interval = cpu_to_le16(0x0100);
 	} else {
 		type = PAGE_SCAN_TYPE_STANDARD;	/* default */
 
 		/* default 1.28 sec page scan */
-		acp.interval = __constant_cpu_to_le16(0x0800);
+		acp.interval = cpu_to_le16(0x0800);
 	}
 
-	acp.window = __constant_cpu_to_le16(0x0012);
+	acp.window = cpu_to_le16(0x0012);
 
 	if (__cpu_to_le16(hdev->page_scan_interval) != acp.interval ||
 	    __cpu_to_le16(hdev->page_scan_window) != acp.window)
@@ -1336,50 +1549,6 @@ static void write_fast_connectable(struct hci_request *req, bool enable)
 		hci_req_add(req, HCI_OP_WRITE_PAGE_SCAN_TYPE, 1, &type);
 }
 
-static u8 get_adv_type(struct hci_dev *hdev)
-{
-	struct pending_cmd *cmd;
-	bool connectable;
-
-	/* If there's a pending mgmt command the flag will not yet have
-	 * it's final value, so check for this first.
-	 */
-	cmd = mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev);
-	if (cmd) {
-		struct mgmt_mode *cp = cmd->param;
-		connectable = !!cp->val;
-	} else {
-		connectable = test_bit(HCI_CONNECTABLE, &hdev->dev_flags);
-	}
-
-	return connectable ? LE_ADV_IND : LE_ADV_NONCONN_IND;
-}
-
-static void enable_advertising(struct hci_request *req)
-{
-	struct hci_dev *hdev = req->hdev;
-	struct hci_cp_le_set_adv_param cp;
-	u8 enable = 0x01;
-
-	memset(&cp, 0, sizeof(cp));
-	cp.min_interval = __constant_cpu_to_le16(0x0800);
-	cp.max_interval = __constant_cpu_to_le16(0x0800);
-	cp.type = get_adv_type(hdev);
-	cp.own_address_type = hdev->own_addr_type;
-	cp.channel_map = 0x07;
-
-	hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp);
-
-	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
-}
-
-static void disable_advertising(struct hci_request *req)
-{
-	u8 enable = 0x00;
-
-	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
-}
-
 static void set_connectable_complete(struct hci_dev *hdev, u8 status)
 {
 	struct pending_cmd *cmd;
@@ -2065,7 +2234,7 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data,
 	}
 
 	if (memcmp(cp->uuid, bt_uuid_any, 16) == 0) {
-		err = hci_uuids_clear(hdev);
+		hci_uuids_clear(hdev);
 
 		if (enable_service_cache(hdev)) {
 			err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_UUID,
@@ -2205,6 +2374,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 {
 	struct mgmt_cp_load_link_keys *cp = data;
 	u16 key_count, expected_len;
+	bool changed;
 	int i;
 
 	BT_DBG("request for %s", hdev->name);
@@ -2219,7 +2389,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 					sizeof(struct mgmt_link_key_info);
 	if (expected_len != len) {
 		BT_ERR("load_link_keys: expected %u bytes, got %u bytes",
-		       len, expected_len);
+		       expected_len, len);
 		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
 				  MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -2234,7 +2404,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_link_key_info *key = &cp->keys[i];
 
-		if (key->addr.type != BDADDR_BREDR)
+		if (key->addr.type != BDADDR_BREDR || key->type > 0x08)
 			return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS,
 					  MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -2244,9 +2414,12 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 	hci_link_keys_clear(hdev);
 
 	if (cp->debug_keys)
-		set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags);
+		changed = !test_and_set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags);
 	else
-		clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags);
+		changed = test_and_clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags);
+
+	if (changed)
+		new_settings(hdev, NULL);
 
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_link_key_info *key = &cp->keys[i];
@@ -2306,10 +2479,22 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 		goto unlock;
 	}
 
-	if (cp->addr.type == BDADDR_BREDR)
+	if (cp->addr.type == BDADDR_BREDR) {
 		err = hci_remove_link_key(hdev, &cp->addr.bdaddr);
-	else
-		err = hci_remove_ltk(hdev, &cp->addr.bdaddr);
+	} else {
+		u8 addr_type;
+
+		if (cp->addr.type == BDADDR_LE_PUBLIC)
+			addr_type = ADDR_LE_DEV_PUBLIC;
+		else
+			addr_type = ADDR_LE_DEV_RANDOM;
+
+		hci_remove_irk(hdev, &cp->addr.bdaddr, addr_type);
+
+		hci_conn_params_del(hdev, &cp->addr.bdaddr, addr_type);
+
+		err = hci_remove_ltk(hdev, &cp->addr.bdaddr, addr_type);
+	}
 
 	if (err < 0) {
 		err = cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE,
@@ -2633,6 +2818,16 @@ static void pairing_complete(struct pending_cmd *cmd, u8 status)
 	mgmt_pending_remove(cmd);
 }
 
+void mgmt_smp_complete(struct hci_conn *conn, bool complete)
+{
+	u8 status = complete ? MGMT_STATUS_SUCCESS : MGMT_STATUS_FAILED;
+	struct pending_cmd *cmd;
+
+	cmd = find_pairing(conn);
+	if (cmd)
+		pairing_complete(cmd, status);
+}
+
 static void pairing_complete_cb(struct hci_conn *conn, u8 status)
 {
 	struct pending_cmd *cmd;
@@ -2646,7 +2841,7 @@ static void pairing_complete_cb(struct hci_conn *conn, u8 status)
 		pairing_complete(cmd, mgmt_status(status));
 }
 
-static void le_connect_complete_cb(struct hci_conn *conn, u8 status)
+static void le_pairing_complete_cb(struct hci_conn *conn, u8 status)
 {
 	struct pending_cmd *cmd;
 
@@ -2692,17 +2887,24 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	}
 
 	sec_level = BT_SECURITY_MEDIUM;
-	if (cp->io_cap == 0x03)
-		auth_type = HCI_AT_DEDICATED_BONDING;
-	else
-		auth_type = HCI_AT_DEDICATED_BONDING_MITM;
+	auth_type = HCI_AT_DEDICATED_BONDING;
 
-	if (cp->addr.type == BDADDR_BREDR)
-		conn = hci_connect(hdev, ACL_LINK, &cp->addr.bdaddr,
-				   cp->addr.type, sec_level, auth_type);
-	else
-		conn = hci_connect(hdev, LE_LINK, &cp->addr.bdaddr,
-				   cp->addr.type, sec_level, auth_type);
+	if (cp->addr.type == BDADDR_BREDR) {
+		conn = hci_connect_acl(hdev, &cp->addr.bdaddr, sec_level,
+				       auth_type);
+	} else {
+		u8 addr_type;
+
+		/* Convert from L2CAP channel address type to HCI address type
+		 */
+		if (cp->addr.type == BDADDR_LE_PUBLIC)
+			addr_type = ADDR_LE_DEV_PUBLIC;
+		else
+			addr_type = ADDR_LE_DEV_RANDOM;
+
+		conn = hci_connect_le(hdev, &cp->addr.bdaddr, addr_type,
+				      sec_level, auth_type);
+	}
 
 	if (IS_ERR(conn)) {
 		int status;
@@ -2733,13 +2935,16 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	}
 
 	/* For LE, just connecting isn't a proof that the pairing finished */
-	if (cp->addr.type == BDADDR_BREDR)
+	if (cp->addr.type == BDADDR_BREDR) {
 		conn->connect_cfm_cb = pairing_complete_cb;
-	else
-		conn->connect_cfm_cb = le_connect_complete_cb;
+		conn->security_cfm_cb = pairing_complete_cb;
+		conn->disconn_cfm_cb = pairing_complete_cb;
+	} else {
+		conn->connect_cfm_cb = le_pairing_complete_cb;
+		conn->security_cfm_cb = le_pairing_complete_cb;
+		conn->disconn_cfm_cb = le_pairing_complete_cb;
+	}
 
-	conn->security_cfm_cb = pairing_complete_cb;
-	conn->disconn_cfm_cb = pairing_complete_cb;
 	conn->io_capability = cp->io_cap;
 	cmd->user_data = conn;
 
@@ -2826,8 +3031,13 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev,
 	}
 
 	if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) {
-		/* Continue with pairing via SMP */
+		/* Continue with pairing via SMP. The hdev lock must be
+		 * released as SMP may try to recquire it for crypto
+		 * purposes.
+		 */
+		hci_dev_unlock(hdev);
 		err = smp_user_confirm_reply(conn, mgmt_op, passkey);
+		hci_dev_lock(hdev);
 
 		if (!err)
 			err = cmd_complete(sk, hdev->id, mgmt_op,
@@ -3071,7 +3281,12 @@ static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev,
 		goto unlock;
 	}
 
-	err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL);
+	if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags))
+		err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_EXT_DATA,
+				   0, NULL);
+	else
+		err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL);
+
 	if (err < 0)
 		mgmt_pending_remove(cmd);
 
@@ -3083,23 +3298,46 @@ unlock:
 static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 			       void *data, u16 len)
 {
-	struct mgmt_cp_add_remote_oob_data *cp = data;
-	u8 status;
 	int err;
 
 	BT_DBG("%s ", hdev->name);
 
 	hci_dev_lock(hdev);
 
-	err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr, cp->hash,
-				      cp->randomizer);
-	if (err < 0)
-		status = MGMT_STATUS_FAILED;
-	else
-		status = MGMT_STATUS_SUCCESS;
+	if (len == MGMT_ADD_REMOTE_OOB_DATA_SIZE) {
+		struct mgmt_cp_add_remote_oob_data *cp = data;
+		u8 status;
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, status,
-			   &cp->addr, sizeof(cp->addr));
+		err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr,
+					      cp->hash, cp->randomizer);
+		if (err < 0)
+			status = MGMT_STATUS_FAILED;
+		else
+			status = MGMT_STATUS_SUCCESS;
+
+		err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA,
+				   status, &cp->addr, sizeof(cp->addr));
+	} else if (len == MGMT_ADD_REMOTE_OOB_EXT_DATA_SIZE) {
+		struct mgmt_cp_add_remote_oob_ext_data *cp = data;
+		u8 status;
+
+		err = hci_add_remote_oob_ext_data(hdev, &cp->addr.bdaddr,
+						  cp->hash192,
+						  cp->randomizer192,
+						  cp->hash256,
+						  cp->randomizer256);
+		if (err < 0)
+			status = MGMT_STATUS_FAILED;
+		else
+			status = MGMT_STATUS_SUCCESS;
+
+		err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA,
+				   status, &cp->addr, sizeof(cp->addr));
+	} else {
+		BT_ERR("add_remote_oob_data: invalid length of %u bytes", len);
+		err = cmd_status(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA,
+				 MGMT_STATUS_INVALID_PARAMS);
+	}
 
 	hci_dev_unlock(hdev);
 	return err;
@@ -3152,6 +3390,8 @@ static int mgmt_start_discovery_failed(struct hci_dev *hdev, u8 status)
 
 static void start_discovery_complete(struct hci_dev *hdev, u8 status)
 {
+	unsigned long timeout = 0;
+
 	BT_DBG("status %d", status);
 
 	if (status) {
@@ -3167,13 +3407,11 @@ static void start_discovery_complete(struct hci_dev *hdev, u8 status)
 
 	switch (hdev->discovery.type) {
 	case DISCOV_TYPE_LE:
-		queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable,
-				   DISCOV_LE_TIMEOUT);
+		timeout = msecs_to_jiffies(DISCOV_LE_TIMEOUT);
 		break;
 
 	case DISCOV_TYPE_INTERLEAVED:
-		queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable,
-				   DISCOV_INTERLEAVED_TIMEOUT);
+		timeout = msecs_to_jiffies(hdev->discov_interleaved_timeout);
 		break;
 
 	case DISCOV_TYPE_BREDR:
@@ -3182,6 +3420,11 @@ static void start_discovery_complete(struct hci_dev *hdev, u8 status)
 	default:
 		BT_ERR("Invalid discovery type %d", hdev->discovery.type);
 	}
+
+	if (!timeout)
+		return;
+
+	queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable, timeout);
 }
 
 static int start_discovery(struct sock *sk, struct hci_dev *hdev,
@@ -3195,7 +3438,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
 	struct hci_request req;
 	/* General inquiry access code (GIAC) */
 	u8 lap[3] = { 0x33, 0x8b, 0x9e };
-	u8 status;
+	u8 status, own_addr_type;
 	int err;
 
 	BT_DBG("%s", hdev->name);
@@ -3280,18 +3523,31 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
 			goto failed;
 		}
 
-		if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) {
+		/* If controller is scanning, it means the background scanning
+		 * is running. Thus, we should temporarily stop it in order to
+		 * set the discovery scanning parameters.
+		 */
+		if (test_bit(HCI_LE_SCAN, &hdev->dev_flags))
+			hci_req_add_le_scan_disable(&req);
+
+		memset(&param_cp, 0, sizeof(param_cp));
+
+		/* All active scans will be done with either a resolvable
+		 * private address (when privacy feature has been enabled)
+		 * or unresolvable private address.
+		 */
+		err = hci_update_random_address(&req, true, &own_addr_type);
+		if (err < 0) {
 			err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
-					 MGMT_STATUS_BUSY);
+					 MGMT_STATUS_FAILED);
 			mgmt_pending_remove(cmd);
 			goto failed;
 		}
 
-		memset(&param_cp, 0, sizeof(param_cp));
 		param_cp.type = LE_SCAN_ACTIVE;
 		param_cp.interval = cpu_to_le16(DISCOV_LE_SCAN_INT);
 		param_cp.window = cpu_to_le16(DISCOV_LE_SCAN_WIN);
-		param_cp.own_address_type = hdev->own_addr_type;
+		param_cp.own_address_type = own_addr_type;
 		hci_req_add(&req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
 			    &param_cp);
 
@@ -3358,10 +3614,7 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
 {
 	struct mgmt_cp_stop_discovery *mgmt_cp = data;
 	struct pending_cmd *cmd;
-	struct hci_cp_remote_name_req_cancel cp;
-	struct inquiry_entry *e;
 	struct hci_request req;
-	struct hci_cp_le_set_scan_enable enable_cp;
 	int err;
 
 	BT_DBG("%s", hdev->name);
@@ -3390,55 +3643,22 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	hci_req_init(&req, hdev);
 
-	switch (hdev->discovery.state) {
-	case DISCOVERY_FINDING:
-		if (test_bit(HCI_INQUIRY, &hdev->flags)) {
-			hci_req_add(&req, HCI_OP_INQUIRY_CANCEL, 0, NULL);
-		} else {
-			cancel_delayed_work(&hdev->le_scan_disable);
-
-			memset(&enable_cp, 0, sizeof(enable_cp));
-			enable_cp.enable = LE_SCAN_DISABLE;
-			hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE,
-				    sizeof(enable_cp), &enable_cp);
-		}
-
-		break;
-
-	case DISCOVERY_RESOLVING:
-		e = hci_inquiry_cache_lookup_resolve(hdev, BDADDR_ANY,
-						     NAME_PENDING);
-		if (!e) {
-			mgmt_pending_remove(cmd);
-			err = cmd_complete(sk, hdev->id,
-					   MGMT_OP_STOP_DISCOVERY, 0,
-					   &mgmt_cp->type,
-					   sizeof(mgmt_cp->type));
-			hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
-			goto unlock;
-		}
-
-		bacpy(&cp.bdaddr, &e->data.bdaddr);
-		hci_req_add(&req, HCI_OP_REMOTE_NAME_REQ_CANCEL, sizeof(cp),
-			    &cp);
-
-		break;
+	hci_stop_discovery(&req);
 
-	default:
-		BT_DBG("unknown discovery state %u", hdev->discovery.state);
-
-		mgmt_pending_remove(cmd);
-		err = cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY,
-				   MGMT_STATUS_FAILED, &mgmt_cp->type,
-				   sizeof(mgmt_cp->type));
+	err = hci_req_run(&req, stop_discovery_complete);
+	if (!err) {
+		hci_discovery_set_state(hdev, DISCOVERY_STOPPING);
 		goto unlock;
 	}
 
-	err = hci_req_run(&req, stop_discovery_complete);
-	if (err < 0)
-		mgmt_pending_remove(cmd);
-	else
-		hci_discovery_set_state(hdev, DISCOVERY_STOPPING);
+	mgmt_pending_remove(cmd);
+
+	/* If no HCI commands were sent we're done */
+	if (err == -ENODATA) {
+		err = cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY, 0,
+				   &mgmt_cp->type, sizeof(mgmt_cp->type));
+		hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+	}
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -3457,15 +3677,17 @@ static int confirm_name(struct sock *sk, struct hci_dev *hdev, void *data,
 	hci_dev_lock(hdev);
 
 	if (!hci_discovery_active(hdev)) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_CONFIRM_NAME,
-				 MGMT_STATUS_FAILED);
+		err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME,
+				   MGMT_STATUS_FAILED, &cp->addr,
+				   sizeof(cp->addr));
 		goto failed;
 	}
 
 	e = hci_inquiry_cache_lookup_unknown(hdev, &cp->addr.bdaddr);
 	if (!e) {
-		err = cmd_status(sk, hdev->id, MGMT_OP_CONFIRM_NAME,
-				 MGMT_STATUS_INVALID_PARAMS);
+		err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME,
+				   MGMT_STATUS_INVALID_PARAMS, &cp->addr,
+				   sizeof(cp->addr));
 		goto failed;
 	}
 
@@ -3754,6 +3976,21 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev,
 
 	err = cmd_complete(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, 0, NULL, 0);
 
+	/* If background scan is running, restart it so new parameters are
+	 * loaded.
+	 */
+	if (test_bit(HCI_LE_SCAN, &hdev->dev_flags) &&
+	    hdev->discovery.state == DISCOVERY_STOPPED) {
+		struct hci_request req;
+
+		hci_req_init(&req, hdev);
+
+		hci_req_add_le_scan_disable(&req);
+		hci_req_add_le_passive_scan(&req);
+
+		hci_req_run(&req, NULL);
+	}
+
 	hci_dev_unlock(hdev);
 
 	return err;
@@ -3999,15 +4236,269 @@ unlock:
 	return err;
 }
 
+static int set_secure_conn(struct sock *sk, struct hci_dev *hdev,
+			   void *data, u16 len)
+{
+	struct mgmt_mode *cp = data;
+	struct pending_cmd *cmd;
+	u8 val, status;
+	int err;
+
+	BT_DBG("request for %s", hdev->name);
+
+	status = mgmt_bredr_support(hdev);
+	if (status)
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN,
+				  status);
+
+	if (!lmp_sc_capable(hdev) &&
+	    !test_bit(HCI_FORCE_SC, &hdev->dev_flags))
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN,
+				  MGMT_STATUS_NOT_SUPPORTED);
+
+	if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02)
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN,
+				  MGMT_STATUS_INVALID_PARAMS);
+
+	hci_dev_lock(hdev);
+
+	if (!hdev_is_powered(hdev)) {
+		bool changed;
+
+		if (cp->val) {
+			changed = !test_and_set_bit(HCI_SC_ENABLED,
+						    &hdev->dev_flags);
+			if (cp->val == 0x02)
+				set_bit(HCI_SC_ONLY, &hdev->dev_flags);
+			else
+				clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
+		} else {
+			changed = test_and_clear_bit(HCI_SC_ENABLED,
+						     &hdev->dev_flags);
+			clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
+		}
+
+		err = send_settings_rsp(sk, MGMT_OP_SET_SECURE_CONN, hdev);
+		if (err < 0)
+			goto failed;
+
+		if (changed)
+			err = new_settings(hdev, sk);
+
+		goto failed;
+	}
+
+	if (mgmt_pending_find(MGMT_OP_SET_SECURE_CONN, hdev)) {
+		err = cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN,
+				 MGMT_STATUS_BUSY);
+		goto failed;
+	}
+
+	val = !!cp->val;
+
+	if (val == test_bit(HCI_SC_ENABLED, &hdev->dev_flags) &&
+	    (cp->val == 0x02) == test_bit(HCI_SC_ONLY, &hdev->dev_flags)) {
+		err = send_settings_rsp(sk, MGMT_OP_SET_SECURE_CONN, hdev);
+		goto failed;
+	}
+
+	cmd = mgmt_pending_add(sk, MGMT_OP_SET_SECURE_CONN, hdev, data, len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto failed;
+	}
+
+	err = hci_send_cmd(hdev, HCI_OP_WRITE_SC_SUPPORT, 1, &val);
+	if (err < 0) {
+		mgmt_pending_remove(cmd);
+		goto failed;
+	}
+
+	if (cp->val == 0x02)
+		set_bit(HCI_SC_ONLY, &hdev->dev_flags);
+	else
+		clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
+
+failed:
+	hci_dev_unlock(hdev);
+	return err;
+}
+
+static int set_debug_keys(struct sock *sk, struct hci_dev *hdev,
+			  void *data, u16 len)
+{
+	struct mgmt_mode *cp = data;
+	bool changed;
+	int err;
+
+	BT_DBG("request for %s", hdev->name);
+
+	if (cp->val != 0x00 && cp->val != 0x01)
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_DEBUG_KEYS,
+				  MGMT_STATUS_INVALID_PARAMS);
+
+	hci_dev_lock(hdev);
+
+	if (cp->val)
+		changed = !test_and_set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags);
+	else
+		changed = test_and_clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags);
+
+	err = send_settings_rsp(sk, MGMT_OP_SET_DEBUG_KEYS, hdev);
+	if (err < 0)
+		goto unlock;
+
+	if (changed)
+		err = new_settings(hdev, sk);
+
+unlock:
+	hci_dev_unlock(hdev);
+	return err;
+}
+
+static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data,
+		       u16 len)
+{
+	struct mgmt_cp_set_privacy *cp = cp_data;
+	bool changed;
+	int err;
+
+	BT_DBG("request for %s", hdev->name);
+
+	if (!lmp_le_capable(hdev))
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY,
+				  MGMT_STATUS_NOT_SUPPORTED);
+
+	if (cp->privacy != 0x00 && cp->privacy != 0x01)
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY,
+				  MGMT_STATUS_INVALID_PARAMS);
+
+	if (hdev_is_powered(hdev))
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY,
+				  MGMT_STATUS_REJECTED);
+
+	hci_dev_lock(hdev);
+
+	/* If user space supports this command it is also expected to
+	 * handle IRKs. Therefore, set the HCI_RPA_RESOLVING flag.
+	 */
+	set_bit(HCI_RPA_RESOLVING, &hdev->dev_flags);
+
+	if (cp->privacy) {
+		changed = !test_and_set_bit(HCI_PRIVACY, &hdev->dev_flags);
+		memcpy(hdev->irk, cp->irk, sizeof(hdev->irk));
+		set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
+	} else {
+		changed = test_and_clear_bit(HCI_PRIVACY, &hdev->dev_flags);
+		memset(hdev->irk, 0, sizeof(hdev->irk));
+		clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
+	}
+
+	err = send_settings_rsp(sk, MGMT_OP_SET_PRIVACY, hdev);
+	if (err < 0)
+		goto unlock;
+
+	if (changed)
+		err = new_settings(hdev, sk);
+
+unlock:
+	hci_dev_unlock(hdev);
+	return err;
+}
+
+static bool irk_is_valid(struct mgmt_irk_info *irk)
+{
+	switch (irk->addr.type) {
+	case BDADDR_LE_PUBLIC:
+		return true;
+
+	case BDADDR_LE_RANDOM:
+		/* Two most significant bits shall be set */
+		if ((irk->addr.bdaddr.b[5] & 0xc0) != 0xc0)
+			return false;
+		return true;
+	}
+
+	return false;
+}
+
+static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
+		     u16 len)
+{
+	struct mgmt_cp_load_irks *cp = cp_data;
+	u16 irk_count, expected_len;
+	int i, err;
+
+	BT_DBG("request for %s", hdev->name);
+
+	if (!lmp_le_capable(hdev))
+		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS,
+				  MGMT_STATUS_NOT_SUPPORTED);
+
+	irk_count = __le16_to_cpu(cp->irk_count);
+
+	expected_len = sizeof(*cp) + irk_count * sizeof(struct mgmt_irk_info);
+	if (expected_len != len) {
+		BT_ERR("load_irks: expected %u bytes, got %u bytes",
+		       expected_len, len);
+		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS,
+				  MGMT_STATUS_INVALID_PARAMS);
+	}
+
+	BT_DBG("%s irk_count %u", hdev->name, irk_count);
+
+	for (i = 0; i < irk_count; i++) {
+		struct mgmt_irk_info *key = &cp->irks[i];
+
+		if (!irk_is_valid(key))
+			return cmd_status(sk, hdev->id,
+					  MGMT_OP_LOAD_IRKS,
+					  MGMT_STATUS_INVALID_PARAMS);
+	}
+
+	hci_dev_lock(hdev);
+
+	hci_smp_irks_clear(hdev);
+
+	for (i = 0; i < irk_count; i++) {
+		struct mgmt_irk_info *irk = &cp->irks[i];
+		u8 addr_type;
+
+		if (irk->addr.type == BDADDR_LE_PUBLIC)
+			addr_type = ADDR_LE_DEV_PUBLIC;
+		else
+			addr_type = ADDR_LE_DEV_RANDOM;
+
+		hci_add_irk(hdev, &irk->addr.bdaddr, addr_type, irk->val,
+			    BDADDR_ANY);
+	}
+
+	set_bit(HCI_RPA_RESOLVING, &hdev->dev_flags);
+
+	err = cmd_complete(sk, hdev->id, MGMT_OP_LOAD_IRKS, 0, NULL, 0);
+
+	hci_dev_unlock(hdev);
+
+	return err;
+}
+
 static bool ltk_is_valid(struct mgmt_ltk_info *key)
 {
-	if (key->authenticated != 0x00 && key->authenticated != 0x01)
-		return false;
 	if (key->master != 0x00 && key->master != 0x01)
 		return false;
-	if (!bdaddr_type_is_le(key->addr.type))
-		return false;
-	return true;
+
+	switch (key->addr.type) {
+	case BDADDR_LE_PUBLIC:
+		return true;
+
+	case BDADDR_LE_RANDOM:
+		/* Two most significant bits shall be set */
+		if ((key->addr.bdaddr.b[5] & 0xc0) != 0xc0)
+			return false;
+		return true;
+	}
+
+	return false;
 }
 
 static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
@@ -4029,7 +4520,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 					sizeof(struct mgmt_ltk_info);
 	if (expected_len != len) {
 		BT_ERR("load_keys: expected %u bytes, got %u bytes",
-		       len, expected_len);
+		       expected_len, len);
 		return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS,
 				  MGMT_STATUS_INVALID_PARAMS);
 	}
@@ -4051,7 +4542,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_ltk_info *key = &cp->keys[i];
-		u8 type, addr_type;
+		u8 type, addr_type, authenticated;
 
 		if (key->addr.type == BDADDR_LE_PUBLIC)
 			addr_type = ADDR_LE_DEV_PUBLIC;
@@ -4063,9 +4554,20 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 		else
 			type = HCI_SMP_LTK_SLAVE;
 
-		hci_add_ltk(hdev, &key->addr.bdaddr, addr_type,
-			    type, 0, key->authenticated, key->val,
-			    key->enc_size, key->ediv, key->rand);
+		switch (key->type) {
+		case MGMT_LTK_UNAUTHENTICATED:
+			authenticated = 0x00;
+			break;
+		case MGMT_LTK_AUTHENTICATED:
+			authenticated = 0x01;
+			break;
+		default:
+			continue;
+		}
+
+		hci_add_ltk(hdev, &key->addr.bdaddr, addr_type, type,
+			    authenticated, key->val, key->enc_size, key->ediv,
+			    key->rand);
 	}
 
 	err = cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, 0,
@@ -4076,6 +4578,218 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 	return err;
 }
 
+struct cmd_conn_lookup {
+	struct hci_conn *conn;
+	bool valid_tx_power;
+	u8 mgmt_status;
+};
+
+static void get_conn_info_complete(struct pending_cmd *cmd, void *data)
+{
+	struct cmd_conn_lookup *match = data;
+	struct mgmt_cp_get_conn_info *cp;
+	struct mgmt_rp_get_conn_info rp;
+	struct hci_conn *conn = cmd->user_data;
+
+	if (conn != match->conn)
+		return;
+
+	cp = (struct mgmt_cp_get_conn_info *) cmd->param;
+
+	memset(&rp, 0, sizeof(rp));
+	bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr);
+	rp.addr.type = cp->addr.type;
+
+	if (!match->mgmt_status) {
+		rp.rssi = conn->rssi;
+
+		if (match->valid_tx_power) {
+			rp.tx_power = conn->tx_power;
+			rp.max_tx_power = conn->max_tx_power;
+		} else {
+			rp.tx_power = HCI_TX_POWER_INVALID;
+			rp.max_tx_power = HCI_TX_POWER_INVALID;
+		}
+	}
+
+	cmd_complete(cmd->sk, cmd->index, MGMT_OP_GET_CONN_INFO,
+		     match->mgmt_status, &rp, sizeof(rp));
+
+	hci_conn_drop(conn);
+
+	mgmt_pending_remove(cmd);
+}
+
+static void conn_info_refresh_complete(struct hci_dev *hdev, u8 status)
+{
+	struct hci_cp_read_rssi *cp;
+	struct hci_conn *conn;
+	struct cmd_conn_lookup match;
+	u16 handle;
+
+	BT_DBG("status 0x%02x", status);
+
+	hci_dev_lock(hdev);
+
+	/* TX power data is valid in case request completed successfully,
+	 * otherwise we assume it's not valid. At the moment we assume that
+	 * either both or none of current and max values are valid to keep code
+	 * simple.
+	 */
+	match.valid_tx_power = !status;
+
+	/* Commands sent in request are either Read RSSI or Read Transmit Power
+	 * Level so we check which one was last sent to retrieve connection
+	 * handle.  Both commands have handle as first parameter so it's safe to
+	 * cast data on the same command struct.
+	 *
+	 * First command sent is always Read RSSI and we fail only if it fails.
+	 * In other case we simply override error to indicate success as we
+	 * already remembered if TX power value is actually valid.
+	 */
+	cp = hci_sent_cmd_data(hdev, HCI_OP_READ_RSSI);
+	if (!cp) {
+		cp = hci_sent_cmd_data(hdev, HCI_OP_READ_TX_POWER);
+		status = 0;
+	}
+
+	if (!cp) {
+		BT_ERR("invalid sent_cmd in response");
+		goto unlock;
+	}
+
+	handle = __le16_to_cpu(cp->handle);
+	conn = hci_conn_hash_lookup_handle(hdev, handle);
+	if (!conn) {
+		BT_ERR("unknown handle (%d) in response", handle);
+		goto unlock;
+	}
+
+	match.conn = conn;
+	match.mgmt_status = mgmt_status(status);
+
+	/* Cache refresh is complete, now reply for mgmt request for given
+	 * connection only.
+	 */
+	mgmt_pending_foreach(MGMT_OP_GET_CONN_INFO, hdev,
+			     get_conn_info_complete, &match);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
+static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data,
+			 u16 len)
+{
+	struct mgmt_cp_get_conn_info *cp = data;
+	struct mgmt_rp_get_conn_info rp;
+	struct hci_conn *conn;
+	unsigned long conn_info_age;
+	int err = 0;
+
+	BT_DBG("%s", hdev->name);
+
+	memset(&rp, 0, sizeof(rp));
+	bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr);
+	rp.addr.type = cp->addr.type;
+
+	if (!bdaddr_type_is_valid(cp->addr.type))
+		return cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+				    MGMT_STATUS_INVALID_PARAMS,
+				    &rp, sizeof(rp));
+
+	hci_dev_lock(hdev);
+
+	if (!hdev_is_powered(hdev)) {
+		err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+				   MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp));
+		goto unlock;
+	}
+
+	if (cp->addr.type == BDADDR_BREDR)
+		conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK,
+					       &cp->addr.bdaddr);
+	else
+		conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->addr.bdaddr);
+
+	if (!conn || conn->state != BT_CONNECTED) {
+		err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+				   MGMT_STATUS_NOT_CONNECTED, &rp, sizeof(rp));
+		goto unlock;
+	}
+
+	/* To avoid client trying to guess when to poll again for information we
+	 * calculate conn info age as random value between min/max set in hdev.
+	 */
+	conn_info_age = hdev->conn_info_min_age +
+			prandom_u32_max(hdev->conn_info_max_age -
+					hdev->conn_info_min_age);
+
+	/* Query controller to refresh cached values if they are too old or were
+	 * never read.
+	 */
+	if (time_after(jiffies, conn->conn_info_timestamp +
+		       msecs_to_jiffies(conn_info_age)) ||
+	    !conn->conn_info_timestamp) {
+		struct hci_request req;
+		struct hci_cp_read_tx_power req_txp_cp;
+		struct hci_cp_read_rssi req_rssi_cp;
+		struct pending_cmd *cmd;
+
+		hci_req_init(&req, hdev);
+		req_rssi_cp.handle = cpu_to_le16(conn->handle);
+		hci_req_add(&req, HCI_OP_READ_RSSI, sizeof(req_rssi_cp),
+			    &req_rssi_cp);
+
+		/* For LE links TX power does not change thus we don't need to
+		 * query for it once value is known.
+		 */
+		if (!bdaddr_type_is_le(cp->addr.type) ||
+		    conn->tx_power == HCI_TX_POWER_INVALID) {
+			req_txp_cp.handle = cpu_to_le16(conn->handle);
+			req_txp_cp.type = 0x00;
+			hci_req_add(&req, HCI_OP_READ_TX_POWER,
+				    sizeof(req_txp_cp), &req_txp_cp);
+		}
+
+		/* Max TX power needs to be read only once per connection */
+		if (conn->max_tx_power == HCI_TX_POWER_INVALID) {
+			req_txp_cp.handle = cpu_to_le16(conn->handle);
+			req_txp_cp.type = 0x01;
+			hci_req_add(&req, HCI_OP_READ_TX_POWER,
+				    sizeof(req_txp_cp), &req_txp_cp);
+		}
+
+		err = hci_req_run(&req, conn_info_refresh_complete);
+		if (err < 0)
+			goto unlock;
+
+		cmd = mgmt_pending_add(sk, MGMT_OP_GET_CONN_INFO, hdev,
+				       data, len);
+		if (!cmd) {
+			err = -ENOMEM;
+			goto unlock;
+		}
+
+		hci_conn_hold(conn);
+		cmd->user_data = conn;
+
+		conn->conn_info_timestamp = jiffies;
+	} else {
+		/* Cache is valid, just reply with values cached in hci_conn */
+		rp.rssi = conn->rssi;
+		rp.tx_power = conn->tx_power;
+		rp.max_tx_power = conn->max_tx_power;
+
+		err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+				   MGMT_STATUS_SUCCESS, &rp, sizeof(rp));
+	}
+
+unlock:
+	hci_dev_unlock(hdev);
+	return err;
+}
+
 static const struct mgmt_handler {
 	int (*func) (struct sock *sk, struct hci_dev *hdev, void *data,
 		     u16 data_len);
@@ -4115,7 +4829,7 @@ static const struct mgmt_handler {
 	{ user_passkey_reply,     false, MGMT_USER_PASSKEY_REPLY_SIZE },
 	{ user_passkey_neg_reply, false, MGMT_USER_PASSKEY_NEG_REPLY_SIZE },
 	{ read_local_oob_data,    false, MGMT_READ_LOCAL_OOB_DATA_SIZE },
-	{ add_remote_oob_data,    false, MGMT_ADD_REMOTE_OOB_DATA_SIZE },
+	{ add_remote_oob_data,    true,  MGMT_ADD_REMOTE_OOB_DATA_SIZE },
 	{ remove_remote_oob_data, false, MGMT_REMOVE_REMOTE_OOB_DATA_SIZE },
 	{ start_discovery,        false, MGMT_START_DISCOVERY_SIZE },
 	{ stop_discovery,         false, MGMT_STOP_DISCOVERY_SIZE },
@@ -4127,6 +4841,11 @@ static const struct mgmt_handler {
 	{ set_bredr,              false, MGMT_SETTING_SIZE },
 	{ set_static_address,     false, MGMT_SET_STATIC_ADDRESS_SIZE },
 	{ set_scan_params,        false, MGMT_SET_SCAN_PARAMS_SIZE },
+	{ set_secure_conn,        false, MGMT_SETTING_SIZE },
+	{ set_debug_keys,         false, MGMT_SETTING_SIZE },
+	{ set_privacy,            false, MGMT_SET_PRIVACY_SIZE },
+	{ load_irks,              true,  MGMT_LOAD_IRKS_SIZE },
+	{ get_conn_info,          false, MGMT_GET_CONN_INFO_SIZE },
 };
 
 
@@ -4243,6 +4962,17 @@ void mgmt_index_removed(struct hci_dev *hdev)
 	mgmt_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, NULL);
 }
 
+/* This function requires the caller holds hdev->lock */
+static void restart_le_auto_conns(struct hci_dev *hdev)
+{
+	struct hci_conn_params *p;
+
+	list_for_each_entry(p, &hdev->le_conn_params, list) {
+		if (p->auto_connect == HCI_AUTO_CONN_ALWAYS)
+			hci_pend_le_conn_add(hdev, &p->addr, p->addr_type);
+	}
+}
+
 static void powered_complete(struct hci_dev *hdev, u8 status)
 {
 	struct cmd_lookup match = { NULL, hdev };
@@ -4251,6 +4981,8 @@ static void powered_complete(struct hci_dev *hdev, u8 status)
 
 	hci_dev_lock(hdev);
 
+	restart_le_auto_conns(hdev);
+
 	mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match);
 
 	new_settings(hdev, match.sk);
@@ -4292,11 +5024,6 @@ static int powered_update_hci(struct hci_dev *hdev)
 	}
 
 	if (lmp_le_capable(hdev)) {
-		/* Set random address to static address if configured */
-		if (bacmp(&hdev->static_addr, BDADDR_ANY))
-			hci_req_add(&req, HCI_OP_LE_SET_RANDOM_ADDR, 6,
-				    &hdev->static_addr);
-
 		/* Make sure the controller has a good default for
 		 * advertising data. This also applies to the case
 		 * where BR/EDR was toggled during the AUTO_OFF phase.
@@ -4422,6 +5149,10 @@ void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable)
 	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev))
 		return;
 
+	/* Powering off may clear the scan mode - don't let that interfere */
+	if (!discoverable && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev))
+		return;
+
 	if (discoverable) {
 		changed = !test_and_set_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
 	} else {
@@ -4455,6 +5186,10 @@ void mgmt_connectable(struct hci_dev *hdev, u8 connectable)
 	if (mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev))
 		return;
 
+	/* Powering off may clear the scan mode - don't let that interfere */
+	if (!connectable && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev))
+		return;
+
 	if (connectable)
 		changed = !test_and_set_bit(HCI_CONNECTABLE, &hdev->dev_flags);
 	else
@@ -4464,6 +5199,18 @@ void mgmt_connectable(struct hci_dev *hdev, u8 connectable)
 		new_settings(hdev, NULL);
 }
 
+void mgmt_advertising(struct hci_dev *hdev, u8 advertising)
+{
+	/* Powering off may stop advertising - don't let that interfere */
+	if (!advertising && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev))
+		return;
+
+	if (advertising)
+		set_bit(HCI_ADVERTISING, &hdev->dev_flags);
+	else
+		clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
+}
+
 void mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status)
 {
 	u8 mgmt_err = mgmt_status(status);
@@ -4494,28 +5241,112 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 	mgmt_event(MGMT_EV_NEW_LINK_KEY, hdev, &ev, sizeof(ev), NULL);
 }
 
-void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent)
+static u8 mgmt_ltk_type(struct smp_ltk *ltk)
+{
+	if (ltk->authenticated)
+		return MGMT_LTK_AUTHENTICATED;
+
+	return MGMT_LTK_UNAUTHENTICATED;
+}
+
+void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent)
 {
 	struct mgmt_ev_new_long_term_key ev;
 
 	memset(&ev, 0, sizeof(ev));
 
-	ev.store_hint = persistent;
+	/* Devices using resolvable or non-resolvable random addresses
+	 * without providing an indentity resolving key don't require
+	 * to store long term keys. Their addresses will change the
+	 * next time around.
+	 *
+	 * Only when a remote device provides an identity address
+	 * make sure the long term key is stored. If the remote
+	 * identity is known, the long term keys are internally
+	 * mapped to the identity address. So allow static random
+	 * and public addresses here.
+	 */
+	if (key->bdaddr_type == ADDR_LE_DEV_RANDOM &&
+	    (key->bdaddr.b[5] & 0xc0) != 0xc0)
+		ev.store_hint = 0x00;
+	else
+		ev.store_hint = persistent;
+
 	bacpy(&ev.key.addr.bdaddr, &key->bdaddr);
 	ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type);
-	ev.key.authenticated = key->authenticated;
+	ev.key.type = mgmt_ltk_type(key);
 	ev.key.enc_size = key->enc_size;
 	ev.key.ediv = key->ediv;
+	ev.key.rand = key->rand;
 
 	if (key->type == HCI_SMP_LTK)
 		ev.key.master = 1;
 
-	memcpy(ev.key.rand, key->rand, sizeof(key->rand));
 	memcpy(ev.key.val, key->val, sizeof(key->val));
 
 	mgmt_event(MGMT_EV_NEW_LONG_TERM_KEY, hdev, &ev, sizeof(ev), NULL);
 }
 
+void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk)
+{
+	struct mgmt_ev_new_irk ev;
+
+	memset(&ev, 0, sizeof(ev));
+
+	/* For identity resolving keys from devices that are already
+	 * using a public address or static random address, do not
+	 * ask for storing this key. The identity resolving key really
+	 * is only mandatory for devices using resovlable random
+	 * addresses.
+	 *
+	 * Storing all identity resolving keys has the downside that
+	 * they will be also loaded on next boot of they system. More
+	 * identity resolving keys, means more time during scanning is
+	 * needed to actually resolve these addresses.
+	 */
+	if (bacmp(&irk->rpa, BDADDR_ANY))
+		ev.store_hint = 0x01;
+	else
+		ev.store_hint = 0x00;
+
+	bacpy(&ev.rpa, &irk->rpa);
+	bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr);
+	ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type);
+	memcpy(ev.irk.val, irk->val, sizeof(irk->val));
+
+	mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL);
+}
+
+void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk,
+		   bool persistent)
+{
+	struct mgmt_ev_new_csrk ev;
+
+	memset(&ev, 0, sizeof(ev));
+
+	/* Devices using resolvable or non-resolvable random addresses
+	 * without providing an indentity resolving key don't require
+	 * to store signature resolving keys. Their addresses will change
+	 * the next time around.
+	 *
+	 * Only when a remote device provides an identity address
+	 * make sure the signature resolving key is stored. So allow
+	 * static random and public addresses here.
+	 */
+	if (csrk->bdaddr_type == ADDR_LE_DEV_RANDOM &&
+	    (csrk->bdaddr.b[5] & 0xc0) != 0xc0)
+		ev.store_hint = 0x00;
+	else
+		ev.store_hint = persistent;
+
+	bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr);
+	ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type);
+	ev.key.master = csrk->master;
+	memcpy(ev.key.val, csrk->val, sizeof(csrk->val));
+
+	mgmt_event(MGMT_EV_NEW_CSRK, hdev, &ev, sizeof(ev), NULL);
+}
+
 static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data,
 				  u8 data_len)
 {
@@ -4590,11 +5421,32 @@ static void unpair_device_rsp(struct pending_cmd *cmd, void *data)
 }
 
 void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			      u8 link_type, u8 addr_type, u8 reason)
+			      u8 link_type, u8 addr_type, u8 reason,
+			      bool mgmt_connected)
 {
 	struct mgmt_ev_device_disconnected ev;
+	struct pending_cmd *power_off;
 	struct sock *sk = NULL;
 
+	power_off = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev);
+	if (power_off) {
+		struct mgmt_mode *cp = power_off->param;
+
+		/* The connection is still in hci_conn_hash so test for 1
+		 * instead of 0 to know if this is the last one.
+		 */
+		if (!cp->val && hci_conn_count(hdev) == 1) {
+			cancel_delayed_work(&hdev->power_off);
+			queue_work(hdev->req_workqueue, &hdev->power_off.work);
+		}
+	}
+
+	if (!mgmt_connected)
+		return;
+
+	if (link_type != ACL_LINK && link_type != LE_LINK)
+		return;
+
 	mgmt_pending_foreach(MGMT_OP_DISCONNECT, hdev, disconnect_rsp, &sk);
 
 	bacpy(&ev.addr.bdaddr, bdaddr);
@@ -4613,6 +5465,8 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			    u8 link_type, u8 addr_type, u8 status)
 {
+	u8 bdaddr_type = link_to_bdaddr(link_type, addr_type);
+	struct mgmt_cp_disconnect *cp;
 	struct mgmt_rp_disconnect rp;
 	struct pending_cmd *cmd;
 
@@ -4623,8 +5477,16 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	if (!cmd)
 		return;
 
+	cp = cmd->param;
+
+	if (bacmp(bdaddr, &cp->addr.bdaddr))
+		return;
+
+	if (cp->addr.type != bdaddr_type)
+		return;
+
 	bacpy(&rp.addr.bdaddr, bdaddr);
-	rp.addr.type = link_to_bdaddr(link_type, addr_type);
+	rp.addr.type = bdaddr_type;
 
 	cmd_complete(cmd->sk, cmd->index, MGMT_OP_DISCONNECT,
 		     mgmt_status(status), &rp, sizeof(rp));
@@ -4636,6 +5498,20 @@ void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			 u8 addr_type, u8 status)
 {
 	struct mgmt_ev_connect_failed ev;
+	struct pending_cmd *power_off;
+
+	power_off = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev);
+	if (power_off) {
+		struct mgmt_mode *cp = power_off->param;
+
+		/* The connection is still in hci_conn_hash so test for 1
+		 * instead of 0 to know if this is the last one.
+		 */
+		if (!cp->val && hci_conn_count(hdev) == 1) {
+			cancel_delayed_work(&hdev->power_off);
+			queue_work(hdev->req_workqueue, &hdev->power_off.work);
+		}
+	}
 
 	bacpy(&ev.addr.bdaddr, bdaddr);
 	ev.addr.type = link_to_bdaddr(link_type, addr_type);
@@ -4694,7 +5570,7 @@ void mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 }
 
 int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			      u8 link_type, u8 addr_type, __le32 value,
+			      u8 link_type, u8 addr_type, u32 value,
 			      u8 confirm_hint)
 {
 	struct mgmt_ev_user_confirm_request ev;
@@ -4704,7 +5580,7 @@ int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	bacpy(&ev.addr.bdaddr, bdaddr);
 	ev.addr.type = link_to_bdaddr(link_type, addr_type);
 	ev.confirm_hint = confirm_hint;
-	ev.value = value;
+	ev.value = cpu_to_le32(value);
 
 	return mgmt_event(MGMT_EV_USER_CONFIRM_REQUEST, hdev, &ev, sizeof(ev),
 			  NULL);
@@ -4897,6 +5773,43 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
 	hci_req_run(&req, NULL);
 }
 
+void mgmt_sc_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
+{
+	struct cmd_lookup match = { NULL, hdev };
+	bool changed = false;
+
+	if (status) {
+		u8 mgmt_err = mgmt_status(status);
+
+		if (enable) {
+			if (test_and_clear_bit(HCI_SC_ENABLED,
+					       &hdev->dev_flags))
+				new_settings(hdev, NULL);
+			clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
+		}
+
+		mgmt_pending_foreach(MGMT_OP_SET_SECURE_CONN, hdev,
+				     cmd_status_rsp, &mgmt_err);
+		return;
+	}
+
+	if (enable) {
+		changed = !test_and_set_bit(HCI_SC_ENABLED, &hdev->dev_flags);
+	} else {
+		changed = test_and_clear_bit(HCI_SC_ENABLED, &hdev->dev_flags);
+		clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
+	}
+
+	mgmt_pending_foreach(MGMT_OP_SET_SECURE_CONN, hdev,
+			     settings_rsp, &match);
+
+	if (changed)
+		new_settings(hdev, match.sk);
+
+	if (match.sk)
+		sock_put(match.sk);
+}
+
 static void sk_lookup(struct pending_cmd *cmd, void *data)
 {
 	struct cmd_lookup *match = data;
@@ -4951,8 +5864,9 @@ void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status)
 		   cmd ? cmd->sk : NULL);
 }
 
-void mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
-					     u8 *randomizer, u8 status)
+void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192,
+				       u8 *randomizer192, u8 *hash256,
+				       u8 *randomizer256, u8 status)
 {
 	struct pending_cmd *cmd;
 
@@ -4966,42 +5880,72 @@ void mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
 		cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
 			   mgmt_status(status));
 	} else {
-		struct mgmt_rp_read_local_oob_data rp;
+		if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags) &&
+		    hash256 && randomizer256) {
+			struct mgmt_rp_read_local_oob_ext_data rp;
+
+			memcpy(rp.hash192, hash192, sizeof(rp.hash192));
+			memcpy(rp.randomizer192, randomizer192,
+			       sizeof(rp.randomizer192));
 
-		memcpy(rp.hash, hash, sizeof(rp.hash));
-		memcpy(rp.randomizer, randomizer, sizeof(rp.randomizer));
+			memcpy(rp.hash256, hash256, sizeof(rp.hash256));
+			memcpy(rp.randomizer256, randomizer256,
+			       sizeof(rp.randomizer256));
+
+			cmd_complete(cmd->sk, hdev->id,
+				     MGMT_OP_READ_LOCAL_OOB_DATA, 0,
+				     &rp, sizeof(rp));
+		} else {
+			struct mgmt_rp_read_local_oob_data rp;
 
-		cmd_complete(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
-			     0, &rp, sizeof(rp));
+			memcpy(rp.hash, hash192, sizeof(rp.hash));
+			memcpy(rp.randomizer, randomizer192,
+			       sizeof(rp.randomizer));
+
+			cmd_complete(cmd->sk, hdev->id,
+				     MGMT_OP_READ_LOCAL_OOB_DATA, 0,
+				     &rp, sizeof(rp));
+		}
 	}
 
 	mgmt_pending_remove(cmd);
 }
 
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-		       u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name, u8
-		       ssp, u8 *eir, u16 eir_len)
+		       u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name,
+		       u8 ssp, u8 *eir, u16 eir_len, u8 *scan_rsp,
+		       u8 scan_rsp_len)
 {
 	char buf[512];
 	struct mgmt_ev_device_found *ev = (void *) buf;
+	struct smp_irk *irk;
 	size_t ev_size;
 
 	if (!hci_discovery_active(hdev))
 		return;
 
-	/* Leave 5 bytes for a potential CoD field */
-	if (sizeof(*ev) + eir_len + 5 > sizeof(buf))
+	/* Make sure that the buffer is big enough. The 5 extra bytes
+	 * are for the potential CoD field.
+	 */
+	if (sizeof(*ev) + eir_len + scan_rsp_len + 5 > sizeof(buf))
 		return;
 
 	memset(buf, 0, sizeof(buf));
 
-	bacpy(&ev->addr.bdaddr, bdaddr);
-	ev->addr.type = link_to_bdaddr(link_type, addr_type);
+	irk = hci_get_irk(hdev, bdaddr, addr_type);
+	if (irk) {
+		bacpy(&ev->addr.bdaddr, &irk->bdaddr);
+		ev->addr.type = link_to_bdaddr(link_type, irk->addr_type);
+	} else {
+		bacpy(&ev->addr.bdaddr, bdaddr);
+		ev->addr.type = link_to_bdaddr(link_type, addr_type);
+	}
+
 	ev->rssi = rssi;
 	if (cfm_name)
-		ev->flags |= __constant_cpu_to_le32(MGMT_DEV_FOUND_CONFIRM_NAME);
+		ev->flags |= cpu_to_le32(MGMT_DEV_FOUND_CONFIRM_NAME);
 	if (!ssp)
-		ev->flags |= __constant_cpu_to_le32(MGMT_DEV_FOUND_LEGACY_PAIRING);
+		ev->flags |= cpu_to_le32(MGMT_DEV_FOUND_LEGACY_PAIRING);
 
 	if (eir_len > 0)
 		memcpy(ev->eir, eir, eir_len);
@@ -5010,8 +5954,11 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		eir_len = eir_append_data(ev->eir, eir_len, EIR_CLASS_OF_DEV,
 					  dev_class, 3);
 
-	ev->eir_len = cpu_to_le16(eir_len);
-	ev_size = sizeof(*ev) + eir_len;
+	if (scan_rsp_len > 0)
+		memcpy(ev->eir + eir_len, scan_rsp, scan_rsp_len);
+
+	ev->eir_len = cpu_to_le16(eir_len + scan_rsp_len);
+	ev_size = sizeof(*ev) + eir_len + scan_rsp_len;
 
 	mgmt_event(MGMT_EV_DEVICE_FOUND, hdev, ev, ev_size, NULL);
 }
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index facd8a79c03..754b6fe4f74 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -186,9 +186,9 @@ static void rfcomm_l2state_change(struct sock *sk)
 	rfcomm_schedule();
 }
 
-static void rfcomm_l2data_ready(struct sock *sk, int bytes)
+static void rfcomm_l2data_ready(struct sock *sk)
 {
-	BT_DBG("%p bytes %d", sk, bytes);
+	BT_DBG("%p", sk);
 	rfcomm_schedule();
 }
 
@@ -216,6 +216,7 @@ static int rfcomm_check_security(struct rfcomm_dlc *d)
 
 	switch (d->sec_level) {
 	case BT_SECURITY_HIGH:
+	case BT_SECURITY_FIPS:
 		auth_type = HCI_AT_GENERAL_BONDING_MITM;
 		break;
 	case BT_SECURITY_MEDIUM:
@@ -306,7 +307,7 @@ struct rfcomm_dlc *rfcomm_dlc_alloc(gfp_t prio)
 	setup_timer(&d->timer, rfcomm_dlc_timeout, (unsigned long)d);
 
 	skb_queue_head_init(&d->tx_queue);
-	spin_lock_init(&d->lock);
+	mutex_init(&d->lock);
 	atomic_set(&d->refcnt, 1);
 
 	rfcomm_dlc_clear_state(d);
@@ -359,6 +360,11 @@ static struct rfcomm_dlc *rfcomm_dlc_get(struct rfcomm_session *s, u8 dlci)
 	return NULL;
 }
 
+static int rfcomm_check_channel(u8 channel)
+{
+	return channel < 1 || channel > 30;
+}
+
 static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 channel)
 {
 	struct rfcomm_session *s;
@@ -368,7 +374,7 @@ static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst,
 	BT_DBG("dlc %p state %ld %pMR -> %pMR channel %d",
 	       d, d->state, src, dst, channel);
 
-	if (channel < 1 || channel > 30)
+	if (rfcomm_check_channel(channel))
 		return -EINVAL;
 
 	if (d->state != BT_OPEN && d->state != BT_CLOSED)
@@ -425,6 +431,20 @@ int rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 chann
 	return r;
 }
 
+static void __rfcomm_dlc_disconn(struct rfcomm_dlc *d)
+{
+	struct rfcomm_session *s = d->session;
+
+	d->state = BT_DISCONN;
+	if (skb_queue_empty(&d->tx_queue)) {
+		rfcomm_send_disc(s, d->dlci);
+		rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT);
+	} else {
+		rfcomm_queue_disc(d);
+		rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT * 2);
+	}
+}
+
 static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err)
 {
 	struct rfcomm_session *s = d->session;
@@ -437,32 +457,29 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err)
 	switch (d->state) {
 	case BT_CONNECT:
 	case BT_CONFIG:
+	case BT_OPEN:
+	case BT_CONNECT2:
 		if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
 			set_bit(RFCOMM_AUTH_REJECT, &d->flags);
 			rfcomm_schedule();
-			break;
+			return 0;
 		}
-		/* Fall through */
+	}
 
+	switch (d->state) {
+	case BT_CONNECT:
 	case BT_CONNECTED:
-		d->state = BT_DISCONN;
-		if (skb_queue_empty(&d->tx_queue)) {
-			rfcomm_send_disc(s, d->dlci);
-			rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT);
-		} else {
-			rfcomm_queue_disc(d);
-			rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT * 2);
-		}
+		__rfcomm_dlc_disconn(d);
 		break;
 
-	case BT_OPEN:
-	case BT_CONNECT2:
-		if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
-			set_bit(RFCOMM_AUTH_REJECT, &d->flags);
-			rfcomm_schedule();
+	case BT_CONFIG:
+		if (s->state != BT_BOUND) {
+			__rfcomm_dlc_disconn(d);
 			break;
 		}
-		/* Fall through */
+		/* if closing a dlc in a session that hasn't been started,
+		 * just close and unlink the dlc
+		 */
 
 	default:
 		rfcomm_dlc_clear_timer(d);
@@ -513,6 +530,25 @@ no_session:
 	return r;
 }
 
+struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel)
+{
+	struct rfcomm_session *s;
+	struct rfcomm_dlc *dlc = NULL;
+	u8 dlci;
+
+	if (rfcomm_check_channel(channel))
+		return ERR_PTR(-EINVAL);
+
+	rfcomm_lock();
+	s = rfcomm_session_get(src, dst);
+	if (s) {
+		dlci = __dlci(!s->initiator, channel);
+		dlc = rfcomm_dlc_get(s, dlci);
+	}
+	rfcomm_unlock();
+	return dlc;
+}
+
 int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb)
 {
 	int len = skb->len;
@@ -533,6 +569,20 @@ int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb)
 	return len;
 }
 
+void rfcomm_dlc_send_noerror(struct rfcomm_dlc *d, struct sk_buff *skb)
+{
+	int len = skb->len;
+
+	BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len);
+
+	rfcomm_make_uih(skb, d->addr);
+	skb_queue_tail(&d->tx_queue, skb);
+
+	if (d->state == BT_CONNECTED &&
+	    !test_bit(RFCOMM_TX_THROTTLED, &d->flags))
+		rfcomm_schedule();
+}
+
 void __rfcomm_dlc_throttle(struct rfcomm_dlc *d)
 {
 	BT_DBG("dlc %p state %ld", d, d->state);
@@ -718,7 +768,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src,
 
 	bacpy(&addr.l2_bdaddr, dst);
 	addr.l2_family = AF_BLUETOOTH;
-	addr.l2_psm    = __constant_cpu_to_le16(RFCOMM_PSM);
+	addr.l2_psm    = cpu_to_le16(RFCOMM_PSM);
 	addr.l2_cid    = 0;
 	addr.l2_bdaddr_type = BDADDR_BREDR;
 	*err = kernel_connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK);
@@ -1943,12 +1993,11 @@ static void rfcomm_process_sessions(void)
 			continue;
 		}
 
-		if (s->state == BT_LISTEN) {
+		switch (s->state) {
+		case BT_LISTEN:
 			rfcomm_accept_connection(s);
 			continue;
-		}
 
-		switch (s->state) {
 		case BT_BOUND:
 			s = rfcomm_check_connection(s);
 			break;
@@ -1983,7 +2032,7 @@ static int rfcomm_add_listener(bdaddr_t *ba)
 	/* Bind socket */
 	bacpy(&addr.l2_bdaddr, ba);
 	addr.l2_family = AF_BLUETOOTH;
-	addr.l2_psm    = __constant_cpu_to_le16(RFCOMM_PSM);
+	addr.l2_psm    = cpu_to_le16(RFCOMM_PSM);
 	addr.l2_cid    = 0;
 	addr.l2_bdaddr_type = BDADDR_BREDR;
 	err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr));
@@ -2085,7 +2134,8 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt)
 				set_bit(RFCOMM_SEC_PENDING, &d->flags);
 				rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT);
 				continue;
-			} else if (d->sec_level == BT_SECURITY_HIGH) {
+			} else if (d->sec_level == BT_SECURITY_HIGH ||
+				   d->sec_level == BT_SECURITY_FIPS) {
 				set_bit(RFCOMM_ENC_DROP, &d->flags);
 				continue;
 			}
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 3c2d3e4aa2f..c603a5eb472 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -54,7 +54,7 @@ static void rfcomm_sk_data_ready(struct rfcomm_dlc *d, struct sk_buff *skb)
 
 	atomic_add(skb->len, &sk->sk_rmem_alloc);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 
 	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		rfcomm_dlc_throttle(d);
@@ -84,7 +84,7 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err)
 			sock_set_flag(sk, SOCK_ZAPPED);
 			bt_accept_unlink(sk);
 		}
-		parent->sk_data_ready(parent, 0);
+		parent->sk_data_ready(parent);
 	} else {
 		if (d->state == BT_CONNECTED)
 			rfcomm_session_getaddr(d->session,
@@ -105,13 +105,18 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err)
 }
 
 /* ---- Socket functions ---- */
-static struct sock *__rfcomm_get_sock_by_addr(u8 channel, bdaddr_t *src)
+static struct sock *__rfcomm_get_listen_sock_by_addr(u8 channel, bdaddr_t *src)
 {
 	struct sock *sk = NULL;
 
 	sk_for_each(sk, &rfcomm_sk_list.head) {
-		if (rfcomm_pi(sk)->channel == channel &&
-				!bacmp(&rfcomm_pi(sk)->src, src))
+		if (rfcomm_pi(sk)->channel != channel)
+			continue;
+
+		if (bacmp(&rfcomm_pi(sk)->src, src))
+			continue;
+
+		if (sk->sk_state == BT_BOUND || sk->sk_state == BT_LISTEN)
 			break;
 	}
 
@@ -331,6 +336,7 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr
 {
 	struct sockaddr_rc *sa = (struct sockaddr_rc *) addr;
 	struct sock *sk = sock->sk;
+	int chan = sa->rc_channel;
 	int err = 0;
 
 	BT_DBG("sk %p %pMR", sk, &sa->rc_bdaddr);
@@ -352,12 +358,12 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr
 
 	write_lock(&rfcomm_sk_list.lock);
 
-	if (sa->rc_channel && __rfcomm_get_sock_by_addr(sa->rc_channel, &sa->rc_bdaddr)) {
+	if (chan && __rfcomm_get_listen_sock_by_addr(chan, &sa->rc_bdaddr)) {
 		err = -EADDRINUSE;
 	} else {
 		/* Save source address */
 		bacpy(&rfcomm_pi(sk)->src, &sa->rc_bdaddr);
-		rfcomm_pi(sk)->channel = sa->rc_channel;
+		rfcomm_pi(sk)->channel = chan;
 		sk->sk_state = BT_BOUND;
 	}
 
@@ -439,7 +445,7 @@ static int rfcomm_sock_listen(struct socket *sock, int backlog)
 		write_lock(&rfcomm_sk_list.lock);
 
 		for (channel = 1; channel < 31; channel++)
-			if (!__rfcomm_get_sock_by_addr(channel, src)) {
+			if (!__rfcomm_get_listen_sock_by_addr(channel, src)) {
 				rfcomm_pi(sk)->channel = channel;
 				err = 0;
 				break;
@@ -528,6 +534,10 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int *
 
 	BT_DBG("sock %p, sk %p", sock, sk);
 
+	if (peer && sk->sk_state != BT_CONNECTED &&
+	    sk->sk_state != BT_CONNECT && sk->sk_state != BT_CONNECT2)
+		return -ENOTCONN;
+
 	memset(sa, 0, sizeof(*sa));
 	sa->rc_family  = AF_BLUETOOTH;
 	sa->rc_channel = rfcomm_pi(sk)->channel;
@@ -648,6 +658,11 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __u
 			break;
 		}
 
+		if (opt & RFCOMM_LM_FIPS) {
+			err = -EINVAL;
+			break;
+		}
+
 		if (opt & RFCOMM_LM_AUTH)
 			rfcomm_pi(sk)->sec_level = BT_SECURITY_LOW;
 		if (opt & RFCOMM_LM_ENCRYPT)
@@ -762,7 +777,11 @@ static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __u
 			break;
 		case BT_SECURITY_HIGH:
 			opt = RFCOMM_LM_AUTH | RFCOMM_LM_ENCRYPT |
-							RFCOMM_LM_SECURE;
+			      RFCOMM_LM_SECURE;
+			break;
+		case BT_SECURITY_FIPS:
+			opt = RFCOMM_LM_AUTH | RFCOMM_LM_ENCRYPT |
+			      RFCOMM_LM_SECURE | RFCOMM_LM_FIPS;
 			break;
 		default:
 			opt = 0;
@@ -774,6 +793,7 @@ static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __u
 
 		if (put_user(opt, (u32 __user *) optval))
 			err = -EFAULT;
+
 		break;
 
 	case RFCOMM_CONNINFO:
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index 84fcf9fff3e..8e385a0ae60 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -40,6 +40,7 @@
 #define RFCOMM_TTY_MAJOR 216		/* device node major id of the usb/bluetooth.c driver */
 #define RFCOMM_TTY_MINOR 0
 
+static DEFINE_MUTEX(rfcomm_ioctl_mutex);
 static struct tty_driver *rfcomm_tty_driver;
 
 struct rfcomm_dev {
@@ -51,6 +52,8 @@ struct rfcomm_dev {
 	unsigned long		flags;
 	int			err;
 
+	unsigned long		status;		/* don't export to userspace */
+
 	bdaddr_t		src;
 	bdaddr_t		dst;
 	u8			channel;
@@ -67,7 +70,7 @@ struct rfcomm_dev {
 };
 
 static LIST_HEAD(rfcomm_dev_list);
-static DEFINE_SPINLOCK(rfcomm_dev_lock);
+static DEFINE_MUTEX(rfcomm_dev_lock);
 
 static void rfcomm_dev_data_ready(struct rfcomm_dlc *dlc, struct sk_buff *skb);
 static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err);
@@ -82,10 +85,6 @@ static void rfcomm_dev_destruct(struct tty_port *port)
 
 	BT_DBG("dev %p dlc %p", dev, dlc);
 
-	spin_lock(&rfcomm_dev_lock);
-	list_del(&dev->list);
-	spin_unlock(&rfcomm_dev_lock);
-
 	rfcomm_dlc_lock(dlc);
 	/* Detach DLC if it's owned by this dev */
 	if (dlc->owner == dev)
@@ -94,7 +93,12 @@ static void rfcomm_dev_destruct(struct tty_port *port)
 
 	rfcomm_dlc_put(dlc);
 
-	tty_unregister_device(rfcomm_tty_driver, dev->id);
+	if (dev->tty_dev)
+		tty_unregister_device(rfcomm_tty_driver, dev->id);
+
+	mutex_lock(&rfcomm_dev_lock);
+	list_del(&dev->list);
+	mutex_unlock(&rfcomm_dev_lock);
 
 	kfree(dev);
 
@@ -107,8 +111,12 @@ static void rfcomm_dev_destruct(struct tty_port *port)
 static int rfcomm_dev_activate(struct tty_port *port, struct tty_struct *tty)
 {
 	struct rfcomm_dev *dev = container_of(port, struct rfcomm_dev, port);
+	int err;
 
-	return rfcomm_dlc_open(dev->dlc, &dev->src, &dev->dst, dev->channel);
+	err = rfcomm_dlc_open(dev->dlc, &dev->src, &dev->dst, dev->channel);
+	if (err)
+		set_bit(TTY_IO_ERROR, &tty->flags);
+	return err;
 }
 
 /* we block the open until the dlc->state becomes BT_CONNECTED */
@@ -138,7 +146,7 @@ static const struct tty_port_operations rfcomm_port_ops = {
 	.carrier_raised = rfcomm_dev_carrier_raised,
 };
 
-static struct rfcomm_dev *__rfcomm_dev_get(int id)
+static struct rfcomm_dev *__rfcomm_dev_lookup(int id)
 {
 	struct rfcomm_dev *dev;
 
@@ -153,36 +161,41 @@ static struct rfcomm_dev *rfcomm_dev_get(int id)
 {
 	struct rfcomm_dev *dev;
 
-	spin_lock(&rfcomm_dev_lock);
+	mutex_lock(&rfcomm_dev_lock);
 
-	dev = __rfcomm_dev_get(id);
+	dev = __rfcomm_dev_lookup(id);
 
-	if (dev) {
-		if (test_bit(RFCOMM_TTY_RELEASED, &dev->flags))
-			dev = NULL;
-		else
-			tty_port_get(&dev->port);
-	}
+	if (dev && !tty_port_get(&dev->port))
+		dev = NULL;
 
-	spin_unlock(&rfcomm_dev_lock);
+	mutex_unlock(&rfcomm_dev_lock);
 
 	return dev;
 }
 
-static struct device *rfcomm_get_device(struct rfcomm_dev *dev)
+static void rfcomm_reparent_device(struct rfcomm_dev *dev)
 {
 	struct hci_dev *hdev;
 	struct hci_conn *conn;
 
 	hdev = hci_get_route(&dev->dst, &dev->src);
 	if (!hdev)
-		return NULL;
+		return;
 
+	/* The lookup results are unsafe to access without the
+	 * hci device lock (FIXME: why is this not documented?)
+	 */
+	hci_dev_lock(hdev);
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &dev->dst);
 
-	hci_dev_put(hdev);
+	/* Just because the acl link is in the hash table is no
+	 * guarantee the sysfs device has been added ...
+	 */
+	if (conn && device_is_registered(&conn->dev))
+		device_move(dev->tty_dev, &conn->dev, DPM_ORDER_DEV_AFTER_PARENT);
 
-	return conn ? &conn->dev : NULL;
+	hci_dev_unlock(hdev);
+	hci_dev_put(hdev);
 }
 
 static ssize_t show_address(struct device *tty_dev, struct device_attribute *attr, char *buf)
@@ -200,19 +213,18 @@ static ssize_t show_channel(struct device *tty_dev, struct device_attribute *att
 static DEVICE_ATTR(address, S_IRUGO, show_address, NULL);
 static DEVICE_ATTR(channel, S_IRUGO, show_channel, NULL);
 
-static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc)
+static struct rfcomm_dev *__rfcomm_dev_add(struct rfcomm_dev_req *req,
+					   struct rfcomm_dlc *dlc)
 {
 	struct rfcomm_dev *dev, *entry;
 	struct list_head *head = &rfcomm_dev_list;
 	int err = 0;
 
-	BT_DBG("id %d channel %d", req->dev_id, req->channel);
-
 	dev = kzalloc(sizeof(struct rfcomm_dev), GFP_KERNEL);
 	if (!dev)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
-	spin_lock(&rfcomm_dev_lock);
+	mutex_lock(&rfcomm_dev_lock);
 
 	if (req->dev_id < 0) {
 		dev->id = 0;
@@ -293,22 +305,37 @@ static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc)
 	   holds reference to this module. */
 	__module_get(THIS_MODULE);
 
+	mutex_unlock(&rfcomm_dev_lock);
+	return dev;
+
 out:
-	spin_unlock(&rfcomm_dev_lock);
+	mutex_unlock(&rfcomm_dev_lock);
+	kfree(dev);
+	return ERR_PTR(err);
+}
+
+static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc)
+{
+	struct rfcomm_dev *dev;
+	struct device *tty;
+
+	BT_DBG("id %d channel %d", req->dev_id, req->channel);
 
-	if (err < 0)
-		goto free;
+	dev = __rfcomm_dev_add(req, dlc);
+	if (IS_ERR(dev)) {
+		rfcomm_dlc_put(dlc);
+		return PTR_ERR(dev);
+	}
 
-	dev->tty_dev = tty_port_register_device(&dev->port, rfcomm_tty_driver,
+	tty = tty_port_register_device(&dev->port, rfcomm_tty_driver,
 			dev->id, NULL);
-	if (IS_ERR(dev->tty_dev)) {
-		err = PTR_ERR(dev->tty_dev);
-		spin_lock(&rfcomm_dev_lock);
-		list_del(&dev->list);
-		spin_unlock(&rfcomm_dev_lock);
-		goto free;
+	if (IS_ERR(tty)) {
+		tty_port_put(&dev->port);
+		return PTR_ERR(tty);
 	}
 
+	dev->tty_dev = tty;
+	rfcomm_reparent_device(dev);
 	dev_set_drvdata(dev->tty_dev, dev);
 
 	if (device_create_file(dev->tty_dev, &dev_attr_address) < 0)
@@ -318,24 +345,23 @@ out:
 		BT_ERR("Failed to create channel attribute");
 
 	return dev->id;
-
-free:
-	kfree(dev);
-	return err;
 }
 
 /* ---- Send buffer ---- */
-static inline unsigned int rfcomm_room(struct rfcomm_dlc *dlc)
+static inline unsigned int rfcomm_room(struct rfcomm_dev *dev)
 {
-	/* We can't let it be zero, because we don't get a callback
-	   when tx_credits becomes nonzero, hence we'd never wake up */
-	return dlc->mtu * (dlc->tx_credits?:1);
+	struct rfcomm_dlc *dlc = dev->dlc;
+
+	/* Limit the outstanding number of packets not yet sent to 40 */
+	int pending = 40 - atomic_read(&dev->wmem_alloc);
+
+	return max(0, pending) * dlc->mtu;
 }
 
 static void rfcomm_wfree(struct sk_buff *skb)
 {
 	struct rfcomm_dev *dev = (void *) skb->sk;
-	atomic_sub(skb->truesize, &dev->wmem_alloc);
+	atomic_dec(&dev->wmem_alloc);
 	if (test_bit(RFCOMM_TTY_ATTACHED, &dev->flags))
 		tty_port_tty_wakeup(&dev->port);
 	tty_port_put(&dev->port);
@@ -344,28 +370,24 @@ static void rfcomm_wfree(struct sk_buff *skb)
 static void rfcomm_set_owner_w(struct sk_buff *skb, struct rfcomm_dev *dev)
 {
 	tty_port_get(&dev->port);
-	atomic_add(skb->truesize, &dev->wmem_alloc);
+	atomic_inc(&dev->wmem_alloc);
 	skb->sk = (void *) dev;
 	skb->destructor = rfcomm_wfree;
 }
 
 static struct sk_buff *rfcomm_wmalloc(struct rfcomm_dev *dev, unsigned long size, gfp_t priority)
 {
-	if (atomic_read(&dev->wmem_alloc) < rfcomm_room(dev->dlc)) {
-		struct sk_buff *skb = alloc_skb(size, priority);
-		if (skb) {
-			rfcomm_set_owner_w(skb, dev);
-			return skb;
-		}
-	}
-	return NULL;
+	struct sk_buff *skb = alloc_skb(size, priority);
+	if (skb)
+		rfcomm_set_owner_w(skb, dev);
+	return skb;
 }
 
 /* ---- Device IOCTLs ---- */
 
 #define NOCAP_FLAGS ((1 << RFCOMM_REUSE_DLC) | (1 << RFCOMM_RELEASE_ONHUP))
 
-static int rfcomm_create_dev(struct sock *sk, void __user *arg)
+static int __rfcomm_create_dev(struct sock *sk, void __user *arg)
 {
 	struct rfcomm_dev_req req;
 	struct rfcomm_dlc *dlc;
@@ -387,16 +409,22 @@ static int rfcomm_create_dev(struct sock *sk, void __user *arg)
 		dlc = rfcomm_pi(sk)->dlc;
 		rfcomm_dlc_hold(dlc);
 	} else {
+		/* Validate the channel is unused */
+		dlc = rfcomm_dlc_exists(&req.src, &req.dst, req.channel);
+		if (IS_ERR(dlc))
+			return PTR_ERR(dlc);
+		else if (dlc) {
+			rfcomm_dlc_put(dlc);
+			return -EBUSY;
+		}
 		dlc = rfcomm_dlc_alloc(GFP_KERNEL);
 		if (!dlc)
 			return -ENOMEM;
 	}
 
 	id = rfcomm_dev_add(&req, dlc);
-	if (id < 0) {
-		rfcomm_dlc_put(dlc);
+	if (id < 0)
 		return id;
-	}
 
 	if (req.flags & (1 << RFCOMM_REUSE_DLC)) {
 		/* DLC is now used by device.
@@ -407,7 +435,7 @@ static int rfcomm_create_dev(struct sock *sk, void __user *arg)
 	return id;
 }
 
-static int rfcomm_release_dev(void __user *arg)
+static int __rfcomm_release_dev(void __user *arg)
 {
 	struct rfcomm_dev_req req;
 	struct rfcomm_dev *dev;
@@ -427,6 +455,12 @@ static int rfcomm_release_dev(void __user *arg)
 		return -EPERM;
 	}
 
+	/* only release once */
+	if (test_and_set_bit(RFCOMM_DEV_RELEASED, &dev->status)) {
+		tty_port_put(&dev->port);
+		return -EALREADY;
+	}
+
 	if (req.flags & (1 << RFCOMM_HANGUP_NOW))
 		rfcomm_dlc_close(dev->dlc, 0);
 
@@ -437,13 +471,35 @@ static int rfcomm_release_dev(void __user *arg)
 		tty_kref_put(tty);
 	}
 
-	if (!test_and_set_bit(RFCOMM_TTY_RELEASED, &dev->flags))
+	if (!test_bit(RFCOMM_TTY_OWNED, &dev->status))
 		tty_port_put(&dev->port);
 
 	tty_port_put(&dev->port);
 	return 0;
 }
 
+static int rfcomm_create_dev(struct sock *sk, void __user *arg)
+{
+	int ret;
+
+	mutex_lock(&rfcomm_ioctl_mutex);
+	ret = __rfcomm_create_dev(sk, arg);
+	mutex_unlock(&rfcomm_ioctl_mutex);
+
+	return ret;
+}
+
+static int rfcomm_release_dev(void __user *arg)
+{
+	int ret;
+
+	mutex_lock(&rfcomm_ioctl_mutex);
+	ret = __rfcomm_release_dev(arg);
+	mutex_unlock(&rfcomm_ioctl_mutex);
+
+	return ret;
+}
+
 static int rfcomm_get_dev_list(void __user *arg)
 {
 	struct rfcomm_dev *dev;
@@ -468,10 +524,10 @@ static int rfcomm_get_dev_list(void __user *arg)
 
 	di = dl->dev_info;
 
-	spin_lock(&rfcomm_dev_lock);
+	mutex_lock(&rfcomm_dev_lock);
 
 	list_for_each_entry(dev, &rfcomm_dev_list, list) {
-		if (test_bit(RFCOMM_TTY_RELEASED, &dev->flags))
+		if (!tty_port_get(&dev->port))
 			continue;
 		(di + n)->id      = dev->id;
 		(di + n)->flags   = dev->flags;
@@ -479,11 +535,12 @@ static int rfcomm_get_dev_list(void __user *arg)
 		(di + n)->channel = dev->channel;
 		bacpy(&(di + n)->src, &dev->src);
 		bacpy(&(di + n)->dst, &dev->dst);
+		tty_port_put(&dev->port);
 		if (++n >= dev_num)
 			break;
 	}
 
-	spin_unlock(&rfcomm_dev_lock);
+	mutex_unlock(&rfcomm_dev_lock);
 
 	dl->dev_num = n;
 	size = sizeof(*dl) + n * sizeof(*di);
@@ -576,8 +633,7 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err)
 
 	dev->err = err;
 	if (dlc->state == BT_CONNECTED) {
-		device_move(dev->tty_dev, rfcomm_get_device(dev),
-			    DPM_ORDER_DEV_AFTER_PARENT);
+		rfcomm_reparent_device(dev);
 
 		wake_up_interruptible(&dev->port.open_wait);
 	} else if (dlc->state == BT_CLOSED)
@@ -670,10 +726,22 @@ static int rfcomm_tty_install(struct tty_driver *driver, struct tty_struct *tty)
 
 	/* install the tty_port */
 	err = tty_port_install(&dev->port, driver, tty);
-	if (err)
+	if (err) {
 		rfcomm_tty_cleanup(tty);
+		return err;
+	}
 
-	return err;
+	/* take over the tty_port reference if the port was created with the
+	 * flag RFCOMM_RELEASE_ONHUP. This will force the release of the port
+	 * when the last process closes the tty. The behaviour is expected by
+	 * userspace.
+	 */
+	if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) {
+		set_bit(RFCOMM_TTY_OWNED, &dev->status);
+		tty_port_put(&dev->port);
+	}
+
+	return 0;
 }
 
 static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp)
@@ -717,7 +785,7 @@ static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, in
 	struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data;
 	struct rfcomm_dlc *dlc = dev->dlc;
 	struct sk_buff *skb;
-	int err = 0, sent = 0, size;
+	int sent = 0, size;
 
 	BT_DBG("tty %p count %d", tty, count);
 
@@ -725,7 +793,6 @@ static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, in
 		size = min_t(uint, count, dlc->mtu);
 
 		skb = rfcomm_wmalloc(dev, size + RFCOMM_SKB_RESERVE, GFP_ATOMIC);
-
 		if (!skb)
 			break;
 
@@ -733,32 +800,24 @@ static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, in
 
 		memcpy(skb_put(skb, size), buf + sent, size);
 
-		err = rfcomm_dlc_send(dlc, skb);
-		if (err < 0) {
-			kfree_skb(skb);
-			break;
-		}
+		rfcomm_dlc_send_noerror(dlc, skb);
 
 		sent  += size;
 		count -= size;
 	}
 
-	return sent ? sent : err;
+	return sent;
 }
 
 static int rfcomm_tty_write_room(struct tty_struct *tty)
 {
 	struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data;
-	int room;
+	int room = 0;
 
-	BT_DBG("tty %p", tty);
+	if (dev && dev->dlc)
+		room = rfcomm_room(dev);
 
-	if (!dev || !dev->dlc)
-		return 0;
-
-	room = rfcomm_room(dev->dlc) - atomic_read(&dev->wmem_alloc);
-	if (room < 0)
-		room = 0;
+	BT_DBG("tty %p room %d", tty, room);
 
 	return room;
 }
@@ -1010,10 +1069,6 @@ static void rfcomm_tty_hangup(struct tty_struct *tty)
 	BT_DBG("tty %p dev %p", tty, dev);
 
 	tty_port_hangup(&dev->port);
-
-	if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags) &&
-	    !test_and_set_bit(RFCOMM_TTY_RELEASED, &dev->flags))
-		tty_port_put(&dev->port);
 }
 
 static int rfcomm_tty_tiocmget(struct tty_struct *tty)
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 24fa3964b3c..c06dbd3938e 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -676,20 +676,20 @@ static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting)
 		bacpy(&cp.bdaddr, &conn->dst);
 		cp.pkt_type = cpu_to_le16(conn->pkt_type);
 
-		cp.tx_bandwidth   = __constant_cpu_to_le32(0x00001f40);
-		cp.rx_bandwidth   = __constant_cpu_to_le32(0x00001f40);
+		cp.tx_bandwidth   = cpu_to_le32(0x00001f40);
+		cp.rx_bandwidth   = cpu_to_le32(0x00001f40);
 		cp.content_format = cpu_to_le16(setting);
 
 		switch (setting & SCO_AIRMODE_MASK) {
 		case SCO_AIRMODE_TRANSP:
 			if (conn->pkt_type & ESCO_2EV3)
-				cp.max_latency = __constant_cpu_to_le16(0x0008);
+				cp.max_latency = cpu_to_le16(0x0008);
 			else
-				cp.max_latency = __constant_cpu_to_le16(0x000D);
+				cp.max_latency = cpu_to_le16(0x000D);
 			cp.retrans_effort = 0x02;
 			break;
 		case SCO_AIRMODE_CVSD:
-			cp.max_latency = __constant_cpu_to_le16(0xffff);
+			cp.max_latency = cpu_to_le16(0xffff);
 			cp.retrans_effort = 0xff;
 			break;
 		}
@@ -1024,7 +1024,7 @@ static void sco_conn_ready(struct sco_conn *conn)
 			sk->sk_state = BT_CONNECTED;
 
 		/* Wake up parent */
-		parent->sk_data_ready(parent, 1);
+		parent->sk_data_ready(parent);
 
 		bh_unlock_sock(parent);
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 4b07acb8293..e33a982161c 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -35,14 +35,41 @@
 
 #define AUTH_REQ_MASK   0x07
 
-static inline void swap128(u8 src[16], u8 dst[16])
+#define SMP_FLAG_TK_VALID	1
+#define SMP_FLAG_CFM_PENDING	2
+#define SMP_FLAG_MITM_AUTH	3
+#define SMP_FLAG_COMPLETE	4
+#define SMP_FLAG_INITIATOR	5
+
+struct smp_chan {
+	struct l2cap_conn *conn;
+	u8		preq[7]; /* SMP Pairing Request */
+	u8		prsp[7]; /* SMP Pairing Response */
+	u8		prnd[16]; /* SMP Pairing Random (local) */
+	u8		rrnd[16]; /* SMP Pairing Random (remote) */
+	u8		pcnf[16]; /* SMP Pairing Confirm */
+	u8		tk[16]; /* SMP Temporary Key */
+	u8		enc_key_size;
+	u8		remote_key_dist;
+	bdaddr_t	id_addr;
+	u8		id_addr_type;
+	u8		irk[16];
+	struct smp_csrk	*csrk;
+	struct smp_csrk	*slave_csrk;
+	struct smp_ltk	*ltk;
+	struct smp_ltk	*slave_ltk;
+	struct smp_irk	*remote_irk;
+	unsigned long	flags;
+};
+
+static inline void swap128(const u8 src[16], u8 dst[16])
 {
 	int i;
 	for (i = 0; i < 16; i++)
 		dst[15 - i] = src[i];
 }
 
-static inline void swap56(u8 src[7], u8 dst[7])
+static inline void swap56(const u8 src[7], u8 dst[7])
 {
 	int i;
 	for (i = 0; i < 7; i++)
@@ -53,8 +80,8 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
 {
 	struct blkcipher_desc desc;
 	struct scatterlist sg;
-	int err, iv_len;
-	unsigned char iv[128];
+	uint8_t tmp[16], data[16];
+	int err;
 
 	if (tfm == NULL) {
 		BT_ERR("tfm %p", tfm);
@@ -64,27 +91,89 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
 	desc.tfm = tfm;
 	desc.flags = 0;
 
-	err = crypto_blkcipher_setkey(tfm, k, 16);
+	/* The most significant octet of key corresponds to k[0] */
+	swap128(k, tmp);
+
+	err = crypto_blkcipher_setkey(tfm, tmp, 16);
 	if (err) {
 		BT_ERR("cipher setkey failed: %d", err);
 		return err;
 	}
 
-	sg_init_one(&sg, r, 16);
+	/* Most significant octet of plaintextData corresponds to data[0] */
+	swap128(r, data);
 
-	iv_len = crypto_blkcipher_ivsize(tfm);
-	if (iv_len) {
-		memset(&iv, 0xff, iv_len);
-		crypto_blkcipher_set_iv(tfm, iv, iv_len);
-	}
+	sg_init_one(&sg, data, 16);
 
 	err = crypto_blkcipher_encrypt(&desc, &sg, &sg, 16);
 	if (err)
 		BT_ERR("Encrypt data error %d", err);
 
+	/* Most significant octet of encryptedData corresponds to data[0] */
+	swap128(data, r);
+
 	return err;
 }
 
+static int smp_ah(struct crypto_blkcipher *tfm, u8 irk[16], u8 r[3], u8 res[3])
+{
+	u8 _res[16];
+	int err;
+
+	/* r' = padding || r */
+	memcpy(_res, r, 3);
+	memset(_res + 3, 0, 13);
+
+	err = smp_e(tfm, irk, _res);
+	if (err) {
+		BT_ERR("Encrypt error");
+		return err;
+	}
+
+	/* The output of the random address function ah is:
+	 *	ah(h, r) = e(k, r') mod 2^24
+	 * The output of the security function e is then truncated to 24 bits
+	 * by taking the least significant 24 bits of the output of e as the
+	 * result of ah.
+	 */
+	memcpy(res, _res, 3);
+
+	return 0;
+}
+
+bool smp_irk_matches(struct crypto_blkcipher *tfm, u8 irk[16],
+		     bdaddr_t *bdaddr)
+{
+	u8 hash[3];
+	int err;
+
+	BT_DBG("RPA %pMR IRK %*phN", bdaddr, 16, irk);
+
+	err = smp_ah(tfm, irk, &bdaddr->b[3], hash);
+	if (err)
+		return false;
+
+	return !memcmp(bdaddr->b, hash, 3);
+}
+
+int smp_generate_rpa(struct crypto_blkcipher *tfm, u8 irk[16], bdaddr_t *rpa)
+{
+	int err;
+
+	get_random_bytes(&rpa->b[3], 3);
+
+	rpa->b[5] &= 0x3f;	/* Clear two most significant bits */
+	rpa->b[5] |= 0x40;	/* Set second most significant bit */
+
+	err = smp_ah(tfm, irk, &rpa->b[3], rpa->b);
+	if (err < 0)
+		return err;
+
+	BT_DBG("RPA %pMR", rpa);
+
+	return 0;
+}
+
 static int smp_c1(struct crypto_blkcipher *tfm, u8 k[16], u8 r[16],
 		  u8 preq[7], u8 pres[7], u8 _iat, bdaddr_t *ia,
 		  u8 _rat, bdaddr_t *ra, u8 res[16])
@@ -95,16 +184,15 @@ static int smp_c1(struct crypto_blkcipher *tfm, u8 k[16], u8 r[16],
 	memset(p1, 0, 16);
 
 	/* p1 = pres || preq || _rat || _iat */
-	swap56(pres, p1);
-	swap56(preq, p1 + 7);
-	p1[14] = _rat;
-	p1[15] = _iat;
-
-	memset(p2, 0, 16);
+	p1[0] = _iat;
+	p1[1] = _rat;
+	memcpy(p1 + 2, preq, 7);
+	memcpy(p1 + 9, pres, 7);
 
 	/* p2 = padding || ia || ra */
-	baswap((bdaddr_t *) (p2 + 4), ia);
-	baswap((bdaddr_t *) (p2 + 10), ra);
+	memcpy(p2, ra, 6);
+	memcpy(p2 + 6, ia, 6);
+	memset(p2 + 12, 0, 4);
 
 	/* res = r XOR p1 */
 	u128_xor((u128 *) res, (u128 *) r, (u128 *) p1);
@@ -133,8 +221,8 @@ static int smp_s1(struct crypto_blkcipher *tfm, u8 k[16], u8 r1[16],
 	int err;
 
 	/* Just least significant octets from r1 and r2 are considered */
-	memcpy(_r, r1 + 8, 8);
-	memcpy(_r + 8, r2 + 8, 8);
+	memcpy(_r, r2, 8);
+	memcpy(_r + 8, r1, 8);
 
 	err = smp_e(tfm, k, _r);
 	if (err)
@@ -143,13 +231,6 @@ static int smp_s1(struct crypto_blkcipher *tfm, u8 k[16], u8 r1[16],
 	return err;
 }
 
-static int smp_rand(u8 *buf)
-{
-	get_random_bytes(buf, 16);
-
-	return 0;
-}
-
 static struct sk_buff *smp_build_cmd(struct l2cap_conn *conn, u8 code,
 				     u16 dlen, void *data)
 {
@@ -168,7 +249,7 @@ static struct sk_buff *smp_build_cmd(struct l2cap_conn *conn, u8 code,
 
 	lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE);
 	lh->len = cpu_to_le16(sizeof(code) + dlen);
-	lh->cid = __constant_cpu_to_le16(L2CAP_CID_SMP);
+	lh->cid = cpu_to_le16(L2CAP_CID_SMP);
 
 	memcpy(skb_put(skb, sizeof(code)), &code, sizeof(code));
 
@@ -217,31 +298,45 @@ static void build_pairing_cmd(struct l2cap_conn *conn,
 			      struct smp_cmd_pairing *req,
 			      struct smp_cmd_pairing *rsp, __u8 authreq)
 {
-	u8 dist_keys = 0;
+	struct smp_chan *smp = conn->smp_chan;
+	struct hci_conn *hcon = conn->hcon;
+	struct hci_dev *hdev = hcon->hdev;
+	u8 local_dist = 0, remote_dist = 0;
 
 	if (test_bit(HCI_PAIRABLE, &conn->hcon->hdev->dev_flags)) {
-		dist_keys = SMP_DIST_ENC_KEY;
+		local_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN;
+		remote_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN;
 		authreq |= SMP_AUTH_BONDING;
 	} else {
 		authreq &= ~SMP_AUTH_BONDING;
 	}
 
+	if (test_bit(HCI_RPA_RESOLVING, &hdev->dev_flags))
+		remote_dist |= SMP_DIST_ID_KEY;
+
+	if (test_bit(HCI_PRIVACY, &hdev->dev_flags))
+		local_dist |= SMP_DIST_ID_KEY;
+
 	if (rsp == NULL) {
 		req->io_capability = conn->hcon->io_capability;
 		req->oob_flag = SMP_OOB_NOT_PRESENT;
 		req->max_key_size = SMP_MAX_ENC_KEY_SIZE;
-		req->init_key_dist = 0;
-		req->resp_key_dist = dist_keys;
+		req->init_key_dist = local_dist;
+		req->resp_key_dist = remote_dist;
 		req->auth_req = (authreq & AUTH_REQ_MASK);
+
+		smp->remote_key_dist = remote_dist;
 		return;
 	}
 
 	rsp->io_capability = conn->hcon->io_capability;
 	rsp->oob_flag = SMP_OOB_NOT_PRESENT;
 	rsp->max_key_size = SMP_MAX_ENC_KEY_SIZE;
-	rsp->init_key_dist = 0;
-	rsp->resp_key_dist = req->resp_key_dist & dist_keys;
+	rsp->init_key_dist = req->init_key_dist & remote_dist;
+	rsp->resp_key_dist = req->resp_key_dist & local_dist;
 	rsp->auth_req = (authreq & AUTH_REQ_MASK);
+
+	smp->remote_key_dist = rsp->init_key_dist;
 }
 
 static u8 check_enc_key_size(struct l2cap_conn *conn, __u8 max_key_size)
@@ -257,11 +352,11 @@ static u8 check_enc_key_size(struct l2cap_conn *conn, __u8 max_key_size)
 	return 0;
 }
 
-static void smp_failure(struct l2cap_conn *conn, u8 reason, u8 send)
+static void smp_failure(struct l2cap_conn *conn, u8 reason)
 {
 	struct hci_conn *hcon = conn->hcon;
 
-	if (send)
+	if (reason)
 		smp_send_cmd(conn, SMP_CMD_PAIRING_FAIL, sizeof(reason),
 			     &reason);
 
@@ -290,6 +385,16 @@ static const u8 gen_method[5][5] = {
 	{ CFM_PASSKEY, CFM_PASSKEY, REQ_PASSKEY, JUST_WORKS, OVERLAP     },
 };
 
+static u8 get_auth_method(struct smp_chan *smp, u8 local_io, u8 remote_io)
+{
+	/* If either side has unknown io_caps, use JUST WORKS */
+	if (local_io > SMP_IO_KEYBOARD_DISPLAY ||
+	    remote_io > SMP_IO_KEYBOARD_DISPLAY)
+		return JUST_WORKS;
+
+	return gen_method[remote_io][local_io];
+}
+
 static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 						u8 local_io, u8 remote_io)
 {
@@ -301,33 +406,34 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 
 	/* Initialize key for JUST WORKS */
 	memset(smp->tk, 0, sizeof(smp->tk));
-	clear_bit(SMP_FLAG_TK_VALID, &smp->smp_flags);
+	clear_bit(SMP_FLAG_TK_VALID, &smp->flags);
 
 	BT_DBG("tk_request: auth:%d lcl:%d rem:%d", auth, local_io, remote_io);
 
 	/* If neither side wants MITM, use JUST WORKS */
-	/* If either side has unknown io_caps, use JUST WORKS */
 	/* Otherwise, look up method from the table */
-	if (!(auth & SMP_AUTH_MITM) ||
-	    local_io > SMP_IO_KEYBOARD_DISPLAY ||
-	    remote_io > SMP_IO_KEYBOARD_DISPLAY)
+	if (!(auth & SMP_AUTH_MITM))
 		method = JUST_WORKS;
 	else
-		method = gen_method[remote_io][local_io];
+		method = get_auth_method(smp, local_io, remote_io);
 
 	/* If not bonding, don't ask user to confirm a Zero TK */
 	if (!(auth & SMP_AUTH_BONDING) && method == JUST_CFM)
 		method = JUST_WORKS;
 
+	/* Don't confirm locally initiated pairing attempts */
+	if (method == JUST_CFM && test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+		method = JUST_WORKS;
+
 	/* If Just Works, Continue with Zero TK */
 	if (method == JUST_WORKS) {
-		set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags);
+		set_bit(SMP_FLAG_TK_VALID, &smp->flags);
 		return 0;
 	}
 
 	/* Not Just Works/Confirm results in MITM Authentication */
 	if (method != JUST_CFM)
-		set_bit(SMP_FLAG_MITM_AUTH, &smp->smp_flags);
+		set_bit(SMP_FLAG_MITM_AUTH, &smp->flags);
 
 	/* If both devices have Keyoard-Display I/O, the master
 	 * Confirms and the slave Enters the passkey.
@@ -339,16 +445,14 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 			method = REQ_PASSKEY;
 	}
 
-	/* Generate random passkey. Not valid until confirmed. */
+	/* Generate random passkey. */
 	if (method == CFM_PASSKEY) {
-		u8 key[16];
-
-		memset(key, 0, sizeof(key));
+		memset(smp->tk, 0, sizeof(smp->tk));
 		get_random_bytes(&passkey, sizeof(passkey));
 		passkey %= 1000000;
-		put_unaligned_le32(passkey, key);
-		swap128(key, smp->tk);
+		put_unaligned_le32(passkey, smp->tk);
 		BT_DBG("PassKey: %d", passkey);
+		set_bit(SMP_FLAG_TK_VALID, &smp->flags);
 	}
 
 	hci_dev_lock(hcon->hdev);
@@ -356,141 +460,120 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 	if (method == REQ_PASSKEY)
 		ret = mgmt_user_passkey_request(hcon->hdev, &hcon->dst,
 						hcon->type, hcon->dst_type);
-	else
+	else if (method == JUST_CFM)
 		ret = mgmt_user_confirm_request(hcon->hdev, &hcon->dst,
 						hcon->type, hcon->dst_type,
-						cpu_to_le32(passkey), 0);
+						passkey, 1);
+	else
+		ret = mgmt_user_passkey_notify(hcon->hdev, &hcon->dst,
+						hcon->type, hcon->dst_type,
+						passkey, 0);
 
 	hci_dev_unlock(hcon->hdev);
 
 	return ret;
 }
 
-static void confirm_work(struct work_struct *work)
+static u8 smp_confirm(struct smp_chan *smp)
 {
-	struct smp_chan *smp = container_of(work, struct smp_chan, confirm);
 	struct l2cap_conn *conn = smp->conn;
-	struct crypto_blkcipher *tfm;
+	struct hci_dev *hdev = conn->hcon->hdev;
+	struct crypto_blkcipher *tfm = hdev->tfm_aes;
 	struct smp_cmd_pairing_confirm cp;
 	int ret;
-	u8 res[16], reason;
 
 	BT_DBG("conn %p", conn);
 
-	tfm = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(tfm)) {
-		reason = SMP_UNSPECIFIED;
-		goto error;
-	}
+	/* Prevent mutual access to hdev->tfm_aes */
+	hci_dev_lock(hdev);
 
-	smp->tfm = tfm;
+	ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp,
+		     conn->hcon->init_addr_type, &conn->hcon->init_addr,
+		     conn->hcon->resp_addr_type, &conn->hcon->resp_addr,
+		     cp.confirm_val);
 
-	if (conn->hcon->out)
-		ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp,
-			     conn->hcon->src_type, &conn->hcon->src,
-			     conn->hcon->dst_type, &conn->hcon->dst, res);
-	else
-		ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp,
-			     conn->hcon->dst_type, &conn->hcon->dst,
-			     conn->hcon->src_type, &conn->hcon->src, res);
-	if (ret) {
-		reason = SMP_UNSPECIFIED;
-		goto error;
-	}
+	hci_dev_unlock(hdev);
 
-	clear_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags);
+	if (ret)
+		return SMP_UNSPECIFIED;
 
-	swap128(res, cp.confirm_val);
-	smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp);
+	clear_bit(SMP_FLAG_CFM_PENDING, &smp->flags);
 
-	return;
+	smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp);
 
-error:
-	smp_failure(conn, reason, 1);
+	return 0;
 }
 
-static void random_work(struct work_struct *work)
+static u8 smp_random(struct smp_chan *smp)
 {
-	struct smp_chan *smp = container_of(work, struct smp_chan, random);
 	struct l2cap_conn *conn = smp->conn;
 	struct hci_conn *hcon = conn->hcon;
-	struct crypto_blkcipher *tfm = smp->tfm;
-	u8 reason, confirm[16], res[16], key[16];
+	struct hci_dev *hdev = hcon->hdev;
+	struct crypto_blkcipher *tfm = hdev->tfm_aes;
+	u8 confirm[16];
 	int ret;
 
-	if (IS_ERR_OR_NULL(tfm)) {
-		reason = SMP_UNSPECIFIED;
-		goto error;
-	}
+	if (IS_ERR_OR_NULL(tfm))
+		return SMP_UNSPECIFIED;
 
 	BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave");
 
-	if (hcon->out)
-		ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp,
-			     hcon->src_type, &hcon->src,
-			     hcon->dst_type, &hcon->dst, res);
-	else
-		ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp,
-			     hcon->dst_type, &hcon->dst,
-			     hcon->src_type, &hcon->src, res);
-	if (ret) {
-		reason = SMP_UNSPECIFIED;
-		goto error;
-	}
+	/* Prevent mutual access to hdev->tfm_aes */
+	hci_dev_lock(hdev);
+
+	ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp,
+		     hcon->init_addr_type, &hcon->init_addr,
+		     hcon->resp_addr_type, &hcon->resp_addr, confirm);
+
+	hci_dev_unlock(hdev);
 
-	swap128(res, confirm);
+	if (ret)
+		return SMP_UNSPECIFIED;
 
 	if (memcmp(smp->pcnf, confirm, sizeof(smp->pcnf)) != 0) {
 		BT_ERR("Pairing failed (confirmation values mismatch)");
-		reason = SMP_CONFIRM_FAILED;
-		goto error;
+		return SMP_CONFIRM_FAILED;
 	}
 
 	if (hcon->out) {
-		u8 stk[16], rand[8];
-		__le16 ediv;
+		u8 stk[16];
+		__le64 rand = 0;
+		__le16 ediv = 0;
 
-		memset(rand, 0, sizeof(rand));
-		ediv = 0;
-
-		smp_s1(tfm, smp->tk, smp->rrnd, smp->prnd, key);
-		swap128(key, stk);
+		smp_s1(tfm, smp->tk, smp->rrnd, smp->prnd, stk);
 
 		memset(stk + smp->enc_key_size, 0,
 		       SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size);
 
-		if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->flags)) {
-			reason = SMP_UNSPECIFIED;
-			goto error;
-		}
+		if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->flags))
+			return SMP_UNSPECIFIED;
 
 		hci_le_start_enc(hcon, ediv, rand, stk);
 		hcon->enc_key_size = smp->enc_key_size;
 	} else {
-		u8 stk[16], r[16], rand[8];
-		__le16 ediv;
-
-		memset(rand, 0, sizeof(rand));
-		ediv = 0;
+		u8 stk[16], auth;
+		__le64 rand = 0;
+		__le16 ediv = 0;
 
-		swap128(smp->prnd, r);
-		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(r), r);
+		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
+			     smp->prnd);
 
-		smp_s1(tfm, smp->tk, smp->prnd, smp->rrnd, key);
-		swap128(key, stk);
+		smp_s1(tfm, smp->tk, smp->prnd, smp->rrnd, stk);
 
 		memset(stk + smp->enc_key_size, 0,
 		       SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size);
 
+		if (hcon->pending_sec_level == BT_SECURITY_HIGH)
+			auth = 1;
+		else
+			auth = 0;
+
 		hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type,
-			    HCI_SMP_STK_SLAVE, 0, 0, stk, smp->enc_key_size,
+			    HCI_SMP_STK_SLAVE, auth, stk, smp->enc_key_size,
 			    ediv, rand);
 	}
 
-	return;
-
-error:
-	smp_failure(conn, reason, 1);
+	return 0;
 }
 
 static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
@@ -501,9 +584,6 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 	if (!smp)
 		return NULL;
 
-	INIT_WORK(&smp->confirm, confirm_work);
-	INIT_WORK(&smp->random, random_work);
-
 	smp->conn = conn;
 	conn->smp_chan = smp;
 	conn->hcon->smp_conn = conn;
@@ -516,11 +596,33 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 void smp_chan_destroy(struct l2cap_conn *conn)
 {
 	struct smp_chan *smp = conn->smp_chan;
+	bool complete;
 
 	BUG_ON(!smp);
 
-	if (smp->tfm)
-		crypto_free_blkcipher(smp->tfm);
+	complete = test_bit(SMP_FLAG_COMPLETE, &smp->flags);
+	mgmt_smp_complete(conn->hcon, complete);
+
+	kfree(smp->csrk);
+	kfree(smp->slave_csrk);
+
+	/* If pairing failed clean up any keys we might have */
+	if (!complete) {
+		if (smp->ltk) {
+			list_del(&smp->ltk->list);
+			kfree(smp->ltk);
+		}
+
+		if (smp->slave_ltk) {
+			list_del(&smp->slave_ltk->list);
+			kfree(smp->slave_ltk);
+		}
+
+		if (smp->remote_irk) {
+			list_del(&smp->remote_irk->list);
+			kfree(smp->remote_irk);
+		}
+	}
 
 	kfree(smp);
 	conn->smp_chan = NULL;
@@ -533,7 +635,6 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 	struct l2cap_conn *conn = hcon->smp_conn;
 	struct smp_chan *smp;
 	u32 value;
-	u8 key[16];
 
 	BT_DBG("");
 
@@ -545,26 +646,28 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 	switch (mgmt_op) {
 	case MGMT_OP_USER_PASSKEY_REPLY:
 		value = le32_to_cpu(passkey);
-		memset(key, 0, sizeof(key));
+		memset(smp->tk, 0, sizeof(smp->tk));
 		BT_DBG("PassKey: %d", value);
-		put_unaligned_le32(value, key);
-		swap128(key, smp->tk);
+		put_unaligned_le32(value, smp->tk);
 		/* Fall Through */
 	case MGMT_OP_USER_CONFIRM_REPLY:
-		set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags);
+		set_bit(SMP_FLAG_TK_VALID, &smp->flags);
 		break;
 	case MGMT_OP_USER_PASSKEY_NEG_REPLY:
 	case MGMT_OP_USER_CONFIRM_NEG_REPLY:
-		smp_failure(conn, SMP_PASSKEY_ENTRY_FAILED, 1);
+		smp_failure(conn, SMP_PASSKEY_ENTRY_FAILED);
 		return 0;
 	default:
-		smp_failure(conn, SMP_PASSKEY_ENTRY_FAILED, 1);
+		smp_failure(conn, SMP_PASSKEY_ENTRY_FAILED);
 		return -EOPNOTSUPP;
 	}
 
 	/* If it is our turn to send Pairing Confirm, do so now */
-	if (test_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags))
-		queue_work(hcon->hdev->workqueue, &smp->confirm);
+	if (test_bit(SMP_FLAG_CFM_PENDING, &smp->flags)) {
+		u8 rsp = smp_confirm(smp);
+		if (rsp)
+			smp_failure(conn, rsp);
+	}
 
 	return 0;
 }
@@ -573,12 +676,14 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_pairing rsp, *req = (void *) skb->data;
 	struct smp_chan *smp;
-	u8 key_size;
-	u8 auth = SMP_AUTH_NONE;
+	u8 key_size, auth, sec_level;
 	int ret;
 
 	BT_DBG("conn %p", conn);
 
+	if (skb->len < sizeof(*req))
+		return SMP_INVALID_PARAMS;
+
 	if (conn->hcon->link_mode & HCI_LM_MASTER)
 		return SMP_CMD_NOTSUPP;
 
@@ -595,10 +700,21 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	skb_pull(skb, sizeof(*req));
 
 	/* We didn't start the pairing, so match remote */
-	if (req->auth_req & SMP_AUTH_BONDING)
-		auth = req->auth_req;
+	auth = req->auth_req;
+
+	sec_level = authreq_to_seclevel(auth);
+	if (sec_level > conn->hcon->pending_sec_level)
+		conn->hcon->pending_sec_level = sec_level;
 
-	conn->hcon->pending_sec_level = authreq_to_seclevel(auth);
+	/* If we need MITM check that it can be acheived */
+	if (conn->hcon->pending_sec_level >= BT_SECURITY_HIGH) {
+		u8 method;
+
+		method = get_auth_method(smp, conn->hcon->io_capability,
+					 req->io_capability);
+		if (method == JUST_WORKS || method == JUST_CFM)
+			return SMP_AUTH_REQUIREMENTS;
+	}
 
 	build_pairing_cmd(conn, req, &rsp, auth);
 
@@ -606,9 +722,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (check_enc_key_size(conn, key_size))
 		return SMP_ENC_KEY_SIZE;
 
-	ret = smp_rand(smp->prnd);
-	if (ret)
-		return SMP_UNSPECIFIED;
+	get_random_bytes(smp->prnd, sizeof(smp->prnd));
 
 	smp->prsp[0] = SMP_CMD_PAIRING_RSP;
 	memcpy(&smp->prsp[1], &rsp, sizeof(rsp));
@@ -620,6 +734,8 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (ret)
 		return SMP_UNSPECIFIED;
 
+	clear_bit(SMP_FLAG_INITIATOR, &smp->flags);
+
 	return 0;
 }
 
@@ -627,12 +743,14 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_pairing *req, *rsp = (void *) skb->data;
 	struct smp_chan *smp = conn->smp_chan;
-	struct hci_dev *hdev = conn->hcon->hdev;
 	u8 key_size, auth = SMP_AUTH_NONE;
 	int ret;
 
 	BT_DBG("conn %p", conn);
 
+	if (skb->len < sizeof(*rsp))
+		return SMP_INVALID_PARAMS;
+
 	if (!(conn->hcon->link_mode & HCI_LM_MASTER))
 		return SMP_CMD_NOTSUPP;
 
@@ -644,13 +762,26 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (check_enc_key_size(conn, key_size))
 		return SMP_ENC_KEY_SIZE;
 
-	ret = smp_rand(smp->prnd);
-	if (ret)
-		return SMP_UNSPECIFIED;
+	/* If we need MITM check that it can be acheived */
+	if (conn->hcon->pending_sec_level >= BT_SECURITY_HIGH) {
+		u8 method;
+
+		method = get_auth_method(smp, req->io_capability,
+					 rsp->io_capability);
+		if (method == JUST_WORKS || method == JUST_CFM)
+			return SMP_AUTH_REQUIREMENTS;
+	}
+
+	get_random_bytes(smp->prnd, sizeof(smp->prnd));
 
 	smp->prsp[0] = SMP_CMD_PAIRING_RSP;
 	memcpy(&smp->prsp[1], rsp, sizeof(*rsp));
 
+	/* Update remote key distribution in case the remote cleared
+	 * some bits that we had enabled in our request.
+	 */
+	smp->remote_key_dist &= rsp->resp_key_dist;
+
 	if ((req->auth_req & SMP_AUTH_BONDING) &&
 	    (rsp->auth_req & SMP_AUTH_BONDING))
 		auth = SMP_AUTH_BONDING;
@@ -661,13 +792,11 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (ret)
 		return SMP_UNSPECIFIED;
 
-	set_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags);
+	set_bit(SMP_FLAG_CFM_PENDING, &smp->flags);
 
 	/* Can't compose response until we have been confirmed */
-	if (!test_bit(SMP_FLAG_TK_VALID, &smp->smp_flags))
-		return 0;
-
-	queue_work(hdev->workqueue, &smp->confirm);
+	if (test_bit(SMP_FLAG_TK_VALID, &smp->flags))
+		return smp_confirm(smp);
 
 	return 0;
 }
@@ -675,24 +804,22 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_chan *smp = conn->smp_chan;
-	struct hci_dev *hdev = conn->hcon->hdev;
 
 	BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave");
 
+	if (skb->len < sizeof(smp->pcnf))
+		return SMP_INVALID_PARAMS;
+
 	memcpy(smp->pcnf, skb->data, sizeof(smp->pcnf));
 	skb_pull(skb, sizeof(smp->pcnf));
 
-	if (conn->hcon->out) {
-		u8 random[16];
-
-		swap128(smp->prnd, random);
-		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(random),
-			     random);
-	} else if (test_bit(SMP_FLAG_TK_VALID, &smp->smp_flags)) {
-		queue_work(hdev->workqueue, &smp->confirm);
-	} else {
-		set_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags);
-	}
+	if (conn->hcon->out)
+		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
+			     smp->prnd);
+	else if (test_bit(SMP_FLAG_TK_VALID, &smp->flags))
+		return smp_confirm(smp);
+	else
+		set_bit(SMP_FLAG_CFM_PENDING, &smp->flags);
 
 	return 0;
 }
@@ -700,16 +827,16 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_chan *smp = conn->smp_chan;
-	struct hci_dev *hdev = conn->hcon->hdev;
 
 	BT_DBG("conn %p", conn);
 
-	swap128(skb->data, smp->rrnd);
-	skb_pull(skb, sizeof(smp->rrnd));
+	if (skb->len < sizeof(smp->rrnd))
+		return SMP_INVALID_PARAMS;
 
-	queue_work(hdev->workqueue, &smp->random);
+	memcpy(smp->rrnd, skb->data, sizeof(smp->rrnd));
+	skb_pull(skb, sizeof(smp->rrnd));
 
-	return 0;
+	return smp_random(smp);
 }
 
 static u8 smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level)
@@ -717,7 +844,8 @@ static u8 smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level)
 	struct smp_ltk *key;
 	struct hci_conn *hcon = conn->hcon;
 
-	key = hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type);
+	key = hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type,
+				   hcon->out);
 	if (!key)
 		return 0;
 
@@ -739,13 +867,19 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	struct smp_cmd_pairing cp;
 	struct hci_conn *hcon = conn->hcon;
 	struct smp_chan *smp;
+	u8 sec_level;
 
 	BT_DBG("conn %p", conn);
 
+	if (skb->len < sizeof(*rp))
+		return SMP_INVALID_PARAMS;
+
 	if (!(conn->hcon->link_mode & HCI_LM_MASTER))
 		return SMP_CMD_NOTSUPP;
 
-	hcon->pending_sec_level = authreq_to_seclevel(rp->auth_req);
+	sec_level = authreq_to_seclevel(rp->auth_req);
+	if (sec_level > hcon->pending_sec_level)
+		hcon->pending_sec_level = sec_level;
 
 	if (smp_ltk_encrypt(conn, hcon->pending_sec_level))
 		return 0;
@@ -765,29 +899,46 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 
 	smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
 
+	clear_bit(SMP_FLAG_INITIATOR, &smp->flags);
+
 	return 0;
 }
 
+bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level)
+{
+	if (sec_level == BT_SECURITY_LOW)
+		return true;
+
+	if (hcon->sec_level >= sec_level)
+		return true;
+
+	return false;
+}
+
 int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 {
 	struct l2cap_conn *conn = hcon->l2cap_data;
-	struct smp_chan *smp = conn->smp_chan;
+	struct smp_chan *smp;
 	__u8 authreq;
 
 	BT_DBG("conn %p hcon %p level 0x%2.2x", conn, hcon, sec_level);
 
-	if (!test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags))
+	/* This may be NULL if there's an unexpected disconnection */
+	if (!conn)
 		return 1;
 
-	if (sec_level == BT_SECURITY_LOW)
+	if (!test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags))
 		return 1;
 
-	if (hcon->sec_level >= sec_level)
+	if (smp_sufficient_security(hcon, sec_level))
 		return 1;
 
+	if (sec_level > hcon->pending_sec_level)
+		hcon->pending_sec_level = sec_level;
+
 	if (hcon->link_mode & HCI_LM_MASTER)
-		if (smp_ltk_encrypt(conn, sec_level))
-			goto done;
+		if (smp_ltk_encrypt(conn, hcon->pending_sec_level))
+			return 0;
 
 	if (test_and_set_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags))
 		return 0;
@@ -798,6 +949,13 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 
 	authreq = seclevel_to_authreq(sec_level);
 
+	/* Require MITM if IO Capability allows or the security level
+	 * requires it.
+	 */
+	if (hcon->io_capability != HCI_IO_NO_INPUT_OUTPUT ||
+	    hcon->pending_sec_level > BT_SECURITY_MEDIUM)
+		authreq |= SMP_AUTH_MITM;
+
 	if (hcon->link_mode & HCI_LM_MASTER) {
 		struct smp_cmd_pairing cp;
 
@@ -812,8 +970,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 		smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp);
 	}
 
-done:
-	hcon->pending_sec_level = sec_level;
+	set_bit(SMP_FLAG_INITIATOR, &smp->flags);
 
 	return 0;
 }
@@ -823,6 +980,15 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb)
 	struct smp_cmd_encrypt_info *rp = (void *) skb->data;
 	struct smp_chan *smp = conn->smp_chan;
 
+	BT_DBG("conn %p", conn);
+
+	if (skb->len < sizeof(*rp))
+		return SMP_INVALID_PARAMS;
+
+	/* Ignore this PDU if it wasn't requested */
+	if (!(smp->remote_key_dist & SMP_DIST_ENC_KEY))
+		return 0;
+
 	skb_pull(skb, sizeof(*rp));
 
 	memcpy(smp->tk, rp->ltk, sizeof(smp->tk));
@@ -836,16 +1002,138 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb)
 	struct smp_chan *smp = conn->smp_chan;
 	struct hci_dev *hdev = conn->hcon->hdev;
 	struct hci_conn *hcon = conn->hcon;
+	struct smp_ltk *ltk;
 	u8 authenticated;
 
+	BT_DBG("conn %p", conn);
+
+	if (skb->len < sizeof(*rp))
+		return SMP_INVALID_PARAMS;
+
+	/* Ignore this PDU if it wasn't requested */
+	if (!(smp->remote_key_dist & SMP_DIST_ENC_KEY))
+		return 0;
+
+	/* Mark the information as received */
+	smp->remote_key_dist &= ~SMP_DIST_ENC_KEY;
+
 	skb_pull(skb, sizeof(*rp));
 
 	hci_dev_lock(hdev);
 	authenticated = (hcon->sec_level == BT_SECURITY_HIGH);
-	hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, HCI_SMP_LTK, 1,
-		    authenticated, smp->tk, smp->enc_key_size,
-		    rp->ediv, rp->rand);
-	smp_distribute_keys(conn, 1);
+	ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, HCI_SMP_LTK,
+			  authenticated, smp->tk, smp->enc_key_size,
+			  rp->ediv, rp->rand);
+	smp->ltk = ltk;
+	if (!(smp->remote_key_dist & SMP_DIST_ID_KEY))
+		smp_distribute_keys(conn);
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int smp_cmd_ident_info(struct l2cap_conn *conn, struct sk_buff *skb)
+{
+	struct smp_cmd_ident_info *info = (void *) skb->data;
+	struct smp_chan *smp = conn->smp_chan;
+
+	BT_DBG("");
+
+	if (skb->len < sizeof(*info))
+		return SMP_INVALID_PARAMS;
+
+	/* Ignore this PDU if it wasn't requested */
+	if (!(smp->remote_key_dist & SMP_DIST_ID_KEY))
+		return 0;
+
+	skb_pull(skb, sizeof(*info));
+
+	memcpy(smp->irk, info->irk, 16);
+
+	return 0;
+}
+
+static int smp_cmd_ident_addr_info(struct l2cap_conn *conn,
+				   struct sk_buff *skb)
+{
+	struct smp_cmd_ident_addr_info *info = (void *) skb->data;
+	struct smp_chan *smp = conn->smp_chan;
+	struct hci_conn *hcon = conn->hcon;
+	bdaddr_t rpa;
+
+	BT_DBG("");
+
+	if (skb->len < sizeof(*info))
+		return SMP_INVALID_PARAMS;
+
+	/* Ignore this PDU if it wasn't requested */
+	if (!(smp->remote_key_dist & SMP_DIST_ID_KEY))
+		return 0;
+
+	/* Mark the information as received */
+	smp->remote_key_dist &= ~SMP_DIST_ID_KEY;
+
+	skb_pull(skb, sizeof(*info));
+
+	/* Strictly speaking the Core Specification (4.1) allows sending
+	 * an empty address which would force us to rely on just the IRK
+	 * as "identity information". However, since such
+	 * implementations are not known of and in order to not over
+	 * complicate our implementation, simply pretend that we never
+	 * received an IRK for such a device.
+	 */
+	if (!bacmp(&info->bdaddr, BDADDR_ANY)) {
+		BT_ERR("Ignoring IRK with no identity address");
+		smp_distribute_keys(conn);
+		return 0;
+	}
+
+	bacpy(&smp->id_addr, &info->bdaddr);
+	smp->id_addr_type = info->addr_type;
+
+	if (hci_bdaddr_is_rpa(&hcon->dst, hcon->dst_type))
+		bacpy(&rpa, &hcon->dst);
+	else
+		bacpy(&rpa, BDADDR_ANY);
+
+	smp->remote_irk = hci_add_irk(conn->hcon->hdev, &smp->id_addr,
+				      smp->id_addr_type, smp->irk, &rpa);
+
+	smp_distribute_keys(conn);
+
+	return 0;
+}
+
+static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb)
+{
+	struct smp_cmd_sign_info *rp = (void *) skb->data;
+	struct smp_chan *smp = conn->smp_chan;
+	struct hci_dev *hdev = conn->hcon->hdev;
+	struct smp_csrk *csrk;
+
+	BT_DBG("conn %p", conn);
+
+	if (skb->len < sizeof(*rp))
+		return SMP_INVALID_PARAMS;
+
+	/* Ignore this PDU if it wasn't requested */
+	if (!(smp->remote_key_dist & SMP_DIST_SIGN))
+		return 0;
+
+	/* Mark the information as received */
+	smp->remote_key_dist &= ~SMP_DIST_SIGN;
+
+	skb_pull(skb, sizeof(*rp));
+
+	hci_dev_lock(hdev);
+	csrk = kzalloc(sizeof(*csrk), GFP_KERNEL);
+	if (csrk) {
+		csrk->master = 0x01;
+		memcpy(csrk->val, rp->csrk, sizeof(csrk->val));
+	}
+	smp->csrk = csrk;
+	if (!(smp->remote_key_dist & SMP_DIST_SIGN))
+		smp_distribute_keys(conn);
 	hci_dev_unlock(hdev);
 
 	return 0;
@@ -895,7 +1183,7 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb)
 		break;
 
 	case SMP_CMD_PAIRING_FAIL:
-		smp_failure(conn, skb->data[0], 0);
+		smp_failure(conn, 0);
 		reason = 0;
 		err = -EPERM;
 		break;
@@ -925,10 +1213,15 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb)
 		break;
 
 	case SMP_CMD_IDENT_INFO:
+		reason = smp_cmd_ident_info(conn, skb);
+		break;
+
 	case SMP_CMD_IDENT_ADDR_INFO:
+		reason = smp_cmd_ident_addr_info(conn, skb);
+		break;
+
 	case SMP_CMD_SIGN_INFO:
-		/* Just ignored */
-		reason = 0;
+		reason = smp_cmd_sign_info(conn, skb);
 		break;
 
 	default:
@@ -941,32 +1234,84 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb)
 
 done:
 	if (reason)
-		smp_failure(conn, reason, 1);
+		smp_failure(conn, reason);
 
 	kfree_skb(skb);
 	return err;
 }
 
-int smp_distribute_keys(struct l2cap_conn *conn, __u8 force)
+static void smp_notify_keys(struct l2cap_conn *conn)
+{
+	struct smp_chan *smp = conn->smp_chan;
+	struct hci_conn *hcon = conn->hcon;
+	struct hci_dev *hdev = hcon->hdev;
+	struct smp_cmd_pairing *req = (void *) &smp->preq[1];
+	struct smp_cmd_pairing *rsp = (void *) &smp->prsp[1];
+	bool persistent;
+
+	if (smp->remote_irk) {
+		mgmt_new_irk(hdev, smp->remote_irk);
+		/* Now that user space can be considered to know the
+		 * identity address track the connection based on it
+		 * from now on.
+		 */
+		bacpy(&hcon->dst, &smp->remote_irk->bdaddr);
+		hcon->dst_type = smp->remote_irk->addr_type;
+		l2cap_conn_update_id_addr(hcon);
+	}
+
+	/* The LTKs and CSRKs should be persistent only if both sides
+	 * had the bonding bit set in their authentication requests.
+	 */
+	persistent = !!((req->auth_req & rsp->auth_req) & SMP_AUTH_BONDING);
+
+	if (smp->csrk) {
+		smp->csrk->bdaddr_type = hcon->dst_type;
+		bacpy(&smp->csrk->bdaddr, &hcon->dst);
+		mgmt_new_csrk(hdev, smp->csrk, persistent);
+	}
+
+	if (smp->slave_csrk) {
+		smp->slave_csrk->bdaddr_type = hcon->dst_type;
+		bacpy(&smp->slave_csrk->bdaddr, &hcon->dst);
+		mgmt_new_csrk(hdev, smp->slave_csrk, persistent);
+	}
+
+	if (smp->ltk) {
+		smp->ltk->bdaddr_type = hcon->dst_type;
+		bacpy(&smp->ltk->bdaddr, &hcon->dst);
+		mgmt_new_ltk(hdev, smp->ltk, persistent);
+	}
+
+	if (smp->slave_ltk) {
+		smp->slave_ltk->bdaddr_type = hcon->dst_type;
+		bacpy(&smp->slave_ltk->bdaddr, &hcon->dst);
+		mgmt_new_ltk(hdev, smp->slave_ltk, persistent);
+	}
+}
+
+int smp_distribute_keys(struct l2cap_conn *conn)
 {
 	struct smp_cmd_pairing *req, *rsp;
 	struct smp_chan *smp = conn->smp_chan;
+	struct hci_conn *hcon = conn->hcon;
+	struct hci_dev *hdev = hcon->hdev;
 	__u8 *keydist;
 
-	BT_DBG("conn %p force %d", conn, force);
+	BT_DBG("conn %p", conn);
 
-	if (!test_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags))
+	if (!test_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags))
 		return 0;
 
 	rsp = (void *) &smp->prsp[1];
 
 	/* The responder sends its keys first */
-	if (!force && conn->hcon->out && (rsp->resp_key_dist & 0x07))
+	if (hcon->out && (smp->remote_key_dist & 0x07))
 		return 0;
 
 	req = (void *) &smp->preq[1];
 
-	if (conn->hcon->out) {
+	if (hcon->out) {
 		keydist = &rsp->init_key_dist;
 		*keydist &= req->init_key_dist;
 	} else {
@@ -974,28 +1319,30 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force)
 		*keydist &= req->resp_key_dist;
 	}
 
-
 	BT_DBG("keydist 0x%x", *keydist);
 
 	if (*keydist & SMP_DIST_ENC_KEY) {
 		struct smp_cmd_encrypt_info enc;
 		struct smp_cmd_master_ident ident;
-		struct hci_conn *hcon = conn->hcon;
+		struct smp_ltk *ltk;
 		u8 authenticated;
 		__le16 ediv;
+		__le64 rand;
 
 		get_random_bytes(enc.ltk, sizeof(enc.ltk));
 		get_random_bytes(&ediv, sizeof(ediv));
-		get_random_bytes(ident.rand, sizeof(ident.rand));
+		get_random_bytes(&rand, sizeof(rand));
 
 		smp_send_cmd(conn, SMP_CMD_ENCRYPT_INFO, sizeof(enc), &enc);
 
 		authenticated = hcon->sec_level == BT_SECURITY_HIGH;
-		hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type,
-			    HCI_SMP_LTK_SLAVE, 1, authenticated,
-			    enc.ltk, smp->enc_key_size, ediv, ident.rand);
+		ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type,
+				  HCI_SMP_LTK_SLAVE, authenticated, enc.ltk,
+				  smp->enc_key_size, ediv, rand);
+		smp->slave_ltk = ltk;
 
 		ident.ediv = ediv;
+		ident.rand = rand;
 
 		smp_send_cmd(conn, SMP_CMD_MASTER_IDENT, sizeof(ident), &ident);
 
@@ -1006,14 +1353,18 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force)
 		struct smp_cmd_ident_addr_info addrinfo;
 		struct smp_cmd_ident_info idinfo;
 
-		/* Send a dummy key */
-		get_random_bytes(idinfo.irk, sizeof(idinfo.irk));
+		memcpy(idinfo.irk, hdev->irk, sizeof(idinfo.irk));
 
 		smp_send_cmd(conn, SMP_CMD_IDENT_INFO, sizeof(idinfo), &idinfo);
 
-		/* Just public address */
-		memset(&addrinfo, 0, sizeof(addrinfo));
-		bacpy(&addrinfo.bdaddr, &conn->hcon->src);
+		/* The hci_conn contains the local identity address
+		 * after the connection has been established.
+		 *
+		 * This is true even when the connection has been
+		 * established using a resolvable random address.
+		 */
+		bacpy(&addrinfo.bdaddr, &hcon->src);
+		addrinfo.addr_type = hcon->src_type;
 
 		smp_send_cmd(conn, SMP_CMD_IDENT_ADDR_INFO, sizeof(addrinfo),
 			     &addrinfo);
@@ -1023,20 +1374,33 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force)
 
 	if (*keydist & SMP_DIST_SIGN) {
 		struct smp_cmd_sign_info sign;
+		struct smp_csrk *csrk;
 
-		/* Send a dummy key */
+		/* Generate a new random key */
 		get_random_bytes(sign.csrk, sizeof(sign.csrk));
 
+		csrk = kzalloc(sizeof(*csrk), GFP_KERNEL);
+		if (csrk) {
+			csrk->master = 0x00;
+			memcpy(csrk->val, sign.csrk, sizeof(csrk->val));
+		}
+		smp->slave_csrk = csrk;
+
 		smp_send_cmd(conn, SMP_CMD_SIGN_INFO, sizeof(sign), &sign);
 
 		*keydist &= ~SMP_DIST_SIGN;
 	}
 
-	if (conn->hcon->out || force) {
-		clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags);
-		cancel_delayed_work_sync(&conn->security_timer);
-		smp_chan_destroy(conn);
-	}
+	/* If there are still keys to be received wait for them */
+	if ((smp->remote_key_dist & 0x07))
+		return 0;
+
+	clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags);
+	cancel_delayed_work_sync(&conn->security_timer);
+	set_bit(SMP_FLAG_COMPLETE, &smp->flags);
+	smp_notify_keys(conn);
+
+	smp_chan_destroy(conn);
 
 	return 0;
 }
diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h
index f8ba07f3e5f..5a8dc36460a 100644
--- a/net/bluetooth/smp.h
+++ b/net/bluetooth/smp.h
@@ -78,7 +78,7 @@ struct smp_cmd_encrypt_info {
 #define SMP_CMD_MASTER_IDENT	0x07
 struct smp_cmd_master_ident {
 	__le16	ediv;
-	__u8	rand[8];
+	__le64	rand;
 } __packed;
 
 #define SMP_CMD_IDENT_INFO	0x08
@@ -111,36 +111,22 @@ struct smp_cmd_security_req {
 #define SMP_CMD_NOTSUPP			0x07
 #define SMP_UNSPECIFIED			0x08
 #define SMP_REPEATED_ATTEMPTS		0x09
+#define SMP_INVALID_PARAMS		0x0a
 
 #define SMP_MIN_ENC_KEY_SIZE		7
 #define SMP_MAX_ENC_KEY_SIZE		16
 
-#define SMP_FLAG_TK_VALID	1
-#define SMP_FLAG_CFM_PENDING	2
-#define SMP_FLAG_MITM_AUTH	3
-
-struct smp_chan {
-	struct l2cap_conn *conn;
-	u8		preq[7]; /* SMP Pairing Request */
-	u8		prsp[7]; /* SMP Pairing Response */
-	u8		prnd[16]; /* SMP Pairing Random (local) */
-	u8		rrnd[16]; /* SMP Pairing Random (remote) */
-	u8		pcnf[16]; /* SMP Pairing Confirm */
-	u8		tk[16]; /* SMP Temporary Key */
-	u8		enc_key_size;
-	unsigned long	smp_flags;
-	struct crypto_blkcipher	*tfm;
-	struct work_struct confirm;
-	struct work_struct random;
-
-};
-
 /* SMP Commands */
+bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level);
 int smp_conn_security(struct hci_conn *hcon, __u8 sec_level);
 int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb);
-int smp_distribute_keys(struct l2cap_conn *conn, __u8 force);
+int smp_distribute_keys(struct l2cap_conn *conn);
 int smp_user_confirm_reply(struct hci_conn *conn, u16 mgmt_op, __le32 passkey);
 
 void smp_chan_destroy(struct l2cap_conn *conn);
 
+bool smp_irk_matches(struct crypto_blkcipher *tfm, u8 irk[16],
+		     bdaddr_t *bdaddr);
+int smp_generate_rpa(struct crypto_blkcipher *tfm, u8 irk[16], bdaddr_t *rpa);
+
 #endif /* __SMP_H */
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index e85498b2f16..8590b942bff 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_BRIDGE) += bridge.o
 
 bridge-y	:= br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \
-			br_ioctl.o br_notify.o br_stp.o br_stp_bpdu.o \
+			br_ioctl.o br_stp.o br_stp_bpdu.o \
 			br_stp_if.o br_stp_timer.o br_netlink.o
 
 bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o
@@ -16,4 +16,4 @@ bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o
 
 bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o
 
-obj-$(CONFIG_BRIDGE_NF_EBTABLES) += netfilter/
+obj-$(CONFIG_NETFILTER) += netfilter/
diff --git a/net/bridge/br.c b/net/bridge/br.c
index ba780cc8e51..1a755a1e541 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -22,14 +22,127 @@
 
 #include "br_private.h"
 
-static const struct stp_proto br_stp_proto = {
-	.rcv	= br_stp_rcv,
+/*
+ * Handle changes in state of network devices enslaved to a bridge.
+ *
+ * Note: don't care about up/down if bridge itself is down, because
+ *     port state is checked when bridge is brought up.
+ */
+static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net_bridge_port *p;
+	struct net_bridge *br;
+	bool changed_addr;
+	int err;
+
+	/* register of bridge completed, add sysfs entries */
+	if ((dev->priv_flags & IFF_EBRIDGE) && event == NETDEV_REGISTER) {
+		br_sysfs_addbr(dev);
+		return NOTIFY_DONE;
+	}
+
+	/* not a port of a bridge */
+	p = br_port_get_rtnl(dev);
+	if (!p)
+		return NOTIFY_DONE;
+
+	br = p->br;
+
+	switch (event) {
+	case NETDEV_CHANGEMTU:
+		dev_set_mtu(br->dev, br_min_mtu(br));
+		break;
+
+	case NETDEV_CHANGEADDR:
+		spin_lock_bh(&br->lock);
+		br_fdb_changeaddr(p, dev->dev_addr);
+		changed_addr = br_stp_recalculate_bridge_id(br);
+		spin_unlock_bh(&br->lock);
+
+		if (changed_addr)
+			call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
+
+		break;
+
+	case NETDEV_CHANGE:
+		br_port_carrier_check(p);
+		break;
+
+	case NETDEV_FEAT_CHANGE:
+		netdev_update_features(br->dev);
+		break;
+
+	case NETDEV_DOWN:
+		spin_lock_bh(&br->lock);
+		if (br->dev->flags & IFF_UP)
+			br_stp_disable_port(p);
+		spin_unlock_bh(&br->lock);
+		break;
+
+	case NETDEV_UP:
+		if (netif_running(br->dev) && netif_oper_up(dev)) {
+			spin_lock_bh(&br->lock);
+			br_stp_enable_port(p);
+			spin_unlock_bh(&br->lock);
+		}
+		break;
+
+	case NETDEV_UNREGISTER:
+		br_del_if(br, dev);
+		break;
+
+	case NETDEV_CHANGENAME:
+		err = br_sysfs_renameif(p);
+		if (err)
+			return notifier_from_errno(err);
+		break;
+
+	case NETDEV_PRE_TYPE_CHANGE:
+		/* Forbid underlaying device to change its type. */
+		return NOTIFY_BAD;
+
+	case NETDEV_RESEND_IGMP:
+		/* Propagate to master device */
+		call_netdevice_notifiers(event, br->dev);
+		break;
+	}
+
+	/* Events that may cause spanning tree to refresh */
+	if (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
+	    event == NETDEV_CHANGE || event == NETDEV_DOWN)
+		br_ifinfo_notify(RTM_NEWLINK, p);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block br_device_notifier = {
+	.notifier_call = br_device_event
 };
 
+static void __net_exit br_net_exit(struct net *net)
+{
+	struct net_device *dev;
+	LIST_HEAD(list);
+
+	rtnl_lock();
+	for_each_netdev(net, dev)
+		if (dev->priv_flags & IFF_EBRIDGE)
+			br_dev_delete(dev, &list);
+
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
+
+}
+
 static struct pernet_operations br_net_ops = {
 	.exit	= br_net_exit,
 };
 
+static const struct stp_proto br_stp_proto = {
+	.rcv	= br_stp_rcv,
+};
+
 static int __init br_init(void)
 {
 	int err;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index f00cfd2a014..568cccd39a3 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -32,7 +32,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	const unsigned char *dest = skb->data;
 	struct net_bridge_fdb_entry *dst;
 	struct net_bridge_mdb_entry *mdst;
-	struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats);
+	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
 	u16 vid = 0;
 
 	rcu_read_lock();
@@ -49,14 +49,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	brstats->tx_bytes += skb->len;
 	u64_stats_update_end(&brstats->syncp);
 
-	if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
-		goto out;
-
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);
 	skb_pull(skb, ETH_HLEN);
 
+	if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
+		goto out;
+
 	if (is_broadcast_ether_addr(dest))
 		br_flood_deliver(br, skb, false);
 	else if (is_multicast_ether_addr(dest)) {
@@ -88,18 +88,11 @@ out:
 static int br_dev_init(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
-	int i;
 
-	br->stats = alloc_percpu(struct br_cpu_netstats);
+	br->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!br->stats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct br_cpu_netstats *br_dev_stats;
-		br_dev_stats = per_cpu_ptr(br->stats, i);
-		u64_stats_init(&br_dev_stats->syncp);
-	}
-
 	return 0;
 }
 
@@ -119,6 +112,12 @@ static void br_dev_set_multicast_list(struct net_device *dev)
 {
 }
 
+static void br_dev_change_rx_flags(struct net_device *dev, int change)
+{
+	if (change & IFF_PROMISC)
+		br_manage_promisc(netdev_priv(dev));
+}
+
 static int br_dev_stop(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
@@ -135,17 +134,17 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev,
 						struct rtnl_link_stats64 *stats)
 {
 	struct net_bridge *br = netdev_priv(dev);
-	struct br_cpu_netstats tmp, sum = { 0 };
+	struct pcpu_sw_netstats tmp, sum = { 0 };
 	unsigned int cpu;
 
 	for_each_possible_cpu(cpu) {
 		unsigned int start;
-		const struct br_cpu_netstats *bstats
+		const struct pcpu_sw_netstats *bstats
 			= per_cpu_ptr(br->stats, cpu);
 		do {
-			start = u64_stats_fetch_begin_bh(&bstats->syncp);
+			start = u64_stats_fetch_begin_irq(&bstats->syncp);
 			memcpy(&tmp, bstats, sizeof(tmp));
-		} while (u64_stats_fetch_retry_bh(&bstats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&bstats->syncp, start));
 		sum.tx_bytes   += tmp.tx_bytes;
 		sum.tx_packets += tmp.tx_packets;
 		sum.rx_bytes   += tmp.rx_bytes;
@@ -187,8 +186,7 @@ static int br_set_mac_address(struct net_device *dev, void *p)
 
 	spin_lock_bh(&br->lock);
 	if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) {
-		memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
-		br_fdb_change_mac_address(br, addr->sa_data);
+		/* Mac address will be changed in br_stp_change_bridge_id(). */
 		br_stp_change_bridge_id(br, addr->sa_data);
 	}
 	spin_unlock_bh(&br->lock);
@@ -226,8 +224,34 @@ static void br_netpoll_cleanup(struct net_device *dev)
 		br_netpoll_disable(p);
 }
 
-static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
-			    gfp_t gfp)
+static int __br_netpoll_enable(struct net_bridge_port *p)
+{
+	struct netpoll *np;
+	int err;
+
+	np = kzalloc(sizeof(*p->np), GFP_KERNEL);
+	if (!np)
+		return -ENOMEM;
+
+	err = __netpoll_setup(np, p->dev);
+	if (err) {
+		kfree(np);
+		return err;
+	}
+
+	p->np = np;
+	return err;
+}
+
+int br_netpoll_enable(struct net_bridge_port *p)
+{
+	if (!p->br->dev->npinfo)
+		return 0;
+
+	return __br_netpoll_enable(p);
+}
+
+static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
 {
 	struct net_bridge *br = netdev_priv(dev);
 	struct net_bridge_port *p;
@@ -236,7 +260,7 @@ static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
 	list_for_each_entry(p, &br->port_list, list) {
 		if (!p->dev)
 			continue;
-		err = br_netpoll_enable(p, gfp);
+		err = __br_netpoll_enable(p);
 		if (err)
 			goto fail;
 	}
@@ -249,28 +273,6 @@ fail:
 	goto out;
 }
 
-int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
-{
-	struct netpoll *np;
-	int err;
-
-	if (!p->br->dev->npinfo)
-		return 0;
-
-	np = kzalloc(sizeof(*p->np), gfp);
-	if (!np)
-		return -ENOMEM;
-
-	err = __netpoll_setup(np, p->dev, gfp);
-	if (err) {
-		kfree(np);
-		return err;
-	}
-
-	p->np = np;
-	return err;
-}
-
 void br_netpoll_disable(struct net_bridge_port *p)
 {
 	struct netpoll *np = p->np;
@@ -313,6 +315,7 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_get_stats64	 = br_get_stats64,
 	.ndo_set_mac_address	 = br_set_mac_address,
 	.ndo_set_rx_mode	 = br_dev_set_multicast_list,
+	.ndo_change_rx_flags	 = br_dev_change_rx_flags,
 	.ndo_change_mtu		 = br_change_mtu,
 	.ndo_do_ioctl		 = br_dev_ioctl,
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -352,14 +355,15 @@ void br_dev_setup(struct net_device *dev)
 
 	dev->netdev_ops = &br_netdev_ops;
 	dev->destructor = br_dev_free;
-	SET_ETHTOOL_OPS(dev, &br_ethtool_ops);
+	dev->ethtool_ops = &br_ethtool_ops;
 	SET_NETDEV_DEVTYPE(dev, &br_type);
 	dev->tx_queue_len = 0;
 	dev->priv_flags = IFF_EBRIDGE;
 
 	dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL |
-			NETIF_F_HW_VLAN_CTAG_TX;
-	dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX;
+			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+	dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
+			   NETIF_F_HW_VLAN_STAG_TX;
 	dev->vlan_features = COMMON_FEATURES;
 
 	br->dev = dev;
@@ -370,10 +374,11 @@ void br_dev_setup(struct net_device *dev)
 	br->bridge_id.prio[0] = 0x80;
 	br->bridge_id.prio[1] = 0x00;
 
-	memcpy(br->group_addr, eth_reserved_addr_base, ETH_ALEN);
+	ether_addr_copy(br->group_addr, eth_reserved_addr_base);
 
 	br->stp_enabled = BR_NO_STP;
 	br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
+	br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT;
 
 	br->designated_root = br->bridge_id;
 	br->bridge_max_age = br->max_age = 20 * HZ;
@@ -384,4 +389,5 @@ void br_dev_setup(struct net_device *dev)
 	br_netfilter_rtable_init(br);
 	br_stp_timer_init(br);
 	br_multicast_init(br);
+	br_vlan_init(br);
 }
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 33e8f23acdd..b524c36c127 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -27,6 +27,9 @@
 #include "br_private.h"
 
 static struct kmem_cache *br_fdb_cache __read_mostly;
+static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head,
+					     const unsigned char *addr,
+					     __u16 vid);
 static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
 		      const unsigned char *addr, u16 vid);
 static void fdb_notify(struct net_bridge *br,
@@ -82,18 +85,114 @@ static void fdb_rcu_free(struct rcu_head *head)
 	kmem_cache_free(br_fdb_cache, ent);
 }
 
+/* When a static FDB entry is added, the mac address from the entry is
+ * added to the bridge private HW address list and all required ports
+ * are then updated with the new information.
+ * Called under RTNL.
+ */
+static void fdb_add_hw(struct net_bridge *br, const unsigned char *addr)
+{
+	int err;
+	struct net_bridge_port *p, *tmp;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (!br_promisc_port(p)) {
+			err = dev_uc_add(p->dev, addr);
+			if (err)
+				goto undo;
+		}
+	}
+
+	return;
+undo:
+	list_for_each_entry(tmp, &br->port_list, list) {
+		if (tmp == p)
+			break;
+		if (!br_promisc_port(tmp))
+			dev_uc_del(tmp->dev, addr);
+	}
+}
+
+/* When a static FDB entry is deleted, the HW address from that entry is
+ * also removed from the bridge private HW address list and updates all
+ * the ports with needed information.
+ * Called under RTNL.
+ */
+static void fdb_del_hw(struct net_bridge *br, const unsigned char *addr)
+{
+	struct net_bridge_port *p;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (!br_promisc_port(p))
+			dev_uc_del(p->dev, addr);
+	}
+}
+
 static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
 {
+	if (f->is_static)
+		fdb_del_hw(br, f->addr.addr);
+
 	hlist_del_rcu(&f->hlist);
 	fdb_notify(br, f, RTM_DELNEIGH);
 	call_rcu(&f->rcu, fdb_rcu_free);
 }
 
+/* Delete a local entry if no other port had the same address. */
+static void fdb_delete_local(struct net_bridge *br,
+			     const struct net_bridge_port *p,
+			     struct net_bridge_fdb_entry *f)
+{
+	const unsigned char *addr = f->addr.addr;
+	u16 vid = f->vlan_id;
+	struct net_bridge_port *op;
+
+	/* Maybe another port has same hw addr? */
+	list_for_each_entry(op, &br->port_list, list) {
+		if (op != p && ether_addr_equal(op->dev->dev_addr, addr) &&
+		    (!vid || nbp_vlan_find(op, vid))) {
+			f->dst = op;
+			f->added_by_user = 0;
+			return;
+		}
+	}
+
+	/* Maybe bridge device has same hw addr? */
+	if (p && ether_addr_equal(br->dev->dev_addr, addr) &&
+	    (!vid || br_vlan_find(br, vid))) {
+		f->dst = NULL;
+		f->added_by_user = 0;
+		return;
+	}
+
+	fdb_delete(br, f);
+}
+
+void br_fdb_find_delete_local(struct net_bridge *br,
+			      const struct net_bridge_port *p,
+			      const unsigned char *addr, u16 vid)
+{
+	struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
+	struct net_bridge_fdb_entry *f;
+
+	spin_lock_bh(&br->hash_lock);
+	f = fdb_find(head, addr, vid);
+	if (f && f->is_local && !f->added_by_user && f->dst == p)
+		fdb_delete_local(br, p, f);
+	spin_unlock_bh(&br->hash_lock);
+}
+
 void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
 {
 	struct net_bridge *br = p->br;
-	bool no_vlan = (nbp_get_vlan_info(p) == NULL) ? true : false;
+	struct net_port_vlans *pv = nbp_get_vlan_info(p);
+	bool no_vlan = !pv;
 	int i;
+	u16 vid;
 
 	spin_lock_bh(&br->hash_lock);
 
@@ -104,38 +203,34 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
 			struct net_bridge_fdb_entry *f;
 
 			f = hlist_entry(h, struct net_bridge_fdb_entry, hlist);
-			if (f->dst == p && f->is_local) {
-				/* maybe another port has same hw addr? */
-				struct net_bridge_port *op;
-				u16 vid = f->vlan_id;
-				list_for_each_entry(op, &br->port_list, list) {
-					if (op != p &&
-					    ether_addr_equal(op->dev->dev_addr,
-							     f->addr.addr) &&
-					    nbp_vlan_find(op, vid)) {
-						f->dst = op;
-						goto insert;
-					}
-				}
-
+			if (f->dst == p && f->is_local && !f->added_by_user) {
 				/* delete old one */
-				fdb_delete(br, f);
-insert:
-				/* insert new address,  may fail if invalid
-				 * address or dup.
-				 */
-				fdb_insert(br, p, newaddr, vid);
+				fdb_delete_local(br, p, f);
 
 				/* if this port has no vlan information
 				 * configured, we can safely be done at
 				 * this point.
 				 */
 				if (no_vlan)
-					goto done;
+					goto insert;
 			}
 		}
 	}
 
+insert:
+	/* insert new address,  may fail if invalid address or dup. */
+	fdb_insert(br, p, newaddr, 0);
+
+	if (no_vlan)
+		goto done;
+
+	/* Now add entries for every VLAN configured on the port.
+	 * This function runs under RTNL so the bitmap will not change
+	 * from under us.
+	 */
+	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
+		fdb_insert(br, p, newaddr, vid);
+
 done:
 	spin_unlock_bh(&br->hash_lock);
 }
@@ -146,10 +241,12 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
 	struct net_port_vlans *pv;
 	u16 vid = 0;
 
+	spin_lock_bh(&br->hash_lock);
+
 	/* If old entry was unassociated with any port, then delete it. */
 	f = __br_fdb_get(br, br->dev->dev_addr, 0);
 	if (f && f->is_local && !f->dst)
-		fdb_delete(br, f);
+		fdb_delete_local(br, NULL, f);
 
 	fdb_insert(br, NULL, newaddr, 0);
 
@@ -159,14 +256,16 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
 	 */
 	pv = br_get_vlan_info(br);
 	if (!pv)
-		return;
+		goto out;
 
 	for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) {
 		f = __br_fdb_get(br, br->dev->dev_addr, vid);
 		if (f && f->is_local && !f->dst)
-			fdb_delete(br, f);
+			fdb_delete_local(br, NULL, f);
 		fdb_insert(br, NULL, newaddr, vid);
 	}
+out:
+	spin_unlock_bh(&br->hash_lock);
 }
 
 void br_fdb_cleanup(unsigned long _data)
@@ -235,25 +334,11 @@ void br_fdb_delete_by_port(struct net_bridge *br,
 
 			if (f->is_static && !do_all)
 				continue;
-			/*
-			 * if multiple ports all have the same device address
-			 * then when one port is deleted, assign
-			 * the local entry to other port
-			 */
-			if (f->is_local) {
-				struct net_bridge_port *op;
-				list_for_each_entry(op, &br->port_list, list) {
-					if (op != p &&
-					    ether_addr_equal(op->dev->dev_addr,
-							     f->addr.addr)) {
-						f->dst = op;
-						goto skip_delete;
-					}
-				}
-			}
 
-			fdb_delete(br, f);
-		skip_delete: ;
+			if (f->is_local)
+				fdb_delete_local(br, p, f);
+			else
+				fdb_delete(br, f);
 		}
 	}
 	spin_unlock_bh(&br->hash_lock);
@@ -397,6 +482,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head,
 		fdb->vlan_id = vid;
 		fdb->is_local = 0;
 		fdb->is_static = 0;
+		fdb->added_by_user = 0;
 		fdb->updated = fdb->used = jiffies;
 		hlist_add_head_rcu(&fdb->hlist, head);
 	}
@@ -430,6 +516,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
 		return -ENOMEM;
 
 	fdb->is_local = fdb->is_static = 1;
+	fdb_add_hw(br, addr);
 	fdb_notify(br, fdb, RTM_NEWNEIGH);
 	return 0;
 }
@@ -447,10 +534,11 @@ int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
 }
 
 void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
-		   const unsigned char *addr, u16 vid)
+		   const unsigned char *addr, u16 vid, bool added_by_user)
 {
 	struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
 	struct net_bridge_fdb_entry *fdb;
+	bool fdb_modified = false;
 
 	/* some users want to always flood. */
 	if (hold_time(br) == 0)
@@ -471,15 +559,25 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 					source->dev->name);
 		} else {
 			/* fastpath: update of existing entry */
-			fdb->dst = source;
+			if (unlikely(source != fdb->dst)) {
+				fdb->dst = source;
+				fdb_modified = true;
+			}
 			fdb->updated = jiffies;
+			if (unlikely(added_by_user))
+				fdb->added_by_user = 1;
+			if (unlikely(fdb_modified))
+				fdb_notify(br, fdb, RTM_NEWNEIGH);
 		}
 	} else {
 		spin_lock(&br->hash_lock);
 		if (likely(!fdb_find(head, addr, vid))) {
 			fdb = fdb_create(head, source, addr, vid);
-			if (fdb)
+			if (fdb) {
+				if (unlikely(added_by_user))
+					fdb->added_by_user = 1;
 				fdb_notify(br, fdb, RTM_NEWNEIGH);
+			}
 		}
 		/* else  we lose race and someone else inserts
 		 * it first, don't bother updating
@@ -524,6 +622,8 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
 
 	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr))
 		goto nla_put_failure;
+	if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex))
+		goto nla_put_failure;
 	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
 	ci.ndm_confirmed = 0;
 	ci.ndm_updated	 = jiffies_to_clock_t(now - fdb->updated);
@@ -545,6 +645,7 @@ static inline size_t fdb_nlmsg_size(void)
 {
 	return NLMSG_ALIGN(sizeof(struct ndmsg))
 		+ nla_total_size(ETH_ALEN) /* NDA_LLADDR */
+		+ nla_total_size(sizeof(u32)) /* NDA_MASTER */
 		+ nla_total_size(sizeof(u16)) /* NDA_VLAN */
 		+ nla_total_size(sizeof(struct nda_cacheinfo));
 }
@@ -570,8 +671,7 @@ static void fdb_notify(struct net_bridge *br,
 	rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
+	rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
 }
 
 /* Dump information about entries, in response to GETNEIGH */
@@ -638,16 +738,29 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
 	}
 
 	if (fdb_to_nud(fdb) != state) {
-		if (state & NUD_PERMANENT)
-			fdb->is_local = fdb->is_static = 1;
-		else if (state & NUD_NOARP) {
+		if (state & NUD_PERMANENT) {
+			fdb->is_local = 1;
+			if (!fdb->is_static) {
+				fdb->is_static = 1;
+				fdb_add_hw(br, addr);
+			}
+		} else if (state & NUD_NOARP) {
+			fdb->is_local = 0;
+			if (!fdb->is_static) {
+				fdb->is_static = 1;
+				fdb_add_hw(br, addr);
+			}
+		} else {
 			fdb->is_local = 0;
-			fdb->is_static = 1;
-		} else
-			fdb->is_local = fdb->is_static = 0;
+			if (fdb->is_static) {
+				fdb->is_static = 0;
+				fdb_del_hw(br, addr);
+			}
+		}
 
 		modified = true;
 	}
+	fdb->added_by_user = 1;
 
 	fdb->used = jiffies;
 	if (modified) {
@@ -665,7 +778,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
 
 	if (ndm->ndm_flags & NTF_USE) {
 		rcu_read_lock();
-		br_fdb_update(p->br, p, addr, vid);
+		br_fdb_update(p->br, p, addr, vid, true);
 		rcu_read_unlock();
 	} else {
 		spin_lock_bh(&p->br->hash_lock);
@@ -750,8 +863,7 @@ out:
 	return err;
 }
 
-int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr,
-		       u16 vlan)
+static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vlan)
 {
 	struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)];
 	struct net_bridge_fdb_entry *fdb;
@@ -834,3 +946,59 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 out:
 	return err;
 }
+
+int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p)
+{
+	struct net_bridge_fdb_entry *fdb, *tmp;
+	int i;
+	int err;
+
+	ASSERT_RTNL();
+
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		hlist_for_each_entry(fdb, &br->hash[i], hlist) {
+			/* We only care for static entries */
+			if (!fdb->is_static)
+				continue;
+
+			err = dev_uc_add(p->dev, fdb->addr.addr);
+			if (err)
+				goto rollback;
+		}
+	}
+	return 0;
+
+rollback:
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		hlist_for_each_entry(tmp, &br->hash[i], hlist) {
+			/* If we reached the fdb that failed, we can stop */
+			if (tmp == fdb)
+				break;
+
+			/* We only care for static entries */
+			if (!tmp->is_static)
+				continue;
+
+			dev_uc_del(p->dev, tmp->addr.addr);
+		}
+	}
+	return err;
+}
+
+void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p)
+{
+	struct net_bridge_fdb_entry *fdb;
+	int i;
+
+	ASSERT_RTNL();
+
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		hlist_for_each_entry_rcu(fdb, &br->hash[i], hlist) {
+			/* We only care for static entries */
+			if (!fdb->is_static)
+				continue;
+
+			dev_uc_del(p->dev, fdb->addr.addr);
+		}
+	}
+}
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 4b81b147178..056b67b0e27 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -26,25 +26,20 @@ static int deliver_clone(const struct net_bridge_port *prev,
 			 void (*__packet_hook)(const struct net_bridge_port *p,
 					       struct sk_buff *skb));
 
-/* Don't forward packets to originating port or forwarding diasabled */
+/* Don't forward packets to originating port or forwarding disabled */
 static inline int should_deliver(const struct net_bridge_port *p,
 				 const struct sk_buff *skb)
 {
-	return (((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
+	return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
 		br_allowed_egress(p->br, nbp_get_vlan_info(p), skb) &&
-		p->state == BR_STATE_FORWARDING);
-}
-
-static inline unsigned int packet_length(const struct sk_buff *skb)
-{
-	return skb->len - (skb->protocol == htons(ETH_P_8021Q) ? VLAN_HLEN : 0);
+		p->state == BR_STATE_FORWARDING;
 }
 
 int br_dev_queue_push_xmit(struct sk_buff *skb)
 {
 	/* ip_fragment doesn't copy the MAC header */
 	if (nf_bridge_maybe_copy_header(skb) ||
-	    (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb))) {
+	    !is_skb_forwardable(skb->dev, skb)) {
 		kfree_skb(skb);
 	} else {
 		skb_push(skb, ETH_HLEN);
@@ -71,7 +66,7 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
 	skb->dev = to->dev;
 
 	if (unlikely(netpoll_tx_running(to->br->dev))) {
-		if (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb))
+		if (!is_skb_forwardable(skb->dev, skb))
 			kfree_skb(skb);
 		else {
 			skb_push(skb, ETH_HLEN);
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 4bf02adb5dc..3eca3fdf8fe 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -61,7 +61,7 @@ static int port_cost(struct net_device *dev)
 }
 
 
-/* Check for port carrier transistions. */
+/* Check for port carrier transitions. */
 void br_port_carrier_check(struct net_bridge_port *p)
 {
 	struct net_device *dev = p->dev;
@@ -85,6 +85,111 @@ void br_port_carrier_check(struct net_bridge_port *p)
 	spin_unlock_bh(&br->lock);
 }
 
+static void br_port_set_promisc(struct net_bridge_port *p)
+{
+	int err = 0;
+
+	if (br_promisc_port(p))
+		return;
+
+	err = dev_set_promiscuity(p->dev, 1);
+	if (err)
+		return;
+
+	br_fdb_unsync_static(p->br, p);
+	p->flags |= BR_PROMISC;
+}
+
+static void br_port_clear_promisc(struct net_bridge_port *p)
+{
+	int err;
+
+	/* Check if the port is already non-promisc or if it doesn't
+	 * support UNICAST filtering.  Without unicast filtering support
+	 * we'll end up re-enabling promisc mode anyway, so just check for
+	 * it here.
+	 */
+	if (!br_promisc_port(p) || !(p->dev->priv_flags & IFF_UNICAST_FLT))
+		return;
+
+	/* Since we'll be clearing the promisc mode, program the port
+	 * first so that we don't have interruption in traffic.
+	 */
+	err = br_fdb_sync_static(p->br, p);
+	if (err)
+		return;
+
+	dev_set_promiscuity(p->dev, -1);
+	p->flags &= ~BR_PROMISC;
+}
+
+/* When a port is added or removed or when certain port flags
+ * change, this function is called to automatically manage
+ * promiscuity setting of all the bridge ports.  We are always called
+ * under RTNL so can skip using rcu primitives.
+ */
+void br_manage_promisc(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+	bool set_all = false;
+
+	/* If vlan filtering is disabled or bridge interface is placed
+	 * into promiscuous mode, place all ports in promiscuous mode.
+	 */
+	if ((br->dev->flags & IFF_PROMISC) || !br_vlan_enabled(br))
+		set_all = true;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (set_all) {
+			br_port_set_promisc(p);
+		} else {
+			/* If the number of auto-ports is <= 1, then all other
+			 * ports will have their output configuration
+			 * statically specified through fdbs.  Since ingress
+			 * on the auto-port becomes forwarding/egress to other
+			 * ports and egress configuration is statically known,
+			 * we can say that ingress configuration of the
+			 * auto-port is also statically known.
+			 * This lets us disable promiscuous mode and write
+			 * this config to hw.
+			 */
+			if (br->auto_cnt == 0 ||
+			    (br->auto_cnt == 1 && br_auto_port(p)))
+				br_port_clear_promisc(p);
+			else
+				br_port_set_promisc(p);
+		}
+	}
+}
+
+static void nbp_update_port_count(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+	u32 cnt = 0;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (br_auto_port(p))
+			cnt++;
+	}
+	if (br->auto_cnt != cnt) {
+		br->auto_cnt = cnt;
+		br_manage_promisc(br);
+	}
+}
+
+static void nbp_delete_promisc(struct net_bridge_port *p)
+{
+	/* If port is currently promiscuous, unset promiscuity.
+	 * Otherwise, it is a static port so remove all addresses
+	 * from it.
+	 */
+	dev_set_allmulti(p->dev, -1);
+	if (br_promisc_port(p))
+		dev_set_promiscuity(p->dev, -1);
+	else
+		br_fdb_unsync_static(p->br, p);
+}
+
 static void release_nbp(struct kobject *kobj)
 {
 	struct net_bridge_port *p
@@ -133,7 +238,7 @@ static void del_nbp(struct net_bridge_port *p)
 
 	sysfs_remove_link(br->ifobj, p->dev->name);
 
-	dev_set_promiscuity(dev, -1);
+	nbp_delete_promisc(p);
 
 	spin_lock_bh(&br->lock);
 	br_stp_disable_port(p);
@@ -141,10 +246,11 @@ static void del_nbp(struct net_bridge_port *p)
 
 	br_ifinfo_notify(RTM_DELLINK, p);
 
+	list_del_rcu(&p->list);
+
 	nbp_vlan_flush(p);
 	br_fdb_delete_by_port(br, p, 1);
-
-	list_del_rcu(&p->list);
+	nbp_update_port_count(br);
 
 	dev->priv_flags &= ~IFF_BRIDGE_PORT;
 
@@ -353,7 +459,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 
 	call_netdevice_notifiers(NETDEV_JOIN, dev);
 
-	err = dev_set_promiscuity(dev, 1);
+	err = dev_set_allmulti(dev, 1);
 	if (err)
 		goto put_back;
 
@@ -366,7 +472,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 	if (err)
 		goto err2;
 
-	err = br_netpoll_enable(p, GFP_KERNEL);
+	err = br_netpoll_enable(p);
 	if (err)
 		goto err3;
 
@@ -384,11 +490,16 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 
 	list_add_rcu(&p->list, &br->port_list);
 
+	nbp_update_port_count(br);
+
 	netdev_update_features(br->dev);
 
 	if (br->dev->needed_headroom < dev->needed_headroom)
 		br->dev->needed_headroom = dev->needed_headroom;
 
+	if (br_fdb_insert(br, p, dev->dev_addr, 0))
+		netdev_err(dev, "failed insert local address bridge forwarding table\n");
+
 	spin_lock_bh(&br->lock);
 	changed_addr = br_stp_recalculate_bridge_id(br);
 
@@ -404,9 +515,6 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 
 	dev_set_mtu(br->dev, br_min_mtu(br));
 
-	if (br_fdb_insert(br, p, dev->dev_addr, 0))
-		netdev_err(dev, "failed insert local address bridge forwarding table\n");
-
 	kobject_uevent(&p->kobj, KOBJ_ADD);
 
 	return 0;
@@ -421,7 +529,7 @@ err2:
 	kobject_put(&p->kobj);
 	p = NULL; /* kobject_put frees */
 err1:
-	dev_set_promiscuity(dev, -1);
+	dev_set_allmulti(dev, -1);
 put_back:
 	dev_put(dev);
 	kfree(p);
@@ -456,17 +564,10 @@ int br_del_if(struct net_bridge *br, struct net_device *dev)
 	return 0;
 }
 
-void __net_exit br_net_exit(struct net *net)
+void br_port_flags_change(struct net_bridge_port *p, unsigned long mask)
 {
-	struct net_device *dev;
-	LIST_HEAD(list);
-
-	rtnl_lock();
-	for_each_netdev(net, dev)
-		if (dev->priv_flags & IFF_EBRIDGE)
-			br_dev_delete(dev, &list);
-
-	unregister_netdevice_many(&list);
-	rtnl_unlock();
+	struct net_bridge *br = p->br;
 
+	if (mask & BR_AUTO_MASK)
+		nbp_update_port_count(br);
 }
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 7e73c32e205..366c4364907 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -28,7 +28,8 @@ static int br_pass_frame_up(struct sk_buff *skb)
 {
 	struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
 	struct net_bridge *br = netdev_priv(brdev);
-	struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats);
+	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
+	struct net_port_vlans *pv;
 
 	u64_stats_update_begin(&brstats->syncp);
 	brstats->rx_packets++;
@@ -39,18 +40,18 @@ static int br_pass_frame_up(struct sk_buff *skb)
 	 * packet is allowed except in promisc modue when someone
 	 * may be running packet capture.
 	 */
+	pv = br_get_vlan_info(br);
 	if (!(brdev->flags & IFF_PROMISC) &&
-	    !br_allowed_egress(br, br_get_vlan_info(br), skb)) {
+	    !br_allowed_egress(br, pv, skb)) {
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
 
-	skb = br_handle_vlan(br, br_get_vlan_info(br), skb);
-	if (!skb)
-		return NET_RX_DROP;
-
 	indev = skb->dev;
 	skb->dev = brdev;
+	skb = br_handle_vlan(br, pv, skb);
+	if (!skb)
+		return NET_RX_DROP;
 
 	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL,
 		       netif_receive_skb);
@@ -72,12 +73,12 @@ int br_handle_frame_finish(struct sk_buff *skb)
 		goto drop;
 
 	if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid))
-		goto drop;
+		goto out;
 
 	/* insert into forwarding database after filtering to avoid spoofing */
 	br = p->br;
 	if (p->flags & BR_LEARNING)
-		br_fdb_update(br, p, eth_hdr(skb)->h_source, vid);
+		br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
 
 	if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) &&
 	    br_multicast_rcv(br, p, skb, vid))
@@ -146,9 +147,9 @@ static int br_handle_local_finish(struct sk_buff *skb)
 	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
 	u16 vid = 0;
 
-	br_vlan_get_tag(skb, &vid);
-	if (p->flags & BR_LEARNING)
-		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid);
+	/* check if vlan is allowed, to avoid spoofing */
+	if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid))
+		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
 	return 0;	 /* process further */
 }
 
@@ -176,6 +177,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 	p = br_port_get_rcu(skb->dev);
 
 	if (unlikely(is_link_local_ether_addr(dest))) {
+		u16 fwd_mask = p->br->group_fwd_mask_required;
+
 		/*
 		 * See IEEE 802.1D Table 7-10 Reserved addresses
 		 *
@@ -193,7 +196,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 		case 0x00:	/* Bridge Group Address */
 			/* If STP is turned off,
 			   then must forward to keep loop detection */
-			if (p->br->stp_enabled == BR_NO_STP)
+			if (p->br->stp_enabled == BR_NO_STP ||
+			    fwd_mask & (1u << dest[5]))
 				goto forward;
 			break;
 
@@ -202,7 +206,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 
 		default:
 			/* Allow selective forwarding for most other protocols */
-			if (p->br->group_fwd_mask & (1u << dest[5]))
+			fwd_mask |= p->br->group_fwd_mask;
+			if (fwd_mask & (1u << dest[5]))
 				goto forward;
 		}
 
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index cd8c3a44ab7..a9a4a1b7863 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -381,7 +381,7 @@ int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct net_bridge *br = netdev_priv(dev);
 
-	switch(cmd) {
+	switch (cmd) {
 	case SIOCDEVPRIVATE:
 		return old_dev_ioctl(dev, rq, cmd);
 
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index b7b1914dfa2..5df05269d17 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -418,13 +418,13 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP)) {
-		if (timer_pending(&br->ip4_querier.timer))
+		if (timer_pending(&br->ip4_other_query.timer))
 			return -EBUSY;
 
 		ip.u.ip4 = entry->addr.u.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
-		if (timer_pending(&br->ip6_querier.timer))
+		if (timer_pending(&br->ip6_other_query.timer))
 			return -EBUSY;
 
 		ip.u.ip6 = entry->addr.u.ip6;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 4c214b2b88e..abfa0b65a11 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/err.h>
+#include <linux/export.h>
 #include <linux/if_ether.h>
 #include <linux/igmp.h>
 #include <linux/jhash.h>
@@ -35,7 +36,7 @@
 #include "br_private.h"
 
 static void br_multicast_start_querier(struct net_bridge *br,
-				       struct bridge_mcast_query *query);
+				       struct bridge_mcast_own_query *query);
 unsigned int br_mdb_rehash_seq;
 
 static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
@@ -363,7 +364,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 	skb_reset_mac_header(skb);
 	eth = eth_hdr(skb);
 
-	memcpy(eth->h_source, br->dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(eth->h_source, br->dev->dev_addr);
 	eth->h_dest[0] = 1;
 	eth->h_dest[1] = 0;
 	eth->h_dest[2] = 0x5e;
@@ -433,7 +434,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 	skb_reset_mac_header(skb);
 	eth = eth_hdr(skb);
 
-	memcpy(eth->h_source, br->dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(eth->h_source, br->dev->dev_addr);
 	eth->h_proto = htons(ETH_P_IPV6);
 	skb_put(skb, sizeof(*eth));
 
@@ -761,7 +762,7 @@ static void br_multicast_local_router_expired(unsigned long data)
 }
 
 static void br_multicast_querier_expired(struct net_bridge *br,
-					 struct bridge_mcast_query *query)
+					 struct bridge_mcast_own_query *query)
 {
 	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) || br->multicast_disabled)
@@ -777,7 +778,7 @@ static void br_ip4_multicast_querier_expired(unsigned long data)
 {
 	struct net_bridge *br = (void *)data;
 
-	br_multicast_querier_expired(br, &br->ip4_query);
+	br_multicast_querier_expired(br, &br->ip4_own_query);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -785,10 +786,22 @@ static void br_ip6_multicast_querier_expired(unsigned long data)
 {
 	struct net_bridge *br = (void *)data;
 
-	br_multicast_querier_expired(br, &br->ip6_query);
+	br_multicast_querier_expired(br, &br->ip6_own_query);
 }
 #endif
 
+static void br_multicast_select_own_querier(struct net_bridge *br,
+					    struct br_ip *ip,
+					    struct sk_buff *skb)
+{
+	if (ip->proto == htons(ETH_P_IP))
+		br->ip4_querier.addr.u.ip4 = ip_hdr(skb)->saddr;
+#if IS_ENABLED(CONFIG_IPV6)
+	else
+		br->ip6_querier.addr.u.ip6 = ipv6_hdr(skb)->saddr;
+#endif
+}
+
 static void __br_multicast_send_query(struct net_bridge *br,
 				      struct net_bridge_port *port,
 				      struct br_ip *ip)
@@ -804,17 +817,19 @@ static void __br_multicast_send_query(struct net_bridge *br,
 		skb->dev = port->dev;
 		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
 			dev_queue_xmit);
-	} else
+	} else {
+		br_multicast_select_own_querier(br, ip, skb);
 		netif_rx(skb);
+	}
 }
 
 static void br_multicast_send_query(struct net_bridge *br,
 				    struct net_bridge_port *port,
-				    struct bridge_mcast_query *query)
+				    struct bridge_mcast_own_query *own_query)
 {
 	unsigned long time;
 	struct br_ip br_group;
-	struct bridge_mcast_querier *querier = NULL;
+	struct bridge_mcast_other_query *other_query = NULL;
 
 	if (!netif_running(br->dev) || br->multicast_disabled ||
 	    !br->multicast_querier)
@@ -822,31 +837,32 @@ static void br_multicast_send_query(struct net_bridge *br,
 
 	memset(&br_group.u, 0, sizeof(br_group.u));
 
-	if (port ? (query == &port->ip4_query) :
-		   (query == &br->ip4_query)) {
-		querier = &br->ip4_querier;
+	if (port ? (own_query == &port->ip4_own_query) :
+		   (own_query == &br->ip4_own_query)) {
+		other_query = &br->ip4_other_query;
 		br_group.proto = htons(ETH_P_IP);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
-		querier = &br->ip6_querier;
+		other_query = &br->ip6_other_query;
 		br_group.proto = htons(ETH_P_IPV6);
 #endif
 	}
 
-	if (!querier || timer_pending(&querier->timer))
+	if (!other_query || timer_pending(&other_query->timer))
 		return;
 
 	__br_multicast_send_query(br, port, &br_group);
 
 	time = jiffies;
-	time += query->startup_sent < br->multicast_startup_query_count ?
+	time += own_query->startup_sent < br->multicast_startup_query_count ?
 		br->multicast_startup_query_interval :
 		br->multicast_query_interval;
-	mod_timer(&query->timer, time);
+	mod_timer(&own_query->timer, time);
 }
 
-static void br_multicast_port_query_expired(struct net_bridge_port *port,
-					    struct bridge_mcast_query *query)
+static void
+br_multicast_port_query_expired(struct net_bridge_port *port,
+				struct bridge_mcast_own_query *query)
 {
 	struct net_bridge *br = port->br;
 
@@ -868,7 +884,7 @@ static void br_ip4_multicast_port_query_expired(unsigned long data)
 {
 	struct net_bridge_port *port = (void *)data;
 
-	br_multicast_port_query_expired(port, &port->ip4_query);
+	br_multicast_port_query_expired(port, &port->ip4_own_query);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -876,7 +892,7 @@ static void br_ip6_multicast_port_query_expired(unsigned long data)
 {
 	struct net_bridge_port *port = (void *)data;
 
-	br_multicast_port_query_expired(port, &port->ip6_query);
+	br_multicast_port_query_expired(port, &port->ip6_own_query);
 }
 #endif
 
@@ -886,11 +902,11 @@ void br_multicast_add_port(struct net_bridge_port *port)
 
 	setup_timer(&port->multicast_router_timer, br_multicast_router_expired,
 		    (unsigned long)port);
-	setup_timer(&port->ip4_query.timer, br_ip4_multicast_port_query_expired,
-		    (unsigned long)port);
+	setup_timer(&port->ip4_own_query.timer,
+		    br_ip4_multicast_port_query_expired, (unsigned long)port);
 #if IS_ENABLED(CONFIG_IPV6)
-	setup_timer(&port->ip6_query.timer, br_ip6_multicast_port_query_expired,
-		    (unsigned long)port);
+	setup_timer(&port->ip6_own_query.timer,
+		    br_ip6_multicast_port_query_expired, (unsigned long)port);
 #endif
 }
 
@@ -899,7 +915,7 @@ void br_multicast_del_port(struct net_bridge_port *port)
 	del_timer_sync(&port->multicast_router_timer);
 }
 
-static void br_multicast_enable(struct bridge_mcast_query *query)
+static void br_multicast_enable(struct bridge_mcast_own_query *query)
 {
 	query->startup_sent = 0;
 
@@ -916,9 +932,9 @@ void br_multicast_enable_port(struct net_bridge_port *port)
 	if (br->multicast_disabled || !netif_running(br->dev))
 		goto out;
 
-	br_multicast_enable(&port->ip4_query);
+	br_multicast_enable(&port->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
-	br_multicast_enable(&port->ip6_query);
+	br_multicast_enable(&port->ip6_own_query);
 #endif
 
 out:
@@ -938,9 +954,9 @@ void br_multicast_disable_port(struct net_bridge_port *port)
 	if (!hlist_unhashed(&port->rlist))
 		hlist_del_init_rcu(&port->rlist);
 	del_timer(&port->multicast_router_timer);
-	del_timer(&port->ip4_query.timer);
+	del_timer(&port->ip4_own_query.timer);
 #if IS_ENABLED(CONFIG_IPV6)
-	del_timer(&port->ip6_query.timer);
+	del_timer(&port->ip6_own_query.timer);
 #endif
 	spin_unlock(&br->multicast_lock);
 }
@@ -1064,15 +1080,80 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 }
 #endif
 
+static bool br_ip4_multicast_select_querier(struct net_bridge *br,
+					    struct net_bridge_port *port,
+					    __be32 saddr)
+{
+	if (!timer_pending(&br->ip4_own_query.timer) &&
+	    !timer_pending(&br->ip4_other_query.timer))
+		goto update;
+
+	if (!br->ip4_querier.addr.u.ip4)
+		goto update;
+
+	if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.u.ip4))
+		goto update;
+
+	return false;
+
+update:
+	br->ip4_querier.addr.u.ip4 = saddr;
+
+	/* update protected by general multicast_lock by caller */
+	rcu_assign_pointer(br->ip4_querier.port, port);
+
+	return true;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static bool br_ip6_multicast_select_querier(struct net_bridge *br,
+					    struct net_bridge_port *port,
+					    struct in6_addr *saddr)
+{
+	if (!timer_pending(&br->ip6_own_query.timer) &&
+	    !timer_pending(&br->ip6_other_query.timer))
+		goto update;
+
+	if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.u.ip6) <= 0)
+		goto update;
+
+	return false;
+
+update:
+	br->ip6_querier.addr.u.ip6 = *saddr;
+
+	/* update protected by general multicast_lock by caller */
+	rcu_assign_pointer(br->ip6_querier.port, port);
+
+	return true;
+}
+#endif
+
+static bool br_multicast_select_querier(struct net_bridge *br,
+					struct net_bridge_port *port,
+					struct br_ip *saddr)
+{
+	switch (saddr->proto) {
+	case htons(ETH_P_IP):
+		return br_ip4_multicast_select_querier(br, port, saddr->u.ip4);
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		return br_ip6_multicast_select_querier(br, port, &saddr->u.ip6);
+#endif
+	}
+
+	return false;
+}
+
 static void
-br_multicast_update_querier_timer(struct net_bridge *br,
-				  struct bridge_mcast_querier *querier,
-				  unsigned long max_delay)
+br_multicast_update_query_timer(struct net_bridge *br,
+				struct bridge_mcast_other_query *query,
+				unsigned long max_delay)
 {
-	if (!timer_pending(&querier->timer))
-		querier->delay_time = jiffies + max_delay;
+	if (!timer_pending(&query->timer))
+		query->delay_time = jiffies + max_delay;
 
-	mod_timer(&querier->timer, jiffies + br->multicast_querier_interval);
+	mod_timer(&query->timer, jiffies + br->multicast_querier_interval);
 }
 
 /*
@@ -1125,15 +1206,14 @@ timer:
 
 static void br_multicast_query_received(struct net_bridge *br,
 					struct net_bridge_port *port,
-					struct bridge_mcast_querier *querier,
-					int saddr,
+					struct bridge_mcast_other_query *query,
+					struct br_ip *saddr,
 					unsigned long max_delay)
 {
-	if (saddr)
-		br_multicast_update_querier_timer(br, querier, max_delay);
-	else if (timer_pending(&querier->timer))
+	if (!br_multicast_select_querier(br, port, saddr))
 		return;
 
+	br_multicast_update_query_timer(br, query, max_delay);
 	br_multicast_mark_router(br, port);
 }
 
@@ -1148,6 +1228,7 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 	struct igmpv3_query *ih3;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
+	struct br_ip saddr;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
 	__be32 group;
@@ -1181,11 +1262,22 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 			    IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1;
 	}
 
-	br_multicast_query_received(br, port, &br->ip4_querier, !!iph->saddr,
-				    max_delay);
+	/* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer
+	 * all-systems destination addresses (224.0.0.1) for general queries
+	 */
+	if (!group && iph->daddr != htonl(INADDR_ALLHOSTS_GROUP)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (!group) {
+		saddr.proto = htons(ETH_P_IP);
+		saddr.u.ip4 = iph->saddr;
 
-	if (!group)
+		br_multicast_query_received(br, port, &br->ip4_other_query,
+					    &saddr, max_delay);
 		goto out;
+	}
 
 	mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group, vid);
 	if (!mp)
@@ -1225,9 +1317,11 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	struct mld2_query *mld2q;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
+	struct br_ip saddr;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
 	const struct in6_addr *group = NULL;
+	bool is_general_query;
 	int err = 0;
 
 	spin_lock(&br->multicast_lock);
@@ -1235,6 +1329,12 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
+	/* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+	if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (skb->len == sizeof(*mld)) {
 		if (!pskb_may_pull(skb, sizeof(*mld))) {
 			err = -EINVAL;
@@ -1256,11 +1356,26 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 		max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL);
 	}
 
-	br_multicast_query_received(br, port, &br->ip6_querier,
-				    !ipv6_addr_any(&ip6h->saddr), max_delay);
+	is_general_query = group && ipv6_addr_any(group);
+
+	/* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer
+	 * all-nodes destination address (ff02::1) for general queries
+	 */
+	if (is_general_query && !ipv6_addr_is_ll_all_nodes(&ip6h->daddr)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (is_general_query) {
+		saddr.proto = htons(ETH_P_IPV6);
+		saddr.u.ip6 = ip6h->saddr;
 
-	if (!group)
+		br_multicast_query_received(br, port, &br->ip6_other_query,
+					    &saddr, max_delay);
 		goto out;
+	} else if (!group) {
+		goto out;
+	}
 
 	mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group, vid);
 	if (!mp)
@@ -1288,11 +1403,12 @@ out:
 }
 #endif
 
-static void br_multicast_leave_group(struct net_bridge *br,
-				     struct net_bridge_port *port,
-				     struct br_ip *group,
-				     struct bridge_mcast_querier *querier,
-				     struct bridge_mcast_query *query)
+static void
+br_multicast_leave_group(struct net_bridge *br,
+			 struct net_bridge_port *port,
+			 struct br_ip *group,
+			 struct bridge_mcast_other_query *other_query,
+			 struct bridge_mcast_own_query *own_query)
 {
 	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_mdb_entry *mp;
@@ -1303,7 +1419,7 @@ static void br_multicast_leave_group(struct net_bridge *br,
 	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) ||
 	    (port && port->state == BR_STATE_DISABLED) ||
-	    timer_pending(&querier->timer))
+	    timer_pending(&other_query->timer))
 		goto out;
 
 	mdb = mlock_dereference(br->mdb, br);
@@ -1317,7 +1433,7 @@ static void br_multicast_leave_group(struct net_bridge *br,
 		time = jiffies + br->multicast_last_member_count *
 				 br->multicast_last_member_interval;
 
-		mod_timer(&query->timer, time);
+		mod_timer(&own_query->timer, time);
 
 		for (p = mlock_dereference(mp->ports, br);
 		     p != NULL;
@@ -1398,17 +1514,19 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 					 __u16 vid)
 {
 	struct br_ip br_group;
-	struct bridge_mcast_query *query = port ? &port->ip4_query :
-						  &br->ip4_query;
+	struct bridge_mcast_own_query *own_query;
 
 	if (ipv4_is_local_multicast(group))
 		return;
 
+	own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
+
 	br_group.u.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
 
-	br_multicast_leave_group(br, port, &br_group, &br->ip4_querier, query);
+	br_multicast_leave_group(br, port, &br_group, &br->ip4_other_query,
+				 own_query);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1418,18 +1536,19 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 					 __u16 vid)
 {
 	struct br_ip br_group;
-	struct bridge_mcast_query *query = port ? &port->ip6_query :
-						  &br->ip6_query;
-
+	struct bridge_mcast_own_query *own_query;
 
 	if (ipv6_addr_is_ll_all_nodes(group))
 		return;
 
+	own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
+
 	br_group.u.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
 
-	br_multicast_leave_group(br, port, &br_group, &br->ip6_querier, query);
+	br_multicast_leave_group(br, port, &br_group, &br->ip6_other_query,
+				 own_query);
 }
 #endif
 
@@ -1696,12 +1815,14 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
 }
 
 static void br_multicast_query_expired(struct net_bridge *br,
-				       struct bridge_mcast_query *query)
+				       struct bridge_mcast_own_query *query,
+				       struct bridge_mcast_querier *querier)
 {
 	spin_lock(&br->multicast_lock);
 	if (query->startup_sent < br->multicast_startup_query_count)
 		query->startup_sent++;
 
+	rcu_assign_pointer(querier, NULL);
 	br_multicast_send_query(br, NULL, query);
 	spin_unlock(&br->multicast_lock);
 }
@@ -1710,7 +1831,7 @@ static void br_ip4_multicast_query_expired(unsigned long data)
 {
 	struct net_bridge *br = (void *)data;
 
-	br_multicast_query_expired(br, &br->ip4_query);
+	br_multicast_query_expired(br, &br->ip4_own_query, &br->ip4_querier);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1718,7 +1839,7 @@ static void br_ip6_multicast_query_expired(unsigned long data)
 {
 	struct net_bridge *br = (void *)data;
 
-	br_multicast_query_expired(br, &br->ip6_query);
+	br_multicast_query_expired(br, &br->ip6_own_query, &br->ip6_querier);
 }
 #endif
 
@@ -1740,28 +1861,30 @@ void br_multicast_init(struct net_bridge *br)
 	br->multicast_querier_interval = 255 * HZ;
 	br->multicast_membership_interval = 260 * HZ;
 
-	br->ip4_querier.delay_time = 0;
+	br->ip4_other_query.delay_time = 0;
+	br->ip4_querier.port = NULL;
 #if IS_ENABLED(CONFIG_IPV6)
-	br->ip6_querier.delay_time = 0;
+	br->ip6_other_query.delay_time = 0;
+	br->ip6_querier.port = NULL;
 #endif
 
 	spin_lock_init(&br->multicast_lock);
 	setup_timer(&br->multicast_router_timer,
 		    br_multicast_local_router_expired, 0);
-	setup_timer(&br->ip4_querier.timer, br_ip4_multicast_querier_expired,
-		    (unsigned long)br);
-	setup_timer(&br->ip4_query.timer, br_ip4_multicast_query_expired,
+	setup_timer(&br->ip4_other_query.timer,
+		    br_ip4_multicast_querier_expired, (unsigned long)br);
+	setup_timer(&br->ip4_own_query.timer, br_ip4_multicast_query_expired,
 		    (unsigned long)br);
 #if IS_ENABLED(CONFIG_IPV6)
-	setup_timer(&br->ip6_querier.timer, br_ip6_multicast_querier_expired,
-		    (unsigned long)br);
-	setup_timer(&br->ip6_query.timer, br_ip6_multicast_query_expired,
+	setup_timer(&br->ip6_other_query.timer,
+		    br_ip6_multicast_querier_expired, (unsigned long)br);
+	setup_timer(&br->ip6_own_query.timer, br_ip6_multicast_query_expired,
 		    (unsigned long)br);
 #endif
 }
 
 static void __br_multicast_open(struct net_bridge *br,
-				struct bridge_mcast_query *query)
+				struct bridge_mcast_own_query *query)
 {
 	query->startup_sent = 0;
 
@@ -1773,9 +1896,9 @@ static void __br_multicast_open(struct net_bridge *br,
 
 void br_multicast_open(struct net_bridge *br)
 {
-	__br_multicast_open(br, &br->ip4_query);
+	__br_multicast_open(br, &br->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
-	__br_multicast_open(br, &br->ip6_query);
+	__br_multicast_open(br, &br->ip6_own_query);
 #endif
 }
 
@@ -1788,11 +1911,11 @@ void br_multicast_stop(struct net_bridge *br)
 	int i;
 
 	del_timer_sync(&br->multicast_router_timer);
-	del_timer_sync(&br->ip4_querier.timer);
-	del_timer_sync(&br->ip4_query.timer);
+	del_timer_sync(&br->ip4_other_query.timer);
+	del_timer_sync(&br->ip4_own_query.timer);
 #if IS_ENABLED(CONFIG_IPV6)
-	del_timer_sync(&br->ip6_querier.timer);
-	del_timer_sync(&br->ip6_query.timer);
+	del_timer_sync(&br->ip6_other_query.timer);
+	del_timer_sync(&br->ip6_own_query.timer);
 #endif
 
 	spin_lock_bh(&br->multicast_lock);
@@ -1896,7 +2019,7 @@ unlock:
 }
 
 static void br_multicast_start_querier(struct net_bridge *br,
-				       struct bridge_mcast_query *query)
+				       struct bridge_mcast_own_query *query)
 {
 	struct net_bridge_port *port;
 
@@ -1907,11 +2030,11 @@ static void br_multicast_start_querier(struct net_bridge *br,
 		    port->state == BR_STATE_BLOCKING)
 			continue;
 
-		if (query == &br->ip4_query)
-			br_multicast_enable(&port->ip4_query);
+		if (query == &br->ip4_own_query)
+			br_multicast_enable(&port->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
 		else
-			br_multicast_enable(&port->ip6_query);
+			br_multicast_enable(&port->ip6_own_query);
 #endif
 	}
 }
@@ -1947,9 +2070,9 @@ rollback:
 			goto rollback;
 	}
 
-	br_multicast_start_querier(br, &br->ip4_query);
+	br_multicast_start_querier(br, &br->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
-	br_multicast_start_querier(br, &br->ip6_query);
+	br_multicast_start_querier(br, &br->ip6_own_query);
 #endif
 
 unlock:
@@ -1974,16 +2097,16 @@ int br_multicast_set_querier(struct net_bridge *br, unsigned long val)
 
 	max_delay = br->multicast_query_response_interval;
 
-	if (!timer_pending(&br->ip4_querier.timer))
-		br->ip4_querier.delay_time = jiffies + max_delay;
+	if (!timer_pending(&br->ip4_other_query.timer))
+		br->ip4_other_query.delay_time = jiffies + max_delay;
 
-	br_multicast_start_querier(br, &br->ip4_query);
+	br_multicast_start_querier(br, &br->ip4_own_query);
 
 #if IS_ENABLED(CONFIG_IPV6)
-	if (!timer_pending(&br->ip6_querier.timer))
-		br->ip6_querier.delay_time = jiffies + max_delay;
+	if (!timer_pending(&br->ip6_other_query.timer))
+		br->ip6_other_query.delay_time = jiffies + max_delay;
 
-	br_multicast_start_querier(br, &br->ip6_query);
+	br_multicast_start_querier(br, &br->ip6_own_query);
 #endif
 
 unlock:
@@ -1998,7 +2121,7 @@ int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val)
 	u32 old;
 	struct net_bridge_mdb_htable *mdb;
 
-	spin_lock(&br->multicast_lock);
+	spin_lock_bh(&br->multicast_lock);
 	if (!netif_running(br->dev))
 		goto unlock;
 
@@ -2030,7 +2153,113 @@ rollback:
 	}
 
 unlock:
-	spin_unlock(&br->multicast_lock);
+	spin_unlock_bh(&br->multicast_lock);
 
 	return err;
 }
+
+/**
+ * br_multicast_list_adjacent - Returns snooped multicast addresses
+ * @dev:	The bridge port adjacent to which to retrieve addresses
+ * @br_ip_list:	The list to store found, snooped multicast IP addresses in
+ *
+ * Creates a list of IP addresses (struct br_ip_list) sensed by the multicast
+ * snooping feature on all bridge ports of dev's bridge device, excluding
+ * the addresses from dev itself.
+ *
+ * Returns the number of items added to br_ip_list.
+ *
+ * Notes:
+ * - br_ip_list needs to be initialized by caller
+ * - br_ip_list might contain duplicates in the end
+ *   (needs to be taken care of by caller)
+ * - br_ip_list needs to be freed by caller
+ */
+int br_multicast_list_adjacent(struct net_device *dev,
+			       struct list_head *br_ip_list)
+{
+	struct net_bridge *br;
+	struct net_bridge_port *port;
+	struct net_bridge_port_group *group;
+	struct br_ip_list *entry;
+	int count = 0;
+
+	rcu_read_lock();
+	if (!br_ip_list || !br_port_exists(dev))
+		goto unlock;
+
+	port = br_port_get_rcu(dev);
+	if (!port || !port->br)
+		goto unlock;
+
+	br = port->br;
+
+	list_for_each_entry_rcu(port, &br->port_list, list) {
+		if (!port->dev || port->dev == dev)
+			continue;
+
+		hlist_for_each_entry_rcu(group, &port->mglist, mglist) {
+			entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+			if (!entry)
+				goto unlock;
+
+			entry->addr = group->addr;
+			list_add(&entry->list, br_ip_list);
+			count++;
+		}
+	}
+
+unlock:
+	rcu_read_unlock();
+	return count;
+}
+EXPORT_SYMBOL_GPL(br_multicast_list_adjacent);
+
+/**
+ * br_multicast_has_querier_adjacent - Checks for a querier behind a bridge port
+ * @dev: The bridge port adjacent to which to check for a querier
+ * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6
+ *
+ * Checks whether the given interface has a bridge on top and if so returns
+ * true if a selected querier is behind one of the other ports of this
+ * bridge. Otherwise returns false.
+ */
+bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto)
+{
+	struct net_bridge *br;
+	struct net_bridge_port *port;
+	bool ret = false;
+
+	rcu_read_lock();
+	if (!br_port_exists(dev))
+		goto unlock;
+
+	port = br_port_get_rcu(dev);
+	if (!port || !port->br)
+		goto unlock;
+
+	br = port->br;
+
+	switch (proto) {
+	case ETH_P_IP:
+		if (!timer_pending(&br->ip4_other_query.timer) ||
+		    rcu_dereference(br->ip4_querier.port) == port)
+			goto unlock;
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case ETH_P_IPV6:
+		if (!timer_pending(&br->ip6_other_query.timer) ||
+		    rcu_dereference(br->ip6_querier.port) == port)
+			goto unlock;
+		break;
+#endif
+	default:
+		goto unlock;
+	}
+
+	ret = true;
+unlock:
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent);
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 80cad2cf02a..a615264cf01 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -167,7 +167,7 @@ void br_netfilter_rtable_init(struct net_bridge *br)
 	rt->dst.dev = br->dev;
 	rt->dst.path = &rt->dst;
 	dst_init_metrics(&rt->dst, br_dst_default_metrics, true);
-	rt->dst.flags	= DST_NOXFRM | DST_NOPEER | DST_FAKE_RTABLE;
+	rt->dst.flags	= DST_NOXFRM | DST_FAKE_RTABLE;
 	rt->dst.ops = &fake_dst_ops;
 }
 
@@ -506,7 +506,7 @@ bridged_dnat:
 					       1);
 				return 0;
 			}
-			memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN);
+			ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
 			skb->pkt_type = PACKET_HOST;
 		}
 	} else {
@@ -535,7 +535,7 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct
 	if (brnf_pass_vlan_indev == 0 || !vlan_tx_tag_present(skb))
 		return br;
 
-	vlan = __vlan_find_dev_deep(br, skb->vlan_proto,
+	vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto,
 				    vlan_tx_tag_get(skb) & VLAN_VID_MASK);
 
 	return vlan ? vlan : br;
@@ -859,12 +859,12 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 	return NF_STOLEN;
 }
 
-#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4)
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
 static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 {
 	int ret;
 
-	if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) &&
+	if (skb->protocol == htons(ETH_P_IP) &&
 	    skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu &&
 	    !skb_is_gso(skb)) {
 		if (br_parse_ip_options(skb))
@@ -1001,7 +1001,7 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
 #ifdef CONFIG_SYSCTL
 static
 int brnf_sysctl_call_tables(struct ctl_table *ctl, int write,
-			    void __user * buffer, size_t * lenp, loff_t * ppos)
+			    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
 
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index f75d92e4f96..26edb518b83 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -195,8 +195,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port)
 	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	rtnl_set_sk_err(net, RTNLGRP_LINK, err);
 }
 
 
@@ -329,6 +328,7 @@ static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[],
 static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 {
 	int err;
+	unsigned long old_flags = p->flags;
 
 	br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
 	br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
@@ -354,6 +354,8 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 		if (err)
 			return err;
 	}
+
+	br_port_flags_change(p, old_flags ^ p->flags);
 	return 0;
 }
 
@@ -373,7 +375,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
 
 	p = br_port_get_rtnl(dev);
 	/* We want to accept dev as bridge itself if the AF_SPEC
-	 * is set to see if someone is setting vlan info on the brigde
+	 * is set to see if someone is setting vlan info on the bridge
 	 */
 	if (!p && !afspec)
 		return -EINVAL;
@@ -389,7 +391,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
 			err = br_setport(p, tb);
 			spin_unlock_bh(&p->br->lock);
 		} else {
-			/* Binary compatability with old RSTP */
+			/* Binary compatibility with old RSTP */
 			if (nla_len(protinfo) < sizeof(u8))
 				return -EINVAL;
 
@@ -446,6 +448,20 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 	return 0;
 }
 
+static int br_dev_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[])
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	if (tb[IFLA_ADDRESS]) {
+		spin_lock_bh(&br->lock);
+		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
+		spin_unlock_bh(&br->lock);
+	}
+
+	return register_netdevice(dev);
+}
+
 static size_t br_get_link_af_size(const struct net_device *dev)
 {
 	struct net_port_vlans *pv;
@@ -474,6 +490,7 @@ struct rtnl_link_ops br_link_ops __read_mostly = {
 	.priv_size	= sizeof(struct net_bridge),
 	.setup		= br_dev_setup,
 	.validate	= br_validate,
+	.newlink	= br_dev_newlink,
 	.dellink	= br_dev_delete,
 };
 
@@ -482,9 +499,7 @@ int __init br_netlink_init(void)
 	int err;
 
 	br_mdb_init();
-	err = rtnl_af_register(&br_af_ops);
-	if (err)
-		goto out;
+	rtnl_af_register(&br_af_ops);
 
 	err = rtnl_link_register(&br_link_ops);
 	if (err)
@@ -494,7 +509,6 @@ int __init br_netlink_init(void)
 
 out_af:
 	rtnl_af_unregister(&br_af_ops);
-out:
 	br_mdb_uninit();
 	return err;
 }
diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c
deleted file mode 100644
index 2998dd1769a..00000000000
--- a/net/bridge/br_notify.c
+++ /dev/null
@@ -1,118 +0,0 @@
-/*
- *	Device event handling
- *	Linux ethernet bridge
- *
- *	Authors:
- *	Lennert Buytenhek		<buytenh@gnu.org>
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/rtnetlink.h>
-#include <net/net_namespace.h>
-
-#include "br_private.h"
-
-static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr);
-
-struct notifier_block br_device_notifier = {
-	.notifier_call = br_device_event
-};
-
-/*
- * Handle changes in state of network devices enslaved to a bridge.
- *
- * Note: don't care about up/down if bridge itself is down, because
- *     port state is checked when bridge is brought up.
- */
-static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr)
-{
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct net_bridge_port *p;
-	struct net_bridge *br;
-	bool changed_addr;
-	int err;
-
-	/* register of bridge completed, add sysfs entries */
-	if ((dev->priv_flags & IFF_EBRIDGE) && event == NETDEV_REGISTER) {
-		br_sysfs_addbr(dev);
-		return NOTIFY_DONE;
-	}
-
-	/* not a port of a bridge */
-	p = br_port_get_rtnl(dev);
-	if (!p)
-		return NOTIFY_DONE;
-
-	br = p->br;
-
-	switch (event) {
-	case NETDEV_CHANGEMTU:
-		dev_set_mtu(br->dev, br_min_mtu(br));
-		break;
-
-	case NETDEV_CHANGEADDR:
-		spin_lock_bh(&br->lock);
-		br_fdb_changeaddr(p, dev->dev_addr);
-		changed_addr = br_stp_recalculate_bridge_id(br);
-		spin_unlock_bh(&br->lock);
-
-		if (changed_addr)
-			call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
-
-		break;
-
-	case NETDEV_CHANGE:
-		br_port_carrier_check(p);
-		break;
-
-	case NETDEV_FEAT_CHANGE:
-		netdev_update_features(br->dev);
-		break;
-
-	case NETDEV_DOWN:
-		spin_lock_bh(&br->lock);
-		if (br->dev->flags & IFF_UP)
-			br_stp_disable_port(p);
-		spin_unlock_bh(&br->lock);
-		break;
-
-	case NETDEV_UP:
-		if (netif_running(br->dev) && netif_oper_up(dev)) {
-			spin_lock_bh(&br->lock);
-			br_stp_enable_port(p);
-			spin_unlock_bh(&br->lock);
-		}
-		break;
-
-	case NETDEV_UNREGISTER:
-		br_del_if(br, dev);
-		break;
-
-	case NETDEV_CHANGENAME:
-		err = br_sysfs_renameif(p);
-		if (err)
-			return notifier_from_errno(err);
-		break;
-
-	case NETDEV_PRE_TYPE_CHANGE:
-		/* Forbid underlaying device to change its type. */
-		return NOTIFY_BAD;
-
-	case NETDEV_RESEND_IGMP:
-		/* Propagate to master device */
-		call_netdevice_notifiers(event, br->dev);
-		break;
-	}
-
-	/* Events that may cause spanning tree to refresh */
-	if (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
-	    event == NETDEV_CHANGE || event == NETDEV_DOWN)
-		br_ifinfo_notify(RTM_NEWLINK, p);
-
-	return NOTIFY_DONE;
-}
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 045d56eaeca..23caf5b0309 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -35,6 +35,8 @@
 #define BR_GROUPFWD_DEFAULT	0
 /* Don't allow forwarding control protocols like STP and LLDP */
 #define BR_GROUPFWD_RESTRICTED	0x4007u
+/* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */
+#define BR_GROUPFWD_8021AD	0xB801u
 
 /* Path to usermode spanning tree program */
 #define BR_STP_PROG	"/sbin/bridge-stp"
@@ -46,38 +48,32 @@ typedef __u16 port_id;
 struct bridge_id
 {
 	unsigned char	prio[2];
-	unsigned char	addr[6];
+	unsigned char	addr[ETH_ALEN];
 };
 
 struct mac_addr
 {
-	unsigned char	addr[6];
-};
-
-struct br_ip
-{
-	union {
-		__be32	ip4;
-#if IS_ENABLED(CONFIG_IPV6)
-		struct in6_addr ip6;
-#endif
-	} u;
-	__be16		proto;
-	__u16		vid;
+	unsigned char	addr[ETH_ALEN];
 };
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 /* our own querier */
-struct bridge_mcast_query {
+struct bridge_mcast_own_query {
 	struct timer_list	timer;
 	u32			startup_sent;
 };
 
 /* other querier */
-struct bridge_mcast_querier {
+struct bridge_mcast_other_query {
 	struct timer_list		timer;
 	unsigned long			delay_time;
 };
+
+/* selected querier */
+struct bridge_mcast_querier {
+	struct br_ip addr;
+	struct net_bridge_port __rcu	*port;
+};
 #endif
 
 struct net_port_vlans {
@@ -104,6 +100,7 @@ struct net_bridge_fdb_entry
 	mac_addr			addr;
 	unsigned char			is_local;
 	unsigned char			is_static;
+	unsigned char			added_by_user;
 	__u16				vlan_id;
 };
 
@@ -173,11 +170,13 @@ struct net_bridge_port
 #define BR_ADMIN_COST		0x00000010
 #define BR_LEARNING		0x00000020
 #define BR_FLOOD		0x00000040
+#define BR_AUTO_MASK (BR_FLOOD | BR_LEARNING)
+#define BR_PROMISC		0x00000080
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
-	struct bridge_mcast_query	ip4_query;
+	struct bridge_mcast_own_query	ip4_own_query;
 #if IS_ENABLED(CONFIG_IPV6)
-	struct bridge_mcast_query	ip6_query;
+	struct bridge_mcast_own_query	ip6_own_query;
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 	unsigned char			multicast_router;
 	struct timer_list		multicast_router_timer;
@@ -197,6 +196,9 @@ struct net_bridge_port
 #endif
 };
 
+#define br_auto_port(p) ((p)->flags & BR_AUTO_MASK)
+#define br_promisc_port(p) ((p)->flags & BR_PROMISC)
+
 #define br_port_exists(dev) (dev->priv_flags & IFF_BRIDGE_PORT)
 
 static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev)
@@ -210,21 +212,13 @@ static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device *
 		rtnl_dereference(dev->rx_handler_data) : NULL;
 }
 
-struct br_cpu_netstats {
-	u64			rx_packets;
-	u64			rx_bytes;
-	u64			tx_packets;
-	u64			tx_bytes;
-	struct u64_stats_sync	syncp;
-};
-
 struct net_bridge
 {
 	spinlock_t			lock;
 	struct list_head		port_list;
 	struct net_device		*dev;
 
-	struct br_cpu_netstats __percpu *stats;
+	struct pcpu_sw_netstats		__percpu *stats;
 	spinlock_t			hash_lock;
 	struct hlist_head		hash[BR_HASH_SIZE];
 #ifdef CONFIG_BRIDGE_NETFILTER
@@ -234,6 +228,7 @@ struct net_bridge
 	bool				nf_call_arptables;
 #endif
 	u16				group_fwd_mask;
+	u16				group_fwd_mask_required;
 
 	/* STP */
 	bridge_id			designated_root;
@@ -248,6 +243,7 @@ struct net_bridge
 	unsigned long			bridge_forward_delay;
 
 	u8				group_addr[ETH_ALEN];
+	bool				group_addr_set;
 	u16				root_port;
 
 	enum {
@@ -284,11 +280,13 @@ struct net_bridge
 	struct hlist_head		router_list;
 
 	struct timer_list		multicast_router_timer;
+	struct bridge_mcast_other_query	ip4_other_query;
+	struct bridge_mcast_own_query	ip4_own_query;
 	struct bridge_mcast_querier	ip4_querier;
-	struct bridge_mcast_query	ip4_query;
 #if IS_ENABLED(CONFIG_IPV6)
+	struct bridge_mcast_other_query	ip6_other_query;
+	struct bridge_mcast_own_query	ip6_own_query;
 	struct bridge_mcast_querier	ip6_querier;
-	struct bridge_mcast_query	ip6_query;
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 #endif
 
@@ -297,8 +295,10 @@ struct net_bridge
 	struct timer_list		topology_change_timer;
 	struct timer_list		gc_timer;
 	struct kobject			*ifobj;
+	u32				auto_cnt;
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
 	u8				vlan_enabled;
+	__be16				vlan_proto;
 	struct net_port_vlans __rcu	*vlan_info;
 #endif
 };
@@ -334,8 +334,6 @@ struct br_input_skb_cb {
 #define br_debug(br, format, args...)			\
 	pr_debug("%s: " format,  (br)->dev->name, ##args)
 
-extern struct notifier_block br_device_notifier;
-
 /* called under bridge lock */
 static inline int br_is_root_bridge(const struct net_bridge *br)
 {
@@ -356,7 +354,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
 		netpoll_send_skb(np, skb);
 }
 
-int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp);
+int br_netpoll_enable(struct net_bridge_port *p);
 void br_netpoll_disable(struct net_bridge_port *p);
 #else
 static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
@@ -364,7 +362,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
 {
 }
 
-static inline int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
+static inline int br_netpoll_enable(struct net_bridge_port *p)
 {
 	return 0;
 }
@@ -378,6 +376,9 @@ static inline void br_netpoll_disable(struct net_bridge_port *p)
 int br_fdb_init(void);
 void br_fdb_fini(void);
 void br_fdb_flush(struct net_bridge *br);
+void br_fdb_find_delete_local(struct net_bridge *br,
+			      const struct net_bridge_port *p,
+			      const unsigned char *addr, u16 vid);
 void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr);
 void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr);
 void br_fdb_cleanup(unsigned long arg);
@@ -391,8 +392,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, unsigned long count,
 int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
 		  const unsigned char *addr, u16 vid);
 void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
-		   const unsigned char *addr, u16 vid);
-int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vid);
+		   const unsigned char *addr, u16 vid, bool added_by_user);
 
 int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 		  struct net_device *dev, const unsigned char *addr);
@@ -400,6 +400,8 @@ int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev,
 	       const unsigned char *addr, u16 nlh_flags);
 int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		struct net_device *dev, int idx);
+int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p);
+void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p);
 
 /* br_forward.c */
 void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb);
@@ -415,12 +417,13 @@ void br_flood_forward(struct net_bridge *br, struct sk_buff *skb,
 void br_port_carrier_check(struct net_bridge_port *p);
 int br_add_bridge(struct net *net, const char *name);
 int br_del_bridge(struct net *net, const char *name);
-void br_net_exit(struct net *net);
 int br_add_if(struct net_bridge *br, struct net_device *dev);
 int br_del_if(struct net_bridge *br, struct net_device *dev);
 int br_min_mtu(const struct net_bridge *br);
 netdev_features_t br_features_recompute(struct net_bridge *br,
 					netdev_features_t features);
+void br_port_flags_change(struct net_bridge_port *port, unsigned long mask);
+void br_manage_promisc(struct net_bridge *br);
 
 /* br_input.c */
 int br_handle_frame_finish(struct sk_buff *skb);
@@ -491,7 +494,7 @@ static inline bool br_multicast_is_router(struct net_bridge *br)
 
 static inline bool
 __br_multicast_querier_exists(struct net_bridge *br,
-			      struct bridge_mcast_querier *querier)
+			      struct bridge_mcast_other_query *querier)
 {
 	return time_is_before_jiffies(querier->delay_time) &&
 	       (br->multicast_querier || timer_pending(&querier->timer));
@@ -502,10 +505,10 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
 {
 	switch (eth->h_proto) {
 	case (htons(ETH_P_IP)):
-		return __br_multicast_querier_exists(br, &br->ip4_querier);
+		return __br_multicast_querier_exists(br, &br->ip4_other_query);
 #if IS_ENABLED(CONFIG_IPV6)
 	case (htons(ETH_P_IPV6)):
-		return __br_multicast_querier_exists(br, &br->ip6_querier);
+		return __br_multicast_querier_exists(br, &br->ip6_other_query);
 #endif
 	default:
 		return false;
@@ -587,13 +590,18 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 			struct sk_buff *skb, u16 *vid);
 bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v,
 		       const struct sk_buff *skb);
+bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid);
 struct sk_buff *br_handle_vlan(struct net_bridge *br,
 			       const struct net_port_vlans *v,
 			       struct sk_buff *skb);
 int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
 int br_vlan_delete(struct net_bridge *br, u16 vid);
 void br_vlan_flush(struct net_bridge *br);
+bool br_vlan_find(struct net_bridge *br, u16 vid);
+void br_recalculate_fwd_mask(struct net_bridge *br);
 int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
+int br_vlan_set_proto(struct net_bridge *br, unsigned long val);
+void br_vlan_init(struct net_bridge *br);
 int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
 int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
 void nbp_vlan_flush(struct net_bridge_port *port);
@@ -637,6 +645,10 @@ static inline u16 br_get_pvid(const struct net_port_vlans *v)
 	return v->pvid ?: VLAN_N_VID;
 }
 
+static inline int br_vlan_enabled(struct net_bridge *br)
+{
+	return br->vlan_enabled;
+}
 #else
 static inline bool br_allowed_ingress(struct net_bridge *br,
 				      struct net_port_vlans *v,
@@ -653,6 +665,12 @@ static inline bool br_allowed_egress(struct net_bridge *br,
 	return true;
 }
 
+static inline bool br_should_learn(struct net_bridge_port *p,
+				   struct sk_buff *skb, u16 *vid)
+{
+	return true;
+}
+
 static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
 					     const struct net_port_vlans *v,
 					     struct sk_buff *skb)
@@ -674,6 +692,19 @@ static inline void br_vlan_flush(struct net_bridge *br)
 {
 }
 
+static inline bool br_vlan_find(struct net_bridge *br, u16 vid)
+{
+	return false;
+}
+
+static inline void br_recalculate_fwd_mask(struct net_bridge *br)
+{
+}
+
+static inline void br_vlan_init(struct net_bridge *br)
+{
+}
+
 static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
 {
 	return -EOPNOTSUPP;
@@ -712,6 +743,11 @@ static inline u16 br_get_pvid(const struct net_port_vlans *v)
 {
 	return VLAN_N_VID;	/* Returns invalid vid */
 }
+
+static inline int br_vlan_enabled(struct net_bridge *br)
+{
+	return 0;
+}
 #endif
 
 /* br_netfilter.c */
@@ -721,7 +757,7 @@ void br_netfilter_fini(void);
 void br_netfilter_rtable_init(struct net_bridge *);
 #else
 #define br_netfilter_init()	(0)
-#define br_netfilter_fini()	do { } while(0)
+#define br_netfilter_fini()	do { } while (0)
 #define br_netfilter_rtable_init(x)
 #endif
 
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 656a6f3e40d..189ba1e7d85 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -194,6 +194,8 @@ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr)
 
 	wasroot = br_is_root_bridge(br);
 
+	br_fdb_change_mac_address(br, addr);
+
 	memcpy(oldaddr, br->bridge_id.addr, ETH_ALEN);
 	memcpy(br->bridge_id.addr, addr, ETH_ALEN);
 	memcpy(br->dev->dev_addr, addr, ETH_ALEN);
diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index 950663d4d33..558c46d19e0 100644
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -110,7 +110,7 @@ static void br_tcn_timer_expired(unsigned long arg)
 	if (!br_is_root_bridge(br) && (br->dev->flags & IFF_UP)) {
 		br_transmit_tcn(br);
 
-		mod_timer(&br->tcn_timer,jiffies + br->bridge_hello_time);
+		mod_timer(&br->tcn_timer, jiffies + br->bridge_hello_time);
 	}
 	spin_unlock(&br->lock);
 }
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index 3b9637fb793..c9e2572b15f 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -49,53 +49,51 @@ static ssize_t store_bridge_parm(struct device *d,
 }
 
 
-static ssize_t show_forward_delay(struct device *d,
+static ssize_t forward_delay_show(struct device *d,
 				  struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
 	return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->forward_delay));
 }
 
-static ssize_t store_forward_delay(struct device *d,
+static ssize_t forward_delay_store(struct device *d,
 				   struct device_attribute *attr,
 				   const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, br_set_forward_delay);
 }
-static DEVICE_ATTR(forward_delay, S_IRUGO | S_IWUSR,
-		   show_forward_delay, store_forward_delay);
+static DEVICE_ATTR_RW(forward_delay);
 
-static ssize_t show_hello_time(struct device *d, struct device_attribute *attr,
+static ssize_t hello_time_show(struct device *d, struct device_attribute *attr,
 			       char *buf)
 {
 	return sprintf(buf, "%lu\n",
 		       jiffies_to_clock_t(to_bridge(d)->hello_time));
 }
 
-static ssize_t store_hello_time(struct device *d,
+static ssize_t hello_time_store(struct device *d,
 				struct device_attribute *attr, const char *buf,
 				size_t len)
 {
 	return store_bridge_parm(d, buf, len, br_set_hello_time);
 }
-static DEVICE_ATTR(hello_time, S_IRUGO | S_IWUSR, show_hello_time,
-		   store_hello_time);
+static DEVICE_ATTR_RW(hello_time);
 
-static ssize_t show_max_age(struct device *d, struct device_attribute *attr,
+static ssize_t max_age_show(struct device *d, struct device_attribute *attr,
 			    char *buf)
 {
 	return sprintf(buf, "%lu\n",
 		       jiffies_to_clock_t(to_bridge(d)->max_age));
 }
 
-static ssize_t store_max_age(struct device *d, struct device_attribute *attr,
+static ssize_t max_age_store(struct device *d, struct device_attribute *attr,
 			     const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, br_set_max_age);
 }
-static DEVICE_ATTR(max_age, S_IRUGO | S_IWUSR, show_max_age, store_max_age);
+static DEVICE_ATTR_RW(max_age);
 
-static ssize_t show_ageing_time(struct device *d,
+static ssize_t ageing_time_show(struct device *d,
 				struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -108,16 +106,15 @@ static int set_ageing_time(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_ageing_time(struct device *d,
+static ssize_t ageing_time_store(struct device *d,
 				 struct device_attribute *attr,
 				 const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_ageing_time);
 }
-static DEVICE_ATTR(ageing_time, S_IRUGO | S_IWUSR, show_ageing_time,
-		   store_ageing_time);
+static DEVICE_ATTR_RW(ageing_time);
 
-static ssize_t show_stp_state(struct device *d,
+static ssize_t stp_state_show(struct device *d,
 			      struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -125,7 +122,7 @@ static ssize_t show_stp_state(struct device *d,
 }
 
 
-static ssize_t store_stp_state(struct device *d,
+static ssize_t stp_state_store(struct device *d,
 			       struct device_attribute *attr, const char *buf,
 			       size_t len)
 {
@@ -147,20 +144,21 @@ static ssize_t store_stp_state(struct device *d,
 
 	return len;
 }
-static DEVICE_ATTR(stp_state, S_IRUGO | S_IWUSR, show_stp_state,
-		   store_stp_state);
+static DEVICE_ATTR_RW(stp_state);
 
-static ssize_t show_group_fwd_mask(struct device *d,
-			      struct device_attribute *attr, char *buf)
+static ssize_t group_fwd_mask_show(struct device *d,
+				   struct device_attribute *attr,
+				   char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
 	return sprintf(buf, "%#x\n", br->group_fwd_mask);
 }
 
 
-static ssize_t store_group_fwd_mask(struct device *d,
-			       struct device_attribute *attr, const char *buf,
-			       size_t len)
+static ssize_t group_fwd_mask_store(struct device *d,
+				    struct device_attribute *attr,
+				    const char *buf,
+				    size_t len)
 {
 	struct net_bridge *br = to_bridge(d);
 	char *endp;
@@ -180,10 +178,9 @@ static ssize_t store_group_fwd_mask(struct device *d,
 
 	return len;
 }
-static DEVICE_ATTR(group_fwd_mask, S_IRUGO | S_IWUSR, show_group_fwd_mask,
-		   store_group_fwd_mask);
+static DEVICE_ATTR_RW(group_fwd_mask);
 
-static ssize_t show_priority(struct device *d, struct device_attribute *attr,
+static ssize_t priority_show(struct device *d, struct device_attribute *attr,
 			     char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -197,93 +194,91 @@ static int set_priority(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_priority(struct device *d, struct device_attribute *attr,
-			       const char *buf, size_t len)
+static ssize_t priority_store(struct device *d, struct device_attribute *attr,
+			      const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_priority);
 }
-static DEVICE_ATTR(priority, S_IRUGO | S_IWUSR, show_priority, store_priority);
+static DEVICE_ATTR_RW(priority);
 
-static ssize_t show_root_id(struct device *d, struct device_attribute *attr,
+static ssize_t root_id_show(struct device *d, struct device_attribute *attr,
 			    char *buf)
 {
 	return br_show_bridge_id(buf, &to_bridge(d)->designated_root);
 }
-static DEVICE_ATTR(root_id, S_IRUGO, show_root_id, NULL);
+static DEVICE_ATTR_RO(root_id);
 
-static ssize_t show_bridge_id(struct device *d, struct device_attribute *attr,
+static ssize_t bridge_id_show(struct device *d, struct device_attribute *attr,
 			      char *buf)
 {
 	return br_show_bridge_id(buf, &to_bridge(d)->bridge_id);
 }
-static DEVICE_ATTR(bridge_id, S_IRUGO, show_bridge_id, NULL);
+static DEVICE_ATTR_RO(bridge_id);
 
-static ssize_t show_root_port(struct device *d, struct device_attribute *attr,
+static ssize_t root_port_show(struct device *d, struct device_attribute *attr,
 			      char *buf)
 {
 	return sprintf(buf, "%d\n", to_bridge(d)->root_port);
 }
-static DEVICE_ATTR(root_port, S_IRUGO, show_root_port, NULL);
+static DEVICE_ATTR_RO(root_port);
 
-static ssize_t show_root_path_cost(struct device *d,
+static ssize_t root_path_cost_show(struct device *d,
 				   struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%d\n", to_bridge(d)->root_path_cost);
 }
-static DEVICE_ATTR(root_path_cost, S_IRUGO, show_root_path_cost, NULL);
+static DEVICE_ATTR_RO(root_path_cost);
 
-static ssize_t show_topology_change(struct device *d,
+static ssize_t topology_change_show(struct device *d,
 				    struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%d\n", to_bridge(d)->topology_change);
 }
-static DEVICE_ATTR(topology_change, S_IRUGO, show_topology_change, NULL);
+static DEVICE_ATTR_RO(topology_change);
 
-static ssize_t show_topology_change_detected(struct device *d,
+static ssize_t topology_change_detected_show(struct device *d,
 					     struct device_attribute *attr,
 					     char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
 	return sprintf(buf, "%d\n", br->topology_change_detected);
 }
-static DEVICE_ATTR(topology_change_detected, S_IRUGO,
-		   show_topology_change_detected, NULL);
+static DEVICE_ATTR_RO(topology_change_detected);
 
-static ssize_t show_hello_timer(struct device *d,
+static ssize_t hello_timer_show(struct device *d,
 				struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
 	return sprintf(buf, "%ld\n", br_timer_value(&br->hello_timer));
 }
-static DEVICE_ATTR(hello_timer, S_IRUGO, show_hello_timer, NULL);
+static DEVICE_ATTR_RO(hello_timer);
 
-static ssize_t show_tcn_timer(struct device *d, struct device_attribute *attr,
+static ssize_t tcn_timer_show(struct device *d, struct device_attribute *attr,
 			      char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
 	return sprintf(buf, "%ld\n", br_timer_value(&br->tcn_timer));
 }
-static DEVICE_ATTR(tcn_timer, S_IRUGO, show_tcn_timer, NULL);
+static DEVICE_ATTR_RO(tcn_timer);
 
-static ssize_t show_topology_change_timer(struct device *d,
+static ssize_t topology_change_timer_show(struct device *d,
 					  struct device_attribute *attr,
 					  char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
 	return sprintf(buf, "%ld\n", br_timer_value(&br->topology_change_timer));
 }
-static DEVICE_ATTR(topology_change_timer, S_IRUGO, show_topology_change_timer,
-		   NULL);
+static DEVICE_ATTR_RO(topology_change_timer);
 
-static ssize_t show_gc_timer(struct device *d, struct device_attribute *attr,
+static ssize_t gc_timer_show(struct device *d, struct device_attribute *attr,
 			     char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
 	return sprintf(buf, "%ld\n", br_timer_value(&br->gc_timer));
 }
-static DEVICE_ATTR(gc_timer, S_IRUGO, show_gc_timer, NULL);
+static DEVICE_ATTR_RO(gc_timer);
 
-static ssize_t show_group_addr(struct device *d,
+static ssize_t group_addr_show(struct device *d,
 			       struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -293,7 +288,7 @@ static ssize_t show_group_addr(struct device *d,
 		       br->group_addr[4], br->group_addr[5]);
 }
 
-static ssize_t store_group_addr(struct device *d,
+static ssize_t group_addr_store(struct device *d,
 				struct device_attribute *attr,
 				const char *buf, size_t len)
 {
@@ -317,17 +312,25 @@ static ssize_t store_group_addr(struct device *d,
 	    new_addr[5] == 3)		/* 802.1X PAE address */
 		return -EINVAL;
 
+	if (!rtnl_trylock())
+		return restart_syscall();
+
 	spin_lock_bh(&br->lock);
 	for (i = 0; i < 6; i++)
 		br->group_addr[i] = new_addr[i];
 	spin_unlock_bh(&br->lock);
+
+	br->group_addr_set = true;
+	br_recalculate_fwd_mask(br);
+
+	rtnl_unlock();
+
 	return len;
 }
 
-static DEVICE_ATTR(group_addr, S_IRUGO | S_IWUSR,
-		   show_group_addr, store_group_addr);
+static DEVICE_ATTR_RW(group_addr);
 
-static ssize_t store_flush(struct device *d,
+static ssize_t flush_store(struct device *d,
 			   struct device_attribute *attr,
 			   const char *buf, size_t len)
 {
@@ -339,26 +342,25 @@ static ssize_t store_flush(struct device *d,
 	br_fdb_flush(br);
 	return len;
 }
-static DEVICE_ATTR(flush, S_IWUSR, NULL, store_flush);
+static DEVICE_ATTR_WO(flush);
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
-static ssize_t show_multicast_router(struct device *d,
+static ssize_t multicast_router_show(struct device *d,
 				     struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
 	return sprintf(buf, "%d\n", br->multicast_router);
 }
 
-static ssize_t store_multicast_router(struct device *d,
+static ssize_t multicast_router_store(struct device *d,
 				      struct device_attribute *attr,
 				      const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, br_multicast_set_router);
 }
-static DEVICE_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router,
-		   store_multicast_router);
+static DEVICE_ATTR_RW(multicast_router);
 
-static ssize_t show_multicast_snooping(struct device *d,
+static ssize_t multicast_snooping_show(struct device *d,
 				       struct device_attribute *attr,
 				       char *buf)
 {
@@ -366,18 +368,17 @@ static ssize_t show_multicast_snooping(struct device *d,
 	return sprintf(buf, "%d\n", !br->multicast_disabled);
 }
 
-static ssize_t store_multicast_snooping(struct device *d,
+static ssize_t multicast_snooping_store(struct device *d,
 					struct device_attribute *attr,
 					const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, br_multicast_toggle);
 }
-static DEVICE_ATTR(multicast_snooping, S_IRUGO | S_IWUSR,
-		   show_multicast_snooping, store_multicast_snooping);
+static DEVICE_ATTR_RW(multicast_snooping);
 
-static ssize_t show_multicast_query_use_ifaddr(struct device *d,
-				      struct device_attribute *attr,
-				      char *buf)
+static ssize_t multicast_query_use_ifaddr_show(struct device *d,
+					       struct device_attribute *attr,
+					       char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
 	return sprintf(buf, "%d\n", br->multicast_query_use_ifaddr);
@@ -390,17 +391,15 @@ static int set_query_use_ifaddr(struct net_bridge *br, unsigned long val)
 }
 
 static ssize_t
-store_multicast_query_use_ifaddr(struct device *d,
+multicast_query_use_ifaddr_store(struct device *d,
 				 struct device_attribute *attr,
 				 const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_query_use_ifaddr);
 }
-static DEVICE_ATTR(multicast_query_use_ifaddr, S_IRUGO | S_IWUSR,
-		   show_multicast_query_use_ifaddr,
-		   store_multicast_query_use_ifaddr);
+static DEVICE_ATTR_RW(multicast_query_use_ifaddr);
 
-static ssize_t show_multicast_querier(struct device *d,
+static ssize_t multicast_querier_show(struct device *d,
 				      struct device_attribute *attr,
 				      char *buf)
 {
@@ -408,16 +407,15 @@ static ssize_t show_multicast_querier(struct device *d,
 	return sprintf(buf, "%d\n", br->multicast_querier);
 }
 
-static ssize_t store_multicast_querier(struct device *d,
+static ssize_t multicast_querier_store(struct device *d,
 				       struct device_attribute *attr,
 				       const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, br_multicast_set_querier);
 }
-static DEVICE_ATTR(multicast_querier, S_IRUGO | S_IWUSR,
-		   show_multicast_querier, store_multicast_querier);
+static DEVICE_ATTR_RW(multicast_querier);
 
-static ssize_t show_hash_elasticity(struct device *d,
+static ssize_t hash_elasticity_show(struct device *d,
 				    struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -430,31 +428,29 @@ static int set_elasticity(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_hash_elasticity(struct device *d,
+static ssize_t hash_elasticity_store(struct device *d,
 				     struct device_attribute *attr,
 				     const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_elasticity);
 }
-static DEVICE_ATTR(hash_elasticity, S_IRUGO | S_IWUSR, show_hash_elasticity,
-		   store_hash_elasticity);
+static DEVICE_ATTR_RW(hash_elasticity);
 
-static ssize_t show_hash_max(struct device *d, struct device_attribute *attr,
+static ssize_t hash_max_show(struct device *d, struct device_attribute *attr,
 			     char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
 	return sprintf(buf, "%u\n", br->hash_max);
 }
 
-static ssize_t store_hash_max(struct device *d, struct device_attribute *attr,
+static ssize_t hash_max_store(struct device *d, struct device_attribute *attr,
 			      const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, br_multicast_set_hash_max);
 }
-static DEVICE_ATTR(hash_max, S_IRUGO | S_IWUSR, show_hash_max,
-		   store_hash_max);
+static DEVICE_ATTR_RW(hash_max);
 
-static ssize_t show_multicast_last_member_count(struct device *d,
+static ssize_t multicast_last_member_count_show(struct device *d,
 						struct device_attribute *attr,
 						char *buf)
 {
@@ -468,17 +464,15 @@ static int set_last_member_count(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_multicast_last_member_count(struct device *d,
+static ssize_t multicast_last_member_count_store(struct device *d,
 						 struct device_attribute *attr,
 						 const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_last_member_count);
 }
-static DEVICE_ATTR(multicast_last_member_count, S_IRUGO | S_IWUSR,
-		   show_multicast_last_member_count,
-		   store_multicast_last_member_count);
+static DEVICE_ATTR_RW(multicast_last_member_count);
 
-static ssize_t show_multicast_startup_query_count(
+static ssize_t multicast_startup_query_count_show(
 	struct device *d, struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -491,17 +485,15 @@ static int set_startup_query_count(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_multicast_startup_query_count(
+static ssize_t multicast_startup_query_count_store(
 	struct device *d, struct device_attribute *attr, const char *buf,
 	size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_startup_query_count);
 }
-static DEVICE_ATTR(multicast_startup_query_count, S_IRUGO | S_IWUSR,
-		   show_multicast_startup_query_count,
-		   store_multicast_startup_query_count);
+static DEVICE_ATTR_RW(multicast_startup_query_count);
 
-static ssize_t show_multicast_last_member_interval(
+static ssize_t multicast_last_member_interval_show(
 	struct device *d, struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -515,17 +507,15 @@ static int set_last_member_interval(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_multicast_last_member_interval(
+static ssize_t multicast_last_member_interval_store(
 	struct device *d, struct device_attribute *attr, const char *buf,
 	size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_last_member_interval);
 }
-static DEVICE_ATTR(multicast_last_member_interval, S_IRUGO | S_IWUSR,
-		   show_multicast_last_member_interval,
-		   store_multicast_last_member_interval);
+static DEVICE_ATTR_RW(multicast_last_member_interval);
 
-static ssize_t show_multicast_membership_interval(
+static ssize_t multicast_membership_interval_show(
 	struct device *d, struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -539,17 +529,15 @@ static int set_membership_interval(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_multicast_membership_interval(
+static ssize_t multicast_membership_interval_store(
 	struct device *d, struct device_attribute *attr, const char *buf,
 	size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_membership_interval);
 }
-static DEVICE_ATTR(multicast_membership_interval, S_IRUGO | S_IWUSR,
-		   show_multicast_membership_interval,
-		   store_multicast_membership_interval);
+static DEVICE_ATTR_RW(multicast_membership_interval);
 
-static ssize_t show_multicast_querier_interval(struct device *d,
+static ssize_t multicast_querier_interval_show(struct device *d,
 					       struct device_attribute *attr,
 					       char *buf)
 {
@@ -564,17 +552,15 @@ static int set_querier_interval(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_multicast_querier_interval(struct device *d,
+static ssize_t multicast_querier_interval_store(struct device *d,
 						struct device_attribute *attr,
 						const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_querier_interval);
 }
-static DEVICE_ATTR(multicast_querier_interval, S_IRUGO | S_IWUSR,
-		   show_multicast_querier_interval,
-		   store_multicast_querier_interval);
+static DEVICE_ATTR_RW(multicast_querier_interval);
 
-static ssize_t show_multicast_query_interval(struct device *d,
+static ssize_t multicast_query_interval_show(struct device *d,
 					     struct device_attribute *attr,
 					     char *buf)
 {
@@ -589,17 +575,15 @@ static int set_query_interval(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_multicast_query_interval(struct device *d,
+static ssize_t multicast_query_interval_store(struct device *d,
 					      struct device_attribute *attr,
 					      const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_query_interval);
 }
-static DEVICE_ATTR(multicast_query_interval, S_IRUGO | S_IWUSR,
-		   show_multicast_query_interval,
-		   store_multicast_query_interval);
+static DEVICE_ATTR_RW(multicast_query_interval);
 
-static ssize_t show_multicast_query_response_interval(
+static ssize_t multicast_query_response_interval_show(
 	struct device *d, struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -614,17 +598,15 @@ static int set_query_response_interval(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_multicast_query_response_interval(
+static ssize_t multicast_query_response_interval_store(
 	struct device *d, struct device_attribute *attr, const char *buf,
 	size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_query_response_interval);
 }
-static DEVICE_ATTR(multicast_query_response_interval, S_IRUGO | S_IWUSR,
-		   show_multicast_query_response_interval,
-		   store_multicast_query_response_interval);
+static DEVICE_ATTR_RW(multicast_query_response_interval);
 
-static ssize_t show_multicast_startup_query_interval(
+static ssize_t multicast_startup_query_interval_show(
 	struct device *d, struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -639,18 +621,16 @@ static int set_startup_query_interval(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_multicast_startup_query_interval(
+static ssize_t multicast_startup_query_interval_store(
 	struct device *d, struct device_attribute *attr, const char *buf,
 	size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_startup_query_interval);
 }
-static DEVICE_ATTR(multicast_startup_query_interval, S_IRUGO | S_IWUSR,
-		   show_multicast_startup_query_interval,
-		   store_multicast_startup_query_interval);
+static DEVICE_ATTR_RW(multicast_startup_query_interval);
 #endif
 #ifdef CONFIG_BRIDGE_NETFILTER
-static ssize_t show_nf_call_iptables(
+static ssize_t nf_call_iptables_show(
 	struct device *d, struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -663,16 +643,15 @@ static int set_nf_call_iptables(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_nf_call_iptables(
+static ssize_t nf_call_iptables_store(
 	struct device *d, struct device_attribute *attr, const char *buf,
 	size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_nf_call_iptables);
 }
-static DEVICE_ATTR(nf_call_iptables, S_IRUGO | S_IWUSR,
-		   show_nf_call_iptables, store_nf_call_iptables);
+static DEVICE_ATTR_RW(nf_call_iptables);
 
-static ssize_t show_nf_call_ip6tables(
+static ssize_t nf_call_ip6tables_show(
 	struct device *d, struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -685,16 +664,15 @@ static int set_nf_call_ip6tables(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_nf_call_ip6tables(
+static ssize_t nf_call_ip6tables_store(
 	struct device *d, struct device_attribute *attr, const char *buf,
 	size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_nf_call_ip6tables);
 }
-static DEVICE_ATTR(nf_call_ip6tables, S_IRUGO | S_IWUSR,
-		   show_nf_call_ip6tables, store_nf_call_ip6tables);
+static DEVICE_ATTR_RW(nf_call_ip6tables);
 
-static ssize_t show_nf_call_arptables(
+static ssize_t nf_call_arptables_show(
 	struct device *d, struct device_attribute *attr, char *buf)
 {
 	struct net_bridge *br = to_bridge(d);
@@ -707,17 +685,16 @@ static int set_nf_call_arptables(struct net_bridge *br, unsigned long val)
 	return 0;
 }
 
-static ssize_t store_nf_call_arptables(
+static ssize_t nf_call_arptables_store(
 	struct device *d, struct device_attribute *attr, const char *buf,
 	size_t len)
 {
 	return store_bridge_parm(d, buf, len, set_nf_call_arptables);
 }
-static DEVICE_ATTR(nf_call_arptables, S_IRUGO | S_IWUSR,
-		   show_nf_call_arptables, store_nf_call_arptables);
+static DEVICE_ATTR_RW(nf_call_arptables);
 #endif
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
-static ssize_t show_vlan_filtering(struct device *d,
+static ssize_t vlan_filtering_show(struct device *d,
 				   struct device_attribute *attr,
 				   char *buf)
 {
@@ -725,14 +702,29 @@ static ssize_t show_vlan_filtering(struct device *d,
 	return sprintf(buf, "%d\n", br->vlan_enabled);
 }
 
-static ssize_t store_vlan_filtering(struct device *d,
+static ssize_t vlan_filtering_store(struct device *d,
 				    struct device_attribute *attr,
 				    const char *buf, size_t len)
 {
 	return store_bridge_parm(d, buf, len, br_vlan_filter_toggle);
 }
-static DEVICE_ATTR(vlan_filtering, S_IRUGO | S_IWUSR,
-		   show_vlan_filtering, store_vlan_filtering);
+static DEVICE_ATTR_RW(vlan_filtering);
+
+static ssize_t vlan_protocol_show(struct device *d,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%#06x\n", ntohs(br->vlan_proto));
+}
+
+static ssize_t vlan_protocol_store(struct device *d,
+				   struct device_attribute *attr,
+				   const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_vlan_set_proto);
+}
+static DEVICE_ATTR_RW(vlan_protocol);
 #endif
 
 static struct attribute *bridge_attrs[] = {
@@ -778,6 +770,7 @@ static struct attribute *bridge_attrs[] = {
 #endif
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
 	&dev_attr_vlan_filtering.attr,
+	&dev_attr_vlan_protocol.attr,
 #endif
 	NULL
 };
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 2a2cdb756d5..e561cd59b8a 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -26,7 +26,7 @@ struct brport_attribute {
 	int (*store)(struct net_bridge_port *, unsigned long);
 };
 
-#define BRPORT_ATTR(_name,_mode,_show,_store)		        \
+#define BRPORT_ATTR(_name, _mode, _show, _store)		\
 const struct brport_attribute brport_attr_##_name = { 	        \
 	.attr = {.name = __stringify(_name), 			\
 		 .mode = _mode },				\
@@ -41,20 +41,30 @@ static ssize_t show_##_name(struct net_bridge_port *p, char *buf) \
 }								\
 static int store_##_name(struct net_bridge_port *p, unsigned long v) \
 {								\
-	unsigned long flags = p->flags;				\
-	if (v)							\
-		flags |= _mask;					\
-	else							\
-		flags &= ~_mask;				\
-	if (flags != p->flags) {				\
-		p->flags = flags;				\
-		br_ifinfo_notify(RTM_NEWLINK, p);		\
-	}							\
-	return 0;						\
+	return store_flag(p, v, _mask);				\
 }								\
 static BRPORT_ATTR(_name, S_IRUGO | S_IWUSR,			\
 		   show_##_name, store_##_name)
 
+static int store_flag(struct net_bridge_port *p, unsigned long v,
+		      unsigned long mask)
+{
+	unsigned long flags;
+
+	flags = p->flags;
+
+	if (v)
+		flags |= mask;
+	else
+		flags &= ~mask;
+
+	if (flags != p->flags) {
+		p->flags = flags;
+		br_port_flags_change(p, mask);
+		br_ifinfo_notify(RTM_NEWLINK, p);
+	}
+	return 0;
+}
 
 static ssize_t show_path_cost(struct net_bridge_port *p, char *buf)
 {
@@ -209,21 +219,21 @@ static const struct brport_attribute *brport_attrs[] = {
 #define to_brport_attr(_at) container_of(_at, struct brport_attribute, attr)
 #define to_brport(obj)	container_of(obj, struct net_bridge_port, kobj)
 
-static ssize_t brport_show(struct kobject * kobj,
-			   struct attribute * attr, char * buf)
+static ssize_t brport_show(struct kobject *kobj,
+			   struct attribute *attr, char *buf)
 {
-	struct brport_attribute * brport_attr = to_brport_attr(attr);
-	struct net_bridge_port * p = to_brport(kobj);
+	struct brport_attribute *brport_attr = to_brport_attr(attr);
+	struct net_bridge_port *p = to_brport(kobj);
 
 	return brport_attr->show(p, buf);
 }
 
-static ssize_t brport_store(struct kobject * kobj,
-			    struct attribute * attr,
-			    const char * buf, size_t count)
+static ssize_t brport_store(struct kobject *kobj,
+			    struct attribute *attr,
+			    const char *buf, size_t count)
 {
-	struct brport_attribute * brport_attr = to_brport_attr(attr);
-	struct net_bridge_port * p = to_brport(kobj);
+	struct brport_attribute *brport_attr = to_brport_attr(attr);
+	struct net_bridge_port *p = to_brport(kobj);
 	ssize_t ret = -EINVAL;
 	char *endp;
 	unsigned long val;
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index af5ebd18d70..2b2774fe070 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -60,7 +60,7 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags)
 		 * that ever changes this code will allow tagged
 		 * traffic to enter the bridge.
 		 */
-		err = vlan_vid_add(dev, htons(ETH_P_8021Q), vid);
+		err = vlan_vid_add(dev, br->vlan_proto, vid);
 		if (err)
 			return err;
 	}
@@ -80,7 +80,7 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags)
 
 out_filt:
 	if (p)
-		vlan_vid_del(dev, htons(ETH_P_8021Q), vid);
+		vlan_vid_del(dev, br->vlan_proto, vid);
 	return err;
 }
 
@@ -92,16 +92,18 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid)
 	__vlan_delete_pvid(v, vid);
 	clear_bit(vid, v->untagged_bitmap);
 
-	if (v->port_idx)
-		vlan_vid_del(v->parent.port->dev, htons(ETH_P_8021Q), vid);
+	if (v->port_idx) {
+		struct net_bridge_port *p = v->parent.port;
+		vlan_vid_del(p->dev, p->br->vlan_proto, vid);
+	}
 
 	clear_bit(vid, v->vlan_bitmap);
 	v->num_vlans--;
 	if (bitmap_empty(v->vlan_bitmap, VLAN_N_VID)) {
 		if (v->port_idx)
-			rcu_assign_pointer(v->parent.port->vlan_info, NULL);
+			RCU_INIT_POINTER(v->parent.port->vlan_info, NULL);
 		else
-			rcu_assign_pointer(v->parent.br->vlan_info, NULL);
+			RCU_INIT_POINTER(v->parent.br->vlan_info, NULL);
 		kfree_rcu(v, rcu);
 	}
 	return 0;
@@ -113,28 +115,12 @@ static void __vlan_flush(struct net_port_vlans *v)
 	v->pvid = 0;
 	bitmap_zero(v->vlan_bitmap, VLAN_N_VID);
 	if (v->port_idx)
-		rcu_assign_pointer(v->parent.port->vlan_info, NULL);
+		RCU_INIT_POINTER(v->parent.port->vlan_info, NULL);
 	else
-		rcu_assign_pointer(v->parent.br->vlan_info, NULL);
+		RCU_INIT_POINTER(v->parent.br->vlan_info, NULL);
 	kfree_rcu(v, rcu);
 }
 
-/* Strip the tag from the packet.  Will return skb with tci set 0.  */
-static struct sk_buff *br_vlan_untag(struct sk_buff *skb)
-{
-	if (skb->protocol != htons(ETH_P_8021Q)) {
-		skb->vlan_tci = 0;
-		return skb;
-	}
-
-	skb->vlan_tci = 0;
-	skb = vlan_untag(skb);
-	if (skb)
-		skb->vlan_tci = 0;
-
-	return skb;
-}
-
 struct sk_buff *br_handle_vlan(struct net_bridge *br,
 			       const struct net_port_vlans *pv,
 			       struct sk_buff *skb)
@@ -144,34 +130,27 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
 	if (!br->vlan_enabled)
 		goto out;
 
+	/* Vlan filter table must be configured at this point.  The
+	 * only exception is the bridge is set in promisc mode and the
+	 * packet is destined for the bridge device.  In this case
+	 * pass the packet as is.
+	 */
+	if (!pv) {
+		if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) {
+			goto out;
+		} else {
+			kfree_skb(skb);
+			return NULL;
+		}
+	}
+
 	/* At this point, we know that the frame was filtered and contains
 	 * a valid vlan id.  If the vlan id is set in the untagged bitmap,
-	 * send untagged; otherwise, send taged.
+	 * send untagged; otherwise, send tagged.
 	 */
 	br_vlan_get_tag(skb, &vid);
 	if (test_bit(vid, pv->untagged_bitmap))
-		skb = br_vlan_untag(skb);
-	else {
-		/* Egress policy says "send tagged".  If output device
-		 * is the  bridge, we need to add the VLAN header
-		 * ourselves since we'll be going through the RX path.
-		 * Sending to ports puts the frame on the TX path and
-		 * we let dev_hard_start_xmit() add the header.
-		 */
-		if (skb->protocol != htons(ETH_P_8021Q) &&
-		    pv->port_idx == 0) {
-			/* vlan_put_tag expects skb->data to point to
-			 * mac header.
-			 */
-			skb_push(skb, ETH_HLEN);
-			skb = __vlan_put_tag(skb, skb->vlan_proto, skb->vlan_tci);
-			if (!skb)
-				goto out;
-			/* put skb->data back to where it was */
-			skb_pull(skb, ETH_HLEN);
-			skb->vlan_tci = 0;
-		}
-	}
+		skb->vlan_tci = 0;
 
 out:
 	return skb;
@@ -181,7 +160,8 @@ out:
 bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 			struct sk_buff *skb, u16 *vid)
 {
-	int err;
+	bool tagged;
+	__be16 proto;
 
 	/* If VLAN filtering is disabled on the bridge, all packets are
 	 * permitted.
@@ -193,9 +173,43 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	 * rejected.
 	 */
 	if (!v)
-		return false;
+		goto drop;
+
+	proto = br->vlan_proto;
+
+	/* If vlan tx offload is disabled on bridge device and frame was
+	 * sent from vlan device on the bridge device, it does not have
+	 * HW accelerated vlan tag.
+	 */
+	if (unlikely(!vlan_tx_tag_present(skb) &&
+		     skb->protocol == proto)) {
+		skb = vlan_untag(skb);
+		if (unlikely(!skb))
+			return false;
+	}
+
+	if (!br_vlan_get_tag(skb, vid)) {
+		/* Tagged frame */
+		if (skb->vlan_proto != proto) {
+			/* Protocol-mismatch, empty out vlan_tci for new tag */
+			skb_push(skb, ETH_HLEN);
+			skb = __vlan_put_tag(skb, skb->vlan_proto,
+					     vlan_tx_tag_get(skb));
+			if (unlikely(!skb))
+				return false;
+
+			skb_pull(skb, ETH_HLEN);
+			skb_reset_mac_len(skb);
+			*vid = 0;
+			tagged = false;
+		} else {
+			tagged = true;
+		}
+	} else {
+		/* Untagged frame */
+		tagged = false;
+	}
 
-	err = br_vlan_get_tag(skb, vid);
 	if (!*vid) {
 		u16 pvid = br_get_pvid(v);
 
@@ -204,15 +218,15 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 		 * vlan untagged or priority-tagged traffic belongs to.
 		 */
 		if (pvid == VLAN_N_VID)
-			return false;
+			goto drop;
 
 		/* PVID is set on this port.  Any untagged or priority-tagged
 		 * ingress frame is considered to belong to this vlan.
 		 */
 		*vid = pvid;
-		if (likely(err))
+		if (likely(!tagged))
 			/* Untagged Frame. */
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pvid);
+			__vlan_hwaccel_put_tag(skb, proto, pvid);
 		else
 			/* Priority-tagged Frame.
 			 * At this point, We know that skb->vlan_tci had
@@ -227,7 +241,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	/* Frame had a valid vlan tag.  See if vlan is allowed */
 	if (test_bit(*vid, v->vlan_bitmap))
 		return true;
-
+drop:
+	kfree_skb(skb);
 	return false;
 }
 
@@ -251,6 +266,36 @@ bool br_allowed_egress(struct net_bridge *br,
 	return false;
 }
 
+/* Called under RCU */
+bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
+{
+	struct net_bridge *br = p->br;
+	struct net_port_vlans *v;
+
+	if (!br->vlan_enabled)
+		return true;
+
+	v = rcu_dereference(p->vlan_info);
+	if (!v)
+		return false;
+
+	if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto)
+		*vid = 0;
+
+	if (!*vid) {
+		*vid = br_get_pvid(v);
+		if (*vid == VLAN_N_VID)
+			return false;
+
+		return true;
+	}
+
+	if (test_bit(*vid, v->vlan_bitmap))
+		return true;
+
+	return false;
+}
+
 /* Must be protected by RTNL.
  * Must be called with vid in range from 1 to 4094 inclusive.
  */
@@ -296,9 +341,7 @@ int br_vlan_delete(struct net_bridge *br, u16 vid)
 	if (!pv)
 		return -EINVAL;
 
-	spin_lock_bh(&br->hash_lock);
-	fdb_delete_by_addr(br, br->dev->dev_addr, vid);
-	spin_unlock_bh(&br->hash_lock);
+	br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid);
 
 	__vlan_del(pv, vid);
 	return 0;
@@ -316,6 +359,52 @@ void br_vlan_flush(struct net_bridge *br)
 	__vlan_flush(pv);
 }
 
+bool br_vlan_find(struct net_bridge *br, u16 vid)
+{
+	struct net_port_vlans *pv;
+	bool found = false;
+
+	rcu_read_lock();
+	pv = rcu_dereference(br->vlan_info);
+
+	if (!pv)
+		goto out;
+
+	if (test_bit(vid, pv->vlan_bitmap))
+		found = true;
+
+out:
+	rcu_read_unlock();
+	return found;
+}
+
+/* Must be protected by RTNL. */
+static void recalculate_group_addr(struct net_bridge *br)
+{
+	if (br->group_addr_set)
+		return;
+
+	spin_lock_bh(&br->lock);
+	if (!br->vlan_enabled || br->vlan_proto == htons(ETH_P_8021Q)) {
+		/* Bridge Group Address */
+		br->group_addr[5] = 0x00;
+	} else { /* vlan_enabled && ETH_P_8021AD */
+		/* Provider Bridge Group Address */
+		br->group_addr[5] = 0x08;
+	}
+	spin_unlock_bh(&br->lock);
+}
+
+/* Must be protected by RTNL. */
+void br_recalculate_fwd_mask(struct net_bridge *br)
+{
+	if (!br->vlan_enabled || br->vlan_proto == htons(ETH_P_8021Q))
+		br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT;
+	else /* vlan_enabled && ETH_P_8021AD */
+		br->group_fwd_mask_required = BR_GROUPFWD_8021AD &
+					      ~(1u << br->group_addr[5]);
+}
+
 int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val)
 {
 	if (!rtnl_trylock())
@@ -325,12 +414,88 @@ int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val)
 		goto unlock;
 
 	br->vlan_enabled = val;
+	br_manage_promisc(br);
+	recalculate_group_addr(br);
+	br_recalculate_fwd_mask(br);
 
 unlock:
 	rtnl_unlock();
 	return 0;
 }
 
+int br_vlan_set_proto(struct net_bridge *br, unsigned long val)
+{
+	int err = 0;
+	struct net_bridge_port *p;
+	struct net_port_vlans *pv;
+	__be16 proto, oldproto;
+	u16 vid, errvid;
+
+	if (val != ETH_P_8021Q && val != ETH_P_8021AD)
+		return -EPROTONOSUPPORT;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	proto = htons(val);
+	if (br->vlan_proto == proto)
+		goto unlock;
+
+	/* Add VLANs for the new proto to the device filter. */
+	list_for_each_entry(p, &br->port_list, list) {
+		pv = rtnl_dereference(p->vlan_info);
+		if (!pv)
+			continue;
+
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+			err = vlan_vid_add(p->dev, proto, vid);
+			if (err)
+				goto err_filt;
+		}
+	}
+
+	oldproto = br->vlan_proto;
+	br->vlan_proto = proto;
+
+	recalculate_group_addr(br);
+	br_recalculate_fwd_mask(br);
+
+	/* Delete VLANs for the old proto from the device filter. */
+	list_for_each_entry(p, &br->port_list, list) {
+		pv = rtnl_dereference(p->vlan_info);
+		if (!pv)
+			continue;
+
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
+			vlan_vid_del(p->dev, oldproto, vid);
+	}
+
+unlock:
+	rtnl_unlock();
+	return err;
+
+err_filt:
+	errvid = vid;
+	for_each_set_bit(vid, pv->vlan_bitmap, errvid)
+		vlan_vid_del(p->dev, proto, vid);
+
+	list_for_each_entry_continue_reverse(p, &br->port_list, list) {
+		pv = rtnl_dereference(p->vlan_info);
+		if (!pv)
+			continue;
+
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
+			vlan_vid_del(p->dev, proto, vid);
+	}
+
+	goto unlock;
+}
+
+void br_vlan_init(struct net_bridge *br)
+{
+	br->vlan_proto = htons(ETH_P_8021Q);
+}
+
 /* Must be protected by RTNL.
  * Must be called with vid in range from 1 to 4094 inclusive.
  */
@@ -380,9 +545,7 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid)
 	if (!pv)
 		return -EINVAL;
 
-	spin_lock_bh(&port->br->hash_lock);
-	fdb_delete_by_addr(port->br, port->dev->dev_addr, vid);
-	spin_unlock_bh(&port->br->hash_lock);
+	br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid);
 
 	return __vlan_del(pv, vid);
 }
@@ -399,7 +562,7 @@ void nbp_vlan_flush(struct net_bridge_port *port)
 		return;
 
 	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
-		vlan_vid_del(port->dev, htons(ETH_P_8021Q), vid);
+		vlan_vid_del(port->dev, port->br->vlan_proto, vid);
 
 	__vlan_flush(pv);
 }
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index 5ca74a0e595..629dc77874a 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -2,14 +2,23 @@
 # Bridge netfilter configuration
 #
 #
-config NF_TABLES_BRIDGE
-	depends on NF_TABLES
+menuconfig NF_TABLES_BRIDGE
+	depends on BRIDGE && NETFILTER && NF_TABLES
 	tristate "Ethernet Bridge nf_tables support"
 
+if NF_TABLES_BRIDGE
+
+config NFT_BRIDGE_META
+	tristate "Netfilter nf_table bridge meta support"
+	depends on NFT_META
+	help
+	  Add support for bridge dedicated meta key.
+
+endif # NF_TABLES_BRIDGE
+
 menuconfig BRIDGE_NF_EBTABLES
 	tristate "Ethernet Bridge tables (ebtables) support"
-	depends on BRIDGE && NETFILTER
-	select NETFILTER_XTABLES
+	depends on BRIDGE && NETFILTER && NETFILTER_XTABLES
 	help
 	  ebtables is a general, extensible frame/packet identification
 	  framework. Say 'Y' or 'M' here if you want to do Ethernet
diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile
index ea7629f58b3..6f2f3943d66 100644
--- a/net/bridge/netfilter/Makefile
+++ b/net/bridge/netfilter/Makefile
@@ -3,6 +3,7 @@
 #
 
 obj-$(CONFIG_NF_TABLES_BRIDGE) += nf_tables_bridge.o
+obj-$(CONFIG_NFT_BRIDGE_META)  += nft_meta_bridge.o
 
 obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o
 
diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c
index 3fb3c848aff..9024283d2bc 100644
--- a/net/bridge/netfilter/ebt_among.c
+++ b/net/bridge/netfilter/ebt_among.c
@@ -28,7 +28,7 @@ static bool ebt_mac_wormhash_contains(const struct ebt_mac_wormhash *wh,
 	uint32_t cmp[2] = { 0, 0 };
 	int key = ((const unsigned char *)mac)[5];
 
-	memcpy(((char *) cmp) + 2, mac, ETH_ALEN);
+	ether_addr_copy(((char *) cmp) + 2, mac);
 	start = wh->table[key];
 	limit = wh->table[key + 1];
 	if (ip) {
diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c
index c59f7bfae6e..4e0b0c35932 100644
--- a/net/bridge/netfilter/ebt_dnat.c
+++ b/net/bridge/netfilter/ebt_dnat.c
@@ -22,7 +22,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	if (!skb_make_writable(skb, 0))
 		return EBT_DROP;
 
-	memcpy(eth_hdr(skb)->h_dest, info->mac, ETH_ALEN);
+	ether_addr_copy(eth_hdr(skb)->h_dest, info->mac);
 	return info->target;
 }
 
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index 19c37a4929b..5322a36867a 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -96,7 +96,7 @@ ebt_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum,
 		bitmask = NF_LOG_MASK;
 
 	if ((bitmask & EBT_LOG_IP) && eth_hdr(skb)->h_proto ==
-	   htons(ETH_P_IP)){
+	   htons(ETH_P_IP)) {
 		const struct iphdr *ih;
 		struct iphdr _iph;
 
diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c
index 46624bb6d9b..203964997a5 100644
--- a/net/bridge/netfilter/ebt_redirect.c
+++ b/net/bridge/netfilter/ebt_redirect.c
@@ -25,10 +25,10 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
 
 	if (par->hooknum != NF_BR_BROUTING)
 		/* rcu_read_lock()ed by nf_hook_slow */
-		memcpy(eth_hdr(skb)->h_dest,
-		       br_port_get_rcu(par->in)->br->dev->dev_addr, ETH_ALEN);
+		ether_addr_copy(eth_hdr(skb)->h_dest,
+				br_port_get_rcu(par->in)->br->dev->dev_addr);
 	else
-		memcpy(eth_hdr(skb)->h_dest, par->in->dev_addr, ETH_ALEN);
+		ether_addr_copy(eth_hdr(skb)->h_dest, par->in->dev_addr);
 	skb->pkt_type = PACKET_HOST;
 	return info->target;
 }
diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c
index f8f0bd1a1d5..e56ccd060d2 100644
--- a/net/bridge/netfilter/ebt_snat.c
+++ b/net/bridge/netfilter/ebt_snat.c
@@ -24,7 +24,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	if (!skb_make_writable(skb, 0))
 		return EBT_DROP;
 
-	memcpy(eth_hdr(skb)->h_source, info->mac, ETH_ALEN);
+	ether_addr_copy(eth_hdr(skb)->h_source, info->mac);
 	if (!(info->target & NAT_ARP_BIT) &&
 	    eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) {
 		const struct arphdr *ap;
@@ -35,7 +35,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 			return EBT_DROP;
 		if (ap->ar_hln != ETH_ALEN)
 			goto out;
-		if (skb_store_bits(skb, sizeof(_ah), info->mac,ETH_ALEN))
+		if (skb_store_bits(skb, sizeof(_ah), info->mac, ETH_ALEN))
 			return EBT_DROP;
 	}
 out:
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index dbd1c783431..d2cdf5d6e98 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -23,8 +23,7 @@ static struct ebt_entries initial_chain = {
 	.policy		= EBT_ACCEPT,
 };
 
-static struct ebt_replace_kernel initial_table =
-{
+static struct ebt_replace_kernel initial_table = {
 	.name		= "broute",
 	.valid_hooks	= 1 << NF_BR_BROUTING,
 	.entries_size	= sizeof(struct ebt_entries),
@@ -41,8 +40,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
 	return 0;
 }
 
-static const struct ebt_table broute_table =
-{
+static const struct ebt_table broute_table = {
 	.name		= "broute",
 	.table		= &initial_table,
 	.valid_hooks	= 1 << NF_BR_BROUTING,
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index bb2da7b706e..ce205aabf9c 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -14,8 +14,7 @@
 #define FILTER_VALID_HOOKS ((1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | \
    (1 << NF_BR_LOCAL_OUT))
 
-static struct ebt_entries initial_chains[] =
-{
+static struct ebt_entries initial_chains[] = {
 	{
 		.name	= "INPUT",
 		.policy	= EBT_ACCEPT,
@@ -30,8 +29,7 @@ static struct ebt_entries initial_chains[] =
 	},
 };
 
-static struct ebt_replace_kernel initial_table =
-{
+static struct ebt_replace_kernel initial_table = {
 	.name		= "filter",
 	.valid_hooks	= FILTER_VALID_HOOKS,
 	.entries_size	= 3 * sizeof(struct ebt_entries),
@@ -50,8 +48,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
 	return 0;
 }
 
-static const struct ebt_table frame_filter =
-{
+static const struct ebt_table frame_filter = {
 	.name		= "filter",
 	.table		= &initial_table,
 	.valid_hooks	= FILTER_VALID_HOOKS,
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index bd238f1f105..a0ac2984fb6 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -14,8 +14,7 @@
 #define NAT_VALID_HOOKS ((1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_OUT) | \
    (1 << NF_BR_POST_ROUTING))
 
-static struct ebt_entries initial_chains[] =
-{
+static struct ebt_entries initial_chains[] = {
 	{
 		.name	= "PREROUTING",
 		.policy	= EBT_ACCEPT,
@@ -30,8 +29,7 @@ static struct ebt_entries initial_chains[] =
 	}
 };
 
-static struct ebt_replace_kernel initial_table =
-{
+static struct ebt_replace_kernel initial_table = {
 	.name		= "nat",
 	.valid_hooks	= NAT_VALID_HOOKS,
 	.entries_size	= 3 * sizeof(struct ebt_entries),
@@ -50,8 +48,7 @@ static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
 	return 0;
 }
 
-static struct ebt_table frame_nat =
-{
+static struct ebt_table frame_nat = {
 	.name		= "nat",
 	.table		= &initial_table,
 	.valid_hooks	= NAT_VALID_HOOKS,
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index ac780242838..1059ed3bc25 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -118,10 +118,10 @@ ebt_dev_check(const char *entry, const struct net_device *device)
 	/* 1 is the wildcard token */
 	while (entry[i] != '\0' && entry[i] != 1 && entry[i] == devname[i])
 		i++;
-	return (devname[i] != entry[i] && entry[i] != 1);
+	return devname[i] != entry[i] && entry[i] != 1;
 }
 
-#define FWINV2(bool,invflg) ((bool) ^ !!(e->invflags & invflg))
+#define FWINV2(bool, invflg) ((bool) ^ !!(e->invflags & invflg))
 /* process standard matches */
 static inline int
 ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb,
@@ -1044,10 +1044,9 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
 	if (repl->num_counters &&
 	   copy_to_user(repl->counters, counterstmp,
 	   repl->num_counters * sizeof(struct ebt_counter))) {
-		ret = -EFAULT;
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("ebtables: counters copy to user failed while replacing table\n");
 	}
-	else
-		ret = 0;
 
 	/* decrease module count and free resources */
 	EBT_ENTRY_ITERATE(table->entries, table->entries_size,
@@ -1441,7 +1440,7 @@ static int copy_everything_to_user(struct ebt_table *t, void __user *user,
 		return -EFAULT;
 
 	if (*len != sizeof(struct ebt_replace) + entries_size +
-	   (tmp.num_counters? nentries * sizeof(struct ebt_counter): 0))
+	   (tmp.num_counters ? nentries * sizeof(struct ebt_counter) : 0))
 		return -EINVAL;
 
 	if (tmp.nentries != nentries) {
@@ -1477,7 +1476,7 @@ static int do_ebt_set_ctl(struct sock *sk,
 	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	switch(cmd) {
+	switch (cmd) {
 	case EBT_SO_SET_ENTRIES:
 		ret = do_replace(net, user, len);
 		break;
@@ -1507,10 +1506,10 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	if (!t)
 		return ret;
 
-	switch(cmd) {
+	switch (cmd) {
 	case EBT_SO_GET_INFO:
 	case EBT_SO_GET_INIT_INFO:
-		if (*len != sizeof(struct ebt_replace)){
+		if (*len != sizeof(struct ebt_replace)) {
 			ret = -EINVAL;
 			mutex_unlock(&ebt_mutex);
 			break;
@@ -1525,7 +1524,7 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 			tmp.valid_hooks = t->table->valid_hooks;
 		}
 		mutex_unlock(&ebt_mutex);
-		if (copy_to_user(user, &tmp, *len) != 0){
+		if (copy_to_user(user, &tmp, *len) != 0) {
 			BUGPRINT("c2u Didn't work\n");
 			ret = -EFAULT;
 			break;
@@ -2375,8 +2374,7 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd,
 }
 #endif
 
-static struct nf_sockopt_ops ebt_sockopts =
-{
+static struct nf_sockopt_ops ebt_sockopts = {
 	.pf		= PF_INET,
 	.set_optmin	= EBT_BASE_CTL,
 	.set_optmax	= EBT_SO_SET_MAX + 1,
diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c
index cf54b22818c..5bcc0d8b31f 100644
--- a/net/bridge/netfilter/nf_tables_bridge.c
+++ b/net/bridge/netfilter/nf_tables_bridge.c
@@ -14,10 +14,30 @@
 #include <linux/netfilter_bridge.h>
 #include <net/netfilter/nf_tables.h>
 
+static unsigned int
+nft_do_chain_bridge(const struct nf_hook_ops *ops,
+		    struct sk_buff *skb,
+		    const struct net_device *in,
+		    const struct net_device *out,
+		    int (*okfn)(struct sk_buff *))
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo(&pkt, ops, skb, in, out);
+
+	return nft_do_chain(&pkt, ops);
+}
+
 static struct nft_af_info nft_af_bridge __read_mostly = {
 	.family		= NFPROTO_BRIDGE,
 	.nhooks		= NF_BR_NUMHOOKS,
 	.owner		= THIS_MODULE,
+	.nops		= 1,
+	.hooks		= {
+		[NF_BR_LOCAL_IN]	= nft_do_chain_bridge,
+		[NF_BR_FORWARD]		= nft_do_chain_bridge,
+		[NF_BR_LOCAL_OUT]	= nft_do_chain_bridge,
+	},
 };
 
 static int nf_tables_bridge_init_net(struct net *net)
@@ -48,32 +68,14 @@ static struct pernet_operations nf_tables_bridge_net_ops = {
 	.exit	= nf_tables_bridge_exit_net,
 };
 
-static unsigned int
-nft_do_chain_bridge(const struct nf_hook_ops *ops,
-		    struct sk_buff *skb,
-		    const struct net_device *in,
-		    const struct net_device *out,
-		    int (*okfn)(struct sk_buff *))
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo(&pkt, ops, skb, in, out);
-
-	return nft_do_chain_pktinfo(&pkt, ops);
-}
-
-static struct nf_chain_type filter_bridge = {
-	.family		= NFPROTO_BRIDGE,
+static const struct nf_chain_type filter_bridge = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_BRIDGE,
+	.owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_BR_LOCAL_IN) |
 			  (1 << NF_BR_FORWARD) |
 			  (1 << NF_BR_LOCAL_OUT),
-	.fn		= {
-		[NF_BR_LOCAL_IN]	= nft_do_chain_bridge,
-		[NF_BR_FORWARD]		= nft_do_chain_bridge,
-		[NF_BR_LOCAL_OUT]	= nft_do_chain_bridge,
-	},
 };
 
 static int __init nf_tables_bridge_init(void)
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
new file mode 100644
index 00000000000..4f02109d708
--- /dev/null
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -0,0 +1,139 @@
+/*
+ * Copyright (c) 2014 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_meta.h>
+
+#include "../br_private.h"
+
+static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
+				     struct nft_data data[NFT_REG_MAX + 1],
+				     const struct nft_pktinfo *pkt)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+	const struct net_device *in = pkt->in, *out = pkt->out;
+	struct nft_data *dest = &data[priv->dreg];
+	const struct net_bridge_port *p;
+
+	switch (priv->key) {
+	case NFT_META_BRI_IIFNAME:
+		if (in == NULL || (p = br_port_get_rcu(in)) == NULL)
+			goto err;
+		break;
+	case NFT_META_BRI_OIFNAME:
+		if (out == NULL || (p = br_port_get_rcu(out)) == NULL)
+			goto err;
+		break;
+	default:
+		goto out;
+	}
+
+	strncpy((char *)dest->data, p->br->dev->name, sizeof(dest->data));
+	return;
+out:
+	return nft_meta_get_eval(expr, data, pkt);
+err:
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static int nft_meta_bridge_get_init(const struct nft_ctx *ctx,
+				    const struct nft_expr *expr,
+				    const struct nlattr * const tb[])
+{
+	struct nft_meta *priv = nft_expr_priv(expr);
+	int err;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+	switch (priv->key) {
+	case NFT_META_BRI_IIFNAME:
+	case NFT_META_BRI_OIFNAME:
+		break;
+	default:
+		return nft_meta_get_init(ctx, expr, tb);
+	}
+
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		return err;
+
+	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static struct nft_expr_type nft_meta_bridge_type;
+static const struct nft_expr_ops nft_meta_bridge_get_ops = {
+	.type		= &nft_meta_bridge_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.eval		= nft_meta_bridge_get_eval,
+	.init		= nft_meta_bridge_get_init,
+	.dump		= nft_meta_get_dump,
+};
+
+static const struct nft_expr_ops nft_meta_bridge_set_ops = {
+	.type		= &nft_meta_bridge_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.eval		= nft_meta_set_eval,
+	.init		= nft_meta_set_init,
+	.dump		= nft_meta_set_dump,
+};
+
+static const struct nft_expr_ops *
+nft_meta_bridge_select_ops(const struct nft_ctx *ctx,
+			   const struct nlattr * const tb[])
+{
+	if (tb[NFTA_META_KEY] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG])
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_META_DREG])
+		return &nft_meta_bridge_get_ops;
+
+	if (tb[NFTA_META_SREG])
+		return &nft_meta_bridge_set_ops;
+
+	return ERR_PTR(-EINVAL);
+}
+
+static struct nft_expr_type nft_meta_bridge_type __read_mostly = {
+	.family         = NFPROTO_BRIDGE,
+	.name           = "meta",
+	.select_ops     = &nft_meta_bridge_select_ops,
+	.policy         = nft_meta_policy,
+	.maxattr        = NFTA_META_MAX,
+	.owner          = THIS_MODULE,
+};
+
+static int __init nft_meta_bridge_module_init(void)
+{
+	return nft_register_expr(&nft_meta_bridge_type);
+}
+
+static void __exit nft_meta_bridge_module_exit(void)
+{
+	nft_unregister_expr(&nft_meta_bridge_type);
+}
+
+module_init(nft_meta_bridge_module_init);
+module_exit(nft_meta_bridge_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta");
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index 4dca159435c..edbca468fa7 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -22,6 +22,7 @@
 #include <net/pkt_sched.h>
 #include <net/caif/caif_device.h>
 #include <net/caif/caif_layer.h>
+#include <net/caif/caif_dev.h>
 #include <net/caif/cfpkt.h>
 #include <net/caif/cfcnfg.h>
 #include <net/caif/cfserl.h>
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index d6be3edb7a4..e8437094d15 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -124,7 +124,6 @@ static void caif_flow_ctrl(struct sock *sk, int mode)
 static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int err;
-	int skb_len;
 	unsigned long flags;
 	struct sk_buff_head *list = &sk->sk_receive_queue;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
@@ -153,14 +152,13 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	 * may be freed by other threads of control pulling packets
 	 * from the queue.
 	 */
-	skb_len = skb->len;
 	spin_lock_irqsave(&list->lock, flags);
 	if (!sock_flag(sk, SOCK_DEAD))
 		__skb_queue_tail(list, skb);
 	spin_unlock_irqrestore(&list->lock, flags);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb_len);
+		sk->sk_data_ready(sk);
 	else
 		kfree_skb(skb);
 	return 0;
diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c
index 75ed04b78fa..ba02db02290 100644
--- a/net/caif/caif_usb.c
+++ b/net/caif/caif_usb.c
@@ -14,6 +14,7 @@
 #include <linux/mii.h>
 #include <linux/usb.h>
 #include <linux/usb/usbnet.h>
+#include <linux/etherdevice.h>
 #include <net/netns/generic.h>
 #include <net/caif/caif_dev.h>
 #include <net/caif/caif_layer.h>
@@ -105,8 +106,8 @@ static struct cflayer *cfusbl_create(int phyid, u8 ethaddr[ETH_ALEN],
 	 *	5-11	source address
 	 *	12-13	protocol type
 	 */
-	memcpy(&this->tx_eth_hdr[ETH_ALEN], braddr, ETH_ALEN);
-	memcpy(&this->tx_eth_hdr[ETH_ALEN], ethaddr, ETH_ALEN);
+	ether_addr_copy(&this->tx_eth_hdr[ETH_ALEN], braddr);
+	ether_addr_copy(&this->tx_eth_hdr[ETH_ALEN], ethaddr);
 	this->tx_eth_hdr[12] = cpu_to_be16(ETH_P_802_EX1) & 0xff;
 	this->tx_eth_hdr[13] = (cpu_to_be16(ETH_P_802_EX1) >> 8) & 0xff;
 	pr_debug("caif ethernet TX-header dst:%pM src:%pM type:%02x%02x\n",
diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c
index 353f793d1b3..a6e11546305 100644
--- a/net/caif/cfsrvl.c
+++ b/net/caif/cfsrvl.c
@@ -15,6 +15,7 @@
 #include <net/caif/caif_layer.h>
 #include <net/caif/cfsrvl.h>
 #include <net/caif/cfpkt.h>
+#include <net/caif/caif_dev.h>
 
 #define SRVL_CTRL_PKT_SIZE 1
 #define SRVL_FLOW_OFF 0x81
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 7344a8fa1bb..4589ff67bfa 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -285,7 +285,7 @@ static int chnl_net_open(struct net_device *dev)
 				goto error;
 		}
 
-		lldev = dev_get_by_index(dev_net(dev), llifindex);
+		lldev = __dev_get_by_index(dev_net(dev), llifindex);
 
 		if (lldev == NULL) {
 			pr_debug("no interface?\n");
@@ -307,7 +307,6 @@ static int chnl_net_open(struct net_device *dev)
 		mtu = min_t(int, dev->mtu, lldev->mtu - (headroom + tailroom));
 		mtu = min_t(int, GPRS_PDP_MTU, mtu);
 		dev_set_mtu(dev, mtu);
-		dev_put(lldev);
 
 		if (mtu < 100) {
 			pr_warn("CAIF Interface MTU too small (%d)\n", mtu);
diff --git a/net/can/af_can.c b/net/can/af_can.c
index d249874a366..ce82337521f 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -57,6 +57,7 @@
 #include <linux/skbuff.h>
 #include <linux/can.h>
 #include <linux/can/core.h>
+#include <linux/can/skb.h>
 #include <linux/ratelimit.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
@@ -290,7 +291,7 @@ int can_send(struct sk_buff *skb, int loop)
 				return -ENOMEM;
 			}
 
-			newskb->sk = skb->sk;
+			can_skb_set_owner(newskb, skb->sk);
 			newskb->ip_summed = CHECKSUM_UNNECESSARY;
 			newskb->pkt_type = PACKET_BROADCAST;
 		}
@@ -337,6 +338,29 @@ static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev)
 }
 
 /**
+ * effhash - hash function for 29 bit CAN identifier reduction
+ * @can_id: 29 bit CAN identifier
+ *
+ * Description:
+ *  To reduce the linear traversal in one linked list of _single_ EFF CAN
+ *  frame subscriptions the 29 bit identifier is mapped to 10 bits.
+ *  (see CAN_EFF_RCV_HASH_BITS definition)
+ *
+ * Return:
+ *  Hash value from 0x000 - 0x3FF ( enforced by CAN_EFF_RCV_HASH_BITS mask )
+ */
+static unsigned int effhash(canid_t can_id)
+{
+	unsigned int hash;
+
+	hash = can_id;
+	hash ^= can_id >> CAN_EFF_RCV_HASH_BITS;
+	hash ^= can_id >> (2 * CAN_EFF_RCV_HASH_BITS);
+
+	return hash & ((1 << CAN_EFF_RCV_HASH_BITS) - 1);
+}
+
+/**
  * find_rcv_list - determine optimal filterlist inside device filter struct
  * @can_id: pointer to CAN identifier of a given can_filter
  * @mask: pointer to CAN mask of a given can_filter
@@ -399,10 +423,8 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
 	    !(*can_id & CAN_RTR_FLAG)) {
 
 		if (*can_id & CAN_EFF_FLAG) {
-			if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS)) {
-				/* RFC: a future use-case for hash-tables? */
-				return &d->rx[RX_EFF];
-			}
+			if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS))
+				return &d->rx_eff[effhash(*can_id)];
 		} else {
 			if (*mask == (CAN_SFF_MASK | CAN_EFF_RTR_FLAGS))
 				return &d->rx_sff[*can_id];
@@ -631,7 +653,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb)
 		return matches;
 
 	if (can_id & CAN_EFF_FLAG) {
-		hlist_for_each_entry_rcu(r, &d->rx[RX_EFF], list) {
+		hlist_for_each_entry_rcu(r, &d->rx_eff[effhash(can_id)], list) {
 			if (r->can_id == can_id) {
 				deliver(skb, r);
 				matches++;
diff --git a/net/can/af_can.h b/net/can/af_can.h
index 6de58b40535..fca0fe9fc45 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -59,12 +59,17 @@ struct receiver {
 	char *ident;
 };
 
-enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_EFF, RX_MAX };
+#define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS)
+#define CAN_EFF_RCV_HASH_BITS 10
+#define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS)
+
+enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX };
 
 /* per device receive filters linked at dev->ml_priv */
 struct dev_rcv_lists {
 	struct hlist_head rx[RX_MAX];
-	struct hlist_head rx_sff[0x800];
+	struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ];
+	struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ];
 	int remove_on_zero_entries;
 	int entries;
 };
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 46f20bfafc0..dcb75c0e66c 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -268,7 +268,7 @@ static void bcm_can_tx(struct bcm_op *op)
 
 	/* send with loopback */
 	skb->dev = dev;
-	skb->sk = op->sk;
+	can_skb_set_owner(skb, op->sk);
 	can_send(skb, 1);
 
 	/* update statistics */
@@ -1223,7 +1223,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
 
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	skb->dev = dev;
-	skb->sk  = sk;
+	can_skb_set_owner(skb, sk);
 	err = can_send(skb, 1); /* send with loopback */
 	dev_put(dev);
 
@@ -1256,8 +1256,7 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	if (!ifindex && msg->msg_name) {
 		/* no bound device as default => check msg_name */
-		struct sockaddr_can *addr =
-			(struct sockaddr_can *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name);
 
 		if (msg->msg_namelen < sizeof(*addr))
 			return -EINVAL;
@@ -1568,6 +1567,7 @@ static int bcm_recvmsg(struct kiocb *iocb, struct socket *sock,
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (msg->msg_name) {
+		__sockaddr_check_size(sizeof(struct sockaddr_can));
 		msg->msg_namelen = sizeof(struct sockaddr_can);
 		memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
 	}
diff --git a/net/can/gw.c b/net/can/gw.c
index 3f9b0f3a281..050a2110d43 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -804,7 +804,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 	u8 limhops = 0;
 	int err = 0;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (nlmsg_len(nlh) < sizeof(*r))
@@ -839,23 +839,21 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 	if (!gwj->ccgw.src_idx || !gwj->ccgw.dst_idx)
 		goto out;
 
-	gwj->src.dev = dev_get_by_index(&init_net, gwj->ccgw.src_idx);
+	gwj->src.dev = __dev_get_by_index(&init_net, gwj->ccgw.src_idx);
 
 	if (!gwj->src.dev)
 		goto out;
 
-	/* check for CAN netdev not using header_ops - see gw_rcv() */
-	if (gwj->src.dev->type != ARPHRD_CAN || gwj->src.dev->header_ops)
-		goto put_src_out;
+	if (gwj->src.dev->type != ARPHRD_CAN)
+		goto out;
 
-	gwj->dst.dev = dev_get_by_index(&init_net, gwj->ccgw.dst_idx);
+	gwj->dst.dev = __dev_get_by_index(&init_net, gwj->ccgw.dst_idx);
 
 	if (!gwj->dst.dev)
-		goto put_src_out;
+		goto out;
 
-	/* check for CAN netdev not using header_ops - see gw_rcv() */
-	if (gwj->dst.dev->type != ARPHRD_CAN || gwj->dst.dev->header_ops)
-		goto put_src_dst_out;
+	if (gwj->dst.dev->type != ARPHRD_CAN)
+		goto out;
 
 	gwj->limit_hops = limhops;
 
@@ -864,11 +862,6 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 	err = cgw_register_filter(gwj);
 	if (!err)
 		hlist_add_head_rcu(&gwj->list, &cgw_list);
-
-put_src_dst_out:
-	dev_put(gwj->dst.dev);
-put_src_out:
-	dev_put(gwj->src.dev);
 out:
 	if (err)
 		kmem_cache_free(cgw_cache, gwj);
@@ -900,7 +893,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh)
 	u8 limhops = 0;
 	int err = 0;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (nlmsg_len(nlh) < sizeof(*r))
diff --git a/net/can/proc.c b/net/can/proc.c
index b543470c8f8..1a19b985a86 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -80,7 +80,6 @@ static const char rx_list_name[][8] = {
 	[RX_ALL] = "rx_all",
 	[RX_FIL] = "rx_fil",
 	[RX_INV] = "rx_inv",
-	[RX_EFF] = "rx_eff",
 };
 
 /*
@@ -389,25 +388,26 @@ static const struct file_operations can_rcvlist_proc_fops = {
 	.release	= single_release,
 };
 
-static inline void can_rcvlist_sff_proc_show_one(struct seq_file *m,
-						 struct net_device *dev,
-						 struct dev_rcv_lists *d)
+static inline void can_rcvlist_proc_show_array(struct seq_file *m,
+					       struct net_device *dev,
+					       struct hlist_head *rcv_array,
+					       unsigned int rcv_array_sz)
 {
-	int i;
+	unsigned int i;
 	int all_empty = 1;
 
 	/* check whether at least one list is non-empty */
-	for (i = 0; i < 0x800; i++)
-		if (!hlist_empty(&d->rx_sff[i])) {
+	for (i = 0; i < rcv_array_sz; i++)
+		if (!hlist_empty(&rcv_array[i])) {
 			all_empty = 0;
 			break;
 		}
 
 	if (!all_empty) {
 		can_print_recv_banner(m);
-		for (i = 0; i < 0x800; i++) {
-			if (!hlist_empty(&d->rx_sff[i]))
-				can_print_rcvlist(m, &d->rx_sff[i], dev);
+		for (i = 0; i < rcv_array_sz; i++) {
+			if (!hlist_empty(&rcv_array[i]))
+				can_print_rcvlist(m, &rcv_array[i], dev);
 		}
 	} else
 		seq_printf(m, "  (%s: no entry)\n", DNAME(dev));
@@ -425,12 +425,15 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
 
 	/* sff receive list for 'all' CAN devices (dev == NULL) */
 	d = &can_rx_alldev_list;
-	can_rcvlist_sff_proc_show_one(m, NULL, d);
+	can_rcvlist_proc_show_array(m, NULL, d->rx_sff, ARRAY_SIZE(d->rx_sff));
 
 	/* sff receive list for registered CAN devices */
 	for_each_netdev_rcu(&init_net, dev) {
-		if (dev->type == ARPHRD_CAN && dev->ml_priv)
-			can_rcvlist_sff_proc_show_one(m, dev, dev->ml_priv);
+		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
+			d = dev->ml_priv;
+			can_rcvlist_proc_show_array(m, dev, d->rx_sff,
+						    ARRAY_SIZE(d->rx_sff));
+		}
 	}
 
 	rcu_read_unlock();
@@ -452,6 +455,49 @@ static const struct file_operations can_rcvlist_sff_proc_fops = {
 	.release	= single_release,
 };
 
+
+static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
+{
+	struct net_device *dev;
+	struct dev_rcv_lists *d;
+
+	/* RX_EFF */
+	seq_puts(m, "\nreceive list 'rx_eff':\n");
+
+	rcu_read_lock();
+
+	/* eff receive list for 'all' CAN devices (dev == NULL) */
+	d = &can_rx_alldev_list;
+	can_rcvlist_proc_show_array(m, NULL, d->rx_eff, ARRAY_SIZE(d->rx_eff));
+
+	/* eff receive list for registered CAN devices */
+	for_each_netdev_rcu(&init_net, dev) {
+		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
+			d = dev->ml_priv;
+			can_rcvlist_proc_show_array(m, dev, d->rx_eff,
+						    ARRAY_SIZE(d->rx_eff));
+		}
+	}
+
+	rcu_read_unlock();
+
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static int can_rcvlist_eff_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, can_rcvlist_eff_proc_show, NULL);
+}
+
+static const struct file_operations can_rcvlist_eff_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= can_rcvlist_eff_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 /*
  * proc utility functions
  */
@@ -491,8 +537,8 @@ void can_init_proc(void)
 					   &can_rcvlist_proc_fops, (void *)RX_FIL);
 	pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644, can_dir,
 					   &can_rcvlist_proc_fops, (void *)RX_INV);
-	pde_rcvlist_eff = proc_create_data(CAN_PROC_RCVLIST_EFF, 0644, can_dir,
-					   &can_rcvlist_proc_fops, (void *)RX_EFF);
+	pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644, can_dir,
+				      &can_rcvlist_eff_proc_fops);
 	pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644, can_dir,
 				      &can_rcvlist_sff_proc_fops);
 }
diff --git a/net/can/raw.c b/net/can/raw.c
index 641e1c89512..081e81fd017 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -121,13 +121,9 @@ static void raw_rcv(struct sk_buff *oskb, void *data)
 	if (!ro->recv_own_msgs && oskb->sk == sk)
 		return;
 
-	/* do not pass frames with DLC > 8 to a legacy socket */
-	if (!ro->fd_frames) {
-		struct canfd_frame *cfd = (struct canfd_frame *)oskb->data;
-
-		if (unlikely(cfd->len > CAN_MAX_DLEN))
-			return;
-	}
+	/* do not pass non-CAN2.0 frames to a legacy socket */
+	if (!ro->fd_frames && oskb->len != CAN_MTU)
+		return;
 
 	/* clone the given skb to be able to enqueue it into the rcv queue */
 	skb = skb_clone(oskb, GFP_ATOMIC);
@@ -675,8 +671,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock,
 	int err;
 
 	if (msg->msg_name) {
-		struct sockaddr_can *addr =
-			(struct sockaddr_can *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name);
 
 		if (msg->msg_namelen < sizeof(*addr))
 			return -EINVAL;
@@ -716,6 +711,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	skb->dev = dev;
 	skb->sk  = sk;
+	skb->priority = sk->sk_priority;
 
 	err = can_send(skb, ro->loopback);
 
@@ -738,9 +734,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock,
 		       struct msghdr *msg, size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct raw_sock *ro = raw_sk(sk);
 	struct sk_buff *skb;
-	int rxmtu;
 	int err = 0;
 	int noblock;
 
@@ -751,20 +745,10 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (!skb)
 		return err;
 
-	/*
-	 * when serving a legacy socket the DLC <= 8 is already checked inside
-	 * raw_rcv(). Now check if we need to pass a canfd_frame to a legacy
-	 * socket and cut the possible CANFD_MTU/CAN_MTU length to CAN_MTU
-	 */
-	if (!ro->fd_frames)
-		rxmtu = CAN_MTU;
-	else
-		rxmtu = skb->len;
-
-	if (size < rxmtu)
+	if (size < skb->len)
 		msg->msg_flags |= MSG_TRUNC;
 	else
-		size = rxmtu;
+		size = skb->len;
 
 	err = memcpy_toiovec(msg->msg_iov, skb->data, size);
 	if (err < 0) {
@@ -775,6 +759,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock,
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (msg->msg_name) {
+		__sockaddr_check_size(sizeof(struct sockaddr_can));
 		msg->msg_namelen = sizeof(struct sockaddr_can);
 		memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
 	}
diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c
index bf3e6a13c21..621b5f65407 100644
--- a/net/ceph/buffer.c
+++ b/net/ceph/buffer.c
@@ -6,6 +6,7 @@
 
 #include <linux/ceph/buffer.h>
 #include <linux/ceph/decode.h>
+#include <linux/ceph/libceph.h> /* for ceph_kv{malloc,free} */
 
 struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
 {
@@ -15,16 +16,10 @@ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
 	if (!b)
 		return NULL;
 
-	b->vec.iov_base = kmalloc(len, gfp | __GFP_NOWARN);
-	if (b->vec.iov_base) {
-		b->is_vmalloc = false;
-	} else {
-		b->vec.iov_base = __vmalloc(len, gfp | __GFP_HIGHMEM, PAGE_KERNEL);
-		if (!b->vec.iov_base) {
-			kfree(b);
-			return NULL;
-		}
-		b->is_vmalloc = true;
+	b->vec.iov_base = ceph_kvmalloc(len, gfp);
+	if (!b->vec.iov_base) {
+		kfree(b);
+		return NULL;
 	}
 
 	kref_init(&b->kref);
@@ -40,12 +35,7 @@ void ceph_buffer_release(struct kref *kref)
 	struct ceph_buffer *b = container_of(kref, struct ceph_buffer, kref);
 
 	dout("buffer_release %p\n", b);
-	if (b->vec.iov_base) {
-		if (b->is_vmalloc)
-			vfree(b->vec.iov_base);
-		else
-			kfree(b->vec.iov_base);
-	}
+	ceph_kvfree(b->vec.iov_base);
 	kfree(b);
 }
 EXPORT_SYMBOL(ceph_buffer_release);
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 34b11ee8124..1675021d8c1 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/statfs.h>
 #include <linux/string.h>
+#include <linux/vmalloc.h>
 #include <linux/nsproxy.h>
 #include <net/net_namespace.h>
 
@@ -71,6 +72,8 @@ const char *ceph_msg_type_name(int type)
 	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
 	case CEPH_MSG_STATFS: return "statfs";
 	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
+	case CEPH_MSG_MON_GET_VERSION: return "mon_get_version";
+	case CEPH_MSG_MON_GET_VERSION_REPLY: return "mon_get_version_reply";
 	case CEPH_MSG_MDS_MAP: return "mds_map";
 	case CEPH_MSG_CLIENT_SESSION: return "client_session";
 	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
@@ -170,6 +173,25 @@ int ceph_compare_options(struct ceph_options *new_opt,
 }
 EXPORT_SYMBOL(ceph_compare_options);
 
+void *ceph_kvmalloc(size_t size, gfp_t flags)
+{
+	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+		void *ptr = kmalloc(size, flags | __GFP_NOWARN);
+		if (ptr)
+			return ptr;
+	}
+
+	return __vmalloc(size, flags | __GFP_HIGHMEM, PAGE_KERNEL);
+}
+
+void ceph_kvfree(const void *ptr)
+{
+	if (is_vmalloc_addr(ptr))
+		vfree(ptr);
+	else
+		kfree(ptr);
+}
+
 
 static int parse_fsid(const char *str, struct ceph_fsid *fsid)
 {
@@ -461,8 +483,8 @@ EXPORT_SYMBOL(ceph_client_id);
  * create a fresh client instance
  */
 struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
-				       unsigned int supported_features,
-				       unsigned int required_features)
+				       u64 supported_features,
+				       u64 required_features)
 {
 	struct ceph_client *client;
 	struct ceph_entity_addr *myaddr = NULL;
diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c
index 089613234f0..16bc199d9a6 100644
--- a/net/ceph/crush/crush.c
+++ b/net/ceph/crush/crush.c
@@ -116,11 +116,14 @@ void crush_destroy(struct crush_map *map)
 	if (map->rules) {
 		__u32 b;
 		for (b = 0; b < map->max_rules; b++)
-			kfree(map->rules[b]);
+			crush_destroy_rule(map->rules[b]);
 		kfree(map->rules);
 	}
 
 	kfree(map);
 }
 
-
+void crush_destroy_rule(struct crush_rule *rule)
+{
+	kfree(rule);
+}
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index cbd06a91941..a1ef53c0441 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -189,7 +189,7 @@ static int terminal(int x)
 static int bucket_tree_choose(struct crush_bucket_tree *bucket,
 			      int x, int r)
 {
-	int n, l;
+	int n;
 	__u32 w;
 	__u64 t;
 
@@ -197,6 +197,7 @@ static int bucket_tree_choose(struct crush_bucket_tree *bucket,
 	n = bucket->num_nodes >> 1;
 
 	while (!terminal(n)) {
+		int l;
 		/* pick point in [0, w) */
 		w = bucket->node_weights[n];
 		t = (__u64)crush_hash32_4(bucket->h.hash, x, n, r,
@@ -264,8 +265,12 @@ static int crush_bucket_choose(struct crush_bucket *in, int x, int r)
  * true if device is marked "out" (failed, fully offloaded)
  * of the cluster
  */
-static int is_out(const struct crush_map *map, const __u32 *weight, int item, int x)
+static int is_out(const struct crush_map *map,
+		  const __u32 *weight, int weight_max,
+		  int item, int x)
 {
+	if (item >= weight_max)
+		return 1;
 	if (weight[item] >= 0x10000)
 		return 0;
 	if (weight[item] == 0)
@@ -277,7 +282,7 @@ static int is_out(const struct crush_map *map, const __u32 *weight, int item, in
 }
 
 /**
- * crush_choose - choose numrep distinct items of given type
+ * crush_choose_firstn - choose numrep distinct items of given type
  * @map: the crush_map
  * @bucket: the bucket we are choose an item from
  * @x: crush input value
@@ -285,18 +290,28 @@ static int is_out(const struct crush_map *map, const __u32 *weight, int item, in
  * @type: the type of item to choose
  * @out: pointer to output vector
  * @outpos: our position in that vector
- * @firstn: true if choosing "first n" items, false if choosing "indep"
- * @recurse_to_leaf: true if we want one device under each item of given type
- * @descend_once: true if we should only try one descent before giving up
+ * @tries: number of attempts to make
+ * @recurse_tries: number of attempts to have recursive chooseleaf make
+ * @local_retries: localized retries
+ * @local_fallback_retries: localized fallback retries
+ * @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose)
+ * @vary_r: pass r to recursive calls
  * @out2: second output vector for leaf items (if @recurse_to_leaf)
+ * @parent_r: r value passed from the parent
  */
-static int crush_choose(const struct crush_map *map,
-			struct crush_bucket *bucket,
-			const __u32 *weight,
-			int x, int numrep, int type,
-			int *out, int outpos,
-			int firstn, int recurse_to_leaf,
-			int descend_once, int *out2)
+static int crush_choose_firstn(const struct crush_map *map,
+			       struct crush_bucket *bucket,
+			       const __u32 *weight, int weight_max,
+			       int x, int numrep, int type,
+			       int *out, int outpos,
+			       unsigned int tries,
+			       unsigned int recurse_tries,
+			       unsigned int local_retries,
+			       unsigned int local_fallback_retries,
+			       int recurse_to_leaf,
+			       unsigned int vary_r,
+			       int *out2,
+			       int parent_r)
 {
 	int rep;
 	unsigned int ftotal, flocal;
@@ -308,8 +323,11 @@ static int crush_choose(const struct crush_map *map,
 	int itemtype;
 	int collide, reject;
 
-	dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "",
-		bucket->id, x, outpos, numrep);
+	dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d\n",
+		recurse_to_leaf ? "_LEAF" : "",
+		bucket->id, x, outpos, numrep,
+		tries, recurse_tries, local_retries, local_fallback_retries,
+		parent_r);
 
 	for (rep = outpos; rep < numrep; rep++) {
 		/* keep trying until we get a non-out, non-colliding item */
@@ -324,36 +342,18 @@ static int crush_choose(const struct crush_map *map,
 			do {
 				collide = 0;
 				retry_bucket = 0;
-				r = rep;
-				if (in->alg == CRUSH_BUCKET_UNIFORM) {
-					/* be careful */
-					if (firstn || (__u32)numrep >= in->size)
-						/* r' = r + f_total */
-						r += ftotal;
-					else if (in->size % numrep == 0)
-						/* r'=r+(n+1)*f_local */
-						r += (numrep+1) *
-							(flocal+ftotal);
-					else
-						/* r' = r + n*f_local */
-						r += numrep * (flocal+ftotal);
-				} else {
-					if (firstn)
-						/* r' = r + f_total */
-						r += ftotal;
-					else
-						/* r' = r + n*f_local */
-						r += numrep * (flocal+ftotal);
-				}
+				r = rep + parent_r;
+				/* r' = r + f_total */
+				r += ftotal;
 
 				/* bucket choose */
 				if (in->size == 0) {
 					reject = 1;
 					goto reject;
 				}
-				if (map->choose_local_fallback_tries > 0 &&
+				if (local_fallback_retries > 0 &&
 				    flocal >= (in->size>>1) &&
-				    flocal > map->choose_local_fallback_tries)
+				    flocal > local_fallback_retries)
 					item = bucket_perm_choose(in, x, r);
 				else
 					item = crush_bucket_choose(in, x, r);
@@ -394,14 +394,23 @@ static int crush_choose(const struct crush_map *map,
 				reject = 0;
 				if (!collide && recurse_to_leaf) {
 					if (item < 0) {
-						if (crush_choose(map,
+						int sub_r;
+						if (vary_r)
+							sub_r = r >> (vary_r-1);
+						else
+							sub_r = 0;
+						if (crush_choose_firstn(map,
 							 map->buckets[-1-item],
-							 weight,
+							 weight, weight_max,
 							 x, outpos+1, 0,
 							 out2, outpos,
-							 firstn, 0,
-							 map->chooseleaf_descend_once,
-							 NULL) <= outpos)
+							 recurse_tries, 0,
+							 local_retries,
+							 local_fallback_retries,
+							 0,
+							 vary_r,
+							 NULL,
+							 sub_r) <= outpos)
 							/* didn't get leaf */
 							reject = 1;
 					} else {
@@ -414,6 +423,7 @@ static int crush_choose(const struct crush_map *map,
 					/* out? */
 					if (itemtype == 0)
 						reject = is_out(map, weight,
+								weight_max,
 								item, x);
 					else
 						reject = 0;
@@ -424,17 +434,14 @@ reject:
 					ftotal++;
 					flocal++;
 
-					if (reject && descend_once)
-						/* let outer call try again */
-						skip_rep = 1;
-					else if (collide && flocal <= map->choose_local_tries)
+					if (collide && flocal <= local_retries)
 						/* retry locally a few times */
 						retry_bucket = 1;
-					else if (map->choose_local_fallback_tries > 0 &&
-						 flocal <= in->size + map->choose_local_fallback_tries)
+					else if (local_fallback_retries > 0 &&
+						 flocal <= in->size + local_fallback_retries)
 						/* exhaustive bucket search */
 						retry_bucket = 1;
-					else if (ftotal <= map->choose_total_tries)
+					else if (ftotal < tries)
 						/* then retry descent */
 						retry_descent = 1;
 					else
@@ -464,21 +471,179 @@ reject:
 
 
 /**
+ * crush_choose_indep: alternative breadth-first positionally stable mapping
+ *
+ */
+static void crush_choose_indep(const struct crush_map *map,
+			       struct crush_bucket *bucket,
+			       const __u32 *weight, int weight_max,
+			       int x, int left, int numrep, int type,
+			       int *out, int outpos,
+			       unsigned int tries,
+			       unsigned int recurse_tries,
+			       int recurse_to_leaf,
+			       int *out2,
+			       int parent_r)
+{
+	struct crush_bucket *in = bucket;
+	int endpos = outpos + left;
+	int rep;
+	unsigned int ftotal;
+	int r;
+	int i;
+	int item = 0;
+	int itemtype;
+	int collide;
+
+	dprintk("CHOOSE%s INDEP bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "",
+		bucket->id, x, outpos, numrep);
+
+	/* initially my result is undefined */
+	for (rep = outpos; rep < endpos; rep++) {
+		out[rep] = CRUSH_ITEM_UNDEF;
+		if (out2)
+			out2[rep] = CRUSH_ITEM_UNDEF;
+	}
+
+	for (ftotal = 0; left > 0 && ftotal < tries; ftotal++) {
+		for (rep = outpos; rep < endpos; rep++) {
+			if (out[rep] != CRUSH_ITEM_UNDEF)
+				continue;
+
+			in = bucket;  /* initial bucket */
+
+			/* choose through intervening buckets */
+			for (;;) {
+				/* note: we base the choice on the position
+				 * even in the nested call.  that means that
+				 * if the first layer chooses the same bucket
+				 * in a different position, we will tend to
+				 * choose a different item in that bucket.
+				 * this will involve more devices in data
+				 * movement and tend to distribute the load.
+				 */
+				r = rep + parent_r;
+
+				/* be careful */
+				if (in->alg == CRUSH_BUCKET_UNIFORM &&
+				    in->size % numrep == 0)
+					/* r'=r+(n+1)*f_total */
+					r += (numrep+1) * ftotal;
+				else
+					/* r' = r + n*f_total */
+					r += numrep * ftotal;
+
+				/* bucket choose */
+				if (in->size == 0) {
+					dprintk("   empty bucket\n");
+					break;
+				}
+
+				item = crush_bucket_choose(in, x, r);
+				if (item >= map->max_devices) {
+					dprintk("   bad item %d\n", item);
+					out[rep] = CRUSH_ITEM_NONE;
+					if (out2)
+						out2[rep] = CRUSH_ITEM_NONE;
+					left--;
+					break;
+				}
+
+				/* desired type? */
+				if (item < 0)
+					itemtype = map->buckets[-1-item]->type;
+				else
+					itemtype = 0;
+				dprintk("  item %d type %d\n", item, itemtype);
+
+				/* keep going? */
+				if (itemtype != type) {
+					if (item >= 0 ||
+					    (-1-item) >= map->max_buckets) {
+						dprintk("   bad item type %d\n", type);
+						out[rep] = CRUSH_ITEM_NONE;
+						if (out2)
+							out2[rep] =
+								CRUSH_ITEM_NONE;
+						left--;
+						break;
+					}
+					in = map->buckets[-1-item];
+					continue;
+				}
+
+				/* collision? */
+				collide = 0;
+				for (i = outpos; i < endpos; i++) {
+					if (out[i] == item) {
+						collide = 1;
+						break;
+					}
+				}
+				if (collide)
+					break;
+
+				if (recurse_to_leaf) {
+					if (item < 0) {
+						crush_choose_indep(map,
+						   map->buckets[-1-item],
+						   weight, weight_max,
+						   x, 1, numrep, 0,
+						   out2, rep,
+						   recurse_tries, 0,
+						   0, NULL, r);
+						if (out2[rep] == CRUSH_ITEM_NONE) {
+							/* placed nothing; no leaf */
+							break;
+						}
+					} else {
+						/* we already have a leaf! */
+						out2[rep] = item;
+					}
+				}
+
+				/* out? */
+				if (itemtype == 0 &&
+				    is_out(map, weight, weight_max, item, x))
+					break;
+
+				/* yay! */
+				out[rep] = item;
+				left--;
+				break;
+			}
+		}
+	}
+	for (rep = outpos; rep < endpos; rep++) {
+		if (out[rep] == CRUSH_ITEM_UNDEF) {
+			out[rep] = CRUSH_ITEM_NONE;
+		}
+		if (out2 && out2[rep] == CRUSH_ITEM_UNDEF) {
+			out2[rep] = CRUSH_ITEM_NONE;
+		}
+	}
+}
+
+/**
  * crush_do_rule - calculate a mapping with the given input and rule
  * @map: the crush_map
  * @ruleno: the rule id
  * @x: hash input
  * @result: pointer to result vector
  * @result_max: maximum result size
+ * @weight: weight vector (for map leaves)
+ * @weight_max: size of weight vector
+ * @scratch: scratch vector for private use; must be >= 3 * result_max
  */
 int crush_do_rule(const struct crush_map *map,
 		  int ruleno, int x, int *result, int result_max,
-		  const __u32 *weight)
+		  const __u32 *weight, int weight_max,
+		  int *scratch)
 {
 	int result_len;
-	int a[CRUSH_MAX_SET];
-	int b[CRUSH_MAX_SET];
-	int c[CRUSH_MAX_SET];
+	int *a = scratch;
+	int *b = scratch + result_max;
+	int *c = scratch + result_max*2;
 	int recurse_to_leaf;
 	int *w;
 	int wsize = 0;
@@ -489,8 +654,20 @@ int crush_do_rule(const struct crush_map *map,
 	__u32 step;
 	int i, j;
 	int numrep;
-	int firstn;
-	const int descend_once = 0;
+	/*
+	 * the original choose_total_tries value was off by one (it
+	 * counted "retries" and not "tries").  add one.
+	 */
+	int choose_tries = map->choose_total_tries + 1;
+	int choose_leaf_tries = 0;
+	/*
+	 * the local tries values were counted as "retries", though,
+	 * and need no adjustment
+	 */
+	int choose_local_retries = map->choose_local_tries;
+	int choose_local_fallback_retries = map->choose_local_fallback_tries;
+
+	int vary_r = map->chooseleaf_vary_r;
 
 	if ((__u32)ruleno >= map->max_rules) {
 		dprintk(" bad ruleno %d\n", ruleno);
@@ -503,29 +680,54 @@ int crush_do_rule(const struct crush_map *map,
 	o = b;
 
 	for (step = 0; step < rule->len; step++) {
+		int firstn = 0;
 		struct crush_rule_step *curstep = &rule->steps[step];
 
-		firstn = 0;
 		switch (curstep->op) {
 		case CRUSH_RULE_TAKE:
 			w[0] = curstep->arg1;
 			wsize = 1;
 			break;
 
-		case CRUSH_RULE_CHOOSE_LEAF_FIRSTN:
+		case CRUSH_RULE_SET_CHOOSE_TRIES:
+			if (curstep->arg1 > 0)
+				choose_tries = curstep->arg1;
+			break;
+
+		case CRUSH_RULE_SET_CHOOSELEAF_TRIES:
+			if (curstep->arg1 > 0)
+				choose_leaf_tries = curstep->arg1;
+			break;
+
+		case CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES:
+			if (curstep->arg1 >= 0)
+				choose_local_retries = curstep->arg1;
+			break;
+
+		case CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES:
+			if (curstep->arg1 >= 0)
+				choose_local_fallback_retries = curstep->arg1;
+			break;
+
+		case CRUSH_RULE_SET_CHOOSELEAF_VARY_R:
+			if (curstep->arg1 >= 0)
+				vary_r = curstep->arg1;
+			break;
+
+		case CRUSH_RULE_CHOOSELEAF_FIRSTN:
 		case CRUSH_RULE_CHOOSE_FIRSTN:
 			firstn = 1;
 			/* fall through */
-		case CRUSH_RULE_CHOOSE_LEAF_INDEP:
+		case CRUSH_RULE_CHOOSELEAF_INDEP:
 		case CRUSH_RULE_CHOOSE_INDEP:
 			if (wsize == 0)
 				break;
 
 			recurse_to_leaf =
 				curstep->op ==
-				 CRUSH_RULE_CHOOSE_LEAF_FIRSTN ||
+				 CRUSH_RULE_CHOOSELEAF_FIRSTN ||
 				curstep->op ==
-				CRUSH_RULE_CHOOSE_LEAF_INDEP;
+				CRUSH_RULE_CHOOSELEAF_INDEP;
 
 			/* reset output */
 			osize = 0;
@@ -543,22 +745,53 @@ int crush_do_rule(const struct crush_map *map,
 						continue;
 				}
 				j = 0;
-				osize += crush_choose(map,
-						      map->buckets[-1-w[i]],
-						      weight,
-						      x, numrep,
-						      curstep->arg2,
-						      o+osize, j,
-						      firstn,
-						      recurse_to_leaf,
-						      descend_once, c+osize);
+				if (firstn) {
+					int recurse_tries;
+					if (choose_leaf_tries)
+						recurse_tries =
+							choose_leaf_tries;
+					else if (map->chooseleaf_descend_once)
+						recurse_tries = 1;
+					else
+						recurse_tries = choose_tries;
+					osize += crush_choose_firstn(
+						map,
+						map->buckets[-1-w[i]],
+						weight, weight_max,
+						x, numrep,
+						curstep->arg2,
+						o+osize, j,
+						choose_tries,
+						recurse_tries,
+						choose_local_retries,
+						choose_local_fallback_retries,
+						recurse_to_leaf,
+						vary_r,
+						c+osize,
+						0);
+				} else {
+					crush_choose_indep(
+						map,
+						map->buckets[-1-w[i]],
+						weight, weight_max,
+						x, numrep, numrep,
+						curstep->arg2,
+						o+osize, j,
+						choose_tries,
+						choose_leaf_tries ?
+						   choose_leaf_tries : 1,
+						recurse_to_leaf,
+						c+osize,
+						0);
+					osize += numrep;
+				}
 			}
 
 			if (recurse_to_leaf)
 				/* copy final _leaf_ values to output set */
 				memcpy(o, c, osize*sizeof(*o));
 
-			/* swap t and w arrays */
+			/* swap o and w arrays */
 			tmp = o;
 			o = w;
 			w = tmp;
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 83661cdc076..d1a62c69a9f 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -53,34 +53,55 @@ static int osdmap_show(struct seq_file *s, void *p)
 {
 	int i;
 	struct ceph_client *client = s->private;
+	struct ceph_osdmap *map = client->osdc.osdmap;
 	struct rb_node *n;
 
-	if (client->osdc.osdmap == NULL)
+	if (map == NULL)
 		return 0;
-	seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch);
+
+	seq_printf(s, "epoch %d\n", map->epoch);
 	seq_printf(s, "flags%s%s\n",
-		   (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ?
-		   " NEARFULL" : "",
-		   (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ?
-		   " FULL" : "");
-	for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) {
+		   (map->flags & CEPH_OSDMAP_NEARFULL) ?  " NEARFULL" : "",
+		   (map->flags & CEPH_OSDMAP_FULL) ?  " FULL" : "");
+
+	for (n = rb_first(&map->pg_pools); n; n = rb_next(n)) {
 		struct ceph_pg_pool_info *pool =
 			rb_entry(n, struct ceph_pg_pool_info, node);
-		seq_printf(s, "pg_pool %llu pg_num %d / %d\n",
-			   (unsigned long long)pool->id, pool->pg_num,
-			   pool->pg_num_mask);
+
+		seq_printf(s, "pool %lld pg_num %u (%d) read_tier %lld write_tier %lld\n",
+			   pool->id, pool->pg_num, pool->pg_num_mask,
+			   pool->read_tier, pool->write_tier);
 	}
-	for (i = 0; i < client->osdc.osdmap->max_osd; i++) {
-		struct ceph_entity_addr *addr =
-			&client->osdc.osdmap->osd_addr[i];
-		int state = client->osdc.osdmap->osd_state[i];
+	for (i = 0; i < map->max_osd; i++) {
+		struct ceph_entity_addr *addr = &map->osd_addr[i];
+		int state = map->osd_state[i];
 		char sb[64];
 
-		seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n",
+		seq_printf(s, "osd%d\t%s\t%3d%%\t(%s)\t%3d%%\n",
 			   i, ceph_pr_addr(&addr->in_addr),
-			   ((client->osdc.osdmap->osd_weight[i]*100) >> 16),
-			   ceph_osdmap_state_str(sb, sizeof(sb), state));
+			   ((map->osd_weight[i]*100) >> 16),
+			   ceph_osdmap_state_str(sb, sizeof(sb), state),
+			   ((ceph_get_primary_affinity(map, i)*100) >> 16));
+	}
+	for (n = rb_first(&map->pg_temp); n; n = rb_next(n)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(n, struct ceph_pg_mapping, node);
+
+		seq_printf(s, "pg_temp %llu.%x [", pg->pgid.pool,
+			   pg->pgid.seed);
+		for (i = 0; i < pg->pg_temp.len; i++)
+			seq_printf(s, "%s%d", (i == 0 ? "" : ","),
+				   pg->pg_temp.osds[i]);
+		seq_printf(s, "]\n");
 	}
+	for (n = rb_first(&map->primary_temp); n; n = rb_next(n)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(n, struct ceph_pg_mapping, node);
+
+		seq_printf(s, "primary_temp %llu.%x %d\n", pg->pgid.pool,
+			   pg->pgid.seed, pg->primary_temp.osd);
+	}
+
 	return 0;
 }
 
@@ -105,9 +126,13 @@ static int monc_show(struct seq_file *s, void *p)
 		req = rb_entry(rp, struct ceph_mon_generic_request, node);
 		op = le16_to_cpu(req->request->hdr.type);
 		if (op == CEPH_MSG_STATFS)
-			seq_printf(s, "%lld statfs\n", req->tid);
+			seq_printf(s, "%llu statfs\n", req->tid);
+		else if (op == CEPH_MSG_POOLOP)
+			seq_printf(s, "%llu poolop\n", req->tid);
+		else if (op == CEPH_MSG_MON_GET_VERSION)
+			seq_printf(s, "%llu mon_get_version", req->tid);
 		else
-			seq_printf(s, "%lld unknown\n", req->tid);
+			seq_printf(s, "%llu unknown\n", req->tid);
 	}
 
 	mutex_unlock(&monc->mutex);
@@ -132,7 +157,8 @@ static int osdc_show(struct seq_file *s, void *pp)
 			   req->r_osd ? req->r_osd->o_osd : -1,
 			   req->r_pgid.pool, req->r_pgid.seed);
 
-		seq_printf(s, "%.*s", req->r_oid_len, req->r_oid);
+		seq_printf(s, "%.*s", req->r_base_oid.name_len,
+			   req->r_base_oid.name);
 
 		if (req->r_reassert_version.epoch)
 			seq_printf(s, "\t%u'%llu",
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 4a5df7b1cc9..1948d592aa5 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -15,6 +15,7 @@
 #include <linux/dns_resolver.h>
 #include <net/tcp.h>
 
+#include <linux/ceph/ceph_features.h>
 #include <linux/ceph/libceph.h>
 #include <linux/ceph/messenger.h>
 #include <linux/ceph/decode.h>
@@ -382,7 +383,7 @@ static void con_sock_state_closed(struct ceph_connection *con)
  */
 
 /* data available on socket, or listen socket received a connect */
-static void ceph_sock_data_ready(struct sock *sk, int count_unused)
+static void ceph_sock_data_ready(struct sock *sk)
 {
 	struct ceph_connection *con = sk->sk_user_data;
 	if (atomic_read(&con->msgr->stopping)) {
@@ -556,7 +557,7 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
 	return r;
 }
 
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+static int __ceph_tcp_sendpage(struct socket *sock, struct page *page,
 		     int offset, size_t size, bool more)
 {
 	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR);
@@ -569,6 +570,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 	return ret;
 }
 
+static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+		     int offset, size_t size, bool more)
+{
+	int ret;
+	struct kvec iov;
+
+	/* sendpage cannot properly handle pages with page_count == 0,
+	 * we need to fallback to sendmsg if that's the case */
+	if (page_count(page) >= 1)
+		return __ceph_tcp_sendpage(sock, page, offset, size, more);
+
+	iov.iov_base = kmap(page) + offset;
+	iov.iov_len = size;
+	ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more);
+	kunmap(page);
+
+	return ret;
+}
 
 /*
  * Shutdown/close the socket for the given connection.
@@ -777,13 +796,12 @@ static void ceph_msg_data_bio_cursor_init(struct ceph_msg_data_cursor *cursor,
 
 	bio = data->bio;
 	BUG_ON(!bio);
-	BUG_ON(!bio->bi_vcnt);
 
 	cursor->resid = min(length, data->bio_length);
 	cursor->bio = bio;
-	cursor->vector_index = 0;
-	cursor->vector_offset = 0;
-	cursor->last_piece = length <= bio->bi_io_vec[0].bv_len;
+	cursor->bvec_iter = bio->bi_iter;
+	cursor->last_piece =
+		cursor->resid <= bio_iter_len(bio, cursor->bvec_iter);
 }
 
 static struct page *ceph_msg_data_bio_next(struct ceph_msg_data_cursor *cursor,
@@ -792,71 +810,67 @@ static struct page *ceph_msg_data_bio_next(struct ceph_msg_data_cursor *cursor,
 {
 	struct ceph_msg_data *data = cursor->data;
 	struct bio *bio;
-	struct bio_vec *bio_vec;
-	unsigned int index;
+	struct bio_vec bio_vec;
 
 	BUG_ON(data->type != CEPH_MSG_DATA_BIO);
 
 	bio = cursor->bio;
 	BUG_ON(!bio);
 
-	index = cursor->vector_index;
-	BUG_ON(index >= (unsigned int) bio->bi_vcnt);
+	bio_vec = bio_iter_iovec(bio, cursor->bvec_iter);
 
-	bio_vec = &bio->bi_io_vec[index];
-	BUG_ON(cursor->vector_offset >= bio_vec->bv_len);
-	*page_offset = (size_t) (bio_vec->bv_offset + cursor->vector_offset);
+	*page_offset = (size_t) bio_vec.bv_offset;
 	BUG_ON(*page_offset >= PAGE_SIZE);
 	if (cursor->last_piece) /* pagelist offset is always 0 */
 		*length = cursor->resid;
 	else
-		*length = (size_t) (bio_vec->bv_len - cursor->vector_offset);
+		*length = (size_t) bio_vec.bv_len;
 	BUG_ON(*length > cursor->resid);
 	BUG_ON(*page_offset + *length > PAGE_SIZE);
 
-	return bio_vec->bv_page;
+	return bio_vec.bv_page;
 }
 
 static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor,
 					size_t bytes)
 {
 	struct bio *bio;
-	struct bio_vec *bio_vec;
-	unsigned int index;
+	struct bio_vec bio_vec;
 
 	BUG_ON(cursor->data->type != CEPH_MSG_DATA_BIO);
 
 	bio = cursor->bio;
 	BUG_ON(!bio);
 
-	index = cursor->vector_index;
-	BUG_ON(index >= (unsigned int) bio->bi_vcnt);
-	bio_vec = &bio->bi_io_vec[index];
+	bio_vec = bio_iter_iovec(bio, cursor->bvec_iter);
 
 	/* Advance the cursor offset */
 
 	BUG_ON(cursor->resid < bytes);
 	cursor->resid -= bytes;
-	cursor->vector_offset += bytes;
-	if (cursor->vector_offset < bio_vec->bv_len)
+
+	bio_advance_iter(bio, &cursor->bvec_iter, bytes);
+
+	if (bytes < bio_vec.bv_len)
 		return false;	/* more bytes to process in this segment */
-	BUG_ON(cursor->vector_offset != bio_vec->bv_len);
 
 	/* Move on to the next segment, and possibly the next bio */
 
-	if (++index == (unsigned int) bio->bi_vcnt) {
+	if (!cursor->bvec_iter.bi_size) {
 		bio = bio->bi_next;
-		index = 0;
+		cursor->bio = bio;
+		if (bio)
+			cursor->bvec_iter = bio->bi_iter;
+		else
+			memset(&cursor->bvec_iter, 0,
+			       sizeof(cursor->bvec_iter));
 	}
-	cursor->bio = bio;
-	cursor->vector_index = index;
-	cursor->vector_offset = 0;
 
 	if (!cursor->last_piece) {
 		BUG_ON(!cursor->resid);
 		BUG_ON(!bio);
 		/* A short read is OK, so use <= rather than == */
-		if (cursor->resid <= bio->bi_io_vec[index].bv_len)
+		if (cursor->resid <= bio_iter_len(bio, cursor->bvec_iter))
 			cursor->last_piece = true;
 	}
 
@@ -923,6 +937,9 @@ static bool ceph_msg_data_pages_advance(struct ceph_msg_data_cursor *cursor,
 	if (!bytes || cursor->page_offset)
 		return false;	/* more bytes to process in the current page */
 
+	if (!cursor->resid)
+		return false;   /* no more data */
+
 	/* Move on to the next page; offset is already at 0 */
 
 	BUG_ON(cursor->page_index >= cursor->page_count);
@@ -1008,6 +1025,9 @@ static bool ceph_msg_data_pagelist_advance(struct ceph_msg_data_cursor *cursor,
 	if (!bytes || cursor->offset & ~PAGE_MASK)
 		return false;	/* more bytes to process in the current page */
 
+	if (!cursor->resid)
+		return false;   /* no more data */
+
 	/* Move on to the next page */
 
 	BUG_ON(list_is_last(&cursor->page->lru, &pagelist->head));
@@ -1865,7 +1885,9 @@ int ceph_parse_ips(const char *c, const char *end,
 				port = (port * 10) + (*p - '0');
 				p++;
 			}
-			if (port > 65535 || port == 0)
+			if (port == 0)
+				port = CEPH_MON_PORT;
+			else if (port > 65535)
 				goto bad;
 		} else {
 			port = CEPH_MON_PORT;
@@ -1945,7 +1967,8 @@ static int process_connect(struct ceph_connection *con)
 {
 	u64 sup_feat = con->msgr->supported_features;
 	u64 req_feat = con->msgr->required_features;
-	u64 server_feat = le64_to_cpu(con->in_reply.features);
+	u64 server_feat = ceph_sanitize_features(
+				le64_to_cpu(con->in_reply.features));
 	int ret;
 
 	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
@@ -2853,8 +2876,8 @@ static void con_fault(struct ceph_connection *con)
  */
 void ceph_messenger_init(struct ceph_messenger *msgr,
 			struct ceph_entity_addr *myaddr,
-			u32 supported_features,
-			u32 required_features,
+			u64 supported_features,
+			u64 required_features,
 			bool nocrc)
 {
 	msgr->supported_features = supported_features;
@@ -3126,15 +3149,8 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 	INIT_LIST_HEAD(&m->data);
 
 	/* front */
-	m->front_max = front_len;
 	if (front_len) {
-		if (front_len > PAGE_CACHE_SIZE) {
-			m->front.iov_base = __vmalloc(front_len, flags,
-						      PAGE_KERNEL);
-			m->front_is_vmalloc = true;
-		} else {
-			m->front.iov_base = kmalloc(front_len, flags);
-		}
+		m->front.iov_base = ceph_kvmalloc(front_len, flags);
 		if (m->front.iov_base == NULL) {
 			dout("ceph_msg_new can't allocate %d bytes\n",
 			     front_len);
@@ -3143,7 +3159,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 	} else {
 		m->front.iov_base = NULL;
 	}
-	m->front.iov_len = front_len;
+	m->front_alloc_len = m->front.iov_len = front_len;
 
 	dout("ceph_msg_new %p front %d\n", m, front_len);
 	return m;
@@ -3256,10 +3272,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
 void ceph_msg_kfree(struct ceph_msg *m)
 {
 	dout("msg_kfree %p\n", m);
-	if (m->front_is_vmalloc)
-		vfree(m->front.iov_base);
-	else
-		kfree(m->front.iov_base);
+	ceph_kvfree(m->front.iov_base);
 	kmem_cache_free(ceph_msg_cache, m);
 }
 
@@ -3301,8 +3314,8 @@ EXPORT_SYMBOL(ceph_msg_last_put);
 
 void ceph_msg_dump(struct ceph_msg *msg)
 {
-	pr_debug("msg_dump %p (front_max %d length %zd)\n", msg,
-		 msg->front_max, msg->data_length);
+	pr_debug("msg_dump %p (front_alloc_len %d length %zd)\n", msg,
+		 msg->front_alloc_len, msg->data_length);
 	print_hex_dump(KERN_DEBUG, "header: ",
 		       DUMP_PREFIX_OFFSET, 16, 1,
 		       &msg->hdr, sizeof(msg->hdr), true);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 1fe25cd29d0..067d3af2eaf 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -152,7 +152,7 @@ static int __open_session(struct ceph_mon_client *monc)
 		/* initiatiate authentication handshake */
 		ret = ceph_auth_build_hello(monc->auth,
 					    monc->m_auth->front.iov_base,
-					    monc->m_auth->front_max);
+					    monc->m_auth->front_alloc_len);
 		__send_prepared_auth_request(monc, ret);
 	} else {
 		dout("open_session mon%d already open\n", monc->cur_mon);
@@ -196,7 +196,7 @@ static void __send_subscribe(struct ceph_mon_client *monc)
 		int num;
 
 		p = msg->front.iov_base;
-		end = p + msg->front_max;
+		end = p + msg->front_alloc_len;
 
 		num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap;
 		ceph_encode_32(&p, num);
@@ -296,6 +296,33 @@ void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc)
 		__send_subscribe(monc);
 	mutex_unlock(&monc->mutex);
 }
+EXPORT_SYMBOL(ceph_monc_request_next_osdmap);
+
+int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
+			  unsigned long timeout)
+{
+	unsigned long started = jiffies;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	while (monc->have_osdmap < epoch) {
+		mutex_unlock(&monc->mutex);
+
+		if (timeout != 0 && time_after_eq(jiffies, started + timeout))
+			return -ETIMEDOUT;
+
+		ret = wait_event_interruptible_timeout(monc->client->auth_wq,
+					 monc->have_osdmap >= epoch, timeout);
+		if (ret < 0)
+			return ret;
+
+		mutex_lock(&monc->mutex);
+	}
+
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_monc_wait_osdmap);
 
 /*
  *
@@ -477,14 +504,13 @@ static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
 	return m;
 }
 
-static int do_generic_request(struct ceph_mon_client *monc,
-			      struct ceph_mon_generic_request *req)
+static int __do_generic_request(struct ceph_mon_client *monc, u64 tid,
+				struct ceph_mon_generic_request *req)
 {
 	int err;
 
 	/* register request */
-	mutex_lock(&monc->mutex);
-	req->tid = ++monc->last_tid;
+	req->tid = tid != 0 ? tid : ++monc->last_tid;
 	req->request->hdr.tid = cpu_to_le64(req->tid);
 	__insert_generic_request(monc, req);
 	monc->num_generic_requests++;
@@ -496,13 +522,24 @@ static int do_generic_request(struct ceph_mon_client *monc,
 	mutex_lock(&monc->mutex);
 	rb_erase(&req->node, &monc->generic_request_tree);
 	monc->num_generic_requests--;
-	mutex_unlock(&monc->mutex);
 
 	if (!err)
 		err = req->result;
 	return err;
 }
 
+static int do_generic_request(struct ceph_mon_client *monc,
+			      struct ceph_mon_generic_request *req)
+{
+	int err;
+
+	mutex_lock(&monc->mutex);
+	err = __do_generic_request(monc, 0, req);
+	mutex_unlock(&monc->mutex);
+
+	return err;
+}
+
 /*
  * statfs
  */
@@ -579,6 +616,96 @@ out:
 }
 EXPORT_SYMBOL(ceph_monc_do_statfs);
 
+static void handle_get_version_reply(struct ceph_mon_client *monc,
+				     struct ceph_msg *msg)
+{
+	struct ceph_mon_generic_request *req;
+	u64 tid = le64_to_cpu(msg->hdr.tid);
+	void *p = msg->front.iov_base;
+	void *end = p + msg->front_alloc_len;
+	u64 handle;
+
+	dout("%s %p tid %llu\n", __func__, msg, tid);
+
+	ceph_decode_need(&p, end, 2*sizeof(u64), bad);
+	handle = ceph_decode_64(&p);
+	if (tid != 0 && tid != handle)
+		goto bad;
+
+	mutex_lock(&monc->mutex);
+	req = __lookup_generic_req(monc, handle);
+	if (req) {
+		*(u64 *)req->buf = ceph_decode_64(&p);
+		req->result = 0;
+		get_generic_request(req);
+	}
+	mutex_unlock(&monc->mutex);
+	if (req) {
+		complete_all(&req->completion);
+		put_generic_request(req);
+	}
+
+	return;
+bad:
+	pr_err("corrupt mon_get_version reply\n");
+	ceph_msg_dump(msg);
+}
+
+/*
+ * Send MMonGetVersion and wait for the reply.
+ *
+ * @what: one of "mdsmap", "osdmap" or "monmap"
+ */
+int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what,
+			     u64 *newest)
+{
+	struct ceph_mon_generic_request *req;
+	void *p, *end;
+	u64 tid;
+	int err;
+
+	req = kzalloc(sizeof(*req), GFP_NOFS);
+	if (!req)
+		return -ENOMEM;
+
+	kref_init(&req->kref);
+	req->buf = newest;
+	req->buf_len = sizeof(*newest);
+	init_completion(&req->completion);
+
+	req->request = ceph_msg_new(CEPH_MSG_MON_GET_VERSION,
+				    sizeof(u64) + sizeof(u32) + strlen(what),
+				    GFP_NOFS, true);
+	if (!req->request) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	req->reply = ceph_msg_new(CEPH_MSG_MON_GET_VERSION_REPLY, 1024,
+				  GFP_NOFS, true);
+	if (!req->reply) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	p = req->request->front.iov_base;
+	end = p + req->request->front_alloc_len;
+
+	/* fill out request */
+	mutex_lock(&monc->mutex);
+	tid = ++monc->last_tid;
+	ceph_encode_64(&p, tid); /* handle */
+	ceph_encode_string(&p, end, what, strlen(what));
+
+	err = __do_generic_request(monc, tid, req);
+
+	mutex_unlock(&monc->mutex);
+out:
+	kref_put(&req->kref, release_generic_request);
+	return err;
+}
+EXPORT_SYMBOL(ceph_monc_do_get_version);
+
 /*
  * pool ops
  */
@@ -897,7 +1024,7 @@ static void handle_auth_reply(struct ceph_mon_client *monc,
 	ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base,
 				     msg->front.iov_len,
 				     monc->m_auth->front.iov_base,
-				     monc->m_auth->front_max);
+				     monc->m_auth->front_alloc_len);
 	if (ret < 0) {
 		monc->client->auth_err = ret;
 		wake_up_all(&monc->client->auth_wq);
@@ -939,7 +1066,7 @@ static int __validate_auth(struct ceph_mon_client *monc)
 		return 0;
 
 	ret = ceph_build_auth(monc->auth, monc->m_auth->front.iov_base,
-			      monc->m_auth->front_max);
+			      monc->m_auth->front_alloc_len);
 	if (ret <= 0)
 		return ret; /* either an error, or no need to authenticate */
 	__send_prepared_auth_request(monc, ret);
@@ -981,6 +1108,10 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 		handle_statfs_reply(monc, msg);
 		break;
 
+	case CEPH_MSG_MON_GET_VERSION_REPLY:
+		handle_get_version_reply(monc, msg);
+		break;
+
 	case CEPH_MSG_POOLOP_REPLY:
 		handle_poolop_reply(monc, msg);
 		break;
@@ -1029,6 +1160,15 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 	case CEPH_MSG_AUTH_REPLY:
 		m = ceph_msg_get(monc->m_auth_reply);
 		break;
+	case CEPH_MSG_MON_GET_VERSION_REPLY:
+		if (le64_to_cpu(hdr->tid) != 0)
+			return get_generic_reply(con, hdr, skip);
+
+		/*
+		 * Older OSDs don't set reply tid even if the orignal
+		 * request had a non-zero tid.  Workaround this weirdness
+		 * by falling through to the allocate case.
+		 */
 	case CEPH_MSG_MON_MAP:
 	case CEPH_MSG_MDS_MAP:
 	case CEPH_MSG_OSD_MAP:
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 2b4b32aaa89..05be0c18169 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -338,7 +338,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 	msg_size = 4 + 4 + 8 + 8 + 4+8;
 	msg_size += 2 + 4 + 8 + 4 + 4; /* oloc */
 	msg_size += 1 + 8 + 4 + 4;     /* pg_t */
-	msg_size += 4 + MAX_OBJ_NAME_SIZE;
+	msg_size += 4 + CEPH_MAX_OID_NAME_LEN; /* oid */
 	msg_size += 2 + num_ops*sizeof(struct ceph_osd_op);
 	msg_size += 8;  /* snapid */
 	msg_size += 8;  /* snap_seq */
@@ -368,6 +368,9 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 	INIT_LIST_HEAD(&req->r_req_lru_item);
 	INIT_LIST_HEAD(&req->r_osd_item);
 
+	req->r_base_oloc.pool = -1;
+	req->r_target_oloc.pool = -1;
+
 	/* create reply message */
 	if (use_mempool)
 		msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
@@ -433,6 +436,7 @@ static bool osd_req_opcode_valid(u16 opcode)
 	case CEPH_OSD_OP_OMAPCLEAR:
 	case CEPH_OSD_OP_OMAPRMKEYS:
 	case CEPH_OSD_OP_OMAP_CMP:
+	case CEPH_OSD_OP_SETALLOCHINT:
 	case CEPH_OSD_OP_CLONERANGE:
 	case CEPH_OSD_OP_ASSERT_SRC_VERSION:
 	case CEPH_OSD_OP_SRC_CMPXATTR:
@@ -588,6 +592,26 @@ void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
 }
 EXPORT_SYMBOL(osd_req_op_watch_init);
 
+void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
+				unsigned int which,
+				u64 expected_object_size,
+				u64 expected_write_size)
+{
+	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
+						      CEPH_OSD_OP_SETALLOCHINT);
+
+	op->alloc_hint.expected_object_size = expected_object_size;
+	op->alloc_hint.expected_write_size = expected_write_size;
+
+	/*
+	 * CEPH_OSD_OP_SETALLOCHINT op is advisory and therefore deemed
+	 * not worth a feature bit.  Set FAILOK per-op flag to make
+	 * sure older osds don't trip over an unsupported opcode.
+	 */
+	op->flags |= CEPH_OSD_OP_FLAG_FAILOK;
+}
+EXPORT_SYMBOL(osd_req_op_alloc_hint_init);
+
 static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
 				struct ceph_osd_data *osd_data)
 {
@@ -678,6 +702,12 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 		dst->watch.ver = cpu_to_le64(src->watch.ver);
 		dst->watch.flag = src->watch.flag;
 		break;
+	case CEPH_OSD_OP_SETALLOCHINT:
+		dst->alloc_hint.expected_object_size =
+		    cpu_to_le64(src->alloc_hint.expected_object_size);
+		dst->alloc_hint.expected_write_size =
+		    cpu_to_le64(src->alloc_hint.expected_write_size);
+		break;
 	default:
 		pr_err("unsupported osd opcode %s\n",
 			ceph_osd_op_name(src->op));
@@ -685,7 +715,9 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 
 		return 0;
 	}
+
 	dst->op = cpu_to_le16(src->op);
+	dst->flags = cpu_to_le32(src->flags);
 	dst->payload_len = cpu_to_le32(src->payload_len);
 
 	return request_data_len;
@@ -761,11 +793,11 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	if (num_ops > 1)
 		osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC);
 
-	req->r_file_layout = *layout;  /* keep a copy */
+	req->r_base_oloc.pool = ceph_file_layout_pg_pool(*layout);
 
-	snprintf(req->r_oid, sizeof(req->r_oid), "%llx.%08llx",
-		vino.ino, objnum);
-	req->r_oid_len = strlen(req->r_oid);
+	snprintf(req->r_base_oid.name, sizeof(req->r_base_oid.name),
+		 "%llx.%08llx", vino.ino, objnum);
+	req->r_base_oid.name_len = strlen(req->r_base_oid.name);
 
 	return req;
 }
@@ -1044,8 +1076,8 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 			!ceph_con_opened(&osd->o_con)) {
 		struct ceph_osd_request *req;
 
-		dout(" osd addr hasn't changed and connection never opened,"
-		     " letting msgr retry");
+		dout("osd addr hasn't changed and connection never opened, "
+		     "letting msgr retry\n");
 		/* touch each r_stamp for handle_timeout()'s benfit */
 		list_for_each_entry(req, &osd->o_requests, r_osd_item)
 			req->r_stamp = jiffies;
@@ -1232,6 +1264,61 @@ void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc,
 EXPORT_SYMBOL(ceph_osdc_set_request_linger);
 
 /*
+ * Returns whether a request should be blocked from being sent
+ * based on the current osdmap and osd_client settings.
+ *
+ * Caller should hold map_sem for read.
+ */
+static bool __req_should_be_paused(struct ceph_osd_client *osdc,
+				   struct ceph_osd_request *req)
+{
+	bool pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
+	bool pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
+		ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+	return (req->r_flags & CEPH_OSD_FLAG_READ && pauserd) ||
+		(req->r_flags & CEPH_OSD_FLAG_WRITE && pausewr);
+}
+
+/*
+ * Calculate mapping of a request to a PG.  Takes tiering into account.
+ */
+static int __calc_request_pg(struct ceph_osdmap *osdmap,
+			     struct ceph_osd_request *req,
+			     struct ceph_pg *pg_out)
+{
+	bool need_check_tiering;
+
+	need_check_tiering = false;
+	if (req->r_target_oloc.pool == -1) {
+		req->r_target_oloc = req->r_base_oloc; /* struct */
+		need_check_tiering = true;
+	}
+	if (req->r_target_oid.name_len == 0) {
+		ceph_oid_copy(&req->r_target_oid, &req->r_base_oid);
+		need_check_tiering = true;
+	}
+
+	if (need_check_tiering &&
+	    (req->r_flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) {
+		struct ceph_pg_pool_info *pi;
+
+		pi = ceph_pg_pool_by_id(osdmap, req->r_target_oloc.pool);
+		if (pi) {
+			if ((req->r_flags & CEPH_OSD_FLAG_READ) &&
+			    pi->read_tier >= 0)
+				req->r_target_oloc.pool = pi->read_tier;
+			if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
+			    pi->write_tier >= 0)
+				req->r_target_oloc.pool = pi->write_tier;
+		}
+		/* !pi is caught in ceph_oloc_oid_to_pg() */
+	}
+
+	return ceph_oloc_oid_to_pg(osdmap, &req->r_target_oloc,
+				   &req->r_target_oid, pg_out);
+}
+
+/*
  * Pick an osd (the first 'up' osd in the pg), allocate the osd struct
  * (as needed), and set the request r_osd appropriately.  If there is
  * no up osd, set r_osd to NULL.  Move the request to the appropriate list
@@ -1246,30 +1333,35 @@ static int __map_request(struct ceph_osd_client *osdc,
 {
 	struct ceph_pg pgid;
 	int acting[CEPH_PG_MAX_SIZE];
-	int o = -1, num = 0;
+	int num, o;
 	int err;
+	bool was_paused;
 
 	dout("map_request %p tid %lld\n", req, req->r_tid);
-	err = ceph_calc_ceph_pg(&pgid, req->r_oid, osdc->osdmap,
-				ceph_file_layout_pg_pool(req->r_file_layout));
+
+	err = __calc_request_pg(osdc->osdmap, req, &pgid);
 	if (err) {
 		list_move(&req->r_req_lru_item, &osdc->req_notarget);
 		return err;
 	}
 	req->r_pgid = pgid;
 
-	err = ceph_calc_pg_acting(osdc->osdmap, pgid, acting);
-	if (err > 0) {
-		o = acting[0];
-		num = err;
-	}
+	num = ceph_calc_pg_acting(osdc->osdmap, pgid, acting, &o);
+	if (num < 0)
+		num = 0;
+
+	was_paused = req->r_paused;
+	req->r_paused = __req_should_be_paused(osdc, req);
+	if (was_paused && !req->r_paused)
+		force_resend = 1;
 
 	if ((!force_resend &&
 	     req->r_osd && req->r_osd->o_osd == o &&
 	     req->r_sent >= req->r_osd->o_incarnation &&
 	     req->r_num_pg_osds == num &&
 	     memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) ||
-	    (req->r_osd == NULL && o == -1))
+	    (req->r_osd == NULL && o == -1) ||
+	    req->r_paused)
 		return 0;  /* no change */
 
 	dout("map_request tid %llu pgid %lld.%x osd%d (was osd%d)\n",
@@ -1331,7 +1423,7 @@ static void __send_request(struct ceph_osd_client *osdc,
 	/* fill in message content that changes each time we send it */
 	put_unaligned_le32(osdc->osdmap->epoch, req->r_request_osdmap_epoch);
 	put_unaligned_le32(req->r_flags, req->r_request_flags);
-	put_unaligned_le64(req->r_pgid.pool, req->r_request_pool);
+	put_unaligned_le64(req->r_target_oloc.pool, req->r_request_pool);
 	p = req->r_request_pgid;
 	ceph_encode_64(&p, req->r_pgid.pool);
 	ceph_encode_32(&p, req->r_pgid.seed);
@@ -1362,6 +1454,40 @@ static void __send_queued(struct ceph_osd_client *osdc)
 }
 
 /*
+ * Caller should hold map_sem for read and request_mutex.
+ */
+static int __ceph_osdc_start_request(struct ceph_osd_client *osdc,
+				     struct ceph_osd_request *req,
+				     bool nofail)
+{
+	int rc;
+
+	__register_request(osdc, req);
+	req->r_sent = 0;
+	req->r_got_reply = 0;
+	rc = __map_request(osdc, req, 0);
+	if (rc < 0) {
+		if (nofail) {
+			dout("osdc_start_request failed map, "
+				" will retry %lld\n", req->r_tid);
+			rc = 0;
+		} else {
+			__unregister_request(osdc, req);
+		}
+		return rc;
+	}
+
+	if (req->r_osd == NULL) {
+		dout("send_request %p no up osds in pg\n", req);
+		ceph_monc_request_next_osdmap(&osdc->client->monc);
+	} else {
+		__send_queued(osdc);
+	}
+
+	return 0;
+}
+
+/*
  * Timeout callback, called every N seconds when 1 or more osd
  * requests has been active for more than N seconds.  When this
  * happens, we ping all OSDs with requests who have timed out to
@@ -1432,6 +1558,109 @@ static void handle_osds_timeout(struct work_struct *work)
 			      round_jiffies_relative(delay));
 }
 
+static int ceph_oloc_decode(void **p, void *end,
+			    struct ceph_object_locator *oloc)
+{
+	u8 struct_v, struct_cv;
+	u32 len;
+	void *struct_end;
+	int ret = 0;
+
+	ceph_decode_need(p, end, 1 + 1 + 4, e_inval);
+	struct_v = ceph_decode_8(p);
+	struct_cv = ceph_decode_8(p);
+	if (struct_v < 3) {
+		pr_warn("got v %d < 3 cv %d of ceph_object_locator\n",
+			struct_v, struct_cv);
+		goto e_inval;
+	}
+	if (struct_cv > 6) {
+		pr_warn("got v %d cv %d > 6 of ceph_object_locator\n",
+			struct_v, struct_cv);
+		goto e_inval;
+	}
+	len = ceph_decode_32(p);
+	ceph_decode_need(p, end, len, e_inval);
+	struct_end = *p + len;
+
+	oloc->pool = ceph_decode_64(p);
+	*p += 4; /* skip preferred */
+
+	len = ceph_decode_32(p);
+	if (len > 0) {
+		pr_warn("ceph_object_locator::key is set\n");
+		goto e_inval;
+	}
+
+	if (struct_v >= 5) {
+		len = ceph_decode_32(p);
+		if (len > 0) {
+			pr_warn("ceph_object_locator::nspace is set\n");
+			goto e_inval;
+		}
+	}
+
+	if (struct_v >= 6) {
+		s64 hash = ceph_decode_64(p);
+		if (hash != -1) {
+			pr_warn("ceph_object_locator::hash is set\n");
+			goto e_inval;
+		}
+	}
+
+	/* skip the rest */
+	*p = struct_end;
+out:
+	return ret;
+
+e_inval:
+	ret = -EINVAL;
+	goto out;
+}
+
+static int ceph_redirect_decode(void **p, void *end,
+				struct ceph_request_redirect *redir)
+{
+	u8 struct_v, struct_cv;
+	u32 len;
+	void *struct_end;
+	int ret;
+
+	ceph_decode_need(p, end, 1 + 1 + 4, e_inval);
+	struct_v = ceph_decode_8(p);
+	struct_cv = ceph_decode_8(p);
+	if (struct_cv > 1) {
+		pr_warn("got v %d cv %d > 1 of ceph_request_redirect\n",
+			struct_v, struct_cv);
+		goto e_inval;
+	}
+	len = ceph_decode_32(p);
+	ceph_decode_need(p, end, len, e_inval);
+	struct_end = *p + len;
+
+	ret = ceph_oloc_decode(p, end, &redir->oloc);
+	if (ret)
+		goto out;
+
+	len = ceph_decode_32(p);
+	if (len > 0) {
+		pr_warn("ceph_request_redirect::object_name is set\n");
+		goto e_inval;
+	}
+
+	len = ceph_decode_32(p);
+	*p += len; /* skip osd_instructions */
+
+	/* skip the rest */
+	*p = struct_end;
+out:
+	return ret;
+
+e_inval:
+	ret = -EINVAL;
+	goto out;
+}
+
 static void complete_request(struct ceph_osd_request *req)
 {
 	complete_all(&req->r_safe_completion);  /* fsync waiter */
@@ -1446,6 +1675,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 {
 	void *p, *end;
 	struct ceph_osd_request *req;
+	struct ceph_request_redirect redir;
 	u64 tid;
 	int object_len;
 	unsigned int numops;
@@ -1484,6 +1714,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 	osdmap_epoch = ceph_decode_32(&p);
 
 	/* lookup */
+	down_read(&osdc->map_sem);
 	mutex_lock(&osdc->request_mutex);
 	req = __lookup_request(osdc, tid);
 	if (req == NULL) {
@@ -1525,10 +1756,40 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 	for (i = 0; i < numops; i++)
 		req->r_reply_op_result[i] = ceph_decode_32(&p);
 
-	already_completed = req->r_got_reply;
+	if (le16_to_cpu(msg->hdr.version) >= 6) {
+		p += 8 + 4; /* skip replay_version */
+		p += 8; /* skip user_version */
 
-	if (!req->r_got_reply) {
+		err = ceph_redirect_decode(&p, end, &redir);
+		if (err)
+			goto bad_put;
+	} else {
+		redir.oloc.pool = -1;
+	}
 
+	if (redir.oloc.pool != -1) {
+		dout("redirect pool %lld\n", redir.oloc.pool);
+
+		__unregister_request(osdc, req);
+
+		req->r_target_oloc = redir.oloc; /* struct */
+
+		/*
+		 * Start redirect requests with nofail=true.  If
+		 * mapping fails, request will end up on the notarget
+		 * list, waiting for the new osdmap (which can take
+		 * a while), even though the original request mapped
+		 * successfully.  In the future we might want to follow
+		 * original request's nofail setting here.
+		 */
+		err = __ceph_osdc_start_request(osdc, req, true);
+		BUG_ON(err);
+
+		goto out_unlock;
+	}
+
+	already_completed = req->r_got_reply;
+	if (!req->r_got_reply) {
 		req->r_result = result;
 		dout("handle_reply result %d bytes %d\n", req->r_result,
 		     bytes);
@@ -1542,8 +1803,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 		req->r_got_reply = 1;
 	} else if ((flags & CEPH_OSD_FLAG_ONDISK) == 0) {
 		dout("handle_reply tid %llu dup ack\n", tid);
-		mutex_unlock(&osdc->request_mutex);
-		goto done;
+		goto out_unlock;
 	}
 
 	dout("handle_reply tid %llu flags %d\n", tid, flags);
@@ -1558,6 +1818,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 		__unregister_request(osdc, req);
 
 	mutex_unlock(&osdc->request_mutex);
+	up_read(&osdc->map_sem);
 
 	if (!already_completed) {
 		if (req->r_unsafe_callback &&
@@ -1575,15 +1836,27 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 		complete_request(req);
 	}
 
-done:
+out:
 	dout("req=%p req->r_linger=%d\n", req, req->r_linger);
 	ceph_osdc_put_request(req);
 	return;
+out_unlock:
+	mutex_unlock(&osdc->request_mutex);
+	up_read(&osdc->map_sem);
+	goto out;
 
 bad_put:
+	req->r_result = -EIO;
+	__unregister_request(osdc, req);
+	if (req->r_callback)
+		req->r_callback(req, msg);
+	else
+		complete_all(&req->r_completion);
+	complete_request(req);
 	ceph_osdc_put_request(req);
 bad_mutex:
 	mutex_unlock(&osdc->request_mutex);
+	up_read(&osdc->map_sem);
 bad:
 	pr_err("corrupt osd_op_reply got %d %d\n",
 	       (int)msg->front.iov_len, le32_to_cpu(msg->hdr.front_len));
@@ -1613,14 +1886,17 @@ static void reset_changed_osds(struct ceph_osd_client *osdc)
  *
  * Caller should hold map_sem for read.
  */
-static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
+static void kick_requests(struct ceph_osd_client *osdc, bool force_resend,
+			  bool force_resend_writes)
 {
 	struct ceph_osd_request *req, *nreq;
 	struct rb_node *p;
 	int needmap = 0;
 	int err;
+	bool force_resend_req;
 
-	dout("kick_requests %s\n", force_resend ? " (force resend)" : "");
+	dout("kick_requests %s %s\n", force_resend ? " (force resend)" : "",
+		force_resend_writes ? " (force resend writes)" : "");
 	mutex_lock(&osdc->request_mutex);
 	for (p = rb_first(&osdc->requests); p; ) {
 		req = rb_entry(p, struct ceph_osd_request, r_node);
@@ -1645,7 +1921,10 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 			continue;
 		}
 
-		err = __map_request(osdc, req, force_resend);
+		force_resend_req = force_resend ||
+			(force_resend_writes &&
+				req->r_flags & CEPH_OSD_FLAG_WRITE);
+		err = __map_request(osdc, req, force_resend_req);
 		if (err < 0)
 			continue;  /* error */
 		if (req->r_osd == NULL) {
@@ -1665,7 +1944,8 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 				 r_linger_item) {
 		dout("linger req=%p req->r_osd=%p\n", req, req->r_osd);
 
-		err = __map_request(osdc, req, force_resend);
+		err = __map_request(osdc, req,
+				    force_resend || force_resend_writes);
 		dout("__map_request returned %d\n", err);
 		if (err == 0)
 			continue;  /* no change and no osd was specified */
@@ -1707,6 +1987,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 	struct ceph_osdmap *newmap = NULL, *oldmap;
 	int err;
 	struct ceph_fsid fsid;
+	bool was_full;
 
 	dout("handle_map have %u\n", osdc->osdmap ? osdc->osdmap->epoch : 0);
 	p = msg->front.iov_base;
@@ -1720,6 +2001,8 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 
 	down_write(&osdc->map_sem);
 
+	was_full = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+
 	/* incremental maps */
 	ceph_decode_32_safe(&p, end, nr_maps, bad);
 	dout(" %d inc maps\n", nr_maps);
@@ -1744,7 +2027,10 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 				ceph_osdmap_destroy(osdc->osdmap);
 				osdc->osdmap = newmap;
 			}
-			kick_requests(osdc, 0);
+			was_full = was_full ||
+				ceph_osdmap_flag(osdc->osdmap,
+						 CEPH_OSDMAP_FULL);
+			kick_requests(osdc, 0, was_full);
 		} else {
 			dout("ignoring incremental map %u len %d\n",
 			     epoch, maplen);
@@ -1774,7 +2060,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 			int skipped_map = 0;
 
 			dout("taking full map %u len %d\n", epoch, maplen);
-			newmap = osdmap_decode(&p, p+maplen);
+			newmap = ceph_osdmap_decode(&p, p+maplen);
 			if (IS_ERR(newmap)) {
 				err = PTR_ERR(newmap);
 				goto bad;
@@ -1787,7 +2073,10 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 					skipped_map = 1;
 				ceph_osdmap_destroy(oldmap);
 			}
-			kick_requests(osdc, skipped_map);
+			was_full = was_full ||
+				ceph_osdmap_flag(osdc->osdmap,
+						 CEPH_OSDMAP_FULL);
+			kick_requests(osdc, skipped_map, was_full);
 		}
 		p += maplen;
 		nr_maps--;
@@ -1804,7 +2093,9 @@ done:
 	 * we find out when we are no longer full and stop returning
 	 * ENOSPC.
 	 */
-	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL))
+	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+		ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD) ||
+		ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR))
 		ceph_monc_request_next_osdmap(&osdc->client->monc);
 
 	mutex_lock(&osdc->request_mutex);
@@ -1818,7 +2109,6 @@ bad:
 	pr_err("osdc handle_map corrupt msg\n");
 	ceph_msg_dump(msg);
 	up_write(&osdc->map_sem);
-	return;
 }
 
 /*
@@ -2017,7 +2307,6 @@ done_err:
 
 bad:
 	pr_err("osdc handle_watch_notify corrupt msg\n");
-	return;
 }
 
 /*
@@ -2068,10 +2357,11 @@ void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off,
 	ceph_encode_32(&p, -1);  /* preferred */
 
 	/* oid */
-	ceph_encode_32(&p, req->r_oid_len);
-	memcpy(p, req->r_oid, req->r_oid_len);
-	dout("oid '%.*s' len %d\n", req->r_oid_len, req->r_oid, req->r_oid_len);
-	p += req->r_oid_len;
+	ceph_encode_32(&p, req->r_base_oid.name_len);
+	memcpy(p, req->r_base_oid.name, req->r_base_oid.name_len);
+	dout("oid '%.*s' len %d\n", req->r_base_oid.name_len,
+	     req->r_base_oid.name, req->r_base_oid.name_len);
+	p += req->r_base_oid.name_len;
 
 	/* ops--can imply data */
 	ceph_encode_16(&p, (u16)req->r_num_ops);
@@ -2125,34 +2415,16 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
 			    struct ceph_osd_request *req,
 			    bool nofail)
 {
-	int rc = 0;
+	int rc;
 
 	down_read(&osdc->map_sem);
 	mutex_lock(&osdc->request_mutex);
-	__register_request(osdc, req);
-	req->r_sent = 0;
-	req->r_got_reply = 0;
-	rc = __map_request(osdc, req, 0);
-	if (rc < 0) {
-		if (nofail) {
-			dout("osdc_start_request failed map, "
-				" will retry %lld\n", req->r_tid);
-			rc = 0;
-		} else {
-			__unregister_request(osdc, req);
-		}
-		goto out_unlock;
-	}
-	if (req->r_osd == NULL) {
-		dout("send_request %p no up osds in pg\n", req);
-		ceph_monc_request_next_osdmap(&osdc->client->monc);
-	} else {
-		__send_queued(osdc);
-	}
-	rc = 0;
-out_unlock:
+
+	rc = __ceph_osdc_start_request(osdc, req, nofail);
+
 	mutex_unlock(&osdc->request_mutex);
 	up_read(&osdc->map_sem);
+
 	return rc;
 }
 EXPORT_SYMBOL(ceph_osdc_start_request);
@@ -2219,7 +2491,7 @@ EXPORT_SYMBOL(ceph_osdc_sync);
  * Call all pending notify callbacks - for use after a watch is
  * unregistered, to make sure no more callbacks for it will be invoked
  */
-extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc)
+void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc)
 {
 	flush_workqueue(osdc->notify_wq);
 }
@@ -2278,9 +2550,12 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
 	err = -ENOMEM;
 	osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify");
 	if (!osdc->notify_wq)
-		goto out_msgpool;
+		goto out_msgpool_reply;
+
 	return 0;
 
+out_msgpool_reply:
+	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
 out_msgpool:
 	ceph_msgpool_destroy(&osdc->msgpool_op);
 out_mempool:
@@ -2454,7 +2729,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	struct ceph_osd_client *osdc = osd->o_osdc;
 	struct ceph_msg *m;
 	struct ceph_osd_request *req;
-	int front = le32_to_cpu(hdr->front_len);
+	int front_len = le32_to_cpu(hdr->front_len);
 	int data_len = le32_to_cpu(hdr->data_len);
 	u64 tid;
 
@@ -2474,12 +2749,13 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 		     req->r_reply, req->r_reply->con);
 	ceph_msg_revoke_incoming(req->r_reply);
 
-	if (front > req->r_reply->front.iov_len) {
+	if (front_len > req->r_reply->front_alloc_len) {
 		pr_warning("get_reply front %d > preallocated %d (%u#%llu)\n",
-			   front, (int)req->r_reply->front.iov_len,
+			   front_len, req->r_reply->front_alloc_len,
 			   (unsigned int)con->peer_name.type,
 			   le64_to_cpu(con->peer_name.num));
-		m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front, GFP_NOFS, false);
+		m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS,
+				 false);
 		if (!m)
 			goto out;
 		ceph_msg_put(req->r_reply);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index dbd9a479242..c547e46084d 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -329,6 +329,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	dout("crush decode tunable chooseleaf_descend_once = %d",
 	     c->chooseleaf_descend_once);
 
+	ceph_decode_need(p, end, sizeof(u8), done);
+	c->chooseleaf_vary_r = ceph_decode_8(p);
+	dout("crush decode tunable chooseleaf_vary_r = %d",
+	     c->chooseleaf_vary_r);
+
 done:
 	dout("crush_decode success\n");
 	return c;
@@ -343,7 +348,7 @@ bad:
 
 /*
  * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
- * to a set of osds)
+ * to a set of osds) and primary_temp (explicit primary setting)
  */
 static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
 {
@@ -464,6 +469,11 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, u64 id)
 	return NULL;
 }
 
+struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id)
+{
+	return __lookup_pg_pool(&map->pg_pools, id);
+}
+
 const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id)
 {
 	struct ceph_pg_pool_info *pi;
@@ -501,7 +511,7 @@ static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
 	kfree(pi);
 }
 
-static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
+static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
 {
 	u8 ev, cv;
 	unsigned len, num;
@@ -514,8 +524,8 @@ static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
 		pr_warning("got v %d < 5 cv %d of ceph_pg_pool\n", ev, cv);
 		return -EINVAL;
 	}
-	if (cv > 7) {
-		pr_warning("got v %d cv %d > 7 of ceph_pg_pool\n", ev, cv);
+	if (cv > 9) {
+		pr_warning("got v %d cv %d > 9 of ceph_pg_pool\n", ev, cv);
 		return -EINVAL;
 	}
 	len = ceph_decode_32(p);
@@ -543,12 +553,34 @@ static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
 		*p += len;
 	}
 
-	/* skip removed snaps */
+	/* skip removed_snaps */
 	num = ceph_decode_32(p);
 	*p += num * (8 + 8);
 
 	*p += 8;  /* skip auid */
 	pi->flags = ceph_decode_64(p);
+	*p += 4;  /* skip crash_replay_interval */
+
+	if (ev >= 7)
+		*p += 1;  /* skip min_size */
+
+	if (ev >= 8)
+		*p += 8 + 8;  /* skip quota_max_* */
+
+	if (ev >= 9) {
+		/* skip tiers */
+		num = ceph_decode_32(p);
+		*p += num * 8;
+
+		*p += 8;  /* skip tier_of */
+		*p += 1;  /* skip cache_mode */
+
+		pi->read_tier = ceph_decode_64(p);
+		pi->write_tier = ceph_decode_64(p);
+	} else {
+		pi->read_tier = -1;
+		pi->write_tier = -1;
+	}
 
 	/* ignore the rest */
 
@@ -560,7 +592,7 @@ bad:
 	return -EINVAL;
 }
 
-static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
+static int decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
 {
 	struct ceph_pg_pool_info *pi;
 	u32 num, len;
@@ -606,6 +638,13 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
 		rb_erase(&pg->node, &map->pg_temp);
 		kfree(pg);
 	}
+	while (!RB_EMPTY_ROOT(&map->primary_temp)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(rb_first(&map->primary_temp),
+				 struct ceph_pg_mapping, node);
+		rb_erase(&pg->node, &map->primary_temp);
+		kfree(pg);
+	}
 	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
 		struct ceph_pg_pool_info *pi =
 			rb_entry(rb_first(&map->pg_pools),
@@ -615,186 +654,516 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
 	kfree(map->osd_state);
 	kfree(map->osd_weight);
 	kfree(map->osd_addr);
+	kfree(map->osd_primary_affinity);
 	kfree(map);
 }
 
 /*
- * adjust max osd value.  reallocate arrays.
+ * Adjust max_osd value, (re)allocate arrays.
+ *
+ * The new elements are properly initialized.
  */
 static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
 {
 	u8 *state;
-	struct ceph_entity_addr *addr;
 	u32 *weight;
+	struct ceph_entity_addr *addr;
+	int i;
 
-	state = kcalloc(max, sizeof(*state), GFP_NOFS);
-	addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
-	weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
-	if (state == NULL || addr == NULL || weight == NULL) {
+	state = krealloc(map->osd_state, max*sizeof(*state), GFP_NOFS);
+	weight = krealloc(map->osd_weight, max*sizeof(*weight), GFP_NOFS);
+	addr = krealloc(map->osd_addr, max*sizeof(*addr), GFP_NOFS);
+	if (!state || !weight || !addr) {
 		kfree(state);
-		kfree(addr);
 		kfree(weight);
+		kfree(addr);
+
 		return -ENOMEM;
 	}
 
-	/* copy old? */
-	if (map->osd_state) {
-		memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
-		memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
-		memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
-		kfree(map->osd_state);
-		kfree(map->osd_addr);
-		kfree(map->osd_weight);
+	for (i = map->max_osd; i < max; i++) {
+		state[i] = 0;
+		weight[i] = CEPH_OSD_OUT;
+		memset(addr + i, 0, sizeof(*addr));
 	}
 
 	map->osd_state = state;
 	map->osd_weight = weight;
 	map->osd_addr = addr;
+
+	if (map->osd_primary_affinity) {
+		u32 *affinity;
+
+		affinity = krealloc(map->osd_primary_affinity,
+				    max*sizeof(*affinity), GFP_NOFS);
+		if (!affinity)
+			return -ENOMEM;
+
+		for (i = map->max_osd; i < max; i++)
+			affinity[i] = CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+
+		map->osd_primary_affinity = affinity;
+	}
+
 	map->max_osd = max;
+
 	return 0;
 }
 
+#define OSDMAP_WRAPPER_COMPAT_VER	7
+#define OSDMAP_CLIENT_DATA_COMPAT_VER	1
+
 /*
- * decode a full map.
+ * Return 0 or error.  On success, *v is set to 0 for old (v6) osdmaps,
+ * to struct_v of the client_data section for new (v7 and above)
+ * osdmaps.
  */
-struct ceph_osdmap *osdmap_decode(void **p, void *end)
+static int get_osdmap_client_data_v(void **p, void *end,
+				    const char *prefix, u8 *v)
 {
-	struct ceph_osdmap *map;
-	u16 version;
-	u32 len, max, i;
-	int err = -EINVAL;
-	void *start = *p;
-	struct ceph_pg_pool_info *pi;
+	u8 struct_v;
+
+	ceph_decode_8_safe(p, end, struct_v, e_inval);
+	if (struct_v >= 7) {
+		u8 struct_compat;
+
+		ceph_decode_8_safe(p, end, struct_compat, e_inval);
+		if (struct_compat > OSDMAP_WRAPPER_COMPAT_VER) {
+			pr_warning("got v %d cv %d > %d of %s ceph_osdmap\n",
+				   struct_v, struct_compat,
+				   OSDMAP_WRAPPER_COMPAT_VER, prefix);
+			return -EINVAL;
+		}
+		*p += 4; /* ignore wrapper struct_len */
+
+		ceph_decode_8_safe(p, end, struct_v, e_inval);
+		ceph_decode_8_safe(p, end, struct_compat, e_inval);
+		if (struct_compat > OSDMAP_CLIENT_DATA_COMPAT_VER) {
+			pr_warning("got v %d cv %d > %d of %s ceph_osdmap client data\n",
+				   struct_v, struct_compat,
+				   OSDMAP_CLIENT_DATA_COMPAT_VER, prefix);
+			return -EINVAL;
+		}
+		*p += 4; /* ignore client data struct_len */
+	} else {
+		u16 version;
+
+		*p -= 1;
+		ceph_decode_16_safe(p, end, version, e_inval);
+		if (version < 6) {
+			pr_warning("got v %d < 6 of %s ceph_osdmap\n", version,
+				   prefix);
+			return -EINVAL;
+		}
 
-	dout("osdmap_decode %p to %p len %d\n", *p, end, (int)(end - *p));
+		/* old osdmap enconding */
+		struct_v = 0;
+	}
 
-	map = kzalloc(sizeof(*map), GFP_NOFS);
-	if (map == NULL)
-		return ERR_PTR(-ENOMEM);
-	map->pg_temp = RB_ROOT;
+	*v = struct_v;
+	return 0;
 
-	ceph_decode_16_safe(p, end, version, bad);
-	if (version > 6) {
-		pr_warning("got unknown v %d > 6 of osdmap\n", version);
-		goto bad;
+e_inval:
+	return -EINVAL;
+}
+
+static int __decode_pools(void **p, void *end, struct ceph_osdmap *map,
+			  bool incremental)
+{
+	u32 n;
+
+	ceph_decode_32_safe(p, end, n, e_inval);
+	while (n--) {
+		struct ceph_pg_pool_info *pi;
+		u64 pool;
+		int ret;
+
+		ceph_decode_64_safe(p, end, pool, e_inval);
+
+		pi = __lookup_pg_pool(&map->pg_pools, pool);
+		if (!incremental || !pi) {
+			pi = kzalloc(sizeof(*pi), GFP_NOFS);
+			if (!pi)
+				return -ENOMEM;
+
+			pi->id = pool;
+
+			ret = __insert_pg_pool(&map->pg_pools, pi);
+			if (ret) {
+				kfree(pi);
+				return ret;
+			}
+		}
+
+		ret = decode_pool(p, end, pi);
+		if (ret)
+			return ret;
 	}
-	if (version < 6) {
-		pr_warning("got old v %d < 6 of osdmap\n", version);
-		goto bad;
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int decode_pools(void **p, void *end, struct ceph_osdmap *map)
+{
+	return __decode_pools(p, end, map, false);
+}
+
+static int decode_new_pools(void **p, void *end, struct ceph_osdmap *map)
+{
+	return __decode_pools(p, end, map, true);
+}
+
+static int __decode_pg_temp(void **p, void *end, struct ceph_osdmap *map,
+			    bool incremental)
+{
+	u32 n;
+
+	ceph_decode_32_safe(p, end, n, e_inval);
+	while (n--) {
+		struct ceph_pg pgid;
+		u32 len, i;
+		int ret;
+
+		ret = ceph_decode_pgid(p, end, &pgid);
+		if (ret)
+			return ret;
+
+		ceph_decode_32_safe(p, end, len, e_inval);
+
+		ret = __remove_pg_mapping(&map->pg_temp, pgid);
+		BUG_ON(!incremental && ret != -ENOENT);
+
+		if (!incremental || len > 0) {
+			struct ceph_pg_mapping *pg;
+
+			ceph_decode_need(p, end, len*sizeof(u32), e_inval);
+
+			if (len > (UINT_MAX - sizeof(*pg)) / sizeof(u32))
+				return -EINVAL;
+
+			pg = kzalloc(sizeof(*pg) + len*sizeof(u32), GFP_NOFS);
+			if (!pg)
+				return -ENOMEM;
+
+			pg->pgid = pgid;
+			pg->pg_temp.len = len;
+			for (i = 0; i < len; i++)
+				pg->pg_temp.osds[i] = ceph_decode_32(p);
+
+			ret = __insert_pg_mapping(pg, &map->pg_temp);
+			if (ret) {
+				kfree(pg);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int decode_pg_temp(void **p, void *end, struct ceph_osdmap *map)
+{
+	return __decode_pg_temp(p, end, map, false);
+}
+
+static int decode_new_pg_temp(void **p, void *end, struct ceph_osdmap *map)
+{
+	return __decode_pg_temp(p, end, map, true);
+}
+
+static int __decode_primary_temp(void **p, void *end, struct ceph_osdmap *map,
+				 bool incremental)
+{
+	u32 n;
+
+	ceph_decode_32_safe(p, end, n, e_inval);
+	while (n--) {
+		struct ceph_pg pgid;
+		u32 osd;
+		int ret;
+
+		ret = ceph_decode_pgid(p, end, &pgid);
+		if (ret)
+			return ret;
+
+		ceph_decode_32_safe(p, end, osd, e_inval);
+
+		ret = __remove_pg_mapping(&map->primary_temp, pgid);
+		BUG_ON(!incremental && ret != -ENOENT);
+
+		if (!incremental || osd != (u32)-1) {
+			struct ceph_pg_mapping *pg;
+
+			pg = kzalloc(sizeof(*pg), GFP_NOFS);
+			if (!pg)
+				return -ENOMEM;
+
+			pg->pgid = pgid;
+			pg->primary_temp.osd = osd;
+
+			ret = __insert_pg_mapping(pg, &map->primary_temp);
+			if (ret) {
+				kfree(pg);
+				return ret;
+			}
+		}
 	}
 
-	ceph_decode_need(p, end, 2*sizeof(u64)+6*sizeof(u32), bad);
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int decode_primary_temp(void **p, void *end, struct ceph_osdmap *map)
+{
+	return __decode_primary_temp(p, end, map, false);
+}
+
+static int decode_new_primary_temp(void **p, void *end,
+				   struct ceph_osdmap *map)
+{
+	return __decode_primary_temp(p, end, map, true);
+}
+
+u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd)
+{
+	BUG_ON(osd >= map->max_osd);
+
+	if (!map->osd_primary_affinity)
+		return CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+
+	return map->osd_primary_affinity[osd];
+}
+
+static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff)
+{
+	BUG_ON(osd >= map->max_osd);
+
+	if (!map->osd_primary_affinity) {
+		int i;
+
+		map->osd_primary_affinity = kmalloc(map->max_osd*sizeof(u32),
+						    GFP_NOFS);
+		if (!map->osd_primary_affinity)
+			return -ENOMEM;
+
+		for (i = 0; i < map->max_osd; i++)
+			map->osd_primary_affinity[i] =
+			    CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+	}
+
+	map->osd_primary_affinity[osd] = aff;
+
+	return 0;
+}
+
+static int decode_primary_affinity(void **p, void *end,
+				   struct ceph_osdmap *map)
+{
+	u32 len, i;
+
+	ceph_decode_32_safe(p, end, len, e_inval);
+	if (len == 0) {
+		kfree(map->osd_primary_affinity);
+		map->osd_primary_affinity = NULL;
+		return 0;
+	}
+	if (len != map->max_osd)
+		goto e_inval;
+
+	ceph_decode_need(p, end, map->max_osd*sizeof(u32), e_inval);
+
+	for (i = 0; i < map->max_osd; i++) {
+		int ret;
+
+		ret = set_primary_affinity(map, i, ceph_decode_32(p));
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int decode_new_primary_affinity(void **p, void *end,
+				       struct ceph_osdmap *map)
+{
+	u32 n;
+
+	ceph_decode_32_safe(p, end, n, e_inval);
+	while (n--) {
+		u32 osd, aff;
+		int ret;
+
+		ceph_decode_32_safe(p, end, osd, e_inval);
+		ceph_decode_32_safe(p, end, aff, e_inval);
+
+		ret = set_primary_affinity(map, osd, aff);
+		if (ret)
+			return ret;
+
+		pr_info("osd%d primary-affinity 0x%x\n", osd, aff);
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+/*
+ * decode a full map.
+ */
+static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
+{
+	u8 struct_v;
+	u32 epoch = 0;
+	void *start = *p;
+	u32 max;
+	u32 len, i;
+	int err;
+
+	dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p));
+
+	err = get_osdmap_client_data_v(p, end, "full", &struct_v);
+	if (err)
+		goto bad;
+
+	/* fsid, epoch, created, modified */
+	ceph_decode_need(p, end, sizeof(map->fsid) + sizeof(u32) +
+			 sizeof(map->created) + sizeof(map->modified), e_inval);
 	ceph_decode_copy(p, &map->fsid, sizeof(map->fsid));
-	map->epoch = ceph_decode_32(p);
+	epoch = map->epoch = ceph_decode_32(p);
 	ceph_decode_copy(p, &map->created, sizeof(map->created));
 	ceph_decode_copy(p, &map->modified, sizeof(map->modified));
 
-	ceph_decode_32_safe(p, end, max, bad);
-	while (max--) {
-		ceph_decode_need(p, end, 8 + 2, bad);
-		err = -ENOMEM;
-		pi = kzalloc(sizeof(*pi), GFP_NOFS);
-		if (!pi)
-			goto bad;
-		pi->id = ceph_decode_64(p);
-		err = __decode_pool(p, end, pi);
-		if (err < 0) {
-			kfree(pi);
-			goto bad;
-		}
-		__insert_pg_pool(&map->pg_pools, pi);
-	}
+	/* pools */
+	err = decode_pools(p, end, map);
+	if (err)
+		goto bad;
 
-	err = __decode_pool_names(p, end, map);
-	if (err < 0) {
-		dout("fail to decode pool names");
+	/* pool_name */
+	err = decode_pool_names(p, end, map);
+	if (err)
 		goto bad;
-	}
 
-	ceph_decode_32_safe(p, end, map->pool_max, bad);
+	ceph_decode_32_safe(p, end, map->pool_max, e_inval);
 
-	ceph_decode_32_safe(p, end, map->flags, bad);
+	ceph_decode_32_safe(p, end, map->flags, e_inval);
 
-	max = ceph_decode_32(p);
+	/* max_osd */
+	ceph_decode_32_safe(p, end, max, e_inval);
 
 	/* (re)alloc osd arrays */
 	err = osdmap_set_max_osd(map, max);
-	if (err < 0)
+	if (err)
 		goto bad;
-	dout("osdmap_decode max_osd = %d\n", map->max_osd);
 
-	/* osds */
-	err = -EINVAL;
+	/* osd_state, osd_weight, osd_addrs->client_addr */
 	ceph_decode_need(p, end, 3*sizeof(u32) +
 			 map->max_osd*(1 + sizeof(*map->osd_weight) +
-				       sizeof(*map->osd_addr)), bad);
-	*p += 4; /* skip length field (should match max) */
+				       sizeof(*map->osd_addr)), e_inval);
+
+	if (ceph_decode_32(p) != map->max_osd)
+		goto e_inval;
+
 	ceph_decode_copy(p, map->osd_state, map->max_osd);
 
-	*p += 4; /* skip length field (should match max) */
+	if (ceph_decode_32(p) != map->max_osd)
+		goto e_inval;
+
 	for (i = 0; i < map->max_osd; i++)
 		map->osd_weight[i] = ceph_decode_32(p);
 
-	*p += 4; /* skip length field (should match max) */
+	if (ceph_decode_32(p) != map->max_osd)
+		goto e_inval;
+
 	ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
 	for (i = 0; i < map->max_osd; i++)
 		ceph_decode_addr(&map->osd_addr[i]);
 
 	/* pg_temp */
-	ceph_decode_32_safe(p, end, len, bad);
-	for (i = 0; i < len; i++) {
-		int n, j;
-		struct ceph_pg pgid;
-		struct ceph_pg_mapping *pg;
+	err = decode_pg_temp(p, end, map);
+	if (err)
+		goto bad;
 
-		err = ceph_decode_pgid(p, end, &pgid);
+	/* primary_temp */
+	if (struct_v >= 1) {
+		err = decode_primary_temp(p, end, map);
 		if (err)
 			goto bad;
-		ceph_decode_need(p, end, sizeof(u32), bad);
-		n = ceph_decode_32(p);
-		err = -EINVAL;
-		if (n > (UINT_MAX - sizeof(*pg)) / sizeof(u32))
-			goto bad;
-		ceph_decode_need(p, end, n * sizeof(u32), bad);
-		err = -ENOMEM;
-		pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS);
-		if (!pg)
-			goto bad;
-		pg->pgid = pgid;
-		pg->len = n;
-		for (j = 0; j < n; j++)
-			pg->osds[j] = ceph_decode_32(p);
+	}
 
-		err = __insert_pg_mapping(pg, &map->pg_temp);
+	/* primary_affinity */
+	if (struct_v >= 2) {
+		err = decode_primary_affinity(p, end, map);
 		if (err)
 			goto bad;
-		dout(" added pg_temp %lld.%x len %d\n", pgid.pool, pgid.seed,
-		     len);
+	} else {
+		/* XXX can this happen? */
+		kfree(map->osd_primary_affinity);
+		map->osd_primary_affinity = NULL;
 	}
 
 	/* crush */
-	ceph_decode_32_safe(p, end, len, bad);
-	dout("osdmap_decode crush len %d from off 0x%x\n", len,
-	     (int)(*p - start));
-	ceph_decode_need(p, end, len, bad);
-	map->crush = crush_decode(*p, end);
-	*p += len;
+	ceph_decode_32_safe(p, end, len, e_inval);
+	map->crush = crush_decode(*p, min(*p + len, end));
 	if (IS_ERR(map->crush)) {
 		err = PTR_ERR(map->crush);
 		map->crush = NULL;
 		goto bad;
 	}
+	*p += len;
 
-	/* ignore the rest of the map */
+	/* ignore the rest */
 	*p = end;
 
-	dout("osdmap_decode done %p %p\n", *p, end);
-	return map;
+	dout("full osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd);
+	return 0;
 
+e_inval:
+	err = -EINVAL;
 bad:
-	dout("osdmap_decode fail err %d\n", err);
-	ceph_osdmap_destroy(map);
-	return ERR_PTR(err);
+	pr_err("corrupt full osdmap (%d) epoch %d off %d (%p of %p-%p)\n",
+	       err, epoch, (int)(*p - start), *p, start, end);
+	print_hex_dump(KERN_DEBUG, "osdmap: ",
+		       DUMP_PREFIX_OFFSET, 16, 1,
+		       start, end - start, true);
+	return err;
+}
+
+/*
+ * Allocate and decode a full map.
+ */
+struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
+{
+	struct ceph_osdmap *map;
+	int ret;
+
+	map = kzalloc(sizeof(*map), GFP_NOFS);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	map->pg_temp = RB_ROOT;
+	map->primary_temp = RB_ROOT;
+	mutex_init(&map->crush_scratch_mutex);
+
+	ret = osdmap_decode(p, end, map);
+	if (ret) {
+		ceph_osdmap_destroy(map);
+		return ERR_PTR(ret);
+	}
+
+	return map;
 }
 
 /*
@@ -813,17 +1182,18 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	__s64 new_pool_max;
 	__s32 new_flags, max;
 	void *start = *p;
-	int err = -EINVAL;
-	u16 version;
+	int err;
+	u8 struct_v;
+
+	dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p));
 
-	ceph_decode_16_safe(p, end, version, bad);
-	if (version != 6) {
-		pr_warning("got unknown v %d != 6 of inc osdmap\n", version);
+	err = get_osdmap_client_data_v(p, end, "inc", &struct_v);
+	if (err)
 		goto bad;
-	}
 
-	ceph_decode_need(p, end, sizeof(fsid)+sizeof(modified)+2*sizeof(u32),
-			 bad);
+	/* fsid, epoch, modified, new_pool_max, new_flags */
+	ceph_decode_need(p, end, sizeof(fsid) + sizeof(u32) + sizeof(modified) +
+			 sizeof(u64) + sizeof(u32), e_inval);
 	ceph_decode_copy(p, &fsid, sizeof(fsid));
 	epoch = ceph_decode_32(p);
 	BUG_ON(epoch != map->epoch+1);
@@ -832,21 +1202,22 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	new_flags = ceph_decode_32(p);
 
 	/* full map? */
-	ceph_decode_32_safe(p, end, len, bad);
+	ceph_decode_32_safe(p, end, len, e_inval);
 	if (len > 0) {
 		dout("apply_incremental full map len %d, %p to %p\n",
 		     len, *p, end);
-		return osdmap_decode(p, min(*p+len, end));
+		return ceph_osdmap_decode(p, min(*p+len, end));
 	}
 
 	/* new crush? */
-	ceph_decode_32_safe(p, end, len, bad);
+	ceph_decode_32_safe(p, end, len, e_inval);
 	if (len > 0) {
-		dout("apply_incremental new crush map len %d, %p to %p\n",
-		     len, *p, end);
 		newcrush = crush_decode(*p, min(*p+len, end));
-		if (IS_ERR(newcrush))
-			return ERR_CAST(newcrush);
+		if (IS_ERR(newcrush)) {
+			err = PTR_ERR(newcrush);
+			newcrush = NULL;
+			goto bad;
+		}
 		*p += len;
 	}
 
@@ -856,13 +1227,11 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	if (new_pool_max >= 0)
 		map->pool_max = new_pool_max;
 
-	ceph_decode_need(p, end, 5*sizeof(u32), bad);
-
 	/* new max? */
-	max = ceph_decode_32(p);
+	ceph_decode_32_safe(p, end, max, e_inval);
 	if (max >= 0) {
 		err = osdmap_set_max_osd(map, max);
-		if (err < 0)
+		if (err)
 			goto bad;
 	}
 
@@ -875,51 +1244,34 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 		newcrush = NULL;
 	}
 
-	/* new_pool */
-	ceph_decode_32_safe(p, end, len, bad);
-	while (len--) {
-		struct ceph_pg_pool_info *pi;
+	/* new_pools */
+	err = decode_new_pools(p, end, map);
+	if (err)
+		goto bad;
 
-		ceph_decode_64_safe(p, end, pool, bad);
-		pi = __lookup_pg_pool(&map->pg_pools, pool);
-		if (!pi) {
-			pi = kzalloc(sizeof(*pi), GFP_NOFS);
-			if (!pi) {
-				err = -ENOMEM;
-				goto bad;
-			}
-			pi->id = pool;
-			__insert_pg_pool(&map->pg_pools, pi);
-		}
-		err = __decode_pool(p, end, pi);
-		if (err < 0)
-			goto bad;
-	}
-	if (version >= 5) {
-		err = __decode_pool_names(p, end, map);
-		if (err < 0)
-			goto bad;
-	}
+	/* new_pool_names */
+	err = decode_pool_names(p, end, map);
+	if (err)
+		goto bad;
 
 	/* old_pool */
-	ceph_decode_32_safe(p, end, len, bad);
+	ceph_decode_32_safe(p, end, len, e_inval);
 	while (len--) {
 		struct ceph_pg_pool_info *pi;
 
-		ceph_decode_64_safe(p, end, pool, bad);
+		ceph_decode_64_safe(p, end, pool, e_inval);
 		pi = __lookup_pg_pool(&map->pg_pools, pool);
 		if (pi)
 			__remove_pg_pool(&map->pg_pools, pi);
 	}
 
 	/* new_up */
-	err = -EINVAL;
-	ceph_decode_32_safe(p, end, len, bad);
+	ceph_decode_32_safe(p, end, len, e_inval);
 	while (len--) {
 		u32 osd;
 		struct ceph_entity_addr addr;
-		ceph_decode_32_safe(p, end, osd, bad);
-		ceph_decode_copy_safe(p, end, &addr, sizeof(addr), bad);
+		ceph_decode_32_safe(p, end, osd, e_inval);
+		ceph_decode_copy_safe(p, end, &addr, sizeof(addr), e_inval);
 		ceph_decode_addr(&addr);
 		pr_info("osd%d up\n", osd);
 		BUG_ON(osd >= map->max_osd);
@@ -928,11 +1280,11 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	}
 
 	/* new_state */
-	ceph_decode_32_safe(p, end, len, bad);
+	ceph_decode_32_safe(p, end, len, e_inval);
 	while (len--) {
 		u32 osd;
 		u8 xorstate;
-		ceph_decode_32_safe(p, end, osd, bad);
+		ceph_decode_32_safe(p, end, osd, e_inval);
 		xorstate = **(u8 **)p;
 		(*p)++;  /* clean flag */
 		if (xorstate == 0)
@@ -944,10 +1296,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	}
 
 	/* new_weight */
-	ceph_decode_32_safe(p, end, len, bad);
+	ceph_decode_32_safe(p, end, len, e_inval);
 	while (len--) {
 		u32 osd, off;
-		ceph_decode_need(p, end, sizeof(u32)*2, bad);
+		ceph_decode_need(p, end, sizeof(u32)*2, e_inval);
 		osd = ceph_decode_32(p);
 		off = ceph_decode_32(p);
 		pr_info("osd%d weight 0x%x %s\n", osd, off,
@@ -958,56 +1310,35 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	}
 
 	/* new_pg_temp */
-	ceph_decode_32_safe(p, end, len, bad);
-	while (len--) {
-		struct ceph_pg_mapping *pg;
-		int j;
-		struct ceph_pg pgid;
-		u32 pglen;
+	err = decode_new_pg_temp(p, end, map);
+	if (err)
+		goto bad;
 
-		err = ceph_decode_pgid(p, end, &pgid);
+	/* new_primary_temp */
+	if (struct_v >= 1) {
+		err = decode_new_primary_temp(p, end, map);
 		if (err)
 			goto bad;
-		ceph_decode_need(p, end, sizeof(u32), bad);
-		pglen = ceph_decode_32(p);
-		if (pglen) {
-			ceph_decode_need(p, end, pglen*sizeof(u32), bad);
-
-			/* removing existing (if any) */
-			(void) __remove_pg_mapping(&map->pg_temp, pgid);
+	}
 
-			/* insert */
-			err = -EINVAL;
-			if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32))
-				goto bad;
-			err = -ENOMEM;
-			pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS);
-			if (!pg)
-				goto bad;
-			pg->pgid = pgid;
-			pg->len = pglen;
-			for (j = 0; j < pglen; j++)
-				pg->osds[j] = ceph_decode_32(p);
-			err = __insert_pg_mapping(pg, &map->pg_temp);
-			if (err) {
-				kfree(pg);
-				goto bad;
-			}
-			dout(" added pg_temp %lld.%x len %d\n", pgid.pool,
-			     pgid.seed, pglen);
-		} else {
-			/* remove */
-			__remove_pg_mapping(&map->pg_temp, pgid);
-		}
+	/* new_primary_affinity */
+	if (struct_v >= 2) {
+		err = decode_new_primary_affinity(p, end, map);
+		if (err)
+			goto bad;
 	}
 
 	/* ignore the rest */
 	*p = end;
+
+	dout("inc osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd);
 	return map;
 
+e_inval:
+	err = -EINVAL;
 bad:
-	pr_err("corrupt inc osdmap epoch %d off %d (%p of %p-%p)\n",
-	       epoch, (int)(*p - start), *p, start, end);
+	pr_err("corrupt inc osdmap (%d) epoch %d off %d (%p of %p-%p)\n",
+	       err, epoch, (int)(*p - start), *p, start, end);
 	print_hex_dump(KERN_DEBUG, "osdmap: ",
 		       DUMP_PREFIX_OFFSET, 16, 1,
 		       start, end - start, true);
@@ -1090,71 +1421,275 @@ invalid:
 EXPORT_SYMBOL(ceph_calc_file_object_mapping);
 
 /*
- * calculate an object layout (i.e. pgid) from an oid,
- * file_layout, and osdmap
+ * Calculate mapping of a (oloc, oid) pair to a PG.  Should only be
+ * called with target's (oloc, oid), since tiering isn't taken into
+ * account.
  */
-int ceph_calc_ceph_pg(struct ceph_pg *pg, const char *oid,
-			struct ceph_osdmap *osdmap, uint64_t pool)
+int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
+			struct ceph_object_locator *oloc,
+			struct ceph_object_id *oid,
+			struct ceph_pg *pg_out)
 {
-	struct ceph_pg_pool_info *pool_info;
+	struct ceph_pg_pool_info *pi;
 
-	BUG_ON(!osdmap);
-	pool_info = __lookup_pg_pool(&osdmap->pg_pools, pool);
-	if (!pool_info)
+	pi = __lookup_pg_pool(&osdmap->pg_pools, oloc->pool);
+	if (!pi)
 		return -EIO;
-	pg->pool = pool;
-	pg->seed = ceph_str_hash(pool_info->object_hash, oid, strlen(oid));
 
-	dout("%s '%s' pgid %lld.%x\n", __func__, oid, pg->pool, pg->seed);
+	pg_out->pool = oloc->pool;
+	pg_out->seed = ceph_str_hash(pi->object_hash, oid->name,
+				     oid->name_len);
+
+	dout("%s '%.*s' pgid %llu.%x\n", __func__, oid->name_len, oid->name,
+	     pg_out->pool, pg_out->seed);
 	return 0;
 }
-EXPORT_SYMBOL(ceph_calc_ceph_pg);
+EXPORT_SYMBOL(ceph_oloc_oid_to_pg);
+
+static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
+		    int *result, int result_max,
+		    const __u32 *weight, int weight_max)
+{
+	int r;
+
+	BUG_ON(result_max > CEPH_PG_MAX_SIZE);
+
+	mutex_lock(&map->crush_scratch_mutex);
+	r = crush_do_rule(map->crush, ruleno, x, result, result_max,
+			  weight, weight_max, map->crush_scratch_ary);
+	mutex_unlock(&map->crush_scratch_mutex);
+
+	return r;
+}
 
 /*
- * Calculate raw osd vector for the given pgid.  Return pointer to osd
- * array, or NULL on failure.
+ * Calculate raw (crush) set for given pgid.
+ *
+ * Return raw set length, or error.
  */
-static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
-			int *osds, int *num)
+static int pg_to_raw_osds(struct ceph_osdmap *osdmap,
+			  struct ceph_pg_pool_info *pool,
+			  struct ceph_pg pgid, u32 pps, int *osds)
 {
-	struct ceph_pg_mapping *pg;
-	struct ceph_pg_pool_info *pool;
 	int ruleno;
-	int r;
-	u32 pps;
+	int len;
 
-	pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
-	if (!pool)
-		return NULL;
+	/* crush */
+	ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset,
+				 pool->type, pool->size);
+	if (ruleno < 0) {
+		pr_err("no crush rule: pool %lld ruleset %d type %d size %d\n",
+		       pgid.pool, pool->crush_ruleset, pool->type,
+		       pool->size);
+		return -ENOENT;
+	}
 
-	/* pg_temp? */
+	len = do_crush(osdmap, ruleno, pps, osds,
+		       min_t(int, pool->size, CEPH_PG_MAX_SIZE),
+		       osdmap->osd_weight, osdmap->max_osd);
+	if (len < 0) {
+		pr_err("error %d from crush rule %d: pool %lld ruleset %d type %d size %d\n",
+		       len, ruleno, pgid.pool, pool->crush_ruleset,
+		       pool->type, pool->size);
+		return len;
+	}
+
+	return len;
+}
+
+/*
+ * Given raw set, calculate up set and up primary.
+ *
+ * Return up set length.  *primary is set to up primary osd id, or -1
+ * if up set is empty.
+ */
+static int raw_to_up_osds(struct ceph_osdmap *osdmap,
+			  struct ceph_pg_pool_info *pool,
+			  int *osds, int len, int *primary)
+{
+	int up_primary = -1;
+	int i;
+
+	if (ceph_can_shift_osds(pool)) {
+		int removed = 0;
+
+		for (i = 0; i < len; i++) {
+			if (ceph_osd_is_down(osdmap, osds[i])) {
+				removed++;
+				continue;
+			}
+			if (removed)
+				osds[i - removed] = osds[i];
+		}
+
+		len -= removed;
+		if (len > 0)
+			up_primary = osds[0];
+	} else {
+		for (i = len - 1; i >= 0; i--) {
+			if (ceph_osd_is_down(osdmap, osds[i]))
+				osds[i] = CRUSH_ITEM_NONE;
+			else
+				up_primary = osds[i];
+		}
+	}
+
+	*primary = up_primary;
+	return len;
+}
+
+static void apply_primary_affinity(struct ceph_osdmap *osdmap, u32 pps,
+				   struct ceph_pg_pool_info *pool,
+				   int *osds, int len, int *primary)
+{
+	int i;
+	int pos = -1;
+
+	/*
+	 * Do we have any non-default primary_affinity values for these
+	 * osds?
+	 */
+	if (!osdmap->osd_primary_affinity)
+		return;
+
+	for (i = 0; i < len; i++) {
+		int osd = osds[i];
+
+		if (osd != CRUSH_ITEM_NONE &&
+		    osdmap->osd_primary_affinity[osd] !=
+					CEPH_OSD_DEFAULT_PRIMARY_AFFINITY) {
+			break;
+		}
+	}
+	if (i == len)
+		return;
+
+	/*
+	 * Pick the primary.  Feed both the seed (for the pg) and the
+	 * osd into the hash/rng so that a proportional fraction of an
+	 * osd's pgs get rejected as primary.
+	 */
+	for (i = 0; i < len; i++) {
+		int osd = osds[i];
+		u32 aff;
+
+		if (osd == CRUSH_ITEM_NONE)
+			continue;
+
+		aff = osdmap->osd_primary_affinity[osd];
+		if (aff < CEPH_OSD_MAX_PRIMARY_AFFINITY &&
+		    (crush_hash32_2(CRUSH_HASH_RJENKINS1,
+				    pps, osd) >> 16) >= aff) {
+			/*
+			 * We chose not to use this primary.  Note it
+			 * anyway as a fallback in case we don't pick
+			 * anyone else, but keep looking.
+			 */
+			if (pos < 0)
+				pos = i;
+		} else {
+			pos = i;
+			break;
+		}
+	}
+	if (pos < 0)
+		return;
+
+	*primary = osds[pos];
+
+	if (ceph_can_shift_osds(pool) && pos > 0) {
+		/* move the new primary to the front */
+		for (i = pos; i > 0; i--)
+			osds[i] = osds[i - 1];
+		osds[0] = *primary;
+	}
+}
+
+/*
+ * Given up set, apply pg_temp and primary_temp mappings.
+ *
+ * Return acting set length.  *primary is set to acting primary osd id,
+ * or -1 if acting set is empty.
+ */
+static int apply_temps(struct ceph_osdmap *osdmap,
+		       struct ceph_pg_pool_info *pool, struct ceph_pg pgid,
+		       int *osds, int len, int *primary)
+{
+	struct ceph_pg_mapping *pg;
+	int temp_len;
+	int temp_primary;
+	int i;
+
+	/* raw_pg -> pg */
 	pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num,
 				    pool->pg_num_mask);
+
+	/* pg_temp? */
 	pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
 	if (pg) {
-		*num = pg->len;
-		return pg->osds;
+		temp_len = 0;
+		temp_primary = -1;
+
+		for (i = 0; i < pg->pg_temp.len; i++) {
+			if (ceph_osd_is_down(osdmap, pg->pg_temp.osds[i])) {
+				if (ceph_can_shift_osds(pool))
+					continue;
+				else
+					osds[temp_len++] = CRUSH_ITEM_NONE;
+			} else {
+				osds[temp_len++] = pg->pg_temp.osds[i];
+			}
+		}
+
+		/* apply pg_temp's primary */
+		for (i = 0; i < temp_len; i++) {
+			if (osds[i] != CRUSH_ITEM_NONE) {
+				temp_primary = osds[i];
+				break;
+			}
+		}
+	} else {
+		temp_len = len;
+		temp_primary = *primary;
 	}
 
-	/* crush */
-	ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset,
-				 pool->type, pool->size);
-	if (ruleno < 0) {
-		pr_err("no crush rule pool %lld ruleset %d type %d size %d\n",
-		       pgid.pool, pool->crush_ruleset, pool->type,
-		       pool->size);
-		return NULL;
+	/* primary_temp? */
+	pg = __lookup_pg_mapping(&osdmap->primary_temp, pgid);
+	if (pg)
+		temp_primary = pg->primary_temp.osd;
+
+	*primary = temp_primary;
+	return temp_len;
+}
+
+/*
+ * Calculate acting set for given pgid.
+ *
+ * Return acting set length, or error.  *primary is set to acting
+ * primary osd id, or -1 if acting set is empty or on error.
+ */
+int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
+			int *osds, int *primary)
+{
+	struct ceph_pg_pool_info *pool;
+	u32 pps;
+	int len;
+
+	pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
+	if (!pool) {
+		*primary = -1;
+		return -ENOENT;
 	}
 
 	if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
-		/* hash pool id and seed sothat pool PGs do not overlap */
+		/* hash pool id and seed so that pool PGs do not overlap */
 		pps = crush_hash32_2(CRUSH_HASH_RJENKINS1,
 				     ceph_stable_mod(pgid.seed, pool->pgp_num,
 						     pool->pgp_num_mask),
 				     pgid.pool);
 	} else {
 		/*
-		 * legacy ehavior: add ps and pool together.  this is
+		 * legacy behavior: add ps and pool together.  this is
 		 * not a great approach because the PGs from each pool
 		 * will overlap on top of each other: 0.5 == 1.4 ==
 		 * 2.3 == ...
@@ -1163,38 +1698,20 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
 				      pool->pgp_num_mask) +
 			(unsigned)pgid.pool;
 	}
-	r = crush_do_rule(osdmap->crush, ruleno, pps, osds,
-			  min_t(int, pool->size, *num),
-			  osdmap->osd_weight);
-	if (r < 0) {
-		pr_err("error %d from crush rule: pool %lld ruleset %d type %d"
-		       " size %d\n", r, pgid.pool, pool->crush_ruleset,
-		       pool->type, pool->size);
-		return NULL;
+
+	len = pg_to_raw_osds(osdmap, pool, pgid, pps, osds);
+	if (len < 0) {
+		*primary = -1;
+		return len;
 	}
-	*num = r;
-	return osds;
-}
 
-/*
- * Return acting set for given pgid.
- */
-int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
-			int *acting)
-{
-	int rawosds[CEPH_PG_MAX_SIZE], *osds;
-	int i, o, num = CEPH_PG_MAX_SIZE;
+	len = raw_to_up_osds(osdmap, pool, osds, len, primary);
 
-	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
-	if (!osds)
-		return -1;
+	apply_primary_affinity(osdmap, pps, pool, osds, len, primary);
+
+	len = apply_temps(osdmap, pool, pgid, osds, len, primary);
 
-	/* primary is first up osd */
-	o = 0;
-	for (i = 0; i < num; i++)
-		if (ceph_osd_is_up(osdmap, osds[i]))
-			acting[o++] = osds[i];
-	return o;
+	return len;
 }
 
 /*
@@ -1202,17 +1719,11 @@ int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
  */
 int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
 {
-	int rawosds[CEPH_PG_MAX_SIZE], *osds;
-	int i, num = CEPH_PG_MAX_SIZE;
+	int osds[CEPH_PG_MAX_SIZE];
+	int primary;
 
-	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
-	if (!osds)
-		return -1;
+	ceph_calc_pg_acting(osdmap, pgid, osds, &primary);
 
-	/* primary is first up osd */
-	for (i = 0; i < num; i++)
-		if (ceph_osd_is_up(osdmap, osds[i]))
-			return osds[i];
-	return -1;
+	return primary;
 }
 EXPORT_SYMBOL(ceph_calc_pg_primary);
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index 815a2249cfa..555013034f7 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -53,7 +53,10 @@ void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty)
 			set_page_dirty_lock(pages[i]);
 		put_page(pages[i]);
 	}
-	kfree(pages);
+	if (is_vmalloc_addr(pages))
+		vfree(pages);
+	else
+		kfree(pages);
 }
 EXPORT_SYMBOL(ceph_put_page_vector);
 
@@ -165,36 +168,6 @@ void ceph_copy_from_page_vector(struct page **pages,
 EXPORT_SYMBOL(ceph_copy_from_page_vector);
 
 /*
- * copy user data from a page vector into a user pointer
- */
-int ceph_copy_page_vector_to_user(struct page **pages,
-					 void __user *data,
-					 loff_t off, size_t len)
-{
-	int i = 0;
-	int po = off & ~PAGE_CACHE_MASK;
-	int left = len;
-	int l, bad;
-
-	while (left > 0) {
-		l = min_t(int, left, PAGE_CACHE_SIZE-po);
-		bad = copy_to_user(data, page_address(pages[i]) + po, l);
-		if (bad == l)
-			return -EFAULT;
-		data += l - bad;
-		left -= l - bad;
-		if (po) {
-			po += l - bad;
-			if (po == PAGE_CACHE_SIZE)
-				po = 0;
-		}
-		i++;
-	}
-	return len;
-}
-EXPORT_SYMBOL(ceph_copy_page_vector_to_user);
-
-/*
  * Zero an extent within a page vector.  Offset is relative to the
  * start of the first page.
  */
diff --git a/net/compat.c b/net/compat.c
index dd32e34c1e2..bc8aeefddf3 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -85,7 +85,7 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 {
 	int tot_len;
 
-	if (kern_msg->msg_namelen) {
+	if (kern_msg->msg_name && kern_msg->msg_namelen) {
 		if (mode == VERIFY_READ) {
 			int err = move_addr_to_kernel(kern_msg->msg_name,
 						      kern_msg->msg_namelen,
@@ -93,10 +93,11 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 			if (err < 0)
 				return err;
 		}
-		if (kern_msg->msg_name)
-			kern_msg->msg_name = kern_address;
-	} else
+		kern_msg->msg_name = kern_address;
+	} else {
 		kern_msg->msg_name = NULL;
+		kern_msg->msg_namelen = 0;
+	}
 
 	tot_len = iov_from_user_compat_to_kern(kern_iov,
 					  (struct compat_iovec __user *)kern_msg->msg_iov,
@@ -384,8 +385,8 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
 	return sock_setsockopt(sock, level, optname, optval, optlen);
 }
 
-asmlinkage long compat_sys_setsockopt(int fd, int level, int optname,
-				char __user *optval, unsigned int optlen)
+COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
+		       char __user *, optval, unsigned int, optlen)
 {
 	int err;
 	struct socket *sock = sockfd_lookup(fd, &err);
@@ -504,8 +505,8 @@ int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *usersta
 }
 EXPORT_SYMBOL(compat_sock_get_timestampns);
 
-asmlinkage long compat_sys_getsockopt(int fd, int level, int optname,
-				char __user *optval, int __user *optlen)
+COMPAT_SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
+		       char __user *, optval, int __user *, optlen)
 {
 	int err;
 	struct socket *sock = sockfd_lookup(fd, &err);
@@ -735,15 +736,15 @@ static unsigned char nas[21] = {
 };
 #undef AL
 
-asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags)
+COMPAT_SYSCALL_DEFINE3(sendmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags)
 {
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
 	return __sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
 }
 
-asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg,
-				    unsigned int vlen, unsigned int flags)
+COMPAT_SYSCALL_DEFINE4(sendmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
+		       unsigned int, vlen, unsigned int, flags)
 {
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
@@ -751,28 +752,28 @@ asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg,
 			      flags | MSG_CMSG_COMPAT);
 }
 
-asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags)
+COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags)
 {
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
 	return __sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
 }
 
-asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len, unsigned int flags)
+COMPAT_SYSCALL_DEFINE4(recv, int, fd, void __user *, buf, compat_size_t, len, unsigned int, flags)
 {
 	return sys_recv(fd, buf, len, flags | MSG_CMSG_COMPAT);
 }
 
-asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, size_t len,
-				    unsigned int flags, struct sockaddr __user *addr,
-				    int __user *addrlen)
+COMPAT_SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, buf, compat_size_t, len,
+		       unsigned int, flags, struct sockaddr __user *, addr,
+		       int __user *, addrlen)
 {
 	return sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr, addrlen);
 }
 
-asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg,
-				    unsigned int vlen, unsigned int flags,
-				    struct compat_timespec __user *timeout)
+COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
+		       unsigned int, vlen, unsigned int, flags,
+		       struct compat_timespec __user *, timeout)
 {
 	int datagrams;
 	struct timespec ktspec;
@@ -780,27 +781,22 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg,
 	if (flags & MSG_CMSG_COMPAT)
 		return -EINVAL;
 
-	if (COMPAT_USE_64BIT_TIME)
-		return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
-				      flags | MSG_CMSG_COMPAT,
-				      (struct timespec *) timeout);
-
 	if (timeout == NULL)
 		return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
 				      flags | MSG_CMSG_COMPAT, NULL);
 
-	if (get_compat_timespec(&ktspec, timeout))
+	if (compat_get_timespec(&ktspec, timeout))
 		return -EFAULT;
 
 	datagrams = __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
 				   flags | MSG_CMSG_COMPAT, &ktspec);
-	if (datagrams > 0 && put_compat_timespec(&ktspec, timeout))
+	if (datagrams > 0 && compat_put_timespec(&ktspec, timeout))
 		datagrams = -EFAULT;
 
 	return datagrams;
 }
 
-asmlinkage long compat_sys_socketcall(int call, u32 __user *args)
+COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
 {
 	int ret;
 	u32 a[6];
diff --git a/net/core/Makefile b/net/core/Makefile
index b33b996f5dd..71093d94ad2 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
 
 obj-y		     += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
 			neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
-			sock_diag.o dev_ioctl.o
+			sock_diag.o dev_ioctl.o tso.o
 
 obj-$(CONFIG_XFRM) += flow.o
 obj-y += net-sysfs.o
@@ -21,4 +21,6 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o
 obj-$(CONFIG_TRACEPOINTS) += net-traces.o
 obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o
 obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
-obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o
+obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o
+obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
+obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o
diff --git a/net/core/datagram.c b/net/core/datagram.c
index a16ed7bbe37..488dd1a825c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -740,17 +740,37 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 
 	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
 	if (likely(!sum)) {
-		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
 			netdev_rx_csum_fault(skb->dev);
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
+	skb->csum_valid = !sum;
 	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete_head);
 
 __sum16 __skb_checksum_complete(struct sk_buff *skb)
 {
-	return __skb_checksum_complete_head(skb, skb->len);
+	__wsum csum;
+	__sum16 sum;
+
+	csum = skb_checksum(skb, 0, skb->len, 0);
+
+	/* skb->csum holds pseudo checksum */
+	sum = csum_fold(csum_add(skb->csum, csum));
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+
+	/* Save full packet checksum */
+	skb->csum = csum;
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	skb->csum_complete_sw = 1;
+	skb->csum_valid = !sum;
+
+	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 355df36360b..367a586d0c8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -147,6 +147,11 @@ struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
 struct list_head ptype_all __read_mostly;	/* Taps */
 static struct list_head offload_base __read_mostly;
 
+static int netif_rx_internal(struct sk_buff *skb);
+static int call_netdevice_notifiers_info(unsigned long val,
+					 struct net_device *dev,
+					 struct netdev_notifier_info *info);
+
 /*
  * The @dev_base_head list is protected by @dev_base_lock and the rtnl
  * semaphore.
@@ -480,7 +485,7 @@ EXPORT_SYMBOL(dev_add_offload);
  *	and must not be freed until after all the CPU's have gone
  *	through a quiescent state.
  */
-void __dev_remove_offload(struct packet_offload *po)
+static void __dev_remove_offload(struct packet_offload *po)
 {
 	struct list_head *head = &offload_base;
 	struct packet_offload *po1;
@@ -498,7 +503,6 @@ void __dev_remove_offload(struct packet_offload *po)
 out:
 	spin_unlock(&offload_lock);
 }
-EXPORT_SYMBOL(__dev_remove_offload);
 
 /**
  *	dev_remove_offload	 - remove packet offload handler
@@ -1118,6 +1122,8 @@ rollback:
 
 	write_seqcount_end(&devnet_rename_seq);
 
+	netdev_adjacent_rename_links(dev, oldname);
+
 	write_lock_bh(&dev_base_lock);
 	hlist_del_rcu(&dev->name_hlist);
 	write_unlock_bh(&dev_base_lock);
@@ -1137,6 +1143,7 @@ rollback:
 			err = ret;
 			write_seqcount_begin(&devnet_rename_seq);
 			memcpy(dev->name, oldname, IFNAMSIZ);
+			memcpy(oldname, newname, IFNAMSIZ);
 			goto rollback;
 		} else {
 			pr_err("%s: name change rollback failed: %d\n",
@@ -1203,7 +1210,11 @@ EXPORT_SYMBOL(netdev_features_change);
 void netdev_state_change(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
-		call_netdevice_notifiers(NETDEV_CHANGE, dev);
+		struct netdev_notifier_change_info change_info;
+
+		change_info.flags_changed = 0;
+		call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+					      &change_info.info);
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 	}
 }
@@ -1241,7 +1252,7 @@ static int __dev_open(struct net_device *dev)
 	 * If we don't do this there is a chance ndo_poll_controller
 	 * or ndo_poll may be running while we open the device
 	 */
-	netpoll_rx_disable(dev);
+	netpoll_poll_disable(dev);
 
 	ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
 	ret = notifier_to_errno(ret);
@@ -1256,7 +1267,7 @@ static int __dev_open(struct net_device *dev)
 	if (!ret && ops->ndo_open)
 		ret = ops->ndo_open(dev);
 
-	netpoll_rx_enable(dev);
+	netpoll_poll_enable(dev);
 
 	if (ret)
 		clear_bit(__LINK_STATE_START, &dev->state);
@@ -1309,6 +1320,9 @@ static int __dev_close_many(struct list_head *head)
 	might_sleep();
 
 	list_for_each_entry(dev, head, close_list) {
+		/* Temporarily disable netpoll until the interface is down */
+		netpoll_poll_disable(dev);
+
 		call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
 
 		clear_bit(__LINK_STATE_START, &dev->state);
@@ -1319,7 +1333,7 @@ static int __dev_close_many(struct list_head *head)
 		 * dev->stop() will invoke napi_disable() on all of it's
 		 * napi_struct instances on this device.
 		 */
-		smp_mb__after_clear_bit(); /* Commit netif_running(). */
+		smp_mb__after_atomic(); /* Commit netif_running(). */
 	}
 
 	dev_deactivate_many(head);
@@ -1339,6 +1353,7 @@ static int __dev_close_many(struct list_head *head)
 
 		dev->flags &= ~IFF_UP;
 		net_dmaengine_put();
+		netpoll_poll_enable(dev);
 	}
 
 	return 0;
@@ -1349,14 +1364,10 @@ static int __dev_close(struct net_device *dev)
 	int retval;
 	LIST_HEAD(single);
 
-	/* Temporarily disable netpoll until the interface is down */
-	netpoll_rx_disable(dev);
-
 	list_add(&dev->close_list, &single);
 	retval = __dev_close_many(&single);
 	list_del(&single);
 
-	netpoll_rx_enable(dev);
 	return retval;
 }
 
@@ -1394,14 +1405,9 @@ int dev_close(struct net_device *dev)
 	if (dev->flags & IFF_UP) {
 		LIST_HEAD(single);
 
-		/* Block netpoll rx while the interface is going down */
-		netpoll_rx_disable(dev);
-
 		list_add(&dev->close_list, &single);
 		dev_close_many(&single);
 		list_del(&single);
-
-		netpoll_rx_enable(dev);
 	}
 	return 0;
 }
@@ -1566,14 +1572,14 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
  *	are as for raw_notifier_call_chain().
  */
 
-int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev,
-				  struct netdev_notifier_info *info)
+static int call_netdevice_notifiers_info(unsigned long val,
+					 struct net_device *dev,
+					 struct netdev_notifier_info *info)
 {
 	ASSERT_RTNL();
 	netdev_notifier_info_init(info, dev);
 	return raw_notifier_call_chain(&netdev_chain, val, info);
 }
-EXPORT_SYMBOL(call_netdevice_notifiers_info);
 
 /**
  *	call_netdevice_notifiers - call all network notifier blocks
@@ -1641,8 +1647,7 @@ static inline void net_timestamp_set(struct sk_buff *skb)
 			__net_timestamp(SKB);		\
 	}						\
 
-static inline bool is_skb_forwardable(struct net_device *dev,
-				      struct sk_buff *skb)
+bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb)
 {
 	unsigned int len;
 
@@ -1661,6 +1666,30 @@ static inline bool is_skb_forwardable(struct net_device *dev,
 
 	return false;
 }
+EXPORT_SYMBOL_GPL(is_skb_forwardable);
+
+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
+		if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
+			atomic_long_inc(&dev->rx_dropped);
+			kfree_skb(skb);
+			return NET_RX_DROP;
+		}
+	}
+
+	if (unlikely(!is_skb_forwardable(dev, skb))) {
+		atomic_long_inc(&dev->rx_dropped);
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+
+	skb_scrub_packet(skb, true);
+	skb->protocol = eth_type_trans(skb, dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__dev_forward_skb);
 
 /**
  * dev_forward_skb - loopback an skb to another netif
@@ -1682,24 +1711,7 @@ static inline bool is_skb_forwardable(struct net_device *dev,
  */
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
-		if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
-			atomic_long_inc(&dev->rx_dropped);
-			kfree_skb(skb);
-			return NET_RX_DROP;
-		}
-	}
-
-	if (unlikely(!is_skb_forwardable(dev, skb))) {
-		atomic_long_inc(&dev->rx_dropped);
-		kfree_skb(skb);
-		return NET_RX_DROP;
-	}
-
-	skb_scrub_packet(skb, true);
-	skb->protocol = eth_type_trans(skb, dev);
-
-	return netif_rx(skb);
+	return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
 
@@ -2079,7 +2091,7 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
 }
 EXPORT_SYMBOL(netif_set_real_num_tx_queues);
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 /**
  *	netif_set_real_num_rx_queues - set actual number of RX queues used
  *	@dev: Network device
@@ -2282,10 +2294,10 @@ out:
 }
 EXPORT_SYMBOL(skb_checksum_help);
 
-__be16 skb_network_protocol(struct sk_buff *skb)
+__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
+	unsigned int vlan_depth = skb->mac_len;
 	__be16 type = skb->protocol;
-	int vlan_depth = ETH_HLEN;
 
 	/* Tunnel gso handlers can set protocol to ethernet. */
 	if (type == htons(ETH_P_TEB)) {
@@ -2298,17 +2310,34 @@ __be16 skb_network_protocol(struct sk_buff *skb)
 		type = eth->h_proto;
 	}
 
-	while (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
-		struct vlan_hdr *vh;
+	/* if skb->protocol is 802.1Q/AD then the header should already be
+	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
+	 * ETH_HLEN otherwise
+	 */
+	if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
+		if (vlan_depth) {
+			if (unlikely(WARN_ON(vlan_depth < VLAN_HLEN)))
+				return 0;
+			vlan_depth -= VLAN_HLEN;
+		} else {
+			vlan_depth = ETH_HLEN;
+		}
+		do {
+			struct vlan_hdr *vh;
 
-		if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN)))
-			return 0;
+			if (unlikely(!pskb_may_pull(skb,
+						    vlan_depth + VLAN_HLEN)))
+				return 0;
 
-		vh = (struct vlan_hdr *)(skb->data + vlan_depth);
-		type = vh->h_vlan_encapsulated_proto;
-		vlan_depth += VLAN_HLEN;
+			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
+			type = vh->h_vlan_encapsulated_proto;
+			vlan_depth += VLAN_HLEN;
+		} while (type == htons(ETH_P_8021Q) ||
+			 type == htons(ETH_P_8021AD));
 	}
 
+	*depth = vlan_depth;
+
 	return type;
 }
 
@@ -2322,12 +2351,13 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
 {
 	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
 	struct packet_offload *ptype;
-	__be16 type = skb_network_protocol(skb);
+	int vlan_depth = skb->mac_len;
+	__be16 type = skb_network_protocol(skb, &vlan_depth);
 
 	if (unlikely(!type))
 		return ERR_PTR(-EINVAL);
 
-	__skb_pull(skb, skb->mac_len);
+	__skb_pull(skb, vlan_depth);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, &offload_base, list) {
@@ -2454,13 +2484,8 @@ static void dev_gso_skb_destructor(struct sk_buff *skb)
 {
 	struct dev_gso_cb *cb;
 
-	do {
-		struct sk_buff *nskb = skb->next;
-
-		skb->next = nskb->next;
-		nskb->next = NULL;
-		kfree_skb(nskb);
-	} while (skb->next);
+	kfree_skb_list(skb->next);
+	skb->next = NULL;
 
 	cb = DEV_GSO_CB(skb);
 	if (cb->destructor)
@@ -2495,11 +2520,39 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
 	return 0;
 }
 
+/* If MPLS offload request, verify we are testing hardware MPLS features
+ * instead of standard features for the netdev.
+ */
+#ifdef CONFIG_NET_MPLS_GSO
+static netdev_features_t net_mpls_features(struct sk_buff *skb,
+					   netdev_features_t features,
+					   __be16 type)
+{
+	if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC))
+		features &= skb->dev->mpls_features;
+
+	return features;
+}
+#else
+static netdev_features_t net_mpls_features(struct sk_buff *skb,
+					   netdev_features_t features,
+					   __be16 type)
+{
+	return features;
+}
+#endif
+
 static netdev_features_t harmonize_features(struct sk_buff *skb,
 	netdev_features_t features)
 {
+	int tmp;
+	__be16 type;
+
+	type = skb_network_protocol(skb, &tmp);
+	features = net_mpls_features(skb, features, type);
+
 	if (skb->ip_summed != CHECKSUM_NONE &&
-	    !can_checksum_protocol(features, skb_network_protocol(skb))) {
+	    !can_checksum_protocol(features, type)) {
 		features &= ~NETIF_F_ALL_CSUM;
 	} else if (illegal_highdma(skb->dev, skb)) {
 		features &= ~NETIF_F_SG;
@@ -2536,7 +2589,7 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 EXPORT_SYMBOL(netif_skb_features);
 
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq, void *accel_priv)
+			struct netdev_queue *txq)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int rc = NETDEV_TX_OK;
@@ -2602,13 +2655,10 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			dev_queue_xmit_nit(skb, dev);
 
 		skb_len = skb->len;
-		if (accel_priv)
-			rc = ops->ndo_dfwd_start_xmit(skb, dev, accel_priv);
-		else
-			rc = ops->ndo_start_xmit(skb, dev);
-
+		trace_net_dev_start_xmit(skb, dev);
+		rc = ops->ndo_start_xmit(skb, dev);
 		trace_net_dev_xmit(skb, rc, dev, skb_len);
-		if (rc == NETDEV_TX_OK && txq)
+		if (rc == NETDEV_TX_OK)
 			txq_trans_update(txq);
 		return rc;
 	}
@@ -2624,10 +2674,8 @@ gso:
 			dev_queue_xmit_nit(nskb, dev);
 
 		skb_len = nskb->len;
-		if (accel_priv)
-			rc = ops->ndo_dfwd_start_xmit(nskb, dev, accel_priv);
-		else
-			rc = ops->ndo_start_xmit(nskb, dev);
+		trace_net_dev_start_xmit(nskb, dev);
+		rc = ops->ndo_start_xmit(nskb, dev);
 		trace_net_dev_xmit(nskb, rc, dev, skb_len);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
@@ -2747,7 +2795,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	return rc;
 }
 
-#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 static void skb_update_prio(struct sk_buff *skb)
 {
 	struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
@@ -2784,8 +2832,9 @@ int dev_loopback_xmit(struct sk_buff *skb)
 EXPORT_SYMBOL(dev_loopback_xmit);
 
 /**
- *	dev_queue_xmit - transmit a buffer
+ *	__dev_queue_xmit - transmit a buffer
  *	@skb: buffer to transmit
+ *	@accel_priv: private data used for L2 forwarding offload
  *
  *	Queue a buffer for transmission to a network device. The caller must
  *	have set the device and priority and built the buffer before calling
@@ -2808,7 +2857,7 @@ EXPORT_SYMBOL(dev_loopback_xmit);
  *      the BH enable code must have IRQs enabled so that it will not deadlock.
  *          --BLG
  */
-int dev_queue_xmit(struct sk_buff *skb)
+static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 {
 	struct net_device *dev = skb->dev;
 	struct netdev_queue *txq;
@@ -2824,7 +2873,7 @@ int dev_queue_xmit(struct sk_buff *skb)
 
 	skb_update_prio(skb);
 
-	txq = netdev_pick_tx(dev, skb);
+	txq = netdev_pick_tx(dev, skb, accel_priv);
 	q = rcu_dereference_bh(txq->qdisc);
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -2860,7 +2909,7 @@ int dev_queue_xmit(struct sk_buff *skb)
 
 			if (!netif_xmit_stopped(txq)) {
 				__this_cpu_inc(xmit_recursion);
-				rc = dev_hard_start_xmit(skb, dev, txq, NULL);
+				rc = dev_hard_start_xmit(skb, dev, txq);
 				__this_cpu_dec(xmit_recursion);
 				if (dev_xmit_complete(rc)) {
 					HARD_TX_UNLOCK(dev, txq);
@@ -2883,14 +2932,26 @@ recursion_alert:
 	rc = -ENETDOWN;
 	rcu_read_unlock_bh();
 
+	atomic_long_inc(&dev->tx_dropped);
 	kfree_skb(skb);
 	return rc;
 out:
 	rcu_read_unlock_bh();
 	return rc;
 }
+
+int dev_queue_xmit(struct sk_buff *skb)
+{
+	return __dev_queue_xmit(skb, NULL);
+}
 EXPORT_SYMBOL(dev_queue_xmit);
 
+int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
+{
+	return __dev_queue_xmit(skb, accel_priv);
+}
+EXPORT_SYMBOL(dev_queue_xmit_accel);
+
 
 /*=======================================================================
 			Receiver routines
@@ -2944,7 +3005,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		flow_table = rcu_dereference(rxqueue->rps_flow_table);
 		if (!flow_table)
 			goto out;
-		flow_id = skb->rxhash & flow_table->mask;
+		flow_id = skb_get_hash(skb) & flow_table->mask;
 		rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
 							rxq_index, flow_id);
 		if (rc < 0)
@@ -2978,6 +3039,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	struct rps_sock_flow_table *sock_flow_table;
 	int cpu = -1;
 	u16 tcpu;
+	u32 hash;
 
 	if (skb_rx_queue_recorded(skb)) {
 		u16 index = skb_get_rx_queue(skb);
@@ -3006,7 +3068,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	skb_reset_network_header(skb);
-	if (!skb_get_rxhash(skb))
+	hash = skb_get_hash(skb);
+	if (!hash)
 		goto done;
 
 	flow_table = rcu_dereference(rxqueue->rps_flow_table);
@@ -3015,11 +3078,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		u16 next_cpu;
 		struct rps_dev_flow *rflow;
 
-		rflow = &flow_table->flows[skb->rxhash & flow_table->mask];
+		rflow = &flow_table->flows[hash & flow_table->mask];
 		tcpu = rflow->cpu;
 
-		next_cpu = sock_flow_table->ents[skb->rxhash &
-		    sock_flow_table->mask];
+		next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask];
 
 		/*
 		 * If the desired CPU (where last recvmsg was done) is
@@ -3048,7 +3110,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	if (map) {
-		tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+		tcpu = map->cpus[((u64) hash * map->len) >> 32];
 
 		if (cpu_online(tcpu)) {
 			cpu = tcpu;
@@ -3151,7 +3213,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
 	rcu_read_lock();
 	fl = rcu_dereference(sd->flow_limit);
 	if (fl) {
-		new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1);
+		new_flow = skb_get_hash(skb) & (fl->num_buckets - 1);
 		old_flow = fl->history[fl->history_head];
 		fl->history[fl->history_head] = new_flow;
 
@@ -3219,29 +3281,10 @@ enqueue:
 	return NET_RX_DROP;
 }
 
-/**
- *	netif_rx	-	post buffer to the network code
- *	@skb: buffer to post
- *
- *	This function receives a packet from a device driver and queues it for
- *	the upper (protocol) levels to process.  It always succeeds. The buffer
- *	may be dropped during processing for congestion control or by the
- *	protocol layers.
- *
- *	return values:
- *	NET_RX_SUCCESS	(no congestion)
- *	NET_RX_DROP     (packet was dropped)
- *
- */
-
-int netif_rx(struct sk_buff *skb)
+static int netif_rx_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	/* if netpoll wants it, pretend we never saw it */
-	if (netpoll_rx(skb))
-		return NET_RX_DROP;
-
 	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
 	trace_netif_rx(skb);
@@ -3270,14 +3313,38 @@ int netif_rx(struct sk_buff *skb)
 	}
 	return ret;
 }
+
+/**
+ *	netif_rx	-	post buffer to the network code
+ *	@skb: buffer to post
+ *
+ *	This function receives a packet from a device driver and queues it for
+ *	the upper (protocol) levels to process.  It always succeeds. The buffer
+ *	may be dropped during processing for congestion control or by the
+ *	protocol layers.
+ *
+ *	return values:
+ *	NET_RX_SUCCESS	(no congestion)
+ *	NET_RX_DROP     (packet was dropped)
+ *
+ */
+
+int netif_rx(struct sk_buff *skb)
+{
+	trace_netif_rx_entry(skb);
+
+	return netif_rx_internal(skb);
+}
 EXPORT_SYMBOL(netif_rx);
 
 int netif_rx_ni(struct sk_buff *skb)
 {
 	int err;
 
+	trace_netif_rx_ni_entry(skb);
+
 	preempt_disable();
-	err = netif_rx(skb);
+	err = netif_rx_internal(skb);
 	if (local_softirq_pending())
 		do_softirq();
 	preempt_enable();
@@ -3328,7 +3395,7 @@ static void net_tx_action(struct softirq_action *h)
 
 			root_lock = qdisc_lock(q);
 			if (spin_trylock(root_lock)) {
-				smp_mb__before_clear_bit();
+				smp_mb__before_atomic();
 				clear_bit(__QDISC_STATE_SCHED,
 					  &q->state);
 				qdisc_run(q);
@@ -3338,7 +3405,7 @@ static void net_tx_action(struct softirq_action *h)
 					      &q->state)) {
 					__netif_reschedule(q);
 				} else {
-					smp_mb__before_clear_bit();
+					smp_mb__before_atomic();
 					clear_bit(__QDISC_STATE_SCHED,
 						  &q->state);
 				}
@@ -3424,7 +3491,7 @@ out:
  *	@rx_handler: receive handler to register
  *	@rx_handler_data: data pointer that is used by rx handler
  *
- *	Register a receive hander for a device. This handler will then be
+ *	Register a receive handler for a device. This handler will then be
  *	called from __netif_receive_skb. A negative errno code is returned
  *	on a failure.
  *
@@ -3478,11 +3545,11 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
 static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
 {
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_ARP):
-	case __constant_htons(ETH_P_IP):
-	case __constant_htons(ETH_P_IPV6):
-	case __constant_htons(ETH_P_8021Q):
-	case __constant_htons(ETH_P_8021AD):
+	case htons(ETH_P_ARP):
+	case htons(ETH_P_IP):
+	case htons(ETH_P_IPV6):
+	case htons(ETH_P_8021Q):
+	case htons(ETH_P_8021AD):
 		return true;
 	default:
 		return false;
@@ -3503,10 +3570,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 
 	trace_netif_receive_skb(skb);
 
-	/* if we've gotten here through NAPI, check netpoll */
-	if (netpoll_receive_skb(skb))
-		goto out;
-
 	orig_dev = skb->dev;
 
 	skb_reset_network_header(skb);
@@ -3633,7 +3696,6 @@ drop:
 
 unlock:
 	rcu_read_unlock();
-out:
 	return ret;
 }
 
@@ -3662,22 +3724,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	return ret;
 }
 
-/**
- *	netif_receive_skb - process receive buffer from network
- *	@skb: buffer to process
- *
- *	netif_receive_skb() is the main receive data processing function.
- *	It always succeeds. The buffer may be dropped during processing
- *	for congestion control or by the protocol layers.
- *
- *	This function may only be called from softirq context and interrupts
- *	should be enabled.
- *
- *	Return values (usually ignored):
- *	NET_RX_SUCCESS: no congestion
- *	NET_RX_DROP: packet was dropped
- */
-int netif_receive_skb(struct sk_buff *skb)
+static int netif_receive_skb_internal(struct sk_buff *skb)
 {
 	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
@@ -3703,6 +3750,28 @@ int netif_receive_skb(struct sk_buff *skb)
 #endif
 	return __netif_receive_skb(skb);
 }
+
+/**
+ *	netif_receive_skb - process receive buffer from network
+ *	@skb: buffer to process
+ *
+ *	netif_receive_skb() is the main receive data processing function.
+ *	It always succeeds. The buffer may be dropped during processing
+ *	for congestion control or by the protocol layers.
+ *
+ *	This function may only be called from softirq context and interrupts
+ *	should be enabled.
+ *
+ *	Return values (usually ignored):
+ *	NET_RX_SUCCESS: no congestion
+ *	NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb(struct sk_buff *skb)
+{
+	trace_netif_receive_skb_entry(skb);
+
+	return netif_receive_skb_internal(skb);
+}
 EXPORT_SYMBOL(netif_receive_skb);
 
 /* Network device is going away, flush any packets still pending
@@ -3752,7 +3821,7 @@ static int napi_gro_complete(struct sk_buff *skb)
 		if (ptype->type != type || !ptype->callbacks.gro_complete)
 			continue;
 
-		err = ptype->callbacks.gro_complete(skb);
+		err = ptype->callbacks.gro_complete(skb, 0);
 		break;
 	}
 	rcu_read_unlock();
@@ -3764,7 +3833,7 @@ static int napi_gro_complete(struct sk_buff *skb)
 	}
 
 out:
-	return netif_receive_skb(skb);
+	return netif_receive_skb_internal(skb);
 }
 
 /* napi->gro_list contains packets ordered by age.
@@ -3800,21 +3869,66 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct sk_buff *p;
 	unsigned int maclen = skb->dev->hard_header_len;
+	u32 hash = skb_get_hash_raw(skb);
 
 	for (p = napi->gro_list; p; p = p->next) {
 		unsigned long diffs;
 
+		NAPI_GRO_CB(p)->flush = 0;
+
+		if (hash != skb_get_hash_raw(p)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+
 		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
 		diffs |= p->vlan_tci ^ skb->vlan_tci;
 		if (maclen == ETH_HLEN)
 			diffs |= compare_ether_header(skb_mac_header(p),
-						      skb_gro_mac_header(skb));
+						      skb_mac_header(skb));
 		else if (!diffs)
 			diffs = memcmp(skb_mac_header(p),
-				       skb_gro_mac_header(skb),
+				       skb_mac_header(skb),
 				       maclen);
 		NAPI_GRO_CB(p)->same_flow = !diffs;
-		NAPI_GRO_CB(p)->flush = 0;
+	}
+}
+
+static void skb_gro_reset_offset(struct sk_buff *skb)
+{
+	const struct skb_shared_info *pinfo = skb_shinfo(skb);
+	const skb_frag_t *frag0 = &pinfo->frags[0];
+
+	NAPI_GRO_CB(skb)->data_offset = 0;
+	NAPI_GRO_CB(skb)->frag0 = NULL;
+	NAPI_GRO_CB(skb)->frag0_len = 0;
+
+	if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
+	    pinfo->nr_frags &&
+	    !PageHighMem(skb_frag_page(frag0))) {
+		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
+		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
+	}
+}
+
+static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
+{
+	struct skb_shared_info *pinfo = skb_shinfo(skb);
+
+	BUG_ON(skb->end - skb->tail < grow);
+
+	memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
+
+	skb->data_len -= grow;
+	skb->tail += grow;
+
+	pinfo->frags[0].page_offset += grow;
+	skb_frag_size_sub(&pinfo->frags[0], grow);
+
+	if (unlikely(!skb_frag_size(&pinfo->frags[0]))) {
+		skb_frag_unref(skb, 0);
+		memmove(pinfo->frags, pinfo->frags + 1,
+			--pinfo->nr_frags * sizeof(pinfo->frags[0]));
 	}
 }
 
@@ -3826,14 +3940,16 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	struct list_head *head = &offload_base;
 	int same_flow;
 	enum gro_result ret;
+	int grow;
 
-	if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
+	if (!(skb->dev->features & NETIF_F_GRO))
 		goto normal;
 
 	if (skb_is_gso(skb) || skb_has_frag_list(skb))
 		goto normal;
 
 	gro_list_prepare(napi, skb);
+	NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
@@ -3845,6 +3961,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->same_flow = 0;
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
+		NAPI_GRO_CB(skb)->udp_mark = 0;
 
 		pp = ptype->callbacks.gro_receive(&napi->gro_list, skb);
 		break;
@@ -3869,39 +3986,35 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	if (same_flow)
 		goto ok;
 
-	if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS)
+	if (NAPI_GRO_CB(skb)->flush)
 		goto normal;
 
-	napi->gro_count++;
+	if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) {
+		struct sk_buff *nskb = napi->gro_list;
+
+		/* locate the end of the list to select the 'oldest' flow */
+		while (nskb->next) {
+			pp = &nskb->next;
+			nskb = *pp;
+		}
+		*pp = NULL;
+		nskb->next = NULL;
+		napi_gro_complete(nskb);
+	} else {
+		napi->gro_count++;
+	}
 	NAPI_GRO_CB(skb)->count = 1;
 	NAPI_GRO_CB(skb)->age = jiffies;
+	NAPI_GRO_CB(skb)->last = skb;
 	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	skb->next = napi->gro_list;
 	napi->gro_list = skb;
 	ret = GRO_HELD;
 
 pull:
-	if (skb_headlen(skb) < skb_gro_offset(skb)) {
-		int grow = skb_gro_offset(skb) - skb_headlen(skb);
-
-		BUG_ON(skb->end - skb->tail < grow);
-
-		memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
-
-		skb->tail += grow;
-		skb->data_len -= grow;
-
-		skb_shinfo(skb)->frags[0].page_offset += grow;
-		skb_frag_size_sub(&skb_shinfo(skb)->frags[0], grow);
-
-		if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) {
-			skb_frag_unref(skb, 0);
-			memmove(skb_shinfo(skb)->frags,
-				skb_shinfo(skb)->frags + 1,
-				--skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
-		}
-	}
-
+	grow = skb_gro_offset(skb) - skb_headlen(skb);
+	if (grow > 0)
+		gro_pull_from_frag0(skb, grow);
 ok:
 	return ret;
 
@@ -3910,12 +4023,39 @@ normal:
 	goto pull;
 }
 
+struct packet_offload *gro_find_receive_by_type(__be16 type)
+{
+	struct list_head *offload_head = &offload_base;
+	struct packet_offload *ptype;
+
+	list_for_each_entry_rcu(ptype, offload_head, list) {
+		if (ptype->type != type || !ptype->callbacks.gro_receive)
+			continue;
+		return ptype;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(gro_find_receive_by_type);
+
+struct packet_offload *gro_find_complete_by_type(__be16 type)
+{
+	struct list_head *offload_head = &offload_base;
+	struct packet_offload *ptype;
+
+	list_for_each_entry_rcu(ptype, offload_head, list) {
+		if (ptype->type != type || !ptype->callbacks.gro_complete)
+			continue;
+		return ptype;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(gro_find_complete_by_type);
 
 static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 {
 	switch (ret) {
 	case GRO_NORMAL:
-		if (netif_receive_skb(skb))
+		if (netif_receive_skb_internal(skb))
 			ret = GRO_DROP;
 		break;
 
@@ -3938,25 +4078,10 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 	return ret;
 }
 
-static void skb_gro_reset_offset(struct sk_buff *skb)
-{
-	const struct skb_shared_info *pinfo = skb_shinfo(skb);
-	const skb_frag_t *frag0 = &pinfo->frags[0];
-
-	NAPI_GRO_CB(skb)->data_offset = 0;
-	NAPI_GRO_CB(skb)->frag0 = NULL;
-	NAPI_GRO_CB(skb)->frag0_len = 0;
-
-	if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
-	    pinfo->nr_frags &&
-	    !PageHighMem(skb_frag_page(frag0))) {
-		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
-		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
-	}
-}
-
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
+	trace_napi_gro_receive_entry(skb);
+
 	skb_gro_reset_offset(skb);
 
 	return napi_skb_finish(dev_gro_receive(napi, skb), skb);
@@ -3971,6 +4096,9 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+	skb->encapsulation = 0;
+	skb_shinfo(skb)->gso_type = 0;
+	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 
 	napi->skb = skb;
 }
@@ -3987,17 +4115,16 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(napi_get_frags);
 
-static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
-			       gro_result_t ret)
+static gro_result_t napi_frags_finish(struct napi_struct *napi,
+				      struct sk_buff *skb,
+				      gro_result_t ret)
 {
 	switch (ret) {
 	case GRO_NORMAL:
 	case GRO_HELD:
+		__skb_push(skb, ETH_HLEN);
 		skb->protocol = eth_type_trans(skb, skb->dev);
-
-		if (ret == GRO_HELD)
-			skb_gro_pull(skb, -ETH_HLEN);
-		else if (netif_receive_skb(skb))
+		if (ret == GRO_NORMAL && netif_receive_skb_internal(skb))
 			ret = GRO_DROP;
 		break;
 
@@ -4013,39 +4140,42 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
 	return ret;
 }
 
+/* Upper GRO stack assumes network header starts at gro_offset=0
+ * Drivers could call both napi_gro_frags() and napi_gro_receive()
+ * We copy ethernet header into skb->data to have a common layout.
+ */
 static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 {
 	struct sk_buff *skb = napi->skb;
-	struct ethhdr *eth;
-	unsigned int hlen;
-	unsigned int off;
+	const struct ethhdr *eth;
+	unsigned int hlen = sizeof(*eth);
 
 	napi->skb = NULL;
 
 	skb_reset_mac_header(skb);
 	skb_gro_reset_offset(skb);
 
-	off = skb_gro_offset(skb);
-	hlen = off + sizeof(*eth);
-	eth = skb_gro_header_fast(skb, off);
-	if (skb_gro_header_hard(skb, hlen)) {
-		eth = skb_gro_header_slow(skb, hlen, off);
+	eth = skb_gro_header_fast(skb, 0);
+	if (unlikely(skb_gro_header_hard(skb, hlen))) {
+		eth = skb_gro_header_slow(skb, hlen, 0);
 		if (unlikely(!eth)) {
 			napi_reuse_skb(napi, skb);
-			skb = NULL;
-			goto out;
+			return NULL;
 		}
+	} else {
+		gro_pull_from_frag0(skb, hlen);
+		NAPI_GRO_CB(skb)->frag0 += hlen;
+		NAPI_GRO_CB(skb)->frag0_len -= hlen;
 	}
-
-	skb_gro_pull(skb, sizeof(*eth));
+	__skb_pull(skb, hlen);
 
 	/*
 	 * This works because the only protocols we care about don't require
-	 * special handling.  We'll fix it up properly at the end.
+	 * special handling.
+	 * We'll fix it up properly in napi_frags_finish()
 	 */
 	skb->protocol = eth->h_proto;
 
-out:
 	return skb;
 }
 
@@ -4056,12 +4186,14 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
 	if (!skb)
 		return GRO_DROP;
 
+	trace_napi_gro_frags_entry(skb);
+
 	return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
 }
 EXPORT_SYMBOL(napi_gro_frags);
 
 /*
- * net_rps_action sends any pending IPI's for rps.
+ * net_rps_action_and_irq_enable sends any pending IPI's for rps.
  * Note: called with local irq disabled, but exits with local irq enabled.
  */
 static void net_rps_action_and_irq_enable(struct softnet_data *sd)
@@ -4079,8 +4211,8 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
 			struct softnet_data *next = remsd->rps_ipi_next;
 
 			if (cpu_online(remsd->cpu))
-				__smp_call_function_single(remsd->cpu,
-							   &remsd->csd, 0);
+				smp_call_function_single_async(remsd->cpu,
+							   &remsd->csd);
 			remsd = next;
 		}
 	} else
@@ -4104,9 +4236,8 @@ static int process_backlog(struct napi_struct *napi, int quota)
 #endif
 	napi->weight = weight_p;
 	local_irq_disable();
-	while (work < quota) {
+	while (1) {
 		struct sk_buff *skb;
-		unsigned int qlen;
 
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
 			local_irq_enable();
@@ -4120,24 +4251,24 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		}
 
 		rps_lock(sd);
-		qlen = skb_queue_len(&sd->input_pkt_queue);
-		if (qlen)
-			skb_queue_splice_tail_init(&sd->input_pkt_queue,
-						   &sd->process_queue);
-
-		if (qlen < quota - work) {
+		if (skb_queue_empty(&sd->input_pkt_queue)) {
 			/*
 			 * Inline a custom version of __napi_complete().
 			 * only current cpu owns and manipulates this napi,
-			 * and NAPI_STATE_SCHED is the only possible flag set on backlog.
-			 * we can use a plain write instead of clear_bit(),
+			 * and NAPI_STATE_SCHED is the only possible flag set
+			 * on backlog.
+			 * We can use a plain write instead of clear_bit(),
 			 * and we dont need an smp_mb() memory barrier.
 			 */
 			list_del(&napi->poll_list);
 			napi->state = 0;
+			rps_unlock(sd);
 
-			quota = work + qlen;
+			break;
 		}
+
+		skb_queue_splice_tail_init(&sd->input_pkt_queue,
+					   &sd->process_queue);
 		rps_unlock(sd);
 	}
 	local_irq_enable();
@@ -4167,7 +4298,7 @@ void __napi_complete(struct napi_struct *n)
 	BUG_ON(n->gro_list);
 
 	list_del(&n->poll_list);
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(NAPI_STATE_SCHED, &n->state);
 }
 EXPORT_SYMBOL(__napi_complete);
@@ -4266,17 +4397,10 @@ EXPORT_SYMBOL(netif_napi_add);
 
 void netif_napi_del(struct napi_struct *napi)
 {
-	struct sk_buff *skb, *next;
-
 	list_del_init(&napi->dev_list);
 	napi_free_frags(napi);
 
-	for (skb = napi->gro_list; skb; skb = next) {
-		next = skb->next;
-		skb->next = NULL;
-		kfree_skb(skb);
-	}
-
+	kfree_skb_list(napi->gro_list);
 	napi->gro_list = NULL;
 	napi->gro_count = 0;
 }
@@ -4393,19 +4517,6 @@ struct netdev_adjacent {
 	struct rcu_head rcu;
 };
 
-static struct netdev_adjacent *__netdev_find_adj_rcu(struct net_device *dev,
-						     struct net_device *adj_dev,
-						     struct list_head *adj_list)
-{
-	struct netdev_adjacent *adj;
-
-	list_for_each_entry_rcu(adj, adj_list, list) {
-		if (adj->dev == adj_dev)
-			return adj;
-	}
-	return NULL;
-}
-
 static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
 						 struct net_device *adj_dev,
 						 struct list_head *adj_list)
@@ -4444,13 +4555,12 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
  * Find out if a device is linked to an upper device and return true in case
  * it is. The caller must hold the RTNL lock.
  */
-bool netdev_has_any_upper_dev(struct net_device *dev)
+static bool netdev_has_any_upper_dev(struct net_device *dev)
 {
 	ASSERT_RTNL();
 
 	return !list_empty(&dev->all_adj_list.upper);
 }
-EXPORT_SYMBOL(netdev_has_any_upper_dev);
 
 /**
  * netdev_master_upper_dev_get - Get master upper device
@@ -4487,6 +4597,32 @@ void *netdev_adjacent_get_private(struct list_head *adj_list)
 EXPORT_SYMBOL(netdev_adjacent_get_private);
 
 /**
+ * netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next device from the dev's upper list, starting from iter
+ * position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+						 struct list_head **iter)
+{
+	struct netdev_adjacent *upper;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
+
+	upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+	if (&upper->list == &dev->adj_list.upper)
+		return NULL;
+
+	*iter = &upper->list;
+
+	return upper->dev;
+}
+EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+
+/**
  * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
  * @dev: device
  * @iter: list_head ** of the current position
@@ -4499,7 +4635,7 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 {
 	struct netdev_adjacent *upper;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
 
 	upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
 
@@ -4533,8 +4669,7 @@ void *netdev_lower_get_next_private(struct net_device *dev,
 	if (&lower->list == &dev->adj_list.lower)
 		return NULL;
 
-	if (iter)
-		*iter = lower->list.next;
+	*iter = lower->list.next;
 
 	return lower->private;
 }
@@ -4562,14 +4697,60 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 	if (&lower->list == &dev->adj_list.lower)
 		return NULL;
 
-	if (iter)
-		*iter = &lower->list;
+	*iter = &lower->list;
 
 	return lower->private;
 }
 EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
 
 /**
+ * netdev_lower_get_next - Get the next device from the lower neighbour
+ *                         list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->adj_list.lower)
+		return NULL;
+
+	*iter = &lower->list;
+
+	return lower->dev;
+}
+EXPORT_SYMBOL(netdev_lower_get_next);
+
+/**
+ * netdev_lower_get_first_private_rcu - Get the first ->private from the
+ *				       lower neighbour list, RCU
+ *				       variant
+ * @dev: device
+ *
+ * Gets the first netdev_adjacent->private from the dev's lower neighbour
+ * list. The caller must hold RCU read lock.
+ */
+void *netdev_lower_get_first_private_rcu(struct net_device *dev)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_first_or_null_rcu(&dev->adj_list.lower,
+			struct netdev_adjacent, list);
+	if (lower)
+		return lower->private;
+	return NULL;
+}
+EXPORT_SYMBOL(netdev_lower_get_first_private_rcu);
+
+/**
  * netdev_master_upper_dev_get_rcu - Get master upper device
  * @dev: device
  *
@@ -4588,13 +4769,36 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
 
+static int netdev_adjacent_sysfs_add(struct net_device *dev,
+			      struct net_device *adj_dev,
+			      struct list_head *dev_list)
+{
+	char linkname[IFNAMSIZ+7];
+	sprintf(linkname, dev_list == &dev->adj_list.upper ?
+		"upper_%s" : "lower_%s", adj_dev->name);
+	return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj),
+				 linkname);
+}
+static void netdev_adjacent_sysfs_del(struct net_device *dev,
+			       char *name,
+			       struct list_head *dev_list)
+{
+	char linkname[IFNAMSIZ+7];
+	sprintf(linkname, dev_list == &dev->adj_list.upper ?
+		"upper_%s" : "lower_%s", name);
+	sysfs_remove_link(&(dev->dev.kobj), linkname);
+}
+
+#define netdev_adjacent_is_neigh_list(dev, dev_list) \
+		(dev_list == &dev->adj_list.upper || \
+		 dev_list == &dev->adj_list.lower)
+
 static int __netdev_adjacent_dev_insert(struct net_device *dev,
 					struct net_device *adj_dev,
 					struct list_head *dev_list,
 					void *private, bool master)
 {
 	struct netdev_adjacent *adj;
-	char linkname[IFNAMSIZ+7];
 	int ret;
 
 	adj = __netdev_find_adj(dev, adj_dev, dev_list);
@@ -4617,16 +4821,8 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	pr_debug("dev_hold for %s, because of link added from %s to %s\n",
 		 adj_dev->name, dev->name, adj_dev->name);
 
-	if (dev_list == &dev->adj_list.lower) {
-		sprintf(linkname, "lower_%s", adj_dev->name);
-		ret = sysfs_create_link(&(dev->dev.kobj),
-					&(adj_dev->dev.kobj), linkname);
-		if (ret)
-			goto free_adj;
-	} else if (dev_list == &dev->adj_list.upper) {
-		sprintf(linkname, "upper_%s", adj_dev->name);
-		ret = sysfs_create_link(&(dev->dev.kobj),
-					&(adj_dev->dev.kobj), linkname);
+	if (netdev_adjacent_is_neigh_list(dev, dev_list)) {
+		ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list);
 		if (ret)
 			goto free_adj;
 	}
@@ -4646,14 +4842,8 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	return 0;
 
 remove_symlinks:
-	if (dev_list == &dev->adj_list.lower) {
-		sprintf(linkname, "lower_%s", adj_dev->name);
-		sysfs_remove_link(&(dev->dev.kobj), linkname);
-	} else if (dev_list == &dev->adj_list.upper) {
-		sprintf(linkname, "upper_%s", adj_dev->name);
-		sysfs_remove_link(&(dev->dev.kobj), linkname);
-	}
-
+	if (netdev_adjacent_is_neigh_list(dev, dev_list))
+		netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
 free_adj:
 	kfree(adj);
 	dev_put(adj_dev);
@@ -4661,12 +4851,11 @@ free_adj:
 	return ret;
 }
 
-void __netdev_adjacent_dev_remove(struct net_device *dev,
-				  struct net_device *adj_dev,
-				  struct list_head *dev_list)
+static void __netdev_adjacent_dev_remove(struct net_device *dev,
+					 struct net_device *adj_dev,
+					 struct list_head *dev_list)
 {
 	struct netdev_adjacent *adj;
-	char linkname[IFNAMSIZ+7];
 
 	adj = __netdev_find_adj(dev, adj_dev, dev_list);
 
@@ -4686,13 +4875,8 @@ void __netdev_adjacent_dev_remove(struct net_device *dev,
 	if (adj->master)
 		sysfs_remove_link(&(dev->dev.kobj), "master");
 
-	if (dev_list == &dev->adj_list.lower) {
-		sprintf(linkname, "lower_%s", adj_dev->name);
-		sysfs_remove_link(&(dev->dev.kobj), linkname);
-	} else if (dev_list == &dev->adj_list.upper) {
-		sprintf(linkname, "upper_%s", adj_dev->name);
-		sysfs_remove_link(&(dev->dev.kobj), linkname);
-	}
+	if (netdev_adjacent_is_neigh_list(dev, dev_list))
+		netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
 
 	list_del_rcu(&adj->list);
 	pr_debug("dev_put for %s, because link removed from %s to %s\n",
@@ -4701,11 +4885,11 @@ void __netdev_adjacent_dev_remove(struct net_device *dev,
 	kfree_rcu(adj, rcu);
 }
 
-int __netdev_adjacent_dev_link_lists(struct net_device *dev,
-				     struct net_device *upper_dev,
-				     struct list_head *up_list,
-				     struct list_head *down_list,
-				     void *private, bool master)
+static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
+					    struct net_device *upper_dev,
+					    struct list_head *up_list,
+					    struct list_head *down_list,
+					    void *private, bool master)
 {
 	int ret;
 
@@ -4724,8 +4908,8 @@ int __netdev_adjacent_dev_link_lists(struct net_device *dev,
 	return 0;
 }
 
-int __netdev_adjacent_dev_link(struct net_device *dev,
-			       struct net_device *upper_dev)
+static int __netdev_adjacent_dev_link(struct net_device *dev,
+				      struct net_device *upper_dev)
 {
 	return __netdev_adjacent_dev_link_lists(dev, upper_dev,
 						&dev->all_adj_list.upper,
@@ -4733,26 +4917,26 @@ int __netdev_adjacent_dev_link(struct net_device *dev,
 						NULL, false);
 }
 
-void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
-					struct net_device *upper_dev,
-					struct list_head *up_list,
-					struct list_head *down_list)
+static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
+					       struct net_device *upper_dev,
+					       struct list_head *up_list,
+					       struct list_head *down_list)
 {
 	__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
 	__netdev_adjacent_dev_remove(upper_dev, dev, down_list);
 }
 
-void __netdev_adjacent_dev_unlink(struct net_device *dev,
-				  struct net_device *upper_dev)
+static void __netdev_adjacent_dev_unlink(struct net_device *dev,
+					 struct net_device *upper_dev)
 {
 	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
 					   &dev->all_adj_list.upper,
 					   &upper_dev->all_adj_list.lower);
 }
 
-int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
-					 struct net_device *upper_dev,
-					 void *private, bool master)
+static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
+						struct net_device *upper_dev,
+						void *private, bool master)
 {
 	int ret = __netdev_adjacent_dev_link(dev, upper_dev);
 
@@ -4771,8 +4955,8 @@ int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 	return 0;
 }
 
-void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
-					    struct net_device *upper_dev)
+static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
+						   struct net_device *upper_dev)
 {
 	__netdev_adjacent_dev_unlink(dev, upper_dev);
 	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
@@ -4961,20 +5145,24 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
-void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
-				       struct net_device *lower_dev)
+void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
 {
-	struct netdev_adjacent *lower;
+	struct netdev_adjacent *iter;
 
-	if (!lower_dev)
-		return NULL;
-	lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower);
-	if (!lower)
-		return NULL;
+	list_for_each_entry(iter, &dev->adj_list.upper, list) {
+		netdev_adjacent_sysfs_del(iter->dev, oldname,
+					  &iter->dev->adj_list.lower);
+		netdev_adjacent_sysfs_add(iter->dev, dev,
+					  &iter->dev->adj_list.lower);
+	}
 
-	return lower->private;
+	list_for_each_entry(iter, &dev->adj_list.lower, list) {
+		netdev_adjacent_sysfs_del(iter->dev, oldname,
+					  &iter->dev->adj_list.upper);
+		netdev_adjacent_sysfs_add(iter->dev, dev,
+					  &iter->dev->adj_list.upper);
+	}
 }
-EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu);
 
 void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev)
@@ -4991,6 +5179,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
+
+int dev_get_nest_level(struct net_device *dev,
+		       bool (*type_check)(struct net_device *dev))
+{
+	struct net_device *lower = NULL;
+	struct list_head *iter;
+	int max_nest = -1;
+	int nest;
+
+	ASSERT_RTNL();
+
+	netdev_for_each_lower_dev(dev, lower, iter) {
+		nest = dev_get_nest_level(lower, type_check);
+		if (max_nest < nest)
+			max_nest = nest;
+	}
+
+	if (type_check(dev))
+		max_nest++;
+
+	return max_nest;
+}
+EXPORT_SYMBOL(dev_get_nest_level);
+
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -5308,6 +5520,17 @@ int dev_change_flags(struct net_device *dev, unsigned int flags)
 }
 EXPORT_SYMBOL(dev_change_flags);
 
+static int __dev_set_mtu(struct net_device *dev, int new_mtu)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (ops->ndo_change_mtu)
+		return ops->ndo_change_mtu(dev, new_mtu);
+
+	dev->mtu = new_mtu;
+	return 0;
+}
+
 /**
  *	dev_set_mtu - Change maximum transfer unit
  *	@dev: device
@@ -5317,8 +5540,7 @@ EXPORT_SYMBOL(dev_change_flags);
  */
 int dev_set_mtu(struct net_device *dev, int new_mtu)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
-	int err;
+	int err, orig_mtu;
 
 	if (new_mtu == dev->mtu)
 		return 0;
@@ -5330,14 +5552,25 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 	if (!netif_device_present(dev))
 		return -ENODEV;
 
-	err = 0;
-	if (ops->ndo_change_mtu)
-		err = ops->ndo_change_mtu(dev, new_mtu);
-	else
-		dev->mtu = new_mtu;
+	err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev);
+	err = notifier_to_errno(err);
+	if (err)
+		return err;
 
-	if (!err)
-		call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+	orig_mtu = dev->mtu;
+	err = __dev_set_mtu(dev, new_mtu);
+
+	if (!err) {
+		err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+		err = notifier_to_errno(err);
+		if (err) {
+			/* setting mtu back and notifying everyone again,
+			 * so that they have a chance to revert changes.
+			 */
+			__dev_set_mtu(dev, orig_mtu);
+			call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+		}
+	}
 	return err;
 }
 EXPORT_SYMBOL(dev_set_mtu);
@@ -5439,7 +5672,7 @@ static int dev_new_index(struct net *net)
 
 /* Delayed registration/unregisteration */
 static LIST_HEAD(net_todo_list);
-static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
+DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
 
 static void net_set_todo(struct net_device *dev)
 {
@@ -5496,10 +5729,6 @@ static void rollback_registered_many(struct list_head *head)
 		*/
 		call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 
-		if (!dev->rtnl_link_ops ||
-		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
-			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
-
 		/*
 		 *	Flush the unicast and multicast chains
 		 */
@@ -5509,6 +5738,10 @@ static void rollback_registered_many(struct list_head *head)
 		if (dev->netdev_ops->ndo_uninit)
 			dev->netdev_ops->ndo_uninit(dev);
 
+		if (!dev->rtnl_link_ops ||
+		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
+
 		/* Notifier chain MUST detach us all upper devices. */
 		WARN_ON(netdev_has_any_upper_dev(dev));
 
@@ -5592,6 +5825,13 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		}
 	}
 
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (dev->netdev_ops->ndo_busy_poll)
+		features |= NETIF_F_BUSY_POLL;
+	else
+#endif
+		features &= ~NETIF_F_BUSY_POLL;
+
 	return features;
 }
 
@@ -5691,7 +5931,7 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 }
 EXPORT_SYMBOL(netif_stacked_transfer_operstate);
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 static int netif_alloc_rx_queues(struct net_device *dev)
 {
 	unsigned int i, count = dev->num_rx_queues;
@@ -5727,10 +5967,7 @@ static void netdev_init_one_queue(struct net_device *dev,
 
 static void netif_free_tx_queues(struct net_device *dev)
 {
-	if (is_vmalloc_addr(dev->_tx))
-		vfree(dev->_tx);
-	else
-		kfree(dev->_tx);
+	kvfree(dev->_tx);
 }
 
 static int netif_alloc_netdev_queues(struct net_device *dev)
@@ -5830,13 +6067,8 @@ int register_netdevice(struct net_device *dev)
 	dev->features |= NETIF_F_SOFT_FEATURES;
 	dev->wanted_features = dev->features & dev->hw_features;
 
-	/* Turn on no cache copy if HW is doing checksum */
 	if (!(dev->flags & IFF_LOOPBACK)) {
 		dev->hw_features |= NETIF_F_NOCACHE_COPY;
-		if (dev->features & NETIF_F_ALL_CSUM) {
-			dev->wanted_features |= NETIF_F_NOCACHE_COPY;
-			dev->features |= NETIF_F_NOCACHE_COPY;
-		}
 	}
 
 	/* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
@@ -6172,6 +6404,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 		netdev_stats_to_stats64(storage, &dev->stats);
 	}
 	storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
+	storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
 	return storage;
 }
 EXPORT_SYMBOL(dev_get_stats);
@@ -6208,10 +6441,7 @@ void netdev_freemem(struct net_device *dev)
 {
 	char *addr = (char *)dev - dev->padded;
 
-	if (is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
+	kvfree(addr);
 }
 
 /**
@@ -6223,7 +6453,7 @@ void netdev_freemem(struct net_device *dev)
  *	@rxqs:		the number of RX subqueues to allocate
  *
  *	Allocates a struct net_device with private data area for driver use
- *	and performs basic initialization.  Also allocates subquue structs
+ *	and performs basic initialization.  Also allocates subqueue structs
  *	for each queue on the device.
  */
 struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
@@ -6241,7 +6471,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		return NULL;
 	}
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	if (rxqs < 1) {
 		pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n");
 		return NULL;
@@ -6297,7 +6527,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	if (netif_alloc_netdev_queues(dev))
 		goto free_all;
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	dev->num_rx_queues = rxqs;
 	dev->real_num_rx_queues = rxqs;
 	if (netif_alloc_rx_queues(dev))
@@ -6316,11 +6546,6 @@ free_all:
 
 free_pcpu:
 	free_percpu(dev->pcpu_refcnt);
-	netif_free_tx_queues(dev);
-#ifdef CONFIG_RPS
-	kfree(dev->_rx);
-#endif
-
 free_dev:
 	netdev_freemem(dev);
 	return NULL;
@@ -6342,7 +6567,7 @@ void free_netdev(struct net_device *dev)
 	release_net(dev_net(dev));
 
 	netif_free_tx_queues(dev);
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	kfree(dev->_rx);
 #endif
 
@@ -6417,6 +6642,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue);
 /**
  *	unregister_netdevice_many - unregister many devices
  *	@head: list of devices
+ *
+ *  Note: As most callers use a stack allocated list_head,
+ *  we force a list_del() to make sure stack wont be corrupted later.
  */
 void unregister_netdevice_many(struct list_head *head)
 {
@@ -6426,6 +6654,7 @@ void unregister_netdevice_many(struct list_head *head)
 		rollback_registered_many(head);
 		list_for_each_entry(dev, head, unreg_list)
 			net_set_todo(dev);
+		list_del(head);
 	}
 }
 EXPORT_SYMBOL(unregister_netdevice_many);
@@ -6612,11 +6841,11 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 
 	/* Process offline CPU's input_pkt_queue */
 	while ((skb = __skb_dequeue(&oldsd->process_queue))) {
-		netif_rx(skb);
+		netif_rx_internal(skb);
 		input_queue_head_incr(oldsd);
 	}
 	while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
-		netif_rx(skb);
+		netif_rx_internal(skb);
 		input_queue_head_incr(oldsd);
 	}
 
@@ -6881,7 +7110,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list)
 		}
 	}
 	unregister_netdevice_many(&dev_kill_list);
-	list_del(&dev_kill_list);
 	rtnl_unlock();
 }
 
@@ -6929,28 +7157,18 @@ static int __init net_dev_init(void)
 	for_each_possible_cpu(i) {
 		struct softnet_data *sd = &per_cpu(softnet_data, i);
 
-		memset(sd, 0, sizeof(*sd));
 		skb_queue_head_init(&sd->input_pkt_queue);
 		skb_queue_head_init(&sd->process_queue);
-		sd->completion_queue = NULL;
 		INIT_LIST_HEAD(&sd->poll_list);
-		sd->output_queue = NULL;
 		sd->output_queue_tailp = &sd->output_queue;
 #ifdef CONFIG_RPS
 		sd->csd.func = rps_trigger_softirq;
 		sd->csd.info = sd;
-		sd->csd.flags = 0;
 		sd->cpu = i;
 #endif
 
 		sd->backlog.poll = process_backlog;
 		sd->backlog.weight = weight_p;
-		sd->backlog.gro_list = NULL;
-		sd->backlog.gro_count = 0;
-
-#ifdef CONFIG_NET_FLOW_LIMIT
-		sd->flow_limit = NULL;
-#endif
 	}
 
 	dev_boot_phase = 0;
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index ec40a849fc4..b6b230600b9 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -38,7 +38,7 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list,
 	ha->type = addr_type;
 	ha->refcount = 1;
 	ha->global_use = global;
-	ha->synced = sync;
+	ha->synced = sync ? 1 : 0;
 	ha->sync_cnt = 0;
 	list_add_tail_rcu(&ha->list, &list->list);
 	list->count++;
@@ -48,7 +48,8 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list,
 
 static int __hw_addr_add_ex(struct netdev_hw_addr_list *list,
 			    const unsigned char *addr, int addr_len,
-			    unsigned char addr_type, bool global, bool sync)
+			    unsigned char addr_type, bool global, bool sync,
+			    int sync_count)
 {
 	struct netdev_hw_addr *ha;
 
@@ -66,10 +67,10 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list,
 					ha->global_use = true;
 			}
 			if (sync) {
-				if (ha->synced)
+				if (ha->synced && sync_count)
 					return -EEXIST;
 				else
-					ha->synced = true;
+					ha->synced++;
 			}
 			ha->refcount++;
 			return 0;
@@ -84,7 +85,8 @@ static int __hw_addr_add(struct netdev_hw_addr_list *list,
 			 const unsigned char *addr, int addr_len,
 			 unsigned char addr_type)
 {
-	return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false);
+	return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false,
+				0);
 }
 
 static int __hw_addr_del_entry(struct netdev_hw_addr_list *list,
@@ -101,7 +103,7 @@ static int __hw_addr_del_entry(struct netdev_hw_addr_list *list,
 		ha->global_use = false;
 
 	if (sync)
-		ha->synced = false;
+		ha->synced--;
 
 	if (--ha->refcount)
 		return 0;
@@ -139,7 +141,7 @@ static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list,
 	int err;
 
 	err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type,
-			       false, true);
+			       false, true, ha->sync_cnt);
 	if (err && err != -EEXIST)
 		return err;
 
@@ -186,47 +188,6 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list,
 	return err;
 }
 
-int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list,
-			   struct netdev_hw_addr_list *from_list,
-			   int addr_len, unsigned char addr_type)
-{
-	int err;
-	struct netdev_hw_addr *ha, *ha2;
-	unsigned char type;
-
-	list_for_each_entry(ha, &from_list->list, list) {
-		type = addr_type ? addr_type : ha->type;
-		err = __hw_addr_add(to_list, ha->addr, addr_len, type);
-		if (err)
-			goto unroll;
-	}
-	return 0;
-
-unroll:
-	list_for_each_entry(ha2, &from_list->list, list) {
-		if (ha2 == ha)
-			break;
-		type = addr_type ? addr_type : ha2->type;
-		__hw_addr_del(to_list, ha2->addr, addr_len, type);
-	}
-	return err;
-}
-EXPORT_SYMBOL(__hw_addr_add_multiple);
-
-void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list,
-			    struct netdev_hw_addr_list *from_list,
-			    int addr_len, unsigned char addr_type)
-{
-	struct netdev_hw_addr *ha;
-	unsigned char type;
-
-	list_for_each_entry(ha, &from_list->list, list) {
-		type = addr_type ? addr_type : ha->type;
-		__hw_addr_del(to_list, ha->addr, addr_len, type);
-	}
-}
-EXPORT_SYMBOL(__hw_addr_del_multiple);
-
 /* This function only works where there is a strict 1-1 relationship
  * between source and destionation of they synch. If you ever need to
  * sync addresses to more then 1 destination, you need to use
@@ -264,7 +225,92 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
 }
 EXPORT_SYMBOL(__hw_addr_unsync);
 
-void __hw_addr_flush(struct netdev_hw_addr_list *list)
+/**
+ *  __hw_addr_sync_dev - Synchonize device's multicast list
+ *  @list: address list to syncronize
+ *  @dev:  device to sync
+ *  @sync: function to call if address should be added
+ *  @unsync: function to call if address should be removed
+ *
+ *  This funciton is intended to be called from the ndo_set_rx_mode
+ *  function of devices that require explicit address add/remove
+ *  notifications.  The unsync function may be NULL in which case
+ *  the addresses requiring removal will simply be removed without
+ *  any notification to the device.
+ **/
+int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
+		       struct net_device *dev,
+		       int (*sync)(struct net_device *, const unsigned char *),
+		       int (*unsync)(struct net_device *,
+				     const unsigned char *))
+{
+	struct netdev_hw_addr *ha, *tmp;
+	int err;
+
+	/* first go through and flush out any stale entries */
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (!ha->sync_cnt || ha->refcount != 1)
+			continue;
+
+		/* if unsync is defined and fails defer unsyncing address */
+		if (unsync && unsync(dev, ha->addr))
+			continue;
+
+		ha->sync_cnt--;
+		__hw_addr_del_entry(list, ha, false, false);
+	}
+
+	/* go through and sync new entries to the list */
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (ha->sync_cnt)
+			continue;
+
+		err = sync(dev, ha->addr);
+		if (err)
+			return err;
+
+		ha->sync_cnt++;
+		ha->refcount++;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(__hw_addr_sync_dev);
+
+/**
+ *  __hw_addr_unsync_dev - Remove synchonized addresses from device
+ *  @list: address list to remove syncronized addresses from
+ *  @dev:  device to sync
+ *  @unsync: function to call if address should be removed
+ *
+ *  Remove all addresses that were added to the device by __hw_addr_sync_dev().
+ *  This function is intended to be called from the ndo_stop or ndo_open
+ *  functions on devices that require explicit address add/remove
+ *  notifications.  If the unsync function pointer is NULL then this function
+ *  can be used to just reset the sync_cnt for the addresses in the list.
+ **/
+void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
+			  struct net_device *dev,
+			  int (*unsync)(struct net_device *,
+					const unsigned char *))
+{
+	struct netdev_hw_addr *ha, *tmp;
+
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (!ha->sync_cnt)
+			continue;
+
+		/* if unsync is defined and fails defer unsyncing address */
+		if (unsync && unsync(dev, ha->addr))
+			continue;
+
+		ha->sync_cnt--;
+		__hw_addr_del_entry(list, ha, false, false);
+	}
+}
+EXPORT_SYMBOL(__hw_addr_unsync_dev);
+
+static void __hw_addr_flush(struct netdev_hw_addr_list *list)
 {
 	struct netdev_hw_addr *ha, *tmp;
 
@@ -274,7 +320,6 @@ void __hw_addr_flush(struct netdev_hw_addr_list *list)
 	}
 	list->count = 0;
 }
-EXPORT_SYMBOL(__hw_addr_flush);
 
 void __hw_addr_init(struct netdev_hw_addr_list *list)
 {
@@ -400,59 +445,6 @@ int dev_addr_del(struct net_device *dev, const unsigned char *addr,
 }
 EXPORT_SYMBOL(dev_addr_del);
 
-/**
- *	dev_addr_add_multiple - Add device addresses from another device
- *	@to_dev: device to which addresses will be added
- *	@from_dev: device from which addresses will be added
- *	@addr_type: address type - 0 means type will be used from from_dev
- *
- *	Add device addresses of the one device to another.
- **
- *	The caller must hold the rtnl_mutex.
- */
-int dev_addr_add_multiple(struct net_device *to_dev,
-			  struct net_device *from_dev,
-			  unsigned char addr_type)
-{
-	int err;
-
-	ASSERT_RTNL();
-
-	if (from_dev->addr_len != to_dev->addr_len)
-		return -EINVAL;
-	err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs,
-				     to_dev->addr_len, addr_type);
-	if (!err)
-		call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev);
-	return err;
-}
-EXPORT_SYMBOL(dev_addr_add_multiple);
-
-/**
- *	dev_addr_del_multiple - Delete device addresses by another device
- *	@to_dev: device where the addresses will be deleted
- *	@from_dev: device supplying the addresses to be deleted
- *	@addr_type: address type - 0 means type will be used from from_dev
- *
- *	Deletes addresses in to device by the list of addresses in from device.
- *
- *	The caller must hold the rtnl_mutex.
- */
-int dev_addr_del_multiple(struct net_device *to_dev,
-			  struct net_device *from_dev,
-			  unsigned char addr_type)
-{
-	ASSERT_RTNL();
-
-	if (from_dev->addr_len != to_dev->addr_len)
-		return -EINVAL;
-	__hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs,
-			       to_dev->addr_len, addr_type);
-	call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev);
-	return 0;
-}
-EXPORT_SYMBOL(dev_addr_del_multiple);
-
 /*
  * Unicast list handling functions
  */
@@ -676,7 +668,7 @@ static int __dev_mc_add(struct net_device *dev, const unsigned char *addr,
 
 	netif_addr_lock_bh(dev);
 	err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len,
-			       NETDEV_HW_ADDR_T_MULTICAST, global, false);
+			       NETDEV_HW_ADDR_T_MULTICAST, global, false, 0);
 	if (!err)
 		__dev_set_rx_mode(dev);
 	netif_addr_unlock_bh(dev);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 95897183226..e70301eb7a4 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -64,7 +64,6 @@ static struct genl_family net_drop_monitor_family = {
 	.hdrsize        = 0,
 	.name           = "NET_DM",
 	.version        = 2,
-	.maxattr        = NET_DM_CMD_MAX,
 };
 
 static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
diff --git a/net/core/dst.c b/net/core/dst.c
index ca4231ec734..a028409ee43 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -142,12 +142,12 @@ loop:
 	mutex_unlock(&dst_gc_mutex);
 }
 
-int dst_discard(struct sk_buff *skb)
+int dst_discard_sk(struct sock *sk, struct sk_buff *skb)
 {
 	kfree_skb(skb);
 	return 0;
 }
-EXPORT_SYMBOL(dst_discard);
+EXPORT_SYMBOL(dst_discard_sk);
 
 const u32 dst_default_metrics[RTAX_MAX + 1] = {
 	/* This initializer is needed to force linker to place this variable
@@ -184,7 +184,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
 	dst->xfrm = NULL;
 #endif
 	dst->input = dst_discard;
-	dst->output = dst_discard;
+	dst->output = dst_discard_sk;
 	dst->error = 0;
 	dst->obsolete = initial_obsolete;
 	dst->header_len = 0;
@@ -209,8 +209,10 @@ static void ___dst_free(struct dst_entry *dst)
 	/* The first case (dev==NULL) is required, when
 	   protocol module is unloaded.
 	 */
-	if (dst->dev == NULL || !(dst->dev->flags&IFF_UP))
-		dst->input = dst->output = dst_discard;
+	if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) {
+		dst->input = dst_discard;
+		dst->output = dst_discard_sk;
+	}
 	dst->obsolete = DST_OBSOLETE_DEAD;
 }
 
@@ -267,6 +269,15 @@ again:
 }
 EXPORT_SYMBOL(dst_destroy);
 
+static void dst_destroy_rcu(struct rcu_head *head)
+{
+	struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
+
+	dst = dst_destroy(dst);
+	if (dst)
+		__dst_free(dst);
+}
+
 void dst_release(struct dst_entry *dst)
 {
 	if (dst) {
@@ -274,11 +285,8 @@ void dst_release(struct dst_entry *dst)
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		WARN_ON(newrefcnt < 0);
-		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) {
-			dst = dst_destroy(dst);
-			if (dst)
-				__dst_free(dst);
-		}
+		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
 EXPORT_SYMBOL(dst_release);
@@ -361,7 +369,8 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 		return;
 
 	if (!unregister) {
-		dst->input = dst->output = dst_discard;
+		dst->input = dst_discard;
+		dst->output = dst_discard_sk;
 	} else {
 		dst->dev = dev_net(dst->dev)->loopback_dev;
 		dev_hold(dst->dev);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 30071dec287..17cb912793f 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -97,6 +97,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_RXFCS_BIT] =            "rx-fcs",
 	[NETIF_F_RXALL_BIT] =            "rx-all",
 	[NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload",
+	[NETIF_F_BUSY_POLL_BIT] =        "busy-poll",
 };
 
 static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
@@ -556,6 +557,23 @@ err_out:
 	return ret;
 }
 
+static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr,
+					struct ethtool_rxnfc *rx_rings,
+					u32 size)
+{
+	int i;
+
+	if (copy_from_user(indir, useraddr, size * sizeof(indir[0])))
+		return -EFAULT;
+
+	/* Validate ring indices */
+	for (i = 0; i < size; i++)
+		if (indir[i] >= rx_rings->data)
+			return -EINVAL;
+
+	return 0;
+}
+
 static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
@@ -564,7 +582,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 	int ret;
 
 	if (!dev->ethtool_ops->get_rxfh_indir_size ||
-	    !dev->ethtool_ops->get_rxfh_indir)
+	    !dev->ethtool_ops->get_rxfh)
 		return -EOPNOTSUPP;
 	dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
 	if (dev_size == 0)
@@ -590,7 +608,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 	if (!indir)
 		return -ENOMEM;
 
-	ret = dev->ethtool_ops->get_rxfh_indir(dev, indir);
+	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL);
 	if (ret)
 		goto out;
 
@@ -612,8 +630,9 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 	u32 *indir;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	int ret;
+	u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]);
 
-	if (!ops->get_rxfh_indir_size || !ops->set_rxfh_indir ||
+	if (!ops->get_rxfh_indir_size || !ops->set_rxfh ||
 	    !ops->get_rxnfc)
 		return -EOPNOTSUPP;
 
@@ -642,28 +661,184 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 		for (i = 0; i < dev_size; i++)
 			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
 	} else {
-		if (copy_from_user(indir,
-				  useraddr +
-				  offsetof(struct ethtool_rxfh_indir,
-					   ring_index[0]),
-				  dev_size * sizeof(indir[0]))) {
+		ret = ethtool_copy_validate_indir(indir,
+						  useraddr + ringidx_offset,
+						  &rx_rings,
+						  dev_size);
+		if (ret)
+			goto out;
+	}
+
+	ret = ops->set_rxfh(dev, indir, NULL);
+
+out:
+	kfree(indir);
+	return ret;
+}
+
+static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
+					       void __user *useraddr)
+{
+	int ret;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	u32 user_indir_size, user_key_size;
+	u32 dev_indir_size = 0, dev_key_size = 0;
+	struct ethtool_rxfh rxfh;
+	u32 total_size;
+	u32 indir_bytes;
+	u32 *indir = NULL;
+	u8 *hkey = NULL;
+	u8 *rss_config;
+
+	if (!(dev->ethtool_ops->get_rxfh_indir_size ||
+	      dev->ethtool_ops->get_rxfh_key_size) ||
+	      !dev->ethtool_ops->get_rxfh)
+		return -EOPNOTSUPP;
+
+	if (ops->get_rxfh_indir_size)
+		dev_indir_size = ops->get_rxfh_indir_size(dev);
+	if (ops->get_rxfh_key_size)
+		dev_key_size = ops->get_rxfh_key_size(dev);
+
+	if ((dev_key_size + dev_indir_size) == 0)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
+		return -EFAULT;
+	user_indir_size = rxfh.indir_size;
+	user_key_size = rxfh.key_size;
+
+	/* Check that reserved fields are 0 for now */
+	if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
+		return -EINVAL;
+
+	rxfh.indir_size = dev_indir_size;
+	rxfh.key_size = dev_key_size;
+	if (copy_to_user(useraddr, &rxfh, sizeof(rxfh)))
+		return -EFAULT;
+
+	/* If the user buffer size is 0, this is just a query for the
+	 * device table size and key size.  Otherwise, if the User size is
+	 * not equal to device table size or key size it's an error.
+	 */
+	if (!user_indir_size && !user_key_size)
+		return 0;
+
+	if ((user_indir_size && (user_indir_size != dev_indir_size)) ||
+	    (user_key_size && (user_key_size != dev_key_size)))
+		return -EINVAL;
+
+	indir_bytes = user_indir_size * sizeof(indir[0]);
+	total_size = indir_bytes + user_key_size;
+	rss_config = kzalloc(total_size, GFP_USER);
+	if (!rss_config)
+		return -ENOMEM;
+
+	if (user_indir_size)
+		indir = (u32 *)rss_config;
+
+	if (user_key_size)
+		hkey = rss_config + indir_bytes;
+
+	ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey);
+	if (!ret) {
+		if (copy_to_user(useraddr +
+				 offsetof(struct ethtool_rxfh, rss_config[0]),
+				 rss_config, total_size))
 			ret = -EFAULT;
+	}
+
+	kfree(rss_config);
+
+	return ret;
+}
+
+static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
+					       void __user *useraddr)
+{
+	int ret;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxnfc rx_rings;
+	struct ethtool_rxfh rxfh;
+	u32 dev_indir_size = 0, dev_key_size = 0, i;
+	u32 *indir = NULL, indir_bytes = 0;
+	u8 *hkey = NULL;
+	u8 *rss_config;
+	u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
+
+	if (!(ops->get_rxfh_indir_size || ops->get_rxfh_key_size) ||
+	    !ops->get_rxnfc || !ops->set_rxfh)
+		return -EOPNOTSUPP;
+
+	if (ops->get_rxfh_indir_size)
+		dev_indir_size = ops->get_rxfh_indir_size(dev);
+	if (ops->get_rxfh_key_size)
+		dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev);
+	if ((dev_key_size + dev_indir_size) == 0)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
+		return -EFAULT;
+
+	/* Check that reserved fields are 0 for now */
+	if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
+		return -EINVAL;
+
+	/* If either indir or hash key is valid, proceed further.
+	 * It is not valid to request that both be unchanged.
+	 */
+	if ((rxfh.indir_size &&
+	     rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
+	     rxfh.indir_size != dev_indir_size) ||
+	    (rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
+	    (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
+	     rxfh.key_size == 0))
+		return -EINVAL;
+
+	if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
+		indir_bytes = dev_indir_size * sizeof(indir[0]);
+
+	rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER);
+	if (!rss_config)
+		return -ENOMEM;
+
+	rx_rings.cmd = ETHTOOL_GRXRINGS;
+	ret = ops->get_rxnfc(dev, &rx_rings, NULL);
+	if (ret)
+		goto out;
+
+	/* rxfh.indir_size == 0 means reset the indir table to default.
+	 * rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE means leave it unchanged.
+	 */
+	if (rxfh.indir_size &&
+	    rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) {
+		indir = (u32 *)rss_config;
+		ret = ethtool_copy_validate_indir(indir,
+						  useraddr + rss_cfg_offset,
+						  &rx_rings,
+						  rxfh.indir_size);
+		if (ret)
 			goto out;
-		}
+	} else if (rxfh.indir_size == 0) {
+		indir = (u32 *)rss_config;
+		for (i = 0; i < dev_indir_size; i++)
+			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
+	}
 
-		/* Validate ring indices */
-		for (i = 0; i < dev_size; i++) {
-			if (indir[i] >= rx_rings.data) {
-				ret = -EINVAL;
-				goto out;
-			}
+	if (rxfh.key_size) {
+		hkey = rss_config + indir_bytes;
+		if (copy_from_user(hkey,
+				   useraddr + rss_cfg_offset + indir_bytes,
+				   rxfh.key_size)) {
+			ret = -EFAULT;
+			goto out;
 		}
 	}
 
-	ret = ops->set_rxfh_indir(dev, indir);
+	ret = ops->set_rxfh(dev, indir, hkey);
 
 out:
-	kfree(indir);
+	kfree(rss_config);
 	return ret;
 }
 
@@ -1490,6 +1665,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_GRXCLSRULE:
 	case ETHTOOL_GRXCLSRLALL:
 	case ETHTOOL_GRXFHINDIR:
+	case ETHTOOL_GRSSH:
 	case ETHTOOL_GFEATURES:
 	case ETHTOOL_GCHANNELS:
 	case ETHTOOL_GET_TS_INFO:
@@ -1627,6 +1803,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_SRXFHINDIR:
 		rc = ethtool_set_rxfh_indir(dev, useraddr);
 		break;
+	case ETHTOOL_GRSSH:
+		rc = ethtool_get_rxfh(dev, useraddr);
+		break;
+	case ETHTOOL_SRSSH:
+		rc = ethtool_set_rxfh(dev, useraddr);
+		break;
 	case ETHTOOL_GFEATURES:
 		rc = ethtool_get_features(dev, useraddr);
 		break;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index f409e0bd35c..185c341fafb 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -745,6 +745,13 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event,
 			attach_rules(&ops->rules_list, dev);
 		break;
 
+	case NETDEV_CHANGENAME:
+		list_for_each_entry(ops, &net->rules_ops, list) {
+			detach_rules(&ops->rules_list, dev);
+			attach_rules(&ops->rules_list, dev);
+		}
+		break;
+
 	case NETDEV_UNREGISTER:
 		list_for_each_entry(ops, &net->rules_ops, list)
 			detach_rules(&ops->rules_list, dev);
diff --git a/net/core/filter.c b/net/core/filter.c
index 01b780856db..1dbf6462f76 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1,11 +1,16 @@
 /*
  * Linux Socket Filter - Kernel level socket filtering
  *
- * Author:
- *     Jay Schulist <jschlst@samba.org>
+ * Based on the design of the Berkeley Packet Filter. The new
+ * internal format has been designed by PLUMgrid:
  *
- * Based on the design of:
- *     - The Berkeley Packet Filter
+ *	Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
+ *
+ * Authors:
+ *
+ *	Jay Schulist <jschlst@samba.org>
+ *	Alexei Starovoitov <ast@plumgrid.com>
+ *	Daniel Borkmann <dborkman@redhat.com>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -36,11 +41,31 @@
 #include <asm/uaccess.h>
 #include <asm/unaligned.h>
 #include <linux/filter.h>
-#include <linux/reciprocal_div.h>
 #include <linux/ratelimit.h>
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
 
+/* Registers */
+#define BPF_R0	regs[BPF_REG_0]
+#define BPF_R1	regs[BPF_REG_1]
+#define BPF_R2	regs[BPF_REG_2]
+#define BPF_R3	regs[BPF_REG_3]
+#define BPF_R4	regs[BPF_REG_4]
+#define BPF_R5	regs[BPF_REG_5]
+#define BPF_R6	regs[BPF_REG_6]
+#define BPF_R7	regs[BPF_REG_7]
+#define BPF_R8	regs[BPF_REG_8]
+#define BPF_R9	regs[BPF_REG_9]
+#define BPF_R10	regs[BPF_REG_10]
+
+/* Named registers */
+#define DST	regs[insn->dst_reg]
+#define SRC	regs[insn->src_reg]
+#define FP	regs[BPF_REG_FP]
+#define ARG1	regs[BPF_REG_ARG1]
+#define CTX	regs[BPF_REG_CTX]
+#define IMM	insn->imm
+
 /* No hurry in this branch
  *
  * Exported for the bpf jit load helper.
@@ -53,9 +78,9 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
 		ptr = skb_network_header(skb) + k - SKF_NET_OFF;
 	else if (k >= SKF_LL_OFF)
 		ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
-
 	if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
 		return ptr;
+
 	return NULL;
 }
 
@@ -64,6 +89,7 @@ static inline void *load_pointer(const struct sk_buff *skb, int k,
 {
 	if (k >= 0)
 		return skb_header_pointer(skb, k, size, buffer);
+
 	return bpf_internal_load_pointer_neg_helper(skb, k, size);
 }
 
@@ -109,304 +135,960 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sk_filter);
 
+/* Base function for offset calculation. Needs to go into .text section,
+ * therefore keeping it non-static as well; will also be used by JITs
+ * anyway later on, so do not let the compiler omit it.
+ */
+noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	return 0;
+}
+
 /**
- *	sk_run_filter - run a filter on a socket
- *	@skb: buffer to run the filter on
- *	@fentry: filter to apply
+ *	__sk_run_filter - run a filter on a given context
+ *	@ctx: buffer to run the filter on
+ *	@insn: filter to apply
  *
- * Decode and apply filter instructions to the skb->data.
- * Return length to keep, 0 for none. @skb is the data we are
- * filtering, @filter is the array of filter instructions.
- * Because all jumps are guaranteed to be before last instruction,
- * and last instruction guaranteed to be a RET, we dont need to check
- * flen. (We used to pass to this function the length of filter)
+ * Decode and apply filter instructions to the skb->data. Return length to
+ * keep, 0 for none. @ctx is the data we are operating on, @insn is the
+ * array of filter instructions.
  */
-unsigned int sk_run_filter(const struct sk_buff *skb,
-			   const struct sock_filter *fentry)
+static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
 {
+	u64 stack[MAX_BPF_STACK / sizeof(u64)];
+	u64 regs[MAX_BPF_REG], tmp;
+	static const void *jumptable[256] = {
+		[0 ... 255] = &&default_label,
+		/* Now overwrite non-defaults ... */
+		/* 32 bit ALU operations */
+		[BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X,
+		[BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K,
+		[BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X,
+		[BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K,
+		[BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X,
+		[BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K,
+		[BPF_ALU | BPF_OR | BPF_X]  = &&ALU_OR_X,
+		[BPF_ALU | BPF_OR | BPF_K]  = &&ALU_OR_K,
+		[BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X,
+		[BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K,
+		[BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X,
+		[BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K,
+		[BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X,
+		[BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K,
+		[BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X,
+		[BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K,
+		[BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X,
+		[BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K,
+		[BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X,
+		[BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K,
+		[BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X,
+		[BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K,
+		[BPF_ALU | BPF_NEG] = &&ALU_NEG,
+		[BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE,
+		[BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,
+		/* 64 bit ALU operations */
+		[BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X,
+		[BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K,
+		[BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X,
+		[BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K,
+		[BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X,
+		[BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K,
+		[BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X,
+		[BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K,
+		[BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X,
+		[BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K,
+		[BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X,
+		[BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K,
+		[BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X,
+		[BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K,
+		[BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X,
+		[BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K,
+		[BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X,
+		[BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K,
+		[BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X,
+		[BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K,
+		[BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X,
+		[BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K,
+		[BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X,
+		[BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K,
+		[BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
+		/* Call instruction */
+		[BPF_JMP | BPF_CALL] = &&JMP_CALL,
+		/* Jumps */
+		[BPF_JMP | BPF_JA] = &&JMP_JA,
+		[BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X,
+		[BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K,
+		[BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X,
+		[BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K,
+		[BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X,
+		[BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K,
+		[BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X,
+		[BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K,
+		[BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X,
+		[BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K,
+		[BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X,
+		[BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K,
+		[BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X,
+		[BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K,
+		/* Program return */
+		[BPF_JMP | BPF_EXIT] = &&JMP_EXIT,
+		/* Store instructions */
+		[BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B,
+		[BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H,
+		[BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W,
+		[BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW,
+		[BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W,
+		[BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW,
+		[BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B,
+		[BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H,
+		[BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W,
+		[BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW,
+		/* Load instructions */
+		[BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B,
+		[BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H,
+		[BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W,
+		[BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW,
+		[BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W,
+		[BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H,
+		[BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B,
+		[BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W,
+		[BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H,
+		[BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
+	};
 	void *ptr;
-	u32 A = 0;			/* Accumulator */
-	u32 X = 0;			/* Index Register */
-	u32 mem[BPF_MEMWORDS];		/* Scratch Memory Store */
-	u32 tmp;
-	int k;
-
-	/*
-	 * Process array of filter instructions.
-	 */
-	for (;; fentry++) {
-#if defined(CONFIG_X86_32)
-#define	K (fentry->k)
-#else
-		const u32 K = fentry->k;
-#endif
-
-		switch (fentry->code) {
-		case BPF_S_ALU_ADD_X:
-			A += X;
-			continue;
-		case BPF_S_ALU_ADD_K:
-			A += K;
-			continue;
-		case BPF_S_ALU_SUB_X:
-			A -= X;
-			continue;
-		case BPF_S_ALU_SUB_K:
-			A -= K;
-			continue;
-		case BPF_S_ALU_MUL_X:
-			A *= X;
-			continue;
-		case BPF_S_ALU_MUL_K:
-			A *= K;
-			continue;
-		case BPF_S_ALU_DIV_X:
-			if (X == 0)
-				return 0;
-			A /= X;
-			continue;
-		case BPF_S_ALU_DIV_K:
-			A = reciprocal_divide(A, K);
-			continue;
-		case BPF_S_ALU_MOD_X:
-			if (X == 0)
-				return 0;
-			A %= X;
-			continue;
-		case BPF_S_ALU_MOD_K:
-			A %= K;
-			continue;
-		case BPF_S_ALU_AND_X:
-			A &= X;
-			continue;
-		case BPF_S_ALU_AND_K:
-			A &= K;
-			continue;
-		case BPF_S_ALU_OR_X:
-			A |= X;
-			continue;
-		case BPF_S_ALU_OR_K:
-			A |= K;
-			continue;
-		case BPF_S_ANC_ALU_XOR_X:
-		case BPF_S_ALU_XOR_X:
-			A ^= X;
-			continue;
-		case BPF_S_ALU_XOR_K:
-			A ^= K;
-			continue;
-		case BPF_S_ALU_LSH_X:
-			A <<= X;
-			continue;
-		case BPF_S_ALU_LSH_K:
-			A <<= K;
-			continue;
-		case BPF_S_ALU_RSH_X:
-			A >>= X;
-			continue;
-		case BPF_S_ALU_RSH_K:
-			A >>= K;
-			continue;
-		case BPF_S_ALU_NEG:
-			A = -A;
-			continue;
-		case BPF_S_JMP_JA:
-			fentry += K;
-			continue;
-		case BPF_S_JMP_JGT_K:
-			fentry += (A > K) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JGE_K:
-			fentry += (A >= K) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JEQ_K:
-			fentry += (A == K) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JSET_K:
-			fentry += (A & K) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JGT_X:
-			fentry += (A > X) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JGE_X:
-			fentry += (A >= X) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JEQ_X:
-			fentry += (A == X) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JSET_X:
-			fentry += (A & X) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_LD_W_ABS:
-			k = K;
-load_w:
-			ptr = load_pointer(skb, k, 4, &tmp);
-			if (ptr != NULL) {
-				A = get_unaligned_be32(ptr);
-				continue;
-			}
+	int off;
+
+#define CONT	 ({ insn++; goto select_insn; })
+#define CONT_JMP ({ insn++; goto select_insn; })
+
+	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
+	ARG1 = (u64) (unsigned long) ctx;
+
+	/* Registers used in classic BPF programs need to be reset first. */
+	regs[BPF_REG_A] = 0;
+	regs[BPF_REG_X] = 0;
+
+select_insn:
+	goto *jumptable[insn->code];
+
+	/* ALU */
+#define ALU(OPCODE, OP)			\
+	ALU64_##OPCODE##_X:		\
+		DST = DST OP SRC;	\
+		CONT;			\
+	ALU_##OPCODE##_X:		\
+		DST = (u32) DST OP (u32) SRC;	\
+		CONT;			\
+	ALU64_##OPCODE##_K:		\
+		DST = DST OP IMM;		\
+		CONT;			\
+	ALU_##OPCODE##_K:		\
+		DST = (u32) DST OP (u32) IMM;	\
+		CONT;
+
+	ALU(ADD,  +)
+	ALU(SUB,  -)
+	ALU(AND,  &)
+	ALU(OR,   |)
+	ALU(LSH, <<)
+	ALU(RSH, >>)
+	ALU(XOR,  ^)
+	ALU(MUL,  *)
+#undef ALU
+	ALU_NEG:
+		DST = (u32) -DST;
+		CONT;
+	ALU64_NEG:
+		DST = -DST;
+		CONT;
+	ALU_MOV_X:
+		DST = (u32) SRC;
+		CONT;
+	ALU_MOV_K:
+		DST = (u32) IMM;
+		CONT;
+	ALU64_MOV_X:
+		DST = SRC;
+		CONT;
+	ALU64_MOV_K:
+		DST = IMM;
+		CONT;
+	ALU64_ARSH_X:
+		(*(s64 *) &DST) >>= SRC;
+		CONT;
+	ALU64_ARSH_K:
+		(*(s64 *) &DST) >>= IMM;
+		CONT;
+	ALU64_MOD_X:
+		if (unlikely(SRC == 0))
 			return 0;
-		case BPF_S_LD_H_ABS:
-			k = K;
-load_h:
-			ptr = load_pointer(skb, k, 2, &tmp);
-			if (ptr != NULL) {
-				A = get_unaligned_be16(ptr);
-				continue;
-			}
+		tmp = DST;
+		DST = do_div(tmp, SRC);
+		CONT;
+	ALU_MOD_X:
+		if (unlikely(SRC == 0))
 			return 0;
-		case BPF_S_LD_B_ABS:
-			k = K;
-load_b:
-			ptr = load_pointer(skb, k, 1, &tmp);
-			if (ptr != NULL) {
-				A = *(u8 *)ptr;
-				continue;
-			}
+		tmp = (u32) DST;
+		DST = do_div(tmp, (u32) SRC);
+		CONT;
+	ALU64_MOD_K:
+		tmp = DST;
+		DST = do_div(tmp, IMM);
+		CONT;
+	ALU_MOD_K:
+		tmp = (u32) DST;
+		DST = do_div(tmp, (u32) IMM);
+		CONT;
+	ALU64_DIV_X:
+		if (unlikely(SRC == 0))
 			return 0;
-		case BPF_S_LD_W_LEN:
-			A = skb->len;
-			continue;
-		case BPF_S_LDX_W_LEN:
-			X = skb->len;
-			continue;
-		case BPF_S_LD_W_IND:
-			k = X + K;
-			goto load_w;
-		case BPF_S_LD_H_IND:
-			k = X + K;
-			goto load_h;
-		case BPF_S_LD_B_IND:
-			k = X + K;
-			goto load_b;
-		case BPF_S_LDX_B_MSH:
-			ptr = load_pointer(skb, K, 1, &tmp);
-			if (ptr != NULL) {
-				X = (*(u8 *)ptr & 0xf) << 2;
-				continue;
-			}
+		do_div(DST, SRC);
+		CONT;
+	ALU_DIV_X:
+		if (unlikely(SRC == 0))
 			return 0;
-		case BPF_S_LD_IMM:
-			A = K;
-			continue;
-		case BPF_S_LDX_IMM:
-			X = K;
-			continue;
-		case BPF_S_LD_MEM:
-			A = mem[K];
-			continue;
-		case BPF_S_LDX_MEM:
-			X = mem[K];
-			continue;
-		case BPF_S_MISC_TAX:
-			X = A;
-			continue;
-		case BPF_S_MISC_TXA:
-			A = X;
-			continue;
-		case BPF_S_RET_K:
-			return K;
-		case BPF_S_RET_A:
-			return A;
-		case BPF_S_ST:
-			mem[K] = A;
-			continue;
-		case BPF_S_STX:
-			mem[K] = X;
-			continue;
-		case BPF_S_ANC_PROTOCOL:
-			A = ntohs(skb->protocol);
-			continue;
-		case BPF_S_ANC_PKTTYPE:
-			A = skb->pkt_type;
-			continue;
-		case BPF_S_ANC_IFINDEX:
-			if (!skb->dev)
-				return 0;
-			A = skb->dev->ifindex;
-			continue;
-		case BPF_S_ANC_MARK:
-			A = skb->mark;
-			continue;
-		case BPF_S_ANC_QUEUE:
-			A = skb->queue_mapping;
-			continue;
-		case BPF_S_ANC_HATYPE:
-			if (!skb->dev)
-				return 0;
-			A = skb->dev->type;
-			continue;
-		case BPF_S_ANC_RXHASH:
-			A = skb->rxhash;
-			continue;
-		case BPF_S_ANC_CPU:
-			A = raw_smp_processor_id();
-			continue;
-		case BPF_S_ANC_VLAN_TAG:
-			A = vlan_tx_tag_get(skb);
-			continue;
-		case BPF_S_ANC_VLAN_TAG_PRESENT:
-			A = !!vlan_tx_tag_present(skb);
-			continue;
-		case BPF_S_ANC_PAY_OFFSET:
-			A = __skb_get_poff(skb);
-			continue;
-		case BPF_S_ANC_NLATTR: {
-			struct nlattr *nla;
-
-			if (skb_is_nonlinear(skb))
-				return 0;
-			if (A > skb->len - sizeof(struct nlattr))
-				return 0;
-
-			nla = nla_find((struct nlattr *)&skb->data[A],
-				       skb->len - A, X);
-			if (nla)
-				A = (void *)nla - (void *)skb->data;
-			else
-				A = 0;
-			continue;
+		tmp = (u32) DST;
+		do_div(tmp, (u32) SRC);
+		DST = (u32) tmp;
+		CONT;
+	ALU64_DIV_K:
+		do_div(DST, IMM);
+		CONT;
+	ALU_DIV_K:
+		tmp = (u32) DST;
+		do_div(tmp, (u32) IMM);
+		DST = (u32) tmp;
+		CONT;
+	ALU_END_TO_BE:
+		switch (IMM) {
+		case 16:
+			DST = (__force u16) cpu_to_be16(DST);
+			break;
+		case 32:
+			DST = (__force u32) cpu_to_be32(DST);
+			break;
+		case 64:
+			DST = (__force u64) cpu_to_be64(DST);
+			break;
+		}
+		CONT;
+	ALU_END_TO_LE:
+		switch (IMM) {
+		case 16:
+			DST = (__force u16) cpu_to_le16(DST);
+			break;
+		case 32:
+			DST = (__force u32) cpu_to_le32(DST);
+			break;
+		case 64:
+			DST = (__force u64) cpu_to_le64(DST);
+			break;
+		}
+		CONT;
+
+	/* CALL */
+	JMP_CALL:
+		/* Function call scratches BPF_R1-BPF_R5 registers,
+		 * preserves BPF_R6-BPF_R9, and stores return value
+		 * into BPF_R0.
+		 */
+		BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3,
+						       BPF_R4, BPF_R5);
+		CONT;
+
+	/* JMP */
+	JMP_JA:
+		insn += insn->off;
+		CONT;
+	JMP_JEQ_X:
+		if (DST == SRC) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JEQ_K:
+		if (DST == IMM) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JNE_X:
+		if (DST != SRC) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JNE_K:
+		if (DST != IMM) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JGT_X:
+		if (DST > SRC) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JGT_K:
+		if (DST > IMM) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JGE_X:
+		if (DST >= SRC) {
+			insn += insn->off;
+			CONT_JMP;
 		}
-		case BPF_S_ANC_NLATTR_NEST: {
-			struct nlattr *nla;
-
-			if (skb_is_nonlinear(skb))
-				return 0;
-			if (A > skb->len - sizeof(struct nlattr))
-				return 0;
-
-			nla = (struct nlattr *)&skb->data[A];
-			if (nla->nla_len > A - skb->len)
-				return 0;
-
-			nla = nla_find_nested(nla, X);
-			if (nla)
-				A = (void *)nla - (void *)skb->data;
-			else
-				A = 0;
-			continue;
+		CONT;
+	JMP_JGE_K:
+		if (DST >= IMM) {
+			insn += insn->off;
+			CONT_JMP;
 		}
-#ifdef CONFIG_SECCOMP_FILTER
-		case BPF_S_ANC_SECCOMP_LD_W:
-			A = seccomp_bpf_load(fentry->k);
-			continue;
+		CONT;
+	JMP_JSGT_X:
+		if (((s64) DST) > ((s64) SRC)) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JSGT_K:
+		if (((s64) DST) > ((s64) IMM)) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JSGE_X:
+		if (((s64) DST) >= ((s64) SRC)) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JSGE_K:
+		if (((s64) DST) >= ((s64) IMM)) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JSET_X:
+		if (DST & SRC) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_JSET_K:
+		if (DST & IMM) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	JMP_EXIT:
+		return BPF_R0;
+
+	/* STX and ST and LDX*/
+#define LDST(SIZEOP, SIZE)						\
+	STX_MEM_##SIZEOP:						\
+		*(SIZE *)(unsigned long) (DST + insn->off) = SRC;	\
+		CONT;							\
+	ST_MEM_##SIZEOP:						\
+		*(SIZE *)(unsigned long) (DST + insn->off) = IMM;	\
+		CONT;							\
+	LDX_MEM_##SIZEOP:						\
+		DST = *(SIZE *)(unsigned long) (SRC + insn->off);	\
+		CONT;
+
+	LDST(B,   u8)
+	LDST(H,  u16)
+	LDST(W,  u32)
+	LDST(DW, u64)
+#undef LDST
+	STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
+		atomic_add((u32) SRC, (atomic_t *)(unsigned long)
+			   (DST + insn->off));
+		CONT;
+	STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */
+		atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
+			     (DST + insn->off));
+		CONT;
+	LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
+		off = IMM;
+load_word:
+		/* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are
+		 * only appearing in the programs where ctx ==
+		 * skb. All programs keep 'ctx' in regs[BPF_REG_CTX]
+		 * == BPF_R6, sk_convert_filter() saves it in BPF_R6,
+		 * internal BPF verifier will check that BPF_R6 ==
+		 * ctx.
+		 *
+		 * BPF_ABS and BPF_IND are wrappers of function calls,
+		 * so they scratch BPF_R1-BPF_R5 registers, preserve
+		 * BPF_R6-BPF_R9, and store return value into BPF_R0.
+		 *
+		 * Implicit input:
+		 *   ctx == skb == BPF_R6 == CTX
+		 *
+		 * Explicit input:
+		 *   SRC == any register
+		 *   IMM == 32-bit immediate
+		 *
+		 * Output:
+		 *   BPF_R0 - 8/16/32-bit skb data converted to cpu endianness
+		 */
+
+		ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp);
+		if (likely(ptr != NULL)) {
+			BPF_R0 = get_unaligned_be32(ptr);
+			CONT;
+		}
+
+		return 0;
+	LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */
+		off = IMM;
+load_half:
+		ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp);
+		if (likely(ptr != NULL)) {
+			BPF_R0 = get_unaligned_be16(ptr);
+			CONT;
+		}
+
+		return 0;
+	LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */
+		off = IMM;
+load_byte:
+		ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp);
+		if (likely(ptr != NULL)) {
+			BPF_R0 = *(u8 *)ptr;
+			CONT;
+		}
+
+		return 0;
+	LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */
+		off = IMM + SRC;
+		goto load_word;
+	LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */
+		off = IMM + SRC;
+		goto load_half;
+	LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */
+		off = IMM + SRC;
+		goto load_byte;
+
+	default_label:
+		/* If we ever reach this, we have a bug somewhere. */
+		WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
+		return 0;
+}
+
+/* Helper to find the offset of pkt_type in sk_buff structure. We want
+ * to make sure its still a 3bit field starting at a byte boundary;
+ * taken from arch/x86/net/bpf_jit_comp.c.
+ */
+#ifdef __BIG_ENDIAN_BITFIELD
+#define PKT_TYPE_MAX	(7 << 5)
+#else
+#define PKT_TYPE_MAX	7
+#endif
+static unsigned int pkt_type_offset(void)
+{
+	struct sk_buff skb_probe = { .pkt_type = ~0, };
+	u8 *ct = (u8 *) &skb_probe;
+	unsigned int off;
+
+	for (off = 0; off < sizeof(struct sk_buff); off++) {
+		if (ct[off] == PKT_TYPE_MAX)
+			return off;
+	}
+
+	pr_err_once("Please fix %s, as pkt_type couldn't be found!\n", __func__);
+	return -1;
+}
+
+static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
+{
+	return __skb_get_poff((struct sk_buff *)(unsigned long) ctx);
+}
+
+static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
+{
+	struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx;
+	struct nlattr *nla;
+
+	if (skb_is_nonlinear(skb))
+		return 0;
+
+	if (skb->len < sizeof(struct nlattr))
+		return 0;
+
+	if (a > skb->len - sizeof(struct nlattr))
+		return 0;
+
+	nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x);
+	if (nla)
+		return (void *) nla - (void *) skb->data;
+
+	return 0;
+}
+
+static u64 __skb_get_nlattr_nest(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
+{
+	struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx;
+	struct nlattr *nla;
+
+	if (skb_is_nonlinear(skb))
+		return 0;
+
+	if (skb->len < sizeof(struct nlattr))
+		return 0;
+
+	if (a > skb->len - sizeof(struct nlattr))
+		return 0;
+
+	nla = (struct nlattr *) &skb->data[a];
+	if (nla->nla_len > skb->len - a)
+		return 0;
+
+	nla = nla_find_nested(nla, x);
+	if (nla)
+		return (void *) nla - (void *) skb->data;
+
+	return 0;
+}
+
+static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
+{
+	return raw_smp_processor_id();
+}
+
+/* note that this only generates 32-bit random numbers */
+static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
+{
+	return prandom_u32();
+}
+
+static bool convert_bpf_extensions(struct sock_filter *fp,
+				   struct sock_filter_int **insnp)
+{
+	struct sock_filter_int *insn = *insnp;
+
+	switch (fp->k) {
+	case SKF_AD_OFF + SKF_AD_PROTOCOL:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
+
+		/* A = *(u16 *) (CTX + offsetof(protocol)) */
+		*insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
+				      offsetof(struct sk_buff, protocol));
+		/* A = ntohs(A) [emitting a nop or swap16] */
+		*insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16);
+		break;
+
+	case SKF_AD_OFF + SKF_AD_PKTTYPE:
+		*insn = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX,
+				    pkt_type_offset());
+		if (insn->off < 0)
+			return false;
+		insn++;
+		*insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX);
+#ifdef __BIG_ENDIAN_BITFIELD
+		insn++;
+                *insn = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 5);
 #endif
+		break;
+
+	case SKF_AD_OFF + SKF_AD_IFINDEX:
+	case SKF_AD_OFF + SKF_AD_HATYPE:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
+		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2);
+		BUILD_BUG_ON(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)) < 0);
+
+		*insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)),
+				      BPF_REG_TMP, BPF_REG_CTX,
+				      offsetof(struct sk_buff, dev));
+		/* if (tmp != 0) goto pc + 1 */
+		*insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1);
+		*insn++ = BPF_EXIT_INSN();
+		if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX)
+			*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP,
+					    offsetof(struct net_device, ifindex));
+		else
+			*insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP,
+					    offsetof(struct net_device, type));
+		break;
+
+	case SKF_AD_OFF + SKF_AD_MARK:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+
+		*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX,
+				    offsetof(struct sk_buff, mark));
+		break;
+
+	case SKF_AD_OFF + SKF_AD_RXHASH:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+
+		*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX,
+				    offsetof(struct sk_buff, hash));
+		break;
+
+	case SKF_AD_OFF + SKF_AD_QUEUE:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
+
+		*insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
+				    offsetof(struct sk_buff, queue_mapping));
+		break;
+
+	case SKF_AD_OFF + SKF_AD_VLAN_TAG:
+	case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+		BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+
+		/* A = *(u16 *) (CTX + offsetof(vlan_tci)) */
+		*insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
+				      offsetof(struct sk_buff, vlan_tci));
+		if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) {
+			*insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A,
+					      ~VLAN_TAG_PRESENT);
+		} else {
+			/* A >>= 12 */
+			*insn++ = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12);
+			/* A &= 1 */
+			*insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 1);
+		}
+		break;
+
+	case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
+	case SKF_AD_OFF + SKF_AD_NLATTR:
+	case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
+	case SKF_AD_OFF + SKF_AD_CPU:
+	case SKF_AD_OFF + SKF_AD_RANDOM:
+		/* arg1 = CTX */
+		*insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX);
+		/* arg2 = A */
+		*insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A);
+		/* arg3 = X */
+		*insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X);
+		/* Emit call(arg1=CTX, arg2=A, arg3=X) */
+		switch (fp->k) {
+		case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
+			*insn = BPF_EMIT_CALL(__skb_get_pay_offset);
+			break;
+		case SKF_AD_OFF + SKF_AD_NLATTR:
+			*insn = BPF_EMIT_CALL(__skb_get_nlattr);
+			break;
+		case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
+			*insn = BPF_EMIT_CALL(__skb_get_nlattr_nest);
+			break;
+		case SKF_AD_OFF + SKF_AD_CPU:
+			*insn = BPF_EMIT_CALL(__get_raw_cpu_id);
+			break;
+		case SKF_AD_OFF + SKF_AD_RANDOM:
+			*insn = BPF_EMIT_CALL(__get_random_u32);
+			break;
+		}
+		break;
+
+	case SKF_AD_OFF + SKF_AD_ALU_XOR_X:
+		/* A ^= X */
+		*insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X);
+		break;
+
+	default:
+		/* This is just a dummy call to avoid letting the compiler
+		 * evict __bpf_call_base() as an optimization. Placed here
+		 * where no-one bothers.
+		 */
+		BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0);
+		return false;
+	}
+
+	*insnp = insn;
+	return true;
+}
+
+/**
+ *	sk_convert_filter - convert filter program
+ *	@prog: the user passed filter program
+ *	@len: the length of the user passed filter program
+ *	@new_prog: buffer where converted program will be stored
+ *	@new_len: pointer to store length of converted program
+ *
+ * Remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style.
+ * Conversion workflow:
+ *
+ * 1) First pass for calculating the new program length:
+ *   sk_convert_filter(old_prog, old_len, NULL, &new_len)
+ *
+ * 2) 2nd pass to remap in two passes: 1st pass finds new
+ *    jump offsets, 2nd pass remapping:
+ *   new_prog = kmalloc(sizeof(struct sock_filter_int) * new_len);
+ *   sk_convert_filter(old_prog, old_len, new_prog, &new_len);
+ *
+ * User BPF's register A is mapped to our BPF register 6, user BPF
+ * register X is mapped to BPF register 7; frame pointer is always
+ * register 10; Context 'void *ctx' is stored in register 1, that is,
+ * for socket filters: ctx == 'struct sk_buff *', for seccomp:
+ * ctx == 'struct seccomp_data *'.
+ */
+int sk_convert_filter(struct sock_filter *prog, int len,
+		      struct sock_filter_int *new_prog, int *new_len)
+{
+	int new_flen = 0, pass = 0, target, i;
+	struct sock_filter_int *new_insn;
+	struct sock_filter *fp;
+	int *addrs = NULL;
+	u8 bpf_src;
+
+	BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK);
+	BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
+
+	if (len <= 0 || len > BPF_MAXINSNS)
+		return -EINVAL;
+
+	if (new_prog) {
+		addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL);
+		if (!addrs)
+			return -ENOMEM;
+	}
+
+do_pass:
+	new_insn = new_prog;
+	fp = prog;
+
+	if (new_insn)
+		*new_insn = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1);
+	new_insn++;
+
+	for (i = 0; i < len; fp++, i++) {
+		struct sock_filter_int tmp_insns[6] = { };
+		struct sock_filter_int *insn = tmp_insns;
+
+		if (addrs)
+			addrs[i] = new_insn - new_prog;
+
+		switch (fp->code) {
+		/* All arithmetic insns and skb loads map as-is. */
+		case BPF_ALU | BPF_ADD | BPF_X:
+		case BPF_ALU | BPF_ADD | BPF_K:
+		case BPF_ALU | BPF_SUB | BPF_X:
+		case BPF_ALU | BPF_SUB | BPF_K:
+		case BPF_ALU | BPF_AND | BPF_X:
+		case BPF_ALU | BPF_AND | BPF_K:
+		case BPF_ALU | BPF_OR | BPF_X:
+		case BPF_ALU | BPF_OR | BPF_K:
+		case BPF_ALU | BPF_LSH | BPF_X:
+		case BPF_ALU | BPF_LSH | BPF_K:
+		case BPF_ALU | BPF_RSH | BPF_X:
+		case BPF_ALU | BPF_RSH | BPF_K:
+		case BPF_ALU | BPF_XOR | BPF_X:
+		case BPF_ALU | BPF_XOR | BPF_K:
+		case BPF_ALU | BPF_MUL | BPF_X:
+		case BPF_ALU | BPF_MUL | BPF_K:
+		case BPF_ALU | BPF_DIV | BPF_X:
+		case BPF_ALU | BPF_DIV | BPF_K:
+		case BPF_ALU | BPF_MOD | BPF_X:
+		case BPF_ALU | BPF_MOD | BPF_K:
+		case BPF_ALU | BPF_NEG:
+		case BPF_LD | BPF_ABS | BPF_W:
+		case BPF_LD | BPF_ABS | BPF_H:
+		case BPF_LD | BPF_ABS | BPF_B:
+		case BPF_LD | BPF_IND | BPF_W:
+		case BPF_LD | BPF_IND | BPF_H:
+		case BPF_LD | BPF_IND | BPF_B:
+			/* Check for overloaded BPF extension and
+			 * directly convert it if found, otherwise
+			 * just move on with mapping.
+			 */
+			if (BPF_CLASS(fp->code) == BPF_LD &&
+			    BPF_MODE(fp->code) == BPF_ABS &&
+			    convert_bpf_extensions(fp, &insn))
+				break;
+
+			*insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k);
+			break;
+
+		/* Jump transformation cannot use BPF block macros
+		 * everywhere as offset calculation and target updates
+		 * require a bit more work than the rest, i.e. jump
+		 * opcodes map as-is, but offsets need adjustment.
+		 */
+
+#define BPF_EMIT_JMP							\
+	do {								\
+		if (target >= len || target < 0)			\
+			goto err;					\
+		insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0;	\
+		/* Adjust pc relative offset for 2nd or 3rd insn. */	\
+		insn->off -= insn - tmp_insns;				\
+	} while (0)
+
+		case BPF_JMP | BPF_JA:
+			target = i + fp->k + 1;
+			insn->code = fp->code;
+			BPF_EMIT_JMP;
+			break;
+
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
+			if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) {
+				/* BPF immediates are signed, zero extend
+				 * immediate into tmp register and use it
+				 * in compare insn.
+				 */
+				*insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k);
+
+				insn->dst_reg = BPF_REG_A;
+				insn->src_reg = BPF_REG_TMP;
+				bpf_src = BPF_X;
+			} else {
+				insn->dst_reg = BPF_REG_A;
+				insn->src_reg = BPF_REG_X;
+				insn->imm = fp->k;
+				bpf_src = BPF_SRC(fp->code);
+			}
+
+			/* Common case where 'jump_false' is next insn. */
+			if (fp->jf == 0) {
+				insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
+				target = i + fp->jt + 1;
+				BPF_EMIT_JMP;
+				break;
+			}
+
+			/* Convert JEQ into JNE when 'jump_true' is next insn. */
+			if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) {
+				insn->code = BPF_JMP | BPF_JNE | bpf_src;
+				target = i + fp->jf + 1;
+				BPF_EMIT_JMP;
+				break;
+			}
+
+			/* Other jumps are mapped into two insns: Jxx and JA. */
+			target = i + fp->jt + 1;
+			insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
+			BPF_EMIT_JMP;
+			insn++;
+
+			insn->code = BPF_JMP | BPF_JA;
+			target = i + fp->jf + 1;
+			BPF_EMIT_JMP;
+			break;
+
+		/* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
+		case BPF_LDX | BPF_MSH | BPF_B:
+			/* tmp = A */
+			*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A);
+			/* A = BPF_R0 = *(u8 *) (skb->data + K) */
+			*insn++ = BPF_LD_ABS(BPF_B, fp->k);
+			/* A &= 0xf */
+			*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf);
+			/* A <<= 2 */
+			*insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2);
+			/* X = A */
+			*insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
+			/* A = tmp */
+			*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP);
+			break;
+
+		/* RET_K, RET_A are remaped into 2 insns. */
+		case BPF_RET | BPF_A:
+		case BPF_RET | BPF_K:
+			*insn++ = BPF_MOV32_RAW(BPF_RVAL(fp->code) == BPF_K ?
+						BPF_K : BPF_X, BPF_REG_0,
+						BPF_REG_A, fp->k);
+			*insn = BPF_EXIT_INSN();
+			break;
+
+		/* Store to stack. */
+		case BPF_ST:
+		case BPF_STX:
+			*insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) ==
+					    BPF_ST ? BPF_REG_A : BPF_REG_X,
+					    -(BPF_MEMWORDS - fp->k) * 4);
+			break;
+
+		/* Load from stack. */
+		case BPF_LD | BPF_MEM:
+		case BPF_LDX | BPF_MEM:
+			*insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD  ?
+					    BPF_REG_A : BPF_REG_X, BPF_REG_FP,
+					    -(BPF_MEMWORDS - fp->k) * 4);
+			break;
+
+		/* A = K or X = K */
+		case BPF_LD | BPF_IMM:
+		case BPF_LDX | BPF_IMM:
+			*insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ?
+					      BPF_REG_A : BPF_REG_X, fp->k);
+			break;
+
+		/* X = A */
+		case BPF_MISC | BPF_TAX:
+			*insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
+			break;
+
+		/* A = X */
+		case BPF_MISC | BPF_TXA:
+			*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X);
+			break;
+
+		/* A = skb->len or X = skb->len */
+		case BPF_LD | BPF_W | BPF_LEN:
+		case BPF_LDX | BPF_W | BPF_LEN:
+			*insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ?
+					    BPF_REG_A : BPF_REG_X, BPF_REG_CTX,
+					    offsetof(struct sk_buff, len));
+			break;
+
+		/* Access seccomp_data fields. */
+		case BPF_LDX | BPF_ABS | BPF_W:
+			/* A = *(u32 *) (ctx + K) */
+			*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k);
+			break;
+
+		/* Unkown instruction. */
 		default:
-			WARN_RATELIMIT(1, "Unknown code:%u jt:%u tf:%u k:%u\n",
-				       fentry->code, fentry->jt,
-				       fentry->jf, fentry->k);
-			return 0;
+			goto err;
 		}
+
+		insn++;
+		if (new_prog)
+			memcpy(new_insn, tmp_insns,
+			       sizeof(*insn) * (insn - tmp_insns));
+		new_insn += insn - tmp_insns;
 	}
 
+	if (!new_prog) {
+		/* Only calculating new length. */
+		*new_len = new_insn - new_prog;
+		return 0;
+	}
+
+	pass++;
+	if (new_flen != new_insn - new_prog) {
+		new_flen = new_insn - new_prog;
+		if (pass > 2)
+			goto err;
+		goto do_pass;
+	}
+
+	kfree(addrs);
+	BUG_ON(*new_len != new_flen);
 	return 0;
+err:
+	kfree(addrs);
+	return -EINVAL;
 }
-EXPORT_SYMBOL(sk_run_filter);
 
-/*
- * Security :
+/* Security:
+ *
  * A BPF program is able to use 16 cells of memory to store intermediate
- * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter())
+ * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()).
+ *
  * As we dont want to clear mem[] array for each packet going through
  * sk_run_filter(), we check that filter loaded by user never try to read
  * a cell if not previously written, and we check all branches to be sure
@@ -414,44 +1096,46 @@ EXPORT_SYMBOL(sk_run_filter);
  */
 static int check_load_and_stores(struct sock_filter *filter, int flen)
 {
-	u16 *masks, memvalid = 0; /* one bit per cell, 16 cells */
+	u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */
 	int pc, ret = 0;
 
 	BUILD_BUG_ON(BPF_MEMWORDS > 16);
-	masks = kmalloc(flen * sizeof(*masks), GFP_KERNEL);
+
+	masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL);
 	if (!masks)
 		return -ENOMEM;
+
 	memset(masks, 0xff, flen * sizeof(*masks));
 
 	for (pc = 0; pc < flen; pc++) {
 		memvalid &= masks[pc];
 
 		switch (filter[pc].code) {
-		case BPF_S_ST:
-		case BPF_S_STX:
+		case BPF_ST:
+		case BPF_STX:
 			memvalid |= (1 << filter[pc].k);
 			break;
-		case BPF_S_LD_MEM:
-		case BPF_S_LDX_MEM:
+		case BPF_LD | BPF_MEM:
+		case BPF_LDX | BPF_MEM:
 			if (!(memvalid & (1 << filter[pc].k))) {
 				ret = -EINVAL;
 				goto error;
 			}
 			break;
-		case BPF_S_JMP_JA:
-			/* a jump must set masks on target */
+		case BPF_JMP | BPF_JA:
+			/* A jump must set masks on target */
 			masks[pc + 1 + filter[pc].k] &= memvalid;
 			memvalid = ~0;
 			break;
-		case BPF_S_JMP_JEQ_K:
-		case BPF_S_JMP_JEQ_X:
-		case BPF_S_JMP_JGE_K:
-		case BPF_S_JMP_JGE_X:
-		case BPF_S_JMP_JGT_K:
-		case BPF_S_JMP_JGT_X:
-		case BPF_S_JMP_JSET_X:
-		case BPF_S_JMP_JSET_K:
-			/* a jump must set masks on targets */
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
+			/* A jump must set masks on targets */
 			masks[pc + 1 + filter[pc].jt] &= memvalid;
 			masks[pc + 1 + filter[pc].jf] &= memvalid;
 			memvalid = ~0;
@@ -463,6 +1147,72 @@ error:
 	return ret;
 }
 
+static bool chk_code_allowed(u16 code_to_probe)
+{
+	static const bool codes[] = {
+		/* 32 bit ALU operations */
+		[BPF_ALU | BPF_ADD | BPF_K] = true,
+		[BPF_ALU | BPF_ADD | BPF_X] = true,
+		[BPF_ALU | BPF_SUB | BPF_K] = true,
+		[BPF_ALU | BPF_SUB | BPF_X] = true,
+		[BPF_ALU | BPF_MUL | BPF_K] = true,
+		[BPF_ALU | BPF_MUL | BPF_X] = true,
+		[BPF_ALU | BPF_DIV | BPF_K] = true,
+		[BPF_ALU | BPF_DIV | BPF_X] = true,
+		[BPF_ALU | BPF_MOD | BPF_K] = true,
+		[BPF_ALU | BPF_MOD | BPF_X] = true,
+		[BPF_ALU | BPF_AND | BPF_K] = true,
+		[BPF_ALU | BPF_AND | BPF_X] = true,
+		[BPF_ALU | BPF_OR | BPF_K] = true,
+		[BPF_ALU | BPF_OR | BPF_X] = true,
+		[BPF_ALU | BPF_XOR | BPF_K] = true,
+		[BPF_ALU | BPF_XOR | BPF_X] = true,
+		[BPF_ALU | BPF_LSH | BPF_K] = true,
+		[BPF_ALU | BPF_LSH | BPF_X] = true,
+		[BPF_ALU | BPF_RSH | BPF_K] = true,
+		[BPF_ALU | BPF_RSH | BPF_X] = true,
+		[BPF_ALU | BPF_NEG] = true,
+		/* Load instructions */
+		[BPF_LD | BPF_W | BPF_ABS] = true,
+		[BPF_LD | BPF_H | BPF_ABS] = true,
+		[BPF_LD | BPF_B | BPF_ABS] = true,
+		[BPF_LD | BPF_W | BPF_LEN] = true,
+		[BPF_LD | BPF_W | BPF_IND] = true,
+		[BPF_LD | BPF_H | BPF_IND] = true,
+		[BPF_LD | BPF_B | BPF_IND] = true,
+		[BPF_LD | BPF_IMM] = true,
+		[BPF_LD | BPF_MEM] = true,
+		[BPF_LDX | BPF_W | BPF_LEN] = true,
+		[BPF_LDX | BPF_B | BPF_MSH] = true,
+		[BPF_LDX | BPF_IMM] = true,
+		[BPF_LDX | BPF_MEM] = true,
+		/* Store instructions */
+		[BPF_ST] = true,
+		[BPF_STX] = true,
+		/* Misc instructions */
+		[BPF_MISC | BPF_TAX] = true,
+		[BPF_MISC | BPF_TXA] = true,
+		/* Return instructions */
+		[BPF_RET | BPF_K] = true,
+		[BPF_RET | BPF_A] = true,
+		/* Jump instructions */
+		[BPF_JMP | BPF_JA] = true,
+		[BPF_JMP | BPF_JEQ | BPF_K] = true,
+		[BPF_JMP | BPF_JEQ | BPF_X] = true,
+		[BPF_JMP | BPF_JGE | BPF_K] = true,
+		[BPF_JMP | BPF_JGE | BPF_X] = true,
+		[BPF_JMP | BPF_JGT | BPF_K] = true,
+		[BPF_JMP | BPF_JGT | BPF_X] = true,
+		[BPF_JMP | BPF_JSET | BPF_K] = true,
+		[BPF_JMP | BPF_JSET | BPF_X] = true,
+	};
+
+	if (code_to_probe >= ARRAY_SIZE(codes))
+		return false;
+
+	return codes[code_to_probe];
+}
+
 /**
  *	sk_chk_filter - verify socket filter code
  *	@filter: filter to verify
@@ -479,192 +1229,303 @@ error:
  */
 int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
 {
-	/*
-	 * Valid instructions are initialized to non-0.
-	 * Invalid instructions are initialized to 0.
-	 */
-	static const u8 codes[] = {
-		[BPF_ALU|BPF_ADD|BPF_K]  = BPF_S_ALU_ADD_K,
-		[BPF_ALU|BPF_ADD|BPF_X]  = BPF_S_ALU_ADD_X,
-		[BPF_ALU|BPF_SUB|BPF_K]  = BPF_S_ALU_SUB_K,
-		[BPF_ALU|BPF_SUB|BPF_X]  = BPF_S_ALU_SUB_X,
-		[BPF_ALU|BPF_MUL|BPF_K]  = BPF_S_ALU_MUL_K,
-		[BPF_ALU|BPF_MUL|BPF_X]  = BPF_S_ALU_MUL_X,
-		[BPF_ALU|BPF_DIV|BPF_X]  = BPF_S_ALU_DIV_X,
-		[BPF_ALU|BPF_MOD|BPF_K]  = BPF_S_ALU_MOD_K,
-		[BPF_ALU|BPF_MOD|BPF_X]  = BPF_S_ALU_MOD_X,
-		[BPF_ALU|BPF_AND|BPF_K]  = BPF_S_ALU_AND_K,
-		[BPF_ALU|BPF_AND|BPF_X]  = BPF_S_ALU_AND_X,
-		[BPF_ALU|BPF_OR|BPF_K]   = BPF_S_ALU_OR_K,
-		[BPF_ALU|BPF_OR|BPF_X]   = BPF_S_ALU_OR_X,
-		[BPF_ALU|BPF_XOR|BPF_K]  = BPF_S_ALU_XOR_K,
-		[BPF_ALU|BPF_XOR|BPF_X]  = BPF_S_ALU_XOR_X,
-		[BPF_ALU|BPF_LSH|BPF_K]  = BPF_S_ALU_LSH_K,
-		[BPF_ALU|BPF_LSH|BPF_X]  = BPF_S_ALU_LSH_X,
-		[BPF_ALU|BPF_RSH|BPF_K]  = BPF_S_ALU_RSH_K,
-		[BPF_ALU|BPF_RSH|BPF_X]  = BPF_S_ALU_RSH_X,
-		[BPF_ALU|BPF_NEG]        = BPF_S_ALU_NEG,
-		[BPF_LD|BPF_W|BPF_ABS]   = BPF_S_LD_W_ABS,
-		[BPF_LD|BPF_H|BPF_ABS]   = BPF_S_LD_H_ABS,
-		[BPF_LD|BPF_B|BPF_ABS]   = BPF_S_LD_B_ABS,
-		[BPF_LD|BPF_W|BPF_LEN]   = BPF_S_LD_W_LEN,
-		[BPF_LD|BPF_W|BPF_IND]   = BPF_S_LD_W_IND,
-		[BPF_LD|BPF_H|BPF_IND]   = BPF_S_LD_H_IND,
-		[BPF_LD|BPF_B|BPF_IND]   = BPF_S_LD_B_IND,
-		[BPF_LD|BPF_IMM]         = BPF_S_LD_IMM,
-		[BPF_LDX|BPF_W|BPF_LEN]  = BPF_S_LDX_W_LEN,
-		[BPF_LDX|BPF_B|BPF_MSH]  = BPF_S_LDX_B_MSH,
-		[BPF_LDX|BPF_IMM]        = BPF_S_LDX_IMM,
-		[BPF_MISC|BPF_TAX]       = BPF_S_MISC_TAX,
-		[BPF_MISC|BPF_TXA]       = BPF_S_MISC_TXA,
-		[BPF_RET|BPF_K]          = BPF_S_RET_K,
-		[BPF_RET|BPF_A]          = BPF_S_RET_A,
-		[BPF_ALU|BPF_DIV|BPF_K]  = BPF_S_ALU_DIV_K,
-		[BPF_LD|BPF_MEM]         = BPF_S_LD_MEM,
-		[BPF_LDX|BPF_MEM]        = BPF_S_LDX_MEM,
-		[BPF_ST]                 = BPF_S_ST,
-		[BPF_STX]                = BPF_S_STX,
-		[BPF_JMP|BPF_JA]         = BPF_S_JMP_JA,
-		[BPF_JMP|BPF_JEQ|BPF_K]  = BPF_S_JMP_JEQ_K,
-		[BPF_JMP|BPF_JEQ|BPF_X]  = BPF_S_JMP_JEQ_X,
-		[BPF_JMP|BPF_JGE|BPF_K]  = BPF_S_JMP_JGE_K,
-		[BPF_JMP|BPF_JGE|BPF_X]  = BPF_S_JMP_JGE_X,
-		[BPF_JMP|BPF_JGT|BPF_K]  = BPF_S_JMP_JGT_K,
-		[BPF_JMP|BPF_JGT|BPF_X]  = BPF_S_JMP_JGT_X,
-		[BPF_JMP|BPF_JSET|BPF_K] = BPF_S_JMP_JSET_K,
-		[BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X,
-	};
-	int pc;
 	bool anc_found;
+	int pc;
 
 	if (flen == 0 || flen > BPF_MAXINSNS)
 		return -EINVAL;
 
-	/* check the filter code now */
+	/* Check the filter code now */
 	for (pc = 0; pc < flen; pc++) {
 		struct sock_filter *ftest = &filter[pc];
-		u16 code = ftest->code;
 
-		if (code >= ARRAY_SIZE(codes))
-			return -EINVAL;
-		code = codes[code];
-		if (!code)
+		/* May we actually operate on this code? */
+		if (!chk_code_allowed(ftest->code))
 			return -EINVAL;
+
 		/* Some instructions need special checks */
-		switch (code) {
-		case BPF_S_ALU_DIV_K:
-			/* check for division by zero */
+		switch (ftest->code) {
+		case BPF_ALU | BPF_DIV | BPF_K:
+		case BPF_ALU | BPF_MOD | BPF_K:
+			/* Check for division by zero */
 			if (ftest->k == 0)
 				return -EINVAL;
-			ftest->k = reciprocal_value(ftest->k);
 			break;
-		case BPF_S_ALU_MOD_K:
-			/* check for division by zero */
-			if (ftest->k == 0)
-				return -EINVAL;
-			break;
-		case BPF_S_LD_MEM:
-		case BPF_S_LDX_MEM:
-		case BPF_S_ST:
-		case BPF_S_STX:
-			/* check for invalid memory addresses */
+		case BPF_LD | BPF_MEM:
+		case BPF_LDX | BPF_MEM:
+		case BPF_ST:
+		case BPF_STX:
+			/* Check for invalid memory addresses */
 			if (ftest->k >= BPF_MEMWORDS)
 				return -EINVAL;
 			break;
-		case BPF_S_JMP_JA:
-			/*
-			 * Note, the large ftest->k might cause loops.
+		case BPF_JMP | BPF_JA:
+			/* Note, the large ftest->k might cause loops.
 			 * Compare this with conditional jumps below,
 			 * where offsets are limited. --ANK (981016)
 			 */
-			if (ftest->k >= (unsigned int)(flen-pc-1))
+			if (ftest->k >= (unsigned int)(flen - pc - 1))
 				return -EINVAL;
 			break;
-		case BPF_S_JMP_JEQ_K:
-		case BPF_S_JMP_JEQ_X:
-		case BPF_S_JMP_JGE_K:
-		case BPF_S_JMP_JGE_X:
-		case BPF_S_JMP_JGT_K:
-		case BPF_S_JMP_JGT_X:
-		case BPF_S_JMP_JSET_X:
-		case BPF_S_JMP_JSET_K:
-			/* for conditionals both must be safe */
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
+			/* Both conditionals must be safe */
 			if (pc + ftest->jt + 1 >= flen ||
 			    pc + ftest->jf + 1 >= flen)
 				return -EINVAL;
 			break;
-		case BPF_S_LD_W_ABS:
-		case BPF_S_LD_H_ABS:
-		case BPF_S_LD_B_ABS:
+		case BPF_LD | BPF_W | BPF_ABS:
+		case BPF_LD | BPF_H | BPF_ABS:
+		case BPF_LD | BPF_B | BPF_ABS:
 			anc_found = false;
-#define ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE:	\
-				code = BPF_S_ANC_##CODE;	\
-				anc_found = true;		\
-				break
-			switch (ftest->k) {
-			ANCILLARY(PROTOCOL);
-			ANCILLARY(PKTTYPE);
-			ANCILLARY(IFINDEX);
-			ANCILLARY(NLATTR);
-			ANCILLARY(NLATTR_NEST);
-			ANCILLARY(MARK);
-			ANCILLARY(QUEUE);
-			ANCILLARY(HATYPE);
-			ANCILLARY(RXHASH);
-			ANCILLARY(CPU);
-			ANCILLARY(ALU_XOR_X);
-			ANCILLARY(VLAN_TAG);
-			ANCILLARY(VLAN_TAG_PRESENT);
-			ANCILLARY(PAY_OFFSET);
-			}
-
-			/* ancillary operation unknown or unsupported */
+			if (bpf_anc_helper(ftest) & BPF_ANC)
+				anc_found = true;
+			/* Ancillary operation unknown or unsupported */
 			if (anc_found == false && ftest->k >= SKF_AD_OFF)
 				return -EINVAL;
 		}
-		ftest->code = code;
 	}
 
-	/* last instruction must be a RET code */
+	/* Last instruction must be a RET code */
 	switch (filter[flen - 1].code) {
-	case BPF_S_RET_K:
-	case BPF_S_RET_A:
+	case BPF_RET | BPF_K:
+	case BPF_RET | BPF_A:
 		return check_load_and_stores(filter, flen);
 	}
+
 	return -EINVAL;
 }
 EXPORT_SYMBOL(sk_chk_filter);
 
+static int sk_store_orig_filter(struct sk_filter *fp,
+				const struct sock_fprog *fprog)
+{
+	unsigned int fsize = sk_filter_proglen(fprog);
+	struct sock_fprog_kern *fkprog;
+
+	fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL);
+	if (!fp->orig_prog)
+		return -ENOMEM;
+
+	fkprog = fp->orig_prog;
+	fkprog->len = fprog->len;
+	fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL);
+	if (!fkprog->filter) {
+		kfree(fp->orig_prog);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void sk_release_orig_filter(struct sk_filter *fp)
+{
+	struct sock_fprog_kern *fprog = fp->orig_prog;
+
+	if (fprog) {
+		kfree(fprog->filter);
+		kfree(fprog);
+	}
+}
+
 /**
  * 	sk_filter_release_rcu - Release a socket filter by rcu_head
  *	@rcu: rcu_head that contains the sk_filter to free
  */
-void sk_filter_release_rcu(struct rcu_head *rcu)
+static void sk_filter_release_rcu(struct rcu_head *rcu)
 {
 	struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
 
+	sk_release_orig_filter(fp);
+	sk_filter_free(fp);
+}
+
+/**
+ *	sk_filter_release - release a socket filter
+ *	@fp: filter to remove
+ *
+ *	Remove a filter from a socket and release its resources.
+ */
+static void sk_filter_release(struct sk_filter *fp)
+{
+	if (atomic_dec_and_test(&fp->refcnt))
+		call_rcu(&fp->rcu, sk_filter_release_rcu);
+}
+
+void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
+{
+	atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc);
+	sk_filter_release(fp);
+}
+
+void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+	atomic_inc(&fp->refcnt);
+	atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc);
+}
+
+static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp,
+					      struct sock *sk,
+					      unsigned int len)
+{
+	struct sk_filter *fp_new;
+
+	if (sk == NULL)
+		return krealloc(fp, len, GFP_KERNEL);
+
+	fp_new = sock_kmalloc(sk, len, GFP_KERNEL);
+	if (fp_new) {
+		*fp_new = *fp;
+		/* As we're keeping orig_prog in fp_new along,
+		 * we need to make sure we're not evicting it
+		 * from the old fp.
+		 */
+		fp->orig_prog = NULL;
+		sk_filter_uncharge(sk, fp);
+	}
+
+	return fp_new;
+}
+
+static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
+					     struct sock *sk)
+{
+	struct sock_filter *old_prog;
+	struct sk_filter *old_fp;
+	int err, new_len, old_len = fp->len;
+
+	/* We are free to overwrite insns et al right here as it
+	 * won't be used at this point in time anymore internally
+	 * after the migration to the internal BPF instruction
+	 * representation.
+	 */
+	BUILD_BUG_ON(sizeof(struct sock_filter) !=
+		     sizeof(struct sock_filter_int));
+
+	/* Conversion cannot happen on overlapping memory areas,
+	 * so we need to keep the user BPF around until the 2nd
+	 * pass. At this time, the user BPF is stored in fp->insns.
+	 */
+	old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter),
+			   GFP_KERNEL);
+	if (!old_prog) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	/* 1st pass: calculate the new program length. */
+	err = sk_convert_filter(old_prog, old_len, NULL, &new_len);
+	if (err)
+		goto out_err_free;
+
+	/* Expand fp for appending the new filter representation. */
+	old_fp = fp;
+	fp = __sk_migrate_realloc(old_fp, sk, sk_filter_size(new_len));
+	if (!fp) {
+		/* The old_fp is still around in case we couldn't
+		 * allocate new memory, so uncharge on that one.
+		 */
+		fp = old_fp;
+		err = -ENOMEM;
+		goto out_err_free;
+	}
+
+	fp->len = new_len;
+
+	/* 2nd pass: remap sock_filter insns into sock_filter_int insns. */
+	err = sk_convert_filter(old_prog, old_len, fp->insnsi, &new_len);
+	if (err)
+		/* 2nd sk_convert_filter() can fail only if it fails
+		 * to allocate memory, remapping must succeed. Note,
+		 * that at this time old_fp has already been released
+		 * by __sk_migrate_realloc().
+		 */
+		goto out_err_free;
+
+	sk_filter_select_runtime(fp);
+
+	kfree(old_prog);
+	return fp;
+
+out_err_free:
+	kfree(old_prog);
+out_err:
+	/* Rollback filter setup. */
+	if (sk != NULL)
+		sk_filter_uncharge(sk, fp);
+	else
+		kfree(fp);
+	return ERR_PTR(err);
+}
+
+void __weak bpf_int_jit_compile(struct sk_filter *prog)
+{
+}
+
+/**
+ *	sk_filter_select_runtime - select execution runtime for BPF program
+ *	@fp: sk_filter populated with internal BPF program
+ *
+ * try to JIT internal BPF program, if JIT is not available select interpreter
+ * BPF program will be executed via SK_RUN_FILTER() macro
+ */
+void sk_filter_select_runtime(struct sk_filter *fp)
+{
+	fp->bpf_func = (void *) __sk_run_filter;
+
+	/* Probe if internal BPF can be JITed */
+	bpf_int_jit_compile(fp);
+}
+EXPORT_SYMBOL_GPL(sk_filter_select_runtime);
+
+/* free internal BPF program */
+void sk_filter_free(struct sk_filter *fp)
+{
 	bpf_jit_free(fp);
 }
-EXPORT_SYMBOL(sk_filter_release_rcu);
+EXPORT_SYMBOL_GPL(sk_filter_free);
 
-static int __sk_prepare_filter(struct sk_filter *fp)
+static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
+					     struct sock *sk)
 {
 	int err;
 
-	fp->bpf_func = sk_run_filter;
+	fp->bpf_func = NULL;
+	fp->jited = 0;
 
 	err = sk_chk_filter(fp->insns, fp->len);
-	if (err)
-		return err;
+	if (err) {
+		if (sk != NULL)
+			sk_filter_uncharge(sk, fp);
+		else
+			kfree(fp);
+		return ERR_PTR(err);
+	}
 
+	/* Probe if we can JIT compile the filter and if so, do
+	 * the compilation of the filter.
+	 */
 	bpf_jit_compile(fp);
-	return 0;
+
+	/* JIT compiler couldn't process this filter, so do the
+	 * internal BPF translation for the optimized interpreter.
+	 */
+	if (!fp->jited)
+		fp = __sk_migrate_filter(fp, sk);
+
+	return fp;
 }
 
 /**
  *	sk_unattached_filter_create - create an unattached filter
- *	@fprog: the filter program
  *	@pfp: the unattached filter that is created
+ *	@fprog: the filter program
  *
  * Create a filter independent of any socket. We first run some
  * sanity checks on it to make sure it does not explode on us later.
@@ -672,11 +1533,10 @@ static int __sk_prepare_filter(struct sk_filter *fp)
  * a negative errno code is returned. On success the return is zero.
  */
 int sk_unattached_filter_create(struct sk_filter **pfp,
-				struct sock_fprog *fprog)
+				struct sock_fprog_kern *fprog)
 {
+	unsigned int fsize = sk_filter_proglen(fprog);
 	struct sk_filter *fp;
-	unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
-	int err;
 
 	/* Make sure new filter is there and in the right amounts. */
 	if (fprog->filter == NULL)
@@ -685,20 +1545,26 @@ int sk_unattached_filter_create(struct sk_filter **pfp,
 	fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL);
 	if (!fp)
 		return -ENOMEM;
+
 	memcpy(fp->insns, fprog->filter, fsize);
 
 	atomic_set(&fp->refcnt, 1);
 	fp->len = fprog->len;
+	/* Since unattached filters are not copied back to user
+	 * space through sk_get_filter(), we do not need to hold
+	 * a copy here, and can spare us the work.
+	 */
+	fp->orig_prog = NULL;
 
-	err = __sk_prepare_filter(fp);
-	if (err)
-		goto free_mem;
+	/* __sk_prepare_filter() already takes care of uncharging
+	 * memory in case something goes wrong.
+	 */
+	fp = __sk_prepare_filter(fp, NULL);
+	if (IS_ERR(fp))
+		return PTR_ERR(fp);
 
 	*pfp = fp;
 	return 0;
-free_mem:
-	kfree(fp);
-	return err;
 }
 EXPORT_SYMBOL_GPL(sk_unattached_filter_create);
 
@@ -721,7 +1587,7 @@ EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy);
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 {
 	struct sk_filter *fp, *old_fp;
-	unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
+	unsigned int fsize = sk_filter_proglen(fprog);
 	unsigned int sk_fsize = sk_filter_size(fprog->len);
 	int err;
 
@@ -735,6 +1601,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL);
 	if (!fp)
 		return -ENOMEM;
+
 	if (copy_from_user(fp->insns, fprog->filter, fsize)) {
 		sock_kfree_s(sk, fp, sk_fsize);
 		return -EFAULT;
@@ -743,18 +1610,26 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	atomic_set(&fp->refcnt, 1);
 	fp->len = fprog->len;
 
-	err = __sk_prepare_filter(fp);
+	err = sk_store_orig_filter(fp, fprog);
 	if (err) {
 		sk_filter_uncharge(sk, fp);
-		return err;
+		return -ENOMEM;
 	}
 
+	/* __sk_prepare_filter() already takes care of uncharging
+	 * memory in case something goes wrong.
+	 */
+	fp = __sk_prepare_filter(fp, sk);
+	if (IS_ERR(fp))
+		return PTR_ERR(fp);
+
 	old_fp = rcu_dereference_protected(sk->sk_filter,
 					   sock_owned_by_user(sk));
 	rcu_assign_pointer(sk->sk_filter, fp);
 
 	if (old_fp)
 		sk_filter_uncharge(sk, old_fp);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sk_attach_filter);
@@ -774,136 +1649,46 @@ int sk_detach_filter(struct sock *sk)
 		sk_filter_uncharge(sk, filter);
 		ret = 0;
 	}
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(sk_detach_filter);
 
-void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
-{
-	static const u16 decodes[] = {
-		[BPF_S_ALU_ADD_K]	= BPF_ALU|BPF_ADD|BPF_K,
-		[BPF_S_ALU_ADD_X]	= BPF_ALU|BPF_ADD|BPF_X,
-		[BPF_S_ALU_SUB_K]	= BPF_ALU|BPF_SUB|BPF_K,
-		[BPF_S_ALU_SUB_X]	= BPF_ALU|BPF_SUB|BPF_X,
-		[BPF_S_ALU_MUL_K]	= BPF_ALU|BPF_MUL|BPF_K,
-		[BPF_S_ALU_MUL_X]	= BPF_ALU|BPF_MUL|BPF_X,
-		[BPF_S_ALU_DIV_X]	= BPF_ALU|BPF_DIV|BPF_X,
-		[BPF_S_ALU_MOD_K]	= BPF_ALU|BPF_MOD|BPF_K,
-		[BPF_S_ALU_MOD_X]	= BPF_ALU|BPF_MOD|BPF_X,
-		[BPF_S_ALU_AND_K]	= BPF_ALU|BPF_AND|BPF_K,
-		[BPF_S_ALU_AND_X]	= BPF_ALU|BPF_AND|BPF_X,
-		[BPF_S_ALU_OR_K]	= BPF_ALU|BPF_OR|BPF_K,
-		[BPF_S_ALU_OR_X]	= BPF_ALU|BPF_OR|BPF_X,
-		[BPF_S_ALU_XOR_K]	= BPF_ALU|BPF_XOR|BPF_K,
-		[BPF_S_ALU_XOR_X]	= BPF_ALU|BPF_XOR|BPF_X,
-		[BPF_S_ALU_LSH_K]	= BPF_ALU|BPF_LSH|BPF_K,
-		[BPF_S_ALU_LSH_X]	= BPF_ALU|BPF_LSH|BPF_X,
-		[BPF_S_ALU_RSH_K]	= BPF_ALU|BPF_RSH|BPF_K,
-		[BPF_S_ALU_RSH_X]	= BPF_ALU|BPF_RSH|BPF_X,
-		[BPF_S_ALU_NEG]		= BPF_ALU|BPF_NEG,
-		[BPF_S_LD_W_ABS]	= BPF_LD|BPF_W|BPF_ABS,
-		[BPF_S_LD_H_ABS]	= BPF_LD|BPF_H|BPF_ABS,
-		[BPF_S_LD_B_ABS]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_PROTOCOL]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_PKTTYPE]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_IFINDEX]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_NLATTR]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_NLATTR_NEST]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_MARK]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_QUEUE]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_HATYPE]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_RXHASH]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_CPU]		= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_ALU_XOR_X]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_SECCOMP_LD_W] = BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_VLAN_TAG]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_PAY_OFFSET]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_LD_W_LEN]	= BPF_LD|BPF_W|BPF_LEN,
-		[BPF_S_LD_W_IND]	= BPF_LD|BPF_W|BPF_IND,
-		[BPF_S_LD_H_IND]	= BPF_LD|BPF_H|BPF_IND,
-		[BPF_S_LD_B_IND]	= BPF_LD|BPF_B|BPF_IND,
-		[BPF_S_LD_IMM]		= BPF_LD|BPF_IMM,
-		[BPF_S_LDX_W_LEN]	= BPF_LDX|BPF_W|BPF_LEN,
-		[BPF_S_LDX_B_MSH]	= BPF_LDX|BPF_B|BPF_MSH,
-		[BPF_S_LDX_IMM]		= BPF_LDX|BPF_IMM,
-		[BPF_S_MISC_TAX]	= BPF_MISC|BPF_TAX,
-		[BPF_S_MISC_TXA]	= BPF_MISC|BPF_TXA,
-		[BPF_S_RET_K]		= BPF_RET|BPF_K,
-		[BPF_S_RET_A]		= BPF_RET|BPF_A,
-		[BPF_S_ALU_DIV_K]	= BPF_ALU|BPF_DIV|BPF_K,
-		[BPF_S_LD_MEM]		= BPF_LD|BPF_MEM,
-		[BPF_S_LDX_MEM]		= BPF_LDX|BPF_MEM,
-		[BPF_S_ST]		= BPF_ST,
-		[BPF_S_STX]		= BPF_STX,
-		[BPF_S_JMP_JA]		= BPF_JMP|BPF_JA,
-		[BPF_S_JMP_JEQ_K]	= BPF_JMP|BPF_JEQ|BPF_K,
-		[BPF_S_JMP_JEQ_X]	= BPF_JMP|BPF_JEQ|BPF_X,
-		[BPF_S_JMP_JGE_K]	= BPF_JMP|BPF_JGE|BPF_K,
-		[BPF_S_JMP_JGE_X]	= BPF_JMP|BPF_JGE|BPF_X,
-		[BPF_S_JMP_JGT_K]	= BPF_JMP|BPF_JGT|BPF_K,
-		[BPF_S_JMP_JGT_X]	= BPF_JMP|BPF_JGT|BPF_X,
-		[BPF_S_JMP_JSET_K]	= BPF_JMP|BPF_JSET|BPF_K,
-		[BPF_S_JMP_JSET_X]	= BPF_JMP|BPF_JSET|BPF_X,
-	};
-	u16 code;
-
-	code = filt->code;
-
-	to->code = decodes[code];
-	to->jt = filt->jt;
-	to->jf = filt->jf;
-
-	if (code == BPF_S_ALU_DIV_K) {
-		/*
-		 * When loaded this rule user gave us X, which was
-		 * translated into R = r(X). Now we calculate the
-		 * RR = r(R) and report it back. If next time this
-		 * value is loaded and RRR = r(RR) is calculated
-		 * then the R == RRR will be true.
-		 *
-		 * One exception. X == 1 translates into R == 0 and
-		 * we can't calculate RR out of it with r().
-		 */
-
-		if (filt->k == 0)
-			to->k = 1;
-		else
-			to->k = reciprocal_value(filt->k);
-
-		BUG_ON(reciprocal_value(to->k) != filt->k);
-	} else
-		to->k = filt->k;
-}
-
-int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len)
+int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
+		  unsigned int len)
 {
+	struct sock_fprog_kern *fprog;
 	struct sk_filter *filter;
-	int i, ret;
+	int ret = 0;
 
 	lock_sock(sk);
 	filter = rcu_dereference_protected(sk->sk_filter,
-			sock_owned_by_user(sk));
-	ret = 0;
+					   sock_owned_by_user(sk));
 	if (!filter)
 		goto out;
-	ret = filter->len;
+
+	/* We're copying the filter that has been originally attached,
+	 * so no conversion/decode needed anymore.
+	 */
+	fprog = filter->orig_prog;
+
+	ret = fprog->len;
 	if (!len)
+		/* User space only enquires number of filter blocks. */
 		goto out;
+
 	ret = -EINVAL;
-	if (len < filter->len)
+	if (len < fprog->len)
 		goto out;
 
 	ret = -EFAULT;
-	for (i = 0; i < filter->len; i++) {
-		struct sock_filter fb;
-
-		sk_decode_filter(&filter->insns[i], &fb);
-		if (copy_to_user(&ubuf[i], &fb, sizeof(fb)))
-			goto out;
-	}
+	if (copy_to_user(ubuf, fprog->filter, sk_filter_proglen(fprog)))
+		goto out;
 
-	ret = filter->len;
+	/* Instead of bytes, the API requests to return the number
+	 * of filter blocks.
+	 */
+	ret = fprog->len;
 out:
 	release_sock(sk);
 	return ret;
diff --git a/net/core/flow.c b/net/core/flow.c
index dfa602ceb8c..a0348fde1fd 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -24,6 +24,7 @@
 #include <net/flow.h>
 #include <linux/atomic.h>
 #include <linux/security.h>
+#include <net/net_namespace.h>
 
 struct flow_cache_entry {
 	union {
@@ -38,37 +39,14 @@ struct flow_cache_entry {
 	struct flow_cache_object	*object;
 };
 
-struct flow_cache_percpu {
-	struct hlist_head		*hash_table;
-	int				hash_count;
-	u32				hash_rnd;
-	int				hash_rnd_recalc;
-	struct tasklet_struct		flush_tasklet;
-};
-
 struct flow_flush_info {
 	struct flow_cache		*cache;
 	atomic_t			cpuleft;
 	struct completion		completion;
 };
 
-struct flow_cache {
-	u32				hash_shift;
-	struct flow_cache_percpu __percpu *percpu;
-	struct notifier_block		hotcpu_notifier;
-	int				low_watermark;
-	int				high_watermark;
-	struct timer_list		rnd_timer;
-};
-
-atomic_t flow_cache_genid = ATOMIC_INIT(0);
-EXPORT_SYMBOL(flow_cache_genid);
-static struct flow_cache flow_cache_global;
 static struct kmem_cache *flow_cachep __read_mostly;
 
-static DEFINE_SPINLOCK(flow_cache_gc_lock);
-static LIST_HEAD(flow_cache_gc_list);
-
 #define flow_cache_hash_size(cache)	(1 << (cache)->hash_shift)
 #define FLOW_HASH_RND_PERIOD		(10 * 60 * HZ)
 
@@ -84,16 +62,18 @@ static void flow_cache_new_hashrnd(unsigned long arg)
 	add_timer(&fc->rnd_timer);
 }
 
-static int flow_entry_valid(struct flow_cache_entry *fle)
+static int flow_entry_valid(struct flow_cache_entry *fle,
+				struct netns_xfrm *xfrm)
 {
-	if (atomic_read(&flow_cache_genid) != fle->genid)
+	if (atomic_read(&xfrm->flow_cache_genid) != fle->genid)
 		return 0;
 	if (fle->object && !fle->object->ops->check(fle->object))
 		return 0;
 	return 1;
 }
 
-static void flow_entry_kill(struct flow_cache_entry *fle)
+static void flow_entry_kill(struct flow_cache_entry *fle,
+				struct netns_xfrm *xfrm)
 {
 	if (fle->object)
 		fle->object->ops->delete(fle->object);
@@ -104,26 +84,28 @@ static void flow_cache_gc_task(struct work_struct *work)
 {
 	struct list_head gc_list;
 	struct flow_cache_entry *fce, *n;
+	struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+						flow_cache_gc_work);
 
 	INIT_LIST_HEAD(&gc_list);
-	spin_lock_bh(&flow_cache_gc_lock);
-	list_splice_tail_init(&flow_cache_gc_list, &gc_list);
-	spin_unlock_bh(&flow_cache_gc_lock);
+	spin_lock_bh(&xfrm->flow_cache_gc_lock);
+	list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list);
+	spin_unlock_bh(&xfrm->flow_cache_gc_lock);
 
 	list_for_each_entry_safe(fce, n, &gc_list, u.gc_list)
-		flow_entry_kill(fce);
+		flow_entry_kill(fce, xfrm);
 }
-static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task);
 
 static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
-				     int deleted, struct list_head *gc_list)
+				     int deleted, struct list_head *gc_list,
+				     struct netns_xfrm *xfrm)
 {
 	if (deleted) {
 		fcp->hash_count -= deleted;
-		spin_lock_bh(&flow_cache_gc_lock);
-		list_splice_tail(gc_list, &flow_cache_gc_list);
-		spin_unlock_bh(&flow_cache_gc_lock);
-		schedule_work(&flow_cache_gc_work);
+		spin_lock_bh(&xfrm->flow_cache_gc_lock);
+		list_splice_tail(gc_list, &xfrm->flow_cache_gc_list);
+		spin_unlock_bh(&xfrm->flow_cache_gc_lock);
+		schedule_work(&xfrm->flow_cache_gc_work);
 	}
 }
 
@@ -135,6 +117,8 @@ static void __flow_cache_shrink(struct flow_cache *fc,
 	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
 	int i, deleted = 0;
+	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+						flow_cache_global);
 
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
 		int saved = 0;
@@ -142,7 +126,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
 		hlist_for_each_entry_safe(fle, tmp,
 					  &fcp->hash_table[i], u.hlist) {
 			if (saved < shrink_to &&
-			    flow_entry_valid(fle)) {
+			    flow_entry_valid(fle, xfrm)) {
 				saved++;
 			} else {
 				deleted++;
@@ -152,7 +136,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
 		}
 	}
 
-	flow_cache_queue_garbage(fcp, deleted, &gc_list);
+	flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
 }
 
 static void flow_cache_shrink(struct flow_cache *fc,
@@ -208,7 +192,7 @@ struct flow_cache_object *
 flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 		  flow_resolve_t resolver, void *ctx)
 {
-	struct flow_cache *fc = &flow_cache_global;
+	struct flow_cache *fc = &net->xfrm.flow_cache_global;
 	struct flow_cache_percpu *fcp;
 	struct flow_cache_entry *fle, *tfle;
 	struct flow_cache_object *flo;
@@ -258,7 +242,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
 			hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
 			fcp->hash_count++;
 		}
-	} else if (likely(fle->genid == atomic_read(&flow_cache_genid))) {
+	} else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) {
 		flo = fle->object;
 		if (!flo)
 			goto ret_object;
@@ -279,7 +263,7 @@ nocache:
 	}
 	flo = resolver(net, key, family, dir, flo, ctx);
 	if (fle) {
-		fle->genid = atomic_read(&flow_cache_genid);
+		fle->genid = atomic_read(&net->xfrm.flow_cache_genid);
 		if (!IS_ERR(flo))
 			fle->object = flo;
 		else
@@ -303,12 +287,14 @@ static void flow_cache_flush_tasklet(unsigned long data)
 	struct hlist_node *tmp;
 	LIST_HEAD(gc_list);
 	int i, deleted = 0;
+	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+						flow_cache_global);
 
 	fcp = this_cpu_ptr(fc->percpu);
 	for (i = 0; i < flow_cache_hash_size(fc); i++) {
 		hlist_for_each_entry_safe(fle, tmp,
 					  &fcp->hash_table[i], u.hlist) {
-			if (flow_entry_valid(fle))
+			if (flow_entry_valid(fle, xfrm))
 				continue;
 
 			deleted++;
@@ -317,7 +303,7 @@ static void flow_cache_flush_tasklet(unsigned long data)
 		}
 	}
 
-	flow_cache_queue_garbage(fcp, deleted, &gc_list);
+	flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
 
 	if (atomic_dec_and_test(&info->cpuleft))
 		complete(&info->completion);
@@ -351,10 +337,9 @@ static void flow_cache_flush_per_cpu(void *data)
 	tasklet_schedule(tasklet);
 }
 
-void flow_cache_flush(void)
+void flow_cache_flush(struct net *net)
 {
 	struct flow_flush_info info;
-	static DEFINE_MUTEX(flow_flush_sem);
 	cpumask_var_t mask;
 	int i, self;
 
@@ -365,8 +350,8 @@ void flow_cache_flush(void)
 
 	/* Don't want cpus going down or up during this. */
 	get_online_cpus();
-	mutex_lock(&flow_flush_sem);
-	info.cache = &flow_cache_global;
+	mutex_lock(&net->xfrm.flow_flush_sem);
+	info.cache = &net->xfrm.flow_cache_global;
 	for_each_online_cpu(i)
 		if (!flow_cache_percpu_empty(info.cache, i))
 			cpumask_set_cpu(i, mask);
@@ -386,21 +371,23 @@ void flow_cache_flush(void)
 	wait_for_completion(&info.completion);
 
 done:
-	mutex_unlock(&flow_flush_sem);
+	mutex_unlock(&net->xfrm.flow_flush_sem);
 	put_online_cpus();
 	free_cpumask_var(mask);
 }
 
 static void flow_cache_flush_task(struct work_struct *work)
 {
-	flow_cache_flush();
-}
+	struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+						flow_cache_gc_work);
+	struct net *net = container_of(xfrm, struct net, xfrm);
 
-static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task);
+	flow_cache_flush(net);
+}
 
-void flow_cache_flush_deferred(void)
+void flow_cache_flush_deferred(struct net *net)
 {
-	schedule_work(&flow_cache_flush_work);
+	schedule_work(&net->xfrm.flow_cache_flush_work);
 }
 
 static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
@@ -425,7 +412,8 @@ static int flow_cache_cpu(struct notifier_block *nfb,
 			  unsigned long action,
 			  void *hcpu)
 {
-	struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier);
+	struct flow_cache *fc = container_of(nfb, struct flow_cache,
+						hotcpu_notifier);
 	int res, cpu = (unsigned long) hcpu;
 	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
 
@@ -444,9 +432,20 @@ static int flow_cache_cpu(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-static int __init flow_cache_init(struct flow_cache *fc)
+int flow_cache_init(struct net *net)
 {
 	int i;
+	struct flow_cache *fc = &net->xfrm.flow_cache_global;
+
+	if (!flow_cachep)
+		flow_cachep = kmem_cache_create("flow_cache",
+						sizeof(struct flow_cache_entry),
+						0, SLAB_PANIC, NULL);
+	spin_lock_init(&net->xfrm.flow_cache_gc_lock);
+	INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list);
+	INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task);
+	INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task);
+	mutex_init(&net->xfrm.flow_flush_sem);
 
 	fc->hash_shift = 10;
 	fc->low_watermark = 2 * flow_cache_hash_size(fc);
@@ -456,6 +455,8 @@ static int __init flow_cache_init(struct flow_cache *fc)
 	if (!fc->percpu)
 		return -ENOMEM;
 
+	cpu_notifier_register_begin();
+
 	for_each_online_cpu(i) {
 		if (flow_cache_cpu_prepare(fc, i))
 			goto err;
@@ -463,7 +464,9 @@ static int __init flow_cache_init(struct flow_cache *fc)
 	fc->hotcpu_notifier = (struct notifier_block){
 		.notifier_call = flow_cache_cpu,
 	};
-	register_hotcpu_notifier(&fc->hotcpu_notifier);
+	__register_hotcpu_notifier(&fc->hotcpu_notifier);
+
+	cpu_notifier_register_done();
 
 	setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd,
 		    (unsigned long) fc);
@@ -479,19 +482,30 @@ err:
 		fcp->hash_table = NULL;
 	}
 
+	cpu_notifier_register_done();
+
 	free_percpu(fc->percpu);
 	fc->percpu = NULL;
 
 	return -ENOMEM;
 }
+EXPORT_SYMBOL(flow_cache_init);
 
-static int __init flow_cache_init_global(void)
+void flow_cache_fini(struct net *net)
 {
-	flow_cachep = kmem_cache_create("flow_cache",
-					sizeof(struct flow_cache_entry),
-					0, SLAB_PANIC, NULL);
+	int i;
+	struct flow_cache *fc = &net->xfrm.flow_cache_global;
 
-	return flow_cache_init(&flow_cache_global);
-}
+	del_timer_sync(&fc->rnd_timer);
+	unregister_hotcpu_notifier(&fc->hotcpu_notifier);
+
+	for_each_possible_cpu(i) {
+		struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
+		kfree(fcp->hash_table);
+		fcp->hash_table = NULL;
+	}
 
-module_init(flow_cache_init_global);
+	free_percpu(fc->percpu);
+	fc->percpu = NULL;
+}
+EXPORT_SYMBOL(flow_cache_fini);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d6ef1732250..107ed12a532 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -61,7 +61,7 @@ bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
 
 again:
 	switch (proto) {
-	case __constant_htons(ETH_P_IP): {
+	case htons(ETH_P_IP): {
 		const struct iphdr *iph;
 		struct iphdr _iph;
 ip:
@@ -77,7 +77,7 @@ ip:
 		iph_to_flow_copy_addrs(flow, iph);
 		break;
 	}
-	case __constant_htons(ETH_P_IPV6): {
+	case htons(ETH_P_IPV6): {
 		const struct ipv6hdr *iph;
 		struct ipv6hdr _iph;
 ipv6:
@@ -91,8 +91,8 @@ ipv6:
 		nhoff += sizeof(struct ipv6hdr);
 		break;
 	}
-	case __constant_htons(ETH_P_8021AD):
-	case __constant_htons(ETH_P_8021Q): {
+	case htons(ETH_P_8021AD):
+	case htons(ETH_P_8021Q): {
 		const struct vlan_hdr *vlan;
 		struct vlan_hdr _vlan;
 
@@ -104,7 +104,7 @@ ipv6:
 		nhoff += sizeof(*vlan);
 		goto again;
 	}
-	case __constant_htons(ETH_P_PPP_SES): {
+	case htons(ETH_P_PPP_SES): {
 		struct {
 			struct pppoe_hdr hdr;
 			__be16 proto;
@@ -115,9 +115,9 @@ ipv6:
 		proto = hdr->proto;
 		nhoff += PPPOE_SES_HLEN;
 		switch (proto) {
-		case __constant_htons(PPP_IP):
+		case htons(PPP_IP):
 			goto ip;
-		case __constant_htons(PPP_IPV6):
+		case htons(PPP_IPV6):
 			goto ipv6;
 		default:
 			return false;
@@ -202,12 +202,12 @@ static __always_inline u32 __flow_hash_1word(u32 a)
 }
 
 /*
- * __skb_get_rxhash: calculate a flow hash based on src/dst addresses
- * and src/dst port numbers.  Sets rxhash in skb to non-zero hash value
- * on success, zero indicates no valid hash.  Also, sets l4_rxhash in skb
+ * __skb_get_hash: calculate a flow hash based on src/dst addresses
+ * and src/dst port numbers.  Sets hash in skb to non-zero hash value
+ * on success, zero indicates no valid hash.  Also, sets l4_hash in skb
  * if hash is a canonical 4-tuple hash over transport ports.
  */
-void __skb_get_rxhash(struct sk_buff *skb)
+void __skb_get_hash(struct sk_buff *skb)
 {
 	struct flow_keys keys;
 	u32 hash;
@@ -216,7 +216,7 @@ void __skb_get_rxhash(struct sk_buff *skb)
 		return;
 
 	if (keys.ports)
-		skb->l4_rxhash = 1;
+		skb->l4_hash = 1;
 
 	/* get a consistent hash (same value on both flow directions) */
 	if (((__force u32)keys.dst < (__force u32)keys.src) ||
@@ -232,9 +232,9 @@ void __skb_get_rxhash(struct sk_buff *skb)
 	if (!hash)
 		hash = 1;
 
-	skb->rxhash = hash;
+	skb->hash = hash;
 }
-EXPORT_SYMBOL(__skb_get_rxhash);
+EXPORT_SYMBOL(__skb_get_hash);
 
 /*
  * Returns a Tx hash based on the given packet descriptor a Tx queues' number
@@ -323,17 +323,6 @@ u32 __skb_get_poff(const struct sk_buff *skb)
 	return poff;
 }
 
-static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
-{
-	if (unlikely(queue_index >= dev->real_num_tx_queues)) {
-		net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
-				     dev->name, queue_index,
-				     dev->real_num_tx_queues);
-		return 0;
-	}
-	return queue_index;
-}
-
 static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_XPS
@@ -355,7 +344,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 					hash = skb->sk->sk_hash;
 				else
 					hash = (__force u16) skb->protocol ^
-					    skb->rxhash;
+					    skb->hash;
 				hash = __flow_hash_1word(hash);
 				queue_index = map->queues[
 				    ((u64)hash * map->len) >> 32];
@@ -372,7 +361,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 #endif
 }
 
-u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
 	int queue_index = sk_tx_queue_get(sk);
@@ -392,20 +381,23 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 
 	return queue_index;
 }
-EXPORT_SYMBOL(__netdev_pick_tx);
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
-				    struct sk_buff *skb)
+				    struct sk_buff *skb,
+				    void *accel_priv)
 {
 	int queue_index = 0;
 
 	if (dev->real_num_tx_queues != 1) {
 		const struct net_device_ops *ops = dev->netdev_ops;
 		if (ops->ndo_select_queue)
-			queue_index = ops->ndo_select_queue(dev, skb);
+			queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+							    __netdev_pick_tx);
 		else
 			queue_index = __netdev_pick_tx(dev, skb);
-		queue_index = dev_cap_txqueue(dev, queue_index);
+
+		if (!accel_priv)
+			queue_index = netdev_cap_txqueue(dev, queue_index);
 	}
 
 	skb_set_queue_mapping(skb, queue_index);
diff --git a/net/core/iovec.c b/net/core/iovec.c
index b61869429f4..e1ec45ab1e6 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -39,7 +39,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 {
 	int size, ct, err;
 
-	if (m->msg_namelen) {
+	if (m->msg_name && m->msg_namelen) {
 		if (mode == VERIFY_READ) {
 			void __user *namep;
 			namep = (void __user __force *) m->msg_name;
@@ -48,10 +48,10 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 			if (err < 0)
 				return err;
 		}
-		if (m->msg_name)
-			m->msg_name = address;
+		m->msg_name = address;
 	} else {
 		m->msg_name = NULL;
+		m->msg_namelen = 0;
 	}
 
 	size = m->msg_iovlen * sizeof(struct iovec);
@@ -75,61 +75,6 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 }
 
 /*
- *	Copy kernel to iovec. Returns -EFAULT on error.
- */
-
-int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
-		      int offset, int len)
-{
-	int copy;
-	for (; len > 0; ++iov) {
-		/* Skip over the finished iovecs */
-		if (unlikely(offset >= iov->iov_len)) {
-			offset -= iov->iov_len;
-			continue;
-		}
-		copy = min_t(unsigned int, iov->iov_len - offset, len);
-		if (copy_to_user(iov->iov_base + offset, kdata, copy))
-			return -EFAULT;
-		offset = 0;
-		kdata += copy;
-		len -= copy;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_toiovecend);
-
-/*
- *	Copy iovec to kernel. Returns -EFAULT on error.
- */
-
-int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
-			int offset, int len)
-{
-	/* Skip over the finished iovecs */
-	while (offset >= iov->iov_len) {
-		offset -= iov->iov_len;
-		iov++;
-	}
-
-	while (len > 0) {
-		u8 __user *base = iov->iov_base + offset;
-		int copy = min_t(unsigned int, len, iov->iov_len - offset);
-
-		offset = 0;
-		if (copy_from_user(kdata, base, copy))
-			return -EFAULT;
-		len -= copy;
-		kdata += copy;
-		iov++;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_fromiovecend);
-
-/*
  *	And now for the all-in-one: copy and checksum from a user iovec
  *	directly to a datagram
  *	Calls to csum_partial but the last must be in 32 bit chunks
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 9c3a839322b..bd0767e6b2b 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -147,7 +147,7 @@ static void linkwatch_do_dev(struct net_device *dev)
 	 * Make sure the above read is complete since it can be
 	 * rewritten as soon as we clear the bit below.
 	 */
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 
 	/* We are about to handle this device,
 	 * so new events can be accepted
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ce2b77515a9..ef31fef25e5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -117,7 +117,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh)
 
 unsigned long neigh_rand_reach_time(unsigned long base)
 {
-	return base ? (net_random() % base) + (base >> 1) : 0;
+	return base ? (prandom_u32() % base) + (base >> 1) : 0;
 }
 EXPORT_SYMBOL(neigh_rand_reach_time);
 
@@ -766,9 +766,6 @@ static void neigh_periodic_work(struct work_struct *work)
 	nht = rcu_dereference_protected(tbl->nht,
 					lockdep_is_held(&tbl->lock));
 
-	if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
-		goto out;
-
 	/*
 	 *	periodically recompute ReachableTime from random function
 	 */
@@ -781,6 +778,9 @@ static void neigh_periodic_work(struct work_struct *work)
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
 	}
 
+	if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
+		goto out;
+
 	for (i = 0 ; i < (1 << nht->hash_shift); i++) {
 		np = &nht->hash_buckets[i];
 
@@ -828,7 +828,7 @@ out:
 	 * ARP entry timeouts range from 1/2 BASE_REACHABLE_TIME to 3/2
 	 * BASE_REACHABLE_TIME.
 	 */
-	schedule_delayed_work(&tbl->gc_work,
+	queue_delayed_work(system_power_efficient_wq, &tbl->gc_work,
 			      NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1);
 	write_unlock_bh(&tbl->lock);
 }
@@ -836,10 +836,10 @@ out:
 static __inline__ int neigh_max_probes(struct neighbour *n)
 {
 	struct neigh_parms *p = n->parms;
-	return (n->nud_state & NUD_PROBE) ?
-		NEIGH_VAR(p, UCAST_PROBES) :
-		NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) +
-		NEIGH_VAR(p, MCAST_PROBES);
+	int max_probes = NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES);
+	if (!(n->nud_state & NUD_PROBE))
+		max_probes += NEIGH_VAR(p, MCAST_PROBES);
+	return max_probes;
 }
 
 static void neigh_invalidate(struct neighbour *neigh)
@@ -945,6 +945,7 @@ static void neigh_timer_handler(unsigned long arg)
 		neigh->nud_state = NUD_FAILED;
 		notify = 1;
 		neigh_invalidate(neigh);
+		goto out;
 	}
 
 	if (neigh->nud_state & NUD_IN_TIMER) {
@@ -1169,6 +1170,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 						 neigh->parms->reachable_time :
 						 0)));
 		neigh->nud_state = new;
+		notify = 1;
 	}
 
 	if (lladdr != neigh->ha) {
@@ -1238,6 +1240,21 @@ out:
 }
 EXPORT_SYMBOL(neigh_update);
 
+/* Update the neigh to listen temporarily for probe responses, even if it is
+ * in a NUD_FAILED state. The caller has to hold neigh->lock for writing.
+ */
+void __neigh_set_probe_once(struct neighbour *neigh)
+{
+	neigh->updated = jiffies;
+	if (!(neigh->nud_state & NUD_FAILED))
+		return;
+	neigh->nud_state = NUD_INCOMPLETE;
+	atomic_set(&neigh->probes, neigh_max_probes(neigh));
+	neigh_add_timer(neigh,
+			jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME));
+}
+EXPORT_SYMBOL(__neigh_set_probe_once);
+
 struct neighbour *neigh_event_ns(struct neigh_table *tbl,
 				 u8 *lladdr, void *saddr,
 				 struct net_device *dev)
@@ -1282,7 +1299,7 @@ int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb)
 
 	if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
 			    skb->len) < 0 &&
-	    dev->header_ops->rebuild(skb))
+	    dev_rebuild_header(skb))
 		return 0;
 
 	return dev_queue_xmit(skb);
@@ -1399,7 +1416,8 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
 		    struct sk_buff *skb)
 {
 	unsigned long now = jiffies;
-	unsigned long sched_next = now + (net_random() %
+
+	unsigned long sched_next = now + (prandom_u32() %
 					  NEIGH_VAR(p, PROXY_DELAY));
 
 	if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
@@ -1548,7 +1566,8 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl)
 
 	rwlock_init(&tbl->lock);
 	INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work);
-	schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time);
+	queue_delayed_work(system_power_efficient_wq, &tbl->gc_work,
+			tbl->parms.reachable_time);
 	setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl);
 	skb_queue_head_init_class(&tbl->proxy_queue,
 			&neigh_table_proxy_queue_class);
@@ -2070,13 +2089,16 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 					      nla_get_msecs(tbp[i]));
 				break;
 			case NDTPA_ANYCAST_DELAY:
-				NEIGH_VAR_SET(p, ANYCAST_DELAY, nla_get_msecs(tbp[i]));
+				NEIGH_VAR_SET(p, ANYCAST_DELAY,
+					      nla_get_msecs(tbp[i]));
 				break;
 			case NDTPA_PROXY_DELAY:
-				NEIGH_VAR_SET(p, PROXY_DELAY, nla_get_msecs(tbp[i]));
+				NEIGH_VAR_SET(p, PROXY_DELAY,
+					      nla_get_msecs(tbp[i]));
 				break;
 			case NDTPA_LOCKTIME:
-				NEIGH_VAR_SET(p, LOCKTIME, nla_get_msecs(tbp[i]));
+				NEIGH_VAR_SET(p, LOCKTIME,
+					      nla_get_msecs(tbp[i]));
 				break;
 			}
 		}
@@ -2227,7 +2249,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
 	ndm->ndm_pad1    = 0;
 	ndm->ndm_pad2    = 0;
 	ndm->ndm_flags	 = pn->flags | NTF_PROXY;
-	ndm->ndm_type	 = NDA_DST;
+	ndm->ndm_type	 = RTN_UNICAST;
 	ndm->ndm_ifindex = pn->dev->ifindex;
 	ndm->ndm_state	 = NUD_NONE;
 
@@ -2850,7 +2872,7 @@ static void neigh_proc_update(struct ctl_table *ctl, int write)
 {
 	struct net_device *dev = ctl->extra1;
 	struct neigh_parms *p = ctl->extra2;
-	struct net *net = p->net;
+	struct net *net = neigh_parms_net(p);
 	int index = (int *) ctl->data - p->data;
 
 	if (!write)
@@ -3025,7 +3047,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
 	if (!t)
 		goto err;
 
-	for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) {
+	for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) {
 		t->neigh_vars[i].data += (long) p;
 		t->neigh_vars[i].extra1 = dev;
 		t->neigh_vars[i].extra2 = p;
@@ -3037,11 +3059,12 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
 		memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0,
 		       sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL]));
 	} else {
+		struct neigh_table *tbl = p->tbl;
 		dev_name_source = "default";
-		t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = (int *)(p + 1);
-		t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = (int *)(p + 1) + 1;
-		t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = (int *)(p + 1) + 2;
-		t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3;
+		t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = &tbl->gc_interval;
+		t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = &tbl->gc_thresh1;
+		t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = &tbl->gc_thresh2;
+		t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = &tbl->gc_thresh3;
 	}
 
 	if (handler) {
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f3edf9635e0..1cac29ebb05 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -104,6 +104,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
 }
 
 NETDEVICE_SHOW_RO(dev_id, fmt_hex);
+NETDEVICE_SHOW_RO(dev_port, fmt_dec);
 NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec);
 NETDEVICE_SHOW_RO(addr_len, fmt_dec);
 NETDEVICE_SHOW_RO(iflink, fmt_dec);
@@ -252,6 +253,16 @@ static ssize_t operstate_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(operstate);
 
+static ssize_t carrier_changes_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct net_device *netdev = to_net_dev(dev);
+	return sprintf(buf, fmt_dec,
+		       atomic_read(&netdev->carrier_changes));
+}
+static DEVICE_ATTR_RO(carrier_changes);
+
 /* read-write attributes */
 
 static int change_mtu(struct net_device *net, unsigned long new_mtu)
@@ -373,6 +384,7 @@ static struct attribute *net_class_attrs[] = {
 	&dev_attr_netdev_group.attr,
 	&dev_attr_type.attr,
 	&dev_attr_dev_id.attr,
+	&dev_attr_dev_port.attr,
 	&dev_attr_iflink.attr,
 	&dev_attr_ifindex.attr,
 	&dev_attr_addr_assign_type.attr,
@@ -384,6 +396,7 @@ static struct attribute *net_class_attrs[] = {
 	&dev_attr_duplex.attr,
 	&dev_attr_dormant.attr,
 	&dev_attr_operstate.attr,
+	&dev_attr_carrier_changes.attr,
 	&dev_attr_ifalias.attr,
 	&dev_attr_carrier.attr,
 	&dev_attr_mtu.attr,
@@ -498,17 +511,7 @@ static struct attribute_group wireless_group = {
 #define net_class_groups	NULL
 #endif /* CONFIG_SYSFS */
 
-#ifdef CONFIG_RPS
-/*
- * RX queue sysfs structures and functions.
- */
-struct rx_queue_attribute {
-	struct attribute attr;
-	ssize_t (*show)(struct netdev_rx_queue *queue,
-	    struct rx_queue_attribute *attr, char *buf);
-	ssize_t (*store)(struct netdev_rx_queue *queue,
-	    struct rx_queue_attribute *attr, const char *buf, size_t len);
-};
+#ifdef CONFIG_SYSFS
 #define to_rx_queue_attr(_attr) container_of(_attr,		\
     struct rx_queue_attribute, attr)
 
@@ -543,6 +546,7 @@ static const struct sysfs_ops rx_queue_sysfs_ops = {
 	.store = rx_queue_attr_store,
 };
 
+#ifdef CONFIG_RPS
 static ssize_t show_rps_map(struct netdev_rx_queue *queue,
 			    struct rx_queue_attribute *attribute, char *buf)
 {
@@ -676,8 +680,8 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue,
 		while ((mask | (mask >> 1)) != mask)
 			mask |= (mask >> 1);
 		/* On 64 bit arches, must check mask fits in table->mask (u32),
-		 * and on 32bit arches, must check RPS_DEV_FLOW_TABLE_SIZE(mask + 1)
-		 * doesnt overflow.
+		 * and on 32bit arches, must check
+		 * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow.
 		 */
 #if BITS_PER_LONG > 32
 		if (mask > (unsigned long)(u32)mask)
@@ -718,16 +722,20 @@ static struct rx_queue_attribute rps_cpus_attribute =
 static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute =
 	__ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR,
 	    show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt);
+#endif /* CONFIG_RPS */
 
 static struct attribute *rx_queue_default_attrs[] = {
+#ifdef CONFIG_RPS
 	&rps_cpus_attribute.attr,
 	&rps_dev_flow_table_cnt_attribute.attr,
+#endif
 	NULL
 };
 
 static void rx_queue_release(struct kobject *kobj)
 {
 	struct netdev_rx_queue *queue = to_rx_queue(kobj);
+#ifdef CONFIG_RPS
 	struct rps_map *map;
 	struct rps_dev_flow_table *flow_table;
 
@@ -743,15 +751,29 @@ static void rx_queue_release(struct kobject *kobj)
 		RCU_INIT_POINTER(queue->rps_flow_table, NULL);
 		call_rcu(&flow_table->rcu, rps_dev_flow_table_release);
 	}
+#endif
 
 	memset(kobj, 0, sizeof(*kobj));
 	dev_put(queue->dev);
 }
 
+static const void *rx_queue_namespace(struct kobject *kobj)
+{
+	struct netdev_rx_queue *queue = to_rx_queue(kobj);
+	struct device *dev = &queue->dev->dev;
+	const void *ns = NULL;
+
+	if (dev->class && dev->class->ns_type)
+		ns = dev->class->namespace(dev);
+
+	return ns;
+}
+
 static struct kobj_type rx_queue_ktype = {
 	.sysfs_ops = &rx_queue_sysfs_ops,
 	.release = rx_queue_release,
 	.default_attrs = rx_queue_default_attrs,
+	.namespace = rx_queue_namespace
 };
 
 static int rx_queue_add_kobject(struct net_device *net, int index)
@@ -763,25 +785,36 @@ static int rx_queue_add_kobject(struct net_device *net, int index)
 	kobj->kset = net->queues_kset;
 	error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL,
 	    "rx-%u", index);
-	if (error) {
-		kobject_put(kobj);
-		return error;
+	if (error)
+		goto exit;
+
+	if (net->sysfs_rx_queue_group) {
+		error = sysfs_create_group(kobj, net->sysfs_rx_queue_group);
+		if (error)
+			goto exit;
 	}
 
 	kobject_uevent(kobj, KOBJ_ADD);
 	dev_hold(queue->dev);
 
 	return error;
+exit:
+	kobject_put(kobj);
+	return error;
 }
-#endif /* CONFIG_RPS */
+#endif /* CONFIG_SYSFS */
 
 int
 net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num)
 {
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	int i;
 	int error = 0;
 
+#ifndef CONFIG_RPS
+	if (!net->sysfs_rx_queue_group)
+		return 0;
+#endif
 	for (i = old_num; i < new_num; i++) {
 		error = rx_queue_add_kobject(net, i);
 		if (error) {
@@ -790,8 +823,12 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num)
 		}
 	}
 
-	while (--i >= new_num)
+	while (--i >= new_num) {
+		if (net->sysfs_rx_queue_group)
+			sysfs_remove_group(&net->_rx[i].kobj,
+					   net->sysfs_rx_queue_group);
 		kobject_put(&net->_rx[i].kobj);
+	}
 
 	return error;
 #else
@@ -972,15 +1009,12 @@ static struct attribute_group dql_group = {
 #endif /* CONFIG_BQL */
 
 #ifdef CONFIG_XPS
-static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
+static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
 {
 	struct net_device *dev = queue->dev;
-	int i;
-
-	for (i = 0; i < dev->num_tx_queues; i++)
-		if (queue == &dev->_tx[i])
-			break;
+	unsigned int i;
 
+	i = queue - dev->_tx;
 	BUG_ON(i >= dev->num_tx_queues);
 
 	return i;
@@ -1082,10 +1116,23 @@ static void netdev_queue_release(struct kobject *kobj)
 	dev_put(queue->dev);
 }
 
+static const void *netdev_queue_namespace(struct kobject *kobj)
+{
+	struct netdev_queue *queue = to_netdev_queue(kobj);
+	struct device *dev = &queue->dev->dev;
+	const void *ns = NULL;
+
+	if (dev->class && dev->class->ns_type)
+		ns = dev->class->namespace(dev);
+
+	return ns;
+}
+
 static struct kobj_type netdev_queue_ktype = {
 	.sysfs_ops = &netdev_queue_sysfs_ops,
 	.release = netdev_queue_release,
 	.default_attrs = netdev_queue_default_attrs,
+	.namespace = netdev_queue_namespace,
 };
 
 static int netdev_queue_add_kobject(struct net_device *net, int index)
@@ -1155,9 +1202,6 @@ static int register_queue_kobjects(struct net_device *net)
 	    NULL, &net->dev.kobj);
 	if (!net->queues_kset)
 		return -ENOMEM;
-#endif
-
-#ifdef CONFIG_RPS
 	real_rx = net->real_num_rx_queues;
 #endif
 	real_tx = net->real_num_tx_queues;
@@ -1184,7 +1228,7 @@ static void remove_queue_kobjects(struct net_device *net)
 {
 	int real_rx = 0, real_tx = 0;
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	real_rx = net->real_num_rx_queues;
 #endif
 	real_tx = net->real_num_tx_queues;
@@ -1358,7 +1402,7 @@ void netdev_class_remove_file_ns(struct class_attribute *class_attr,
 }
 EXPORT_SYMBOL(netdev_class_remove_file_ns);
 
-int netdev_kobject_init(void)
+int __init netdev_kobject_init(void)
 {
 	kobj_ns_type_register(&net_ns_type_operations);
 	return class_register(&net_class);
diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h
index bd7751ec1c4..2745a1b51e0 100644
--- a/net/core/net-sysfs.h
+++ b/net/core/net-sysfs.h
@@ -1,7 +1,7 @@
 #ifndef __NET_SYSFS_H__
 #define __NET_SYSFS_H__
 
-int netdev_kobject_init(void);
+int __init netdev_kobject_init(void);
 int netdev_register_kobject(struct net_device *);
 void netdev_unregister_kobject(struct net_device *);
 int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 81d3a9a0845..85b62691f4f 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -24,7 +24,7 @@
 
 static LIST_HEAD(pernet_list);
 static struct list_head *first_device = &pernet_list;
-static DEFINE_MUTEX(net_mutex);
+DEFINE_MUTEX(net_mutex);
 
 LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
@@ -273,7 +273,7 @@ static void cleanup_net(struct work_struct *work)
 {
 	const struct pernet_operations *ops;
 	struct net *net, *tmp;
-	LIST_HEAD(net_kill_list);
+	struct list_head net_kill_list;
 	LIST_HEAD(net_exit_list);
 
 	/* Atomically snapshot the list of namespaces to cleanup */
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
new file mode 100644
index 00000000000..30d903b19c6
--- /dev/null
+++ b/net/core/netclassid_cgroup.c
@@ -0,0 +1,111 @@
+/*
+ * net/core/netclassid_cgroup.c	Classid Cgroupfs Handling
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/cgroup.h>
+#include <linux/fdtable.h>
+#include <net/cls_cgroup.h>
+#include <net/sock.h>
+
+static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct cgroup_cls_state, css) : NULL;
+}
+
+struct cgroup_cls_state *task_cls_state(struct task_struct *p)
+{
+	return css_cls_state(task_css(p, net_cls_cgrp_id));
+}
+EXPORT_SYMBOL_GPL(task_cls_state);
+
+static struct cgroup_subsys_state *
+cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct cgroup_cls_state *cs;
+
+	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
+	if (!cs)
+		return ERR_PTR(-ENOMEM);
+
+	return &cs->css;
+}
+
+static int cgrp_css_online(struct cgroup_subsys_state *css)
+{
+	struct cgroup_cls_state *cs = css_cls_state(css);
+	struct cgroup_cls_state *parent = css_cls_state(css->parent);
+
+	if (parent)
+		cs->classid = parent->classid;
+
+	return 0;
+}
+
+static void cgrp_css_free(struct cgroup_subsys_state *css)
+{
+	kfree(css_cls_state(css));
+}
+
+static int update_classid(const void *v, struct file *file, unsigned n)
+{
+	int err;
+	struct socket *sock = sock_from_file(file, &err);
+
+	if (sock)
+		sock->sk->sk_classid = (u32)(unsigned long)v;
+
+	return 0;
+}
+
+static void cgrp_attach(struct cgroup_subsys_state *css,
+			struct cgroup_taskset *tset)
+{
+	struct cgroup_cls_state *cs = css_cls_state(css);
+	void *v = (void *)(unsigned long)cs->classid;
+	struct task_struct *p;
+
+	cgroup_taskset_for_each(p, tset) {
+		task_lock(p);
+		iterate_fd(p->files, 0, update_classid, v);
+		task_unlock(p);
+	}
+}
+
+static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	return css_cls_state(css)->classid;
+}
+
+static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
+			 u64 value)
+{
+	css_cls_state(css)->classid = (u32) value;
+
+	return 0;
+}
+
+static struct cftype ss_files[] = {
+	{
+		.name		= "classid",
+		.read_u64	= read_classid,
+		.write_u64	= write_classid,
+	},
+	{ }	/* terminate */
+};
+
+struct cgroup_subsys net_cls_cgrp_subsys = {
+	.css_alloc		= cgrp_css_alloc,
+	.css_online		= cgrp_css_online,
+	.css_free		= cgrp_css_free,
+	.attach			= cgrp_attach,
+	.base_cftypes		= ss_files,
+};
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 8f971990677..e33937fb32a 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -46,13 +46,9 @@
 
 static struct sk_buff_head skb_pool;
 
-static atomic_t trapped;
-
 DEFINE_STATIC_SRCU(netpoll_srcu);
 
 #define USEC_PER_POLL	50
-#define NETPOLL_RX_ENABLED  1
-#define NETPOLL_RX_DROP     2
 
 #define MAX_SKB_SIZE							\
 	(sizeof(struct ethhdr) +					\
@@ -61,7 +57,6 @@ DEFINE_STATIC_SRCU(netpoll_srcu);
 	 MAX_UDP_CHUNK)
 
 static void zap_completion_queue(void);
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
 static void netpoll_async_cleanup(struct work_struct *work);
 
 static unsigned int carrier_timeout = 4;
@@ -74,6 +69,37 @@ module_param(carrier_timeout, uint, 0644);
 #define np_notice(np, fmt, ...)				\
 	pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
 
+static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
+			      struct netdev_queue *txq)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	int status = NETDEV_TX_OK;
+	netdev_features_t features;
+
+	features = netif_skb_features(skb);
+
+	if (vlan_tx_tag_present(skb) &&
+	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
+		skb = __vlan_put_tag(skb, skb->vlan_proto,
+				     vlan_tx_tag_get(skb));
+		if (unlikely(!skb)) {
+			/* This is actually a packet drop, but we
+			 * don't want the code that calls this
+			 * function to try and operate on a NULL skb.
+			 */
+			goto out;
+		}
+		skb->vlan_tci = 0;
+	}
+
+	status = ops->ndo_start_xmit(skb, dev);
+	if (status == NETDEV_TX_OK)
+		txq_trans_update(txq);
+
+out:
+	return status;
+}
+
 static void queue_process(struct work_struct *work)
 {
 	struct netpoll_info *npinfo =
@@ -83,51 +109,31 @@ static void queue_process(struct work_struct *work)
 
 	while ((skb = skb_dequeue(&npinfo->txq))) {
 		struct net_device *dev = skb->dev;
-		const struct net_device_ops *ops = dev->netdev_ops;
 		struct netdev_queue *txq;
 
 		if (!netif_device_present(dev) || !netif_running(dev)) {
-			__kfree_skb(skb);
+			kfree_skb(skb);
 			continue;
 		}
 
 		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
 
 		local_irq_save(flags);
-		__netif_tx_lock(txq, smp_processor_id());
+		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (netif_xmit_frozen_or_stopped(txq) ||
-		    ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) {
+		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
 			skb_queue_head(&npinfo->txq, skb);
-			__netif_tx_unlock(txq);
+			HARD_TX_UNLOCK(dev, txq);
 			local_irq_restore(flags);
 
 			schedule_delayed_work(&npinfo->tx_work, HZ/10);
 			return;
 		}
-		__netif_tx_unlock(txq);
+		HARD_TX_UNLOCK(dev, txq);
 		local_irq_restore(flags);
 	}
 }
 
-static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
-			    unsigned short ulen, __be32 saddr, __be32 daddr)
-{
-	__wsum psum;
-
-	if (uh->check == 0 || skb_csum_unnecessary(skb))
-		return 0;
-
-	psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
-
-	if (skb->ip_summed == CHECKSUM_COMPLETE &&
-	    !csum_fold(csum_add(psum, skb->csum)))
-		return 0;
-
-	skb->csum = psum;
-
-	return __skb_checksum_complete(skb);
-}
-
 /*
  * Check whether delayed processing was scheduled for our NIC. If so,
  * we attempt to grab the poll lock and use ->poll() to pump the card.
@@ -138,14 +144,8 @@ static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
  * trylock here and interrupts are already disabled in the softirq
  * case. Further, we test the poll_owner to avoid recursion on UP
  * systems where the lock doesn't exist.
- *
- * In cases where there is bi-directional communications, reading only
- * one message at a time can lead to packets being dropped by the
- * network adapter, forcing superfluous retries and possibly timeouts.
- * Thus, we set our budget to greater than 1.
  */
-static int poll_one_napi(struct netpoll_info *npinfo,
-			 struct napi_struct *napi, int budget)
+static int poll_one_napi(struct napi_struct *napi, int budget)
 {
 	int work;
 
@@ -156,52 +156,35 @@ static int poll_one_napi(struct netpoll_info *npinfo,
 	if (!test_bit(NAPI_STATE_SCHED, &napi->state))
 		return budget;
 
-	npinfo->rx_flags |= NETPOLL_RX_DROP;
-	atomic_inc(&trapped);
 	set_bit(NAPI_STATE_NPSVC, &napi->state);
 
 	work = napi->poll(napi, budget);
+	WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
 	trace_napi_poll(napi);
 
 	clear_bit(NAPI_STATE_NPSVC, &napi->state);
-	atomic_dec(&trapped);
-	npinfo->rx_flags &= ~NETPOLL_RX_DROP;
 
 	return budget - work;
 }
 
-static void poll_napi(struct net_device *dev)
+static void poll_napi(struct net_device *dev, int budget)
 {
 	struct napi_struct *napi;
-	int budget = 16;
 
 	list_for_each_entry(napi, &dev->napi_list, dev_list) {
 		if (napi->poll_owner != smp_processor_id() &&
 		    spin_trylock(&napi->poll_lock)) {
-			budget = poll_one_napi(rcu_dereference_bh(dev->npinfo),
-					       napi, budget);
+			budget = poll_one_napi(napi, budget);
 			spin_unlock(&napi->poll_lock);
-
-			if (!budget)
-				break;
 		}
 	}
 }
 
-static void service_neigh_queue(struct netpoll_info *npi)
-{
-	if (npi) {
-		struct sk_buff *skb;
-
-		while ((skb = skb_dequeue(&npi->neigh_tx)))
-			netpoll_neigh_reply(skb, npi);
-	}
-}
-
 static void netpoll_poll_dev(struct net_device *dev)
 {
 	const struct net_device_ops *ops;
 	struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
+	int budget = 0;
 
 	/* Don't do any rx activity if the dev_lock mutex is held
 	 * the dev_open/close paths use this to block netpoll activity
@@ -224,31 +207,14 @@ static void netpoll_poll_dev(struct net_device *dev)
 	/* Process pending work on NIC */
 	ops->ndo_poll_controller(dev);
 
-	poll_napi(dev);
+	poll_napi(dev, budget);
 
 	up(&ni->dev_lock);
 
-	if (dev->flags & IFF_SLAVE) {
-		if (ni) {
-			struct net_device *bond_dev;
-			struct sk_buff *skb;
-			struct netpoll_info *bond_ni;
-
-			bond_dev = netdev_master_upper_dev_get_rcu(dev);
-			bond_ni = rcu_dereference_bh(bond_dev->npinfo);
-			while ((skb = skb_dequeue(&ni->neigh_tx))) {
-				skb->dev = bond_dev;
-				skb_queue_tail(&bond_ni->neigh_tx, skb);
-			}
-		}
-	}
-
-	service_neigh_queue(ni);
-
 	zap_completion_queue();
 }
 
-void netpoll_rx_disable(struct net_device *dev)
+void netpoll_poll_disable(struct net_device *dev)
 {
 	struct netpoll_info *ni;
 	int idx;
@@ -259,9 +225,9 @@ void netpoll_rx_disable(struct net_device *dev)
 		down(&ni->dev_lock);
 	srcu_read_unlock(&netpoll_srcu, idx);
 }
-EXPORT_SYMBOL(netpoll_rx_disable);
+EXPORT_SYMBOL(netpoll_poll_disable);
 
-void netpoll_rx_enable(struct net_device *dev)
+void netpoll_poll_enable(struct net_device *dev)
 {
 	struct netpoll_info *ni;
 	rcu_read_lock();
@@ -270,7 +236,7 @@ void netpoll_rx_enable(struct net_device *dev)
 		up(&ni->dev_lock);
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(netpoll_rx_enable);
+EXPORT_SYMBOL(netpoll_poll_enable);
 
 static void refill_skbs(void)
 {
@@ -304,7 +270,7 @@ static void zap_completion_queue(void)
 		while (clist != NULL) {
 			struct sk_buff *skb = clist;
 			clist = clist->next;
-			if (skb->destructor) {
+			if (!skb_irq_freeable(skb)) {
 				atomic_inc(&skb->users);
 				dev_kfree_skb_any(skb); /* put this one back */
 			} else {
@@ -359,7 +325,6 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 {
 	int status = NETDEV_TX_BUSY;
 	unsigned long tries;
-	const struct net_device_ops *ops = dev->netdev_ops;
 	/* It is up to the caller to keep npinfo alive. */
 	struct netpoll_info *npinfo;
 
@@ -367,7 +332,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 
 	npinfo = rcu_dereference_bh(np->dev->npinfo);
 	if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
-		__kfree_skb(skb);
+		dev_kfree_skb_irq(skb);
 		return;
 	}
 
@@ -375,27 +340,16 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 	if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
 		struct netdev_queue *txq;
 
-		txq = netdev_pick_tx(dev, skb);
+		txq = netdev_pick_tx(dev, skb, NULL);
 
 		/* try until next clock tick */
 		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
 		     tries > 0; --tries) {
-			if (__netif_tx_trylock(txq)) {
-				if (!netif_xmit_stopped(txq)) {
-					if (vlan_tx_tag_present(skb) &&
-					    !vlan_hw_offload_capable(netif_skb_features(skb),
-								     skb->vlan_proto)) {
-						skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
-						if (unlikely(!skb))
-							break;
-						skb->vlan_tci = 0;
-					}
-
-					status = ops->ndo_start_xmit(skb, dev);
-					if (status == NETDEV_TX_OK)
-						txq_trans_update(txq);
-				}
-				__netif_tx_unlock(txq);
+			if (HARD_TX_TRYLOCK(dev, txq)) {
+				if (!netif_xmit_stopped(txq))
+					status = netpoll_start_xmit(skb, dev, txq);
+
+				HARD_TX_UNLOCK(dev, txq);
 
 				if (status == NETDEV_TX_OK)
 					break;
@@ -410,7 +364,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 
 		WARN_ONCE(!irqs_disabled(),
 			"netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
-			dev->name, ops->ndo_start_xmit);
+			dev->name, dev->netdev_ops->ndo_start_xmit);
 
 	}
 
@@ -513,8 +467,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 		skb->protocol = eth->h_proto = htons(ETH_P_IP);
 	}
 
-	memcpy(eth->h_source, np->dev->dev_addr, ETH_ALEN);
-	memcpy(eth->h_dest, np->remote_mac, ETH_ALEN);
+	ether_addr_copy(eth->h_source, np->dev->dev_addr);
+	ether_addr_copy(eth->h_dest, np->remote_mac);
 
 	skb->dev = np->dev;
 
@@ -522,384 +476,6 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 }
 EXPORT_SYMBOL(netpoll_send_udp);
 
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
-{
-	int size, type = ARPOP_REPLY;
-	__be32 sip, tip;
-	unsigned char *sha;
-	struct sk_buff *send_skb;
-	struct netpoll *np, *tmp;
-	unsigned long flags;
-	int hlen, tlen;
-	int hits = 0, proto;
-
-	if (list_empty(&npinfo->rx_np))
-		return;
-
-	/* Before checking the packet, we do some early
-	   inspection whether this is interesting at all */
-	spin_lock_irqsave(&npinfo->rx_lock, flags);
-	list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
-		if (np->dev == skb->dev)
-			hits++;
-	}
-	spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-
-	/* No netpoll struct is using this dev */
-	if (!hits)
-		return;
-
-	proto = ntohs(eth_hdr(skb)->h_proto);
-	if (proto == ETH_P_ARP) {
-		struct arphdr *arp;
-		unsigned char *arp_ptr;
-		/* No arp on this interface */
-		if (skb->dev->flags & IFF_NOARP)
-			return;
-
-		if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
-			return;
-
-		skb_reset_network_header(skb);
-		skb_reset_transport_header(skb);
-		arp = arp_hdr(skb);
-
-		if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
-		     arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
-		    arp->ar_pro != htons(ETH_P_IP) ||
-		    arp->ar_op != htons(ARPOP_REQUEST))
-			return;
-
-		arp_ptr = (unsigned char *)(arp+1);
-		/* save the location of the src hw addr */
-		sha = arp_ptr;
-		arp_ptr += skb->dev->addr_len;
-		memcpy(&sip, arp_ptr, 4);
-		arp_ptr += 4;
-		/* If we actually cared about dst hw addr,
-		   it would get copied here */
-		arp_ptr += skb->dev->addr_len;
-		memcpy(&tip, arp_ptr, 4);
-
-		/* Should we ignore arp? */
-		if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
-			return;
-
-		size = arp_hdr_len(skb->dev);
-
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
-			if (tip != np->local_ip.ip)
-				continue;
-
-			hlen = LL_RESERVED_SPACE(np->dev);
-			tlen = np->dev->needed_tailroom;
-			send_skb = find_skb(np, size + hlen + tlen, hlen);
-			if (!send_skb)
-				continue;
-
-			skb_reset_network_header(send_skb);
-			arp = (struct arphdr *) skb_put(send_skb, size);
-			send_skb->dev = skb->dev;
-			send_skb->protocol = htons(ETH_P_ARP);
-
-			/* Fill the device header for the ARP frame */
-			if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP,
-					    sha, np->dev->dev_addr,
-					    send_skb->len) < 0) {
-				kfree_skb(send_skb);
-				continue;
-			}
-
-			/*
-			 * Fill out the arp protocol part.
-			 *
-			 * we only support ethernet device type,
-			 * which (according to RFC 1390) should
-			 * always equal 1 (Ethernet).
-			 */
-
-			arp->ar_hrd = htons(np->dev->type);
-			arp->ar_pro = htons(ETH_P_IP);
-			arp->ar_hln = np->dev->addr_len;
-			arp->ar_pln = 4;
-			arp->ar_op = htons(type);
-
-			arp_ptr = (unsigned char *)(arp + 1);
-			memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
-			arp_ptr += np->dev->addr_len;
-			memcpy(arp_ptr, &tip, 4);
-			arp_ptr += 4;
-			memcpy(arp_ptr, sha, np->dev->addr_len);
-			arp_ptr += np->dev->addr_len;
-			memcpy(arp_ptr, &sip, 4);
-
-			netpoll_send_skb(np, send_skb);
-
-			/* If there are several rx_skb_hooks for the same
-			 * address we're fine by sending a single reply
-			 */
-			break;
-		}
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-	} else if( proto == ETH_P_IPV6) {
-#if IS_ENABLED(CONFIG_IPV6)
-		struct nd_msg *msg;
-		u8 *lladdr = NULL;
-		struct ipv6hdr *hdr;
-		struct icmp6hdr *icmp6h;
-		const struct in6_addr *saddr;
-		const struct in6_addr *daddr;
-		struct inet6_dev *in6_dev = NULL;
-		struct in6_addr *target;
-
-		in6_dev = in6_dev_get(skb->dev);
-		if (!in6_dev || !in6_dev->cnf.accept_ra)
-			return;
-
-		if (!pskb_may_pull(skb, skb->len))
-			return;
-
-		msg = (struct nd_msg *)skb_transport_header(skb);
-
-		__skb_push(skb, skb->data - skb_transport_header(skb));
-
-		if (ipv6_hdr(skb)->hop_limit != 255)
-			return;
-		if (msg->icmph.icmp6_code != 0)
-			return;
-		if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
-			return;
-
-		saddr = &ipv6_hdr(skb)->saddr;
-		daddr = &ipv6_hdr(skb)->daddr;
-
-		size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr);
-
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
-			if (!ipv6_addr_equal(daddr, &np->local_ip.in6))
-				continue;
-
-			hlen = LL_RESERVED_SPACE(np->dev);
-			tlen = np->dev->needed_tailroom;
-			send_skb = find_skb(np, size + hlen + tlen, hlen);
-			if (!send_skb)
-				continue;
-
-			send_skb->protocol = htons(ETH_P_IPV6);
-			send_skb->dev = skb->dev;
-
-			skb_reset_network_header(send_skb);
-			hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr));
-			*(__be32*)hdr = htonl(0x60000000);
-			hdr->payload_len = htons(size);
-			hdr->nexthdr = IPPROTO_ICMPV6;
-			hdr->hop_limit = 255;
-			hdr->saddr = *saddr;
-			hdr->daddr = *daddr;
-
-			icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr));
-			icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
-			icmp6h->icmp6_router = 0;
-			icmp6h->icmp6_solicited = 1;
-
-			target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr));
-			*target = msg->target;
-			icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size,
-							      IPPROTO_ICMPV6,
-							      csum_partial(icmp6h,
-									   size, 0));
-
-			if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6,
-					    lladdr, np->dev->dev_addr,
-					    send_skb->len) < 0) {
-				kfree_skb(send_skb);
-				continue;
-			}
-
-			netpoll_send_skb(np, send_skb);
-
-			/* If there are several rx_skb_hooks for the same
-			 * address, we're fine by sending a single reply
-			 */
-			break;
-		}
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-#endif
-	}
-}
-
-static bool pkt_is_ns(struct sk_buff *skb)
-{
-	struct nd_msg *msg;
-	struct ipv6hdr *hdr;
-
-	if (skb->protocol != htons(ETH_P_ARP))
-		return false;
-	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
-		return false;
-
-	msg = (struct nd_msg *)skb_transport_header(skb);
-	__skb_push(skb, skb->data - skb_transport_header(skb));
-	hdr = ipv6_hdr(skb);
-
-	if (hdr->nexthdr != IPPROTO_ICMPV6)
-		return false;
-	if (hdr->hop_limit != 255)
-		return false;
-	if (msg->icmph.icmp6_code != 0)
-		return false;
-	if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
-		return false;
-
-	return true;
-}
-
-int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
-{
-	int proto, len, ulen, data_len;
-	int hits = 0, offset;
-	const struct iphdr *iph;
-	struct udphdr *uh;
-	struct netpoll *np, *tmp;
-	uint16_t source;
-
-	if (list_empty(&npinfo->rx_np))
-		goto out;
-
-	if (skb->dev->type != ARPHRD_ETHER)
-		goto out;
-
-	/* check if netpoll clients need ARP */
-	if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) {
-		skb_queue_tail(&npinfo->neigh_tx, skb);
-		return 1;
-	} else if (pkt_is_ns(skb) && atomic_read(&trapped)) {
-		skb_queue_tail(&npinfo->neigh_tx, skb);
-		return 1;
-	}
-
-	if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
-		skb = vlan_untag(skb);
-		if (unlikely(!skb))
-			goto out;
-	}
-
-	proto = ntohs(eth_hdr(skb)->h_proto);
-	if (proto != ETH_P_IP && proto != ETH_P_IPV6)
-		goto out;
-	if (skb->pkt_type == PACKET_OTHERHOST)
-		goto out;
-	if (skb_shared(skb))
-		goto out;
-
-	if (proto == ETH_P_IP) {
-		if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-			goto out;
-		iph = (struct iphdr *)skb->data;
-		if (iph->ihl < 5 || iph->version != 4)
-			goto out;
-		if (!pskb_may_pull(skb, iph->ihl*4))
-			goto out;
-		iph = (struct iphdr *)skb->data;
-		if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
-			goto out;
-
-		len = ntohs(iph->tot_len);
-		if (skb->len < len || len < iph->ihl*4)
-			goto out;
-
-		/*
-		 * Our transport medium may have padded the buffer out.
-		 * Now We trim to the true length of the frame.
-		 */
-		if (pskb_trim_rcsum(skb, len))
-			goto out;
-
-		iph = (struct iphdr *)skb->data;
-		if (iph->protocol != IPPROTO_UDP)
-			goto out;
-
-		len -= iph->ihl*4;
-		uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
-		offset = (unsigned char *)(uh + 1) - skb->data;
-		ulen = ntohs(uh->len);
-		data_len = skb->len - offset;
-		source = ntohs(uh->source);
-
-		if (ulen != len)
-			goto out;
-		if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
-			goto out;
-		list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
-			if (np->local_ip.ip && np->local_ip.ip != iph->daddr)
-				continue;
-			if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr)
-				continue;
-			if (np->local_port && np->local_port != ntohs(uh->dest))
-				continue;
-
-			np->rx_skb_hook(np, source, skb, offset, data_len);
-			hits++;
-		}
-	} else {
-#if IS_ENABLED(CONFIG_IPV6)
-		const struct ipv6hdr *ip6h;
-
-		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
-			goto out;
-		ip6h = (struct ipv6hdr *)skb->data;
-		if (ip6h->version != 6)
-			goto out;
-		len = ntohs(ip6h->payload_len);
-		if (!len)
-			goto out;
-		if (len + sizeof(struct ipv6hdr) > skb->len)
-			goto out;
-		if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr)))
-			goto out;
-		ip6h = ipv6_hdr(skb);
-		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
-			goto out;
-		uh = udp_hdr(skb);
-		offset = (unsigned char *)(uh + 1) - skb->data;
-		ulen = ntohs(uh->len);
-		data_len = skb->len - offset;
-		source = ntohs(uh->source);
-		if (ulen != skb->len)
-			goto out;
-		if (udp6_csum_init(skb, uh, IPPROTO_UDP))
-			goto out;
-		list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
-			if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr))
-				continue;
-			if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr))
-				continue;
-			if (np->local_port && np->local_port != ntohs(uh->dest))
-				continue;
-
-			np->rx_skb_hook(np, source, skb, offset, data_len);
-			hits++;
-		}
-#endif
-	}
-
-	if (!hits)
-		goto out;
-
-	kfree_skb(skb);
-	return 1;
-
-out:
-	if (atomic_read(&trapped)) {
-		kfree_skb(skb);
-		return 1;
-	}
-
-	return 0;
-}
-
 void netpoll_print_options(struct netpoll *np)
 {
 	np_info(np, "local port %d\n", np->local_port);
@@ -941,6 +517,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 {
 	char *cur=opt, *delim;
 	int ipv6;
+	bool ipversion_set = false;
 
 	if (*cur != '@') {
 		if ((delim = strchr(cur, '@')) == NULL)
@@ -953,6 +530,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 	cur++;
 
 	if (*cur != '/') {
+		ipversion_set = true;
 		if ((delim = strchr(cur, '/')) == NULL)
 			goto parse_failed;
 		*delim = 0;
@@ -995,7 +573,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 	ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
 	if (ipv6 < 0)
 		goto parse_failed;
-	else if (np->ipv6 != (bool)ipv6)
+	else if (ipversion_set && np->ipv6 != (bool)ipv6)
 		goto parse_failed;
 	else
 		np->ipv6 = (bool)ipv6;
@@ -1017,11 +595,10 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 }
 EXPORT_SYMBOL(netpoll_parse_options);
 
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 {
 	struct netpoll_info *npinfo;
 	const struct net_device_ops *ops;
-	unsigned long flags;
 	int err;
 
 	np->dev = ndev;
@@ -1037,18 +614,13 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 	}
 
 	if (!ndev->npinfo) {
-		npinfo = kmalloc(sizeof(*npinfo), gfp);
+		npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
 		if (!npinfo) {
 			err = -ENOMEM;
 			goto out;
 		}
 
-		npinfo->rx_flags = 0;
-		INIT_LIST_HEAD(&npinfo->rx_np);
-
-		spin_lock_init(&npinfo->rx_lock);
 		sema_init(&npinfo->dev_lock, 1);
-		skb_queue_head_init(&npinfo->neigh_tx);
 		skb_queue_head_init(&npinfo->txq);
 		INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
 
@@ -1056,7 +628,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 
 		ops = np->dev->netdev_ops;
 		if (ops->ndo_netpoll_setup) {
-			err = ops->ndo_netpoll_setup(ndev, npinfo, gfp);
+			err = ops->ndo_netpoll_setup(ndev, npinfo);
 			if (err)
 				goto free_npinfo;
 		}
@@ -1067,13 +639,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 
 	npinfo->netpoll = np;
 
-	if (np->rx_skb_hook) {
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		npinfo->rx_flags |= NETPOLL_RX_ENABLED;
-		list_add_tail(&np->rx, &npinfo->rx_np);
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-	}
-
 	/* last thing to do is link it to the net device structure */
 	rcu_assign_pointer(ndev->npinfo, npinfo);
 
@@ -1195,7 +760,7 @@ int netpoll_setup(struct netpoll *np)
 	/* fill up the skb queue */
 	refill_skbs();
 
-	err = __netpoll_setup(np, ndev, GFP_KERNEL);
+	err = __netpoll_setup(np, ndev);
 	if (err)
 		goto put;
 
@@ -1222,7 +787,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
 	struct netpoll_info *npinfo =
 			container_of(rcu_head, struct netpoll_info, rcu);
 
-	skb_queue_purge(&npinfo->neigh_tx);
 	skb_queue_purge(&npinfo->txq);
 
 	/* we can't call cancel_delayed_work_sync here, as we are in softirq */
@@ -1238,7 +802,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
 void __netpoll_cleanup(struct netpoll *np)
 {
 	struct netpoll_info *npinfo;
-	unsigned long flags;
 
 	/* rtnl_dereference would be preferable here but
 	 * rcu_cleanup_netpoll path can put us in here safely without
@@ -1248,14 +811,6 @@ void __netpoll_cleanup(struct netpoll *np)
 	if (!npinfo)
 		return;
 
-	if (!list_empty(&npinfo->rx_np)) {
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		list_del(&np->rx);
-		if (list_empty(&npinfo->rx_np))
-			npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-	}
-
 	synchronize_srcu(&netpoll_srcu);
 
 	if (atomic_dec_and_test(&npinfo->refcnt)) {
@@ -1265,7 +820,7 @@ void __netpoll_cleanup(struct netpoll *np)
 		if (ops->ndo_netpoll_cleanup)
 			ops->ndo_netpoll_cleanup(np->dev);
 
-		rcu_assign_pointer(np->dev->npinfo, NULL);
+		RCU_INIT_POINTER(np->dev->npinfo, NULL);
 		call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
 	}
 }
@@ -1299,18 +854,3 @@ out:
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(netpoll_cleanup);
-
-int netpoll_trap(void)
-{
-	return atomic_read(&trapped);
-}
-EXPORT_SYMBOL(netpoll_trap);
-
-void netpoll_set_trap(int trap)
-{
-	if (trap)
-		atomic_inc(&trapped);
-	else
-		atomic_dec(&trapped);
-}
-EXPORT_SYMBOL(netpoll_set_trap);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 9b7cf6c85f8..2f385b9bccc 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -30,7 +30,7 @@
 #define PRIOMAP_MIN_SZ		128
 
 /*
- * Extend @dev->priomap so that it's large enough to accomodate
+ * Extend @dev->priomap so that it's large enough to accommodate
  * @target_idx.  @dev->priomap.priomap_len > @target_idx after successful
  * return.  Must be called under rtnl lock.
  */
@@ -140,7 +140,7 @@ cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
 
 static int cgrp_css_online(struct cgroup_subsys_state *css)
 {
-	struct cgroup_subsys_state *parent_css = css_parent(css);
+	struct cgroup_subsys_state *parent_css = css->parent;
 	struct net_device *dev;
 	int ret = 0;
 
@@ -173,27 +173,27 @@ static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft)
 	return css->cgroup->id;
 }
 
-static int read_priomap(struct cgroup_subsys_state *css, struct cftype *cft,
-			struct cgroup_map_cb *cb)
+static int read_priomap(struct seq_file *sf, void *v)
 {
 	struct net_device *dev;
 
 	rcu_read_lock();
 	for_each_netdev_rcu(&init_net, dev)
-		cb->fill(cb, dev->name, netprio_prio(css, dev));
+		seq_printf(sf, "%s %u\n", dev->name,
+			   netprio_prio(seq_css(sf), dev));
 	rcu_read_unlock();
 	return 0;
 }
 
-static int write_priomap(struct cgroup_subsys_state *css, struct cftype *cft,
-			 const char *buffer)
+static ssize_t write_priomap(struct kernfs_open_file *of,
+			     char *buf, size_t nbytes, loff_t off)
 {
 	char devname[IFNAMSIZ + 1];
 	struct net_device *dev;
 	u32 prio;
 	int ret;
 
-	if (sscanf(buffer, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
+	if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
 		return -EINVAL;
 
 	dev = dev_get_by_name(&init_net, devname);
@@ -202,11 +202,11 @@ static int write_priomap(struct cgroup_subsys_state *css, struct cftype *cft,
 
 	rtnl_lock();
 
-	ret = netprio_set_prio(css, dev, prio);
+	ret = netprio_set_prio(of_css(of), dev, prio);
 
 	rtnl_unlock();
 	dev_put(dev);
-	return ret;
+	return ret ?: nbytes;
 }
 
 static int update_netprio(const void *v, struct file *file, unsigned n)
@@ -224,7 +224,7 @@ static void net_prio_attach(struct cgroup_subsys_state *css,
 	struct task_struct *p;
 	void *v = (void *)(unsigned long)css->cgroup->id;
 
-	cgroup_taskset_for_each(p, css, tset) {
+	cgroup_taskset_for_each(p, tset) {
 		task_lock(p);
 		iterate_fd(p->files, 0, update_netprio, v);
 		task_unlock(p);
@@ -238,21 +238,18 @@ static struct cftype ss_files[] = {
 	},
 	{
 		.name = "ifpriomap",
-		.read_map = read_priomap,
-		.write_string = write_priomap,
+		.seq_show = read_priomap,
+		.write = write_priomap,
 	},
 	{ }	/* terminate */
 };
 
-struct cgroup_subsys net_prio_subsys = {
-	.name		= "net_prio",
+struct cgroup_subsys net_prio_cgrp_subsys = {
 	.css_alloc	= cgrp_css_alloc,
 	.css_online	= cgrp_css_online,
 	.css_free	= cgrp_css_free,
 	.attach		= net_prio_attach,
-	.subsys_id	= net_prio_subsys_id,
 	.base_cftypes	= ss_files,
-	.module		= THIS_MODULE,
 };
 
 static int netprio_device_event(struct notifier_block *unused,
@@ -283,37 +280,9 @@ static struct notifier_block netprio_device_notifier = {
 
 static int __init init_cgroup_netprio(void)
 {
-	int ret;
-
-	ret = cgroup_load_subsys(&net_prio_subsys);
-	if (ret)
-		goto out;
-
 	register_netdevice_notifier(&netprio_device_notifier);
-
-out:
-	return ret;
-}
-
-static void __exit exit_cgroup_netprio(void)
-{
-	struct netprio_map *old;
-	struct net_device *dev;
-
-	unregister_netdevice_notifier(&netprio_device_notifier);
-
-	cgroup_unload_subsys(&net_prio_subsys);
-
-	rtnl_lock();
-	for_each_netdev(&init_net, dev) {
-		old = rtnl_dereference(dev->priomap);
-		RCU_INIT_POINTER(dev->priomap, NULL);
-		if (old)
-			kfree_rcu(old, rcu);
-	}
-	rtnl_unlock();
+	return 0;
 }
 
-module_init(init_cgroup_netprio);
-module_exit(exit_cgroup_netprio);
+subsys_initcall(init_cgroup_netprio);
 MODULE_LICENSE("GPL v2");
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index a797fff7f22..fc17a9d309a 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -389,6 +389,9 @@ struct pktgen_dev {
 #ifdef CONFIG_XFRM
 	__u8	ipsmode;		/* IPSEC mode (config) */
 	__u8	ipsproto;		/* IPSEC type (config) */
+	__u32	spi;
+	struct dst_entry dst;
+	struct dst_ops dstops;
 #endif
 	char result[512];
 };
@@ -473,23 +476,22 @@ static int pgctrl_show(struct seq_file *seq, void *v)
 static ssize_t pgctrl_write(struct file *file, const char __user *buf,
 			    size_t count, loff_t *ppos)
 {
-	int err = 0;
 	char data[128];
 	struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id);
 
-	if (!capable(CAP_NET_ADMIN)) {
-		err = -EPERM;
-		goto out;
-	}
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (count == 0)
+		return -EINVAL;
 
 	if (count > sizeof(data))
 		count = sizeof(data);
 
-	if (copy_from_user(data, buf, count)) {
-		err = -EFAULT;
-		goto out;
-	}
-	data[count - 1] = 0;	/* Make string */
+	if (copy_from_user(data, buf, count))
+		return -EFAULT;
+
+	data[count - 1] = 0;	/* Strip trailing '\n' and terminate string */
 
 	if (!strcmp(data, "stop"))
 		pktgen_stop_all_threads_ifs(pn);
@@ -503,10 +505,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf,
 	else
 		pr_warning("Unknown command: %s\n", data);
 
-	err = count;
-
-out:
-	return err;
+	return count;
 }
 
 static int pgctrl_open(struct inode *inode, struct file *file)
@@ -574,7 +573,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 		   is_zero_ether_addr(pkt_dev->src_mac) ?
 			     pkt_dev->odev->dev_addr : pkt_dev->src_mac);
 
-	seq_printf(seq, "dst_mac: ");
+	seq_puts(seq, "dst_mac: ");
 	seq_printf(seq, "%pM\n", pkt_dev->dst_mac);
 
 	seq_printf(seq,
@@ -589,7 +588,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 
 	if (pkt_dev->nr_labels) {
 		unsigned int i;
-		seq_printf(seq, "     mpls: ");
+		seq_puts(seq, "     mpls: ");
 		for (i = 0; i < pkt_dev->nr_labels; i++)
 			seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]),
 				   i == pkt_dev->nr_labels-1 ? "\n" : ", ");
@@ -614,64 +613,67 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 	if (pkt_dev->node >= 0)
 		seq_printf(seq, "     node: %d\n", pkt_dev->node);
 
-	seq_printf(seq, "     Flags: ");
+	seq_puts(seq, "     Flags: ");
 
 	if (pkt_dev->flags & F_IPV6)
-		seq_printf(seq, "IPV6  ");
+		seq_puts(seq, "IPV6  ");
 
 	if (pkt_dev->flags & F_IPSRC_RND)
-		seq_printf(seq, "IPSRC_RND  ");
+		seq_puts(seq, "IPSRC_RND  ");
 
 	if (pkt_dev->flags & F_IPDST_RND)
-		seq_printf(seq, "IPDST_RND  ");
+		seq_puts(seq, "IPDST_RND  ");
 
 	if (pkt_dev->flags & F_TXSIZE_RND)
-		seq_printf(seq, "TXSIZE_RND  ");
+		seq_puts(seq, "TXSIZE_RND  ");
 
 	if (pkt_dev->flags & F_UDPSRC_RND)
-		seq_printf(seq, "UDPSRC_RND  ");
+		seq_puts(seq, "UDPSRC_RND  ");
 
 	if (pkt_dev->flags & F_UDPDST_RND)
-		seq_printf(seq, "UDPDST_RND  ");
+		seq_puts(seq, "UDPDST_RND  ");
 
 	if (pkt_dev->flags & F_UDPCSUM)
-		seq_printf(seq, "UDPCSUM  ");
+		seq_puts(seq, "UDPCSUM  ");
 
 	if (pkt_dev->flags & F_MPLS_RND)
-		seq_printf(seq,  "MPLS_RND  ");
+		seq_puts(seq,  "MPLS_RND  ");
 
 	if (pkt_dev->flags & F_QUEUE_MAP_RND)
-		seq_printf(seq,  "QUEUE_MAP_RND  ");
+		seq_puts(seq,  "QUEUE_MAP_RND  ");
 
 	if (pkt_dev->flags & F_QUEUE_MAP_CPU)
-		seq_printf(seq,  "QUEUE_MAP_CPU  ");
+		seq_puts(seq,  "QUEUE_MAP_CPU  ");
 
 	if (pkt_dev->cflows) {
 		if (pkt_dev->flags & F_FLOW_SEQ)
-			seq_printf(seq,  "FLOW_SEQ  "); /*in sequence flows*/
+			seq_puts(seq,  "FLOW_SEQ  "); /*in sequence flows*/
 		else
-			seq_printf(seq,  "FLOW_RND  ");
+			seq_puts(seq,  "FLOW_RND  ");
 	}
 
 #ifdef CONFIG_XFRM
-	if (pkt_dev->flags & F_IPSEC_ON)
-		seq_printf(seq,  "IPSEC  ");
+	if (pkt_dev->flags & F_IPSEC_ON) {
+		seq_puts(seq,  "IPSEC  ");
+		if (pkt_dev->spi)
+			seq_printf(seq, "spi:%u", pkt_dev->spi);
+	}
 #endif
 
 	if (pkt_dev->flags & F_MACSRC_RND)
-		seq_printf(seq, "MACSRC_RND  ");
+		seq_puts(seq, "MACSRC_RND  ");
 
 	if (pkt_dev->flags & F_MACDST_RND)
-		seq_printf(seq, "MACDST_RND  ");
+		seq_puts(seq, "MACDST_RND  ");
 
 	if (pkt_dev->flags & F_VID_RND)
-		seq_printf(seq, "VID_RND  ");
+		seq_puts(seq, "VID_RND  ");
 
 	if (pkt_dev->flags & F_SVID_RND)
-		seq_printf(seq, "SVID_RND  ");
+		seq_puts(seq, "SVID_RND  ");
 
 	if (pkt_dev->flags & F_NODE)
-		seq_printf(seq, "NODE_ALLOC  ");
+		seq_puts(seq, "NODE_ALLOC  ");
 
 	seq_puts(seq, "\n");
 
@@ -714,7 +716,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 	if (pkt_dev->result[0])
 		seq_printf(seq, "Result: %s\n", pkt_dev->result);
 	else
-		seq_printf(seq, "Result: Idle\n");
+		seq_puts(seq, "Result: Idle\n");
 
 	return 0;
 }
@@ -1245,7 +1247,13 @@ static ssize_t pktgen_if_write(struct file *file,
 				"Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s",
 				f,
 				"IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, "
-				"MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC, NODE_ALLOC\n");
+				"MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, "
+				"MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, "
+				"QUEUE_MAP_RND, QUEUE_MAP_CPU, UDPCSUM, "
+#ifdef CONFIG_XFRM
+				"IPSEC, "
+#endif
+				"NODE_ALLOC\n");
 			return count;
 		}
 		sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags);
@@ -1434,7 +1442,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (!mac_pton(valstr, pkt_dev->dst_mac))
 			return -EINVAL;
 		/* Set up Dest MAC */
-		memcpy(&pkt_dev->hh[0], pkt_dev->dst_mac, ETH_ALEN);
+		ether_addr_copy(&pkt_dev->hh[0], pkt_dev->dst_mac);
 
 		sprintf(pg_result, "OK: dstmac %pM", pkt_dev->dst_mac);
 		return count;
@@ -1451,7 +1459,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (!mac_pton(valstr, pkt_dev->src_mac))
 			return -EINVAL;
 		/* Set up Src MAC */
-		memcpy(&pkt_dev->hh[6], pkt_dev->src_mac, ETH_ALEN);
+		ether_addr_copy(&pkt_dev->hh[6], pkt_dev->src_mac);
 
 		sprintf(pg_result, "OK: srcmac %pM", pkt_dev->src_mac);
 		return count;
@@ -1476,7 +1484,18 @@ static ssize_t pktgen_if_write(struct file *file,
 		sprintf(pg_result, "OK: flows=%u", pkt_dev->cflows);
 		return count;
 	}
+#ifdef CONFIG_XFRM
+	if (!strcmp(name, "spi")) {
+		len = num_arg(&user_buffer[i], 10, &value);
+		if (len < 0)
+			return len;
 
+		i += len;
+		pkt_dev->spi = value;
+		sprintf(pg_result, "OK: spi=%u", pkt_dev->spi);
+		return count;
+	}
+#endif
 	if (!strcmp(name, "flowlen")) {
 		len = num_arg(&user_buffer[i], 10, &value);
 		if (len < 0)
@@ -1716,14 +1735,14 @@ static int pktgen_thread_show(struct seq_file *seq, void *v)
 
 	BUG_ON(!t);
 
-	seq_printf(seq, "Running: ");
+	seq_puts(seq, "Running: ");
 
 	if_lock(t);
 	list_for_each_entry(pkt_dev, &t->if_list, list)
 		if (pkt_dev->running)
 			seq_printf(seq, "%s ", pkt_dev->odevname);
 
-	seq_printf(seq, "\nStopped: ");
+	seq_puts(seq, "\nStopped: ");
 
 	list_for_each_entry(pkt_dev, &t->if_list, list)
 		if (!pkt_dev->running)
@@ -1732,7 +1751,7 @@ static int pktgen_thread_show(struct seq_file *seq, void *v)
 	if (t->result[0])
 		seq_printf(seq, "\nResult: %s\n", t->result);
 	else
-		seq_printf(seq, "\nResult: NA\n");
+		seq_puts(seq, "\nResult: NA\n");
 
 	if_unlock(t);
 
@@ -2043,10 +2062,10 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
 	/* Default to the interface's mac if not explicitly set. */
 
 	if (is_zero_ether_addr(pkt_dev->src_mac))
-		memcpy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr, ETH_ALEN);
+		ether_addr_copy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr);
 
 	/* Set up Dest MAC */
-	memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN);
+	ether_addr_copy(&(pkt_dev->hh[0]), pkt_dev->dst_mac);
 
 	if (pkt_dev->flags & F_IPV6) {
 		int i, set = 0, err = 1;
@@ -2233,13 +2252,21 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
 	struct xfrm_state *x = pkt_dev->flows[flow].x;
 	struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id);
 	if (!x) {
-		/*slow path: we dont already have xfrm_state*/
-		x = xfrm_stateonly_find(pn->net, DUMMY_MARK,
-					(xfrm_address_t *)&pkt_dev->cur_daddr,
-					(xfrm_address_t *)&pkt_dev->cur_saddr,
-					AF_INET,
-					pkt_dev->ipsmode,
-					pkt_dev->ipsproto, 0);
+
+		if (pkt_dev->spi) {
+			/* We need as quick as possible to find the right SA
+			 * Searching with minimum criteria to archieve this.
+			 */
+			x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET);
+		} else {
+			/* slow path: we dont already have xfrm_state */
+			x = xfrm_stateonly_find(pn->net, DUMMY_MARK,
+						(xfrm_address_t *)&pkt_dev->cur_daddr,
+						(xfrm_address_t *)&pkt_dev->cur_saddr,
+						AF_INET,
+						pkt_dev->ipsmode,
+						pkt_dev->ipsproto, 0);
+		}
 		if (x) {
 			pkt_dev->flows[flow].x = x;
 			set_pkt_overhead(pkt_dev);
@@ -2475,31 +2502,47 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 
 
 #ifdef CONFIG_XFRM
+static u32 pktgen_dst_metrics[RTAX_MAX + 1] = {
+
+	[RTAX_HOPLIMIT] = 0x5, /* Set a static hoplimit */
+};
+
 static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev)
 {
 	struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x;
 	int err = 0;
+	struct net *net = dev_net(pkt_dev->odev);
 
 	if (!x)
 		return 0;
 	/* XXX: we dont support tunnel mode for now until
 	 * we resolve the dst issue */
-	if (x->props.mode != XFRM_MODE_TRANSPORT)
+	if ((x->props.mode != XFRM_MODE_TRANSPORT) && (pkt_dev->spi == 0))
 		return 0;
 
-	spin_lock(&x->lock);
+	/* But when user specify an valid SPI, transformation
+	 * supports both transport/tunnel mode + ESP/AH type.
+	 */
+	if ((x->props.mode == XFRM_MODE_TUNNEL) && (pkt_dev->spi != 0))
+		skb->_skb_refdst = (unsigned long)&pkt_dev->dst | SKB_DST_NOREF;
 
+	rcu_read_lock_bh();
 	err = x->outer_mode->output(x, skb);
-	if (err)
+	rcu_read_unlock_bh();
+	if (err) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
 		goto error;
+	}
 	err = x->type->output(x, skb);
-	if (err)
+	if (err) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR);
 		goto error;
-
+	}
+	spin_lock_bh(&x->lock);
 	x->curlft.bytes += skb->len;
 	x->curlft.packets++;
+	spin_unlock_bh(&x->lock);
 error:
-	spin_unlock(&x->lock);
 	return err;
 }
 
@@ -3295,9 +3338,11 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 	queue_map = skb_get_queue_mapping(pkt_dev->skb);
 	txq = netdev_get_tx_queue(odev, queue_map);
 
-	__netif_tx_lock_bh(txq);
+	local_bh_disable();
+
+	HARD_TX_LOCK(odev, txq, smp_processor_id());
 
-	if (unlikely(netif_xmit_frozen_or_stopped(txq))) {
+	if (unlikely(netif_xmit_frozen_or_drv_stopped(txq))) {
 		ret = NETDEV_TX_BUSY;
 		pkt_dev->last_ok = 0;
 		goto unlock;
@@ -3331,7 +3376,9 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 		pkt_dev->last_ok = 0;
 	}
 unlock:
-	__netif_tx_unlock_bh(txq);
+	HARD_TX_UNLOCK(odev, txq);
+
+	local_bh_enable();
 
 	/* If pkt_dev->count is zero, then run forever */
 	if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) {
@@ -3542,6 +3589,17 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
 #ifdef CONFIG_XFRM
 	pkt_dev->ipsmode = XFRM_MODE_TRANSPORT;
 	pkt_dev->ipsproto = IPPROTO_ESP;
+
+	/* xfrm tunnel mode needs additional dst to extract outter
+	 * ip header protocol/ttl/id field, here creat a phony one.
+	 * instead of looking for a valid rt, which definitely hurting
+	 * performance under such circumstance.
+	 */
+	pkt_dev->dstops.family = AF_INET;
+	pkt_dev->dst.dev = pkt_dev->odev;
+	dst_init_metrics(&pkt_dev->dst, pktgen_dst_metrics, false);
+	pkt_dev->dst.child = &pkt_dev->dst;
+	pkt_dev->dst.ops = &pkt_dev->dstops;
 #endif
 
 	return add_dev_to_thread(t, pkt_dev);
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
new file mode 100644
index 00000000000..d3027a73fd4
--- /dev/null
+++ b/net/core/ptp_classifier.c
@@ -0,0 +1,141 @@
+/* PTP classifier
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+/* The below program is the bpf_asm (tools/net/) representation of
+ * the opcode array in the ptp_filter structure.
+ *
+ * For convenience, this can easily be altered and reviewed with
+ * bpf_asm and bpf_dbg, e.g. `./bpf_asm -c prog` where prog is a
+ * simple file containing the below program:
+ *
+ * ldh [12]                        ; load ethertype
+ *
+ * ; PTP over UDP over IPv4 over Ethernet
+ * test_ipv4:
+ *   jneq #0x800, test_ipv6        ; ETH_P_IP ?
+ *   ldb [23]                      ; load proto
+ *   jneq #17, drop_ipv4           ; IPPROTO_UDP ?
+ *   ldh [20]                      ; load frag offset field
+ *   jset #0x1fff, drop_ipv4       ; don't allow fragments
+ *   ldxb 4*([14]&0xf)             ; load IP header len
+ *   ldh [x + 16]                  ; load UDP dst port
+ *   jneq #319, drop_ipv4          ; is port PTP_EV_PORT ?
+ *   ldh [x + 22]                  ; load payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x10                      ; PTP_CLASS_IPV4
+ *   ret a                         ; return PTP class
+ *   drop_ipv4: ret #0x0           ; PTP_CLASS_NONE
+ *
+ * ; PTP over UDP over IPv6 over Ethernet
+ * test_ipv6:
+ *   jneq #0x86dd, test_8021q      ; ETH_P_IPV6 ?
+ *   ldb [20]                      ; load proto
+ *   jneq #17, drop_ipv6           ; IPPROTO_UDP ?
+ *   ldh [56]                      ; load UDP dst port
+ *   jneq #319, drop_ipv6          ; is port PTP_EV_PORT ?
+ *   ldh [62]                      ; load payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x20                      ; PTP_CLASS_IPV6
+ *   ret a                         ; return PTP class
+ *   drop_ipv6: ret #0x0           ; PTP_CLASS_NONE
+ *
+ * ; PTP over 802.1Q over Ethernet
+ * test_8021q:
+ *   jneq #0x8100, test_ieee1588   ; ETH_P_8021Q ?
+ *   ldh [16]                      ; load inner type
+ *   jneq #0x88f7, drop_ieee1588   ; ETH_P_1588 ?
+ *   ldb [18]                      ; load payload
+ *   and #0x8                      ; as we don't have ports here, test
+ *   jneq #0x0, drop_ieee1588      ; for PTP_GEN_BIT and drop these
+ *   ldh [18]                      ; reload payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x40                      ; PTP_CLASS_V2_VLAN
+ *   ret a                         ; return PTP class
+ *
+ * ; PTP over Ethernet
+ * test_ieee1588:
+ *   jneq #0x88f7, drop_ieee1588   ; ETH_P_1588 ?
+ *   ldb [14]                      ; load payload
+ *   and #0x8                      ; as we don't have ports here, test
+ *   jneq #0x0, drop_ieee1588      ; for PTP_GEN_BIT and drop these
+ *   ldh [14]                      ; reload payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x30                      ; PTP_CLASS_L2
+ *   ret a                         ; return PTP class
+ *   drop_ieee1588: ret #0x0       ; PTP_CLASS_NONE
+ */
+
+#include <linux/skbuff.h>
+#include <linux/filter.h>
+#include <linux/ptp_classify.h>
+
+static struct sk_filter *ptp_insns __read_mostly;
+
+unsigned int ptp_classify_raw(const struct sk_buff *skb)
+{
+	return SK_RUN_FILTER(ptp_insns, skb);
+}
+EXPORT_SYMBOL_GPL(ptp_classify_raw);
+
+void __init ptp_classifier_init(void)
+{
+	static struct sock_filter ptp_filter[] __initdata = {
+		{ 0x28,  0,  0, 0x0000000c },
+		{ 0x15,  0, 12, 0x00000800 },
+		{ 0x30,  0,  0, 0x00000017 },
+		{ 0x15,  0,  9, 0x00000011 },
+		{ 0x28,  0,  0, 0x00000014 },
+		{ 0x45,  7,  0, 0x00001fff },
+		{ 0xb1,  0,  0, 0x0000000e },
+		{ 0x48,  0,  0, 0x00000010 },
+		{ 0x15,  0,  4, 0x0000013f },
+		{ 0x48,  0,  0, 0x00000016 },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000010 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+		{ 0x15,  0,  9, 0x000086dd },
+		{ 0x30,  0,  0, 0x00000014 },
+		{ 0x15,  0,  6, 0x00000011 },
+		{ 0x28,  0,  0, 0x00000038 },
+		{ 0x15,  0,  4, 0x0000013f },
+		{ 0x28,  0,  0, 0x0000003e },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000020 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+		{ 0x15,  0,  9, 0x00008100 },
+		{ 0x28,  0,  0, 0x00000010 },
+		{ 0x15,  0, 15, 0x000088f7 },
+		{ 0x30,  0,  0, 0x00000012 },
+		{ 0x54,  0,  0, 0x00000008 },
+		{ 0x15,  0, 12, 0x00000000 },
+		{ 0x28,  0,  0, 0x00000012 },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000040 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x15,  0,  7, 0x000088f7 },
+		{ 0x30,  0,  0, 0x0000000e },
+		{ 0x54,  0,  0, 0x00000008 },
+		{ 0x15,  0,  4, 0x00000000 },
+		{ 0x28,  0,  0, 0x0000000e },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000030 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+	};
+	struct sock_fprog_kern ptp_prog = {
+		.len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
+	};
+
+	BUG_ON(sk_unattached_filter_create(&ptp_insns, &ptp_prog));
+}
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 4425148d2b5..467f326126e 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -221,5 +221,4 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
 out:
 	spin_unlock_bh(&fastopenq->lock);
 	sock_put(lsk);
-	return;
 }
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index cf67144d3e3..1063996f831 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -353,18 +353,65 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops)
 }
 EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
 
+/* Return with the rtnl_lock held when there are no network
+ * devices unregistering in any network namespace.
+ */
+static void rtnl_lock_unregistering_all(void)
+{
+	struct net *net;
+	bool unregistering;
+	DEFINE_WAIT(wait);
+
+	for (;;) {
+		prepare_to_wait(&netdev_unregistering_wq, &wait,
+				TASK_UNINTERRUPTIBLE);
+		unregistering = false;
+		rtnl_lock();
+		for_each_net(net) {
+			if (net->dev_unreg_count > 0) {
+				unregistering = true;
+				break;
+			}
+		}
+		if (!unregistering)
+			break;
+		__rtnl_unlock();
+		schedule();
+	}
+	finish_wait(&netdev_unregistering_wq, &wait);
+}
+
 /**
  * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
  * @ops: struct rtnl_link_ops * to unregister
  */
 void rtnl_link_unregister(struct rtnl_link_ops *ops)
 {
-	rtnl_lock();
+	/* Close the race with cleanup_net() */
+	mutex_lock(&net_mutex);
+	rtnl_lock_unregistering_all();
 	__rtnl_link_unregister(ops);
 	rtnl_unlock();
+	mutex_unlock(&net_mutex);
 }
 EXPORT_SYMBOL_GPL(rtnl_link_unregister);
 
+static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev)
+{
+	struct net_device *master_dev;
+	const struct rtnl_link_ops *ops;
+
+	master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
+	if (!master_dev)
+		return 0;
+	ops = master_dev->rtnl_link_ops;
+	if (!ops || !ops->get_slave_size)
+		return 0;
+	/* IFLA_INFO_SLAVE_DATA + nested data */
+	return nla_total_size(sizeof(struct nlattr)) +
+	       ops->get_slave_size(master_dev, dev);
+}
+
 static size_t rtnl_link_get_size(const struct net_device *dev)
 {
 	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
@@ -385,6 +432,8 @@ static size_t rtnl_link_get_size(const struct net_device *dev)
 		/* IFLA_INFO_XSTATS */
 		size += nla_total_size(ops->get_xstats_size(dev));
 
+	size += rtnl_link_get_slave_info_data_size(dev);
+
 	return size;
 }
 
@@ -403,34 +452,16 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
 }
 
 /**
- * __rtnl_af_register - Register rtnl_af_ops with rtnetlink.
- * @ops: struct rtnl_af_ops * to register
- *
- * The caller must hold the rtnl_mutex.
- *
- * Returns 0 on success or a negative error code.
- */
-int __rtnl_af_register(struct rtnl_af_ops *ops)
-{
-	list_add_tail(&ops->list, &rtnl_af_ops);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(__rtnl_af_register);
-
-/**
  * rtnl_af_register - Register rtnl_af_ops with rtnetlink.
  * @ops: struct rtnl_af_ops * to register
  *
  * Returns 0 on success or a negative error code.
  */
-int rtnl_af_register(struct rtnl_af_ops *ops)
+void rtnl_af_register(struct rtnl_af_ops *ops)
 {
-	int err;
-
 	rtnl_lock();
-	err = __rtnl_af_register(ops);
+	list_add_tail(&ops->list, &rtnl_af_ops);
 	rtnl_unlock();
-	return err;
 }
 EXPORT_SYMBOL_GPL(rtnl_af_register);
 
@@ -477,40 +508,100 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev)
 	return size;
 }
 
-static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev)
+static bool rtnl_have_link_slave_info(const struct net_device *dev)
 {
-	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
-	struct nlattr *linkinfo, *data;
-	int err = -EMSGSIZE;
+	struct net_device *master_dev;
 
-	linkinfo = nla_nest_start(skb, IFLA_LINKINFO);
-	if (linkinfo == NULL)
-		goto out;
+	master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
+	if (master_dev && master_dev->rtnl_link_ops)
+		return true;
+	return false;
+}
+
+static int rtnl_link_slave_info_fill(struct sk_buff *skb,
+				     const struct net_device *dev)
+{
+	struct net_device *master_dev;
+	const struct rtnl_link_ops *ops;
+	struct nlattr *slave_data;
+	int err;
+
+	master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
+	if (!master_dev)
+		return 0;
+	ops = master_dev->rtnl_link_ops;
+	if (!ops)
+		return 0;
+	if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0)
+		return -EMSGSIZE;
+	if (ops->fill_slave_info) {
+		slave_data = nla_nest_start(skb, IFLA_INFO_SLAVE_DATA);
+		if (!slave_data)
+			return -EMSGSIZE;
+		err = ops->fill_slave_info(skb, master_dev, dev);
+		if (err < 0)
+			goto err_cancel_slave_data;
+		nla_nest_end(skb, slave_data);
+	}
+	return 0;
+
+err_cancel_slave_data:
+	nla_nest_cancel(skb, slave_data);
+	return err;
+}
+
+static int rtnl_link_info_fill(struct sk_buff *skb,
+			       const struct net_device *dev)
+{
+	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
+	struct nlattr *data;
+	int err;
 
+	if (!ops)
+		return 0;
 	if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0)
-		goto err_cancel_link;
+		return -EMSGSIZE;
 	if (ops->fill_xstats) {
 		err = ops->fill_xstats(skb, dev);
 		if (err < 0)
-			goto err_cancel_link;
+			return err;
 	}
 	if (ops->fill_info) {
 		data = nla_nest_start(skb, IFLA_INFO_DATA);
-		if (data == NULL) {
-			err = -EMSGSIZE;
-			goto err_cancel_link;
-		}
+		if (data == NULL)
+			return -EMSGSIZE;
 		err = ops->fill_info(skb, dev);
 		if (err < 0)
 			goto err_cancel_data;
 		nla_nest_end(skb, data);
 	}
-
-	nla_nest_end(skb, linkinfo);
 	return 0;
 
 err_cancel_data:
 	nla_nest_cancel(skb, data);
+	return err;
+}
+
+static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct nlattr *linkinfo;
+	int err = -EMSGSIZE;
+
+	linkinfo = nla_nest_start(skb, IFLA_LINKINFO);
+	if (linkinfo == NULL)
+		goto out;
+
+	err = rtnl_link_info_fill(skb, dev);
+	if (err < 0)
+		goto err_cancel_link;
+
+	err = rtnl_link_slave_info_fill(skb, dev);
+	if (err < 0)
+		goto err_cancel_link;
+
+	nla_nest_end(skb, linkinfo);
+	return 0;
+
 err_cancel_link:
 	nla_nest_cancel(skb, linkinfo);
 out:
@@ -707,14 +798,15 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 		size += num_vfs *
 			(nla_total_size(sizeof(struct ifla_vf_mac)) +
 			 nla_total_size(sizeof(struct ifla_vf_vlan)) +
-			 nla_total_size(sizeof(struct ifla_vf_tx_rate)) +
-			 nla_total_size(sizeof(struct ifla_vf_spoofchk)));
+			 nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
+			 nla_total_size(sizeof(struct ifla_vf_rate)));
 		return size;
 	} else
 		return 0;
 }
 
-static size_t rtnl_port_size(const struct net_device *dev)
+static size_t rtnl_port_size(const struct net_device *dev,
+			     u32 ext_filter_mask)
 {
 	size_t port_size = nla_total_size(4)		/* PORT_VF */
 		+ nla_total_size(PORT_PROFILE_MAX)	/* PORT_PROFILE */
@@ -730,7 +822,8 @@ static size_t rtnl_port_size(const struct net_device *dev)
 	size_t port_self_size = nla_total_size(sizeof(struct nlattr))
 		+ port_size;
 
-	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
+	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
+	    !(ext_filter_mask & RTEXT_FILTER_VF))
 		return 0;
 	if (dev_num_vf(dev->dev.parent))
 		return port_self_size + vf_ports_size +
@@ -762,10 +855,11 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
+	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
 	       + nla_total_size(ext_filter_mask
 			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
 	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
-	       + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+	       + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
 	       + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
 	       + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
 	       + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */
@@ -827,11 +921,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
-static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev)
+static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
+			  u32 ext_filter_mask)
 {
 	int err;
 
-	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
+	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
+	    !(ext_filter_mask & RTEXT_FILTER_VF))
 		return 0;
 
 	err = rtnl_port_self_fill(skb, dev);
@@ -910,7 +1006,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	    (dev->qdisc &&
 	     nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
 	    (dev->ifalias &&
-	     nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)))
+	     nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) ||
+	    nla_put_u32(skb, IFLA_CARRIER_CHANGES,
+			atomic_read(&dev->carrier_changes)))
 		goto nla_put_failure;
 
 	if (1) {
@@ -967,6 +1065,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			struct ifla_vf_info ivi;
 			struct ifla_vf_mac vf_mac;
 			struct ifla_vf_vlan vf_vlan;
+			struct ifla_vf_rate vf_rate;
 			struct ifla_vf_tx_rate vf_tx_rate;
 			struct ifla_vf_spoofchk vf_spoofchk;
 			struct ifla_vf_link_state vf_linkstate;
@@ -987,6 +1086,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 				break;
 			vf_mac.vf =
 				vf_vlan.vf =
+				vf_rate.vf =
 				vf_tx_rate.vf =
 				vf_spoofchk.vf =
 				vf_linkstate.vf = ivi.vf;
@@ -994,7 +1094,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
 			vf_vlan.vlan = ivi.vlan;
 			vf_vlan.qos = ivi.qos;
-			vf_tx_rate.rate = ivi.tx_rate;
+			vf_tx_rate.rate = ivi.max_tx_rate;
+			vf_rate.min_tx_rate = ivi.min_tx_rate;
+			vf_rate.max_tx_rate = ivi.max_tx_rate;
 			vf_spoofchk.setting = ivi.spoofchk;
 			vf_linkstate.link_state = ivi.linkstate;
 			vf = nla_nest_start(skb, IFLA_VF_INFO);
@@ -1004,6 +1106,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			}
 			if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) ||
 			    nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) ||
+			    nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate),
+				    &vf_rate) ||
 			    nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
 				    &vf_tx_rate) ||
 			    nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
@@ -1016,10 +1120,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 		nla_nest_end(skb, vfinfo);
 	}
 
-	if (rtnl_port_fill(skb, dev))
+	if (rtnl_port_fill(skb, dev, ext_filter_mask))
 		goto nla_put_failure;
 
-	if (dev->rtnl_link_ops) {
+	if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) {
 		if (rtnl_link_fill(skb, dev) < 0)
 			goto nla_put_failure;
 	}
@@ -1061,56 +1165,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
-{
-	struct net *net = sock_net(skb->sk);
-	int h, s_h;
-	int idx = 0, s_idx;
-	struct net_device *dev;
-	struct hlist_head *head;
-	struct nlattr *tb[IFLA_MAX+1];
-	u32 ext_filter_mask = 0;
-
-	s_h = cb->args[0];
-	s_idx = cb->args[1];
-
-	rcu_read_lock();
-	cb->seq = net->dev_base_seq;
-
-	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
-
-		if (tb[IFLA_EXT_MASK])
-			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
-	}
-
-	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
-		idx = 0;
-		head = &net->dev_index_head[h];
-		hlist_for_each_entry_rcu(dev, head, index_hlist) {
-			if (idx < s_idx)
-				goto cont;
-			if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
-					     NETLINK_CB(cb->skb).portid,
-					     cb->nlh->nlmsg_seq, 0,
-					     NLM_F_MULTI,
-					     ext_filter_mask) <= 0)
-				goto out;
-
-			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
-cont:
-			idx++;
-		}
-	}
-out:
-	rcu_read_unlock();
-	cb->args[1] = idx;
-	cb->args[0] = h;
-
-	return skb->len;
-}
-
-const struct nla_policy ifla_policy[IFLA_MAX+1] = {
+static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_IFNAME]		= { .type = NLA_STRING, .len = IFNAMSIZ-1 },
 	[IFLA_ADDRESS]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
 	[IFLA_BROADCAST]	= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
@@ -1136,12 +1191,14 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_NUM_TX_QUEUES]	= { .type = NLA_U32 },
 	[IFLA_NUM_RX_QUEUES]	= { .type = NLA_U32 },
 	[IFLA_PHYS_PORT_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
+	[IFLA_CARRIER_CHANGES]	= { .type = NLA_U32 },  /* ignored */
 };
-EXPORT_SYMBOL(ifla_policy);
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
 	[IFLA_INFO_KIND]	= { .type = NLA_STRING },
 	[IFLA_INFO_DATA]	= { .type = NLA_NESTED },
+	[IFLA_INFO_SLAVE_KIND]	= { .type = NLA_STRING },
+	[IFLA_INFO_SLAVE_DATA]	= { .type = NLA_NESTED },
 };
 
 static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
@@ -1157,6 +1214,10 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 				    .len = sizeof(struct ifla_vf_tx_rate) },
 	[IFLA_VF_SPOOFCHK]	= { .type = NLA_BINARY,
 				    .len = sizeof(struct ifla_vf_spoofchk) },
+	[IFLA_VF_RATE]		= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_rate) },
+	[IFLA_VF_LINK_STATE]	= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_link_state) },
 };
 
 static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
@@ -1173,6 +1234,78 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
 	[IFLA_PORT_RESPONSE]	= { .type = NLA_U16, },
 };
 
+static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	int h, s_h;
+	int idx = 0, s_idx;
+	struct net_device *dev;
+	struct hlist_head *head;
+	struct nlattr *tb[IFLA_MAX+1];
+	u32 ext_filter_mask = 0;
+	int err;
+	int hdrlen;
+
+	s_h = cb->args[0];
+	s_idx = cb->args[1];
+
+	rcu_read_lock();
+	cb->seq = net->dev_base_seq;
+
+	/* A hack to preserve kernel<->userspace interface.
+	 * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
+	 * However, before Linux v3.9 the code here assumed rtgenmsg and that's
+	 * what iproute2 < v3.9.0 used.
+	 * We can detect the old iproute2. Even including the IFLA_EXT_MASK
+	 * attribute, its netlink message is shorter than struct ifinfomsg.
+	 */
+	hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
+
+		if (tb[IFLA_EXT_MASK])
+			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
+	}
+
+	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+		idx = 0;
+		head = &net->dev_index_head[h];
+		hlist_for_each_entry_rcu(dev, head, index_hlist) {
+			if (idx < s_idx)
+				goto cont;
+			err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+					       NETLINK_CB(cb->skb).portid,
+					       cb->nlh->nlmsg_seq, 0,
+					       NLM_F_MULTI,
+					       ext_filter_mask);
+			/* If we ran out of room on the first message,
+			 * we're in trouble
+			 */
+			WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
+
+			if (err <= 0)
+				goto out;
+
+			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+cont:
+			idx++;
+		}
+	}
+out:
+	rcu_read_unlock();
+	cb->args[1] = idx;
+	cb->args[0] = h;
+
+	return skb->len;
+}
+
+int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len)
+{
+	return nla_parse(tb, IFLA_MAX, head, len, ifla_policy);
+}
+EXPORT_SYMBOL(rtnl_nla_parse_ifla);
+
 struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[])
 {
 	struct net *net;
@@ -1254,11 +1387,29 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
 		}
 		case IFLA_VF_TX_RATE: {
 			struct ifla_vf_tx_rate *ivt;
+			struct ifla_vf_info ivf;
+			ivt = nla_data(vf);
+			err = -EOPNOTSUPP;
+			if (ops->ndo_get_vf_config)
+				err = ops->ndo_get_vf_config(dev, ivt->vf,
+							     &ivf);
+			if (err)
+				break;
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_rate)
+				err = ops->ndo_set_vf_rate(dev, ivt->vf,
+							   ivf.min_tx_rate,
+							   ivt->rate);
+			break;
+		}
+		case IFLA_VF_RATE: {
+			struct ifla_vf_rate *ivt;
 			ivt = nla_data(vf);
 			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_tx_rate)
-				err = ops->ndo_set_vf_tx_rate(dev, ivt->vf,
-							      ivt->rate);
+			if (ops->ndo_set_vf_rate)
+				err = ops->ndo_set_vf_rate(dev, ivt->vf,
+							   ivt->min_tx_rate,
+							   ivt->max_tx_rate);
 			break;
 		}
 		case IFLA_VF_SPOOFCHK: {
@@ -1324,7 +1475,8 @@ static int do_set_master(struct net_device *dev, int ifindex)
 	return 0;
 }
 
-static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
+static int do_setlink(const struct sk_buff *skb,
+		      struct net_device *dev, struct ifinfomsg *ifm,
 		      struct nlattr **tb, char *ifname, int modified)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -1336,7 +1488,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 			err = PTR_ERR(net);
 			goto errout;
 		}
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+		if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
 			err = -EPERM;
 			goto errout;
 		}
@@ -1590,7 +1742,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (err < 0)
 		goto errout;
 
-	err = do_setlink(dev, ifm, tb, ifname, 0);
+	err = do_setlink(skb, dev, ifm, tb, ifname, 0);
 errout:
 	return err;
 }
@@ -1630,7 +1782,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ops->dellink(dev, &list_kill);
 	unregister_netdevice_many(&list_kill);
-	list_del(&list_kill);
 	return 0;
 }
 
@@ -1707,7 +1858,8 @@ err:
 }
 EXPORT_SYMBOL(rtnl_create_link);
 
-static int rtnl_group_changelink(struct net *net, int group,
+static int rtnl_group_changelink(const struct sk_buff *skb,
+		struct net *net, int group,
 		struct ifinfomsg *ifm,
 		struct nlattr **tb)
 {
@@ -1716,7 +1868,7 @@ static int rtnl_group_changelink(struct net *net, int group,
 
 	for_each_netdev(net, dev) {
 		if (dev->group == group) {
-			err = do_setlink(dev, ifm, tb, NULL, 0);
+			err = do_setlink(skb, dev, ifm, tb, NULL, 0);
 			if (err < 0)
 				return err;
 		}
@@ -1729,7 +1881,9 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	const struct rtnl_link_ops *ops;
+	const struct rtnl_link_ops *m_ops = NULL;
 	struct net_device *dev;
+	struct net_device *master_dev = NULL;
 	struct ifinfomsg *ifm;
 	char kind[MODULE_NAME_LEN];
 	char ifname[IFNAMSIZ];
@@ -1759,6 +1913,12 @@ replay:
 			dev = NULL;
 	}
 
+	if (dev) {
+		master_dev = netdev_master_upper_dev_get(dev);
+		if (master_dev)
+			m_ops = master_dev->rtnl_link_ops;
+	}
+
 	err = validate_linkmsg(dev, tb);
 	if (err < 0)
 		return err;
@@ -1780,7 +1940,10 @@ replay:
 	}
 
 	if (1) {
-		struct nlattr *attr[ops ? ops->maxtype + 1 : 0], **data = NULL;
+		struct nlattr *attr[ops ? ops->maxtype + 1 : 0];
+		struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 0];
+		struct nlattr **data = NULL;
+		struct nlattr **slave_data = NULL;
 		struct net *dest_net;
 
 		if (ops) {
@@ -1799,6 +1962,24 @@ replay:
 			}
 		}
 
+		if (m_ops) {
+			if (m_ops->slave_maxtype &&
+			    linkinfo[IFLA_INFO_SLAVE_DATA]) {
+				err = nla_parse_nested(slave_attr,
+						       m_ops->slave_maxtype,
+						       linkinfo[IFLA_INFO_SLAVE_DATA],
+						       m_ops->slave_policy);
+				if (err < 0)
+					return err;
+				slave_data = slave_attr;
+			}
+			if (m_ops->slave_validate) {
+				err = m_ops->slave_validate(tb, slave_data);
+				if (err < 0)
+					return err;
+			}
+		}
+
 		if (dev) {
 			int modified = 0;
 
@@ -1818,12 +1999,23 @@ replay:
 				modified = 1;
 			}
 
-			return do_setlink(dev, ifm, tb, ifname, modified);
+			if (linkinfo[IFLA_INFO_SLAVE_DATA]) {
+				if (!m_ops || !m_ops->slave_changelink)
+					return -EOPNOTSUPP;
+
+				err = m_ops->slave_changelink(master_dev, dev,
+							      tb, slave_data);
+				if (err < 0)
+					return err;
+				modified = 1;
+			}
+
+			return do_setlink(skb, dev, ifm, tb, ifname, modified);
 		}
 
 		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
 			if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
-				return rtnl_group_changelink(net,
+				return rtnl_group_changelink(skb, net,
 						nla_get_u32(tb[IFLA_GROUP]),
 						ifm, tb);
 			return -ENODEV;
@@ -1861,16 +2053,25 @@ replay:
 
 		dev->ifindex = ifm->ifi_index;
 
-		if (ops->newlink)
+		if (ops->newlink) {
 			err = ops->newlink(net, dev, tb, data);
-		else
+			/* Drivers should call free_netdev() in ->destructor
+			 * and unregister it on failure after registration
+			 * so that device could be finally freed in rtnl_unlock.
+			 */
+			if (err < 0) {
+				/* If device is not registered at all, free it now */
+				if (dev->reg_state == NETREG_UNINITIALIZED)
+					free_netdev(dev);
+				goto out;
+			}
+		} else {
 			err = register_netdevice(dev);
-
-		if (err < 0) {
-			free_netdev(dev);
-			goto out;
+			if (err < 0) {
+				free_netdev(dev);
+				goto out;
+			}
 		}
-
 		err = rtnl_configure_link(dev, ifm);
 		if (err < 0)
 			unregister_netdevice(dev);
@@ -1935,9 +2136,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	u16 min_ifinfo_dump_size = 0;
+	int hdrlen;
+
+	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
+	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 	}
@@ -2014,12 +2219,13 @@ EXPORT_SYMBOL(rtmsg_ifinfo);
 static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
 				   struct net_device *dev,
 				   u8 *addr, u32 pid, u32 seq,
-				   int type, unsigned int flags)
+				   int type, unsigned int flags,
+				   int nlflags)
 {
 	struct nlmsghdr *nlh;
 	struct ndmsg *ndm;
 
-	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags);
 	if (!nlh)
 		return -EMSGSIZE;
 
@@ -2057,7 +2263,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type)
 	if (!skb)
 		goto errout;
 
-	err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF);
+	err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto errout;
@@ -2204,7 +2410,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err = -EINVAL;
 	__u8 *addr;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
@@ -2282,7 +2488,8 @@ static int nlmsg_populate_fdb(struct sk_buff *skb,
 
 		err = nlmsg_populate_fdb_fill(skb, dev, ha->addr,
 					      portid, seq,
-					      RTM_NEWNEIGH, NTF_SELF);
+					      RTM_NEWNEIGH, NTF_SELF,
+					      NLM_F_MULTI);
 		if (err < 0)
 			return err;
 skip:
@@ -2655,7 +2862,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	sz_idx = type>>2;
 	kind = type&3;
 
-	if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN))
+	if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 897da56f3af..ba71212f025 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -85,31 +85,6 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET
-__u32 secure_ip_id(__be32 daddr)
-{
-	u32 hash[MD5_DIGEST_WORDS];
-
-	net_secret_init();
-	hash[0] = (__force __u32) daddr;
-	hash[1] = net_secret[13];
-	hash[2] = net_secret[14];
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	return hash[0];
-}
-
-__u32 secure_ipv6_id(const __be32 daddr[4])
-{
-	__u32 hash[4];
-
-	net_secret_init();
-	memcpy(hash, daddr, 16);
-	md5_transform(hash, net_secret);
-
-	return hash[0];
-}
 
 __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 				 __be16 sport, __be16 dport)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 06e72d3cdf6..c1a33033cbe 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -47,6 +47,8 @@
 #include <linux/in.h>
 #include <linux/inet.h>
 #include <linux/slab.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
 #include <linux/netdevice.h>
 #ifdef CONFIG_NET_CLS_ACT
 #include <net/pkt_sched.h>
@@ -65,6 +67,7 @@
 #include <net/dst.h>
 #include <net/sock.h>
 #include <net/checksum.h>
+#include <net/ip6_checksum.h>
 #include <net/xfrm.h>
 
 #include <asm/uaccess.h>
@@ -74,36 +77,6 @@
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
 
-static void sock_pipe_buf_release(struct pipe_inode_info *pipe,
-				  struct pipe_buffer *buf)
-{
-	put_page(buf->page);
-}
-
-static void sock_pipe_buf_get(struct pipe_inode_info *pipe,
-				struct pipe_buffer *buf)
-{
-	get_page(buf->page);
-}
-
-static int sock_pipe_buf_steal(struct pipe_inode_info *pipe,
-			       struct pipe_buffer *buf)
-{
-	return 1;
-}
-
-
-/* Pipe buffer operations for a socket. */
-static const struct pipe_buf_operations sock_pipe_buf_ops = {
-	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
-	.confirm = generic_pipe_buf_confirm,
-	.release = sock_pipe_buf_release,
-	.steal = sock_pipe_buf_steal,
-	.get = sock_pipe_buf_get,
-};
-
 /**
  *	skb_panic - private function for out-of-line support
  *	@skb:	buffer
@@ -712,17 +685,19 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->inner_network_header = old->inner_network_header;
 	new->inner_mac_header = old->inner_mac_header;
 	skb_dst_copy(new, old);
-	new->rxhash		= old->rxhash;
+	skb_copy_hash(new, old);
 	new->ooo_okay		= old->ooo_okay;
-	new->l4_rxhash		= old->l4_rxhash;
 	new->no_fcs		= old->no_fcs;
 	new->encapsulation	= old->encapsulation;
+	new->encap_hdr_csum	= old->encap_hdr_csum;
+	new->csum_valid		= old->csum_valid;
+	new->csum_complete_sw	= old->csum_complete_sw;
 #ifdef CONFIG_XFRM
 	new->sp			= secpath_get(old->sp);
 #endif
 	memcpy(new->cb, old->cb, sizeof(old->cb));
 	new->csum		= old->csum;
-	new->local_df		= old->local_df;
+	new->ignore_df		= old->ignore_df;
 	new->pkt_type		= old->pkt_type;
 	new->ip_summed		= old->ip_summed;
 	skb_copy_queue_mapping(new, old);
@@ -735,9 +710,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->mark		= old->mark;
 	new->skb_iif		= old->skb_iif;
 	__nf_copy(new, old);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-	new->nf_trace		= old->nf_trace;
-#endif
 #ifdef CONFIG_NET_SCHED
 	new->tc_index		= old->tc_index;
 #ifdef CONFIG_NET_CLS_ACT
@@ -982,10 +954,13 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
 EXPORT_SYMBOL(skb_copy);
 
 /**
- *	__pskb_copy	-	create copy of an sk_buff with private head.
+ *	__pskb_copy_fclone	-  create copy of an sk_buff with private head.
  *	@skb: buffer to copy
  *	@headroom: headroom of new skb
  *	@gfp_mask: allocation priority
+ *	@fclone: if true allocate the copy of the skb from the fclone
+ *	cache instead of the head cache; it is recommended to set this
+ *	to true for the cases where the copy will likely be cloned
  *
  *	Make a copy of both an &sk_buff and part of its data, located
  *	in header. Fragmented data remain shared. This is used when
@@ -995,11 +970,12 @@ EXPORT_SYMBOL(skb_copy);
  *	The returned buffer has a reference count of 1.
  */
 
-struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
+struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom,
+				   gfp_t gfp_mask, bool fclone)
 {
 	unsigned int size = skb_headlen(skb) + headroom;
-	struct sk_buff *n = __alloc_skb(size, gfp_mask,
-					skb_alloc_rx_flag(skb), NUMA_NO_NODE);
+	int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0);
+	struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE);
 
 	if (!n)
 		goto out;
@@ -1039,7 +1015,7 @@ struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
 out:
 	return n;
 }
-EXPORT_SYMBOL(__pskb_copy);
+EXPORT_SYMBOL(__pskb_copy_fclone);
 
 /**
  *	pskb_expand_head - reallocate header of &sk_buff
@@ -1830,7 +1806,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
 		.partial = partial,
 		.nr_pages_max = MAX_SKB_FRAGS,
 		.flags = flags,
-		.ops = &sock_pipe_buf_ops,
+		.ops = &nosteal_pipe_buf_ops,
 		.spd_release = sock_spd_release,
 	};
 	struct sk_buff *frag_iter;
@@ -2122,6 +2098,104 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
 }
 EXPORT_SYMBOL(skb_copy_and_csum_bits);
 
+ /**
+ *	skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy()
+ *	@from: source buffer
+ *
+ *	Calculates the amount of linear headroom needed in the 'to' skb passed
+ *	into skb_zerocopy().
+ */
+unsigned int
+skb_zerocopy_headlen(const struct sk_buff *from)
+{
+	unsigned int hlen = 0;
+
+	if (!from->head_frag ||
+	    skb_headlen(from) < L1_CACHE_BYTES ||
+	    skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+		hlen = skb_headlen(from);
+
+	if (skb_has_frag_list(from))
+		hlen = from->len;
+
+	return hlen;
+}
+EXPORT_SYMBOL_GPL(skb_zerocopy_headlen);
+
+/**
+ *	skb_zerocopy - Zero copy skb to skb
+ *	@to: destination buffer
+ *	@from: source buffer
+ *	@len: number of bytes to copy from source buffer
+ *	@hlen: size of linear headroom in destination buffer
+ *
+ *	Copies up to `len` bytes from `from` to `to` by creating references
+ *	to the frags in the source buffer.
+ *
+ *	The `hlen` as calculated by skb_zerocopy_headlen() specifies the
+ *	headroom in the `to` buffer.
+ *
+ *	Return value:
+ *	0: everything is OK
+ *	-ENOMEM: couldn't orphan frags of @from due to lack of memory
+ *	-EFAULT: skb_copy_bits() found some problem with skb geometry
+ */
+int
+skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
+{
+	int i, j = 0;
+	int plen = 0; /* length of skb->head fragment */
+	int ret;
+	struct page *page;
+	unsigned int offset;
+
+	BUG_ON(!from->head_frag && !hlen);
+
+	/* dont bother with small payloads */
+	if (len <= skb_tailroom(to))
+		return skb_copy_bits(from, 0, skb_put(to, len), len);
+
+	if (hlen) {
+		ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+		if (unlikely(ret))
+			return ret;
+		len -= hlen;
+	} else {
+		plen = min_t(int, skb_headlen(from), len);
+		if (plen) {
+			page = virt_to_head_page(from->head);
+			offset = from->data - (unsigned char *)page_address(page);
+			__skb_fill_page_desc(to, 0, page, offset, plen);
+			get_page(page);
+			j = 1;
+			len -= plen;
+		}
+	}
+
+	to->truesize += len + plen;
+	to->len += len + plen;
+	to->data_len += len + plen;
+
+	if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) {
+		skb_tx_error(from);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
+		if (!len)
+			break;
+		skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i];
+		skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len);
+		len -= skb_shinfo(to)->frags[j].size;
+		skb_frag_ref(to, j);
+		j++;
+	}
+	skb_shinfo(to)->nr_frags = j;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(skb_zerocopy);
+
 void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
 {
 	__wsum csum;
@@ -2784,81 +2858,87 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum);
 
 /**
  *	skb_segment - Perform protocol segmentation on skb.
- *	@skb: buffer to segment
+ *	@head_skb: buffer to segment
  *	@features: features for the output path (see dev->features)
  *
  *	This function performs segmentation on the given skb.  It returns
  *	a pointer to the first in a list of new skbs for the segments.
  *	In case of error it returns ERR_PTR(err).
  */
-struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
+struct sk_buff *skb_segment(struct sk_buff *head_skb,
+			    netdev_features_t features)
 {
 	struct sk_buff *segs = NULL;
 	struct sk_buff *tail = NULL;
-	struct sk_buff *fskb = skb_shinfo(skb)->frag_list;
-	skb_frag_t *skb_frag = skb_shinfo(skb)->frags;
-	unsigned int mss = skb_shinfo(skb)->gso_size;
-	unsigned int doffset = skb->data - skb_mac_header(skb);
+	struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
+	skb_frag_t *frag = skb_shinfo(head_skb)->frags;
+	unsigned int mss = skb_shinfo(head_skb)->gso_size;
+	unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
+	struct sk_buff *frag_skb = head_skb;
 	unsigned int offset = doffset;
-	unsigned int tnl_hlen = skb_tnl_header_len(skb);
+	unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
 	unsigned int headroom;
 	unsigned int len;
 	__be16 proto;
 	bool csum;
 	int sg = !!(features & NETIF_F_SG);
-	int nfrags = skb_shinfo(skb)->nr_frags;
+	int nfrags = skb_shinfo(head_skb)->nr_frags;
 	int err = -ENOMEM;
 	int i = 0;
 	int pos;
+	int dummy;
 
-	proto = skb_network_protocol(skb);
+	__skb_push(head_skb, doffset);
+	proto = skb_network_protocol(head_skb, &dummy);
 	if (unlikely(!proto))
 		return ERR_PTR(-EINVAL);
 
-	csum = !!can_checksum_protocol(features, proto);
-	__skb_push(skb, doffset);
-	headroom = skb_headroom(skb);
-	pos = skb_headlen(skb);
+	csum = !head_skb->encap_hdr_csum &&
+	    !!can_checksum_protocol(features, proto);
+
+	headroom = skb_headroom(head_skb);
+	pos = skb_headlen(head_skb);
 
 	do {
 		struct sk_buff *nskb;
-		skb_frag_t *frag;
+		skb_frag_t *nskb_frag;
 		int hsize;
 		int size;
 
-		len = skb->len - offset;
+		len = head_skb->len - offset;
 		if (len > mss)
 			len = mss;
 
-		hsize = skb_headlen(skb) - offset;
+		hsize = skb_headlen(head_skb) - offset;
 		if (hsize < 0)
 			hsize = 0;
 		if (hsize > len || !sg)
 			hsize = len;
 
-		if (!hsize && i >= nfrags && skb_headlen(fskb) &&
-		    (skb_headlen(fskb) == len || sg)) {
-			BUG_ON(skb_headlen(fskb) > len);
+		if (!hsize && i >= nfrags && skb_headlen(list_skb) &&
+		    (skb_headlen(list_skb) == len || sg)) {
+			BUG_ON(skb_headlen(list_skb) > len);
 
 			i = 0;
-			nfrags = skb_shinfo(fskb)->nr_frags;
-			skb_frag = skb_shinfo(fskb)->frags;
-			pos += skb_headlen(fskb);
+			nfrags = skb_shinfo(list_skb)->nr_frags;
+			frag = skb_shinfo(list_skb)->frags;
+			frag_skb = list_skb;
+			pos += skb_headlen(list_skb);
 
 			while (pos < offset + len) {
 				BUG_ON(i >= nfrags);
 
-				size = skb_frag_size(skb_frag);
+				size = skb_frag_size(frag);
 				if (pos + size > offset + len)
 					break;
 
 				i++;
 				pos += size;
-				skb_frag++;
+				frag++;
 			}
 
-			nskb = skb_clone(fskb, GFP_ATOMIC);
-			fskb = fskb->next;
+			nskb = skb_clone(list_skb, GFP_ATOMIC);
+			list_skb = list_skb->next;
 
 			if (unlikely(!nskb))
 				goto err;
@@ -2879,7 +2959,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 			__skb_push(nskb, doffset);
 		} else {
 			nskb = __alloc_skb(hsize + doffset + headroom,
-					   GFP_ATOMIC, skb_alloc_rx_flag(skb),
+					   GFP_ATOMIC, skb_alloc_rx_flag(head_skb),
 					   NUMA_NO_NODE);
 
 			if (unlikely(!nskb))
@@ -2895,12 +2975,12 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 			segs = nskb;
 		tail = nskb;
 
-		__copy_skb_header(nskb, skb);
-		nskb->mac_len = skb->mac_len;
+		__copy_skb_header(nskb, head_skb);
+		nskb->mac_len = head_skb->mac_len;
 
 		skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
 
-		skb_copy_from_linear_data_offset(skb, -tnl_hlen,
+		skb_copy_from_linear_data_offset(head_skb, -tnl_hlen,
 						 nskb->data - tnl_hlen,
 						 doffset + tnl_hlen);
 
@@ -2909,30 +2989,34 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 
 		if (!sg) {
 			nskb->ip_summed = CHECKSUM_NONE;
-			nskb->csum = skb_copy_and_csum_bits(skb, offset,
+			nskb->csum = skb_copy_and_csum_bits(head_skb, offset,
 							    skb_put(nskb, len),
 							    len, 0);
+			SKB_GSO_CB(nskb)->csum_start =
+			    skb_headroom(nskb) + doffset;
 			continue;
 		}
 
-		frag = skb_shinfo(nskb)->frags;
+		nskb_frag = skb_shinfo(nskb)->frags;
 
-		skb_copy_from_linear_data_offset(skb, offset,
+		skb_copy_from_linear_data_offset(head_skb, offset,
 						 skb_put(nskb, hsize), hsize);
 
-		skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
+		skb_shinfo(nskb)->tx_flags = skb_shinfo(head_skb)->tx_flags &
+			SKBTX_SHARED_FRAG;
 
 		while (pos < offset + len) {
 			if (i >= nfrags) {
-				BUG_ON(skb_headlen(fskb));
+				BUG_ON(skb_headlen(list_skb));
 
 				i = 0;
-				nfrags = skb_shinfo(fskb)->nr_frags;
-				skb_frag = skb_shinfo(fskb)->frags;
+				nfrags = skb_shinfo(list_skb)->nr_frags;
+				frag = skb_shinfo(list_skb)->frags;
+				frag_skb = list_skb;
 
 				BUG_ON(!nfrags);
 
-				fskb = fskb->next;
+				list_skb = list_skb->next;
 			}
 
 			if (unlikely(skb_shinfo(nskb)->nr_frags >=
@@ -2943,27 +3027,30 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 				goto err;
 			}
 
-			*frag = *skb_frag;
-			__skb_frag_ref(frag);
-			size = skb_frag_size(frag);
+			if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC)))
+				goto err;
+
+			*nskb_frag = *frag;
+			__skb_frag_ref(nskb_frag);
+			size = skb_frag_size(nskb_frag);
 
 			if (pos < offset) {
-				frag->page_offset += offset - pos;
-				skb_frag_size_sub(frag, offset - pos);
+				nskb_frag->page_offset += offset - pos;
+				skb_frag_size_sub(nskb_frag, offset - pos);
 			}
 
 			skb_shinfo(nskb)->nr_frags++;
 
 			if (pos + size <= offset + len) {
 				i++;
-				skb_frag++;
+				frag++;
 				pos += size;
 			} else {
-				skb_frag_size_sub(frag, pos + size - (offset + len));
+				skb_frag_size_sub(nskb_frag, pos + size - (offset + len));
 				goto skip_fraglist;
 			}
 
-			frag++;
+			nskb_frag++;
 		}
 
 skip_fraglist:
@@ -2976,16 +3063,15 @@ perform_csum_check:
 			nskb->csum = skb_checksum(nskb, doffset,
 						  nskb->len - doffset, 0);
 			nskb->ip_summed = CHECKSUM_NONE;
+			SKB_GSO_CB(nskb)->csum_start =
+			    skb_headroom(nskb) + doffset;
 		}
-	} while ((offset += len) < skb->len);
+	} while ((offset += len) < head_skb->len);
 
 	return segs;
 
 err:
-	while ((skb = segs)) {
-		segs = skb->next;
-		kfree_skb(skb);
-	}
+	kfree_skb_list(segs);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(skb_segment);
@@ -3003,7 +3089,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	if (unlikely(p->len + len >= 65536))
 		return -E2BIG;
 
-	lp = NAPI_GRO_CB(p)->last ?: p;
+	lp = NAPI_GRO_CB(p)->last;
 	pinfo = skb_shinfo(lp);
 
 	if (headlen <= offset) {
@@ -3119,7 +3205,7 @@ merge:
 
 	__skb_pull(skb, offset);
 
-	if (!NAPI_GRO_CB(p)->last)
+	if (NAPI_GRO_CB(p)->last == p)
 		skb_shinfo(p)->frag_list = skb;
 	else
 		NAPI_GRO_CB(p)->last->next = skb;
@@ -3227,6 +3313,32 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
 	return elt;
 }
 
+/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given
+ * sglist without mark the sg which contain last skb data as the end.
+ * So the caller can mannipulate sg list as will when padding new data after
+ * the first call without calling sg_unmark_end to expend sg list.
+ *
+ * Scenario to use skb_to_sgvec_nomark:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec_nomark(payload1)
+ * 3. skb_to_sgvec_nomark(payload2)
+ *
+ * This is equivalent to:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec(payload1)
+ * 3. sg_unmark_end
+ * 4. skb_to_sgvec(payload2)
+ *
+ * When mapping mutilple payload conditionally, skb_to_sgvec_nomark
+ * is more preferable.
+ */
+int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
+			int offset, int len)
+{
+	return __skb_to_sgvec(skb, sg, offset, len);
+}
+EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark);
+
 int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
 {
 	int nsg = __skb_to_sgvec(skb, sg, offset, len);
@@ -3359,8 +3471,6 @@ static void sock_rmem_free(struct sk_buff *skb)
  */
 int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 {
-	int len = skb->len;
-
 	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
 	    (unsigned int)sk->sk_rcvbuf)
 		return -ENOMEM;
@@ -3375,7 +3485,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 
 	skb_queue_tail(&sk->sk_error_queue, skb);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, len);
+		sk->sk_data_ready(sk);
 	return 0;
 }
 EXPORT_SYMBOL(sock_queue_err_skb);
@@ -3468,6 +3578,238 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
 }
 EXPORT_SYMBOL_GPL(skb_partial_csum_set);
 
+static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len,
+			       unsigned int max)
+{
+	if (skb_headlen(skb) >= len)
+		return 0;
+
+	/* If we need to pullup then pullup to the max, so we
+	 * won't need to do it again.
+	 */
+	if (max > skb->len)
+		max = skb->len;
+
+	if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL)
+		return -ENOMEM;
+
+	if (skb_headlen(skb) < len)
+		return -EPROTO;
+
+	return 0;
+}
+
+#define MAX_TCP_HDR_LEN (15 * 4)
+
+static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb,
+				      typeof(IPPROTO_IP) proto,
+				      unsigned int off)
+{
+	switch (proto) {
+		int err;
+
+	case IPPROTO_TCP:
+		err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr),
+					  off + MAX_TCP_HDR_LEN);
+		if (!err && !skb_partial_csum_set(skb, off,
+						  offsetof(struct tcphdr,
+							   check)))
+			err = -EPROTO;
+		return err ? ERR_PTR(err) : &tcp_hdr(skb)->check;
+
+	case IPPROTO_UDP:
+		err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr),
+					  off + sizeof(struct udphdr));
+		if (!err && !skb_partial_csum_set(skb, off,
+						  offsetof(struct udphdr,
+							   check)))
+			err = -EPROTO;
+		return err ? ERR_PTR(err) : &udp_hdr(skb)->check;
+	}
+
+	return ERR_PTR(-EPROTO);
+}
+
+/* This value should be large enough to cover a tagged ethernet header plus
+ * maximally sized IP and TCP or UDP headers.
+ */
+#define MAX_IP_HDR_LEN 128
+
+static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate)
+{
+	unsigned int off;
+	bool fragment;
+	__sum16 *csum;
+	int err;
+
+	fragment = false;
+
+	err = skb_maybe_pull_tail(skb,
+				  sizeof(struct iphdr),
+				  MAX_IP_HDR_LEN);
+	if (err < 0)
+		goto out;
+
+	if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF))
+		fragment = true;
+
+	off = ip_hdrlen(skb);
+
+	err = -EPROTO;
+
+	if (fragment)
+		goto out;
+
+	csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off);
+	if (IS_ERR(csum))
+		return PTR_ERR(csum);
+
+	if (recalculate)
+		*csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+					   ip_hdr(skb)->daddr,
+					   skb->len - off,
+					   ip_hdr(skb)->protocol, 0);
+	err = 0;
+
+out:
+	return err;
+}
+
+/* This value should be large enough to cover a tagged ethernet header plus
+ * an IPv6 header, all options, and a maximal TCP or UDP header.
+ */
+#define MAX_IPV6_HDR_LEN 256
+
+#define OPT_HDR(type, skb, off) \
+	(type *)(skb_network_header(skb) + (off))
+
+static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
+{
+	int err;
+	u8 nexthdr;
+	unsigned int off;
+	unsigned int len;
+	bool fragment;
+	bool done;
+	__sum16 *csum;
+
+	fragment = false;
+	done = false;
+
+	off = sizeof(struct ipv6hdr);
+
+	err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN);
+	if (err < 0)
+		goto out;
+
+	nexthdr = ipv6_hdr(skb)->nexthdr;
+
+	len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
+	while (off <= len && !done) {
+		switch (nexthdr) {
+		case IPPROTO_DSTOPTS:
+		case IPPROTO_HOPOPTS:
+		case IPPROTO_ROUTING: {
+			struct ipv6_opt_hdr *hp;
+
+			err = skb_maybe_pull_tail(skb,
+						  off +
+						  sizeof(struct ipv6_opt_hdr),
+						  MAX_IPV6_HDR_LEN);
+			if (err < 0)
+				goto out;
+
+			hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
+			nexthdr = hp->nexthdr;
+			off += ipv6_optlen(hp);
+			break;
+		}
+		case IPPROTO_AH: {
+			struct ip_auth_hdr *hp;
+
+			err = skb_maybe_pull_tail(skb,
+						  off +
+						  sizeof(struct ip_auth_hdr),
+						  MAX_IPV6_HDR_LEN);
+			if (err < 0)
+				goto out;
+
+			hp = OPT_HDR(struct ip_auth_hdr, skb, off);
+			nexthdr = hp->nexthdr;
+			off += ipv6_authlen(hp);
+			break;
+		}
+		case IPPROTO_FRAGMENT: {
+			struct frag_hdr *hp;
+
+			err = skb_maybe_pull_tail(skb,
+						  off +
+						  sizeof(struct frag_hdr),
+						  MAX_IPV6_HDR_LEN);
+			if (err < 0)
+				goto out;
+
+			hp = OPT_HDR(struct frag_hdr, skb, off);
+
+			if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
+				fragment = true;
+
+			nexthdr = hp->nexthdr;
+			off += sizeof(struct frag_hdr);
+			break;
+		}
+		default:
+			done = true;
+			break;
+		}
+	}
+
+	err = -EPROTO;
+
+	if (!done || fragment)
+		goto out;
+
+	csum = skb_checksum_setup_ip(skb, nexthdr, off);
+	if (IS_ERR(csum))
+		return PTR_ERR(csum);
+
+	if (recalculate)
+		*csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+					 &ipv6_hdr(skb)->daddr,
+					 skb->len - off, nexthdr, 0);
+	err = 0;
+
+out:
+	return err;
+}
+
+/**
+ * skb_checksum_setup - set up partial checksum offset
+ * @skb: the skb to set up
+ * @recalculate: if true the pseudo-header checksum will be recalculated
+ */
+int skb_checksum_setup(struct sk_buff *skb, bool recalculate)
+{
+	int err;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		err = skb_checksum_setup_ipv4(skb, recalculate);
+		break;
+
+	case htons(ETH_P_IPV6):
+		err = skb_checksum_setup_ipv6(skb, recalculate);
+		break;
+
+	default:
+		err = -EPROTO;
+		break;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(skb_checksum_setup);
+
 void __skb_warn_lro_forwarding(const struct sk_buff *skb)
 {
 	net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n",
@@ -3584,7 +3926,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->skb_iif = 0;
-	skb->local_df = 0;
+	skb->ignore_df = 0;
 	skb_dst_drop(skb);
 	skb->mark = 0;
 	secpath_reset(skb);
@@ -3592,3 +3934,28 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	nf_reset_trace(skb);
 }
 EXPORT_SYMBOL_GPL(skb_scrub_packet);
+
+/**
+ * skb_gso_transport_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_transport_seglen is used to determine the real size of the
+ * individual segments, including Layer4 headers (TCP/UDP).
+ *
+ * The MAC/L2 or network (IP, IPv6) headers are not accounted for.
+ */
+unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
+{
+	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+	if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+		return tcp_hdrlen(skb) + shinfo->gso_size;
+
+	/* UFO sets gso_size to the size of the fragmentation
+	 * payload, i.e. the size of the L4 (UDP) header is already
+	 * accounted for.
+	 */
+	return shinfo->gso_size;
+}
+EXPORT_SYMBOL_GPL(skb_gso_transport_seglen);
diff --git a/net/core/sock.c b/net/core/sock.c
index ab20ed9b0f3..026e01f7027 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -145,6 +145,55 @@
 static DEFINE_MUTEX(proto_list_mutex);
 static LIST_HEAD(proto_list);
 
+/**
+ * sk_ns_capable - General socket capability test
+ * @sk: Socket to use a capability on or through
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket had when the socket was
+ * created and the current process has the capability @cap in the user
+ * namespace @user_ns.
+ */
+bool sk_ns_capable(const struct sock *sk,
+		   struct user_namespace *user_ns, int cap)
+{
+	return file_ns_capable(sk->sk_socket->file, user_ns, cap) &&
+		ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(sk_ns_capable);
+
+/**
+ * sk_capable - Socket global capability test
+ * @sk: Socket to use a capability on or through
+ * @cap: The global capbility to use
+ *
+ * Test to see if the opener of the socket had when the socket was
+ * created and the current process has the capability @cap in all user
+ * namespaces.
+ */
+bool sk_capable(const struct sock *sk, int cap)
+{
+	return sk_ns_capable(sk, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(sk_capable);
+
+/**
+ * sk_net_capable - Network namespace socket capability test
+ * @sk: Socket to use a capability on or through
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket had when the socke was created
+ * and the current process has the capability @cap over the network namespace
+ * the socket is a member of.
+ */
+bool sk_net_capable(const struct sock *sk, int cap)
+{
+	return sk_ns_capable(sk, sock_net(sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(sk_net_capable);
+
+
 #ifdef CONFIG_MEMCG_KMEM
 int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
@@ -428,7 +477,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	spin_unlock_irqrestore(&list->lock, flags);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb_len);
+		sk->sk_data_ready(sk);
 	return 0;
 }
 EXPORT_SYMBOL(sock_queue_rcv_skb);
@@ -735,7 +784,7 @@ set_rcvbuf:
 		break;
 
 	case SO_NO_CHECK:
-		sk->sk_no_check = valbool;
+		sk->sk_no_check_tx = valbool;
 		break;
 
 	case SO_PRIORITY:
@@ -882,7 +931,7 @@ set_rcvbuf:
 
 	case SO_PEEK_OFF:
 		if (sock->ops->set_peek_off)
-			sock->ops->set_peek_off(sk, val);
+			ret = sock->ops->set_peek_off(sk, val);
 		else
 			ret = -EOPNOTSUPP;
 		break;
@@ -925,8 +974,8 @@ set_rcvbuf:
 EXPORT_SYMBOL(sock_setsockopt);
 
 
-void cred_to_ucred(struct pid *pid, const struct cred *cred,
-		   struct ucred *ucred)
+static void cred_to_ucred(struct pid *pid, const struct cred *cred,
+			  struct ucred *ucred)
 {
 	ucred->pid = pid_vnr(pid);
 	ucred->uid = ucred->gid = -1;
@@ -937,7 +986,6 @@ void cred_to_ucred(struct pid *pid, const struct cred *cred,
 		ucred->gid = from_kgid_munged(current_ns, cred->egid);
 	}
 }
-EXPORT_SYMBOL_GPL(cred_to_ucred);
 
 int sock_getsockopt(struct socket *sock, int level, int optname,
 		    char __user *optval, int __user *optlen)
@@ -1016,7 +1064,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_NO_CHECK:
-		v.val = sk->sk_no_check;
+		v.val = sk->sk_no_check_tx;
 		break;
 
 	case SO_PRIORITY:
@@ -1168,6 +1216,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sock_flag(sk, SOCK_FILTER_LOCKED);
 		break;
 
+	case SO_BPF_EXTENSIONS:
+		v.val = bpf_tell_extensions();
+		break;
+
 	case SO_SELECT_ERR_QUEUE:
 		v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
 		break;
@@ -1308,19 +1360,7 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
 	module_put(owner);
 }
 
-#if IS_ENABLED(CONFIG_NET_CLS_CGROUP)
-void sock_update_classid(struct sock *sk)
-{
-	u32 classid;
-
-	classid = task_cls_classid(current);
-	if (classid != sk->sk_classid)
-		sk->sk_classid = classid;
-}
-EXPORT_SYMBOL(sock_update_classid);
-#endif
-
-#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 void sock_update_netprioidx(struct sock *sk)
 {
 	if (in_interrupt())
@@ -1666,22 +1706,6 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
 EXPORT_SYMBOL(sock_wmalloc);
 
 /*
- * Allocate a skb from the socket's receive buffer.
- */
-struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
-			     gfp_t priority)
-{
-	if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) {
-		struct sk_buff *skb = alloc_skb(size, priority);
-		if (skb) {
-			skb_set_owner_r(skb, sk);
-			return skb;
-		}
-	}
-	return NULL;
-}
-
-/*
  * Allocate a memory block from the socket's option memory buffer.
  */
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
@@ -1800,7 +1824,9 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 			while (order) {
 				if (npages >= 1 << order) {
 					page = alloc_pages(sk->sk_allocation |
-							   __GFP_COMP | __GFP_NOWARN,
+							   __GFP_COMP |
+							   __GFP_NOWARN |
+							   __GFP_NORETRY,
 							   order);
 					if (page)
 						goto fill_page;
@@ -1865,14 +1891,12 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio)
 		put_page(pfrag->page);
 	}
 
-	/* We restrict high order allocations to users that can afford to wait */
-	order = (prio & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0;
-
+	order = SKB_FRAG_PAGE_ORDER;
 	do {
 		gfp_t gfp = prio;
 
 		if (order)
-			gfp |= __GFP_COMP | __GFP_NOWARN;
+			gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
 		pfrag->page = alloc_pages(gfp, order);
 		if (likely(pfrag->page)) {
 			pfrag->offset = 0;
@@ -2221,7 +2245,7 @@ static void sock_def_error_report(struct sock *sk)
 	rcu_read_unlock();
 }
 
-static void sock_def_readable(struct sock *sk, int len)
+static void sock_def_readable(struct sock *sk)
 {
 	struct socket_wq *wq;
 
@@ -2382,10 +2406,13 @@ void release_sock(struct sock *sk)
 	if (sk->sk_backlog.tail)
 		__release_sock(sk);
 
+	/* Warning : release_cb() might need to release sk ownership,
+	 * ie call sock_release_ownership(sk) before us.
+	 */
 	if (sk->sk_prot->release_cb)
 		sk->sk_prot->release_cb(sk);
 
-	sk->sk_lock.owned = 0;
+	sock_release_ownership(sk);
 	if (waitqueue_active(&sk->sk_lock.wq))
 		wake_up(&sk->sk_lock.wq);
 	spin_unlock_bh(&sk->sk_lock.slock);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index a0e9cf6379d..a4216a4c957 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -49,38 +49,35 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
 }
 EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
 
-int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
 			     struct sk_buff *skb, int attrtype)
 {
-	struct nlattr *attr;
+	struct sock_fprog_kern *fprog;
 	struct sk_filter *filter;
-	unsigned int len;
+	struct nlattr *attr;
+	unsigned int flen;
 	int err = 0;
 
-	if (!ns_capable(user_ns, CAP_NET_ADMIN)) {
+	if (!may_report_filterinfo) {
 		nla_reserve(skb, attrtype, 0);
 		return 0;
 	}
 
 	rcu_read_lock();
-
 	filter = rcu_dereference(sk->sk_filter);
-	len = filter ? filter->len * sizeof(struct sock_filter) : 0;
+	if (!filter)
+		goto out;
 
-	attr = nla_reserve(skb, attrtype, len);
+	fprog = filter->orig_prog;
+	flen = sk_filter_proglen(fprog);
+
+	attr = nla_reserve(skb, attrtype, flen);
 	if (attr == NULL) {
 		err = -EMSGSIZE;
 		goto out;
 	}
 
-	if (filter) {
-		struct sock_filter *fb = (struct sock_filter *)nla_data(attr);
-		int i;
-
-		for (i = 0; i < filter->len; i++, fb++)
-			sk_decode_filter(&filter->insns[i], fb);
-	}
-
+	memcpy(nla_data(attr), fprog->filter, flen);
 out:
 	rcu_read_unlock();
 	return err;
diff --git a/net/core/stream.c b/net/core/stream.c
index 512f0a24269..301c05f2606 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -122,7 +122,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 	DEFINE_WAIT(wait);
 
 	if (sk_stream_memory_free(sk))
-		current_timeo = vm_wait = (net_random() % (HZ / 5)) + 2;
+		current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2;
 
 	while (1) {
 		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cca44419090..cf9cd13509a 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -122,7 +122,8 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
 				synchronize_rcu();
 				kfree(cur);
 			} else if (!cur && cpumask_test_cpu(i, mask)) {
-				cur = kzalloc(len, GFP_KERNEL);
+				cur = kzalloc_node(len, GFP_KERNEL,
+						   cpu_to_node(i));
 				if (!cur) {
 					/* not unwinding previous changes */
 					ret = -ENOMEM;
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 661b5a40ec1..6521dfd8b7c 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -23,16 +23,11 @@
 #include <linux/skbuff.h>
 #include <linux/export.h>
 
-static struct sock_filter ptp_filter[] = {
-	PTP_FILTER
-};
-
 static unsigned int classify(const struct sk_buff *skb)
 {
-	if (likely(skb->dev &&
-		   skb->dev->phydev &&
+	if (likely(skb->dev && skb->dev->phydev &&
 		   skb->dev->phydev->drv))
-		return sk_run_filter(skb, ptp_filter);
+		return ptp_classify_raw(skb);
 	else
 		return PTP_CLASS_NONE;
 }
@@ -60,11 +55,13 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
 		if (likely(phydev->drv->txtstamp)) {
 			if (!atomic_inc_not_zero(&sk->sk_refcnt))
 				return;
+
 			clone = skb_clone(skb, GFP_ATOMIC);
 			if (!clone) {
 				sock_put(sk);
 				return;
 			}
+
 			clone->sk = sk;
 			phydev->drv->txtstamp(phydev, clone, type);
 		}
@@ -89,12 +86,15 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	}
 
 	*skb_hwtstamps(skb) = *hwtstamps;
+
 	serr = SKB_EXT_ERR(skb);
 	memset(serr, 0, sizeof(*serr));
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 	skb->sk = NULL;
+
 	err = sock_queue_err_skb(sk, skb);
+
 	sock_put(sk);
 	if (err)
 		kfree_skb(skb);
@@ -132,8 +132,3 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb)
 	return false;
 }
 EXPORT_SYMBOL_GPL(skb_defer_rx_timestamp);
-
-void __init skb_timestamping_init(void)
-{
-	BUG_ON(sk_chk_filter(ptp_filter, ARRAY_SIZE(ptp_filter)));
-}
diff --git a/net/core/tso.c b/net/core/tso.c
new file mode 100644
index 00000000000..8c3203c585b
--- /dev/null
+++ b/net/core/tso.c
@@ -0,0 +1,77 @@
+#include <linux/export.h>
+#include <net/ip.h>
+#include <net/tso.h>
+
+/* Calculate expected number of TX descriptors */
+int tso_count_descs(struct sk_buff *skb)
+{
+	/* The Marvell Way */
+	return skb_shinfo(skb)->gso_segs * 2 + skb_shinfo(skb)->nr_frags;
+}
+EXPORT_SYMBOL(tso_count_descs);
+
+void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso,
+		   int size, bool is_last)
+{
+	struct iphdr *iph;
+	struct tcphdr *tcph;
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	int mac_hdr_len = skb_network_offset(skb);
+
+	memcpy(hdr, skb->data, hdr_len);
+	iph = (struct iphdr *)(hdr + mac_hdr_len);
+	iph->id = htons(tso->ip_id);
+	iph->tot_len = htons(size + hdr_len - mac_hdr_len);
+	tcph = (struct tcphdr *)(hdr + skb_transport_offset(skb));
+	tcph->seq = htonl(tso->tcp_seq);
+	tso->ip_id++;
+
+	if (!is_last) {
+		/* Clear all special flags for not last packet */
+		tcph->psh = 0;
+		tcph->fin = 0;
+		tcph->rst = 0;
+	}
+}
+EXPORT_SYMBOL(tso_build_hdr);
+
+void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size)
+{
+	tso->tcp_seq += size;
+	tso->size -= size;
+	tso->data += size;
+
+	if ((tso->size == 0) &&
+	    (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx];
+
+		/* Move to next segment */
+		tso->size = frag->size;
+		tso->data = page_address(frag->page.p) + frag->page_offset;
+		tso->next_frag_idx++;
+	}
+}
+EXPORT_SYMBOL(tso_build_data);
+
+void tso_start(struct sk_buff *skb, struct tso_t *tso)
+{
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+
+	tso->ip_id = ntohs(ip_hdr(skb)->id);
+	tso->tcp_seq = ntohl(tcp_hdr(skb)->seq);
+	tso->next_frag_idx = 0;
+
+	/* Build first data */
+	tso->size = skb_headlen(skb) - hdr_len;
+	tso->data = skb->data + hdr_len;
+	if ((tso->size == 0) &&
+	    (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx];
+
+		/* Move to next segment */
+		tso->size = frag->size;
+		tso->data = page_address(frag->page.p) + frag->page_offset;
+		tso->next_frag_idx++;
+	}
+}
+EXPORT_SYMBOL(tso_start);
diff --git a/net/core/utils.c b/net/core/utils.c
index 2f737bf90b3..eed34338736 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w)
 {
 	struct __net_random_once_work *work =
 		container_of(w, struct __net_random_once_work, work);
-	if (!static_key_enabled(work->key))
-		static_key_slow_inc(work->key);
+	BUG_ON(!static_key_enabled(work->key));
+	static_key_slow_dec(work->key);
 	kfree(work);
 }
 
@@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key)
 }
 
 bool __net_get_random_once(void *buf, int nbytes, bool *done,
-			   struct static_key *done_key)
+			   struct static_key *once_key)
 {
 	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
@@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done,
 	*done = true;
 	spin_unlock_irqrestore(&lock, flags);
 
-	__net_random_once_disable_jump(done_key);
+	__net_random_once_disable_jump(once_key);
 
 	return true;
 }
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 66fbe1948fb..f8b98d89c28 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1669,7 +1669,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlmsghdr *reply_nlh = NULL;
 	const struct reply_func *fn;
 
-	if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN))
+	if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX,
@@ -1688,21 +1688,17 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (!tb[DCB_ATTR_IFNAME])
 		return -EINVAL;
 
-	netdev = dev_get_by_name(net, nla_data(tb[DCB_ATTR_IFNAME]));
+	netdev = __dev_get_by_name(net, nla_data(tb[DCB_ATTR_IFNAME]));
 	if (!netdev)
 		return -ENODEV;
 
-	if (!netdev->dcbnl_ops) {
-		ret = -EOPNOTSUPP;
-		goto out;
-	}
+	if (!netdev->dcbnl_ops)
+		return -EOPNOTSUPP;
 
 	reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, portid, nlh->nlmsg_seq,
 				 nlh->nlmsg_flags, &reply_nlh);
-	if (!reply_skb) {
-		ret = -ENOBUFS;
-		goto out;
-	}
+	if (!reply_skb)
+		return -ENOBUFS;
 
 	ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb);
 	if (ret < 0) {
@@ -1714,7 +1710,6 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ret = rtnl_unicast(reply_skb, net, portid);
 out:
-	dev_put(netdev);
 	return ret;
 }
 
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 30948784dd5..c67816647cc 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -479,7 +479,6 @@ void dccp_feat_list_purge(struct list_head *fn_list);
 
 int dccp_insert_options(struct sock *sk, struct sk_buff *skb);
 int dccp_insert_options_rsk(struct dccp_request_sock *, struct sk_buff *);
-int dccp_insert_option_elapsed_time(struct sk_buff *skb, u32 elapsed);
 u32 dccp_timestamp(void);
 void dccp_timestamping_init(void);
 int dccp_insert_option(struct sk_buff *skb, unsigned char option,
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 14cdafad7a9..3c8ec7d4a34 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -28,7 +28,7 @@ static void dccp_enqueue_skb(struct sock *sk, struct sk_buff *skb)
 	__skb_pull(skb, dccp_hdr(skb)->dccph_doff * 4);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
 	skb_set_owner_r(skb, sk);
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 }
 
 static void dccp_fin(struct sock *sk, struct sk_buff *skb)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index d9f65fc66db..6ca645c4b48 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -75,7 +75,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
 			      RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
 			      IPPROTO_DCCP,
-			      orig_sport, orig_dport, sk, true);
+			      orig_sport, orig_dport, sk);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
@@ -989,6 +989,7 @@ static const struct net_protocol dccp_v4_protocol = {
 	.err_handler	= dccp_v4_err,
 	.no_policy	= 1,
 	.netns_ok	= 1,
+	.icmp_strict_tag_validation = 1,
 };
 
 static const struct proto_ops inet_dccp_ops = {
@@ -1023,7 +1024,6 @@ static struct inet_protosw dccp_v4_protosw = {
 	.protocol	= IPPROTO_DCCP,
 	.prot		= &dccp_v4_prot,
 	.ops		= &inet_dccp_ops,
-	.no_check	= 0,
 	.flags		= INET_PROTOSW_ICSK,
 };
 
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 4ac71ff7c2e..4db3c2a1679 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -141,6 +141,9 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (type == ICMPV6_PKT_TOOBIG) {
 		struct dst_entry *dst = NULL;
 
+		if (!ip6_sk_accept_pmtu(sk))
+			goto out;
+
 		if (sock_owned_by_user(sk))
 			goto out;
 		if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
@@ -237,7 +240,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 
 	final_p = fl6_update_dst(&fl6, np->opt, &final);
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		dst = NULL;
@@ -301,7 +304,7 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
 	security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6));
 
 	/* sk = NULL, but it is safe for now. RST socket required. */
-	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false);
+	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(skb, dst);
 		ip6_xmit(ctl_sk, skb, &fl6, NULL, 0);
@@ -512,7 +515,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 		fl6.fl6_sport = htons(ireq->ir_num);
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
+		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 		if (IS_ERR(dst))
 			goto out;
 	}
@@ -851,7 +854,6 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
-			usin->sin6_addr = flowlabel->dst;
 			fl6_sock_release(flowlabel);
 		}
 	}
@@ -932,7 +934,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	final_p = fl6_update_dst(&fl6, np->opt, &final);
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto failure;
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 9e2f78bc155..c69eb9c4fbb 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -237,7 +237,7 @@ int dccp_child_process(struct sock *parent, struct sock *child,
 
 		/* Wakeup parent, send SIGIO */
 		if (state == DCCP_RESPOND && child->sk_state != state)
-			parent->sk_data_ready(parent, 0);
+			parent->sk_data_ready(parent);
 	} else {
 		/* Alas, it is possible again, because we do lookup
 		 * in main socket hash table and lock on listening
diff --git a/net/dccp/options.c b/net/dccp/options.c
index a58e0b63405..9bce31886bd 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -343,38 +343,6 @@ static inline int dccp_elapsed_time_len(const u32 elapsed_time)
 	return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4;
 }
 
-/* FIXME: This function is currently not used anywhere */
-int dccp_insert_option_elapsed_time(struct sk_buff *skb, u32 elapsed_time)
-{
-	const int elapsed_time_len = dccp_elapsed_time_len(elapsed_time);
-	const int len = 2 + elapsed_time_len;
-	unsigned char *to;
-
-	if (elapsed_time_len == 0)
-		return 0;
-
-	if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
-		return -1;
-
-	DCCP_SKB_CB(skb)->dccpd_opt_len += len;
-
-	to    = skb_push(skb, len);
-	*to++ = DCCPO_ELAPSED_TIME;
-	*to++ = len;
-
-	if (elapsed_time_len == 2) {
-		const __be16 var16 = htons((u16)elapsed_time);
-		memcpy(to, &var16, 2);
-	} else {
-		const __be32 var32 = htonl(elapsed_time);
-		memcpy(to, &var32, 4);
-	}
-
-	return 0;
-}
-
-EXPORT_SYMBOL_GPL(dccp_insert_option_elapsed_time);
-
 static int dccp_insert_option_timestamp(struct sk_buff *skb)
 {
 	__be32 now = htonl(dccp_timestamp());
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 8876078859d..0248e8a3460 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -138,7 +138,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 
 		DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
 
-		err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl);
+		err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
 		return net_xmit_eval(err);
 	}
 	return -ENOBUFS;
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index 4c6bdf97a65..595ddf0459d 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -152,17 +152,6 @@ static const struct file_operations dccpprobe_fops = {
 	.llseek  = noop_llseek,
 };
 
-static __init int setup_jprobe(void)
-{
-	int ret = register_jprobe(&dccp_send_probe);
-
-	if (ret) {
-		request_module("dccp");
-		ret = register_jprobe(&dccp_send_probe);
-	}
-	return ret;
-}
-
 static __init int dccpprobe_init(void)
 {
 	int ret = -ENOMEM;
@@ -174,7 +163,13 @@ static __init int dccpprobe_init(void)
 	if (!proc_create(procname, S_IRUSR, init_net.proc_net, &dccpprobe_fops))
 		goto err0;
 
-	ret = setup_jprobe();
+	ret = register_jprobe(&dccp_send_probe);
+	if (ret) {
+		ret = request_module("dccp");
+		if (!ret)
+			ret = register_jprobe(&dccp_send_probe);
+	}
+
 	if (ret)
 		goto err1;
 
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index eb892b4f481..de2c1e71930 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1084,14 +1084,15 @@ EXPORT_SYMBOL_GPL(dccp_shutdown);
 
 static inline int dccp_mib_init(void)
 {
-	return snmp_mib_init((void __percpu **)dccp_statistics,
-			     sizeof(struct dccp_mib),
-			     __alignof__(struct dccp_mib));
+	dccp_statistics = alloc_percpu(struct dccp_mib);
+	if (!dccp_statistics)
+		return -ENOMEM;
+	return 0;
 }
 
 static inline void dccp_mib_exit(void)
 {
-	snmp_mib_free((void __percpu **)dccp_statistics);
+	free_percpu(dccp_statistics);
 }
 
 static int thash_entries;
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
index 607ab71b5a0..53731e45403 100644
--- a/net/dccp/sysctl.c
+++ b/net/dccp/sysctl.c
@@ -20,6 +20,7 @@
 
 /* Boundary values */
 static int		zero     = 0,
+			one      = 1,
 			u8_max   = 0xFF;
 static unsigned long	seqw_min = DCCPF_SEQ_WMIN,
 			seqw_max = 0xFFFFFFFF;		/* maximum on 32 bit */
@@ -58,7 +59,7 @@ static struct ctl_table dccp_default_table[] = {
 		.maxlen		= sizeof(sysctl_dccp_request_retries),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= &one,
 		.extra2		= &u8_max,
 	},
 	{
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 16f0b223102..1cd46a345cb 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -280,7 +280,7 @@ static ktime_t dccp_timestamp_seed;
  */
 u32 dccp_timestamp(void)
 {
-	s64 delta = ktime_us_delta(ktime_get_real(), dccp_timestamp_seed);
+	u64 delta = (u64)ktime_us_delta(ktime_get_real(), dccp_timestamp_seed);
 
 	do_div(delta, 10);
 	return delta;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index dd4d506ef92..ae011b46c07 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -481,7 +481,7 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf
 
 	sk->sk_backlog_rcv = dn_nsp_backlog_rcv;
 	sk->sk_destruct    = dn_destruct;
-	sk->sk_no_check    = 1;
+	sk->sk_no_check_tx = 1;
 	sk->sk_family      = PF_DECnet;
 	sk->sk_protocol    = 0;
 	sk->sk_allocation  = gfp;
@@ -1808,6 +1808,7 @@ out:
 		rv = (flags & MSG_PEEK) ? -sk->sk_err : sock_error(sk);
 
 	if ((rv >= 0) && msg->msg_name) {
+		__sockaddr_check_size(sizeof(struct sockaddr_dn));
 		memcpy(msg->msg_name, &scp->peer, sizeof(struct sockaddr_dn));
 		msg->msg_namelen = sizeof(struct sockaddr_dn);
 	}
@@ -1914,7 +1915,7 @@ static int dn_sendmsg(struct kiocb *iocb, struct socket *sock,
 	int err = 0;
 	size_t sent = 0;
 	int addr_len = msg->msg_namelen;
-	struct sockaddr_dn *addr = (struct sockaddr_dn *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_dn *, addr, msg->msg_name);
 	struct sk_buff *skb = NULL;
 	struct dn_skb_cb *cb;
 	size_t len;
@@ -2103,8 +2104,6 @@ static struct notifier_block dn_dev_notifier = {
 	.notifier_call = dn_device_event,
 };
 
-extern int dn_route_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *);
-
 static struct packet_type dn_dix_packet_type __read_mostly = {
 	.type =		cpu_to_be16(ETH_P_DNA_RT),
 	.func =		dn_route_rcv,
@@ -2352,9 +2351,6 @@ static const struct proto_ops dn_proto_ops = {
 	.sendpage =	sock_no_sendpage,
 };
 
-void dn_register_sysctl(void);
-void dn_unregister_sysctl(void);
-
 MODULE_DESCRIPTION("The Linux DECnet Network Protocol");
 MODULE_AUTHOR("Linux DECnet Project Team");
 MODULE_LICENSE("GPL");
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index dd0dfb25f4b..3b726f31c64 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -561,6 +561,7 @@ static const struct nla_policy dn_ifa_policy[IFA_MAX+1] = {
 	[IFA_LOCAL]		= { .type = NLA_U16 },
 	[IFA_LABEL]		= { .type = NLA_STRING,
 				    .len = IFNAMSIZ - 1 },
+	[IFA_FLAGS]		= { .type = NLA_U32 },
 };
 
 static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
@@ -573,7 +574,7 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct dn_ifaddr __rcu **ifap;
 	int err = -EINVAL;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
@@ -617,7 +618,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct dn_ifaddr *ifa;
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
@@ -648,7 +649,8 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ifa->ifa_local = nla_get_le16(tb[IFA_LOCAL]);
 	ifa->ifa_address = nla_get_le16(tb[IFA_ADDRESS]);
-	ifa->ifa_flags = ifm->ifa_flags;
+	ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) :
+					 ifm->ifa_flags;
 	ifa->ifa_scope = ifm->ifa_scope;
 	ifa->ifa_dev = dn_db;
 
@@ -669,7 +671,8 @@ static inline size_t dn_ifaddr_nlmsg_size(void)
 	return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
 	       + nla_total_size(IFNAMSIZ) /* IFA_LABEL */
 	       + nla_total_size(2) /* IFA_ADDRESS */
-	       + nla_total_size(2); /* IFA_LOCAL */
+	       + nla_total_size(2) /* IFA_LOCAL */
+	       + nla_total_size(4); /* IFA_FLAGS */
 }
 
 static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa,
@@ -677,6 +680,7 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa,
 {
 	struct ifaddrmsg *ifm;
 	struct nlmsghdr *nlh;
+	u32 ifa_flags = ifa->ifa_flags | IFA_F_PERMANENT;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags);
 	if (nlh == NULL)
@@ -685,7 +689,7 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa,
 	ifm = nlmsg_data(nlh);
 	ifm->ifa_family = AF_DECnet;
 	ifm->ifa_prefixlen = 16;
-	ifm->ifa_flags = ifa->ifa_flags | IFA_F_PERMANENT;
+	ifm->ifa_flags = ifa_flags;
 	ifm->ifa_scope = ifa->ifa_scope;
 	ifm->ifa_index = ifa->ifa_dev->dev->ifindex;
 
@@ -694,7 +698,8 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa,
 	    (ifa->ifa_local &&
 	     nla_put_le16(skb, IFA_LOCAL, ifa->ifa_local)) ||
 	    (ifa->ifa_label[0] &&
-	     nla_put_string(skb, IFA_LABEL, ifa->ifa_label)))
+	     nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) ||
+	     nla_put_u32(skb, IFA_FLAGS, ifa_flags))
 		goto nla_put_failure;
 	return nlmsg_end(skb, nlh);
 
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 57dc159245e..d332aefb084 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -505,7 +505,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *attrs[RTA_MAX+1];
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
@@ -530,7 +530,7 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *attrs[RTA_MAX+1];
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index c344163e6ac..fe5f01485d3 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -585,7 +585,6 @@ out:
 static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig, struct sk_buff_head *queue)
 {
 	int err;
-	int skb_len;
 
 	/* Cast skb->rcvbuf to unsigned... It's pointless, but reduces
 	   number of warnings when compiling with -W --ANK
@@ -600,12 +599,11 @@ static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig
 	if (err)
 		goto out;
 
-	skb_len = skb->len;
 	skb_set_owner_r(skb, sk);
 	skb_queue_tail(queue, skb);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb_len);
+		sk->sk_data_ready(sk);
 out:
 	return err;
 }
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index fe32388ea24..daccc4a36d8 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -752,7 +752,7 @@ static int dn_to_neigh_output(struct sk_buff *skb)
 	return n->output(n, skb);
 }
 
-static int dn_output(struct sk_buff *skb)
+static int dn_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct dn_route *rt = (struct dn_route *)dst;
@@ -838,6 +838,18 @@ drop:
  * Used to catch bugs. This should never normally get
  * called.
  */
+static int dn_rt_bug_sk(struct sock *sk, struct sk_buff *skb)
+{
+	struct dn_skb_cb *cb = DN_SKB_CB(skb);
+
+	net_dbg_ratelimited("dn_rt_bug: skb from:%04x to:%04x\n",
+			    le16_to_cpu(cb->src), le16_to_cpu(cb->dst));
+
+	kfree_skb(skb);
+
+	return NET_RX_DROP;
+}
+
 static int dn_rt_bug(struct sk_buff *skb)
 {
 	struct dn_skb_cb *cb = DN_SKB_CB(skb);
@@ -1288,8 +1300,6 @@ int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *fl, stru
 
 	err = __dn_route_output_key(pprt, fl, flags & MSG_TRYHARD);
 	if (err == 0 && fl->flowidn_proto) {
-		if (!(flags & MSG_DONTWAIT))
-			fl->flowidn_flags |= FLOWI_FLAG_CAN_SLEEP;
 		*pprt = xfrm_lookup(&init_net, *pprt,
 				    flowidn_to_flowi(fl), sk, 0);
 		if (IS_ERR(*pprt)) {
@@ -1465,7 +1475,7 @@ make_route:
 
 	rt->n = neigh;
 	rt->dst.lastuse = jiffies;
-	rt->dst.output = dn_rt_bug;
+	rt->dst.output = dn_rt_bug_sk;
 	switch (res.type) {
 	case RTN_UNICAST:
 		rt->dst.input = dn_forward;
@@ -1668,12 +1678,8 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 
 	if (fld.flowidn_iif) {
 		struct net_device *dev;
-		if ((dev = dev_get_by_index(&init_net, fld.flowidn_iif)) == NULL) {
-			kfree_skb(skb);
-			return -ENODEV;
-		}
-		if (!dev->dn_ptr) {
-			dev_put(dev);
+		dev = __dev_get_by_index(&init_net, fld.flowidn_iif);
+		if (!dev || !dev->dn_ptr) {
 			kfree_skb(skb);
 			return -ENODEV;
 		}
@@ -1695,8 +1701,6 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 		err = dn_route_output_key((struct dst_entry **)&rt, &fld, 0);
 	}
 
-	if (skb->dev)
-		dev_put(skb->dev);
 	skb->dev = NULL;
 	if (err)
 		goto out_free;
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index e83015cecfa..e4d9560a910 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -107,7 +107,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
 	if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
 		return;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		RCV_SKB_FAIL(-EPERM);
 
 	/* Eventually we might send routing messages too */
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index e7b6d53eef8..dd8696a3dbe 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -93,8 +93,8 @@ int dns_query(const char *type, const char *name, size_t namelen,
 	}
 
 	if (!namelen)
-		namelen = strlen(name);
-	if (namelen < 3)
+		namelen = strnlen(name, 256);
+	if (namelen < 3 || namelen > 255)
 		return -EINVAL;
 	desclen += namelen + 1;
 
@@ -149,7 +149,9 @@ int dns_query(const char *type, const char *name, size_t namelen,
 	if (!*_result)
 		goto put;
 
-	memcpy(*_result, upayload->data, len + 1);
+	memcpy(*_result, upayload->data, len);
+	(*_result)[len] = '\0';
+
 	if (_expiry)
 		*_expiry = rkey->expiry;
 
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 0eb5d5e76df..5db37cef50a 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -406,8 +406,9 @@ static int dsa_of_probe(struct platform_device *pdev)
 		goto out_free;
 	}
 
-	chip_index = 0;
+	chip_index = -1;
 	for_each_available_child_of_node(np, child) {
+		chip_index++;
 		cd = &pd->chip[chip_index];
 
 		cd->mii_bus = &mdio_bus->dev;
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 29d684ebca6..64c5af0a10d 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -156,7 +156,7 @@ static int dsa_slave_set_mac_address(struct net_device *dev, void *a)
 		dev_uc_del(master, dev->dev_addr);
 
 out:
-	memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
+	ether_addr_copy(dev->dev_addr, addr->sa_data);
 
 	return 0;
 }
@@ -346,7 +346,7 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 		return slave_dev;
 
 	slave_dev->features = master->vlan_features;
-	SET_ETHTOOL_OPS(slave_dev, &dsa_slave_ethtool_ops);
+	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
 	eth_hw_addr_inherit(slave_dev, master);
 	slave_dev->tx_queue_len = 0;
 
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 8f032bae60a..5dc638cad2e 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -156,7 +156,9 @@ EXPORT_SYMBOL(eth_rebuild_header);
  */
 __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
 {
-	struct ethhdr *eth;
+	unsigned short _service_access_point;
+	const unsigned short *sap;
+	const struct ethhdr *eth;
 
 	skb->dev = dev;
 	skb_reset_mac_header(skb);
@@ -194,7 +196,8 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
 	 *      layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
 	 *      won't work for fault tolerant netware but does for the rest.
 	 */
-	if (unlikely(skb->len >= 2 && *(unsigned short *)(skb->data) == 0xFFFF))
+	sap = skb_header_pointer(skb, 0, sizeof(*sap), &_service_access_point);
+	if (sap && *sap == 0xFFFF)
 		return htons(ETH_P_802_3);
 
 	/*
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index cac505f166d..e5302b7f7ca 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -209,7 +209,7 @@ static int slave_xmit(struct sk_buff *skb, struct hsr_priv *hsr_priv,
 	/* Address substitution (IEC62439-3 pp 26, 50): replace mac
 	 * address of outgoing frame with that of the outgoing slave's.
 	 */
-	memcpy(hsr_ethhdr->ethhdr.h_source, skb->dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(hsr_ethhdr->ethhdr.h_source, skb->dev->dev_addr);
 
 	return dev_queue_xmit(skb);
 }
@@ -346,7 +346,7 @@ static void send_hsr_supervision_frame(struct net_device *hsr_dev, u8 type)
 
 	/* Payload: MacAddressA */
 	hsr_sp = (typeof(hsr_sp)) skb_put(skb, sizeof(*hsr_sp));
-	memcpy(hsr_sp->MacAddressA, hsr_dev->dev_addr, ETH_ALEN);
+	ether_addr_copy(hsr_sp->MacAddressA, hsr_dev->dev_addr);
 
 	dev_queue_xmit(skb);
 	return;
@@ -493,7 +493,7 @@ static int check_slave_ok(struct net_device *dev)
 
 
 /* Default multicast address for HSR Supervision frames */
-static const unsigned char def_multicast_addr[ETH_ALEN] = {
+static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = {
 	0x01, 0x15, 0x4e, 0x00, 0x01, 0x00
 };
 
@@ -519,7 +519,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 	hsr_priv->announce_timer.function = hsr_announce;
 	hsr_priv->announce_timer.data = (unsigned long) hsr_priv;
 
-	memcpy(hsr_priv->sup_multicast_addr, def_multicast_addr, ETH_ALEN);
+	ether_addr_copy(hsr_priv->sup_multicast_addr, def_multicast_addr);
 	hsr_priv->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec;
 
 /* FIXME: should I modify the value of these?
@@ -547,7 +547,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 	hsr_dev->features |= NETIF_F_VLAN_CHALLENGED;
 
 	/* Set hsr_dev's MAC address to that of mac_slave1 */
-	memcpy(hsr_dev->dev_addr, hsr_priv->slave[0]->dev_addr, ETH_ALEN);
+	ether_addr_copy(hsr_dev->dev_addr, hsr_priv->slave[0]->dev_addr);
 
 	/* Set required header length */
 	for (i = 0; i < HSR_MAX_SLAVE; i++) {
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 4bdab152187..83e58449366 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -108,8 +108,8 @@ int hsr_create_self_node(struct list_head *self_node_db,
 	if (!node)
 		return -ENOMEM;
 
-	memcpy(node->MacAddressA, addr_a, ETH_ALEN);
-	memcpy(node->MacAddressB, addr_b, ETH_ALEN);
+	ether_addr_copy(node->MacAddressA, addr_a);
+	ether_addr_copy(node->MacAddressB, addr_b);
 
 	rcu_read_lock();
 	oldnode = list_first_or_null_rcu(self_node_db,
@@ -127,11 +127,6 @@ int hsr_create_self_node(struct list_head *self_node_db,
 	return 0;
 }
 
-static void node_entry_reclaim(struct rcu_head *rh)
-{
-	kfree(container_of(rh, struct node_entry, rcu_head));
-}
-
 
 /* Add/merge node to the database of nodes. 'skb' must contain an HSR
  * supervision frame.
@@ -175,7 +170,7 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv,
 	if (node && !ether_addr_equal(node->MacAddressA, hsr_sp->MacAddressA)) {
 		/* Node has changed its AddrA, frame was received from SlaveB */
 		list_del_rcu(&node->mac_list);
-		call_rcu(&node->rcu_head, node_entry_reclaim);
+		kfree_rcu(node, rcu_head);
 		node = NULL;
 	}
 
@@ -183,7 +178,7 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv,
 	    !ether_addr_equal(node->MacAddressB, hsr_ethsup->ethhdr.h_source)) {
 		/* Cables have been swapped */
 		list_del_rcu(&node->mac_list);
-		call_rcu(&node->rcu_head, node_entry_reclaim);
+		kfree_rcu(node, rcu_head);
 		node = NULL;
 	}
 
@@ -192,7 +187,7 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv,
 	    !ether_addr_equal(node->MacAddressA, hsr_ethsup->ethhdr.h_source)) {
 		/* Cables have been swapped */
 		list_del_rcu(&node->mac_list);
-		call_rcu(&node->rcu_head, node_entry_reclaim);
+		kfree_rcu(node, rcu_head);
 		node = NULL;
 	}
 
@@ -204,7 +199,7 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv,
 		/* Node is known, but frame was received from an unknown
 		 * address. Node is PICS_SUBS capable; merge its AddrB.
 		 */
-		memcpy(node->MacAddressB, hsr_ethsup->ethhdr.h_source, ETH_ALEN);
+		ether_addr_copy(node->MacAddressB, hsr_ethsup->ethhdr.h_source);
 		node->AddrB_if = dev_idx;
 		return node;
 	}
@@ -213,8 +208,8 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv,
 	if (!node)
 		return NULL;
 
-	memcpy(node->MacAddressA, hsr_sp->MacAddressA, ETH_ALEN);
-	memcpy(node->MacAddressB, hsr_ethsup->ethhdr.h_source, ETH_ALEN);
+	ether_addr_copy(node->MacAddressA, hsr_sp->MacAddressA);
+	ether_addr_copy(node->MacAddressB, hsr_ethsup->ethhdr.h_source);
 	if (!ether_addr_equal(hsr_sp->MacAddressA, hsr_ethsup->ethhdr.h_source))
 		node->AddrB_if = dev_idx;
 	else
@@ -255,7 +250,7 @@ void hsr_addr_subst_source(struct hsr_priv *hsr_priv, struct sk_buff *skb)
 	rcu_read_lock();
 	node = find_node_by_AddrB(&hsr_priv->node_db, ethhdr->h_source);
 	if (node)
-		memcpy(ethhdr->h_source, node->MacAddressA, ETH_ALEN);
+		ether_addr_copy(ethhdr->h_source, node->MacAddressA);
 	rcu_read_unlock();
 }
 
@@ -277,7 +272,7 @@ void hsr_addr_subst_dest(struct hsr_priv *hsr_priv, struct ethhdr *ethhdr,
 	rcu_read_lock();
 	node = find_node_by_AddrA(&hsr_priv->node_db, ethhdr->h_dest);
 	if (node && (node->AddrB_if == dev_idx))
-		memcpy(ethhdr->h_dest, node->MacAddressB, ETH_ALEN);
+		ether_addr_copy(ethhdr->h_dest, node->MacAddressB);
 	rcu_read_unlock();
 }
 
@@ -302,7 +297,7 @@ static bool seq_nr_after(u16 a, u16 b)
 
 void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx)
 {
-	if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) {
+	if ((dev_idx < 0) || (dev_idx >= HSR_MAX_SLAVE)) {
 		WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx);
 		return;
 	}
@@ -417,7 +412,7 @@ void hsr_prune_nodes(struct hsr_priv *hsr_priv)
 			hsr_nl_nodedown(hsr_priv, node->MacAddressA);
 			list_del_rcu(&node->mac_list);
 			/* Note that we need to free this entry later: */
-			call_rcu(&node->rcu_head, node_entry_reclaim);
+			kfree_rcu(node, rcu_head);
 		}
 	}
 	rcu_read_unlock();
@@ -433,13 +428,13 @@ void *hsr_get_next_node(struct hsr_priv *hsr_priv, void *_pos,
 		node = list_first_or_null_rcu(&hsr_priv->node_db,
 						struct node_entry, mac_list);
 		if (node)
-			memcpy(addr, node->MacAddressA, ETH_ALEN);
+			ether_addr_copy(addr, node->MacAddressA);
 		return node;
 	}
 
 	node = _pos;
 	list_for_each_entry_continue_rcu(node, &hsr_priv->node_db, mac_list) {
-		memcpy(addr, node->MacAddressA, ETH_ALEN);
+		ether_addr_copy(addr, node->MacAddressA);
 		return node;
 	}
 
@@ -467,7 +462,7 @@ int hsr_get_node_data(struct hsr_priv *hsr_priv,
 		return -ENOENT;	/* No such entry */
 	}
 
-	memcpy(addr_b, node->MacAddressB, ETH_ALEN);
+	ether_addr_copy(addr_b, node->MacAddressB);
 
 	tdiff = jiffies - node->time_in[HSR_DEV_SLAVE_A];
 	if (node->time_in_stale[HSR_DEV_SLAVE_A])
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index af68dd83a4e..3fee5218a69 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -138,8 +138,8 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event,
 			break;
 
 		if (dev == hsr_priv->slave[0])
-			memcpy(hsr_priv->dev->dev_addr,
-			       hsr_priv->slave[0]->dev_addr, ETH_ALEN);
+			ether_addr_copy(hsr_priv->dev->dev_addr,
+					hsr_priv->slave[0]->dev_addr);
 
 		/* Make sure we recognize frames from ourselves in hsr_rcv() */
 		res = hsr_create_self_node(&hsr_priv->self_node_db,
@@ -459,7 +459,7 @@ static int __init hsr_init(void)
 static void __exit hsr_exit(void)
 {
 	unregister_netdevice_notifier(&hsr_nb);
-	del_timer(&prune_timer);
+	del_timer_sync(&prune_timer);
 	hsr_netlink_exit();
 	dev_remove_pack(&hsr_pt);
 }
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
deleted file mode 100644
index 459e200c08a..00000000000
--- a/net/ieee802154/6lowpan.c
+++ /dev/null
@@ -1,1513 +0,0 @@
-/*
- * Copyright 2011, Siemens AG
- * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
- */
-
-/*
- * Based on patches from Jon Smirl <jonsmirl@gmail.com>
- * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- */
-
-/* Jon's code is based on 6lowpan implementation for Contiki which is:
- * Copyright (c) 2008, Swedish Institute of Computer Science.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Institute nor the names of its contributors
- *    may be used to endorse or promote products derived from this software
- *    without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- */
-
-#include <linux/bitops.h>
-#include <linux/if_arp.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/netdevice.h>
-#include <net/af_ieee802154.h>
-#include <net/ieee802154.h>
-#include <net/ieee802154_netdev.h>
-#include <net/ipv6.h>
-
-#include "6lowpan.h"
-
-/* TTL uncompression values */
-static const u8 lowpan_ttl_values[] = {0, 1, 64, 255};
-
-static LIST_HEAD(lowpan_devices);
-
-/* private device info */
-struct lowpan_dev_info {
-	struct net_device	*real_dev; /* real WPAN device ptr */
-	struct mutex		dev_list_mtx; /* mutex for list ops */
-	unsigned short		fragment_tag;
-};
-
-struct lowpan_dev_record {
-	struct net_device *ldev;
-	struct list_head list;
-};
-
-struct lowpan_fragment {
-	struct sk_buff		*skb;		/* skb to be assembled */
-	u16			length;		/* length to be assemled */
-	u32			bytes_rcv;	/* bytes received */
-	u16			tag;		/* current fragment tag */
-	struct timer_list	timer;		/* assembling timer */
-	struct list_head	list;		/* fragments list */
-};
-
-static LIST_HEAD(lowpan_fragments);
-static DEFINE_SPINLOCK(flist_lock);
-
-static inline struct
-lowpan_dev_info *lowpan_dev_info(const struct net_device *dev)
-{
-	return netdev_priv(dev);
-}
-
-static inline void lowpan_address_flip(u8 *src, u8 *dest)
-{
-	int i;
-	for (i = 0; i < IEEE802154_ADDR_LEN; i++)
-		(dest)[IEEE802154_ADDR_LEN - i - 1] = (src)[i];
-}
-
-/* list of all 6lowpan devices, uses for package delivering */
-/* print data in line */
-static inline void lowpan_raw_dump_inline(const char *caller, char *msg,
-				   unsigned char *buf, int len)
-{
-#ifdef DEBUG
-	if (msg)
-		pr_debug("(%s) %s: ", caller, msg);
-	print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE,
-		       16, 1, buf, len, false);
-#endif /* DEBUG */
-}
-
-/*
- * print data in a table format:
- *
- * addr: xx xx xx xx xx xx
- * addr: xx xx xx xx xx xx
- * ...
- */
-static inline void lowpan_raw_dump_table(const char *caller, char *msg,
-				   unsigned char *buf, int len)
-{
-#ifdef DEBUG
-	if (msg)
-		pr_debug("(%s) %s:\n", caller, msg);
-	print_hex_dump(KERN_DEBUG, "\t", DUMP_PREFIX_OFFSET,
-		       16, 1, buf, len, false);
-#endif /* DEBUG */
-}
-
-static u8
-lowpan_compress_addr_64(u8 **hc06_ptr, u8 shift, const struct in6_addr *ipaddr,
-		 const unsigned char *lladdr)
-{
-	u8 val = 0;
-
-	if (is_addr_mac_addr_based(ipaddr, lladdr))
-		val = 3; /* 0-bits */
-	else if (lowpan_is_iid_16_bit_compressable(ipaddr)) {
-		/* compress IID to 16 bits xxxx::XXXX */
-		memcpy(*hc06_ptr, &ipaddr->s6_addr16[7], 2);
-		*hc06_ptr += 2;
-		val = 2; /* 16-bits */
-	} else {
-		/* do not compress IID => xxxx::IID */
-		memcpy(*hc06_ptr, &ipaddr->s6_addr16[4], 8);
-		*hc06_ptr += 8;
-		val = 1; /* 64-bits */
-	}
-
-	return rol8(val, shift);
-}
-
-/*
- * Uncompress address function for source and
- * destination address(non-multicast).
- *
- * address_mode is sam value or dam value.
- */
-static int
-lowpan_uncompress_addr(struct sk_buff *skb,
-		struct in6_addr *ipaddr,
-		const u8 address_mode,
-		const struct ieee802154_addr *lladdr)
-{
-	bool fail;
-
-	switch (address_mode) {
-	case LOWPAN_IPHC_ADDR_00:
-		/* for global link addresses */
-		fail = lowpan_fetch_skb(skb, ipaddr->s6_addr, 16);
-		break;
-	case LOWPAN_IPHC_ADDR_01:
-		/* fe:80::XXXX:XXXX:XXXX:XXXX */
-		ipaddr->s6_addr[0] = 0xFE;
-		ipaddr->s6_addr[1] = 0x80;
-		fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[8], 8);
-		break;
-	case LOWPAN_IPHC_ADDR_02:
-		/* fe:80::ff:fe00:XXXX */
-		ipaddr->s6_addr[0] = 0xFE;
-		ipaddr->s6_addr[1] = 0x80;
-		ipaddr->s6_addr[11] = 0xFF;
-		ipaddr->s6_addr[12] = 0xFE;
-		fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[14], 2);
-		break;
-	case LOWPAN_IPHC_ADDR_03:
-		fail = false;
-		switch (lladdr->addr_type) {
-		case IEEE802154_ADDR_LONG:
-			/* fe:80::XXXX:XXXX:XXXX:XXXX
-			 *        \_________________/
-			 *              hwaddr
-			 */
-			ipaddr->s6_addr[0] = 0xFE;
-			ipaddr->s6_addr[1] = 0x80;
-			memcpy(&ipaddr->s6_addr[8], lladdr->hwaddr,
-					IEEE802154_ADDR_LEN);
-			/* second bit-flip (Universe/Local)
-			 * is done according RFC2464
-			 */
-			ipaddr->s6_addr[8] ^= 0x02;
-			break;
-		case IEEE802154_ADDR_SHORT:
-			/* fe:80::ff:fe00:XXXX
-			 *		  \__/
-			 *	       short_addr
-			 *
-			 * Universe/Local bit is zero.
-			 */
-			ipaddr->s6_addr[0] = 0xFE;
-			ipaddr->s6_addr[1] = 0x80;
-			ipaddr->s6_addr[11] = 0xFF;
-			ipaddr->s6_addr[12] = 0xFE;
-			ipaddr->s6_addr16[7] = htons(lladdr->short_addr);
-			break;
-		default:
-			pr_debug("Invalid addr_type set\n");
-			return -EINVAL;
-		}
-		break;
-	default:
-		pr_debug("Invalid address mode value: 0x%x\n", address_mode);
-		return -EINVAL;
-	}
-
-	if (fail) {
-		pr_debug("Failed to fetch skb data\n");
-		return -EIO;
-	}
-
-	lowpan_raw_dump_inline(NULL, "Reconstructed ipv6 addr is:\n",
-			ipaddr->s6_addr, 16);
-
-	return 0;
-}
-
-/* Uncompress address function for source context
- * based address(non-multicast).
- */
-static int
-lowpan_uncompress_context_based_src_addr(struct sk_buff *skb,
-		struct in6_addr *ipaddr,
-		const u8 sam)
-{
-	switch (sam) {
-	case LOWPAN_IPHC_ADDR_00:
-		/* unspec address ::
-		 * Do nothing, address is already ::
-		 */
-		break;
-	case LOWPAN_IPHC_ADDR_01:
-		/* TODO */
-	case LOWPAN_IPHC_ADDR_02:
-		/* TODO */
-	case LOWPAN_IPHC_ADDR_03:
-		/* TODO */
-		netdev_warn(skb->dev, "SAM value 0x%x not supported\n", sam);
-		return -EINVAL;
-	default:
-		pr_debug("Invalid sam value: 0x%x\n", sam);
-		return -EINVAL;
-	}
-
-	lowpan_raw_dump_inline(NULL,
-			"Reconstructed context based ipv6 src addr is:\n",
-			ipaddr->s6_addr, 16);
-
-	return 0;
-}
-
-/* Uncompress function for multicast destination address,
- * when M bit is set.
- */
-static int
-lowpan_uncompress_multicast_daddr(struct sk_buff *skb,
-		struct in6_addr *ipaddr,
-		const u8 dam)
-{
-	bool fail;
-
-	switch (dam) {
-	case LOWPAN_IPHC_DAM_00:
-		/* 00:  128 bits.  The full address
-		 * is carried in-line.
-		 */
-		fail = lowpan_fetch_skb(skb, ipaddr->s6_addr, 16);
-		break;
-	case LOWPAN_IPHC_DAM_01:
-		/* 01:  48 bits.  The address takes
-		 * the form ffXX::00XX:XXXX:XXXX.
-		 */
-		ipaddr->s6_addr[0] = 0xFF;
-		fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 1);
-		fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[11], 5);
-		break;
-	case LOWPAN_IPHC_DAM_10:
-		/* 10:  32 bits.  The address takes
-		 * the form ffXX::00XX:XXXX.
-		 */
-		ipaddr->s6_addr[0] = 0xFF;
-		fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 1);
-		fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[13], 3);
-		break;
-	case LOWPAN_IPHC_DAM_11:
-		/* 11:  8 bits.  The address takes
-		 * the form ff02::00XX.
-		 */
-		ipaddr->s6_addr[0] = 0xFF;
-		ipaddr->s6_addr[1] = 0x02;
-		fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[15], 1);
-		break;
-	default:
-		pr_debug("DAM value has a wrong value: 0x%x\n", dam);
-		return -EINVAL;
-	}
-
-	if (fail) {
-		pr_debug("Failed to fetch skb data\n");
-		return -EIO;
-	}
-
-	lowpan_raw_dump_inline(NULL, "Reconstructed ipv6 multicast addr is:\n",
-			ipaddr->s6_addr, 16);
-
-	return 0;
-}
-
-static void
-lowpan_compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb)
-{
-	struct udphdr *uh = udp_hdr(skb);
-
-	if (((uh->source & LOWPAN_NHC_UDP_4BIT_MASK) ==
-				LOWPAN_NHC_UDP_4BIT_PORT) &&
-	    ((uh->dest & LOWPAN_NHC_UDP_4BIT_MASK) ==
-				LOWPAN_NHC_UDP_4BIT_PORT)) {
-		pr_debug("UDP header: both ports compression to 4 bits\n");
-		**hc06_ptr = LOWPAN_NHC_UDP_CS_P_11;
-		**(hc06_ptr + 1) = /* subtraction is faster */
-		   (u8)((uh->dest - LOWPAN_NHC_UDP_4BIT_PORT) +
-		       ((uh->source & LOWPAN_NHC_UDP_4BIT_PORT) << 4));
-		*hc06_ptr += 2;
-	} else if ((uh->dest & LOWPAN_NHC_UDP_8BIT_MASK) ==
-			LOWPAN_NHC_UDP_8BIT_PORT) {
-		pr_debug("UDP header: remove 8 bits of dest\n");
-		**hc06_ptr = LOWPAN_NHC_UDP_CS_P_01;
-		memcpy(*hc06_ptr + 1, &uh->source, 2);
-		**(hc06_ptr + 3) = (u8)(uh->dest - LOWPAN_NHC_UDP_8BIT_PORT);
-		*hc06_ptr += 4;
-	} else if ((uh->source & LOWPAN_NHC_UDP_8BIT_MASK) ==
-			LOWPAN_NHC_UDP_8BIT_PORT) {
-		pr_debug("UDP header: remove 8 bits of source\n");
-		**hc06_ptr = LOWPAN_NHC_UDP_CS_P_10;
-		memcpy(*hc06_ptr + 1, &uh->dest, 2);
-		**(hc06_ptr + 3) = (u8)(uh->source - LOWPAN_NHC_UDP_8BIT_PORT);
-		*hc06_ptr += 4;
-	} else {
-		pr_debug("UDP header: can't compress\n");
-		**hc06_ptr = LOWPAN_NHC_UDP_CS_P_00;
-		memcpy(*hc06_ptr + 1, &uh->source, 2);
-		memcpy(*hc06_ptr + 3, &uh->dest, 2);
-		*hc06_ptr += 5;
-	}
-
-	/* checksum is always inline */
-	memcpy(*hc06_ptr, &uh->check, 2);
-	*hc06_ptr += 2;
-
-	/* skip the UDP header */
-	skb_pull(skb, sizeof(struct udphdr));
-}
-
-static inline int lowpan_fetch_skb_u8(struct sk_buff *skb, u8 *val)
-{
-	if (unlikely(!pskb_may_pull(skb, 1)))
-		return -EINVAL;
-
-	*val = skb->data[0];
-	skb_pull(skb, 1);
-
-	return 0;
-}
-
-static inline int lowpan_fetch_skb_u16(struct sk_buff *skb, u16 *val)
-{
-	if (unlikely(!pskb_may_pull(skb, 2)))
-		return -EINVAL;
-
-	*val = (skb->data[0] << 8) | skb->data[1];
-	skb_pull(skb, 2);
-
-	return 0;
-}
-
-static int
-lowpan_uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh)
-{
-	u8 tmp;
-
-	if (!uh)
-		goto err;
-
-	if (lowpan_fetch_skb_u8(skb, &tmp))
-		goto err;
-
-	if ((tmp & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) {
-		pr_debug("UDP header uncompression\n");
-		switch (tmp & LOWPAN_NHC_UDP_CS_P_11) {
-		case LOWPAN_NHC_UDP_CS_P_00:
-			memcpy(&uh->source, &skb->data[0], 2);
-			memcpy(&uh->dest, &skb->data[2], 2);
-			skb_pull(skb, 4);
-			break;
-		case LOWPAN_NHC_UDP_CS_P_01:
-			memcpy(&uh->source, &skb->data[0], 2);
-			uh->dest =
-			   skb->data[2] + LOWPAN_NHC_UDP_8BIT_PORT;
-			skb_pull(skb, 3);
-			break;
-		case LOWPAN_NHC_UDP_CS_P_10:
-			uh->source = skb->data[0] + LOWPAN_NHC_UDP_8BIT_PORT;
-			memcpy(&uh->dest, &skb->data[1], 2);
-			skb_pull(skb, 3);
-			break;
-		case LOWPAN_NHC_UDP_CS_P_11:
-			uh->source =
-			   LOWPAN_NHC_UDP_4BIT_PORT + (skb->data[0] >> 4);
-			uh->dest =
-			   LOWPAN_NHC_UDP_4BIT_PORT + (skb->data[0] & 0x0f);
-			skb_pull(skb, 1);
-			break;
-		default:
-			pr_debug("ERROR: unknown UDP format\n");
-			goto err;
-		}
-
-		pr_debug("uncompressed UDP ports: src = %d, dst = %d\n",
-			 uh->source, uh->dest);
-
-		/* copy checksum */
-		memcpy(&uh->check, &skb->data[0], 2);
-		skb_pull(skb, 2);
-
-		/*
-		 * UDP lenght needs to be infered from the lower layers
-		 * here, we obtain the hint from the remaining size of the
-		 * frame
-		 */
-		uh->len = htons(skb->len + sizeof(struct udphdr));
-		pr_debug("uncompressed UDP length: src = %d", uh->len);
-	} else {
-		pr_debug("ERROR: unsupported NH format\n");
-		goto err;
-	}
-
-	return 0;
-err:
-	return -EINVAL;
-}
-
-static int lowpan_header_create(struct sk_buff *skb,
-			   struct net_device *dev,
-			   unsigned short type, const void *_daddr,
-			   const void *_saddr, unsigned int len)
-{
-	u8 tmp, iphc0, iphc1, *hc06_ptr;
-	struct ipv6hdr *hdr;
-	const u8 *saddr = _saddr;
-	const u8 *daddr = _daddr;
-	u8 head[100];
-	struct ieee802154_addr sa, da;
-
-	/* TODO:
-	 * if this package isn't ipv6 one, where should it be routed?
-	 */
-	if (type != ETH_P_IPV6)
-		return 0;
-
-	hdr = ipv6_hdr(skb);
-	hc06_ptr = head + 2;
-
-	pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength  = %d\n"
-		 "\tnexthdr = 0x%02x\n\thop_lim = %d\n", hdr->version,
-		 ntohs(hdr->payload_len), hdr->nexthdr, hdr->hop_limit);
-
-	lowpan_raw_dump_table(__func__, "raw skb network header dump",
-		skb_network_header(skb), sizeof(struct ipv6hdr));
-
-	if (!saddr)
-		saddr = dev->dev_addr;
-
-	lowpan_raw_dump_inline(__func__, "saddr", (unsigned char *)saddr, 8);
-
-	/*
-	 * As we copy some bit-length fields, in the IPHC encoding bytes,
-	 * we sometimes use |=
-	 * If the field is 0, and the current bit value in memory is 1,
-	 * this does not work. We therefore reset the IPHC encoding here
-	 */
-	iphc0 = LOWPAN_DISPATCH_IPHC;
-	iphc1 = 0;
-
-	/* TODO: context lookup */
-
-	lowpan_raw_dump_inline(__func__, "daddr", (unsigned char *)daddr, 8);
-
-	/*
-	 * Traffic class, flow label
-	 * If flow label is 0, compress it. If traffic class is 0, compress it
-	 * We have to process both in the same time as the offset of traffic
-	 * class depends on the presence of version and flow label
-	 */
-
-	/* hc06 format of TC is ECN | DSCP , original one is DSCP | ECN */
-	tmp = (hdr->priority << 4) | (hdr->flow_lbl[0] >> 4);
-	tmp = ((tmp & 0x03) << 6) | (tmp >> 2);
-
-	if (((hdr->flow_lbl[0] & 0x0F) == 0) &&
-	     (hdr->flow_lbl[1] == 0) && (hdr->flow_lbl[2] == 0)) {
-		/* flow label can be compressed */
-		iphc0 |= LOWPAN_IPHC_FL_C;
-		if ((hdr->priority == 0) &&
-		   ((hdr->flow_lbl[0] & 0xF0) == 0)) {
-			/* compress (elide) all */
-			iphc0 |= LOWPAN_IPHC_TC_C;
-		} else {
-			/* compress only the flow label */
-			*hc06_ptr = tmp;
-			hc06_ptr += 1;
-		}
-	} else {
-		/* Flow label cannot be compressed */
-		if ((hdr->priority == 0) &&
-		   ((hdr->flow_lbl[0] & 0xF0) == 0)) {
-			/* compress only traffic class */
-			iphc0 |= LOWPAN_IPHC_TC_C;
-			*hc06_ptr = (tmp & 0xc0) | (hdr->flow_lbl[0] & 0x0F);
-			memcpy(hc06_ptr + 1, &hdr->flow_lbl[1], 2);
-			hc06_ptr += 3;
-		} else {
-			/* compress nothing */
-			memcpy(hc06_ptr, &hdr, 4);
-			/* replace the top byte with new ECN | DSCP format */
-			*hc06_ptr = tmp;
-			hc06_ptr += 4;
-		}
-	}
-
-	/* NOTE: payload length is always compressed */
-
-	/* Next Header is compress if UDP */
-	if (hdr->nexthdr == UIP_PROTO_UDP)
-		iphc0 |= LOWPAN_IPHC_NH_C;
-
-	if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) {
-		*hc06_ptr = hdr->nexthdr;
-		hc06_ptr += 1;
-	}
-
-	/*
-	 * Hop limit
-	 * if 1:   compress, encoding is 01
-	 * if 64:  compress, encoding is 10
-	 * if 255: compress, encoding is 11
-	 * else do not compress
-	 */
-	switch (hdr->hop_limit) {
-	case 1:
-		iphc0 |= LOWPAN_IPHC_TTL_1;
-		break;
-	case 64:
-		iphc0 |= LOWPAN_IPHC_TTL_64;
-		break;
-	case 255:
-		iphc0 |= LOWPAN_IPHC_TTL_255;
-		break;
-	default:
-		*hc06_ptr = hdr->hop_limit;
-		hc06_ptr += 1;
-		break;
-	}
-
-	/* source address compression */
-	if (is_addr_unspecified(&hdr->saddr)) {
-		pr_debug("source address is unspecified, setting SAC\n");
-		iphc1 |= LOWPAN_IPHC_SAC;
-	/* TODO: context lookup */
-	} else if (is_addr_link_local(&hdr->saddr)) {
-		pr_debug("source address is link-local\n");
-		iphc1 |= lowpan_compress_addr_64(&hc06_ptr,
-				LOWPAN_IPHC_SAM_BIT, &hdr->saddr, saddr);
-	} else {
-		pr_debug("send the full source address\n");
-		memcpy(hc06_ptr, &hdr->saddr.s6_addr16[0], 16);
-		hc06_ptr += 16;
-	}
-
-	/* destination address compression */
-	if (is_addr_mcast(&hdr->daddr)) {
-		pr_debug("destination address is multicast: ");
-		iphc1 |= LOWPAN_IPHC_M;
-		if (lowpan_is_mcast_addr_compressable8(&hdr->daddr)) {
-			pr_debug("compressed to 1 octet\n");
-			iphc1 |= LOWPAN_IPHC_DAM_11;
-			/* use last byte */
-			*hc06_ptr = hdr->daddr.s6_addr[15];
-			hc06_ptr += 1;
-		} else if (lowpan_is_mcast_addr_compressable32(&hdr->daddr)) {
-			pr_debug("compressed to 4 octets\n");
-			iphc1 |= LOWPAN_IPHC_DAM_10;
-			/* second byte + the last three */
-			*hc06_ptr = hdr->daddr.s6_addr[1];
-			memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[13], 3);
-			hc06_ptr += 4;
-		} else if (lowpan_is_mcast_addr_compressable48(&hdr->daddr)) {
-			pr_debug("compressed to 6 octets\n");
-			iphc1 |= LOWPAN_IPHC_DAM_01;
-			/* second byte + the last five */
-			*hc06_ptr = hdr->daddr.s6_addr[1];
-			memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[11], 5);
-			hc06_ptr += 6;
-		} else {
-			pr_debug("using full address\n");
-			iphc1 |= LOWPAN_IPHC_DAM_00;
-			memcpy(hc06_ptr, &hdr->daddr.s6_addr[0], 16);
-			hc06_ptr += 16;
-		}
-	} else {
-		/* TODO: context lookup */
-		if (is_addr_link_local(&hdr->daddr)) {
-			pr_debug("dest address is unicast and link-local\n");
-			iphc1 |= lowpan_compress_addr_64(&hc06_ptr,
-				LOWPAN_IPHC_DAM_BIT, &hdr->daddr, daddr);
-		} else {
-			pr_debug("dest address is unicast: using full one\n");
-			memcpy(hc06_ptr, &hdr->daddr.s6_addr16[0], 16);
-			hc06_ptr += 16;
-		}
-	}
-
-	/* UDP header compression */
-	if (hdr->nexthdr == UIP_PROTO_UDP)
-		lowpan_compress_udp_header(&hc06_ptr, skb);
-
-	head[0] = iphc0;
-	head[1] = iphc1;
-
-	skb_pull(skb, sizeof(struct ipv6hdr));
-	skb_reset_transport_header(skb);
-	memcpy(skb_push(skb, hc06_ptr - head), head, hc06_ptr - head);
-	skb_reset_network_header(skb);
-
-	lowpan_raw_dump_table(__func__, "raw skb data dump", skb->data,
-				skb->len);
-
-	/*
-	 * NOTE1: I'm still unsure about the fact that compression and WPAN
-	 * header are created here and not later in the xmit. So wait for
-	 * an opinion of net maintainers.
-	 */
-	/*
-	 * NOTE2: to be absolutely correct, we must derive PANid information
-	 * from MAC subif of the 'dev' and 'real_dev' network devices, but
-	 * this isn't implemented in mainline yet, so currently we assign 0xff
-	 */
-	{
-		mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA;
-		mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev);
-
-		/* prepare wpan address data */
-		sa.addr_type = IEEE802154_ADDR_LONG;
-		sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
-
-		memcpy(&(sa.hwaddr), saddr, 8);
-		/* intra-PAN communications */
-		da.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
-
-		/*
-		 * if the destination address is the broadcast address, use the
-		 * corresponding short address
-		 */
-		if (lowpan_is_addr_broadcast(daddr)) {
-			da.addr_type = IEEE802154_ADDR_SHORT;
-			da.short_addr = IEEE802154_ADDR_BROADCAST;
-		} else {
-			da.addr_type = IEEE802154_ADDR_LONG;
-			memcpy(&(da.hwaddr), daddr, IEEE802154_ADDR_LEN);
-
-			/* request acknowledgment */
-			mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ;
-		}
-
-		return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev,
-				type, (void *)&da, (void *)&sa, skb->len);
-	}
-}
-
-static int lowpan_give_skb_to_devices(struct sk_buff *skb)
-{
-	struct lowpan_dev_record *entry;
-	struct sk_buff *skb_cp;
-	int stat = NET_RX_SUCCESS;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(entry, &lowpan_devices, list)
-		if (lowpan_dev_info(entry->ldev)->real_dev == skb->dev) {
-			skb_cp = skb_copy(skb, GFP_ATOMIC);
-			if (!skb_cp) {
-				stat = -ENOMEM;
-				break;
-			}
-
-			skb_cp->dev = entry->ldev;
-			stat = netif_rx(skb_cp);
-		}
-	rcu_read_unlock();
-
-	return stat;
-}
-
-static int lowpan_skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr)
-{
-	struct sk_buff *new;
-	int stat = NET_RX_SUCCESS;
-
-	new = skb_copy_expand(skb, sizeof(struct ipv6hdr), skb_tailroom(skb),
-								GFP_ATOMIC);
-	kfree_skb(skb);
-
-	if (!new)
-		return -ENOMEM;
-
-	skb_push(new, sizeof(struct ipv6hdr));
-	skb_copy_to_linear_data(new, hdr, sizeof(struct ipv6hdr));
-
-	new->protocol = htons(ETH_P_IPV6);
-	new->pkt_type = PACKET_HOST;
-
-	stat = lowpan_give_skb_to_devices(new);
-
-	kfree_skb(new);
-
-	return stat;
-}
-
-static void lowpan_fragment_timer_expired(unsigned long entry_addr)
-{
-	struct lowpan_fragment *entry = (struct lowpan_fragment *)entry_addr;
-
-	pr_debug("timer expired for frame with tag %d\n", entry->tag);
-
-	list_del(&entry->list);
-	dev_kfree_skb(entry->skb);
-	kfree(entry);
-}
-
-static struct lowpan_fragment *
-lowpan_alloc_new_frame(struct sk_buff *skb, u16 len, u16 tag)
-{
-	struct lowpan_fragment *frame;
-
-	frame = kzalloc(sizeof(struct lowpan_fragment),
-			GFP_ATOMIC);
-	if (!frame)
-		goto frame_err;
-
-	INIT_LIST_HEAD(&frame->list);
-
-	frame->length = len;
-	frame->tag = tag;
-
-	/* allocate buffer for frame assembling */
-	frame->skb = netdev_alloc_skb_ip_align(skb->dev, frame->length +
-					       sizeof(struct ipv6hdr));
-
-	if (!frame->skb)
-		goto skb_err;
-
-	frame->skb->priority = skb->priority;
-
-	/* reserve headroom for uncompressed ipv6 header */
-	skb_reserve(frame->skb, sizeof(struct ipv6hdr));
-	skb_put(frame->skb, frame->length);
-
-	/* copy the first control block to keep a
-	 * trace of the link-layer addresses in case
-	 * of a link-local compressed address
-	 */
-	memcpy(frame->skb->cb, skb->cb, sizeof(skb->cb));
-
-	init_timer(&frame->timer);
-	/* time out is the same as for ipv6 - 60 sec */
-	frame->timer.expires = jiffies + LOWPAN_FRAG_TIMEOUT;
-	frame->timer.data = (unsigned long)frame;
-	frame->timer.function = lowpan_fragment_timer_expired;
-
-	add_timer(&frame->timer);
-
-	list_add_tail(&frame->list, &lowpan_fragments);
-
-	return frame;
-
-skb_err:
-	kfree(frame);
-frame_err:
-	return NULL;
-}
-
-static int
-lowpan_process_data(struct sk_buff *skb)
-{
-	struct ipv6hdr hdr = {};
-	u8 tmp, iphc0, iphc1, num_context = 0;
-	const struct ieee802154_addr *_saddr, *_daddr;
-	int err;
-
-	lowpan_raw_dump_table(__func__, "raw skb data dump", skb->data,
-				skb->len);
-	/* at least two bytes will be used for the encoding */
-	if (skb->len < 2)
-		goto drop;
-
-	if (lowpan_fetch_skb_u8(skb, &iphc0))
-		goto drop;
-
-	/* fragments assembling */
-	switch (iphc0 & LOWPAN_DISPATCH_MASK) {
-	case LOWPAN_DISPATCH_FRAG1:
-	case LOWPAN_DISPATCH_FRAGN:
-	{
-		struct lowpan_fragment *frame;
-		/* slen stores the rightmost 8 bits of the 11 bits length */
-		u8 slen, offset = 0;
-		u16 len, tag;
-		bool found = false;
-
-		if (lowpan_fetch_skb_u8(skb, &slen) || /* frame length */
-		    lowpan_fetch_skb_u16(skb, &tag))  /* fragment tag */
-			goto drop;
-
-		/* adds the 3 MSB to the 8 LSB to retrieve the 11 bits length */
-		len = ((iphc0 & 7) << 8) | slen;
-
-		if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1) {
-			pr_debug("%s received a FRAG1 packet (tag: %d, "
-				 "size of the entire IP packet: %d)",
-				 __func__, tag, len);
-		} else { /* FRAGN */
-			if (lowpan_fetch_skb_u8(skb, &offset))
-				goto unlock_and_drop;
-			pr_debug("%s received a FRAGN packet (tag: %d, "
-				 "size of the entire IP packet: %d, "
-				 "offset: %d)", __func__, tag, len, offset * 8);
-		}
-
-		/*
-		 * check if frame assembling with the same tag is
-		 * already in progress
-		 */
-		spin_lock_bh(&flist_lock);
-
-		list_for_each_entry(frame, &lowpan_fragments, list)
-			if (frame->tag == tag) {
-				found = true;
-				break;
-			}
-
-		/* alloc new frame structure */
-		if (!found) {
-			pr_debug("%s first fragment received for tag %d, "
-				 "begin packet reassembly", __func__, tag);
-			frame = lowpan_alloc_new_frame(skb, len, tag);
-			if (!frame)
-				goto unlock_and_drop;
-		}
-
-		/* if payload fits buffer, copy it */
-		if (likely((offset * 8 + skb->len) <= frame->length))
-			skb_copy_to_linear_data_offset(frame->skb, offset * 8,
-							skb->data, skb->len);
-		else
-			goto unlock_and_drop;
-
-		frame->bytes_rcv += skb->len;
-
-		/* frame assembling complete */
-		if ((frame->bytes_rcv == frame->length) &&
-		     frame->timer.expires > jiffies) {
-			/* if timer haven't expired - first of all delete it */
-			del_timer_sync(&frame->timer);
-			list_del(&frame->list);
-			spin_unlock_bh(&flist_lock);
-
-			pr_debug("%s successfully reassembled fragment "
-				 "(tag %d)", __func__, tag);
-
-			dev_kfree_skb(skb);
-			skb = frame->skb;
-			kfree(frame);
-
-			if (lowpan_fetch_skb_u8(skb, &iphc0))
-				goto drop;
-
-			break;
-		}
-		spin_unlock_bh(&flist_lock);
-
-		return kfree_skb(skb), 0;
-	}
-	default:
-		break;
-	}
-
-	if (lowpan_fetch_skb_u8(skb, &iphc1))
-		goto drop;
-
-	_saddr = &mac_cb(skb)->sa;
-	_daddr = &mac_cb(skb)->da;
-
-	pr_debug("iphc0 = %02x, iphc1 = %02x\n", iphc0, iphc1);
-
-	/* another if the CID flag is set */
-	if (iphc1 & LOWPAN_IPHC_CID) {
-		pr_debug("CID flag is set, increase header with one\n");
-		if (lowpan_fetch_skb_u8(skb, &num_context))
-			goto drop;
-	}
-
-	hdr.version = 6;
-
-	/* Traffic Class and Flow Label */
-	switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) {
-	/*
-	 * Traffic Class and FLow Label carried in-line
-	 * ECN + DSCP + 4-bit Pad + Flow Label (4 bytes)
-	 */
-	case 0: /* 00b */
-		if (lowpan_fetch_skb_u8(skb, &tmp))
-			goto drop;
-
-		memcpy(&hdr.flow_lbl, &skb->data[0], 3);
-		skb_pull(skb, 3);
-		hdr.priority = ((tmp >> 2) & 0x0f);
-		hdr.flow_lbl[0] = ((tmp >> 2) & 0x30) | (tmp << 6) |
-					(hdr.flow_lbl[0] & 0x0f);
-		break;
-	/*
-	 * Traffic class carried in-line
-	 * ECN + DSCP (1 byte), Flow Label is elided
-	 */
-	case 2: /* 10b */
-		if (lowpan_fetch_skb_u8(skb, &tmp))
-			goto drop;
-
-		hdr.priority = ((tmp >> 2) & 0x0f);
-		hdr.flow_lbl[0] = ((tmp << 6) & 0xC0) | ((tmp >> 2) & 0x30);
-		break;
-	/*
-	 * Flow Label carried in-line
-	 * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided
-	 */
-	case 1: /* 01b */
-		if (lowpan_fetch_skb_u8(skb, &tmp))
-			goto drop;
-
-		hdr.flow_lbl[0] = (skb->data[0] & 0x0F) | ((tmp >> 2) & 0x30);
-		memcpy(&hdr.flow_lbl[1], &skb->data[0], 2);
-		skb_pull(skb, 2);
-		break;
-	/* Traffic Class and Flow Label are elided */
-	case 3: /* 11b */
-		break;
-	default:
-		break;
-	}
-
-	/* Next Header */
-	if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) {
-		/* Next header is carried inline */
-		if (lowpan_fetch_skb_u8(skb, &(hdr.nexthdr)))
-			goto drop;
-
-		pr_debug("NH flag is set, next header carried inline: %02x\n",
-			 hdr.nexthdr);
-	}
-
-	/* Hop Limit */
-	if ((iphc0 & 0x03) != LOWPAN_IPHC_TTL_I)
-		hdr.hop_limit = lowpan_ttl_values[iphc0 & 0x03];
-	else {
-		if (lowpan_fetch_skb_u8(skb, &(hdr.hop_limit)))
-			goto drop;
-	}
-
-	/* Extract SAM to the tmp variable */
-	tmp = ((iphc1 & LOWPAN_IPHC_SAM) >> LOWPAN_IPHC_SAM_BIT) & 0x03;
-
-	if (iphc1 & LOWPAN_IPHC_SAC) {
-		/* Source address context based uncompression */
-		pr_debug("SAC bit is set. Handle context based source address.\n");
-		err = lowpan_uncompress_context_based_src_addr(
-				skb, &hdr.saddr, tmp);
-	} else {
-		/* Source address uncompression */
-		pr_debug("source address stateless compression\n");
-		err = lowpan_uncompress_addr(skb, &hdr.saddr, tmp, _saddr);
-	}
-
-	/* Check on error of previous branch */
-	if (err)
-		goto drop;
-
-	/* Extract DAM to the tmp variable */
-	tmp = ((iphc1 & LOWPAN_IPHC_DAM_11) >> LOWPAN_IPHC_DAM_BIT) & 0x03;
-
-	/* check for Multicast Compression */
-	if (iphc1 & LOWPAN_IPHC_M) {
-		if (iphc1 & LOWPAN_IPHC_DAC) {
-			pr_debug("dest: context-based mcast compression\n");
-			/* TODO: implement this */
-		} else {
-			err = lowpan_uncompress_multicast_daddr(
-					skb, &hdr.daddr, tmp);
-			if (err)
-				goto drop;
-		}
-	} else {
-		pr_debug("dest: stateless compression\n");
-		err = lowpan_uncompress_addr(skb, &hdr.daddr, tmp, _daddr);
-		if (err)
-			goto drop;
-	}
-
-	/* UDP data uncompression */
-	if (iphc0 & LOWPAN_IPHC_NH_C) {
-		struct udphdr uh;
-		struct sk_buff *new;
-		if (lowpan_uncompress_udp_header(skb, &uh))
-			goto drop;
-
-		/*
-		 * replace the compressed UDP head by the uncompressed UDP
-		 * header
-		 */
-		new = skb_copy_expand(skb, sizeof(struct udphdr),
-				      skb_tailroom(skb), GFP_ATOMIC);
-		kfree_skb(skb);
-
-		if (!new)
-			return -ENOMEM;
-
-		skb = new;
-
-		skb_push(skb, sizeof(struct udphdr));
-		skb_copy_to_linear_data(skb, &uh, sizeof(struct udphdr));
-
-		lowpan_raw_dump_table(__func__, "raw UDP header dump",
-				      (u8 *)&uh, sizeof(uh));
-
-		hdr.nexthdr = UIP_PROTO_UDP;
-	}
-
-	/* Not fragmented package */
-	hdr.payload_len = htons(skb->len);
-
-	pr_debug("skb headroom size = %d, data length = %d\n",
-		 skb_headroom(skb), skb->len);
-
-	pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength  = %d\n\t"
-		 "nexthdr = 0x%02x\n\thop_lim = %d\n", hdr.version,
-		 ntohs(hdr.payload_len), hdr.nexthdr, hdr.hop_limit);
-
-	lowpan_raw_dump_table(__func__, "raw header dump", (u8 *)&hdr,
-							sizeof(hdr));
-	return lowpan_skb_deliver(skb, &hdr);
-
-unlock_and_drop:
-	spin_unlock_bh(&flist_lock);
-drop:
-	kfree_skb(skb);
-	return -EINVAL;
-}
-
-static int lowpan_set_address(struct net_device *dev, void *p)
-{
-	struct sockaddr *sa = p;
-
-	if (netif_running(dev))
-		return -EBUSY;
-
-	/* TODO: validate addr */
-	memcpy(dev->dev_addr, sa->sa_data, dev->addr_len);
-
-	return 0;
-}
-
-static int
-lowpan_fragment_xmit(struct sk_buff *skb, u8 *head,
-			int mlen, int plen, int offset, int type)
-{
-	struct sk_buff *frag;
-	int hlen;
-
-	hlen = (type == LOWPAN_DISPATCH_FRAG1) ?
-			LOWPAN_FRAG1_HEAD_SIZE : LOWPAN_FRAGN_HEAD_SIZE;
-
-	lowpan_raw_dump_inline(__func__, "6lowpan fragment header", head, hlen);
-
-	frag = netdev_alloc_skb(skb->dev,
-				hlen + mlen + plen + IEEE802154_MFR_SIZE);
-	if (!frag)
-		return -ENOMEM;
-
-	frag->priority = skb->priority;
-
-	/* copy header, MFR and payload */
-	skb_put(frag, mlen);
-	skb_copy_to_linear_data(frag, skb_mac_header(skb), mlen);
-
-	skb_put(frag, hlen);
-	skb_copy_to_linear_data_offset(frag, mlen, head, hlen);
-
-	skb_put(frag, plen);
-	skb_copy_to_linear_data_offset(frag, mlen + hlen,
-				       skb_network_header(skb) + offset, plen);
-
-	lowpan_raw_dump_table(__func__, " raw fragment dump", frag->data,
-								frag->len);
-
-	return dev_queue_xmit(frag);
-}
-
-static int
-lowpan_skb_fragmentation(struct sk_buff *skb, struct net_device *dev)
-{
-	int  err, header_length, payload_length, tag, offset = 0;
-	u8 head[5];
-
-	header_length = skb->mac_len;
-	payload_length = skb->len - header_length;
-	tag = lowpan_dev_info(dev)->fragment_tag++;
-
-	/* first fragment header */
-	head[0] = LOWPAN_DISPATCH_FRAG1 | ((payload_length >> 8) & 0x7);
-	head[1] = payload_length & 0xff;
-	head[2] = tag >> 8;
-	head[3] = tag & 0xff;
-
-	err = lowpan_fragment_xmit(skb, head, header_length, LOWPAN_FRAG_SIZE,
-				   0, LOWPAN_DISPATCH_FRAG1);
-
-	if (err) {
-		pr_debug("%s unable to send FRAG1 packet (tag: %d)",
-			 __func__, tag);
-		goto exit;
-	}
-
-	offset = LOWPAN_FRAG_SIZE;
-
-	/* next fragment header */
-	head[0] &= ~LOWPAN_DISPATCH_FRAG1;
-	head[0] |= LOWPAN_DISPATCH_FRAGN;
-
-	while (payload_length - offset > 0) {
-		int len = LOWPAN_FRAG_SIZE;
-
-		head[4] = offset / 8;
-
-		if (payload_length - offset < len)
-			len = payload_length - offset;
-
-		err = lowpan_fragment_xmit(skb, head, header_length,
-					   len, offset, LOWPAN_DISPATCH_FRAGN);
-		if (err) {
-			pr_debug("%s unable to send a subsequent FRAGN packet "
-				 "(tag: %d, offset: %d", __func__, tag, offset);
-			goto exit;
-		}
-
-		offset += len;
-	}
-
-exit:
-	return err;
-}
-
-static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	int err = -1;
-
-	pr_debug("package xmit\n");
-
-	skb->dev = lowpan_dev_info(dev)->real_dev;
-	if (skb->dev == NULL) {
-		pr_debug("ERROR: no real wpan device found\n");
-		goto error;
-	}
-
-	/* Send directly if less than the MTU minus the 2 checksum bytes. */
-	if (skb->len <= IEEE802154_MTU - IEEE802154_MFR_SIZE) {
-		err = dev_queue_xmit(skb);
-		goto out;
-	}
-
-	pr_debug("frame is too big, fragmentation is needed\n");
-	err = lowpan_skb_fragmentation(skb, dev);
-error:
-	dev_kfree_skb(skb);
-out:
-	if (err)
-		pr_debug("ERROR: xmit failed\n");
-
-	return (err < 0) ? NET_XMIT_DROP : err;
-}
-
-static struct wpan_phy *lowpan_get_phy(const struct net_device *dev)
-{
-	struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
-	return ieee802154_mlme_ops(real_dev)->get_phy(real_dev);
-}
-
-static u16 lowpan_get_pan_id(const struct net_device *dev)
-{
-	struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
-	return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev);
-}
-
-static u16 lowpan_get_short_addr(const struct net_device *dev)
-{
-	struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
-	return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev);
-}
-
-static u8 lowpan_get_dsn(const struct net_device *dev)
-{
-	struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
-	return ieee802154_mlme_ops(real_dev)->get_dsn(real_dev);
-}
-
-static struct header_ops lowpan_header_ops = {
-	.create	= lowpan_header_create,
-};
-
-static const struct net_device_ops lowpan_netdev_ops = {
-	.ndo_start_xmit		= lowpan_xmit,
-	.ndo_set_mac_address	= lowpan_set_address,
-};
-
-static struct ieee802154_mlme_ops lowpan_mlme = {
-	.get_pan_id = lowpan_get_pan_id,
-	.get_phy = lowpan_get_phy,
-	.get_short_addr = lowpan_get_short_addr,
-	.get_dsn = lowpan_get_dsn,
-};
-
-static void lowpan_setup(struct net_device *dev)
-{
-	dev->addr_len		= IEEE802154_ADDR_LEN;
-	memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN);
-	dev->type		= ARPHRD_IEEE802154;
-	/* Frame Control + Sequence Number + Address fields + Security Header */
-	dev->hard_header_len	= 2 + 1 + 20 + 14;
-	dev->needed_tailroom	= 2; /* FCS */
-	dev->mtu		= 1281;
-	dev->tx_queue_len	= 0;
-	dev->flags		= IFF_BROADCAST | IFF_MULTICAST;
-	dev->watchdog_timeo	= 0;
-
-	dev->netdev_ops		= &lowpan_netdev_ops;
-	dev->header_ops		= &lowpan_header_ops;
-	dev->ml_priv		= &lowpan_mlme;
-	dev->destructor		= free_netdev;
-}
-
-static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[])
-{
-	if (tb[IFLA_ADDRESS]) {
-		if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN)
-			return -EINVAL;
-	}
-	return 0;
-}
-
-static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev,
-	struct packet_type *pt, struct net_device *orig_dev)
-{
-	struct sk_buff *local_skb;
-
-	if (!netif_running(dev))
-		goto drop;
-
-	if (dev->type != ARPHRD_IEEE802154)
-		goto drop;
-
-	/* check that it's our buffer */
-	if (skb->data[0] == LOWPAN_DISPATCH_IPV6) {
-		/* Copy the packet so that the IPv6 header is
-		 * properly aligned.
-		 */
-		local_skb = skb_copy_expand(skb, NET_SKB_PAD - 1,
-					    skb_tailroom(skb), GFP_ATOMIC);
-		if (!local_skb)
-			goto drop;
-
-		local_skb->protocol = htons(ETH_P_IPV6);
-		local_skb->pkt_type = PACKET_HOST;
-
-		/* Pull off the 1-byte of 6lowpan header. */
-		skb_pull(local_skb, 1);
-
-		lowpan_give_skb_to_devices(local_skb);
-
-		kfree_skb(local_skb);
-		kfree_skb(skb);
-	} else {
-		switch (skb->data[0] & 0xe0) {
-		case LOWPAN_DISPATCH_IPHC:	/* ipv6 datagram */
-		case LOWPAN_DISPATCH_FRAG1:	/* first fragment header */
-		case LOWPAN_DISPATCH_FRAGN:	/* next fragments headers */
-			local_skb = skb_clone(skb, GFP_ATOMIC);
-			if (!local_skb)
-				goto drop;
-			lowpan_process_data(local_skb);
-
-			kfree_skb(skb);
-			break;
-		default:
-			break;
-		}
-	}
-
-	return NET_RX_SUCCESS;
-
-drop:
-	kfree_skb(skb);
-	return NET_RX_DROP;
-}
-
-static int lowpan_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[])
-{
-	struct net_device *real_dev;
-	struct lowpan_dev_record *entry;
-
-	pr_debug("adding new link\n");
-
-	if (!tb[IFLA_LINK])
-		return -EINVAL;
-	/* find and hold real wpan device */
-	real_dev = dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
-	if (!real_dev)
-		return -ENODEV;
-	if (real_dev->type != ARPHRD_IEEE802154) {
-		dev_put(real_dev);
-		return -EINVAL;
-	}
-
-	lowpan_dev_info(dev)->real_dev = real_dev;
-	lowpan_dev_info(dev)->fragment_tag = 0;
-	mutex_init(&lowpan_dev_info(dev)->dev_list_mtx);
-
-	entry = kzalloc(sizeof(struct lowpan_dev_record), GFP_KERNEL);
-	if (!entry) {
-		dev_put(real_dev);
-		lowpan_dev_info(dev)->real_dev = NULL;
-		return -ENOMEM;
-	}
-
-	entry->ldev = dev;
-
-	/* Set the lowpan harware address to the wpan hardware address. */
-	memcpy(dev->dev_addr, real_dev->dev_addr, IEEE802154_ADDR_LEN);
-
-	mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx);
-	INIT_LIST_HEAD(&entry->list);
-	list_add_tail(&entry->list, &lowpan_devices);
-	mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx);
-
-	register_netdevice(dev);
-
-	return 0;
-}
-
-static void lowpan_dellink(struct net_device *dev, struct list_head *head)
-{
-	struct lowpan_dev_info *lowpan_dev = lowpan_dev_info(dev);
-	struct net_device *real_dev = lowpan_dev->real_dev;
-	struct lowpan_dev_record *entry, *tmp;
-
-	ASSERT_RTNL();
-
-	mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx);
-	list_for_each_entry_safe(entry, tmp, &lowpan_devices, list) {
-		if (entry->ldev == dev) {
-			list_del(&entry->list);
-			kfree(entry);
-		}
-	}
-	mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx);
-
-	mutex_destroy(&lowpan_dev_info(dev)->dev_list_mtx);
-
-	unregister_netdevice_queue(dev, head);
-
-	dev_put(real_dev);
-}
-
-static struct rtnl_link_ops lowpan_link_ops __read_mostly = {
-	.kind		= "lowpan",
-	.priv_size	= sizeof(struct lowpan_dev_info),
-	.setup		= lowpan_setup,
-	.newlink	= lowpan_newlink,
-	.dellink	= lowpan_dellink,
-	.validate	= lowpan_validate,
-};
-
-static inline int __init lowpan_netlink_init(void)
-{
-	return rtnl_link_register(&lowpan_link_ops);
-}
-
-static inline void lowpan_netlink_fini(void)
-{
-	rtnl_link_unregister(&lowpan_link_ops);
-}
-
-static int lowpan_device_event(struct notifier_block *unused,
-			       unsigned long event, void *ptr)
-{
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	LIST_HEAD(del_list);
-	struct lowpan_dev_record *entry, *tmp;
-
-	if (dev->type != ARPHRD_IEEE802154)
-		goto out;
-
-	if (event == NETDEV_UNREGISTER) {
-		list_for_each_entry_safe(entry, tmp, &lowpan_devices, list) {
-			if (lowpan_dev_info(entry->ldev)->real_dev == dev)
-				lowpan_dellink(entry->ldev, &del_list);
-		}
-
-		unregister_netdevice_many(&del_list);
-	}
-
-out:
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block lowpan_dev_notifier = {
-	.notifier_call = lowpan_device_event,
-};
-
-static struct packet_type lowpan_packet_type = {
-	.type = __constant_htons(ETH_P_IEEE802154),
-	.func = lowpan_rcv,
-};
-
-static int __init lowpan_init_module(void)
-{
-	int err = 0;
-
-	err = lowpan_netlink_init();
-	if (err < 0)
-		goto out;
-
-	dev_add_pack(&lowpan_packet_type);
-
-	err = register_netdevice_notifier(&lowpan_dev_notifier);
-	if (err < 0) {
-		dev_remove_pack(&lowpan_packet_type);
-		lowpan_netlink_fini();
-	}
-out:
-	return err;
-}
-
-static void __exit lowpan_cleanup_module(void)
-{
-	struct lowpan_fragment *frame, *tframe;
-
-	lowpan_netlink_fini();
-
-	dev_remove_pack(&lowpan_packet_type);
-
-	unregister_netdevice_notifier(&lowpan_dev_notifier);
-
-	/* Now 6lowpan packet_type is removed, so no new fragments are
-	 * expected on RX, therefore that's the time to clean incomplete
-	 * fragments.
-	 */
-	spin_lock_bh(&flist_lock);
-	list_for_each_entry_safe(frame, tframe, &lowpan_fragments, list) {
-		del_timer_sync(&frame->timer);
-		list_del(&frame->list);
-		dev_kfree_skb(frame->skb);
-		kfree(frame);
-	}
-	spin_unlock_bh(&flist_lock);
-}
-
-module_init(lowpan_init_module);
-module_exit(lowpan_cleanup_module);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_RTNL_LINK("lowpan");
diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h
deleted file mode 100644
index 2869c0526da..00000000000
--- a/net/ieee802154/6lowpan.h
+++ /dev/null
@@ -1,247 +0,0 @@
-/*
- * Copyright 2011, Siemens AG
- * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
- */
-
-/*
- * Based on patches from Jon Smirl <jonsmirl@gmail.com>
- * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- */
-
-/* Jon's code is based on 6lowpan implementation for Contiki which is:
- * Copyright (c) 2008, Swedish Institute of Computer Science.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Institute nor the names of its contributors
- *    may be used to endorse or promote products derived from this software
- *    without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- */
-
-#ifndef __6LOWPAN_H__
-#define __6LOWPAN_H__
-
-#define UIP_802154_SHORTADDR_LEN	2  /* compressed ipv6 address length */
-#define UIP_IPH_LEN			40 /* ipv6 fixed header size */
-#define UIP_PROTO_UDP			17 /* ipv6 next header value for UDP */
-#define UIP_FRAGH_LEN			8  /* ipv6 fragment header size */
-
-/*
- * ipv6 address based on mac
- * second bit-flip (Universe/Local) is done according RFC2464
- */
-#define is_addr_mac_addr_based(a, m) \
-	((((a)->s6_addr[8])  == (((m)[0]) ^ 0x02)) &&	\
-	 (((a)->s6_addr[9])  == (m)[1]) &&		\
-	 (((a)->s6_addr[10]) == (m)[2]) &&		\
-	 (((a)->s6_addr[11]) == (m)[3]) &&		\
-	 (((a)->s6_addr[12]) == (m)[4]) &&		\
-	 (((a)->s6_addr[13]) == (m)[5]) &&		\
-	 (((a)->s6_addr[14]) == (m)[6]) &&		\
-	 (((a)->s6_addr[15]) == (m)[7]))
-
-/* ipv6 address is unspecified */
-#define is_addr_unspecified(a)		\
-	((((a)->s6_addr32[0]) == 0) &&	\
-	 (((a)->s6_addr32[1]) == 0) &&	\
-	 (((a)->s6_addr32[2]) == 0) &&	\
-	 (((a)->s6_addr32[3]) == 0))
-
-/* compare ipv6 addresses prefixes */
-#define ipaddr_prefixcmp(addr1, addr2, length) \
-	(memcmp(addr1, addr2, length >> 3) == 0)
-
-/* local link, i.e. FE80::/10 */
-#define is_addr_link_local(a) (((a)->s6_addr16[0]) == htons(0xFE80))
-
-/*
- * check whether we can compress the IID to 16 bits,
- * it's possible for unicast adresses with first 49 bits are zero only.
- */
-#define lowpan_is_iid_16_bit_compressable(a)	\
-	((((a)->s6_addr16[4]) == 0) &&		\
-	 (((a)->s6_addr[10]) == 0) &&		\
-	 (((a)->s6_addr[11]) == 0xff) &&	\
-	 (((a)->s6_addr[12]) == 0xfe) &&	\
-	 (((a)->s6_addr[13]) == 0))
-
-/* multicast address */
-#define is_addr_mcast(a) (((a)->s6_addr[0]) == 0xFF)
-
-/* check whether the 112-bit gid of the multicast address is mappable to: */
-
-/* 9 bits, for FF02::1 (all nodes) and FF02::2 (all routers) addresses only. */
-#define lowpan_is_mcast_addr_compressable(a)	\
-	((((a)->s6_addr16[1]) == 0) &&		\
-	 (((a)->s6_addr16[2]) == 0) &&		\
-	 (((a)->s6_addr16[3]) == 0) &&		\
-	 (((a)->s6_addr16[4]) == 0) &&		\
-	 (((a)->s6_addr16[5]) == 0) &&		\
-	 (((a)->s6_addr16[6]) == 0) &&		\
-	 (((a)->s6_addr[14])  == 0) &&		\
-	 ((((a)->s6_addr[15]) == 1) || (((a)->s6_addr[15]) == 2)))
-
-/* 48 bits, FFXX::00XX:XXXX:XXXX */
-#define lowpan_is_mcast_addr_compressable48(a)	\
-	((((a)->s6_addr16[1]) == 0) &&		\
-	 (((a)->s6_addr16[2]) == 0) &&		\
-	 (((a)->s6_addr16[3]) == 0) &&		\
-	 (((a)->s6_addr16[4]) == 0) &&		\
-	 (((a)->s6_addr[10]) == 0))
-
-/* 32 bits, FFXX::00XX:XXXX */
-#define lowpan_is_mcast_addr_compressable32(a)	\
-	((((a)->s6_addr16[1]) == 0) &&		\
-	 (((a)->s6_addr16[2]) == 0) &&		\
-	 (((a)->s6_addr16[3]) == 0) &&		\
-	 (((a)->s6_addr16[4]) == 0) &&		\
-	 (((a)->s6_addr16[5]) == 0) &&		\
-	 (((a)->s6_addr[12]) == 0))
-
-/* 8 bits, FF02::00XX */
-#define lowpan_is_mcast_addr_compressable8(a)	\
-	((((a)->s6_addr[1])  == 2) &&		\
-	 (((a)->s6_addr16[1]) == 0) &&		\
-	 (((a)->s6_addr16[2]) == 0) &&		\
-	 (((a)->s6_addr16[3]) == 0) &&		\
-	 (((a)->s6_addr16[4]) == 0) &&		\
-	 (((a)->s6_addr16[5]) == 0) &&		\
-	 (((a)->s6_addr16[6]) == 0) &&		\
-	 (((a)->s6_addr[14]) == 0))
-
-#define lowpan_is_addr_broadcast(a)	\
-	((((a)[0]) == 0xFF) &&	\
-	 (((a)[1]) == 0xFF) &&	\
-	 (((a)[2]) == 0xFF) &&	\
-	 (((a)[3]) == 0xFF) &&	\
-	 (((a)[4]) == 0xFF) &&	\
-	 (((a)[5]) == 0xFF) &&	\
-	 (((a)[6]) == 0xFF) &&	\
-	 (((a)[7]) == 0xFF))
-
-#define LOWPAN_DISPATCH_IPV6	0x41 /* 01000001 = 65 */
-#define LOWPAN_DISPATCH_HC1	0x42 /* 01000010 = 66 */
-#define LOWPAN_DISPATCH_IPHC	0x60 /* 011xxxxx = ... */
-#define LOWPAN_DISPATCH_FRAG1	0xc0 /* 11000xxx */
-#define LOWPAN_DISPATCH_FRAGN	0xe0 /* 11100xxx */
-
-#define LOWPAN_DISPATCH_MASK	0xf8 /* 11111000 */
-
-#define LOWPAN_FRAG_TIMEOUT	(HZ * 60)	/* time-out 60 sec */
-
-#define LOWPAN_FRAG1_HEAD_SIZE	0x4
-#define LOWPAN_FRAGN_HEAD_SIZE	0x5
-
-/*
- * According IEEE802.15.4 standard:
- *   - MTU is 127 octets
- *   - maximum MHR size is 37 octets
- *   - MFR size is 2 octets
- *
- * so minimal payload size that we may guarantee is:
- *   MTU - MHR - MFR = 88 octets
- */
-#define LOWPAN_FRAG_SIZE	88
-
-/*
- * Values of fields within the IPHC encoding first byte
- * (C stands for compressed and I for inline)
- */
-#define LOWPAN_IPHC_TF		0x18
-
-#define LOWPAN_IPHC_FL_C	0x10
-#define LOWPAN_IPHC_TC_C	0x08
-#define LOWPAN_IPHC_NH_C	0x04
-#define LOWPAN_IPHC_TTL_1	0x01
-#define LOWPAN_IPHC_TTL_64	0x02
-#define LOWPAN_IPHC_TTL_255	0x03
-#define LOWPAN_IPHC_TTL_I	0x00
-
-
-/* Values of fields within the IPHC encoding second byte */
-#define LOWPAN_IPHC_CID		0x80
-
-#define LOWPAN_IPHC_ADDR_00	0x00
-#define LOWPAN_IPHC_ADDR_01	0x01
-#define LOWPAN_IPHC_ADDR_02	0x02
-#define LOWPAN_IPHC_ADDR_03	0x03
-
-#define LOWPAN_IPHC_SAC		0x40
-#define LOWPAN_IPHC_SAM		0x30
-
-#define LOWPAN_IPHC_SAM_BIT	4
-
-#define LOWPAN_IPHC_M		0x08
-#define LOWPAN_IPHC_DAC		0x04
-#define LOWPAN_IPHC_DAM_00	0x00
-#define LOWPAN_IPHC_DAM_01	0x01
-#define LOWPAN_IPHC_DAM_10	0x02
-#define LOWPAN_IPHC_DAM_11	0x03
-
-#define LOWPAN_IPHC_DAM_BIT	0
-/*
- * LOWPAN_UDP encoding (works together with IPHC)
- */
-#define LOWPAN_NHC_UDP_MASK		0xF8
-#define LOWPAN_NHC_UDP_ID		0xF0
-#define LOWPAN_NHC_UDP_CHECKSUMC	0x04
-#define LOWPAN_NHC_UDP_CHECKSUMI	0x00
-
-#define LOWPAN_NHC_UDP_4BIT_PORT	0xF0B0
-#define LOWPAN_NHC_UDP_4BIT_MASK	0xFFF0
-#define LOWPAN_NHC_UDP_8BIT_PORT	0xF000
-#define LOWPAN_NHC_UDP_8BIT_MASK	0xFF00
-
-/* values for port compression, _with checksum_ ie bit 5 set to 0 */
-#define LOWPAN_NHC_UDP_CS_P_00	0xF0 /* all inline */
-#define LOWPAN_NHC_UDP_CS_P_01	0xF1 /* source 16bit inline,
-					dest = 0xF0 + 8 bit inline */
-#define LOWPAN_NHC_UDP_CS_P_10	0xF2 /* source = 0xF0 + 8bit inline,
-					dest = 16 bit inline */
-#define LOWPAN_NHC_UDP_CS_P_11	0xF3 /* source & dest = 0xF0B + 4bit inline */
-
-static inline bool lowpan_fetch_skb(struct sk_buff *skb,
-		void *data, const unsigned int len)
-{
-	if (unlikely(!pskb_may_pull(skb, len)))
-		return true;
-
-	skb_copy_from_linear_data(skb, data, len);
-	skb_pull(skb, len);
-
-	return false;
-}
-
-#endif /* __6LOWPAN_H__ */
diff --git a/net/ieee802154/6lowpan_iphc.c b/net/ieee802154/6lowpan_iphc.c
new file mode 100644
index 00000000000..211b5686d71
--- /dev/null
+++ b/net/ieee802154/6lowpan_iphc.c
@@ -0,0 +1,801 @@
+/*
+ * Copyright 2011, Siemens AG
+ * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
+ */
+
+/*
+ * Based on patches from Jon Smirl <jonsmirl@gmail.com>
+ * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+/* Jon's code is based on 6lowpan implementation for Contiki which is:
+ * Copyright (c) 2008, Swedish Institute of Computer Science.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of the Institute nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#include <linux/bitops.h>
+#include <linux/if_arp.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <net/6lowpan.h>
+#include <net/ipv6.h>
+#include <net/af_ieee802154.h>
+
+/*
+ * Uncompress address function for source and
+ * destination address(non-multicast).
+ *
+ * address_mode is sam value or dam value.
+ */
+static int uncompress_addr(struct sk_buff *skb,
+				struct in6_addr *ipaddr, const u8 address_mode,
+				const u8 *lladdr, const u8 addr_type,
+				const u8 addr_len)
+{
+	bool fail;
+
+	switch (address_mode) {
+	case LOWPAN_IPHC_ADDR_00:
+		/* for global link addresses */
+		fail = lowpan_fetch_skb(skb, ipaddr->s6_addr, 16);
+		break;
+	case LOWPAN_IPHC_ADDR_01:
+		/* fe:80::XXXX:XXXX:XXXX:XXXX */
+		ipaddr->s6_addr[0] = 0xFE;
+		ipaddr->s6_addr[1] = 0x80;
+		fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[8], 8);
+		break;
+	case LOWPAN_IPHC_ADDR_02:
+		/* fe:80::ff:fe00:XXXX */
+		ipaddr->s6_addr[0] = 0xFE;
+		ipaddr->s6_addr[1] = 0x80;
+		ipaddr->s6_addr[11] = 0xFF;
+		ipaddr->s6_addr[12] = 0xFE;
+		fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[14], 2);
+		break;
+	case LOWPAN_IPHC_ADDR_03:
+		fail = false;
+		switch (addr_type) {
+		case IEEE802154_ADDR_LONG:
+			/* fe:80::XXXX:XXXX:XXXX:XXXX
+			 *        \_________________/
+			 *              hwaddr
+			 */
+			ipaddr->s6_addr[0] = 0xFE;
+			ipaddr->s6_addr[1] = 0x80;
+			memcpy(&ipaddr->s6_addr[8], lladdr, addr_len);
+			/* second bit-flip (Universe/Local)
+			 * is done according RFC2464
+			 */
+			ipaddr->s6_addr[8] ^= 0x02;
+			break;
+		case IEEE802154_ADDR_SHORT:
+			/* fe:80::ff:fe00:XXXX
+			 *		  \__/
+			 *	       short_addr
+			 *
+			 * Universe/Local bit is zero.
+			 */
+			ipaddr->s6_addr[0] = 0xFE;
+			ipaddr->s6_addr[1] = 0x80;
+			ipaddr->s6_addr[11] = 0xFF;
+			ipaddr->s6_addr[12] = 0xFE;
+			ipaddr->s6_addr16[7] = htons(*((u16 *)lladdr));
+			break;
+		default:
+			pr_debug("Invalid addr_type set\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		pr_debug("Invalid address mode value: 0x%x\n", address_mode);
+		return -EINVAL;
+	}
+
+	if (fail) {
+		pr_debug("Failed to fetch skb data\n");
+		return -EIO;
+	}
+
+	raw_dump_inline(NULL, "Reconstructed ipv6 addr is",
+			ipaddr->s6_addr, 16);
+
+	return 0;
+}
+
+/*
+ * Uncompress address function for source context
+ * based address(non-multicast).
+ */
+static int uncompress_context_based_src_addr(struct sk_buff *skb,
+						struct in6_addr *ipaddr,
+						const u8 sam)
+{
+	switch (sam) {
+	case LOWPAN_IPHC_ADDR_00:
+		/* unspec address ::
+		 * Do nothing, address is already ::
+		 */
+		break;
+	case LOWPAN_IPHC_ADDR_01:
+		/* TODO */
+	case LOWPAN_IPHC_ADDR_02:
+		/* TODO */
+	case LOWPAN_IPHC_ADDR_03:
+		/* TODO */
+		netdev_warn(skb->dev, "SAM value 0x%x not supported\n", sam);
+		return -EINVAL;
+	default:
+		pr_debug("Invalid sam value: 0x%x\n", sam);
+		return -EINVAL;
+	}
+
+	raw_dump_inline(NULL,
+			"Reconstructed context based ipv6 src addr is",
+			ipaddr->s6_addr, 16);
+
+	return 0;
+}
+
+static int skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr,
+		struct net_device *dev, skb_delivery_cb deliver_skb)
+{
+	struct sk_buff *new;
+	int stat;
+
+	new = skb_copy_expand(skb, sizeof(struct ipv6hdr), skb_tailroom(skb),
+								GFP_ATOMIC);
+	kfree_skb(skb);
+
+	if (!new)
+		return -ENOMEM;
+
+	skb_push(new, sizeof(struct ipv6hdr));
+	skb_reset_network_header(new);
+	skb_copy_to_linear_data(new, hdr, sizeof(struct ipv6hdr));
+
+	new->protocol = htons(ETH_P_IPV6);
+	new->pkt_type = PACKET_HOST;
+	new->dev = dev;
+
+	raw_dump_table(__func__, "raw skb data dump before receiving",
+			new->data, new->len);
+
+	stat = deliver_skb(new, dev);
+
+	kfree_skb(new);
+
+	return stat;
+}
+
+/* Uncompress function for multicast destination address,
+ * when M bit is set.
+ */
+static int
+lowpan_uncompress_multicast_daddr(struct sk_buff *skb,
+		struct in6_addr *ipaddr,
+		const u8 dam)
+{
+	bool fail;
+
+	switch (dam) {
+	case LOWPAN_IPHC_DAM_00:
+		/* 00:  128 bits.  The full address
+		 * is carried in-line.
+		 */
+		fail = lowpan_fetch_skb(skb, ipaddr->s6_addr, 16);
+		break;
+	case LOWPAN_IPHC_DAM_01:
+		/* 01:  48 bits.  The address takes
+		 * the form ffXX::00XX:XXXX:XXXX.
+		 */
+		ipaddr->s6_addr[0] = 0xFF;
+		fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 1);
+		fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[11], 5);
+		break;
+	case LOWPAN_IPHC_DAM_10:
+		/* 10:  32 bits.  The address takes
+		 * the form ffXX::00XX:XXXX.
+		 */
+		ipaddr->s6_addr[0] = 0xFF;
+		fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[1], 1);
+		fail |= lowpan_fetch_skb(skb, &ipaddr->s6_addr[13], 3);
+		break;
+	case LOWPAN_IPHC_DAM_11:
+		/* 11:  8 bits.  The address takes
+		 * the form ff02::00XX.
+		 */
+		ipaddr->s6_addr[0] = 0xFF;
+		ipaddr->s6_addr[1] = 0x02;
+		fail = lowpan_fetch_skb(skb, &ipaddr->s6_addr[15], 1);
+		break;
+	default:
+		pr_debug("DAM value has a wrong value: 0x%x\n", dam);
+		return -EINVAL;
+	}
+
+	if (fail) {
+		pr_debug("Failed to fetch skb data\n");
+		return -EIO;
+	}
+
+	raw_dump_inline(NULL, "Reconstructed ipv6 multicast addr is",
+				ipaddr->s6_addr, 16);
+
+	return 0;
+}
+
+static int
+uncompress_udp_header(struct sk_buff *skb, struct udphdr *uh)
+{
+	bool fail;
+	u8 tmp = 0, val = 0;
+
+	if (!uh)
+		goto err;
+
+	fail = lowpan_fetch_skb(skb, &tmp, 1);
+
+	if ((tmp & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) {
+		pr_debug("UDP header uncompression\n");
+		switch (tmp & LOWPAN_NHC_UDP_CS_P_11) {
+		case LOWPAN_NHC_UDP_CS_P_00:
+			fail |= lowpan_fetch_skb(skb, &uh->source, 2);
+			fail |= lowpan_fetch_skb(skb, &uh->dest, 2);
+			break;
+		case LOWPAN_NHC_UDP_CS_P_01:
+			fail |= lowpan_fetch_skb(skb, &uh->source, 2);
+			fail |= lowpan_fetch_skb(skb, &val, 1);
+			uh->dest = htons(val + LOWPAN_NHC_UDP_8BIT_PORT);
+			break;
+		case LOWPAN_NHC_UDP_CS_P_10:
+			fail |= lowpan_fetch_skb(skb, &val, 1);
+			uh->source = htons(val + LOWPAN_NHC_UDP_8BIT_PORT);
+			fail |= lowpan_fetch_skb(skb, &uh->dest, 2);
+			break;
+		case LOWPAN_NHC_UDP_CS_P_11:
+			fail |= lowpan_fetch_skb(skb, &val, 1);
+			uh->source = htons(LOWPAN_NHC_UDP_4BIT_PORT +
+					   (val >> 4));
+			uh->dest = htons(LOWPAN_NHC_UDP_4BIT_PORT +
+					 (val & 0x0f));
+			break;
+		default:
+			pr_debug("ERROR: unknown UDP format\n");
+			goto err;
+			break;
+		}
+
+		pr_debug("uncompressed UDP ports: src = %d, dst = %d\n",
+			 ntohs(uh->source), ntohs(uh->dest));
+
+		/* checksum */
+		if (tmp & LOWPAN_NHC_UDP_CS_C) {
+			pr_debug_ratelimited("checksum elided currently not supported\n");
+			goto err;
+		} else {
+			fail |= lowpan_fetch_skb(skb, &uh->check, 2);
+		}
+
+		/*
+		 * UDP lenght needs to be infered from the lower layers
+		 * here, we obtain the hint from the remaining size of the
+		 * frame
+		 */
+		uh->len = htons(skb->len + sizeof(struct udphdr));
+		pr_debug("uncompressed UDP length: src = %d", ntohs(uh->len));
+	} else {
+		pr_debug("ERROR: unsupported NH format\n");
+		goto err;
+	}
+
+	if (fail)
+		goto err;
+
+	return 0;
+err:
+	return -EINVAL;
+}
+
+/* TTL uncompression values */
+static const u8 lowpan_ttl_values[] = { 0, 1, 64, 255 };
+
+int lowpan_process_data(struct sk_buff *skb, struct net_device *dev,
+		const u8 *saddr, const u8 saddr_type, const u8 saddr_len,
+		const u8 *daddr, const u8 daddr_type, const u8 daddr_len,
+		u8 iphc0, u8 iphc1, skb_delivery_cb deliver_skb)
+{
+	struct ipv6hdr hdr = {};
+	u8 tmp, num_context = 0;
+	int err;
+
+	raw_dump_table(__func__, "raw skb data dump uncompressed",
+				skb->data, skb->len);
+
+	/* another if the CID flag is set */
+	if (iphc1 & LOWPAN_IPHC_CID) {
+		pr_debug("CID flag is set, increase header with one\n");
+		if (lowpan_fetch_skb_u8(skb, &num_context))
+			goto drop;
+	}
+
+	hdr.version = 6;
+
+	/* Traffic Class and Flow Label */
+	switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) {
+	/*
+	 * Traffic Class and FLow Label carried in-line
+	 * ECN + DSCP + 4-bit Pad + Flow Label (4 bytes)
+	 */
+	case 0: /* 00b */
+		if (lowpan_fetch_skb_u8(skb, &tmp))
+			goto drop;
+
+		memcpy(&hdr.flow_lbl, &skb->data[0], 3);
+		skb_pull(skb, 3);
+		hdr.priority = ((tmp >> 2) & 0x0f);
+		hdr.flow_lbl[0] = ((tmp >> 2) & 0x30) | (tmp << 6) |
+					(hdr.flow_lbl[0] & 0x0f);
+		break;
+	/*
+	 * Traffic class carried in-line
+	 * ECN + DSCP (1 byte), Flow Label is elided
+	 */
+	case 2: /* 10b */
+		if (lowpan_fetch_skb_u8(skb, &tmp))
+			goto drop;
+
+		hdr.priority = ((tmp >> 2) & 0x0f);
+		hdr.flow_lbl[0] = ((tmp << 6) & 0xC0) | ((tmp >> 2) & 0x30);
+		break;
+	/*
+	 * Flow Label carried in-line
+	 * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided
+	 */
+	case 1: /* 01b */
+		if (lowpan_fetch_skb_u8(skb, &tmp))
+			goto drop;
+
+		hdr.flow_lbl[0] = (skb->data[0] & 0x0F) | ((tmp >> 2) & 0x30);
+		memcpy(&hdr.flow_lbl[1], &skb->data[0], 2);
+		skb_pull(skb, 2);
+		break;
+	/* Traffic Class and Flow Label are elided */
+	case 3: /* 11b */
+		break;
+	default:
+		break;
+	}
+
+	/* Next Header */
+	if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) {
+		/* Next header is carried inline */
+		if (lowpan_fetch_skb_u8(skb, &(hdr.nexthdr)))
+			goto drop;
+
+		pr_debug("NH flag is set, next header carried inline: %02x\n",
+			 hdr.nexthdr);
+	}
+
+	/* Hop Limit */
+	if ((iphc0 & 0x03) != LOWPAN_IPHC_TTL_I)
+		hdr.hop_limit = lowpan_ttl_values[iphc0 & 0x03];
+	else {
+		if (lowpan_fetch_skb_u8(skb, &(hdr.hop_limit)))
+			goto drop;
+	}
+
+	/* Extract SAM to the tmp variable */
+	tmp = ((iphc1 & LOWPAN_IPHC_SAM) >> LOWPAN_IPHC_SAM_BIT) & 0x03;
+
+	if (iphc1 & LOWPAN_IPHC_SAC) {
+		/* Source address context based uncompression */
+		pr_debug("SAC bit is set. Handle context based source address.\n");
+		err = uncompress_context_based_src_addr(
+				skb, &hdr.saddr, tmp);
+	} else {
+		/* Source address uncompression */
+		pr_debug("source address stateless compression\n");
+		err = uncompress_addr(skb, &hdr.saddr, tmp, saddr,
+					saddr_type, saddr_len);
+	}
+
+	/* Check on error of previous branch */
+	if (err)
+		goto drop;
+
+	/* Extract DAM to the tmp variable */
+	tmp = ((iphc1 & LOWPAN_IPHC_DAM_11) >> LOWPAN_IPHC_DAM_BIT) & 0x03;
+
+	/* check for Multicast Compression */
+	if (iphc1 & LOWPAN_IPHC_M) {
+		if (iphc1 & LOWPAN_IPHC_DAC) {
+			pr_debug("dest: context-based mcast compression\n");
+			/* TODO: implement this */
+		} else {
+			err = lowpan_uncompress_multicast_daddr(
+						skb, &hdr.daddr, tmp);
+			if (err)
+				goto drop;
+		}
+	} else {
+		err = uncompress_addr(skb, &hdr.daddr, tmp, daddr,
+					daddr_type, daddr_len);
+		pr_debug("dest: stateless compression mode %d dest %pI6c\n",
+			tmp, &hdr.daddr);
+		if (err)
+			goto drop;
+	}
+
+	/* UDP data uncompression */
+	if (iphc0 & LOWPAN_IPHC_NH_C) {
+		struct udphdr uh;
+		struct sk_buff *new;
+		if (uncompress_udp_header(skb, &uh))
+			goto drop;
+
+		/*
+		 * replace the compressed UDP head by the uncompressed UDP
+		 * header
+		 */
+		new = skb_copy_expand(skb, sizeof(struct udphdr),
+				      skb_tailroom(skb), GFP_ATOMIC);
+		kfree_skb(skb);
+
+		if (!new)
+			return -ENOMEM;
+
+		skb = new;
+
+		skb_push(skb, sizeof(struct udphdr));
+		skb_reset_transport_header(skb);
+		skb_copy_to_linear_data(skb, &uh, sizeof(struct udphdr));
+
+		raw_dump_table(__func__, "raw UDP header dump",
+				      (u8 *)&uh, sizeof(uh));
+
+		hdr.nexthdr = UIP_PROTO_UDP;
+	}
+
+	hdr.payload_len = htons(skb->len);
+
+	pr_debug("skb headroom size = %d, data length = %d\n",
+		 skb_headroom(skb), skb->len);
+
+	pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength  = %d\n\t"
+		 "nexthdr = 0x%02x\n\thop_lim = %d\n\tdest    = %pI6c\n",
+		hdr.version, ntohs(hdr.payload_len), hdr.nexthdr,
+		hdr.hop_limit, &hdr.daddr);
+
+	raw_dump_table(__func__, "raw header dump", (u8 *)&hdr,
+							sizeof(hdr));
+
+	return skb_deliver(skb, &hdr, dev, deliver_skb);
+
+drop:
+	kfree_skb(skb);
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(lowpan_process_data);
+
+static u8 lowpan_compress_addr_64(u8 **hc06_ptr, u8 shift,
+				const struct in6_addr *ipaddr,
+				const unsigned char *lladdr)
+{
+	u8 val = 0;
+
+	if (is_addr_mac_addr_based(ipaddr, lladdr)) {
+		val = 3; /* 0-bits */
+		pr_debug("address compression 0 bits\n");
+	} else if (lowpan_is_iid_16_bit_compressable(ipaddr)) {
+		/* compress IID to 16 bits xxxx::XXXX */
+		memcpy(*hc06_ptr, &ipaddr->s6_addr16[7], 2);
+		*hc06_ptr += 2;
+		val = 2; /* 16-bits */
+		raw_dump_inline(NULL, "Compressed ipv6 addr is (16 bits)",
+			*hc06_ptr - 2, 2);
+	} else {
+		/* do not compress IID => xxxx::IID */
+		memcpy(*hc06_ptr, &ipaddr->s6_addr16[4], 8);
+		*hc06_ptr += 8;
+		val = 1; /* 64-bits */
+		raw_dump_inline(NULL, "Compressed ipv6 addr is (64 bits)",
+			*hc06_ptr - 8, 8);
+	}
+
+	return rol8(val, shift);
+}
+
+static void compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_hdr(skb);
+	u8 tmp;
+
+	if (((ntohs(uh->source) & LOWPAN_NHC_UDP_4BIT_MASK) ==
+	     LOWPAN_NHC_UDP_4BIT_PORT) &&
+	    ((ntohs(uh->dest) & LOWPAN_NHC_UDP_4BIT_MASK) ==
+	     LOWPAN_NHC_UDP_4BIT_PORT)) {
+		pr_debug("UDP header: both ports compression to 4 bits\n");
+		/* compression value */
+		tmp = LOWPAN_NHC_UDP_CS_P_11;
+		lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp));
+		/* source and destination port */
+		tmp = ntohs(uh->dest) - LOWPAN_NHC_UDP_4BIT_PORT +
+		      ((ntohs(uh->source) - LOWPAN_NHC_UDP_4BIT_PORT) << 4);
+		lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp));
+	} else if ((ntohs(uh->dest) & LOWPAN_NHC_UDP_8BIT_MASK) ==
+			LOWPAN_NHC_UDP_8BIT_PORT) {
+		pr_debug("UDP header: remove 8 bits of dest\n");
+		/* compression value */
+		tmp = LOWPAN_NHC_UDP_CS_P_01;
+		lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp));
+		/* source port */
+		lowpan_push_hc_data(hc06_ptr, &uh->source, sizeof(uh->source));
+		/* destination port */
+		tmp = ntohs(uh->dest) - LOWPAN_NHC_UDP_8BIT_PORT;
+		lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp));
+	} else if ((ntohs(uh->source) & LOWPAN_NHC_UDP_8BIT_MASK) ==
+			LOWPAN_NHC_UDP_8BIT_PORT) {
+		pr_debug("UDP header: remove 8 bits of source\n");
+		/* compression value */
+		tmp = LOWPAN_NHC_UDP_CS_P_10;
+		lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp));
+		/* source port */
+		tmp = ntohs(uh->source) - LOWPAN_NHC_UDP_8BIT_PORT;
+		lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp));
+		/* destination port */
+		lowpan_push_hc_data(hc06_ptr, &uh->dest, sizeof(uh->dest));
+	} else {
+		pr_debug("UDP header: can't compress\n");
+		/* compression value */
+		tmp = LOWPAN_NHC_UDP_CS_P_00;
+		lowpan_push_hc_data(hc06_ptr, &tmp, sizeof(tmp));
+		/* source port */
+		lowpan_push_hc_data(hc06_ptr, &uh->source, sizeof(uh->source));
+		/* destination port */
+		lowpan_push_hc_data(hc06_ptr, &uh->dest, sizeof(uh->dest));
+	}
+
+	/* checksum is always inline */
+	lowpan_push_hc_data(hc06_ptr, &uh->check, sizeof(uh->check));
+
+	/* skip the UDP header */
+	skb_pull(skb, sizeof(struct udphdr));
+}
+
+int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev,
+			unsigned short type, const void *_daddr,
+			const void *_saddr, unsigned int len)
+{
+	u8 tmp, iphc0, iphc1, *hc06_ptr;
+	struct ipv6hdr *hdr;
+	u8 head[100] = {};
+
+	if (type != ETH_P_IPV6)
+		return -EINVAL;
+
+	hdr = ipv6_hdr(skb);
+	hc06_ptr = head + 2;
+
+	pr_debug("IPv6 header dump:\n\tversion = %d\n\tlength  = %d\n"
+		 "\tnexthdr = 0x%02x\n\thop_lim = %d\n\tdest    = %pI6c\n",
+		hdr->version, ntohs(hdr->payload_len), hdr->nexthdr,
+		hdr->hop_limit, &hdr->daddr);
+
+	raw_dump_table(__func__, "raw skb network header dump",
+		skb_network_header(skb), sizeof(struct ipv6hdr));
+
+	/*
+	 * As we copy some bit-length fields, in the IPHC encoding bytes,
+	 * we sometimes use |=
+	 * If the field is 0, and the current bit value in memory is 1,
+	 * this does not work. We therefore reset the IPHC encoding here
+	 */
+	iphc0 = LOWPAN_DISPATCH_IPHC;
+	iphc1 = 0;
+
+	/* TODO: context lookup */
+
+	raw_dump_inline(__func__, "saddr",
+			(unsigned char *)_saddr, IEEE802154_ADDR_LEN);
+	raw_dump_inline(__func__, "daddr",
+			(unsigned char *)_daddr, IEEE802154_ADDR_LEN);
+
+	raw_dump_table(__func__,
+			"sending raw skb network uncompressed packet",
+			skb->data, skb->len);
+
+	/*
+	 * Traffic class, flow label
+	 * If flow label is 0, compress it. If traffic class is 0, compress it
+	 * We have to process both in the same time as the offset of traffic
+	 * class depends on the presence of version and flow label
+	 */
+
+	/* hc06 format of TC is ECN | DSCP , original one is DSCP | ECN */
+	tmp = (hdr->priority << 4) | (hdr->flow_lbl[0] >> 4);
+	tmp = ((tmp & 0x03) << 6) | (tmp >> 2);
+
+	if (((hdr->flow_lbl[0] & 0x0F) == 0) &&
+	     (hdr->flow_lbl[1] == 0) && (hdr->flow_lbl[2] == 0)) {
+		/* flow label can be compressed */
+		iphc0 |= LOWPAN_IPHC_FL_C;
+		if ((hdr->priority == 0) &&
+		   ((hdr->flow_lbl[0] & 0xF0) == 0)) {
+			/* compress (elide) all */
+			iphc0 |= LOWPAN_IPHC_TC_C;
+		} else {
+			/* compress only the flow label */
+			*hc06_ptr = tmp;
+			hc06_ptr += 1;
+		}
+	} else {
+		/* Flow label cannot be compressed */
+		if ((hdr->priority == 0) &&
+		   ((hdr->flow_lbl[0] & 0xF0) == 0)) {
+			/* compress only traffic class */
+			iphc0 |= LOWPAN_IPHC_TC_C;
+			*hc06_ptr = (tmp & 0xc0) | (hdr->flow_lbl[0] & 0x0F);
+			memcpy(hc06_ptr + 1, &hdr->flow_lbl[1], 2);
+			hc06_ptr += 3;
+		} else {
+			/* compress nothing */
+			memcpy(hc06_ptr, hdr, 4);
+			/* replace the top byte with new ECN | DSCP format */
+			*hc06_ptr = tmp;
+			hc06_ptr += 4;
+		}
+	}
+
+	/* NOTE: payload length is always compressed */
+
+	/* Next Header is compress if UDP */
+	if (hdr->nexthdr == UIP_PROTO_UDP)
+		iphc0 |= LOWPAN_IPHC_NH_C;
+
+	if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) {
+		*hc06_ptr = hdr->nexthdr;
+		hc06_ptr += 1;
+	}
+
+	/*
+	 * Hop limit
+	 * if 1:   compress, encoding is 01
+	 * if 64:  compress, encoding is 10
+	 * if 255: compress, encoding is 11
+	 * else do not compress
+	 */
+	switch (hdr->hop_limit) {
+	case 1:
+		iphc0 |= LOWPAN_IPHC_TTL_1;
+		break;
+	case 64:
+		iphc0 |= LOWPAN_IPHC_TTL_64;
+		break;
+	case 255:
+		iphc0 |= LOWPAN_IPHC_TTL_255;
+		break;
+	default:
+		*hc06_ptr = hdr->hop_limit;
+		hc06_ptr += 1;
+		break;
+	}
+
+	/* source address compression */
+	if (is_addr_unspecified(&hdr->saddr)) {
+		pr_debug("source address is unspecified, setting SAC\n");
+		iphc1 |= LOWPAN_IPHC_SAC;
+	/* TODO: context lookup */
+	} else if (is_addr_link_local(&hdr->saddr)) {
+		iphc1 |= lowpan_compress_addr_64(&hc06_ptr,
+				LOWPAN_IPHC_SAM_BIT, &hdr->saddr, _saddr);
+		pr_debug("source address unicast link-local %pI6c "
+			"iphc1 0x%02x\n", &hdr->saddr, iphc1);
+	} else {
+		pr_debug("send the full source address\n");
+		memcpy(hc06_ptr, &hdr->saddr.s6_addr16[0], 16);
+		hc06_ptr += 16;
+	}
+
+	/* destination address compression */
+	if (is_addr_mcast(&hdr->daddr)) {
+		pr_debug("destination address is multicast: ");
+		iphc1 |= LOWPAN_IPHC_M;
+		if (lowpan_is_mcast_addr_compressable8(&hdr->daddr)) {
+			pr_debug("compressed to 1 octet\n");
+			iphc1 |= LOWPAN_IPHC_DAM_11;
+			/* use last byte */
+			*hc06_ptr = hdr->daddr.s6_addr[15];
+			hc06_ptr += 1;
+		} else if (lowpan_is_mcast_addr_compressable32(&hdr->daddr)) {
+			pr_debug("compressed to 4 octets\n");
+			iphc1 |= LOWPAN_IPHC_DAM_10;
+			/* second byte + the last three */
+			*hc06_ptr = hdr->daddr.s6_addr[1];
+			memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[13], 3);
+			hc06_ptr += 4;
+		} else if (lowpan_is_mcast_addr_compressable48(&hdr->daddr)) {
+			pr_debug("compressed to 6 octets\n");
+			iphc1 |= LOWPAN_IPHC_DAM_01;
+			/* second byte + the last five */
+			*hc06_ptr = hdr->daddr.s6_addr[1];
+			memcpy(hc06_ptr + 1, &hdr->daddr.s6_addr[11], 5);
+			hc06_ptr += 6;
+		} else {
+			pr_debug("using full address\n");
+			iphc1 |= LOWPAN_IPHC_DAM_00;
+			memcpy(hc06_ptr, &hdr->daddr.s6_addr[0], 16);
+			hc06_ptr += 16;
+		}
+	} else {
+		/* TODO: context lookup */
+		if (is_addr_link_local(&hdr->daddr)) {
+			iphc1 |= lowpan_compress_addr_64(&hc06_ptr,
+				LOWPAN_IPHC_DAM_BIT, &hdr->daddr, _daddr);
+			pr_debug("dest address unicast link-local %pI6c "
+				"iphc1 0x%02x\n", &hdr->daddr, iphc1);
+		} else {
+			pr_debug("dest address unicast %pI6c\n", &hdr->daddr);
+			memcpy(hc06_ptr, &hdr->daddr.s6_addr16[0], 16);
+			hc06_ptr += 16;
+		}
+	}
+
+	/* UDP header compression */
+	if (hdr->nexthdr == UIP_PROTO_UDP)
+		compress_udp_header(&hc06_ptr, skb);
+
+	head[0] = iphc0;
+	head[1] = iphc1;
+
+	skb_pull(skb, sizeof(struct ipv6hdr));
+	skb_reset_transport_header(skb);
+	memcpy(skb_push(skb, hc06_ptr - head), head, hc06_ptr - head);
+	skb_reset_network_header(skb);
+
+	pr_debug("header len %d skb %u\n", (int)(hc06_ptr - head), skb->len);
+
+	raw_dump_table(__func__, "raw skb data dump compressed",
+				skb->data, skb->len);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(lowpan_header_compress);
+
+MODULE_LICENSE("GPL");
diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c
new file mode 100644
index 00000000000..fe6bd7a7108
--- /dev/null
+++ b/net/ieee802154/6lowpan_rtnl.c
@@ -0,0 +1,683 @@
+/* Copyright 2011, Siemens AG
+ * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
+ */
+
+/* Based on patches from Jon Smirl <jonsmirl@gmail.com>
+ * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/* Jon's code is based on 6lowpan implementation for Contiki which is:
+ * Copyright (c) 2008, Swedish Institute of Computer Science.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of the Institute nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#include <linux/bitops.h>
+#include <linux/if_arp.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/netdevice.h>
+#include <net/af_ieee802154.h>
+#include <net/ieee802154.h>
+#include <net/ieee802154_netdev.h>
+#include <net/6lowpan.h>
+#include <net/ipv6.h>
+
+#include "reassembly.h"
+
+static LIST_HEAD(lowpan_devices);
+
+/* private device info */
+struct lowpan_dev_info {
+	struct net_device	*real_dev; /* real WPAN device ptr */
+	struct mutex		dev_list_mtx; /* mutex for list ops */
+	__be16			fragment_tag;
+};
+
+struct lowpan_dev_record {
+	struct net_device *ldev;
+	struct list_head list;
+};
+
+static inline struct
+lowpan_dev_info *lowpan_dev_info(const struct net_device *dev)
+{
+	return netdev_priv(dev);
+}
+
+static inline void lowpan_address_flip(u8 *src, u8 *dest)
+{
+	int i;
+	for (i = 0; i < IEEE802154_ADDR_LEN; i++)
+		(dest)[IEEE802154_ADDR_LEN - i - 1] = (src)[i];
+}
+
+static int lowpan_header_create(struct sk_buff *skb,
+			   struct net_device *dev,
+			   unsigned short type, const void *_daddr,
+			   const void *_saddr, unsigned int len)
+{
+	const u8 *saddr = _saddr;
+	const u8 *daddr = _daddr;
+	struct ieee802154_addr sa, da;
+	struct ieee802154_mac_cb *cb = mac_cb_init(skb);
+
+	/* TODO:
+	 * if this package isn't ipv6 one, where should it be routed?
+	 */
+	if (type != ETH_P_IPV6)
+		return 0;
+
+	if (!saddr)
+		saddr = dev->dev_addr;
+
+	raw_dump_inline(__func__, "saddr", (unsigned char *)saddr, 8);
+	raw_dump_inline(__func__, "daddr", (unsigned char *)daddr, 8);
+
+	lowpan_header_compress(skb, dev, type, daddr, saddr, len);
+
+	/* NOTE1: I'm still unsure about the fact that compression and WPAN
+	 * header are created here and not later in the xmit. So wait for
+	 * an opinion of net maintainers.
+	 */
+	/* NOTE2: to be absolutely correct, we must derive PANid information
+	 * from MAC subif of the 'dev' and 'real_dev' network devices, but
+	 * this isn't implemented in mainline yet, so currently we assign 0xff
+	 */
+	cb->type = IEEE802154_FC_TYPE_DATA;
+
+	/* prepare wpan address data */
+	sa.mode = IEEE802154_ADDR_LONG;
+	sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
+	sa.extended_addr = ieee802154_devaddr_from_raw(saddr);
+
+	/* intra-PAN communications */
+	da.pan_id = sa.pan_id;
+
+	/* if the destination address is the broadcast address, use the
+	 * corresponding short address
+	 */
+	if (lowpan_is_addr_broadcast(daddr)) {
+		da.mode = IEEE802154_ADDR_SHORT;
+		da.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+	} else {
+		da.mode = IEEE802154_ADDR_LONG;
+		da.extended_addr = ieee802154_devaddr_from_raw(daddr);
+	}
+
+	cb->ackreq = !lowpan_is_addr_broadcast(daddr);
+
+	return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev,
+			type, (void *)&da, (void *)&sa, 0);
+}
+
+static int lowpan_give_skb_to_devices(struct sk_buff *skb,
+					struct net_device *dev)
+{
+	struct lowpan_dev_record *entry;
+	struct sk_buff *skb_cp;
+	int stat = NET_RX_SUCCESS;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(entry, &lowpan_devices, list)
+		if (lowpan_dev_info(entry->ldev)->real_dev == skb->dev) {
+			skb_cp = skb_copy(skb, GFP_ATOMIC);
+			if (!skb_cp) {
+				stat = -ENOMEM;
+				break;
+			}
+
+			skb_cp->dev = entry->ldev;
+			stat = netif_rx(skb_cp);
+		}
+	rcu_read_unlock();
+
+	return stat;
+}
+
+static int process_data(struct sk_buff *skb, const struct ieee802154_hdr *hdr)
+{
+	u8 iphc0, iphc1;
+	struct ieee802154_addr_sa sa, da;
+	void *sap, *dap;
+
+	raw_dump_table(__func__, "raw skb data dump", skb->data, skb->len);
+	/* at least two bytes will be used for the encoding */
+	if (skb->len < 2)
+		goto drop;
+
+	if (lowpan_fetch_skb_u8(skb, &iphc0))
+		goto drop;
+
+	if (lowpan_fetch_skb_u8(skb, &iphc1))
+		goto drop;
+
+	ieee802154_addr_to_sa(&sa, &hdr->source);
+	ieee802154_addr_to_sa(&da, &hdr->dest);
+
+	if (sa.addr_type == IEEE802154_ADDR_SHORT)
+		sap = &sa.short_addr;
+	else
+		sap = &sa.hwaddr;
+
+	if (da.addr_type == IEEE802154_ADDR_SHORT)
+		dap = &da.short_addr;
+	else
+		dap = &da.hwaddr;
+
+	return lowpan_process_data(skb, skb->dev, sap, sa.addr_type,
+				   IEEE802154_ADDR_LEN, dap, da.addr_type,
+				   IEEE802154_ADDR_LEN, iphc0, iphc1,
+				   lowpan_give_skb_to_devices);
+
+drop:
+	kfree_skb(skb);
+	return -EINVAL;
+}
+
+static int lowpan_set_address(struct net_device *dev, void *p)
+{
+	struct sockaddr *sa = p;
+
+	if (netif_running(dev))
+		return -EBUSY;
+
+	/* TODO: validate addr */
+	memcpy(dev->dev_addr, sa->sa_data, dev->addr_len);
+
+	return 0;
+}
+
+static struct sk_buff*
+lowpan_alloc_frag(struct sk_buff *skb, int size,
+		  const struct ieee802154_hdr *master_hdr)
+{
+	struct net_device *real_dev = lowpan_dev_info(skb->dev)->real_dev;
+	struct sk_buff *frag;
+	int rc;
+
+	frag = alloc_skb(real_dev->hard_header_len +
+			 real_dev->needed_tailroom + size,
+			 GFP_ATOMIC);
+
+	if (likely(frag)) {
+		frag->dev = real_dev;
+		frag->priority = skb->priority;
+		skb_reserve(frag, real_dev->hard_header_len);
+		skb_reset_network_header(frag);
+		*mac_cb(frag) = *mac_cb(skb);
+
+		rc = dev_hard_header(frag, real_dev, 0, &master_hdr->dest,
+				     &master_hdr->source, size);
+		if (rc < 0) {
+			kfree_skb(frag);
+			return ERR_PTR(-rc);
+		}
+	} else {
+		frag = ERR_PTR(ENOMEM);
+	}
+
+	return frag;
+}
+
+static int
+lowpan_xmit_fragment(struct sk_buff *skb, const struct ieee802154_hdr *wpan_hdr,
+		     u8 *frag_hdr, int frag_hdrlen,
+		     int offset, int len)
+{
+	struct sk_buff *frag;
+
+	raw_dump_inline(__func__, " fragment header", frag_hdr, frag_hdrlen);
+
+	frag = lowpan_alloc_frag(skb, frag_hdrlen + len, wpan_hdr);
+	if (IS_ERR(frag))
+		return -PTR_ERR(frag);
+
+	memcpy(skb_put(frag, frag_hdrlen), frag_hdr, frag_hdrlen);
+	memcpy(skb_put(frag, len), skb_network_header(skb) + offset, len);
+
+	raw_dump_table(__func__, " fragment dump", frag->data, frag->len);
+
+	return dev_queue_xmit(frag);
+}
+
+static int
+lowpan_xmit_fragmented(struct sk_buff *skb, struct net_device *dev,
+		       const struct ieee802154_hdr *wpan_hdr)
+{
+	u16 dgram_size, dgram_offset;
+	__be16 frag_tag;
+	u8 frag_hdr[5];
+	int frag_cap, frag_len, payload_cap, rc;
+	int skb_unprocessed, skb_offset;
+
+	dgram_size = lowpan_uncompress_size(skb, &dgram_offset) -
+		     skb->mac_len;
+	frag_tag = lowpan_dev_info(dev)->fragment_tag++;
+
+	frag_hdr[0] = LOWPAN_DISPATCH_FRAG1 | ((dgram_size >> 8) & 0x07);
+	frag_hdr[1] = dgram_size & 0xff;
+	memcpy(frag_hdr + 2, &frag_tag, sizeof(frag_tag));
+
+	payload_cap = ieee802154_max_payload(wpan_hdr);
+
+	frag_len = round_down(payload_cap - LOWPAN_FRAG1_HEAD_SIZE -
+			      skb_network_header_len(skb), 8);
+
+	skb_offset = skb_network_header_len(skb);
+	skb_unprocessed = skb->len - skb->mac_len - skb_offset;
+
+	rc = lowpan_xmit_fragment(skb, wpan_hdr, frag_hdr,
+				  LOWPAN_FRAG1_HEAD_SIZE, 0,
+				  frag_len + skb_network_header_len(skb));
+	if (rc) {
+		pr_debug("%s unable to send FRAG1 packet (tag: %d)",
+			 __func__, frag_tag);
+		goto err;
+	}
+
+	frag_hdr[0] &= ~LOWPAN_DISPATCH_FRAG1;
+	frag_hdr[0] |= LOWPAN_DISPATCH_FRAGN;
+	frag_cap = round_down(payload_cap - LOWPAN_FRAGN_HEAD_SIZE, 8);
+
+	do {
+		dgram_offset += frag_len;
+		skb_offset += frag_len;
+		skb_unprocessed -= frag_len;
+		frag_len = min(frag_cap, skb_unprocessed);
+
+		frag_hdr[4] = dgram_offset >> 3;
+
+		rc = lowpan_xmit_fragment(skb, wpan_hdr, frag_hdr,
+					  LOWPAN_FRAGN_HEAD_SIZE, skb_offset,
+					  frag_len);
+		if (rc) {
+			pr_debug("%s unable to send a FRAGN packet. (tag: %d, offset: %d)\n",
+				 __func__, frag_tag, skb_offset);
+			goto err;
+		}
+	} while (skb_unprocessed > frag_cap);
+
+	consume_skb(skb);
+	return NET_XMIT_SUCCESS;
+
+err:
+	kfree_skb(skb);
+	return rc;
+}
+
+static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ieee802154_hdr wpan_hdr;
+	int max_single;
+
+	pr_debug("package xmit\n");
+
+	if (ieee802154_hdr_peek(skb, &wpan_hdr) < 0) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	max_single = ieee802154_max_payload(&wpan_hdr);
+
+	if (skb_tail_pointer(skb) - skb_network_header(skb) <= max_single) {
+		skb->dev = lowpan_dev_info(dev)->real_dev;
+		return dev_queue_xmit(skb);
+	} else {
+		netdev_tx_t rc;
+
+		pr_debug("frame is too big, fragmentation is needed\n");
+		rc = lowpan_xmit_fragmented(skb, dev, &wpan_hdr);
+
+		return rc < 0 ? NET_XMIT_DROP : rc;
+	}
+}
+
+static struct wpan_phy *lowpan_get_phy(const struct net_device *dev)
+{
+	struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
+	return ieee802154_mlme_ops(real_dev)->get_phy(real_dev);
+}
+
+static __le16 lowpan_get_pan_id(const struct net_device *dev)
+{
+	struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
+	return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev);
+}
+
+static __le16 lowpan_get_short_addr(const struct net_device *dev)
+{
+	struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
+	return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev);
+}
+
+static u8 lowpan_get_dsn(const struct net_device *dev)
+{
+	struct net_device *real_dev = lowpan_dev_info(dev)->real_dev;
+	return ieee802154_mlme_ops(real_dev)->get_dsn(real_dev);
+}
+
+static struct header_ops lowpan_header_ops = {
+	.create	= lowpan_header_create,
+};
+
+static struct lock_class_key lowpan_tx_busylock;
+static struct lock_class_key lowpan_netdev_xmit_lock_key;
+
+static void lowpan_set_lockdep_class_one(struct net_device *dev,
+					 struct netdev_queue *txq,
+					 void *_unused)
+{
+	lockdep_set_class(&txq->_xmit_lock,
+			  &lowpan_netdev_xmit_lock_key);
+}
+
+
+static int lowpan_dev_init(struct net_device *dev)
+{
+	netdev_for_each_tx_queue(dev, lowpan_set_lockdep_class_one, NULL);
+	dev->qdisc_tx_busylock = &lowpan_tx_busylock;
+	return 0;
+}
+
+static const struct net_device_ops lowpan_netdev_ops = {
+	.ndo_init		= lowpan_dev_init,
+	.ndo_start_xmit		= lowpan_xmit,
+	.ndo_set_mac_address	= lowpan_set_address,
+};
+
+static struct ieee802154_mlme_ops lowpan_mlme = {
+	.get_pan_id = lowpan_get_pan_id,
+	.get_phy = lowpan_get_phy,
+	.get_short_addr = lowpan_get_short_addr,
+	.get_dsn = lowpan_get_dsn,
+};
+
+static void lowpan_setup(struct net_device *dev)
+{
+	dev->addr_len		= IEEE802154_ADDR_LEN;
+	memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN);
+	dev->type		= ARPHRD_IEEE802154;
+	/* Frame Control + Sequence Number + Address fields + Security Header */
+	dev->hard_header_len	= 2 + 1 + 20 + 14;
+	dev->needed_tailroom	= 2; /* FCS */
+	dev->mtu		= 1281;
+	dev->tx_queue_len	= 0;
+	dev->flags		= IFF_BROADCAST | IFF_MULTICAST;
+	dev->watchdog_timeo	= 0;
+
+	dev->netdev_ops		= &lowpan_netdev_ops;
+	dev->header_ops		= &lowpan_header_ops;
+	dev->ml_priv		= &lowpan_mlme;
+	dev->destructor		= free_netdev;
+}
+
+static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	if (tb[IFLA_ADDRESS]) {
+		if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev,
+	struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct ieee802154_hdr hdr;
+	int ret;
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		goto drop;
+
+	if (!netif_running(dev))
+		goto drop_skb;
+
+	if (dev->type != ARPHRD_IEEE802154)
+		goto drop_skb;
+
+	if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0)
+		goto drop_skb;
+
+	/* check that it's our buffer */
+	if (skb->data[0] == LOWPAN_DISPATCH_IPV6) {
+		skb->protocol = htons(ETH_P_IPV6);
+		skb->pkt_type = PACKET_HOST;
+
+		/* Pull off the 1-byte of 6lowpan header. */
+		skb_pull(skb, 1);
+
+		ret = lowpan_give_skb_to_devices(skb, NULL);
+		if (ret == NET_RX_DROP)
+			goto drop;
+	} else {
+		switch (skb->data[0] & 0xe0) {
+		case LOWPAN_DISPATCH_IPHC:	/* ipv6 datagram */
+			ret = process_data(skb, &hdr);
+			if (ret == NET_RX_DROP)
+				goto drop;
+			break;
+		case LOWPAN_DISPATCH_FRAG1:	/* first fragment header */
+			ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAG1);
+			if (ret == 1) {
+				ret = process_data(skb, &hdr);
+				if (ret == NET_RX_DROP)
+					goto drop;
+			}
+			break;
+		case LOWPAN_DISPATCH_FRAGN:	/* next fragments headers */
+			ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAGN);
+			if (ret == 1) {
+				ret = process_data(skb, &hdr);
+				if (ret == NET_RX_DROP)
+					goto drop;
+			}
+			break;
+		default:
+			break;
+		}
+	}
+
+	return NET_RX_SUCCESS;
+drop_skb:
+	kfree_skb(skb);
+drop:
+	return NET_RX_DROP;
+}
+
+static int lowpan_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[])
+{
+	struct net_device *real_dev;
+	struct lowpan_dev_record *entry;
+
+	pr_debug("adding new link\n");
+
+	if (!tb[IFLA_LINK])
+		return -EINVAL;
+	/* find and hold real wpan device */
+	real_dev = dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	if (!real_dev)
+		return -ENODEV;
+	if (real_dev->type != ARPHRD_IEEE802154) {
+		dev_put(real_dev);
+		return -EINVAL;
+	}
+
+	lowpan_dev_info(dev)->real_dev = real_dev;
+	mutex_init(&lowpan_dev_info(dev)->dev_list_mtx);
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		dev_put(real_dev);
+		lowpan_dev_info(dev)->real_dev = NULL;
+		return -ENOMEM;
+	}
+
+	entry->ldev = dev;
+
+	/* Set the lowpan harware address to the wpan hardware address. */
+	memcpy(dev->dev_addr, real_dev->dev_addr, IEEE802154_ADDR_LEN);
+
+	mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx);
+	INIT_LIST_HEAD(&entry->list);
+	list_add_tail(&entry->list, &lowpan_devices);
+	mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx);
+
+	register_netdevice(dev);
+
+	return 0;
+}
+
+static void lowpan_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct lowpan_dev_info *lowpan_dev = lowpan_dev_info(dev);
+	struct net_device *real_dev = lowpan_dev->real_dev;
+	struct lowpan_dev_record *entry, *tmp;
+
+	ASSERT_RTNL();
+
+	mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx);
+	list_for_each_entry_safe(entry, tmp, &lowpan_devices, list) {
+		if (entry->ldev == dev) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
+	}
+	mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx);
+
+	mutex_destroy(&lowpan_dev_info(dev)->dev_list_mtx);
+
+	unregister_netdevice_queue(dev, head);
+
+	dev_put(real_dev);
+}
+
+static struct rtnl_link_ops lowpan_link_ops __read_mostly = {
+	.kind		= "lowpan",
+	.priv_size	= sizeof(struct lowpan_dev_info),
+	.setup		= lowpan_setup,
+	.newlink	= lowpan_newlink,
+	.dellink	= lowpan_dellink,
+	.validate	= lowpan_validate,
+};
+
+static inline int __init lowpan_netlink_init(void)
+{
+	return rtnl_link_register(&lowpan_link_ops);
+}
+
+static inline void lowpan_netlink_fini(void)
+{
+	rtnl_link_unregister(&lowpan_link_ops);
+}
+
+static int lowpan_device_event(struct notifier_block *unused,
+			       unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	LIST_HEAD(del_list);
+	struct lowpan_dev_record *entry, *tmp;
+
+	if (dev->type != ARPHRD_IEEE802154)
+		goto out;
+
+	if (event == NETDEV_UNREGISTER) {
+		list_for_each_entry_safe(entry, tmp, &lowpan_devices, list) {
+			if (lowpan_dev_info(entry->ldev)->real_dev == dev)
+				lowpan_dellink(entry->ldev, &del_list);
+		}
+
+		unregister_netdevice_many(&del_list);
+	}
+
+out:
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block lowpan_dev_notifier = {
+	.notifier_call = lowpan_device_event,
+};
+
+static struct packet_type lowpan_packet_type = {
+	.type = htons(ETH_P_IEEE802154),
+	.func = lowpan_rcv,
+};
+
+static int __init lowpan_init_module(void)
+{
+	int err = 0;
+
+	err = lowpan_net_frag_init();
+	if (err < 0)
+		goto out;
+
+	err = lowpan_netlink_init();
+	if (err < 0)
+		goto out_frag;
+
+	dev_add_pack(&lowpan_packet_type);
+
+	err = register_netdevice_notifier(&lowpan_dev_notifier);
+	if (err < 0)
+		goto out_pack;
+
+	return 0;
+
+out_pack:
+	dev_remove_pack(&lowpan_packet_type);
+	lowpan_netlink_fini();
+out_frag:
+	lowpan_net_frag_exit();
+out:
+	return err;
+}
+
+static void __exit lowpan_cleanup_module(void)
+{
+	lowpan_netlink_fini();
+
+	dev_remove_pack(&lowpan_packet_type);
+
+	lowpan_net_frag_exit();
+
+	unregister_netdevice_notifier(&lowpan_dev_notifier);
+}
+
+module_init(lowpan_init_module);
+module_exit(lowpan_cleanup_module);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("lowpan");
diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig
index b2e06df0076..8af1330b313 100644
--- a/net/ieee802154/Kconfig
+++ b/net/ieee802154/Kconfig
@@ -13,5 +13,12 @@ config IEEE802154
 config IEEE802154_6LOWPAN
 	tristate "6lowpan support over IEEE 802.15.4"
 	depends on IEEE802154 && IPV6
+	select 6LOWPAN_IPHC
 	---help---
-	IPv6 compression over IEEE 802.15.4.
+	  IPv6 compression over IEEE 802.15.4.
+
+config 6LOWPAN_IPHC
+	tristate
+	---help---
+	  6lowpan compression code which is shared between IEEE 802.15.4 and Bluetooth
+	  stacks.
diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile
index d7716d64c6b..bf1b51497a4 100644
--- a/net/ieee802154/Makefile
+++ b/net/ieee802154/Makefile
@@ -1,5 +1,10 @@
 obj-$(CONFIG_IEEE802154) += ieee802154.o af_802154.o
 obj-$(CONFIG_IEEE802154_6LOWPAN) += 6lowpan.o
+obj-$(CONFIG_6LOWPAN_IPHC) += 6lowpan_iphc.o
 
-ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o
+6lowpan-y := 6lowpan_rtnl.o reassembly.o
+ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o \
+                header_ops.o
 af_802154-y := af_ieee802154.o raw.o dgram.o
+
+ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/ieee802154/af802154.h b/net/ieee802154/af802154.h
index b1ec5253752..8330a09bfc9 100644
--- a/net/ieee802154/af802154.h
+++ b/net/ieee802154/af802154.h
@@ -25,12 +25,13 @@
 #define AF802154_H
 
 struct sk_buff;
-struct net_devce;
+struct net_device;
+struct ieee802154_addr;
 extern struct proto ieee802154_raw_prot;
 extern struct proto ieee802154_dgram_prot;
 void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb);
 int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb);
 struct net_device *ieee802154_get_dev(struct net *net,
-		struct ieee802154_addr *addr);
+				      const struct ieee802154_addr *addr);
 
 #endif
diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c
index 40e606f3788..351d9a94ec2 100644
--- a/net/ieee802154/af_ieee802154.c
+++ b/net/ieee802154/af_ieee802154.c
@@ -43,25 +43,27 @@
 /*
  * Utility function for families
  */
-struct net_device *ieee802154_get_dev(struct net *net,
-		struct ieee802154_addr *addr)
+struct net_device*
+ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr)
 {
 	struct net_device *dev = NULL;
 	struct net_device *tmp;
-	u16 pan_id, short_addr;
+	__le16 pan_id, short_addr;
+	u8 hwaddr[IEEE802154_ADDR_LEN];
 
-	switch (addr->addr_type) {
+	switch (addr->mode) {
 	case IEEE802154_ADDR_LONG:
+		ieee802154_devaddr_to_raw(hwaddr, addr->extended_addr);
 		rcu_read_lock();
-		dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, addr->hwaddr);
+		dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, hwaddr);
 		if (dev)
 			dev_hold(dev);
 		rcu_read_unlock();
 		break;
 	case IEEE802154_ADDR_SHORT:
-		if (addr->pan_id == 0xffff ||
-		    addr->short_addr == IEEE802154_ADDR_UNDEF ||
-		    addr->short_addr == 0xffff)
+		if (addr->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST) ||
+		    addr->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) ||
+		    addr->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST))
 			break;
 
 		rtnl_lock();
@@ -86,7 +88,7 @@ struct net_device *ieee802154_get_dev(struct net *net,
 		break;
 	default:
 		pr_warning("Unsupported ieee802154 address type: %d\n",
-				addr->addr_type);
+				addr->mode);
 		break;
 	}
 
@@ -326,7 +328,7 @@ drop:
 
 
 static struct packet_type ieee802154_packet_type = {
-	.type = __constant_htons(ETH_P_IEEE802154),
+	.type = htons(ETH_P_IEEE802154),
 	.func = ieee802154_rcv,
 };
 
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index 1865fdf5a5a..4f0ed878019 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -21,6 +21,7 @@
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  */
 
+#include <linux/capability.h>
 #include <linux/net.h>
 #include <linux/module.h>
 #include <linux/if_arp.h>
@@ -45,7 +46,12 @@ struct dgram_sock {
 	struct ieee802154_addr dst_addr;
 
 	unsigned int bound:1;
+	unsigned int connected:1;
 	unsigned int want_ack:1;
+	unsigned int secen:1;
+	unsigned int secen_override:1;
+	unsigned int seclevel:3;
+	unsigned int seclevel_override:1;
 };
 
 static inline struct dgram_sock *dgram_sk(const struct sock *sk)
@@ -73,10 +79,7 @@ static int dgram_init(struct sock *sk)
 {
 	struct dgram_sock *ro = dgram_sk(sk);
 
-	ro->dst_addr.addr_type = IEEE802154_ADDR_LONG;
-	ro->dst_addr.pan_id = 0xffff;
 	ro->want_ack = 1;
-	memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr));
 	return 0;
 }
 
@@ -88,6 +91,7 @@ static void dgram_close(struct sock *sk, long timeout)
 static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len)
 {
 	struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr;
+	struct ieee802154_addr haddr;
 	struct dgram_sock *ro = dgram_sk(sk);
 	int err = -EINVAL;
 	struct net_device *dev;
@@ -102,7 +106,8 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len)
 	if (addr->family != AF_IEEE802154)
 		goto out;
 
-	dev = ieee802154_get_dev(sock_net(sk), &addr->addr);
+	ieee802154_addr_from_sa(&haddr, &addr->addr);
+	dev = ieee802154_get_dev(sock_net(sk), &haddr);
 	if (!dev) {
 		err = -ENODEV;
 		goto out;
@@ -113,7 +118,7 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len)
 		goto out_put;
 	}
 
-	memcpy(&ro->src_addr, &addr->addr, sizeof(struct ieee802154_addr));
+	ro->src_addr = haddr;
 
 	ro->bound = 1;
 	err = 0;
@@ -149,8 +154,7 @@ static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg)
 			 * of this packet since that is all
 			 * that will be read.
 			 */
-			/* FIXME: parse the header for more correct value */
-			amount = skb->len - (3+8+8);
+			amount = skb->len - ieee802154_hdr_length(skb);
 		}
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return put_user(amount, (int __user *)arg);
@@ -181,7 +185,8 @@ static int dgram_connect(struct sock *sk, struct sockaddr *uaddr,
 		goto out;
 	}
 
-	memcpy(&ro->dst_addr, &addr->addr, sizeof(struct ieee802154_addr));
+	ieee802154_addr_from_sa(&ro->dst_addr, &addr->addr);
+	ro->connected = 1;
 
 out:
 	release_sock(sk);
@@ -193,10 +198,7 @@ static int dgram_disconnect(struct sock *sk, int flags)
 	struct dgram_sock *ro = dgram_sk(sk);
 
 	lock_sock(sk);
-
-	ro->dst_addr.addr_type = IEEE802154_ADDR_LONG;
-	memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr));
-
+	ro->connected = 0;
 	release_sock(sk);
 
 	return 0;
@@ -208,7 +210,9 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
 	struct net_device *dev;
 	unsigned int mtu;
 	struct sk_buff *skb;
+	struct ieee802154_mac_cb *cb;
 	struct dgram_sock *ro = dgram_sk(sk);
+	struct ieee802154_addr dst_addr;
 	int hlen, tlen;
 	int err;
 
@@ -217,6 +221,11 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
 		return -EOPNOTSUPP;
 	}
 
+	if (!ro->connected && !msg->msg_name)
+		return -EDESTADDRREQ;
+	else if (ro->connected && msg->msg_name)
+		return -EISCONN;
+
 	if (!ro->bound)
 		dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154);
 	else
@@ -232,7 +241,7 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 	if (size > mtu) {
 		pr_debug("size = %Zu, mtu = %u\n", size, mtu);
-		err = -EINVAL;
+		err = -EMSGSIZE;
 		goto out_dev;
 	}
 
@@ -248,18 +257,28 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 	skb_reset_network_header(skb);
 
-	mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA;
-	if (ro->want_ack)
-		mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ;
+	cb = mac_cb_init(skb);
+	cb->type = IEEE802154_FC_TYPE_DATA;
+	cb->ackreq = ro->want_ack;
+
+	if (msg->msg_name) {
+		DECLARE_SOCKADDR(struct sockaddr_ieee802154*, daddr, msg->msg_name);
+
+		ieee802154_addr_from_sa(&dst_addr, &daddr->addr);
+	} else {
+		dst_addr = ro->dst_addr;
+	}
+
+	cb->secen = ro->secen;
+	cb->secen_override = ro->secen_override;
+	cb->seclevel = ro->seclevel;
+	cb->seclevel_override = ro->seclevel_override;
 
-	mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev);
-	err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &ro->dst_addr,
-			ro->bound ? &ro->src_addr : NULL, size);
+	err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &dst_addr,
+			      ro->bound ? &ro->src_addr : NULL, size);
 	if (err < 0)
 		goto out_skb;
 
-	skb_reset_mac_header(skb);
-
 	err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
 	if (err < 0)
 		goto out_skb;
@@ -291,9 +310,7 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk,
 	size_t copied = 0;
 	int err = -EOPNOTSUPP;
 	struct sk_buff *skb;
-	struct sockaddr_ieee802154 *saddr;
-
-	saddr = (struct sockaddr_ieee802154 *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_ieee802154 *, saddr, msg->msg_name);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
@@ -314,7 +331,7 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk,
 
 	if (saddr) {
 		saddr->family = AF_IEEE802154;
-		saddr->addr = mac_cb(skb)->sa;
+		ieee802154_addr_to_sa(&saddr->addr, &mac_cb(skb)->source);
 		*addr_len = sizeof(*saddr);
 	}
 
@@ -330,6 +347,10 @@ out:
 
 static int dgram_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return NET_RX_DROP;
+
 	if (sock_queue_rcv_skb(sk, skb) < 0) {
 		kfree_skb(skb);
 		return NET_RX_DROP;
@@ -338,40 +359,43 @@ static int dgram_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	return NET_RX_SUCCESS;
 }
 
-static inline int ieee802154_match_sock(u8 *hw_addr, u16 pan_id,
-		u16 short_addr, struct dgram_sock *ro)
+static inline bool
+ieee802154_match_sock(__le64 hw_addr, __le16 pan_id, __le16 short_addr,
+		      struct dgram_sock *ro)
 {
 	if (!ro->bound)
-		return 1;
+		return true;
 
-	if (ro->src_addr.addr_type == IEEE802154_ADDR_LONG &&
-	    !memcmp(ro->src_addr.hwaddr, hw_addr, IEEE802154_ADDR_LEN))
-		return 1;
+	if (ro->src_addr.mode == IEEE802154_ADDR_LONG &&
+	    hw_addr == ro->src_addr.extended_addr)
+		return true;
 
-	if (ro->src_addr.addr_type == IEEE802154_ADDR_SHORT &&
-		     pan_id == ro->src_addr.pan_id &&
-		     short_addr == ro->src_addr.short_addr)
-		return 1;
+	if (ro->src_addr.mode == IEEE802154_ADDR_SHORT &&
+	    pan_id == ro->src_addr.pan_id &&
+	    short_addr == ro->src_addr.short_addr)
+		return true;
 
-	return 0;
+	return false;
 }
 
 int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb)
 {
 	struct sock *sk, *prev = NULL;
 	int ret = NET_RX_SUCCESS;
-	u16 pan_id, short_addr;
+	__le16 pan_id, short_addr;
+	__le64 hw_addr;
 
 	/* Data frame processing */
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
 	pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
 	short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev);
+	hw_addr = ieee802154_devaddr_from_raw(dev->dev_addr);
 
 	read_lock(&dgram_lock);
 	sk_for_each(sk, &dgram_head) {
-		if (ieee802154_match_sock(dev->dev_addr, pan_id, short_addr,
-					dgram_sk(sk))) {
+		if (ieee802154_match_sock(hw_addr, pan_id, short_addr,
+					  dgram_sk(sk))) {
 			if (prev) {
 				struct sk_buff *clone;
 				clone = skb_clone(skb, GFP_ATOMIC);
@@ -413,6 +437,20 @@ static int dgram_getsockopt(struct sock *sk, int level, int optname,
 	case WPAN_WANTACK:
 		val = ro->want_ack;
 		break;
+	case WPAN_SECURITY:
+		if (!ro->secen_override)
+			val = WPAN_SECURITY_DEFAULT;
+		else if (ro->secen)
+			val = WPAN_SECURITY_ON;
+		else
+			val = WPAN_SECURITY_OFF;
+		break;
+	case WPAN_SECURITY_LEVEL:
+		if (!ro->seclevel_override)
+			val = WPAN_SECURITY_LEVEL_DEFAULT;
+		else
+			val = ro->seclevel;
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -428,6 +466,7 @@ static int dgram_setsockopt(struct sock *sk, int level, int optname,
 		    char __user *optval, unsigned int optlen)
 {
 	struct dgram_sock *ro = dgram_sk(sk);
+	struct net *net = sock_net(sk);
 	int val;
 	int err = 0;
 
@@ -443,6 +482,47 @@ static int dgram_setsockopt(struct sock *sk, int level, int optname,
 	case WPAN_WANTACK:
 		ro->want_ack = !!val;
 		break;
+	case WPAN_SECURITY:
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN) &&
+		    !ns_capable(net->user_ns, CAP_NET_RAW)) {
+			err = -EPERM;
+			break;
+		}
+
+		switch (val) {
+		case WPAN_SECURITY_DEFAULT:
+			ro->secen_override = 0;
+			break;
+		case WPAN_SECURITY_ON:
+			ro->secen_override = 1;
+			ro->secen = 1;
+			break;
+		case WPAN_SECURITY_OFF:
+			ro->secen_override = 1;
+			ro->secen = 0;
+			break;
+		default:
+			err = -EINVAL;
+			break;
+		}
+		break;
+	case WPAN_SECURITY_LEVEL:
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN) &&
+		    !ns_capable(net->user_ns, CAP_NET_RAW)) {
+			err = -EPERM;
+			break;
+		}
+
+		if (val < WPAN_SECURITY_LEVEL_DEFAULT ||
+		    val > IEEE802154_SCF_SECLEVEL_ENC_MIC128) {
+			err = -EINVAL;
+		} else if (val == WPAN_SECURITY_LEVEL_DEFAULT) {
+			ro->seclevel_override = 0;
+		} else {
+			ro->seclevel_override = 1;
+			ro->seclevel = val;
+		}
+		break;
 	default:
 		err = -ENOPROTOOPT;
 		break;
diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c
new file mode 100644
index 00000000000..c09294e39ca
--- /dev/null
+++ b/net/ieee802154/header_ops.c
@@ -0,0 +1,325 @@
+/*
+ * Copyright (C) 2014 Fraunhofer ITWM
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Written by:
+ * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
+ */
+
+#include <net/mac802154.h>
+#include <net/ieee802154.h>
+#include <net/ieee802154_netdev.h>
+
+static int
+ieee802154_hdr_push_addr(u8 *buf, const struct ieee802154_addr *addr,
+			 bool omit_pan)
+{
+	int pos = 0;
+
+	if (addr->mode == IEEE802154_ADDR_NONE)
+		return 0;
+
+	if (!omit_pan) {
+		memcpy(buf + pos, &addr->pan_id, 2);
+		pos += 2;
+	}
+
+	switch (addr->mode) {
+	case IEEE802154_ADDR_SHORT:
+		memcpy(buf + pos, &addr->short_addr, 2);
+		pos += 2;
+		break;
+
+	case IEEE802154_ADDR_LONG:
+		memcpy(buf + pos, &addr->extended_addr, IEEE802154_ADDR_LEN);
+		pos += IEEE802154_ADDR_LEN;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return pos;
+}
+
+static int
+ieee802154_hdr_push_sechdr(u8 *buf, const struct ieee802154_sechdr *hdr)
+{
+	int pos = 5;
+
+	memcpy(buf, hdr, 1);
+	memcpy(buf + 1, &hdr->frame_counter, 4);
+
+	switch (hdr->key_id_mode) {
+	case IEEE802154_SCF_KEY_IMPLICIT:
+		return pos;
+
+	case IEEE802154_SCF_KEY_INDEX:
+		break;
+
+	case IEEE802154_SCF_KEY_SHORT_INDEX:
+		memcpy(buf + pos, &hdr->short_src, 4);
+		pos += 4;
+		break;
+
+	case IEEE802154_SCF_KEY_HW_INDEX:
+		memcpy(buf + pos, &hdr->extended_src, IEEE802154_ADDR_LEN);
+		pos += IEEE802154_ADDR_LEN;
+		break;
+	}
+
+	buf[pos++] = hdr->key_id;
+
+	return pos;
+}
+
+int
+ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr)
+{
+	u8 buf[MAC802154_FRAME_HARD_HEADER_LEN];
+	int pos = 2;
+	int rc;
+	struct ieee802154_hdr_fc fc = hdr->fc;
+
+	buf[pos++] = hdr->seq;
+
+	fc.dest_addr_mode = hdr->dest.mode;
+
+	rc = ieee802154_hdr_push_addr(buf + pos, &hdr->dest, false);
+	if (rc < 0)
+		return -EINVAL;
+	pos += rc;
+
+	fc.source_addr_mode = hdr->source.mode;
+
+	if (hdr->source.pan_id == hdr->dest.pan_id &&
+	    hdr->dest.mode != IEEE802154_ADDR_NONE)
+		fc.intra_pan = true;
+
+	rc = ieee802154_hdr_push_addr(buf + pos, &hdr->source, fc.intra_pan);
+	if (rc < 0)
+		return -EINVAL;
+	pos += rc;
+
+	if (fc.security_enabled) {
+		fc.version = 1;
+
+		rc = ieee802154_hdr_push_sechdr(buf + pos, &hdr->sec);
+		if (rc < 0)
+			return -EINVAL;
+
+		pos += rc;
+	}
+
+	memcpy(buf, &fc, 2);
+
+	memcpy(skb_push(skb, pos), buf, pos);
+
+	return pos;
+}
+EXPORT_SYMBOL_GPL(ieee802154_hdr_push);
+
+static int
+ieee802154_hdr_get_addr(const u8 *buf, int mode, bool omit_pan,
+			struct ieee802154_addr *addr)
+{
+	int pos = 0;
+
+	addr->mode = mode;
+
+	if (mode == IEEE802154_ADDR_NONE)
+		return 0;
+
+	if (!omit_pan) {
+		memcpy(&addr->pan_id, buf + pos, 2);
+		pos += 2;
+	}
+
+	if (mode == IEEE802154_ADDR_SHORT) {
+		memcpy(&addr->short_addr, buf + pos, 2);
+		return pos + 2;
+	} else {
+		memcpy(&addr->extended_addr, buf + pos, IEEE802154_ADDR_LEN);
+		return pos + IEEE802154_ADDR_LEN;
+	}
+}
+
+static int ieee802154_hdr_addr_len(int mode, bool omit_pan)
+{
+	int pan_len = omit_pan ? 0 : 2;
+
+	switch (mode) {
+	case IEEE802154_ADDR_NONE: return 0;
+	case IEEE802154_ADDR_SHORT: return 2 + pan_len;
+	case IEEE802154_ADDR_LONG: return IEEE802154_ADDR_LEN + pan_len;
+	default: return -EINVAL;
+	}
+}
+
+static int
+ieee802154_hdr_get_sechdr(const u8 *buf, struct ieee802154_sechdr *hdr)
+{
+	int pos = 5;
+
+	memcpy(hdr, buf, 1);
+	memcpy(&hdr->frame_counter, buf + 1, 4);
+
+	switch (hdr->key_id_mode) {
+	case IEEE802154_SCF_KEY_IMPLICIT:
+		return pos;
+
+	case IEEE802154_SCF_KEY_INDEX:
+		break;
+
+	case IEEE802154_SCF_KEY_SHORT_INDEX:
+		memcpy(&hdr->short_src, buf + pos, 4);
+		pos += 4;
+		break;
+
+	case IEEE802154_SCF_KEY_HW_INDEX:
+		memcpy(&hdr->extended_src, buf + pos, IEEE802154_ADDR_LEN);
+		pos += IEEE802154_ADDR_LEN;
+		break;
+	}
+
+	hdr->key_id = buf[pos++];
+
+	return pos;
+}
+
+static int ieee802154_sechdr_lengths[4] = {
+	[IEEE802154_SCF_KEY_IMPLICIT] = 5,
+	[IEEE802154_SCF_KEY_INDEX] = 6,
+	[IEEE802154_SCF_KEY_SHORT_INDEX] = 10,
+	[IEEE802154_SCF_KEY_HW_INDEX] = 14,
+};
+
+static int ieee802154_hdr_sechdr_len(u8 sc)
+{
+	return ieee802154_sechdr_lengths[IEEE802154_SCF_KEY_ID_MODE(sc)];
+}
+
+static int ieee802154_hdr_minlen(const struct ieee802154_hdr *hdr)
+{
+	int dlen, slen;
+
+	dlen = ieee802154_hdr_addr_len(hdr->fc.dest_addr_mode, false);
+	slen = ieee802154_hdr_addr_len(hdr->fc.source_addr_mode,
+				       hdr->fc.intra_pan);
+
+	if (slen < 0 || dlen < 0)
+		return -EINVAL;
+
+	return 3 + dlen + slen + hdr->fc.security_enabled;
+}
+
+static int
+ieee802154_hdr_get_addrs(const u8 *buf, struct ieee802154_hdr *hdr)
+{
+	int pos = 0;
+
+	pos += ieee802154_hdr_get_addr(buf + pos, hdr->fc.dest_addr_mode,
+				       false, &hdr->dest);
+	pos += ieee802154_hdr_get_addr(buf + pos, hdr->fc.source_addr_mode,
+				       hdr->fc.intra_pan, &hdr->source);
+
+	if (hdr->fc.intra_pan)
+		hdr->source.pan_id = hdr->dest.pan_id;
+
+	return pos;
+}
+
+int
+ieee802154_hdr_pull(struct sk_buff *skb, struct ieee802154_hdr *hdr)
+{
+	int pos = 3, rc;
+
+	if (!pskb_may_pull(skb, 3))
+		return -EINVAL;
+
+	memcpy(hdr, skb->data, 3);
+
+	rc = ieee802154_hdr_minlen(hdr);
+	if (rc < 0 || !pskb_may_pull(skb, rc))
+		return -EINVAL;
+
+	pos += ieee802154_hdr_get_addrs(skb->data + pos, hdr);
+
+	if (hdr->fc.security_enabled) {
+		int want = pos + ieee802154_hdr_sechdr_len(skb->data[pos]);
+
+		if (!pskb_may_pull(skb, want))
+			return -EINVAL;
+
+		pos += ieee802154_hdr_get_sechdr(skb->data + pos, &hdr->sec);
+	}
+
+	skb_pull(skb, pos);
+	return pos;
+}
+EXPORT_SYMBOL_GPL(ieee802154_hdr_pull);
+
+int
+ieee802154_hdr_peek_addrs(const struct sk_buff *skb, struct ieee802154_hdr *hdr)
+{
+	const u8 *buf = skb_mac_header(skb);
+	int pos = 3, rc;
+
+	if (buf + 3 > skb_tail_pointer(skb))
+		return -EINVAL;
+
+	memcpy(hdr, buf, 3);
+
+	rc = ieee802154_hdr_minlen(hdr);
+	if (rc < 0 || buf + rc > skb_tail_pointer(skb))
+		return -EINVAL;
+
+	pos += ieee802154_hdr_get_addrs(buf + pos, hdr);
+	return pos;
+}
+EXPORT_SYMBOL_GPL(ieee802154_hdr_peek_addrs);
+
+int
+ieee802154_hdr_peek(const struct sk_buff *skb, struct ieee802154_hdr *hdr)
+{
+	const u8 *buf = skb_mac_header(skb);
+	int pos;
+
+	pos = ieee802154_hdr_peek_addrs(skb, hdr);
+	if (pos < 0)
+		return -EINVAL;
+
+	if (hdr->fc.security_enabled) {
+		u8 key_id_mode = IEEE802154_SCF_KEY_ID_MODE(*(buf + pos));
+		int want = pos + ieee802154_sechdr_lengths[key_id_mode];
+
+		if (buf + want > skb_tail_pointer(skb))
+			return -EINVAL;
+
+		pos += ieee802154_hdr_get_sechdr(buf + pos, &hdr->sec);
+	}
+
+	return pos;
+}
+EXPORT_SYMBOL_GPL(ieee802154_hdr_peek);
+
+int ieee802154_max_payload(const struct ieee802154_hdr *hdr)
+{
+	int hlen = ieee802154_hdr_minlen(hdr);
+
+	if (hdr->fc.security_enabled) {
+		hlen += ieee802154_sechdr_lengths[hdr->sec.key_id_mode] - 1;
+		hlen += ieee802154_sechdr_authtag_len(&hdr->sec);
+	}
+
+	return IEEE802154_MTU - hlen - IEEE802154_MFR_SIZE;
+}
+EXPORT_SYMBOL_GPL(ieee802154_max_payload);
diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h
index cee4425b995..8b83a231299 100644
--- a/net/ieee802154/ieee802154.h
+++ b/net/ieee802154/ieee802154.h
@@ -66,5 +66,25 @@ int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_list_iface(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb);
+int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info);
+
+int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_setparams(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_add_key(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_del_key(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_dump_keys(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int ieee802154_llsec_add_dev(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_del_dev(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_dump_devs(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int ieee802154_llsec_add_devkey(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_del_devkey(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_dump_devkeys(struct sk_buff *skb,
+				  struct netlink_callback *cb);
+int ieee802154_llsec_add_seclevel(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_del_seclevel(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_dump_seclevels(struct sk_buff *skb,
+				    struct netlink_callback *cb);
 
 #endif
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 43f1b2bf469..26efcf4fd2f 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -123,6 +123,27 @@ static const struct genl_ops ieee8021154_ops[] = {
 	IEEE802154_OP(IEEE802154_START_REQ, ieee802154_start_req),
 	IEEE802154_DUMP(IEEE802154_LIST_IFACE, ieee802154_list_iface,
 			ieee802154_dump_iface),
+	IEEE802154_OP(IEEE802154_SET_MACPARAMS, ieee802154_set_macparams),
+	IEEE802154_OP(IEEE802154_LLSEC_GETPARAMS, ieee802154_llsec_getparams),
+	IEEE802154_OP(IEEE802154_LLSEC_SETPARAMS, ieee802154_llsec_setparams),
+	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_KEY, NULL,
+			ieee802154_llsec_dump_keys),
+	IEEE802154_OP(IEEE802154_LLSEC_ADD_KEY, ieee802154_llsec_add_key),
+	IEEE802154_OP(IEEE802154_LLSEC_DEL_KEY, ieee802154_llsec_del_key),
+	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_DEV, NULL,
+			ieee802154_llsec_dump_devs),
+	IEEE802154_OP(IEEE802154_LLSEC_ADD_DEV, ieee802154_llsec_add_dev),
+	IEEE802154_OP(IEEE802154_LLSEC_DEL_DEV, ieee802154_llsec_del_dev),
+	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_DEVKEY, NULL,
+			ieee802154_llsec_dump_devkeys),
+	IEEE802154_OP(IEEE802154_LLSEC_ADD_DEVKEY, ieee802154_llsec_add_devkey),
+	IEEE802154_OP(IEEE802154_LLSEC_DEL_DEVKEY, ieee802154_llsec_del_devkey),
+	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_SECLEVEL, NULL,
+			ieee802154_llsec_dump_seclevels),
+	IEEE802154_OP(IEEE802154_LLSEC_ADD_SECLEVEL,
+		      ieee802154_llsec_add_seclevel),
+	IEEE802154_OP(IEEE802154_LLSEC_DEL_SECLEVEL,
+		      ieee802154_llsec_del_seclevel),
 };
 
 static const struct genl_multicast_group ieee802154_mcgrps[] = {
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index ba5c1e002f3..a3281b8bfd5 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -39,6 +39,26 @@
 
 #include "ieee802154.h"
 
+static int nla_put_hwaddr(struct sk_buff *msg, int type, __le64 hwaddr)
+{
+	return nla_put_u64(msg, type, swab64((__force u64)hwaddr));
+}
+
+static __le64 nla_get_hwaddr(const struct nlattr *nla)
+{
+	return ieee802154_devaddr_from_raw(nla_data(nla));
+}
+
+static int nla_put_shortaddr(struct sk_buff *msg, int type, __le16 addr)
+{
+	return nla_put_u16(msg, type, le16_to_cpu(addr));
+}
+
+static __le16 nla_get_shortaddr(const struct nlattr *nla)
+{
+	return cpu_to_le16(nla_get_u16(nla));
+}
+
 int ieee802154_nl_assoc_indic(struct net_device *dev,
 		struct ieee802154_addr *addr, u8 cap)
 {
@@ -46,7 +66,7 @@ int ieee802154_nl_assoc_indic(struct net_device *dev,
 
 	pr_debug("%s\n", __func__);
 
-	if (addr->addr_type != IEEE802154_ADDR_LONG) {
+	if (addr->mode != IEEE802154_ADDR_LONG) {
 		pr_err("%s: received non-long source address!\n", __func__);
 		return -EINVAL;
 	}
@@ -59,8 +79,8 @@ int ieee802154_nl_assoc_indic(struct net_device *dev,
 	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
 	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
 		    dev->dev_addr) ||
-	    nla_put(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN,
-		    addr->hwaddr) ||
+	    nla_put_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR,
+			   addr->extended_addr) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_CAPABILITY, cap))
 		goto nla_put_failure;
 
@@ -72,7 +92,7 @@ nla_put_failure:
 }
 EXPORT_SYMBOL(ieee802154_nl_assoc_indic);
 
-int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr,
+int ieee802154_nl_assoc_confirm(struct net_device *dev, __le16 short_addr,
 		u8 status)
 {
 	struct sk_buff *msg;
@@ -87,7 +107,7 @@ int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr,
 	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
 	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
 		    dev->dev_addr) ||
-	    nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) ||
+	    nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_STATUS, status))
 		goto nla_put_failure;
 	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
@@ -114,13 +134,13 @@ int ieee802154_nl_disassoc_indic(struct net_device *dev,
 	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
 		    dev->dev_addr))
 		goto nla_put_failure;
-	if (addr->addr_type == IEEE802154_ADDR_LONG) {
-		if (nla_put(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN,
-			    addr->hwaddr))
+	if (addr->mode == IEEE802154_ADDR_LONG) {
+		if (nla_put_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR,
+				   addr->extended_addr))
 			goto nla_put_failure;
 	} else {
-		if (nla_put_u16(msg, IEEE802154_ATTR_SRC_SHORT_ADDR,
-				addr->short_addr))
+		if (nla_put_shortaddr(msg, IEEE802154_ATTR_SRC_SHORT_ADDR,
+				      addr->short_addr))
 			goto nla_put_failure;
 	}
 	if (nla_put_u8(msg, IEEE802154_ATTR_REASON, reason))
@@ -157,8 +177,8 @@ nla_put_failure:
 }
 EXPORT_SYMBOL(ieee802154_nl_disassoc_confirm);
 
-int ieee802154_nl_beacon_indic(struct net_device *dev,
-		u16 panid, u16 coord_addr)
+int ieee802154_nl_beacon_indic(struct net_device *dev, __le16 panid,
+			       __le16 coord_addr)
 {
 	struct sk_buff *msg;
 
@@ -172,8 +192,9 @@ int ieee802154_nl_beacon_indic(struct net_device *dev,
 	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
 	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
 		    dev->dev_addr) ||
-	    nla_put_u16(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, coord_addr) ||
-	    nla_put_u16(msg, IEEE802154_ATTR_COORD_PAN_ID, panid))
+	    nla_put_shortaddr(msg, IEEE802154_ATTR_COORD_SHORT_ADDR,
+			      coord_addr) ||
+	    nla_put_shortaddr(msg, IEEE802154_ATTR_COORD_PAN_ID, panid))
 		goto nla_put_failure;
 	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
 
@@ -243,6 +264,8 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 {
 	void *hdr;
 	struct wpan_phy *phy;
+	struct ieee802154_mlme_ops *ops;
+	__le16 short_addr, pan_id;
 
 	pr_debug("%s\n", __func__);
 
@@ -251,19 +274,45 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 	if (!hdr)
 		goto out;
 
-	phy = ieee802154_mlme_ops(dev)->get_phy(dev);
+	ops = ieee802154_mlme_ops(dev);
+	phy = ops->get_phy(dev);
 	BUG_ON(!phy);
 
+	short_addr = ops->get_short_addr(dev);
+	pan_id = ops->get_pan_id(dev);
+
 	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
 	    nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) ||
 	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
 	    nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN,
 		    dev->dev_addr) ||
-	    nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR,
-			ieee802154_mlme_ops(dev)->get_short_addr(dev)) ||
-	    nla_put_u16(msg, IEEE802154_ATTR_PAN_ID,
-			ieee802154_mlme_ops(dev)->get_pan_id(dev)))
+	    nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) ||
+	    nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, pan_id))
 		goto nla_put_failure;
+
+	if (ops->get_mac_params) {
+		struct ieee802154_mac_params params;
+
+		ops->get_mac_params(dev, &params);
+
+		if (nla_put_s8(msg, IEEE802154_ATTR_TXPOWER,
+			       params.transmit_power) ||
+		    nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, params.lbt) ||
+		    nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE,
+			       params.cca_mode) ||
+		    nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL,
+				params.cca_ed_level) ||
+		    nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES,
+			       params.csma_retries) ||
+		    nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE,
+			       params.min_be) ||
+		    nla_put_u8(msg, IEEE802154_ATTR_CSMA_MAX_BE,
+			       params.max_be) ||
+		    nla_put_s8(msg, IEEE802154_ATTR_FRAME_RETRIES,
+			       params.frame_retries))
+			goto nla_put_failure;
+	}
+
 	wpan_phy_put(phy);
 	return genlmsg_end(msg, hdr);
 
@@ -322,16 +371,16 @@ int ieee802154_associate_req(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 
 	if (info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]) {
-		addr.addr_type = IEEE802154_ADDR_LONG;
-		nla_memcpy(addr.hwaddr,
-				info->attrs[IEEE802154_ATTR_COORD_HW_ADDR],
-				IEEE802154_ADDR_LEN);
+		addr.mode = IEEE802154_ADDR_LONG;
+		addr.extended_addr = nla_get_hwaddr(
+				info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]);
 	} else {
-		addr.addr_type = IEEE802154_ADDR_SHORT;
-		addr.short_addr = nla_get_u16(
+		addr.mode = IEEE802154_ADDR_SHORT;
+		addr.short_addr = nla_get_shortaddr(
 				info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]);
 	}
-	addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]);
+	addr.pan_id = nla_get_shortaddr(
+			info->attrs[IEEE802154_ATTR_COORD_PAN_ID]);
 
 	if (info->attrs[IEEE802154_ATTR_PAGE])
 		page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]);
@@ -365,14 +414,13 @@ int ieee802154_associate_resp(struct sk_buff *skb, struct genl_info *info)
 	if (!ieee802154_mlme_ops(dev)->assoc_resp)
 		goto out;
 
-	addr.addr_type = IEEE802154_ADDR_LONG;
-	nla_memcpy(addr.hwaddr, info->attrs[IEEE802154_ATTR_DEST_HW_ADDR],
-			IEEE802154_ADDR_LEN);
+	addr.mode = IEEE802154_ADDR_LONG;
+	addr.extended_addr = nla_get_hwaddr(
+			info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]);
 	addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
 
-
 	ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr,
-		nla_get_u16(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]),
+		nla_get_shortaddr(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]),
 		nla_get_u8(info->attrs[IEEE802154_ATTR_STATUS]));
 
 out:
@@ -398,13 +446,12 @@ int ieee802154_disassociate_req(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 
 	if (info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]) {
-		addr.addr_type = IEEE802154_ADDR_LONG;
-		nla_memcpy(addr.hwaddr,
-				info->attrs[IEEE802154_ATTR_DEST_HW_ADDR],
-				IEEE802154_ADDR_LEN);
+		addr.mode = IEEE802154_ADDR_LONG;
+		addr.extended_addr = nla_get_hwaddr(
+				info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]);
 	} else {
-		addr.addr_type = IEEE802154_ADDR_SHORT;
-		addr.short_addr = nla_get_u16(
+		addr.mode = IEEE802154_ADDR_SHORT;
+		addr.short_addr = nla_get_shortaddr(
 				info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]);
 	}
 	addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
@@ -449,10 +496,11 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info)
 	if (!ieee802154_mlme_ops(dev)->start_req)
 		goto out;
 
-	addr.addr_type = IEEE802154_ADDR_SHORT;
-	addr.short_addr = nla_get_u16(
+	addr.mode = IEEE802154_ADDR_SHORT;
+	addr.short_addr = nla_get_shortaddr(
 			info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]);
-	addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]);
+	addr.pan_id = nla_get_shortaddr(
+			info->attrs[IEEE802154_ATTR_COORD_PAN_ID]);
 
 	channel = nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]);
 	bcn_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_BCN_ORD]);
@@ -467,7 +515,7 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info)
 		page = 0;
 
 
-	if (addr.short_addr == IEEE802154_ADDR_BROADCAST) {
+	if (addr.short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) {
 		ieee802154_nl_start_confirm(dev, IEEE802154_NO_SHORT_ADDRESS);
 		dev_put(dev);
 		return -EINVAL;
@@ -577,3 +625,902 @@ cont:
 
 	return skb->len;
 }
+
+int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_device *dev = NULL;
+	struct ieee802154_mlme_ops *ops;
+	struct ieee802154_mac_params params;
+	struct wpan_phy *phy;
+	int rc = -EINVAL;
+
+	pr_debug("%s\n", __func__);
+
+	dev = ieee802154_nl_get_dev(info);
+	if (!dev)
+		return -ENODEV;
+
+	ops = ieee802154_mlme_ops(dev);
+
+	if (!ops->get_mac_params || !ops->set_mac_params) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (netif_running(dev)) {
+		rc = -EBUSY;
+		goto out;
+	}
+
+	if (!info->attrs[IEEE802154_ATTR_LBT_ENABLED] &&
+	    !info->attrs[IEEE802154_ATTR_CCA_MODE] &&
+	    !info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL] &&
+	    !info->attrs[IEEE802154_ATTR_CSMA_RETRIES] &&
+	    !info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] &&
+	    !info->attrs[IEEE802154_ATTR_CSMA_MAX_BE] &&
+	    !info->attrs[IEEE802154_ATTR_FRAME_RETRIES])
+		goto out;
+
+	phy = ops->get_phy(dev);
+
+	if ((!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]) ||
+	    (!phy->set_cca_mode && info->attrs[IEEE802154_ATTR_CCA_MODE]) ||
+	    (!phy->set_cca_ed_level &&
+	     info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) ||
+	    (!phy->set_csma_params &&
+	     (info->attrs[IEEE802154_ATTR_CSMA_RETRIES] ||
+	      info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] ||
+	      info->attrs[IEEE802154_ATTR_CSMA_MAX_BE])) ||
+	    (!phy->set_frame_retries &&
+	     info->attrs[IEEE802154_ATTR_FRAME_RETRIES])) {
+		rc = -EOPNOTSUPP;
+		goto out_phy;
+	}
+
+	ops->get_mac_params(dev, &params);
+
+	if (info->attrs[IEEE802154_ATTR_TXPOWER])
+		params.transmit_power = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]);
+
+	if (info->attrs[IEEE802154_ATTR_LBT_ENABLED])
+		params.lbt = nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]);
+
+	if (info->attrs[IEEE802154_ATTR_CCA_MODE])
+		params.cca_mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]);
+
+	if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL])
+		params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]);
+
+	if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES])
+		params.csma_retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]);
+
+	if (info->attrs[IEEE802154_ATTR_CSMA_MIN_BE])
+		params.min_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]);
+
+	if (info->attrs[IEEE802154_ATTR_CSMA_MAX_BE])
+		params.max_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]);
+
+	if (info->attrs[IEEE802154_ATTR_FRAME_RETRIES])
+		params.frame_retries = nla_get_s8(info->attrs[IEEE802154_ATTR_FRAME_RETRIES]);
+
+	rc = ops->set_mac_params(dev, &params);
+
+	wpan_phy_put(phy);
+	dev_put(dev);
+	return rc;
+
+out_phy:
+	wpan_phy_put(phy);
+out:
+	dev_put(dev);
+	return rc;
+}
+
+
+
+static int
+ieee802154_llsec_parse_key_id(struct genl_info *info,
+			      struct ieee802154_llsec_key_id *desc)
+{
+	memset(desc, 0, sizeof(*desc));
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE])
+		return -EINVAL;
+
+	desc->mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]);
+
+	if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) {
+		if (!info->attrs[IEEE802154_ATTR_PAN_ID] &&
+		    !(info->attrs[IEEE802154_ATTR_SHORT_ADDR] ||
+		      info->attrs[IEEE802154_ATTR_HW_ADDR]))
+			return -EINVAL;
+
+		desc->device_addr.pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]);
+
+		if (info->attrs[IEEE802154_ATTR_SHORT_ADDR]) {
+			desc->device_addr.mode = IEEE802154_ADDR_SHORT;
+			desc->device_addr.short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]);
+		} else {
+			desc->device_addr.mode = IEEE802154_ADDR_LONG;
+			desc->device_addr.extended_addr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
+		}
+	}
+
+	if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_ID])
+		return -EINVAL;
+
+	if (desc->mode == IEEE802154_SCF_KEY_SHORT_INDEX &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT])
+		return -EINVAL;
+
+	if (desc->mode == IEEE802154_SCF_KEY_HW_INDEX &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED])
+		return -EINVAL;
+
+	if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT)
+		desc->id = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_ID]);
+
+	switch (desc->mode) {
+	case IEEE802154_SCF_KEY_SHORT_INDEX:
+	{
+		u32 source = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT]);
+		desc->short_source = cpu_to_le32(source);
+		break;
+	}
+	case IEEE802154_SCF_KEY_HW_INDEX:
+		desc->extended_source = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED]);
+		break;
+	}
+
+	return 0;
+}
+
+static int
+ieee802154_llsec_fill_key_id(struct sk_buff *msg,
+			     const struct ieee802154_llsec_key_id *desc)
+{
+	if (nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_MODE, desc->mode))
+		return -EMSGSIZE;
+
+	if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) {
+		if (nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID,
+				      desc->device_addr.pan_id))
+			return -EMSGSIZE;
+
+		if (desc->device_addr.mode == IEEE802154_ADDR_SHORT &&
+		    nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR,
+				      desc->device_addr.short_addr))
+			return -EMSGSIZE;
+
+		if (desc->device_addr.mode == IEEE802154_ADDR_LONG &&
+		    nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR,
+				   desc->device_addr.extended_addr))
+			return -EMSGSIZE;
+	}
+
+	if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT &&
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_ID, desc->id))
+		return -EMSGSIZE;
+
+	if (desc->mode == IEEE802154_SCF_KEY_SHORT_INDEX &&
+	    nla_put_u32(msg, IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT,
+			le32_to_cpu(desc->short_source)))
+		return -EMSGSIZE;
+
+	if (desc->mode == IEEE802154_SCF_KEY_HW_INDEX &&
+	    nla_put_hwaddr(msg, IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED,
+			   desc->extended_source))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *msg;
+	struct net_device *dev = NULL;
+	int rc = -ENOBUFS;
+	struct ieee802154_mlme_ops *ops;
+	void *hdr;
+	struct ieee802154_llsec_params params;
+
+	pr_debug("%s\n", __func__);
+
+	dev = ieee802154_nl_get_dev(info);
+	if (!dev)
+		return -ENODEV;
+
+	ops = ieee802154_mlme_ops(dev);
+	if (!ops->llsec) {
+		rc = -EOPNOTSUPP;
+		goto out_dev;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		goto out_dev;
+
+	hdr = genlmsg_put(msg, 0, info->snd_seq, &nl802154_family, 0,
+		IEEE802154_LLSEC_GETPARAMS);
+	if (!hdr)
+		goto out_free;
+
+	rc = ops->llsec->get_params(dev, &params);
+	if (rc < 0)
+		goto out_free;
+
+	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_ENABLED, params.enabled) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVEL, params.out_level) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER,
+			be32_to_cpu(params.frame_counter)) ||
+	    ieee802154_llsec_fill_key_id(msg, &params.out_key))
+		goto out_free;
+
+	dev_put(dev);
+
+	return ieee802154_nl_reply(msg, info);
+out_free:
+	nlmsg_free(msg);
+out_dev:
+	dev_put(dev);
+	return rc;
+}
+
+int ieee802154_llsec_setparams(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_device *dev = NULL;
+	int rc = -EINVAL;
+	struct ieee802154_mlme_ops *ops;
+	struct ieee802154_llsec_params params;
+	int changed = 0;
+
+	pr_debug("%s\n", __func__);
+
+	dev = ieee802154_nl_get_dev(info);
+	if (!dev)
+		return -ENODEV;
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_ENABLED] &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE] &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL])
+		goto out;
+
+	ops = ieee802154_mlme_ops(dev);
+	if (!ops->llsec) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL] &&
+	    nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]) > 7)
+		goto out;
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_ENABLED]) {
+		params.enabled = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_ENABLED]);
+		changed |= IEEE802154_LLSEC_PARAM_ENABLED;
+	}
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]) {
+		if (ieee802154_llsec_parse_key_id(info, &params.out_key))
+			goto out;
+
+		changed |= IEEE802154_LLSEC_PARAM_OUT_KEY;
+	}
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]) {
+		params.out_level = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]);
+		changed |= IEEE802154_LLSEC_PARAM_OUT_LEVEL;
+	}
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]) {
+		u32 fc = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]);
+
+		params.frame_counter = cpu_to_be32(fc);
+		changed |= IEEE802154_LLSEC_PARAM_FRAME_COUNTER;
+	}
+
+	rc = ops->llsec->set_params(dev, &params, changed);
+
+	dev_put(dev);
+
+	return rc;
+out:
+	dev_put(dev);
+	return rc;
+}
+
+
+
+struct llsec_dump_data {
+	struct sk_buff *skb;
+	int s_idx, s_idx2;
+	int portid;
+	int nlmsg_seq;
+	struct net_device *dev;
+	struct ieee802154_mlme_ops *ops;
+	struct ieee802154_llsec_table *table;
+};
+
+static int
+ieee802154_llsec_dump_table(struct sk_buff *skb, struct netlink_callback *cb,
+			    int (*step)(struct llsec_dump_data*))
+{
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+	struct llsec_dump_data data;
+	int idx = 0;
+	int first_dev = cb->args[0];
+	int rc;
+
+	for_each_netdev(net, dev) {
+		if (idx < first_dev || dev->type != ARPHRD_IEEE802154)
+			goto skip;
+
+		data.ops = ieee802154_mlme_ops(dev);
+		if (!data.ops->llsec)
+			goto skip;
+
+		data.skb = skb;
+		data.s_idx = cb->args[1];
+		data.s_idx2 = cb->args[2];
+		data.dev = dev;
+		data.portid = NETLINK_CB(cb->skb).portid;
+		data.nlmsg_seq = cb->nlh->nlmsg_seq;
+
+		data.ops->llsec->lock_table(dev);
+		data.ops->llsec->get_table(data.dev, &data.table);
+		rc = step(&data);
+		data.ops->llsec->unlock_table(dev);
+
+		if (rc < 0)
+			break;
+
+skip:
+		idx++;
+	}
+	cb->args[0] = idx;
+
+	return skb->len;
+}
+
+static int
+ieee802154_nl_llsec_change(struct sk_buff *skb, struct genl_info *info,
+			   int (*fn)(struct net_device*, struct genl_info*))
+{
+	struct net_device *dev = NULL;
+	int rc = -EINVAL;
+
+	dev = ieee802154_nl_get_dev(info);
+	if (!dev)
+		return -ENODEV;
+
+	if (!ieee802154_mlme_ops(dev)->llsec)
+		rc = -EOPNOTSUPP;
+	else
+		rc = fn(dev, info);
+
+	dev_put(dev);
+	return rc;
+}
+
+
+
+static int
+ieee802154_llsec_parse_key(struct genl_info *info,
+			   struct ieee802154_llsec_key *key)
+{
+	u8 frames;
+	u32 commands[256 / 32];
+
+	memset(key, 0, sizeof(*key));
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES] ||
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_BYTES])
+		return -EINVAL;
+
+	frames = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES]);
+	if ((frames & BIT(IEEE802154_FC_TYPE_MAC_CMD)) &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS])
+		return -EINVAL;
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS]) {
+		nla_memcpy(commands,
+			   info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS],
+			   256 / 8);
+
+		if (commands[0] || commands[1] || commands[2] || commands[3] ||
+		    commands[4] || commands[5] || commands[6] ||
+		    commands[7] >= BIT(IEEE802154_CMD_GTS_REQ + 1))
+			return -EINVAL;
+
+		key->cmd_frame_ids = commands[7];
+	}
+
+	key->frame_types = frames;
+
+	nla_memcpy(key->key, info->attrs[IEEE802154_ATTR_LLSEC_KEY_BYTES],
+		   IEEE802154_LLSEC_KEY_SIZE);
+
+	return 0;
+}
+
+static int llsec_add_key(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_key key;
+	struct ieee802154_llsec_key_id id;
+
+	if (ieee802154_llsec_parse_key(info, &key) ||
+	    ieee802154_llsec_parse_key_id(info, &id))
+		return -EINVAL;
+
+	return ops->llsec->add_key(dev, &id, &key);
+}
+
+int ieee802154_llsec_add_key(struct sk_buff *skb, struct genl_info *info)
+{
+	if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) !=
+	    (NLM_F_CREATE | NLM_F_EXCL))
+		return -EINVAL;
+
+	return ieee802154_nl_llsec_change(skb, info, llsec_add_key);
+}
+
+static int llsec_remove_key(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_key_id id;
+
+	if (ieee802154_llsec_parse_key_id(info, &id))
+		return -EINVAL;
+
+	return ops->llsec->del_key(dev, &id);
+}
+
+int ieee802154_llsec_del_key(struct sk_buff *skb, struct genl_info *info)
+{
+	return ieee802154_nl_llsec_change(skb, info, llsec_remove_key);
+}
+
+static int
+ieee802154_nl_fill_key(struct sk_buff *msg, u32 portid, u32 seq,
+		       const struct ieee802154_llsec_key_entry *key,
+		       const struct net_device *dev)
+{
+	void *hdr;
+	u32 commands[256 / 32];
+
+	hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI,
+			  IEEE802154_LLSEC_LIST_KEY);
+	if (!hdr)
+		goto out;
+
+	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
+	    ieee802154_llsec_fill_key_id(msg, &key->id) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES,
+		       key->key->frame_types))
+		goto nla_put_failure;
+
+	if (key->key->frame_types & BIT(IEEE802154_FC_TYPE_MAC_CMD)) {
+		memset(commands, 0, sizeof(commands));
+		commands[7] = key->key->cmd_frame_ids;
+		if (nla_put(msg, IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS,
+			    sizeof(commands), commands))
+			goto nla_put_failure;
+	}
+
+	if (nla_put(msg, IEEE802154_ATTR_LLSEC_KEY_BYTES,
+		    IEEE802154_LLSEC_KEY_SIZE, key->key->key))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+out:
+	return -EMSGSIZE;
+}
+
+static int llsec_iter_keys(struct llsec_dump_data *data)
+{
+	struct ieee802154_llsec_key_entry *pos;
+	int rc = 0, idx = 0;
+
+	list_for_each_entry(pos, &data->table->keys, list) {
+		if (idx++ < data->s_idx)
+			continue;
+
+		if (ieee802154_nl_fill_key(data->skb, data->portid,
+					   data->nlmsg_seq, pos, data->dev)) {
+			rc = -EMSGSIZE;
+			break;
+		}
+
+		data->s_idx++;
+	}
+
+	return rc;
+}
+
+int ieee802154_llsec_dump_keys(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return ieee802154_llsec_dump_table(skb, cb, llsec_iter_keys);
+}
+
+
+
+static int
+llsec_parse_dev(struct genl_info *info,
+		struct ieee802154_llsec_device *dev)
+{
+	memset(dev, 0, sizeof(*dev));
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER] ||
+	    !info->attrs[IEEE802154_ATTR_HW_ADDR] ||
+	    !info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE] ||
+	    !info->attrs[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE] ||
+	    (!!info->attrs[IEEE802154_ATTR_PAN_ID] !=
+	     !!info->attrs[IEEE802154_ATTR_SHORT_ADDR]))
+		return -EINVAL;
+
+	if (info->attrs[IEEE802154_ATTR_PAN_ID]) {
+		dev->pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]);
+		dev->short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]);
+	} else {
+		dev->short_addr = cpu_to_le16(IEEE802154_ADDR_UNDEF);
+	}
+
+	dev->hwaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
+	dev->frame_counter = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]);
+	dev->seclevel_exempt = !!nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE]);
+	dev->key_mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE]);
+
+	if (dev->key_mode >= __IEEE802154_LLSEC_DEVKEY_MAX)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int llsec_add_dev(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_device desc;
+
+	if (llsec_parse_dev(info, &desc))
+		return -EINVAL;
+
+	return ops->llsec->add_dev(dev, &desc);
+}
+
+int ieee802154_llsec_add_dev(struct sk_buff *skb, struct genl_info *info)
+{
+	if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) !=
+	    (NLM_F_CREATE | NLM_F_EXCL))
+		return -EINVAL;
+
+	return ieee802154_nl_llsec_change(skb, info, llsec_add_dev);
+}
+
+static int llsec_del_dev(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	__le64 devaddr;
+
+	if (!info->attrs[IEEE802154_ATTR_HW_ADDR])
+		return -EINVAL;
+
+	devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
+
+	return ops->llsec->del_dev(dev, devaddr);
+}
+
+int ieee802154_llsec_del_dev(struct sk_buff *skb, struct genl_info *info)
+{
+	return ieee802154_nl_llsec_change(skb, info, llsec_del_dev);
+}
+
+static int
+ieee802154_nl_fill_dev(struct sk_buff *msg, u32 portid, u32 seq,
+		       const struct ieee802154_llsec_device *desc,
+		       const struct net_device *dev)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI,
+			  IEEE802154_LLSEC_LIST_DEV);
+	if (!hdr)
+		goto out;
+
+	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
+	    nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, desc->pan_id) ||
+	    nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR,
+			      desc->short_addr) ||
+	    nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR, desc->hwaddr) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER,
+			desc->frame_counter) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_OVERRIDE,
+		       desc->seclevel_exempt) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_KEY_MODE, desc->key_mode))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+out:
+	return -EMSGSIZE;
+}
+
+static int llsec_iter_devs(struct llsec_dump_data *data)
+{
+	struct ieee802154_llsec_device *pos;
+	int rc = 0, idx = 0;
+
+	list_for_each_entry(pos, &data->table->devices, list) {
+		if (idx++ < data->s_idx)
+			continue;
+
+		if (ieee802154_nl_fill_dev(data->skb, data->portid,
+					   data->nlmsg_seq, pos, data->dev)) {
+			rc = -EMSGSIZE;
+			break;
+		}
+
+		data->s_idx++;
+	}
+
+	return rc;
+}
+
+int ieee802154_llsec_dump_devs(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return ieee802154_llsec_dump_table(skb, cb, llsec_iter_devs);
+}
+
+
+
+static int llsec_add_devkey(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_device_key key;
+	__le64 devaddr;
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER] ||
+	    !info->attrs[IEEE802154_ATTR_HW_ADDR] ||
+	    ieee802154_llsec_parse_key_id(info, &key.key_id))
+		return -EINVAL;
+
+	devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
+	key.frame_counter = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]);
+
+	return ops->llsec->add_devkey(dev, devaddr, &key);
+}
+
+int ieee802154_llsec_add_devkey(struct sk_buff *skb, struct genl_info *info)
+{
+	if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) !=
+	    (NLM_F_CREATE | NLM_F_EXCL))
+		return -EINVAL;
+
+	return ieee802154_nl_llsec_change(skb, info, llsec_add_devkey);
+}
+
+static int llsec_del_devkey(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_device_key key;
+	__le64 devaddr;
+
+	if (!info->attrs[IEEE802154_ATTR_HW_ADDR] ||
+	    ieee802154_llsec_parse_key_id(info, &key.key_id))
+		return -EINVAL;
+
+	devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
+
+	return ops->llsec->del_devkey(dev, devaddr, &key);
+}
+
+int ieee802154_llsec_del_devkey(struct sk_buff *skb, struct genl_info *info)
+{
+	return ieee802154_nl_llsec_change(skb, info, llsec_del_devkey);
+}
+
+static int
+ieee802154_nl_fill_devkey(struct sk_buff *msg, u32 portid, u32 seq,
+			  __le64 devaddr,
+			  const struct ieee802154_llsec_device_key *devkey,
+			  const struct net_device *dev)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI,
+			  IEEE802154_LLSEC_LIST_DEVKEY);
+	if (!hdr)
+		goto out;
+
+	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
+	    nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR, devaddr) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER,
+			devkey->frame_counter) ||
+	    ieee802154_llsec_fill_key_id(msg, &devkey->key_id))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+out:
+	return -EMSGSIZE;
+}
+
+static int llsec_iter_devkeys(struct llsec_dump_data *data)
+{
+	struct ieee802154_llsec_device *dpos;
+	struct ieee802154_llsec_device_key *kpos;
+	int rc = 0, idx = 0, idx2;
+
+	list_for_each_entry(dpos, &data->table->devices, list) {
+		if (idx++ < data->s_idx)
+			continue;
+
+		idx2 = 0;
+
+		list_for_each_entry(kpos, &dpos->keys, list) {
+			if (idx2++ < data->s_idx2)
+				continue;
+
+			if (ieee802154_nl_fill_devkey(data->skb, data->portid,
+						      data->nlmsg_seq,
+						      dpos->hwaddr, kpos,
+						      data->dev)) {
+				return rc = -EMSGSIZE;
+			}
+
+			data->s_idx2++;
+		}
+
+		data->s_idx++;
+	}
+
+	return rc;
+}
+
+int ieee802154_llsec_dump_devkeys(struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	return ieee802154_llsec_dump_table(skb, cb, llsec_iter_devkeys);
+}
+
+
+
+static int
+llsec_parse_seclevel(struct genl_info *info,
+		     struct ieee802154_llsec_seclevel *sl)
+{
+	memset(sl, 0, sizeof(*sl));
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_TYPE] ||
+	    !info->attrs[IEEE802154_ATTR_LLSEC_SECLEVELS] ||
+	    !info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE])
+		return -EINVAL;
+
+	sl->frame_type = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_TYPE]);
+	if (sl->frame_type == IEEE802154_FC_TYPE_MAC_CMD) {
+		if (!info->attrs[IEEE802154_ATTR_LLSEC_CMD_FRAME_ID])
+			return -EINVAL;
+
+		sl->cmd_frame_id = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_CMD_FRAME_ID]);
+	}
+
+	sl->sec_levels = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVELS]);
+	sl->device_override = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE]);
+
+	return 0;
+}
+
+static int llsec_add_seclevel(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_seclevel sl;
+
+	if (llsec_parse_seclevel(info, &sl))
+		return -EINVAL;
+
+	return ops->llsec->add_seclevel(dev, &sl);
+}
+
+int ieee802154_llsec_add_seclevel(struct sk_buff *skb, struct genl_info *info)
+{
+	if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) !=
+	    (NLM_F_CREATE | NLM_F_EXCL))
+		return -EINVAL;
+
+	return ieee802154_nl_llsec_change(skb, info, llsec_add_seclevel);
+}
+
+static int llsec_del_seclevel(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_seclevel sl;
+
+	if (llsec_parse_seclevel(info, &sl))
+		return -EINVAL;
+
+	return ops->llsec->del_seclevel(dev, &sl);
+}
+
+int ieee802154_llsec_del_seclevel(struct sk_buff *skb, struct genl_info *info)
+{
+	return ieee802154_nl_llsec_change(skb, info, llsec_del_seclevel);
+}
+
+static int
+ieee802154_nl_fill_seclevel(struct sk_buff *msg, u32 portid, u32 seq,
+			    const struct ieee802154_llsec_seclevel *sl,
+			    const struct net_device *dev)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI,
+			  IEEE802154_LLSEC_LIST_SECLEVEL);
+	if (!hdr)
+		goto out;
+
+	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_FRAME_TYPE, sl->frame_type) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVELS, sl->sec_levels) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_OVERRIDE,
+		       sl->device_override))
+		goto nla_put_failure;
+
+	if (sl->frame_type == IEEE802154_FC_TYPE_MAC_CMD &&
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_CMD_FRAME_ID,
+		       sl->cmd_frame_id))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+out:
+	return -EMSGSIZE;
+}
+
+static int llsec_iter_seclevels(struct llsec_dump_data *data)
+{
+	struct ieee802154_llsec_seclevel *pos;
+	int rc = 0, idx = 0;
+
+	list_for_each_entry(pos, &data->table->security_levels, list) {
+		if (idx++ < data->s_idx)
+			continue;
+
+		if (ieee802154_nl_fill_seclevel(data->skb, data->portid,
+						data->nlmsg_seq, pos,
+						data->dev)) {
+			rc = -EMSGSIZE;
+			break;
+		}
+
+		data->s_idx++;
+	}
+
+	return rc;
+}
+
+int ieee802154_llsec_dump_seclevels(struct sk_buff *skb,
+				    struct netlink_callback *cb)
+{
+	return ieee802154_llsec_dump_table(skb, cb, llsec_iter_seclevels);
+}
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index d08c7a43dcd..89b265aea15 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -221,8 +221,10 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[IEEE802154_ATTR_DEV_TYPE]) {
 		type = nla_get_u8(info->attrs[IEEE802154_ATTR_DEV_TYPE]);
-		if (type >= __IEEE802154_DEV_MAX)
-			return -EINVAL;
+		if (type >= __IEEE802154_DEV_MAX) {
+			rc = -EINVAL;
+			goto nla_put_failure;
+		}
 	}
 
 	dev = phy->add_iface(phy, devname, type);
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 6adda4d46f9..3a703ab8834 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -52,5 +52,31 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_DURATION] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_ED_LIST] = { .len = 27 },
 	[IEEE802154_ATTR_CHANNEL_PAGE_LIST] = { .len = 32 * 4, },
+
+	[IEEE802154_ATTR_TXPOWER] = { .type = NLA_S8, },
+	[IEEE802154_ATTR_LBT_ENABLED] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_CCA_MODE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, },
+	[IEEE802154_ATTR_CSMA_RETRIES] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_CSMA_MIN_BE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_CSMA_MAX_BE] = { .type = NLA_U8, },
+
+	[IEEE802154_ATTR_FRAME_RETRIES] = { .type = NLA_S8, },
+
+	[IEEE802154_ATTR_LLSEC_ENABLED] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_SECLEVEL] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_KEY_MODE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT] = { .type = NLA_U32, },
+	[IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED] = { .type = NLA_HW_ADDR, },
+	[IEEE802154_ATTR_LLSEC_KEY_ID] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_FRAME_COUNTER] = { .type = NLA_U32 },
+	[IEEE802154_ATTR_LLSEC_KEY_BYTES] = { .len = 16, },
+	[IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS] = { .len = 258 / 8 },
+	[IEEE802154_ATTR_LLSEC_FRAME_TYPE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_CMD_FRAME_ID] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_SECLEVELS] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE] = { .type = NLA_U8, },
 };
 
diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c
index 41f538b8e59..74d54fae33d 100644
--- a/net/ieee802154/raw.c
+++ b/net/ieee802154/raw.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <net/sock.h>
 #include <net/af_ieee802154.h>
+#include <net/ieee802154_netdev.h>
 
 #include "af802154.h"
 
@@ -55,21 +56,24 @@ static void raw_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 }
 
-static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int len)
+static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len)
 {
-	struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr;
+	struct ieee802154_addr addr;
+	struct sockaddr_ieee802154 *uaddr = (struct sockaddr_ieee802154 *)_uaddr;
 	int err = 0;
 	struct net_device *dev = NULL;
 
-	if (len < sizeof(*addr))
+	if (len < sizeof(*uaddr))
 		return -EINVAL;
 
-	if (addr->family != AF_IEEE802154)
+	uaddr = (struct sockaddr_ieee802154 *)_uaddr;
+	if (uaddr->family != AF_IEEE802154)
 		return -EINVAL;
 
 	lock_sock(sk);
 
-	dev = ieee802154_get_dev(sock_net(sk), &addr->addr);
+	ieee802154_addr_from_sa(&addr, &uaddr->addr);
+	dev = ieee802154_get_dev(sock_net(sk), &addr);
 	if (!dev) {
 		err = -ENODEV;
 		goto out;
@@ -209,6 +213,10 @@ out:
 
 static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return NET_RX_DROP;
+
 	if (sock_queue_rcv_skb(sk, skb) < 0) {
 		kfree_skb(skb);
 		return NET_RX_DROP;
diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c
new file mode 100644
index 00000000000..6f1428c4870
--- /dev/null
+++ b/net/ieee802154/reassembly.c
@@ -0,0 +1,585 @@
+/*	6LoWPAN fragment reassembly
+ *
+ *
+ *	Authors:
+ *	Alexander Aring		<aar@pengutronix.de>
+ *
+ *	Based on: net/ipv6/reassembly.c
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "6LoWPAN: " fmt
+
+#include <linux/net.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/random.h>
+#include <linux/jhash.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+
+#include <net/ieee802154_netdev.h>
+#include <net/6lowpan.h>
+#include <net/ipv6.h>
+#include <net/inet_frag.h>
+
+#include "reassembly.h"
+
+struct lowpan_frag_info {
+	__be16 d_tag;
+	u16 d_size;
+	u8 d_offset;
+};
+
+static struct lowpan_frag_info *lowpan_cb(struct sk_buff *skb)
+{
+	return (struct lowpan_frag_info *)skb->cb;
+}
+
+static struct inet_frags lowpan_frags;
+
+static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
+			     struct sk_buff *prev, struct net_device *dev);
+
+static unsigned int lowpan_hash_frag(__be16 tag, u16 d_size,
+				     const struct ieee802154_addr *saddr,
+				     const struct ieee802154_addr *daddr)
+{
+	u32 c;
+
+	net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
+	c = jhash_3words(ieee802154_addr_hash(saddr),
+			 ieee802154_addr_hash(daddr),
+			 (__force u32)(tag + (d_size << 16)),
+			 lowpan_frags.rnd);
+
+	return c & (INETFRAGS_HASHSZ - 1);
+}
+
+static unsigned int lowpan_hashfn(struct inet_frag_queue *q)
+{
+	struct lowpan_frag_queue *fq;
+
+	fq = container_of(q, struct lowpan_frag_queue, q);
+	return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
+}
+
+static bool lowpan_frag_match(struct inet_frag_queue *q, void *a)
+{
+	struct lowpan_frag_queue *fq;
+	struct lowpan_create_arg *arg = a;
+
+	fq = container_of(q, struct lowpan_frag_queue, q);
+	return	fq->tag == arg->tag && fq->d_size == arg->d_size &&
+		ieee802154_addr_equal(&fq->saddr, arg->src) &&
+		ieee802154_addr_equal(&fq->daddr, arg->dst);
+}
+
+static void lowpan_frag_init(struct inet_frag_queue *q, void *a)
+{
+	struct lowpan_frag_queue *fq;
+	struct lowpan_create_arg *arg = a;
+
+	fq = container_of(q, struct lowpan_frag_queue, q);
+
+	fq->tag = arg->tag;
+	fq->d_size = arg->d_size;
+	fq->saddr = *arg->src;
+	fq->daddr = *arg->dst;
+}
+
+static void lowpan_frag_expire(unsigned long data)
+{
+	struct frag_queue *fq;
+	struct net *net;
+
+	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+	net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags);
+
+	spin_lock(&fq->q.lock);
+
+	if (fq->q.last_in & INET_FRAG_COMPLETE)
+		goto out;
+
+	inet_frag_kill(&fq->q, &lowpan_frags);
+out:
+	spin_unlock(&fq->q.lock);
+	inet_frag_put(&fq->q, &lowpan_frags);
+}
+
+static inline struct lowpan_frag_queue *
+fq_find(struct net *net, const struct lowpan_frag_info *frag_info,
+	const struct ieee802154_addr *src,
+	const struct ieee802154_addr *dst)
+{
+	struct inet_frag_queue *q;
+	struct lowpan_create_arg arg;
+	unsigned int hash;
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
+
+	arg.tag = frag_info->d_tag;
+	arg.d_size = frag_info->d_size;
+	arg.src = src;
+	arg.dst = dst;
+
+	read_lock(&lowpan_frags.lock);
+	hash = lowpan_hash_frag(frag_info->d_tag, frag_info->d_size, src, dst);
+
+	q = inet_frag_find(&ieee802154_lowpan->frags,
+			   &lowpan_frags, &arg, hash);
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
+		return NULL;
+	}
+	return container_of(q, struct lowpan_frag_queue, q);
+}
+
+static int lowpan_frag_queue(struct lowpan_frag_queue *fq,
+			     struct sk_buff *skb, const u8 frag_type)
+{
+	struct sk_buff *prev, *next;
+	struct net_device *dev;
+	int end, offset;
+
+	if (fq->q.last_in & INET_FRAG_COMPLETE)
+		goto err;
+
+	offset = lowpan_cb(skb)->d_offset << 3;
+	end = lowpan_cb(skb)->d_size;
+
+	/* Is this the final fragment? */
+	if (offset + skb->len == end) {
+		/* If we already have some bits beyond end
+		 * or have different end, the segment is corrupted.
+		 */
+		if (end < fq->q.len ||
+		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
+			goto err;
+		fq->q.last_in |= INET_FRAG_LAST_IN;
+		fq->q.len = end;
+	} else {
+		if (end > fq->q.len) {
+			/* Some bits beyond end -> corruption. */
+			if (fq->q.last_in & INET_FRAG_LAST_IN)
+				goto err;
+			fq->q.len = end;
+		}
+	}
+
+	/* Find out which fragments are in front and at the back of us
+	 * in the chain of fragments so far.  We must know where to put
+	 * this fragment, right?
+	 */
+	prev = fq->q.fragments_tail;
+	if (!prev || lowpan_cb(prev)->d_offset < lowpan_cb(skb)->d_offset) {
+		next = NULL;
+		goto found;
+	}
+	prev = NULL;
+	for (next = fq->q.fragments; next != NULL; next = next->next) {
+		if (lowpan_cb(next)->d_offset >= lowpan_cb(skb)->d_offset)
+			break;	/* bingo! */
+		prev = next;
+	}
+
+found:
+	/* Insert this fragment in the chain of fragments. */
+	skb->next = next;
+	if (!next)
+		fq->q.fragments_tail = skb;
+	if (prev)
+		prev->next = skb;
+	else
+		fq->q.fragments = skb;
+
+	dev = skb->dev;
+	if (dev)
+		skb->dev = NULL;
+
+	fq->q.stamp = skb->tstamp;
+	if (frag_type == LOWPAN_DISPATCH_FRAG1) {
+		/* Calculate uncomp. 6lowpan header to estimate full size */
+		fq->q.meat += lowpan_uncompress_size(skb, NULL);
+		fq->q.last_in |= INET_FRAG_FIRST_IN;
+	} else {
+		fq->q.meat += skb->len;
+	}
+	add_frag_mem_limit(&fq->q, skb->truesize);
+
+	if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+	    fq->q.meat == fq->q.len) {
+		int res;
+		unsigned long orefdst = skb->_skb_refdst;
+
+		skb->_skb_refdst = 0UL;
+		res = lowpan_frag_reasm(fq, prev, dev);
+		skb->_skb_refdst = orefdst;
+		return res;
+	}
+
+	inet_frag_lru_move(&fq->q);
+	return -1;
+err:
+	kfree_skb(skb);
+	return -1;
+}
+
+/*	Check if this packet is complete.
+ *	Returns NULL on failure by any reason, and pointer
+ *	to current nexthdr field in reassembled frame.
+ *
+ *	It is called with locked fq, and caller must check that
+ *	queue is eligible for reassembly i.e. it is not COMPLETE,
+ *	the last and the first frames arrived and all the bits are here.
+ */
+static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev,
+			     struct net_device *dev)
+{
+	struct sk_buff *fp, *head = fq->q.fragments;
+	int sum_truesize;
+
+	inet_frag_kill(&fq->q, &lowpan_frags);
+
+	/* Make the one we just received the head. */
+	if (prev) {
+		head = prev->next;
+		fp = skb_clone(head, GFP_ATOMIC);
+
+		if (!fp)
+			goto out_oom;
+
+		fp->next = head->next;
+		if (!fp->next)
+			fq->q.fragments_tail = fp;
+		prev->next = fp;
+
+		skb_morph(head, fq->q.fragments);
+		head->next = fq->q.fragments->next;
+
+		consume_skb(fq->q.fragments);
+		fq->q.fragments = head;
+	}
+
+	/* Head of list must not be cloned. */
+	if (skb_unclone(head, GFP_ATOMIC))
+		goto out_oom;
+
+	/* If the first fragment is fragmented itself, we split
+	 * it to two chunks: the first with data and paged part
+	 * and the second, holding only fragments.
+	 */
+	if (skb_has_frag_list(head)) {
+		struct sk_buff *clone;
+		int i, plen = 0;
+
+		clone = alloc_skb(0, GFP_ATOMIC);
+		if (!clone)
+			goto out_oom;
+		clone->next = head->next;
+		head->next = clone;
+		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
+		skb_frag_list_init(head);
+		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
+			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
+		clone->len = head->data_len - plen;
+		clone->data_len = clone->len;
+		head->data_len -= clone->len;
+		head->len -= clone->len;
+		add_frag_mem_limit(&fq->q, clone->truesize);
+	}
+
+	WARN_ON(head == NULL);
+
+	sum_truesize = head->truesize;
+	for (fp = head->next; fp;) {
+		bool headstolen;
+		int delta;
+		struct sk_buff *next = fp->next;
+
+		sum_truesize += fp->truesize;
+		if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
+			kfree_skb_partial(fp, headstolen);
+		} else {
+			if (!skb_shinfo(head)->frag_list)
+				skb_shinfo(head)->frag_list = fp;
+			head->data_len += fp->len;
+			head->len += fp->len;
+			head->truesize += fp->truesize;
+		}
+		fp = next;
+	}
+	sub_frag_mem_limit(&fq->q, sum_truesize);
+
+	head->next = NULL;
+	head->dev = dev;
+	head->tstamp = fq->q.stamp;
+
+	fq->q.fragments = NULL;
+	fq->q.fragments_tail = NULL;
+
+	return 1;
+out_oom:
+	net_dbg_ratelimited("lowpan_frag_reasm: no memory for reassembly\n");
+	return -1;
+}
+
+static int lowpan_get_frag_info(struct sk_buff *skb, const u8 frag_type,
+				struct lowpan_frag_info *frag_info)
+{
+	bool fail;
+	u8 pattern = 0, low = 0;
+
+	fail = lowpan_fetch_skb(skb, &pattern, 1);
+	fail |= lowpan_fetch_skb(skb, &low, 1);
+	frag_info->d_size = (pattern & 7) << 8 | low;
+	fail |= lowpan_fetch_skb(skb, &frag_info->d_tag, 2);
+
+	if (frag_type == LOWPAN_DISPATCH_FRAGN) {
+		fail |= lowpan_fetch_skb(skb, &frag_info->d_offset, 1);
+	} else {
+		skb_reset_network_header(skb);
+		frag_info->d_offset = 0;
+	}
+
+	if (unlikely(fail))
+		return -EIO;
+
+	return 0;
+}
+
+int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type)
+{
+	struct lowpan_frag_queue *fq;
+	struct net *net = dev_net(skb->dev);
+	struct lowpan_frag_info *frag_info = lowpan_cb(skb);
+	struct ieee802154_addr source, dest;
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
+	int err;
+
+	source = mac_cb(skb)->source;
+	dest = mac_cb(skb)->dest;
+
+	err = lowpan_get_frag_info(skb, frag_type, frag_info);
+	if (err < 0)
+		goto err;
+
+	if (frag_info->d_size > ieee802154_lowpan->max_dsize)
+		goto err;
+
+	inet_frag_evictor(&ieee802154_lowpan->frags, &lowpan_frags, false);
+
+	fq = fq_find(net, frag_info, &source, &dest);
+	if (fq != NULL) {
+		int ret;
+		spin_lock(&fq->q.lock);
+		ret = lowpan_frag_queue(fq, skb, frag_type);
+		spin_unlock(&fq->q.lock);
+
+		inet_frag_put(&fq->q, &lowpan_frags);
+		return ret;
+	}
+
+err:
+	kfree_skb(skb);
+	return -1;
+}
+EXPORT_SYMBOL(lowpan_frag_rcv);
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table lowpan_frags_ns_ctl_table[] = {
+	{
+		.procname	= "6lowpanfrag_high_thresh",
+		.data		= &init_net.ieee802154_lowpan.frags.high_thresh,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "6lowpanfrag_low_thresh",
+		.data		= &init_net.ieee802154_lowpan.frags.low_thresh,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "6lowpanfrag_time",
+		.data		= &init_net.ieee802154_lowpan.frags.timeout,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
+		.procname	= "6lowpanfrag_max_datagram_size",
+		.data		= &init_net.ieee802154_lowpan.max_dsize,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{ }
+};
+
+static struct ctl_table lowpan_frags_ctl_table[] = {
+	{
+		.procname	= "6lowpanfrag_secret_interval",
+		.data		= &lowpan_frags.secret_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{ }
+};
+
+static int __net_init lowpan_frags_ns_sysctl_register(struct net *net)
+{
+	struct ctl_table *table;
+	struct ctl_table_header *hdr;
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
+
+	table = lowpan_frags_ns_ctl_table;
+	if (!net_eq(net, &init_net)) {
+		table = kmemdup(table, sizeof(lowpan_frags_ns_ctl_table),
+				GFP_KERNEL);
+		if (table == NULL)
+			goto err_alloc;
+
+		table[0].data = &ieee802154_lowpan->frags.high_thresh;
+		table[1].data = &ieee802154_lowpan->frags.low_thresh;
+		table[2].data = &ieee802154_lowpan->frags.timeout;
+		table[3].data = &ieee802154_lowpan->max_dsize;
+
+		/* Don't export sysctls to unprivileged users */
+		if (net->user_ns != &init_user_ns)
+			table[0].procname = NULL;
+	}
+
+	hdr = register_net_sysctl(net, "net/ieee802154/6lowpan", table);
+	if (hdr == NULL)
+		goto err_reg;
+
+	ieee802154_lowpan->sysctl.frags_hdr = hdr;
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(table);
+err_alloc:
+	return -ENOMEM;
+}
+
+static void __net_exit lowpan_frags_ns_sysctl_unregister(struct net *net)
+{
+	struct ctl_table *table;
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
+
+	table = ieee802154_lowpan->sysctl.frags_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(ieee802154_lowpan->sysctl.frags_hdr);
+	if (!net_eq(net, &init_net))
+		kfree(table);
+}
+
+static struct ctl_table_header *lowpan_ctl_header;
+
+static int lowpan_frags_sysctl_register(void)
+{
+	lowpan_ctl_header = register_net_sysctl(&init_net,
+						"net/ieee802154/6lowpan",
+						lowpan_frags_ctl_table);
+	return lowpan_ctl_header == NULL ? -ENOMEM : 0;
+}
+
+static void lowpan_frags_sysctl_unregister(void)
+{
+	unregister_net_sysctl_table(lowpan_ctl_header);
+}
+#else
+static inline int lowpan_frags_ns_sysctl_register(struct net *net)
+{
+	return 0;
+}
+
+static inline void lowpan_frags_ns_sysctl_unregister(struct net *net)
+{
+}
+
+static inline int lowpan_frags_sysctl_register(void)
+{
+	return 0;
+}
+
+static inline void lowpan_frags_sysctl_unregister(void)
+{
+}
+#endif
+
+static int __net_init lowpan_frags_init_net(struct net *net)
+{
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
+
+	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
+	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
+	ieee802154_lowpan->max_dsize = 0xFFFF;
+
+	inet_frags_init_net(&ieee802154_lowpan->frags);
+
+	return lowpan_frags_ns_sysctl_register(net);
+}
+
+static void __net_exit lowpan_frags_exit_net(struct net *net)
+{
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
+
+	lowpan_frags_ns_sysctl_unregister(net);
+	inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
+}
+
+static struct pernet_operations lowpan_frags_ops = {
+	.init = lowpan_frags_init_net,
+	.exit = lowpan_frags_exit_net,
+};
+
+int __init lowpan_net_frag_init(void)
+{
+	int ret;
+
+	ret = lowpan_frags_sysctl_register();
+	if (ret)
+		return ret;
+
+	ret = register_pernet_subsys(&lowpan_frags_ops);
+	if (ret)
+		goto err_pernet;
+
+	lowpan_frags.hashfn = lowpan_hashfn;
+	lowpan_frags.constructor = lowpan_frag_init;
+	lowpan_frags.destructor = NULL;
+	lowpan_frags.skb_free = NULL;
+	lowpan_frags.qsize = sizeof(struct frag_queue);
+	lowpan_frags.match = lowpan_frag_match;
+	lowpan_frags.frag_expire = lowpan_frag_expire;
+	lowpan_frags.secret_interval = 10 * 60 * HZ;
+	inet_frags_init(&lowpan_frags);
+
+	return ret;
+err_pernet:
+	lowpan_frags_sysctl_unregister();
+	return ret;
+}
+
+void lowpan_net_frag_exit(void)
+{
+	inet_frags_fini(&lowpan_frags);
+	lowpan_frags_sysctl_unregister();
+	unregister_pernet_subsys(&lowpan_frags_ops);
+}
diff --git a/net/ieee802154/reassembly.h b/net/ieee802154/reassembly.h
new file mode 100644
index 00000000000..74e4a7c9819
--- /dev/null
+++ b/net/ieee802154/reassembly.h
@@ -0,0 +1,41 @@
+#ifndef __IEEE802154_6LOWPAN_REASSEMBLY_H__
+#define __IEEE802154_6LOWPAN_REASSEMBLY_H__
+
+#include <net/inet_frag.h>
+
+struct lowpan_create_arg {
+	__be16 tag;
+	u16 d_size;
+	const struct ieee802154_addr *src;
+	const struct ieee802154_addr *dst;
+};
+
+/* Equivalent of ipv4 struct ip
+ */
+struct lowpan_frag_queue {
+	struct inet_frag_queue	q;
+
+	__be16			tag;
+	u16			d_size;
+	struct ieee802154_addr	saddr;
+	struct ieee802154_addr	daddr;
+};
+
+static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a)
+{
+	switch (a->mode) {
+	case IEEE802154_ADDR_LONG:
+		return (((__force u64)a->extended_addr) >> 32) ^
+			(((__force u64)a->extended_addr) & 0xffffffff);
+	case IEEE802154_ADDR_SHORT:
+		return (__force u32)(a->short_addr);
+	default:
+		return 0;
+	}
+}
+
+int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type);
+void lowpan_net_frag_exit(void);
+int lowpan_net_frag_init(void);
+
+#endif /* __IEEE802154_6LOWPAN_REASSEMBLY_H__ */
diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c
index ef56ab5b35f..8d6f6704da8 100644
--- a/net/ieee802154/wpan-class.c
+++ b/net/ieee802154/wpan-class.c
@@ -44,9 +44,7 @@ static DEVICE_ATTR_RO(name);
 
 MASTER_SHOW(current_channel, "%d");
 MASTER_SHOW(current_page, "%d");
-MASTER_SHOW_COMPLEX(transmit_power, "%d +- %d dB",
-	((signed char) (phy->transmit_power << 2)) >> 2,
-	(phy->transmit_power >> 6) ? (phy->transmit_power >> 6) * 3 : 1 );
+MASTER_SHOW(transmit_power, "%d +- 1 dB");
 MASTER_SHOW(cca_mode, "%d");
 
 static ssize_t channels_supported_show(struct device *dev,
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 4b81e91c80f..f032688d20d 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -11,7 +11,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     tcp_offload.o datagram.o raw.o udp.o udplite.o \
 	     udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
 	     fib_frontend.o fib_semantics.o fib_trie.o \
-	     inet_fragment.o ping.o ip_tunnel_core.o
+	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o
 
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
 obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
@@ -19,7 +19,7 @@ obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
 obj-$(CONFIG_IP_MROUTE) += ipmr.o
 obj-$(CONFIG_NET_IPIP) += ipip.o
-gre-y := gre_demux.o gre_offload.o
+gre-y := gre_demux.o
 obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o
 obj-$(CONFIG_NET_IPGRE) += ip_gre.o
 obj-$(CONFIG_NET_IPVTI) += ip_vti.o
@@ -55,4 +55,4 @@ obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
-		      xfrm4_output.o
+		      xfrm4_output.o xfrm4_protocol.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 70011e029ac..d156b3c5f36 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -126,9 +126,6 @@
 static struct list_head inetsw[SOCK_MAX];
 static DEFINE_SPINLOCK(inetsw_lock);
 
-struct ipv4_config ipv4_config;
-EXPORT_SYMBOL(ipv4_config);
-
 /* New destruction routine */
 
 void inet_sock_destruct(struct sock *sk)
@@ -257,7 +254,6 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	struct inet_sock *inet;
 	struct proto *answer_prot;
 	unsigned char answer_flags;
-	char answer_no_check;
 	int try_loading_module = 0;
 	int err;
 
@@ -315,7 +311,6 @@ lookup_protocol:
 
 	sock->ops = answer->ops;
 	answer_prot = answer->prot;
-	answer_no_check = answer->no_check;
 	answer_flags = answer->flags;
 	rcu_read_unlock();
 
@@ -327,7 +322,6 @@ lookup_protocol:
 		goto out;
 
 	err = 0;
-	sk->sk_no_check = answer_no_check;
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = SK_CAN_REUSE;
 
@@ -342,7 +336,7 @@ lookup_protocol:
 			inet->hdrincl = 1;
 	}
 
-	if (ipv4_config.no_pmtu_disc)
+	if (net->ipv4.sysctl_ip_no_pmtu_disc)
 		inet->pmtudisc = IP_PMTUDISC_DONT;
 	else
 		inet->pmtudisc = IP_PMTUDISC_WANT;
@@ -1005,7 +999,6 @@ static struct inet_protosw inetsw_array[] =
 		.protocol =   IPPROTO_TCP,
 		.prot =       &tcp_prot,
 		.ops =        &inet_stream_ops,
-		.no_check =   0,
 		.flags =      INET_PROTOSW_PERMANENT |
 			      INET_PROTOSW_ICSK,
 	},
@@ -1015,7 +1008,6 @@ static struct inet_protosw inetsw_array[] =
 		.protocol =   IPPROTO_UDP,
 		.prot =       &udp_prot,
 		.ops =        &inet_dgram_ops,
-		.no_check =   UDP_CSUM_DEFAULT,
 		.flags =      INET_PROTOSW_PERMANENT,
        },
 
@@ -1024,7 +1016,6 @@ static struct inet_protosw inetsw_array[] =
 		.protocol =   IPPROTO_ICMP,
 		.prot =       &ping_prot,
 		.ops =        &inet_dgram_ops,
-		.no_check =   UDP_CSUM_DEFAULT,
 		.flags =      INET_PROTOSW_REUSE,
        },
 
@@ -1033,7 +1024,6 @@ static struct inet_protosw inetsw_array[] =
 	       .protocol =   IPPROTO_IP,	/* wild card */
 	       .prot =       &raw_prot,
 	       .ops =        &inet_sockraw_ops,
-	       .no_check =   UDP_CSUM_DEFAULT,
 	       .flags =      INET_PROTOSW_REUSE,
        }
 };
@@ -1133,7 +1123,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 	fl4 = &inet->cork.fl.u.ip4;
 	rt = ip_route_connect(fl4, daddr, 0, RT_CONN_FLAGS(sk),
 			      sk->sk_bound_dev_if, sk->sk_protocol,
-			      inet->inet_sport, inet->inet_dport, sk, false);
+			      inet->inet_sport, inet->inet_dport, sk);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
@@ -1264,10 +1254,12 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
+		       SKB_GSO_GRE_CSUM |
 		       SKB_GSO_IPIP |
 		       SKB_GSO_SIT |
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
+		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_MPLS |
 		       0)))
 		goto out;
@@ -1299,8 +1291,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 
 	segs = ERR_PTR(-EPROTONOSUPPORT);
 
-	/* Note : following gso_segment() might change skb->encapsulation */
-	udpfrag = !skb->encapsulation && proto == IPPROTO_UDP;
+	if (skb->encapsulation &&
+	    skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+		udpfrag = proto == IPPROTO_UDP && encap;
+	else
+		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
 
 	ops = rcu_dereference(inet_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment))
@@ -1377,8 +1372,12 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
-		iph2 = ip_hdr(p);
-
+		iph2 = (struct iphdr *)(p->data + off);
+		/* The above works because, with the exception of the top
+		 * (inner most) layer, we only aggregate pkts with the same
+		 * hdr length so all the hdrs we'll need to verify will start
+		 * at the same offset.
+		 */
 		if ((iph->protocol ^ iph2->protocol) |
 		    ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
 		    ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) {
@@ -1390,13 +1389,24 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 		NAPI_GRO_CB(p)->flush |=
 			(iph->ttl ^ iph2->ttl) |
 			(iph->tos ^ iph2->tos) |
-			(__force int)((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) |
-			((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
+			((iph->frag_off ^ iph2->frag_off) & htons(IP_DF));
 
+		/* Save the IP ID check to be included later when we get to
+		 * the transport layer so only the inner most IP ID is checked.
+		 * This is because some GSO/TSO implementations do not
+		 * correctly increment the IP ID for the outer hdrs.
+		 */
+		NAPI_GRO_CB(p)->flush_id =
+			    ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
 		NAPI_GRO_CB(p)->flush |= flush;
 	}
 
 	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_set_network_header(skb, off);
+	/* The above will be needed by the transport layer if there is one
+	 * immediately following this IP hdr.
+	 */
+
 	skb_gro_pull(skb, sizeof(*iph));
 	skb_set_transport_header(skb, skb_gro_offset(skb));
 
@@ -1411,14 +1421,17 @@ out:
 	return pp;
 }
 
-static int inet_gro_complete(struct sk_buff *skb)
+static int inet_gro_complete(struct sk_buff *skb, int nhoff)
 {
-	__be16 newlen = htons(skb->len - skb_network_offset(skb));
-	struct iphdr *iph = ip_hdr(skb);
+	__be16 newlen = htons(skb->len - nhoff);
+	struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);
 	const struct net_offload *ops;
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
+	if (skb->encapsulation)
+		skb_set_inner_network_header(skb, nhoff);
+
 	csum_replace2(&iph->check, iph->tot_len, newlen);
 	iph->tot_len = newlen;
 
@@ -1427,7 +1440,11 @@ static int inet_gro_complete(struct sk_buff *skb)
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
 		goto out_unlock;
 
-	err = ops->callbacks.gro_complete(skb);
+	/* Only need to add sizeof(*iph) to get to the next hdr below
+	 * because any hdr with option will have been flushed in
+	 * inet_gro_receive().
+	 */
+	err = ops->callbacks.gro_complete(skb, nhoff + sizeof(*iph));
 
 out_unlock:
 	rcu_read_unlock();
@@ -1457,22 +1474,20 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family,
 }
 EXPORT_SYMBOL_GPL(inet_ctl_sock_create);
 
-unsigned long snmp_fold_field(void __percpu *mib[], int offt)
+unsigned long snmp_fold_field(void __percpu *mib, int offt)
 {
 	unsigned long res = 0;
-	int i, j;
+	int i;
 
-	for_each_possible_cpu(i) {
-		for (j = 0; j < SNMP_ARRAY_SZ; j++)
-			res += *(((unsigned long *) per_cpu_ptr(mib[j], i)) + offt);
-	}
+	for_each_possible_cpu(i)
+		res += *(((unsigned long *) per_cpu_ptr(mib, i)) + offt);
 	return res;
 }
 EXPORT_SYMBOL_GPL(snmp_fold_field);
 
 #if BITS_PER_LONG==32
 
-u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset)
+u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_offset)
 {
 	u64 res = 0;
 	int cpu;
@@ -1483,12 +1498,12 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset)
 		u64 v;
 		unsigned int start;
 
-		bhptr = per_cpu_ptr(mib[0], cpu);
+		bhptr = per_cpu_ptr(mib, cpu);
 		syncp = (struct u64_stats_sync *)(bhptr + syncp_offset);
 		do {
-			start = u64_stats_fetch_begin_bh(syncp);
+			start = u64_stats_fetch_begin_irq(syncp);
 			v = *(((u64 *) bhptr) + offt);
-		} while (u64_stats_fetch_retry_bh(syncp, start));
+		} while (u64_stats_fetch_retry_irq(syncp, start));
 
 		res += v;
 	}
@@ -1497,25 +1512,6 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset)
 EXPORT_SYMBOL_GPL(snmp_fold_field64);
 #endif
 
-int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align)
-{
-	BUG_ON(ptr == NULL);
-	ptr[0] = __alloc_percpu(mibsize, align);
-	if (!ptr[0])
-		return -ENOMEM;
-
-#if SNMP_ARRAY_SZ == 2
-	ptr[1] = __alloc_percpu(mibsize, align);
-	if (!ptr[1]) {
-		free_percpu(ptr[0]);
-		ptr[0] = NULL;
-		return -ENOMEM;
-	}
-#endif
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snmp_mib_init);
-
 #ifdef CONFIG_IP_MULTICAST
 static const struct net_protocol igmp_protocol = {
 	.handler =	igmp_rcv,
@@ -1529,6 +1525,7 @@ static const struct net_protocol tcp_protocol = {
 	.err_handler	=	tcp_v4_err,
 	.no_policy	=	1,
 	.netns_ok	=	1,
+	.icmp_strict_tag_validation = 1,
 };
 
 static const struct net_protocol udp_protocol = {
@@ -1550,40 +1547,30 @@ static __net_init int ipv4_mib_init_net(struct net *net)
 {
 	int i;
 
-	if (snmp_mib_init((void __percpu **)net->mib.tcp_statistics,
-			  sizeof(struct tcp_mib),
-			  __alignof__(struct tcp_mib)) < 0)
+	net->mib.tcp_statistics = alloc_percpu(struct tcp_mib);
+	if (!net->mib.tcp_statistics)
 		goto err_tcp_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.ip_statistics,
-			  sizeof(struct ipstats_mib),
-			  __alignof__(struct ipstats_mib)) < 0)
+	net->mib.ip_statistics = alloc_percpu(struct ipstats_mib);
+	if (!net->mib.ip_statistics)
 		goto err_ip_mib;
 
 	for_each_possible_cpu(i) {
 		struct ipstats_mib *af_inet_stats;
-		af_inet_stats = per_cpu_ptr(net->mib.ip_statistics[0], i);
-		u64_stats_init(&af_inet_stats->syncp);
-#if SNMP_ARRAY_SZ == 2
-		af_inet_stats = per_cpu_ptr(net->mib.ip_statistics[1], i);
+		af_inet_stats = per_cpu_ptr(net->mib.ip_statistics, i);
 		u64_stats_init(&af_inet_stats->syncp);
-#endif
 	}
 
-	if (snmp_mib_init((void __percpu **)net->mib.net_statistics,
-			  sizeof(struct linux_mib),
-			  __alignof__(struct linux_mib)) < 0)
+	net->mib.net_statistics = alloc_percpu(struct linux_mib);
+	if (!net->mib.net_statistics)
 		goto err_net_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.udp_statistics,
-			  sizeof(struct udp_mib),
-			  __alignof__(struct udp_mib)) < 0)
+	net->mib.udp_statistics = alloc_percpu(struct udp_mib);
+	if (!net->mib.udp_statistics)
 		goto err_udp_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.udplite_statistics,
-			  sizeof(struct udp_mib),
-			  __alignof__(struct udp_mib)) < 0)
+	net->mib.udplite_statistics = alloc_percpu(struct udp_mib);
+	if (!net->mib.udplite_statistics)
 		goto err_udplite_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.icmp_statistics,
-			  sizeof(struct icmp_mib),
-			  __alignof__(struct icmp_mib)) < 0)
+	net->mib.icmp_statistics = alloc_percpu(struct icmp_mib);
+	if (!net->mib.icmp_statistics)
 		goto err_icmp_mib;
 	net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib),
 					      GFP_KERNEL);
@@ -1594,17 +1581,17 @@ static __net_init int ipv4_mib_init_net(struct net *net)
 	return 0;
 
 err_icmpmsg_mib:
-	snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
+	free_percpu(net->mib.icmp_statistics);
 err_icmp_mib:
-	snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
+	free_percpu(net->mib.udplite_statistics);
 err_udplite_mib:
-	snmp_mib_free((void __percpu **)net->mib.udp_statistics);
+	free_percpu(net->mib.udp_statistics);
 err_udp_mib:
-	snmp_mib_free((void __percpu **)net->mib.net_statistics);
+	free_percpu(net->mib.net_statistics);
 err_net_mib:
-	snmp_mib_free((void __percpu **)net->mib.ip_statistics);
+	free_percpu(net->mib.ip_statistics);
 err_ip_mib:
-	snmp_mib_free((void __percpu **)net->mib.tcp_statistics);
+	free_percpu(net->mib.tcp_statistics);
 err_tcp_mib:
 	return -ENOMEM;
 }
@@ -1612,12 +1599,12 @@ err_tcp_mib:
 static __net_exit void ipv4_mib_exit_net(struct net *net)
 {
 	kfree(net->mib.icmpmsg_statistics);
-	snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
-	snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
-	snmp_mib_free((void __percpu **)net->mib.udp_statistics);
-	snmp_mib_free((void __percpu **)net->mib.net_statistics);
-	snmp_mib_free((void __percpu **)net->mib.ip_statistics);
-	snmp_mib_free((void __percpu **)net->mib.tcp_statistics);
+	free_percpu(net->mib.icmp_statistics);
+	free_percpu(net->mib.udplite_statistics);
+	free_percpu(net->mib.udp_statistics);
+	free_percpu(net->mib.net_statistics);
+	free_percpu(net->mib.ip_statistics);
+	free_percpu(net->mib.tcp_statistics);
 }
 
 static __net_initdata struct pernet_operations ipv4_mib_ops = {
@@ -1630,6 +1617,39 @@ static int __init init_ipv4_mibs(void)
 	return register_pernet_subsys(&ipv4_mib_ops);
 }
 
+static __net_init int inet_init_net(struct net *net)
+{
+	/*
+	 * Set defaults for local port range
+	 */
+	seqlock_init(&net->ipv4.ip_local_ports.lock);
+	net->ipv4.ip_local_ports.range[0] =  32768;
+	net->ipv4.ip_local_ports.range[1] =  61000;
+
+	seqlock_init(&net->ipv4.ping_group_range.lock);
+	/*
+	 * Sane defaults - nobody may create ping sockets.
+	 * Boot scripts should set this to distro-specific group.
+	 */
+	net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1);
+	net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0);
+	return 0;
+}
+
+static __net_exit void inet_exit_net(struct net *net)
+{
+}
+
+static __net_initdata struct pernet_operations af_inet_ops = {
+	.init = inet_init_net,
+	.exit = inet_exit_net,
+};
+
+static int __init init_inet_pernet_ops(void)
+{
+	return register_pernet_subsys(&af_inet_ops);
+}
+
 static int ipv4_proc_init(void);
 
 /*
@@ -1683,13 +1703,9 @@ static int __init inet_init(void)
 
 	BUILD_BUG_ON(sizeof(struct inet_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb));
 
-	sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
-	if (!sysctl_local_reserved_ports)
-		goto out;
-
 	rc = proto_register(&tcp_prot, 1);
 	if (rc)
-		goto out_free_reserved_ports;
+		goto out;
 
 	rc = proto_register(&udp_prot, 1);
 	if (rc)
@@ -1774,6 +1790,9 @@ static int __init inet_init(void)
 	if (ip_mr_init())
 		pr_crit("%s: Cannot init ipv4 mroute\n", __func__);
 #endif
+
+	if (init_inet_pernet_ops())
+		pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
 	/*
 	 *	Initialise per-cpu ipv4 mibs
 	 */
@@ -1796,8 +1815,6 @@ out_unregister_udp_proto:
 	proto_unregister(&udp_prot);
 out_unregister_tcp_proto:
 	proto_unregister(&tcp_prot);
-out_free_reserved_ports:
-	kfree(sysctl_local_reserved_ports);
 	goto out;
 }
 
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 717902669d2..a2afa89513a 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -155,6 +155,10 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
 	struct iphdr *iph, *top_iph;
 	struct ip_auth_hdr *ah;
 	struct ah_data *ahp;
+	int seqhi_len = 0;
+	__be32 *seqhi;
+	int sglists = 0;
+	struct scatterlist *seqhisg;
 
 	ahp = x->data;
 	ahash = ahp->ahash;
@@ -167,14 +171,19 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
 	ah = ip_auth_hdr(skb);
 	ihl = ip_hdrlen(skb);
 
+	if (x->props.flags & XFRM_STATE_ESN) {
+		sglists = 1;
+		seqhi_len = sizeof(*seqhi);
+	}
 	err = -ENOMEM;
-	iph = ah_alloc_tmp(ahash, nfrags, ihl);
+	iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + seqhi_len);
 	if (!iph)
 		goto out;
-
-	icv = ah_tmp_icv(ahash, iph, ihl);
+	seqhi = (__be32 *)((char *)iph + ihl);
+	icv = ah_tmp_icv(ahash, seqhi, seqhi_len);
 	req = ah_tmp_req(ahash, icv);
 	sg = ah_req_sg(ahash, req);
+	seqhisg = sg + nfrags;
 
 	memset(ah->auth_data, 0, ahp->icv_trunc_len);
 
@@ -210,10 +219,15 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
 	ah->spi = x->id.spi;
 	ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 
-	sg_init_table(sg, nfrags);
-	skb_to_sgvec(skb, sg, 0, skb->len);
+	sg_init_table(sg, nfrags + sglists);
+	skb_to_sgvec_nomark(skb, sg, 0, skb->len);
 
-	ahash_request_set_crypt(req, sg, icv, skb->len);
+	if (x->props.flags & XFRM_STATE_ESN) {
+		/* Attach seqhi sg right after packet payload */
+		*seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+		sg_set_buf(seqhisg, seqhi, seqhi_len);
+	}
+	ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
 	ahash_request_set_callback(req, 0, ah_output_done, skb);
 
 	AH_SKB_CB(skb)->tmp = iph;
@@ -295,6 +309,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
 	struct ip_auth_hdr *ah;
 	struct ah_data *ahp;
 	int err = -ENOMEM;
+	int seqhi_len = 0;
+	__be32 *seqhi;
+	int sglists = 0;
+	struct scatterlist *seqhisg;
 
 	if (!pskb_may_pull(skb, sizeof(*ah)))
 		goto out;
@@ -335,14 +353,22 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
 	iph = ip_hdr(skb);
 	ihl = ip_hdrlen(skb);
 
-	work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len);
+	if (x->props.flags & XFRM_STATE_ESN) {
+		sglists = 1;
+		seqhi_len = sizeof(*seqhi);
+	}
+
+	work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl +
+				ahp->icv_trunc_len + seqhi_len);
 	if (!work_iph)
 		goto out;
 
-	auth_data = ah_tmp_auth(work_iph, ihl);
+	seqhi = (__be32 *)((char *)work_iph + ihl);
+	auth_data = ah_tmp_auth(seqhi, seqhi_len);
 	icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len);
 	req = ah_tmp_req(ahash, icv);
 	sg = ah_req_sg(ahash, req);
+	seqhisg = sg + nfrags;
 
 	memcpy(work_iph, iph, ihl);
 	memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
@@ -361,10 +387,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
 
 	skb_push(skb, ihl);
 
-	sg_init_table(sg, nfrags);
-	skb_to_sgvec(skb, sg, 0, skb->len);
+	sg_init_table(sg, nfrags + sglists);
+	skb_to_sgvec_nomark(skb, sg, 0, skb->len);
 
-	ahash_request_set_crypt(req, sg, icv, skb->len);
+	if (x->props.flags & XFRM_STATE_ESN) {
+		/* Attach seqhi sg right after packet payload */
+		*seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
+		sg_set_buf(seqhisg, seqhi, seqhi_len);
+	}
+	ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
 	ahash_request_set_callback(req, 0, ah_input_done, skb);
 
 	AH_SKB_CB(skb)->tmp = work_iph;
@@ -397,7 +428,7 @@ out:
 	return err;
 }
 
-static void ah4_err(struct sk_buff *skb, u32 info)
+static int ah4_err(struct sk_buff *skb, u32 info)
 {
 	struct net *net = dev_net(skb->dev);
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
@@ -407,23 +438,25 @@ static void ah4_err(struct sk_buff *skb, u32 info)
 	switch (icmp_hdr(skb)->type) {
 	case ICMP_DEST_UNREACH:
 		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
-			return;
+			return 0;
 	case ICMP_REDIRECT:
 		break;
 	default:
-		return;
+		return 0;
 	}
 
 	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
 			      ah->spi, IPPROTO_AH, AF_INET);
 	if (!x)
-		return;
+		return 0;
 
 	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
 		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
 	else
 		ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
 	xfrm_state_put(x);
+
+	return 0;
 }
 
 static int ah_init_state(struct xfrm_state *x)
@@ -505,6 +538,10 @@ static void ah_destroy(struct xfrm_state *x)
 	kfree(ahp);
 }
 
+static int ah4_rcv_cb(struct sk_buff *skb, int err)
+{
+	return 0;
+}
 
 static const struct xfrm_type ah_type =
 {
@@ -518,11 +555,12 @@ static const struct xfrm_type ah_type =
 	.output		= ah_output
 };
 
-static const struct net_protocol ah4_protocol = {
+static struct xfrm4_protocol ah4_protocol = {
 	.handler	=	xfrm4_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	ah4_rcv_cb,
 	.err_handler	=	ah4_err,
-	.no_policy	=	1,
-	.netns_ok	=	1,
+	.priority	=	0,
 };
 
 static int __init ah4_init(void)
@@ -531,7 +569,7 @@ static int __init ah4_init(void)
 		pr_info("%s: can't add xfrm type\n", __func__);
 		return -EAGAIN;
 	}
-	if (inet_add_protocol(&ah4_protocol, IPPROTO_AH) < 0) {
+	if (xfrm4_protocol_register(&ah4_protocol, IPPROTO_AH) < 0) {
 		pr_info("%s: can't add protocol\n", __func__);
 		xfrm_unregister_type(&ah_type, AF_INET);
 		return -EAGAIN;
@@ -541,7 +579,7 @@ static int __init ah4_init(void)
 
 static void __exit ah4_fini(void)
 {
-	if (inet_del_protocol(&ah4_protocol, IPPROTO_AH) < 0)
+	if (xfrm4_protocol_deregister(&ah4_protocol, IPPROTO_AH) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
 	if (xfrm_unregister_type(&ah_type, AF_INET) < 0)
 		pr_info("%s: can't remove xfrm type\n", __func__);
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index f0418586394..1a9b99e0446 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -381,6 +381,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
 
 static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip)
 {
+	struct net *net = dev_net(in_dev->dev);
 	int scope;
 
 	switch (IN_DEV_ARP_IGNORE(in_dev)) {
@@ -399,6 +400,7 @@ static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip)
 	case 3:	/* Do not reply for scope host addresses */
 		sip = 0;
 		scope = RT_SCOPE_LINK;
+		in_dev = NULL;
 		break;
 	case 4:	/* Reserved */
 	case 5:
@@ -410,7 +412,7 @@ static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip)
 	default:
 		return 0;
 	}
-	return !inet_confirm_addr(in_dev, sip, tip, scope);
+	return !inet_confirm_addr(net, in_dev, sip, tip, scope);
 }
 
 static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
@@ -730,6 +732,7 @@ static int arp_process(struct sk_buff *skb)
 	int addr_type;
 	struct neighbour *n;
 	struct net *net = dev_net(dev);
+	bool is_garp = false;
 
 	/* arp_rcv below verifies the ARP header and verifies the device
 	 * is ARP'able.
@@ -896,10 +899,12 @@ static int arp_process(struct sk_buff *skb)
 		   It is possible, that this option should be enabled for some
 		   devices (strip is candidate)
 		 */
+		is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip &&
+			  inet_addr_type(net, sip) == RTN_UNICAST;
+
 		if (n == NULL &&
-		    (arp->ar_op == htons(ARPOP_REPLY) ||
-		     (arp->ar_op == htons(ARPOP_REQUEST) && tip == sip)) &&
-		    inet_addr_type(net, sip) == RTN_UNICAST)
+		    ((arp->ar_op == htons(ARPOP_REPLY)  &&
+		      inet_addr_type(net, sip) == RTN_UNICAST) || is_garp))
 			n = __neigh_lookup(&arp_tbl, &sip, dev, 1);
 	}
 
@@ -912,8 +917,10 @@ static int arp_process(struct sk_buff *skb)
 		   agents are active. Taking the first reply prevents
 		   arp trashing and chooses the fastest router.
 		 */
-		override = time_after(jiffies, n->updated +
-					       NEIGH_VAR(n->parms, LOCKTIME));
+		override = time_after(jiffies,
+				      n->updated +
+				      NEIGH_VAR(n->parms, LOCKTIME)) ||
+			   is_garp;
 
 		/* Broadcast replies and request packets
 		   do not assert neighbour reachability.
@@ -1110,7 +1117,7 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
 	return err;
 }
 
-int arp_invalidate(struct net_device *dev, __be32 ip)
+static int arp_invalidate(struct net_device *dev, __be32 ip)
 {
 	struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev);
 	int err = -ENXIO;
@@ -1125,7 +1132,6 @@ int arp_invalidate(struct net_device *dev, __be32 ip)
 
 	return err;
 }
-EXPORT_SYMBOL(arp_invalidate);
 
 static int arp_req_delete_public(struct net *net, struct arpreq *r,
 		struct net_device *dev)
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 4b59b6e488d..69e77c8ff28 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1335,8 +1335,7 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def,
 	secattr->flags |= NETLBL_SECATTR_MLS_LVL;
 
 	if (tag_len > 4) {
-		secattr->attr.mls.cat =
-		                       netlbl_secattr_catmap_alloc(GFP_ATOMIC);
+		secattr->attr.mls.cat = netlbl_secattr_catmap_alloc(GFP_ATOMIC);
 		if (secattr->attr.mls.cat == NULL)
 			return -ENOMEM;
 
@@ -1431,8 +1430,7 @@ static int cipso_v4_parsetag_enum(const struct cipso_v4_doi *doi_def,
 	secattr->flags |= NETLBL_SECATTR_MLS_LVL;
 
 	if (tag_len > 4) {
-		secattr->attr.mls.cat =
-			               netlbl_secattr_catmap_alloc(GFP_ATOMIC);
+		secattr->attr.mls.cat = netlbl_secattr_catmap_alloc(GFP_ATOMIC);
 		if (secattr->attr.mls.cat == NULL)
 			return -ENOMEM;
 
@@ -1526,8 +1524,7 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def,
 	secattr->flags |= NETLBL_SECATTR_MLS_LVL;
 
 	if (tag_len > 4) {
-		secattr->attr.mls.cat =
-			               netlbl_secattr_catmap_alloc(GFP_ATOMIC);
+		secattr->attr.mls.cat = netlbl_secattr_catmap_alloc(GFP_ATOMIC);
 		if (secattr->attr.mls.cat == NULL)
 			return -ENOMEM;
 
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 19e36376d2a..a3095fdefbe 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -53,7 +53,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr,
 			      RT_CONN_FLAGS(sk), oif,
 			      sk->sk_protocol,
-			      inet->inet_sport, usin->sin_port, sk, true);
+			      inet->inet_sport, usin->sin_port, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		if (err == -ENETUNREACH)
@@ -86,18 +86,26 @@ out:
 }
 EXPORT_SYMBOL(ip4_datagram_connect);
 
+/* Because UDP xmit path can manipulate sk_dst_cache without holding
+ * socket lock, we need to use sk_dst_set() here,
+ * even if we own the socket lock.
+ */
 void ip4_datagram_release_cb(struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct ip_options_rcu *inet_opt;
 	__be32 daddr = inet->inet_daddr;
+	struct dst_entry *dst;
 	struct flowi4 fl4;
 	struct rtable *rt;
 
-	if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0))
-		return;
-
 	rcu_read_lock();
+
+	dst = __sk_dst_get(sk);
+	if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) {
+		rcu_read_unlock();
+		return;
+	}
 	inet_opt = rcu_dereference(inet->inet_opt);
 	if (inet_opt && inet_opt->opt.srr)
 		daddr = inet_opt->opt.faddr;
@@ -105,8 +113,10 @@ void ip4_datagram_release_cb(struct sock *sk)
 				   inet->inet_saddr, inet->inet_dport,
 				   inet->inet_sport, sk->sk_protocol,
 				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
-	if (!IS_ERR(rt))
-		__sk_dst_set(sk, &rt->dst);
+
+	dst = !IS_ERR(rt) ? &rt->dst : NULL;
+	sk_dst_set(sk, dst);
+
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 43065be3630..e9449376b58 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -99,13 +99,13 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
 	[IFA_BROADCAST] 	= { .type = NLA_U32 },
 	[IFA_LABEL]     	= { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
 	[IFA_CACHEINFO]		= { .len = sizeof(struct ifa_cacheinfo) },
+	[IFA_FLAGS]		= { .type = NLA_U32 },
 };
 
 #define IN4_ADDR_HSIZE_SHIFT	8
 #define IN4_ADDR_HSIZE		(1U << IN4_ADDR_HSIZE_SHIFT)
 
 static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE];
-static DEFINE_SPINLOCK(inet_addr_hash_lock);
 
 static u32 inet_addr_hash(struct net *net, __be32 addr)
 {
@@ -118,16 +118,14 @@ static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa)
 {
 	u32 hash = inet_addr_hash(net, ifa->ifa_local);
 
-	spin_lock(&inet_addr_hash_lock);
+	ASSERT_RTNL();
 	hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]);
-	spin_unlock(&inet_addr_hash_lock);
 }
 
 static void inet_hash_remove(struct in_ifaddr *ifa)
 {
-	spin_lock(&inet_addr_hash_lock);
+	ASSERT_RTNL();
 	hlist_del_init_rcu(&ifa->hash);
-	spin_unlock(&inet_addr_hash_lock);
 }
 
 /**
@@ -463,7 +461,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 	}
 
 	if (!(ifa->ifa_flags & IFA_F_SECONDARY)) {
-		net_srandom(ifa->ifa_local);
+		prandom_seed((__force u32) ifa->ifa_local);
 		ifap = last_primary;
 	}
 
@@ -473,7 +471,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 	inet_hash_insert(dev_net(in_dev->dev), ifa);
 
 	cancel_delayed_work(&check_lifetime_work);
-	schedule_delayed_work(&check_lifetime_work, 0);
+	queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0);
 
 	/* Send message first, then call notifier.
 	   Notifier will trigger FIB update, so that
@@ -683,7 +681,8 @@ static void check_lifetime(struct work_struct *work)
 	if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX))
 		next_sched = now + ADDRCONF_TIMER_FUZZ_MAX;
 
-	schedule_delayed_work(&check_lifetime_work, next_sched - now);
+	queue_delayed_work(system_power_efficient_wq, &check_lifetime_work,
+			next_sched - now);
 }
 
 static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft,
@@ -757,7 +756,8 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 	INIT_HLIST_NODE(&ifa->hash);
 	ifa->ifa_prefixlen = ifm->ifa_prefixlen;
 	ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen);
-	ifa->ifa_flags = ifm->ifa_flags;
+	ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) :
+					 ifm->ifa_flags;
 	ifa->ifa_scope = ifm->ifa_scope;
 	ifa->ifa_dev = in_dev;
 
@@ -827,7 +827,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	ifa_existing = find_matching_ifa(ifa);
 	if (!ifa_existing) {
 		/* It would be best to check for !NLM_F_CREATE here but
-		 * userspace alreay relies on not having to provide this.
+		 * userspace already relies on not having to provide this.
 		 */
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
 		return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid);
@@ -840,7 +840,8 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 		ifa = ifa_existing;
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
 		cancel_delayed_work(&check_lifetime_work);
-		schedule_delayed_work(&check_lifetime_work, 0);
+		queue_delayed_work(system_power_efficient_wq,
+				&check_lifetime_work, 0);
 		rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
 		blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
 	}
@@ -1238,22 +1239,21 @@ static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst,
 
 /*
  * Confirm that local IP address exists using wildcards:
- * - in_dev: only on this interface, 0=any interface
+ * - net: netns to check, cannot be NULL
+ * - in_dev: only on this interface, NULL=any interface
  * - dst: only in the same subnet as dst, 0=any dst
  * - local: address, 0=autoselect the local address
  * - scope: maximum allowed scope value for the local address
  */
-__be32 inet_confirm_addr(struct in_device *in_dev,
+__be32 inet_confirm_addr(struct net *net, struct in_device *in_dev,
 			 __be32 dst, __be32 local, int scope)
 {
 	__be32 addr = 0;
 	struct net_device *dev;
-	struct net *net;
 
-	if (scope != RT_SCOPE_LINK)
+	if (in_dev != NULL)
 		return confirm_addr_indev(in_dev, dst, local, scope);
 
-	net = dev_net(in_dev->dev);
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
 		in_dev = __in_dev_get_rcu(dev);
@@ -1384,6 +1384,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
 				memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
 				set_ifa_lifetime(ifa, INFINITY_LIFE_TIME,
 						 INFINITY_LIFE_TIME);
+				ipv4_devconf_setall(in_dev);
+				neigh_parms_data_state_setall(in_dev->arp_parms);
 				inet_insert_ifa(ifa);
 			}
 		}
@@ -1437,7 +1439,9 @@ static size_t inet_nlmsg_size(void)
 	       + nla_total_size(4) /* IFA_ADDRESS */
 	       + nla_total_size(4) /* IFA_LOCAL */
 	       + nla_total_size(4) /* IFA_BROADCAST */
-	       + nla_total_size(IFNAMSIZ); /* IFA_LABEL */
+	       + nla_total_size(IFNAMSIZ) /* IFA_LABEL */
+	       + nla_total_size(4)  /* IFA_FLAGS */
+	       + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */
 }
 
 static inline u32 cstamp_delta(unsigned long cstamp)
@@ -1505,6 +1509,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
 	     nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) ||
 	    (ifa->ifa_label[0] &&
 	     nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) ||
+	    nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) ||
 	    put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp,
 			  preferred, valid))
 		goto nla_put_failure;
@@ -1693,6 +1698,8 @@ static int inet_netconf_msgsize_devconf(int type)
 		size += nla_total_size(4);
 	if (type == -1 || type == NETCONFA_MC_FORWARDING)
 		size += nla_total_size(4);
+	if (type == -1 || type == NETCONFA_PROXY_NEIGH)
+		size += nla_total_size(4);
 
 	return size;
 }
@@ -1729,6 +1736,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	    nla_put_s32(skb, NETCONFA_MC_FORWARDING,
 			IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0)
 		goto nla_put_failure;
+	if ((type == -1 || type == NETCONFA_PROXY_NEIGH) &&
+	    nla_put_s32(skb, NETCONFA_PROXY_NEIGH,
+			IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
+		goto nla_put_failure;
 
 	return nlmsg_end(skb, nlh);
 
@@ -1766,6 +1777,7 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
 	[NETCONFA_IFINDEX]	= { .len = sizeof(int) },
 	[NETCONFA_FORWARDING]	= { .len = sizeof(int) },
 	[NETCONFA_RP_FILTER]	= { .len = sizeof(int) },
+	[NETCONFA_PROXY_NEIGH]	= { .len = sizeof(int) },
 };
 
 static int inet_netconf_get_devconf(struct sk_buff *in_skb,
@@ -1947,6 +1959,19 @@ static void inet_forward_change(struct net *net)
 	}
 }
 
+static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf)
+{
+	if (cnf == net->ipv4.devconf_dflt)
+		return NETCONFA_IFINDEX_DEFAULT;
+	else if (cnf == net->ipv4.devconf_all)
+		return NETCONFA_IFINDEX_ALL;
+	else {
+		struct in_device *idev
+			= container_of(cnf, struct in_device, cnf);
+		return idev->dev->ifindex;
+	}
+}
+
 static int devinet_conf_proc(struct ctl_table *ctl, int write,
 			     void __user *buffer,
 			     size_t *lenp, loff_t *ppos)
@@ -1959,6 +1984,7 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 		struct ipv4_devconf *cnf = ctl->extra1;
 		struct net *net = ctl->extra2;
 		int i = (int *)ctl->data - cnf->data;
+		int ifindex;
 
 		set_bit(i, cnf->state);
 
@@ -1968,23 +1994,19 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 		    i == IPV4_DEVCONF_ROUTE_LOCALNET - 1)
 			if ((new_value == 0) && (old_value != 0))
 				rt_cache_flush(net);
+
 		if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
 		    new_value != old_value) {
-			int ifindex;
-
-			if (cnf == net->ipv4.devconf_dflt)
-				ifindex = NETCONFA_IFINDEX_DEFAULT;
-			else if (cnf == net->ipv4.devconf_all)
-				ifindex = NETCONFA_IFINDEX_ALL;
-			else {
-				struct in_device *idev =
-					container_of(cnf, struct in_device,
-						     cnf);
-				ifindex = idev->dev->ifindex;
-			}
+			ifindex = devinet_conf_ifindex(net, cnf);
 			inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER,
 						    ifindex, cnf);
 		}
+		if (i == IPV4_DEVCONF_PROXY_ARP - 1 &&
+		    new_value != old_value) {
+			ifindex = devinet_conf_ifindex(net, cnf);
+			inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+						    ifindex, cnf);
+		}
 	}
 
 	return ret;
@@ -2300,7 +2322,7 @@ void __init devinet_init(void)
 	register_gifconf(PF_INET, inet_gifconf);
 	register_netdevice_notifier(&ip_netdev_notifier);
 
-	schedule_delayed_work(&check_lifetime_work, 0);
+	queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0);
 
 	rtnl_af_register(&inet_af_ops);
 
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 7785b28061a..360b565918c 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -473,7 +473,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
 		 net_adj) & ~(blksize - 1)) + net_adj - 2;
 }
 
-static void esp4_err(struct sk_buff *skb, u32 info)
+static int esp4_err(struct sk_buff *skb, u32 info)
 {
 	struct net *net = dev_net(skb->dev);
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
@@ -483,23 +483,25 @@ static void esp4_err(struct sk_buff *skb, u32 info)
 	switch (icmp_hdr(skb)->type) {
 	case ICMP_DEST_UNREACH:
 		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
-			return;
+			return 0;
 	case ICMP_REDIRECT:
 		break;
 	default:
-		return;
+		return 0;
 	}
 
 	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
 			      esph->spi, IPPROTO_ESP, AF_INET);
 	if (!x)
-		return;
+		return 0;
 
 	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
 		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
 	else
 		ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
 	xfrm_state_put(x);
+
+	return 0;
 }
 
 static void esp_destroy(struct xfrm_state *x)
@@ -672,6 +674,11 @@ error:
 	return err;
 }
 
+static int esp4_rcv_cb(struct sk_buff *skb, int err)
+{
+	return 0;
+}
+
 static const struct xfrm_type esp_type =
 {
 	.description	= "ESP4",
@@ -685,11 +692,12 @@ static const struct xfrm_type esp_type =
 	.output		= esp_output
 };
 
-static const struct net_protocol esp4_protocol = {
+static struct xfrm4_protocol esp4_protocol = {
 	.handler	=	xfrm4_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	esp4_rcv_cb,
 	.err_handler	=	esp4_err,
-	.no_policy	=	1,
-	.netns_ok	=	1,
+	.priority	=	0,
 };
 
 static int __init esp4_init(void)
@@ -698,7 +706,7 @@ static int __init esp4_init(void)
 		pr_info("%s: can't add xfrm type\n", __func__);
 		return -EAGAIN;
 	}
-	if (inet_add_protocol(&esp4_protocol, IPPROTO_ESP) < 0) {
+	if (xfrm4_protocol_register(&esp4_protocol, IPPROTO_ESP) < 0) {
 		pr_info("%s: can't add protocol\n", __func__);
 		xfrm_unregister_type(&esp_type, AF_INET);
 		return -EAGAIN;
@@ -708,7 +716,7 @@ static int __init esp4_init(void)
 
 static void __exit esp4_fini(void)
 {
-	if (inet_del_protocol(&esp4_protocol, IPPROTO_ESP) < 0)
+	if (xfrm4_protocol_deregister(&esp4_protocol, IPPROTO_ESP) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
 	if (xfrm_unregister_type(&esp_type, AF_INET) < 0)
 		pr_info("%s: can't remove xfrm type\n", __func__);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index d846304b7b8..255aa9946fe 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -250,7 +250,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	bool dev_match;
 
 	fl4.flowi4_oif = 0;
-	fl4.flowi4_iif = oif;
+	fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX;
 	fl4.daddr = src;
 	fl4.saddr = dst;
 	fl4.flowi4_tos = tos;
@@ -659,7 +659,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 
 	if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
 	    ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
-		return ip_rt_dump(skb, cb);
+		return skb->len;
 
 	s_h = cb->args[0];
 	s_e = cb->args[1];
@@ -1047,6 +1047,8 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 	}
 
 	in_dev = __in_dev_get_rtnl(dev);
+	if (!in_dev)
+		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UP:
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index 388d113fd28..1e4f6600b31 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -33,8 +33,6 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id,
 void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len,
 	       u32 tb_id, const struct nl_info *info, unsigned int nlm_flags);
 struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio);
-int fib_detect_death(struct fib_info *fi, int order,
-		     struct fib_info **last_resort, int *last_idx, int dflt);
 
 static inline void fib_result_assign(struct fib_result *res,
 				     struct fib_info *fi)
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 523be38e37d..f2e15738534 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -104,7 +104,10 @@ errout:
 static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
 {
 	struct fib_result *result = (struct fib_result *) arg->result;
-	struct net_device *dev = result->fi->fib_dev;
+	struct net_device *dev = NULL;
+
+	if (result->fi)
+		dev = result->fi->fib_dev;
 
 	/* do not accept result if the route does
 	 * not meet the required prefix length
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e63f47a4e65..b10cd43a472 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -426,8 +426,9 @@ struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio)
 	return NULL;
 }
 
-int fib_detect_death(struct fib_info *fi, int order,
-		     struct fib_info **last_resort, int *last_idx, int dflt)
+static int fib_detect_death(struct fib_info *fi, int order,
+			    struct fib_info **last_resort, int *last_idx,
+			    int dflt)
 {
 	struct neighbour *n;
 	int state = NUD_NONE;
@@ -630,6 +631,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
 				.daddr = nh->nh_gw,
 				.flowi4_scope = cfg->fc_scope + 1,
 				.flowi4_oif = nh->nh_oif,
+				.flowi4_iif = LOOPBACK_IFINDEX,
 			};
 
 			/* It is not necessary, but requires a bit of thinking */
@@ -819,13 +821,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (fi == NULL)
 		goto failure;
+	fib_info_cnt++;
 	if (cfg->fc_mx) {
 		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
 		if (!fi->fib_metrics)
 			goto failure;
 	} else
 		fi->fib_metrics = (u32 *) dst_default_metrics;
-	fib_info_cnt++;
 
 	fi->fib_net = hold_net(net);
 	fi->fib_protocol = cfg->fc_protocol;
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 5893e99e829..0485bf7f8f0 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -68,6 +68,7 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 
 	skb_push(skb, hdr_len);
 
+	skb_reset_transport_header(skb);
 	greh = (struct gre_base_hdr *)skb->data;
 	greh->flags = tnl_flags_to_gre_flags(tpi->flags);
 	greh->protocol = tpi->proto;
@@ -84,7 +85,8 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 			ptr--;
 		}
 		if (tpi->flags&TUNNEL_CSUM &&
-		    !(skb_shinfo(skb)->gso_type & SKB_GSO_GRE)) {
+		    !(skb_shinfo(skb)->gso_type &
+		      (SKB_GSO_GRE|SKB_GSO_GRE_CSUM))) {
 			*ptr = 0;
 			*(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0,
 								 skb->len, 0));
@@ -93,28 +95,6 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 }
 EXPORT_SYMBOL_GPL(gre_build_header);
 
-static __sum16 check_checksum(struct sk_buff *skb)
-{
-	__sum16 csum = 0;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		csum = csum_fold(skb->csum);
-
-		if (!csum)
-			break;
-		/* Fall through. */
-
-	case CHECKSUM_NONE:
-		skb->csum = 0;
-		csum = __skb_checksum_complete(skb);
-		skb->ip_summed = CHECKSUM_COMPLETE;
-		break;
-	}
-
-	return csum;
-}
-
 static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			    bool *csum_err)
 {
@@ -141,7 +121,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 
 	options = (__be32 *)(greh + 1);
 	if (greh->flags & GRE_CSUM) {
-		if (check_checksum(skb)) {
+		if (skb_checksum_simple_validate(skb)) {
 			*csum_err = true;
 			return -EINVAL;
 		}
@@ -182,6 +162,14 @@ static int gre_cisco_rcv(struct sk_buff *skb)
 	int i;
 	bool csum_err = false;
 
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+	if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
+		/* Looped back packet, drop it! */
+		if (rt_is_output_route(skb_rtable(skb)))
+			goto drop;
+	}
+#endif
+
 	if (parse_gre_header(skb, &tpi, &csum_err) < 0)
 		goto drop;
 
@@ -355,14 +343,7 @@ static int __init gre_init(void)
 		goto err_gre;
 	}
 
-	if (gre_offload_init()) {
-		pr_err("can't add protocol offload\n");
-		goto err_gso;
-	}
-
 	return 0;
-err_gso:
-	gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
 err_gre:
 	inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
 err:
@@ -371,8 +352,6 @@ err:
 
 static void __exit gre_exit(void)
 {
-	gre_offload_exit();
-
 	gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
 	inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
 }
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index e5d43618846..f0bdd47bbbc 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/skbuff.h>
+#include <linux/init.h>
 #include <net/protocol.h>
 #include <net/gre.h>
 
@@ -26,8 +27,9 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	netdev_features_t enc_features;
-	int ghl = GRE_HEADER_SECTION;
+	int ghl;
 	struct gre_base_hdr *greh;
+	u16 mac_offset = skb->mac_header;
 	int mac_len = skb->mac_len;
 	__be16 protocol = skb->protocol;
 	int tnl_hlen;
@@ -40,6 +42,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_DODGY |
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
+				  SKB_GSO_GRE_CSUM |
 				  SKB_GSO_IPIP)))
 		goto out;
 
@@ -48,23 +51,21 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 
 	greh = (struct gre_base_hdr *)skb_transport_header(skb);
 
-	if (greh->flags & GRE_KEY)
-		ghl += GRE_HEADER_SECTION;
-	if (greh->flags & GRE_SEQ)
-		ghl += GRE_HEADER_SECTION;
-	if (greh->flags & GRE_CSUM) {
-		ghl += GRE_HEADER_SECTION;
-		csum = true;
-	} else
-		csum = false;
+	ghl = skb_inner_network_header(skb) - skb_transport_header(skb);
+	if (unlikely(ghl < sizeof(*greh)))
+		goto out;
 
-	/* setup inner skb. */
-	skb->protocol = greh->protocol;
-	skb->encapsulation = 0;
+	csum = !!(greh->flags & GRE_CSUM);
+	if (csum)
+		skb->encap_hdr_csum = 1;
 
 	if (unlikely(!pskb_may_pull(skb, ghl)))
 		goto out;
 
+	/* setup inner skb. */
+	skb->protocol = greh->protocol;
+	skb->encapsulation = 0;
+
 	__skb_pull(skb, ghl);
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, skb_inner_network_offset(skb));
@@ -73,8 +74,10 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	/* segment inner packet. */
 	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
 	segs = skb_mac_gso_segment(skb, enc_features);
-	if (!segs || IS_ERR(segs))
+	if (!segs || IS_ERR(segs)) {
+		skb_gso_error_unwind(skb, protocol, ghl, mac_offset, mac_len);
 		goto out;
+	}
 
 	skb = segs;
 	tnl_hlen = skb_tnl_header_len(skb);
@@ -94,10 +97,13 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				}
 			}
 
-			greh = (struct gre_base_hdr *)(skb->data);
+			skb_reset_transport_header(skb);
+
+			greh = (struct gre_base_hdr *)
+			    skb_transport_header(skb);
 			pcsum = (__be32 *)(greh + 1);
 			*pcsum = 0;
-			*(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0));
+			*(__sum16 *)pcsum = gso_make_checksum(skb, 0);
 		}
 		__skb_push(skb, tnl_hlen - ghl);
 
@@ -113,19 +119,180 @@ out:
 	return segs;
 }
 
+/* Compute the whole skb csum in s/w and store it, then verify GRO csum
+ * starting from gro_offset.
+ */
+static __sum16 gro_skb_checksum(struct sk_buff *skb)
+{
+	__sum16 sum;
+
+	skb->csum = skb_checksum(skb, 0, skb->len, 0);
+	NAPI_GRO_CB(skb)->csum = csum_sub(skb->csum,
+		csum_partial(skb->data, skb_gro_offset(skb), 0));
+	sum = csum_fold(NAPI_GRO_CB(skb)->csum);
+	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) {
+		if (unlikely(!sum) && !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	} else {
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum_complete_sw = 1;
+	}
+
+	return sum;
+}
+
+static struct sk_buff **gre_gro_receive(struct sk_buff **head,
+					struct sk_buff *skb)
+{
+	struct sk_buff **pp = NULL;
+	struct sk_buff *p;
+	const struct gre_base_hdr *greh;
+	unsigned int hlen, grehlen;
+	unsigned int off;
+	int flush = 1;
+	struct packet_offload *ptype;
+	__be16 type;
+
+	off = skb_gro_offset(skb);
+	hlen = off + sizeof(*greh);
+	greh = skb_gro_header_fast(skb, off);
+	if (skb_gro_header_hard(skb, hlen)) {
+		greh = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!greh))
+			goto out;
+	}
+
+	/* Only support version 0 and K (key), C (csum) flags. Note that
+	 * although the support for the S (seq#) flag can be added easily
+	 * for GRO, this is problematic for GSO hence can not be enabled
+	 * here because a GRO pkt may end up in the forwarding path, thus
+	 * requiring GSO support to break it up correctly.
+	 */
+	if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0)
+		goto out;
+
+	type = greh->protocol;
+
+	rcu_read_lock();
+	ptype = gro_find_receive_by_type(type);
+	if (ptype == NULL)
+		goto out_unlock;
+
+	grehlen = GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_KEY)
+		grehlen += GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_CSUM)
+		grehlen += GRE_HEADER_SECTION;
+
+	hlen = off + grehlen;
+	if (skb_gro_header_hard(skb, hlen)) {
+		greh = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!greh))
+			goto out_unlock;
+	}
+	if (greh->flags & GRE_CSUM) { /* Need to verify GRE csum first */
+		__sum16 csum = 0;
+
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			csum = csum_fold(NAPI_GRO_CB(skb)->csum);
+		/* Don't trust csum error calculated/reported by h/w */
+		if (skb->ip_summed == CHECKSUM_NONE || csum != 0)
+			csum = gro_skb_checksum(skb);
+
+		/* GRE CSUM is the 1's complement of the 1's complement sum
+		 * of the GRE hdr plus payload so it should add up to 0xffff
+		 * (and 0 after csum_fold()) just like the IPv4 hdr csum.
+		 */
+		if (csum)
+			goto out_unlock;
+	}
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		const struct gre_base_hdr *greh2;
+
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		/* The following checks are needed to ensure only pkts
+		 * from the same tunnel are considered for aggregation.
+		 * The criteria for "the same tunnel" includes:
+		 * 1) same version (we only support version 0 here)
+		 * 2) same protocol (we only support ETH_P_IP for now)
+		 * 3) same set of flags
+		 * 4) same key if the key field is present.
+		 */
+		greh2 = (struct gre_base_hdr *)(p->data + off);
+
+		if (greh2->flags != greh->flags ||
+		    greh2->protocol != greh->protocol) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+		if (greh->flags & GRE_KEY) {
+			/* compare keys */
+			if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) {
+				NAPI_GRO_CB(p)->same_flow = 0;
+				continue;
+			}
+		}
+	}
+
+	skb_gro_pull(skb, grehlen);
+
+	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
+	skb_gro_postpull_rcsum(skb, greh, grehlen);
+
+	pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+
+static int gre_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff);
+	struct packet_offload *ptype;
+	unsigned int grehlen = sizeof(*greh);
+	int err = -ENOENT;
+	__be16 type;
+
+	skb->encapsulation = 1;
+	skb_shinfo(skb)->gso_type = SKB_GSO_GRE;
+
+	type = greh->protocol;
+	if (greh->flags & GRE_KEY)
+		grehlen += GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_CSUM)
+		grehlen += GRE_HEADER_SECTION;
+
+	rcu_read_lock();
+	ptype = gro_find_complete_by_type(type);
+	if (ptype != NULL)
+		err = ptype->callbacks.gro_complete(skb, nhoff + grehlen);
+
+	rcu_read_unlock();
+	return err;
+}
+
 static const struct net_offload gre_offload = {
 	.callbacks = {
 		.gso_send_check = gre_gso_send_check,
 		.gso_segment = gre_gso_segment,
+		.gro_receive = gre_gro_receive,
+		.gro_complete = gre_gro_complete,
 	},
 };
 
-int __init gre_offload_init(void)
+static int __init gre_offload_init(void)
 {
 	return inet_add_offload(&gre_offload, IPPROTO_GRE);
 }
-
-void __exit gre_offload_exit(void)
-{
-	inet_del_offload(&gre_offload, IPPROTO_GRE);
-}
+device_initcall(gre_offload_init);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 5c0e8bc6e5b..42b7bcf8045 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -337,6 +337,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	struct sock *sk;
 	struct inet_sock *inet;
 	__be32 daddr, saddr;
+	u32 mark = IP4_REPLY_MARK(net, skb->mark);
 
 	if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb))
 		return;
@@ -349,6 +350,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	icmp_param->data.icmph.checksum = 0;
 
 	inet->tos = ip_hdr(skb)->tos;
+	sk->sk_mark = mark;
 	daddr = ipc.addr = ip_hdr(skb)->saddr;
 	saddr = fib_compute_spec_dst(skb);
 	ipc.opt = NULL;
@@ -364,6 +366,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
+	fl4.flowi4_mark = mark;
 	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 	fl4.flowi4_proto = IPPROTO_ICMP;
 	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
@@ -382,7 +385,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 					struct flowi4 *fl4,
 					struct sk_buff *skb_in,
 					const struct iphdr *iph,
-					__be32 saddr, u8 tos,
+					__be32 saddr, u8 tos, u32 mark,
 					int type, int code,
 					struct icmp_bxm *param)
 {
@@ -394,6 +397,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->daddr = (param->replyopts.opt.opt.srr ?
 		      param->replyopts.opt.opt.faddr : iph->saddr);
 	fl4->saddr = saddr;
+	fl4->flowi4_mark = mark;
 	fl4->flowi4_tos = RT_TOS(tos);
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;
@@ -491,6 +495,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	struct flowi4 fl4;
 	__be32 saddr;
 	u8  tos;
+	u32 mark;
 	struct net *net;
 	struct sock *sk;
 
@@ -592,6 +597,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
 					   IPTOS_PREC_INTERNETCONTROL) :
 					  iph->tos;
+	mark = IP4_REPLY_MARK(net, skb_in->mark);
 
 	if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb_in))
 		goto out_unlock;
@@ -608,13 +614,14 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	icmp_param->skb	  = skb_in;
 	icmp_param->offset = skb_network_offset(skb_in);
 	inet_sk(sk)->tos = tos;
+	sk->sk_mark = mark;
 	ipc.addr = iph->saddr;
 	ipc.opt = &icmp_param->replyopts.opt;
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
 
-	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
+	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
 			       type, code, icmp_param);
 	if (IS_ERR(rt))
 		goto out_unlock;
@@ -668,6 +675,16 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
 	rcu_read_unlock();
 }
 
+static bool icmp_tag_validation(int proto)
+{
+	bool ok;
+
+	rcu_read_lock();
+	ok = rcu_dereference(inet_protos[proto])->icmp_strict_tag_validation;
+	rcu_read_unlock();
+	return ok;
+}
+
 /*
  *	Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and
  *	ICMP_PARAMETERPROB.
@@ -705,13 +722,23 @@ static void icmp_unreach(struct sk_buff *skb)
 		case ICMP_PORT_UNREACH:
 			break;
 		case ICMP_FRAG_NEEDED:
-			if (ipv4_config.no_pmtu_disc) {
+			/* for documentation of the ip_no_pmtu_disc
+			 * values please see
+			 * Documentation/networking/ip-sysctl.txt
+			 */
+			switch (net->ipv4.sysctl_ip_no_pmtu_disc) {
+			default:
 				LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"),
 					       &iph->daddr);
-			} else {
-				info = ntohs(icmph->un.frag.mtu);
-				if (!info)
+				break;
+			case 2:
+				goto out;
+			case 3:
+				if (!icmp_tag_validation(iph->protocol))
 					goto out;
+				/* fall through */
+			case 0:
+				info = ntohs(icmph->un.frag.mtu);
 			}
 			break;
 		case ICMP_SR_FAILED:
@@ -886,16 +913,8 @@ int icmp_rcv(struct sk_buff *skb)
 
 	ICMP_INC_STATS_BH(net, ICMP_MIB_INMSGS);
 
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (!csum_fold(skb->csum))
-			break;
-		/* fall through */
-	case CHECKSUM_NONE:
-		skb->csum = 0;
-		if (__skb_checksum_complete(skb))
-			goto csum_error;
-	}
+	if (skb_checksum_simple_validate(skb))
+		goto csum_error;
 
 	if (!pskb_pull(skb, sizeof(*icmph)))
 		goto error;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 7defdc9ba16..db710b059ba 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -211,7 +211,7 @@ static void igmp_stop_timer(struct ip_mc_list *im)
 /* It must be called with locked im->lock */
 static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
 {
-	int tv = net_random() % max_delay;
+	int tv = prandom_u32() % max_delay;
 
 	im->tm_running = 1;
 	if (!mod_timer(&im->timer, jiffies+tv+2))
@@ -220,7 +220,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
 
 static void igmp_gq_start_timer(struct in_device *in_dev)
 {
-	int tv = net_random() % in_dev->mr_maxdelay;
+	int tv = prandom_u32() % in_dev->mr_maxdelay;
 
 	in_dev->mr_gq_running = 1;
 	if (!mod_timer(&in_dev->mr_gq_timer, jiffies+tv+2))
@@ -229,7 +229,7 @@ static void igmp_gq_start_timer(struct in_device *in_dev)
 
 static void igmp_ifc_start_timer(struct in_device *in_dev, int delay)
 {
-	int tv = net_random() % delay;
+	int tv = prandom_u32() % delay;
 
 	if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2))
 		in_dev_hold(in_dev);
@@ -310,7 +310,7 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
 	struct ip_sf_list *psf;
 	int scount = 0;
 
-	for (psf=pmc->sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->sources; psf; psf = psf->sf_next) {
 		if (!is_in(pmc, psf, type, gdeleted, sdeleted))
 			continue;
 		scount++;
@@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	pip->saddr    = fl4.saddr;
 	pip->protocol = IPPROTO_IGMP;
 	pip->tot_len  = 0;	/* filled in later */
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	((u8 *)&pip[1])[0] = IPOPT_RA;
 	((u8 *)&pip[1])[1] = 4;
 	((u8 *)&pip[1])[2] = 0;
@@ -463,7 +463,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 	}
 	first = 1;
 	psf_prev = NULL;
-	for (psf=*psf_list; psf; psf=psf_next) {
+	for (psf = *psf_list; psf; psf = psf_next) {
 		__be32 *psrc;
 
 		psf_next = psf->sf_next;
@@ -520,7 +520,7 @@ empty_source:
 			return skb;
 		if (pmc->crcount || isquery) {
 			/* make sure we have room for group header */
-			if (skb && AVAILABLE(skb)<sizeof(struct igmpv3_grec)) {
+			if (skb && AVAILABLE(skb) < sizeof(struct igmpv3_grec)) {
 				igmpv3_sendpack(skb);
 				skb = NULL; /* add_grhead will get a new one */
 			}
@@ -576,7 +576,7 @@ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf)
 	struct ip_sf_list *psf_prev, *psf_next, *psf;
 
 	psf_prev = NULL;
-	for (psf=*ppsf; psf; psf = psf_next) {
+	for (psf = *ppsf; psf; psf = psf_next) {
 		psf_next = psf->sf_next;
 		if (psf->sf_crcount == 0) {
 			if (psf_prev)
@@ -600,7 +600,7 @@ static void igmpv3_send_cr(struct in_device *in_dev)
 
 	/* deleted MCA's */
 	pmc_prev = NULL;
-	for (pmc=in_dev->mc_tomb; pmc; pmc=pmc_next) {
+	for (pmc = in_dev->mc_tomb; pmc; pmc = pmc_next) {
 		pmc_next = pmc->next;
 		if (pmc->sfmode == MCAST_INCLUDE) {
 			type = IGMPV3_BLOCK_OLD_SOURCES;
@@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	iph->daddr    = dst;
 	iph->saddr    = fl4.saddr;
 	iph->protocol = IPPROTO_IGMP;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	((u8 *)&iph[1])[0] = IPOPT_RA;
 	((u8 *)&iph[1])[1] = 4;
 	((u8 *)&iph[1])[2] = 0;
@@ -764,7 +764,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
 
 static void igmp_timer_expire(unsigned long data)
 {
-	struct ip_mc_list *im=(struct ip_mc_list *)data;
+	struct ip_mc_list *im = (struct ip_mc_list *)data;
 	struct in_device *in_dev = im->interface;
 
 	spin_lock(&im->lock);
@@ -794,10 +794,10 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs)
 	int i, scount;
 
 	scount = 0;
-	for (psf=pmc->sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->sources; psf; psf = psf->sf_next) {
 		if (scount == nsrcs)
 			break;
-		for (i=0; i<nsrcs; i++) {
+		for (i = 0; i < nsrcs; i++) {
 			/* skip inactive filters */
 			if (psf->sf_count[MCAST_INCLUDE] ||
 			    pmc->sfcount[MCAST_EXCLUDE] !=
@@ -825,10 +825,10 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs)
 
 	/* mark INCLUDE-mode sources */
 	scount = 0;
-	for (psf=pmc->sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->sources; psf; psf = psf->sf_next) {
 		if (scount == nsrcs)
 			break;
-		for (i=0; i<nsrcs; i++)
+		for (i = 0; i < nsrcs; i++)
 			if (srcs[i] == psf->sf_inaddr) {
 				psf->sf_gsresp = 1;
 				scount++;
@@ -988,16 +988,8 @@ int igmp_rcv(struct sk_buff *skb)
 	if (!pskb_may_pull(skb, sizeof(struct igmphdr)))
 		goto drop;
 
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (!csum_fold(skb->csum))
-			break;
-		/* fall through */
-	case CHECKSUM_NONE:
-		skb->csum = 0;
-		if (__skb_checksum_complete(skb))
-			goto drop;
-	}
+	if (skb_checksum_simple_validate(skb))
+		goto drop;
 
 	ih = igmp_hdr(skb);
 	switch (ih->type) {
@@ -1103,7 +1095,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 		pmc->tomb = im->tomb;
 		pmc->sources = im->sources;
 		im->tomb = im->sources = NULL;
-		for (psf=pmc->sources; psf; psf=psf->sf_next)
+		for (psf = pmc->sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = pmc->crcount;
 	}
 	spin_unlock_bh(&im->lock);
@@ -1121,7 +1113,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr)
 
 	spin_lock_bh(&in_dev->mc_tomb_lock);
 	pmc_prev = NULL;
-	for (pmc=in_dev->mc_tomb; pmc; pmc=pmc->next) {
+	for (pmc = in_dev->mc_tomb; pmc; pmc = pmc->next) {
 		if (pmc->multiaddr == multiaddr)
 			break;
 		pmc_prev = pmc;
@@ -1134,7 +1126,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr)
 	}
 	spin_unlock_bh(&in_dev->mc_tomb_lock);
 	if (pmc) {
-		for (psf=pmc->tomb; psf; psf=psf_next) {
+		for (psf = pmc->tomb; psf; psf = psf_next) {
 			psf_next = psf->sf_next;
 			kfree(psf);
 		}
@@ -1167,7 +1159,7 @@ static void igmpv3_clear_delrec(struct in_device *in_dev)
 		psf = pmc->tomb;
 		pmc->tomb = NULL;
 		spin_unlock_bh(&pmc->lock);
-		for (; psf; psf=psf_next) {
+		for (; psf; psf = psf_next) {
 			psf_next = psf->sf_next;
 			kfree(psf);
 		}
@@ -1557,7 +1549,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
 	int rv = 0;
 
 	psf_prev = NULL;
-	for (psf=pmc->sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->sources; psf; psf = psf->sf_next) {
 		if (psf->sf_inaddr == *psfsrc)
 			break;
 		psf_prev = psf;
@@ -1630,7 +1622,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 		pmc->sfcount[sfmode]--;
 	}
 	err = 0;
-	for (i=0; i<sfcount; i++) {
+	for (i = 0; i < sfcount; i++) {
 		int rv = ip_mc_del1_src(pmc, sfmode, &psfsrc[i]);
 
 		changerec |= rv > 0;
@@ -1650,7 +1642,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 		pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
 			IGMP_Unsolicited_Report_Count;
 		in_dev->mr_ifc_count = pmc->crcount;
-		for (psf=pmc->sources; psf; psf = psf->sf_next)
+		for (psf = pmc->sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = 0;
 		igmp_ifc_event(pmc->interface);
 	} else if (sf_setstate(pmc) || changerec) {
@@ -1671,7 +1663,7 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode,
 	struct ip_sf_list *psf, *psf_prev;
 
 	psf_prev = NULL;
-	for (psf=pmc->sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->sources; psf; psf = psf->sf_next) {
 		if (psf->sf_inaddr == *psfsrc)
 			break;
 		psf_prev = psf;
@@ -1699,7 +1691,7 @@ static void sf_markstate(struct ip_mc_list *pmc)
 	struct ip_sf_list *psf;
 	int mca_xcount = pmc->sfcount[MCAST_EXCLUDE];
 
-	for (psf=pmc->sources; psf; psf=psf->sf_next)
+	for (psf = pmc->sources; psf; psf = psf->sf_next)
 		if (pmc->sfcount[MCAST_EXCLUDE]) {
 			psf->sf_oldin = mca_xcount ==
 				psf->sf_count[MCAST_EXCLUDE] &&
@@ -1716,7 +1708,7 @@ static int sf_setstate(struct ip_mc_list *pmc)
 	int new_in, rv;
 
 	rv = 0;
-	for (psf=pmc->sources; psf; psf=psf->sf_next) {
+	for (psf = pmc->sources; psf; psf = psf->sf_next) {
 		if (pmc->sfcount[MCAST_EXCLUDE]) {
 			new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] &&
 				!psf->sf_count[MCAST_INCLUDE];
@@ -1726,7 +1718,7 @@ static int sf_setstate(struct ip_mc_list *pmc)
 			if (!psf->sf_oldin) {
 				struct ip_sf_list *prev = NULL;
 
-				for (dpsf=pmc->tomb; dpsf; dpsf=dpsf->sf_next) {
+				for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) {
 					if (dpsf->sf_inaddr == psf->sf_inaddr)
 						break;
 					prev = dpsf;
@@ -1748,7 +1740,7 @@ static int sf_setstate(struct ip_mc_list *pmc)
 			 * add or update "delete" records if an active filter
 			 * is now inactive
 			 */
-			for (dpsf=pmc->tomb; dpsf; dpsf=dpsf->sf_next)
+			for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next)
 				if (dpsf->sf_inaddr == psf->sf_inaddr)
 					break;
 			if (!dpsf) {
@@ -1800,7 +1792,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 	if (!delta)
 		pmc->sfcount[sfmode]++;
 	err = 0;
-	for (i=0; i<sfcount; i++) {
+	for (i = 0; i < sfcount; i++) {
 		err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]);
 		if (err)
 			break;
@@ -1810,7 +1802,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 
 		if (!delta)
 			pmc->sfcount[sfmode]--;
-		for (j=0; j<i; j++)
+		for (j = 0; j < i; j++)
 			(void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]);
 	} else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) {
 #ifdef CONFIG_IP_MULTICAST
@@ -1829,7 +1821,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 		pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
 			IGMP_Unsolicited_Report_Count;
 		in_dev->mr_ifc_count = pmc->crcount;
-		for (psf=pmc->sources; psf; psf = psf->sf_next)
+		for (psf = pmc->sources; psf; psf = psf->sf_next)
 			psf->sf_crcount = 0;
 		igmp_ifc_event(in_dev);
 	} else if (sf_setstate(pmc)) {
@@ -1844,12 +1836,12 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc)
 {
 	struct ip_sf_list *psf, *nextpsf;
 
-	for (psf=pmc->tomb; psf; psf=nextpsf) {
+	for (psf = pmc->tomb; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
 	pmc->tomb = NULL;
-	for (psf=pmc->sources; psf; psf=nextpsf) {
+	for (psf = pmc->sources; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
@@ -1952,6 +1944,10 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 
 	rtnl_lock();
 	in_dev = ip_mc_find_dev(net, imr);
+	if (!in_dev) {
+		ret = -ENODEV;
+		goto out;
+	}
 	ifindex = imr->imr_ifindex;
 	for (imlp = &inet->mc_list;
 	     (iml = rtnl_dereference(*imlp)) != NULL;
@@ -1969,16 +1965,14 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 
 		*imlp = iml->next_rcu;
 
-		if (in_dev)
-			ip_mc_dec_group(in_dev, group);
+		ip_mc_dec_group(in_dev, group);
 		rtnl_unlock();
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
 		kfree_rcu(iml, rcu);
 		return 0;
 	}
-	if (!in_dev)
-		ret = -ENODEV;
+out:
 	rtnl_unlock();
 	return ret;
 }
@@ -2043,7 +2037,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 		if (!psl)
 			goto done;	/* err = -EADDRNOTAVAIL */
 		rv = !0;
-		for (i=0; i<psl->sl_count; i++) {
+		for (i = 0; i < psl->sl_count; i++) {
 			rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr,
 				sizeof(__be32));
 			if (rv == 0)
@@ -2062,7 +2056,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 		ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1,
 			&mreqs->imr_sourceaddr, 1);
 
-		for (j=i+1; j<psl->sl_count; j++)
+		for (j = i+1; j < psl->sl_count; j++)
 			psl->sl_addr[j-1] = psl->sl_addr[j];
 		psl->sl_count--;
 		err = 0;
@@ -2088,7 +2082,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 		newpsl->sl_max = count;
 		newpsl->sl_count = count - IP_SFBLOCK;
 		if (psl) {
-			for (i=0; i<psl->sl_count; i++)
+			for (i = 0; i < psl->sl_count; i++)
 				newpsl->sl_addr[i] = psl->sl_addr[i];
 			/* decrease mem now to avoid the memleak warning */
 			atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc);
@@ -2098,7 +2092,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 		psl = newpsl;
 	}
 	rv = 1;	/* > 0 for insert logic below if sl_count is 0 */
-	for (i=0; i<psl->sl_count; i++) {
+	for (i = 0; i < psl->sl_count; i++) {
 		rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr,
 			sizeof(__be32));
 		if (rv == 0)
@@ -2106,7 +2100,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
 	}
 	if (rv == 0)		/* address already there is an error */
 		goto done;
-	for (j=psl->sl_count-1; j>=i; j--)
+	for (j = psl->sl_count-1; j >= i; j--)
 		psl->sl_addr[j+1] = psl->sl_addr[j];
 	psl->sl_addr[i] = mreqs->imr_sourceaddr;
 	psl->sl_count++;
@@ -2305,7 +2299,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
 	    copy_to_user(optval, gsf, GROUP_FILTER_SIZE(0))) {
 		return -EFAULT;
 	}
-	for (i=0; i<copycount; i++) {
+	for (i = 0; i < copycount; i++) {
 		struct sockaddr_storage ss;
 
 		psin = (struct sockaddr_in *)&ss;
@@ -2350,7 +2344,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif)
 	if (!psl)
 		goto unlock;
 
-	for (i=0; i<psl->sl_count; i++) {
+	for (i = 0; i < psl->sl_count; i++) {
 		if (psl->sl_addr[i] == rmt_addr)
 			break;
 	}
@@ -2423,7 +2417,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u
 		rv = 1;
 	} else if (im) {
 		if (src_addr) {
-			for (psf=im->sources; psf; psf=psf->sf_next) {
+			for (psf = im->sources; psf; psf = psf->sf_next) {
 				if (psf->sf_inaddr == src_addr)
 					break;
 			}
@@ -2762,6 +2756,7 @@ static struct pernet_operations igmp_net_ops = {
 	.init = igmp_net_init,
 	.exit = igmp_net_exit,
 };
+#endif
 
 static int igmp_netdev_event(struct notifier_block *this,
 			     unsigned long event, void *ptr)
@@ -2785,8 +2780,9 @@ static struct notifier_block igmp_notifier = {
 	.notifier_call = igmp_netdev_event,
 };
 
-int __init igmp_mc_proc_init(void)
+int __init igmp_mc_init(void)
 {
+#if defined(CONFIG_PROC_FS)
 	int err;
 
 	err = register_pernet_subsys(&igmp_net_ops);
@@ -2800,5 +2796,7 @@ int __init igmp_mc_proc_init(void)
 reg_notif_fail:
 	unregister_pernet_subsys(&igmp_net_ops);
 	return err;
-}
+#else
+	return register_netdevice_notifier(&igmp_notifier);
 #endif
+}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index fc0e649cc00..14d02ea905b 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -29,19 +29,16 @@ const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
 EXPORT_SYMBOL(inet_csk_timer_bug_msg);
 #endif
 
-unsigned long *sysctl_local_reserved_ports;
-EXPORT_SYMBOL(sysctl_local_reserved_ports);
-
 void inet_get_local_port_range(struct net *net, int *low, int *high)
 {
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
 
-		*low = net->ipv4.sysctl_local_ports.range[0];
-		*high = net->ipv4.sysctl_local_ports.range[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+		*low = net->ipv4.ip_local_ports.range[0];
+		*high = net->ipv4.ip_local_ports.range[1];
+	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
 }
 EXPORT_SYMBOL(inet_get_local_port_range);
 
@@ -109,11 +106,11 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 again:
 		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
-		smallest_rover = rover = net_random() % remaining + low;
+		smallest_rover = rover = prandom_u32() % remaining + low;
 
 		smallest_size = -1;
 		do {
-			if (inet_is_reserved_local_port(rover))
+			if (inet_is_local_reserved_port(net, rover))
 				goto next_nolock;
 			head = &hashinfo->bhash[inet_bhashfn(net, rover,
 					hashinfo->bhash_size)];
@@ -408,7 +405,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	struct net *net = sock_net(sk);
 	int flags = inet_sk_flowi_flags(sk);
 
-	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+	flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol,
 			   flags,
@@ -445,7 +442,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
 
 	rcu_read_lock();
 	opt = rcu_dereference(newinet->inet_opt);
-	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+	flowi4_init_output(fl4, sk->sk_bound_dev_if, inet_rsk(req)->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
@@ -680,6 +677,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
 		newsk->sk_write_space = sk_stream_write_space;
 
+		newsk->sk_mark = inet_rsk(req)->ir_mark;
+
 		newicsk->icsk_retransmits = 0;
 		newicsk->icsk_backoff	  = 0;
 		newicsk->icsk_probes_out  = 0;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 56a964a553d..e34dccbc4d7 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -106,6 +106,10 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 	r->id.idiag_sport = inet->inet_sport;
 	r->id.idiag_dport = inet->inet_dport;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0] = inet->inet_rcv_saddr;
 	r->id.idiag_dst[0] = inet->inet_daddr;
 
@@ -240,12 +244,19 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 
 	r->idiag_family	      = tw->tw_family;
 	r->idiag_retrans      = 0;
+
 	r->id.idiag_if	      = tw->tw_bound_dev_if;
 	sock_diag_save_cookie(tw, r->id.idiag_cookie);
+
 	r->id.idiag_sport     = tw->tw_sport;
 	r->id.idiag_dport     = tw->tw_dport;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0]    = tw->tw_rcv_saddr;
 	r->id.idiag_dst[0]    = tw->tw_daddr;
+
 	r->idiag_state	      = tw->tw_substate;
 	r->idiag_timer	      = 3;
 	r->idiag_expires      = jiffies_to_msecs(tmo);
@@ -726,8 +737,13 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 
 	r->id.idiag_sport = inet->inet_sport;
 	r->id.idiag_dport = ireq->ir_rmt_port;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0] = ireq->ir_loc_addr;
 	r->id.idiag_dst[0] = ireq->ir_rmt_addr;
+
 	r->idiag_expires = jiffies_to_msecs(tmo);
 	r->idiag_rqueue = 0;
 	r->idiag_wqueue = 0;
@@ -914,12 +930,15 @@ skip_listen_ht:
 		spin_lock_bh(lock);
 		sk_nulls_for_each(sk, node, &head->chain) {
 			int res;
+			int state;
 
 			if (!net_eq(sock_net(sk), net))
 				continue;
 			if (num < s_num)
 				goto next_normal;
-			if (!(r->idiag_states & (1 << sk->sk_state)))
+			state = (sk->sk_state == TCP_TIME_WAIT) ?
+				inet_twsk(sk)->tw_substate : sk->sk_state;
+			if (!(r->idiag_states & (1 << state)))
 				goto next_normal;
 			if (r->sdiag_family != AF_UNSPEC &&
 			    sk->sk_family != r->sdiag_family)
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index bb075fc9a14..3b01959bf4b 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -208,7 +208,7 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force)
 	}
 
 	work = frag_mem_limit(nf) - nf->low_thresh;
-	while (work > 0) {
+	while (work > 0 || force) {
 		spin_lock(&nf->lru_lock);
 
 		if (list_empty(&nf->lru_list)) {
@@ -278,9 +278,10 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
 
 	atomic_inc(&qp->refcnt);
 	hlist_add_head(&qp->list, &hb->chain);
+	inet_frag_lru_add(nf, qp);
 	spin_unlock(&hb->chain_lock);
 	read_unlock(&f->lock);
-	inet_frag_lru_add(nf, qp);
+
 	return qp;
 }
 
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 8b9cf279450..43116e8c8e1 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -274,7 +274,7 @@ struct sock *__inet_lookup_established(struct net *net,
 				  const __be32 daddr, const u16 hnum,
 				  const int dif)
 {
-	INET_ADDR_COOKIE(acookie, saddr, daddr)
+	INET_ADDR_COOKIE(acookie, saddr, daddr);
 	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
 	struct sock *sk;
 	const struct hlist_nulls_node *node;
@@ -327,7 +327,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	__be32 daddr = inet->inet_rcv_saddr;
 	__be32 saddr = inet->inet_daddr;
 	int dif = sk->sk_bound_dev_if;
-	INET_ADDR_COOKIE(acookie, saddr, daddr)
+	INET_ADDR_COOKIE(acookie, saddr, daddr);
 	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
 	struct net *net = sock_net(sk);
 	unsigned int hash = inet_ehashfn(net, daddr, lport,
@@ -500,7 +500,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		local_bh_disable();
 		for (i = 1; i <= remaining; i++) {
 			port = low + (i + offset) % remaining;
-			if (inet_is_reserved_local_port(port))
+			if (inet_is_local_reserved_port(net, port))
 				continue;
 			head = &hinfo->bhash[inet_bhashfn(net, port,
 					hinfo->bhash_size)];
diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c
index 1975f52933c..f17ea49b28f 100644
--- a/net/ipv4/inet_lro.c
+++ b/net/ipv4/inet_lro.c
@@ -230,29 +230,6 @@ static void lro_add_packet(struct net_lro_desc *lro_desc, struct sk_buff *skb,
 	lro_desc->last_skb = skb;
 }
 
-static void lro_add_frags(struct net_lro_desc *lro_desc,
-			  int len, int hlen, int truesize,
-			  struct skb_frag_struct *skb_frags,
-			  struct iphdr *iph, struct tcphdr *tcph)
-{
-	struct sk_buff *skb = lro_desc->parent;
-	int tcp_data_len = TCP_PAYLOAD_LENGTH(iph, tcph);
-
-	lro_add_common(lro_desc, iph, tcph, tcp_data_len);
-
-	skb->truesize += truesize;
-
-	skb_frags[0].page_offset += hlen;
-	skb_frag_size_sub(&skb_frags[0], hlen);
-
-	while (tcp_data_len > 0) {
-		*(lro_desc->next_frag) = *skb_frags;
-		tcp_data_len -= skb_frag_size(skb_frags);
-		lro_desc->next_frag++;
-		skb_frags++;
-		skb_shinfo(skb)->nr_frags++;
-	}
-}
 
 static int lro_check_tcp_conn(struct net_lro_desc *lro_desc,
 			      struct iphdr *iph,
@@ -371,128 +348,6 @@ out:
 	return 1;
 }
 
-
-static struct sk_buff *lro_gen_skb(struct net_lro_mgr *lro_mgr,
-				   struct skb_frag_struct *frags,
-				   int len, int true_size,
-				   void *mac_hdr,
-				   int hlen, __wsum sum,
-				   u32 ip_summed)
-{
-	struct sk_buff *skb;
-	struct skb_frag_struct *skb_frags;
-	int data_len = len;
-	int hdr_len = min(len, hlen);
-
-	skb = netdev_alloc_skb(lro_mgr->dev, hlen + lro_mgr->frag_align_pad);
-	if (!skb)
-		return NULL;
-
-	skb_reserve(skb, lro_mgr->frag_align_pad);
-	skb->len = len;
-	skb->data_len = len - hdr_len;
-	skb->truesize += true_size;
-	skb->tail += hdr_len;
-
-	memcpy(skb->data, mac_hdr, hdr_len);
-
-	skb_frags = skb_shinfo(skb)->frags;
-	while (data_len > 0) {
-		*skb_frags = *frags;
-		data_len -= skb_frag_size(frags);
-		skb_frags++;
-		frags++;
-		skb_shinfo(skb)->nr_frags++;
-	}
-
-	skb_shinfo(skb)->frags[0].page_offset += hdr_len;
-	skb_frag_size_sub(&skb_shinfo(skb)->frags[0], hdr_len);
-
-	skb->ip_summed = ip_summed;
-	skb->csum = sum;
-	skb->protocol = eth_type_trans(skb, lro_mgr->dev);
-	return skb;
-}
-
-static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr,
-					  struct skb_frag_struct *frags,
-					  int len, int true_size,
-					  void *priv, __wsum sum)
-{
-	struct net_lro_desc *lro_desc;
-	struct iphdr *iph;
-	struct tcphdr *tcph;
-	struct sk_buff *skb;
-	u64 flags;
-	void *mac_hdr;
-	int mac_hdr_len;
-	int hdr_len = LRO_MAX_PG_HLEN;
-	int vlan_hdr_len = 0;
-
-	if (!lro_mgr->get_frag_header ||
-	    lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph,
-				     (void *)&tcph, &flags, priv)) {
-		mac_hdr = skb_frag_address(frags);
-		goto out1;
-	}
-
-	if (!(flags & LRO_IPV4) || !(flags & LRO_TCP))
-		goto out1;
-
-	hdr_len = (int)((void *)(tcph) + TCP_HDR_LEN(tcph) - mac_hdr);
-	mac_hdr_len = (int)((void *)(iph) - mac_hdr);
-
-	lro_desc = lro_get_desc(lro_mgr, lro_mgr->lro_arr, iph, tcph);
-	if (!lro_desc)
-		goto out1;
-
-	if (!lro_desc->active) { /* start new lro session */
-		if (lro_tcp_ip_check(iph, tcph, len - mac_hdr_len, NULL))
-			goto out1;
-
-		skb = lro_gen_skb(lro_mgr, frags, len, true_size, mac_hdr,
-				  hdr_len, 0, lro_mgr->ip_summed_aggr);
-		if (!skb)
-			goto out;
-
-		if ((skb->protocol == htons(ETH_P_8021Q)) &&
-		    !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID))
-			vlan_hdr_len = VLAN_HLEN;
-
-		iph = (void *)(skb->data + vlan_hdr_len);
-		tcph = (void *)((u8 *)skb->data + vlan_hdr_len
-				+ IP_HDR_LEN(iph));
-
-		lro_init_desc(lro_desc, skb, iph, tcph);
-		LRO_INC_STATS(lro_mgr, aggregated);
-		return NULL;
-	}
-
-	if (lro_desc->tcp_next_seq != ntohl(tcph->seq))
-		goto out2;
-
-	if (lro_tcp_ip_check(iph, tcph, len - mac_hdr_len, lro_desc))
-		goto out2;
-
-	lro_add_frags(lro_desc, len, hdr_len, true_size, frags, iph, tcph);
-	LRO_INC_STATS(lro_mgr, aggregated);
-
-	if ((skb_shinfo(lro_desc->parent)->nr_frags >= lro_mgr->max_aggr) ||
-	    lro_desc->parent->len > (0xFFFF - lro_mgr->dev->mtu))
-		lro_flush(lro_mgr, lro_desc);
-
-	return NULL;
-
-out2: /* send aggregated packets to the stack */
-	lro_flush(lro_mgr, lro_desc);
-
-out1:  /* Original packet has to be posted to the stack */
-	skb = lro_gen_skb(lro_mgr, frags, len, true_size, mac_hdr,
-			  hdr_len, sum, lro_mgr->ip_summed);
-out:
-	return skb;
-}
-
 void lro_receive_skb(struct net_lro_mgr *lro_mgr,
 		     struct sk_buff *skb,
 		     void *priv)
@@ -506,23 +361,6 @@ void lro_receive_skb(struct net_lro_mgr *lro_mgr,
 }
 EXPORT_SYMBOL(lro_receive_skb);
 
-void lro_receive_frags(struct net_lro_mgr *lro_mgr,
-		       struct skb_frag_struct *frags,
-		       int len, int true_size, void *priv, __wsum sum)
-{
-	struct sk_buff *skb;
-
-	skb = __lro_proc_segment(lro_mgr, frags, len, true_size, priv, sum);
-	if (!skb)
-		return;
-
-	if (lro_mgr->features & LRO_F_NAPI)
-		netif_receive_skb(skb);
-	else
-		netif_rx(skb);
-}
-EXPORT_SYMBOL(lro_receive_frags);
-
 void lro_flush_all(struct net_lro_mgr *lro_mgr)
 {
 	int i;
@@ -534,14 +372,3 @@ void lro_flush_all(struct net_lro_mgr *lro_mgr)
 	}
 }
 EXPORT_SYMBOL(lro_flush_all);
-
-void lro_flush_pkt(struct net_lro_mgr *lro_mgr,
-		  struct iphdr *iph, struct tcphdr *tcph)
-{
-	struct net_lro_desc *lro_desc;
-
-	lro_desc = lro_get_desc(lro_mgr, lro_mgr->lro_arr, iph, tcph);
-	if (lro_desc->active)
-		lro_flush(lro_mgr, lro_desc);
-}
-EXPORT_SYMBOL(lro_flush_pkt);
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 33d5537881e..bd5f5928167 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -26,20 +26,7 @@
  *  Theory of operations.
  *  We keep one entry for each peer IP address.  The nodes contains long-living
  *  information about the peer which doesn't depend on routes.
- *  At this moment this information consists only of ID field for the next
- *  outgoing IP packet.  This field is incremented with each packet as encoded
- *  in inet_getid() function (include/net/inetpeer.h).
- *  At the moment of writing this notes identifier of IP packets is generated
- *  to be unpredictable using this code only for packets subjected
- *  (actually or potentially) to defragmentation.  I.e. DF packets less than
- *  PMTU in size when local fragmentation is disabled use a constant ID and do
- *  not use this code (see ip_select_ident() in include/net/ip.h).
  *
- *  Route cache entries hold references to our nodes.
- *  New cache entries get references via lookup by destination IP address in
- *  the avl tree.  The reference is grabbed only when it's needed i.e. only
- *  when we try to output IP packet which needs an unpredictable ID (see
- *  __ip_select_ident() in net/ipv4/route.c).
  *  Nodes are removed only when reference counter goes to 0.
  *  When it's happened the node may be removed when a sufficient amount of
  *  time has been passed since its last use.  The less-recently-used entry can
@@ -62,7 +49,6 @@
  *		refcnt: atomically against modifications on other CPU;
  *		   usually under some other lock to prevent node disappearing
  *		daddr: unchangeable
- *		ip_id_count: atomic value (no lock needed)
  */
 
 static struct kmem_cache *peer_cachep __read_mostly;
@@ -109,13 +95,6 @@ static inline void flush_check(struct inet_peer_base *base, int family)
 	}
 }
 
-void inetpeer_invalidate_family(int family)
-{
-	atomic_t *fp = inetpeer_seq_ptr(family);
-
-	atomic_inc(fp);
-}
-
 #define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */
 
 /* Exported for sysctl_net_ipv4.  */
@@ -127,7 +106,7 @@ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ;	/* usual time to live: 10 min
 static void inetpeer_gc_worker(struct work_struct *work)
 {
 	struct inet_peer *p, *n, *c;
-	LIST_HEAD(list);
+	struct list_head list;
 
 	spin_lock_bh(&gc_lock);
 	list_replace_init(&gc_list, &list);
@@ -227,7 +206,7 @@ static int addr_compare(const struct inetpeer_addr *a,
 	stackptr = _stack;					\
 	*stackptr++ = &_base->root;				\
 	for (u = rcu_deref_locked(_base->root, _base);		\
-	     u != peer_avl_empty; ) {				\
+	     u != peer_avl_empty;) {				\
 		int cmp = addr_compare(_daddr, &u->daddr);	\
 		if (cmp == 0)					\
 			break;					\
@@ -282,7 +261,7 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr,
 	*stackptr++ = &start->avl_left;				\
 	v = &start->avl_left;					\
 	for (u = rcu_deref_locked(*v, base);			\
-	     u->avl_right != peer_avl_empty_rcu; ) {		\
+	     u->avl_right != peer_avl_empty_rcu;) {		\
 		v = &u->avl_right;				\
 		*stackptr++ = v;				\
 		u = rcu_deref_locked(*v, base);			\
@@ -504,10 +483,6 @@ relookup:
 		p->daddr = *daddr;
 		atomic_set(&p->refcnt, 1);
 		atomic_set(&p->rid, 0);
-		atomic_set(&p->ip_id_count,
-				(daddr->family == AF_INET) ?
-					secure_ip_id(daddr->addr.a4) :
-					secure_ipv6_id(daddr->addr.a6));
 		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 		p->rate_tokens = 0;
 		/* 60*HZ is arbitrary, but chosen enough high so that the first
@@ -529,7 +504,7 @@ EXPORT_SYMBOL_GPL(inet_getpeer);
 void inet_putpeer(struct inet_peer *p)
 {
 	p->dtime = (__u32)jiffies;
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_dec(&p->refcnt);
 }
 EXPORT_SYMBOL_GPL(inet_putpeer);
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 694de3b7aeb..3a83ce5efa8 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,24 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+		skb->ignore_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
+
 static int ip_forward_finish(struct sk_buff *skb)
 {
 	struct ip_options *opt	= &(IPCB(skb)->opt);
@@ -54,10 +72,15 @@ static int ip_forward_finish(struct sk_buff *skb)
 
 int ip_forward(struct sk_buff *skb)
 {
+	u32 mtu;
 	struct iphdr *iph;	/* Our header */
 	struct rtable *rt;	/* Route we use */
 	struct ip_options *opt	= &(IPCB(skb)->opt);
 
+	/* that should never happen */
+	if (skb->pkt_type != PACKET_HOST)
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
@@ -67,9 +90,6 @@ int ip_forward(struct sk_buff *skb)
 	if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
 		return NET_RX_SUCCESS;
 
-	if (skb->pkt_type != PACKET_HOST)
-		goto drop;
-
 	skb_forward_csum(skb);
 
 	/*
@@ -88,11 +108,12 @@ int ip_forward(struct sk_buff *skb)
 	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
-	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
-		     (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+	IPCB(skb)->flags |= IPSKB_FORWARDED;
+	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
+	if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) {
 		IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-			  htonl(dst_mtu(&rt->dst)));
+			  htonl(mtu));
 		goto drop;
 	}
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 2481993a497..ed32313e307 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -232,8 +232,9 @@ static void ip_expire(unsigned long arg)
 		 * "Fragment Reassembly Timeout" message, per RFC792.
 		 */
 		if (qp->user == IP_DEFRAG_AF_PACKET ||
-		    (qp->user == IP_DEFRAG_CONNTRACK_IN &&
-		     skb_rtable(head)->rt_type != RTN_LOCAL))
+		    ((qp->user >= IP_DEFRAG_CONNTRACK_IN) &&
+		     (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) &&
+		     (skb_rtable(head)->rt_type != RTN_LOCAL)))
 			goto out_rcu_unlock;
 
 
@@ -704,7 +705,7 @@ struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 			if (ip_defrag(skb, user))
 				return NULL;
-			skb->rxhash = 0;
+			skb_clear_hash(skb);
 		}
 	}
 	return skb;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index d7aea4c5b94..9b842544aea 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -178,7 +178,7 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
 	else
 		itn = net_generic(net, ipgre_net_id);
 
-	iph = (const struct iphdr *)skb->data;
+	iph = (const struct iphdr *)(icmp_hdr(skb) + 1);
 	t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags,
 			     iph->daddr, iph->saddr, tpi->key);
 
@@ -217,6 +217,7 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
 				  iph->saddr, iph->daddr, tpi->key);
 
 	if (tunnel) {
+		skb_pop_mac_header(skb);
 		ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error);
 		return PACKET_RCVD;
 	}
@@ -277,7 +278,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 free_skb:
-	dev_kfree_skb(skb);
+	kfree_skb(skb);
 out:
 	dev->stats.tx_dropped++;
 	return NETDEV_TX_OK;
@@ -300,7 +301,7 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 free_skb:
-	dev_kfree_skb(skb);
+	kfree_skb(skb);
 out:
 	dev->stats.tx_dropped++;
 	return NETDEV_TX_OK;
@@ -409,7 +410,7 @@ static int ipgre_open(struct net_device *dev)
 		struct flowi4 fl4;
 		struct rtable *rt;
 
-		rt = ip_route_output_gre(dev_net(dev), &fl4,
+		rt = ip_route_output_gre(t->net, &fl4,
 					 t->parms.iph.daddr,
 					 t->parms.iph.saddr,
 					 t->parms.o_key,
@@ -433,7 +434,7 @@ static int ipgre_close(struct net_device *dev)
 
 	if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) {
 		struct in_device *in_dev;
-		in_dev = inetdev_by_index(dev_net(dev), t->mlink);
+		in_dev = inetdev_by_index(t->net, t->mlink);
 		if (in_dev)
 			ip_mc_dec_group(in_dev, t->parms.iph.daddr);
 	}
@@ -462,6 +463,7 @@ static const struct net_device_ops ipgre_netdev_ops = {
 static void ipgre_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &ipgre_netdev_ops;
+	dev->type		= ARPHRD_IPGRE;
 	ip_tunnel_setup(dev, ipgre_net_id);
 }
 
@@ -476,7 +478,7 @@ static void __gre_tunnel_init(struct net_device *dev)
 	dev->needed_headroom	= LL_MAX_HEADER + sizeof(struct iphdr) + 4;
 	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr) - 4;
 
-	dev->features		|= NETIF_F_NETNS_LOCAL | GRE_FEATURES;
+	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
 
 	if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) {
@@ -500,7 +502,6 @@ static int ipgre_tunnel_init(struct net_device *dev)
 	memcpy(dev->dev_addr, &iph->saddr, 4);
 	memcpy(dev->broadcast, &iph->daddr, 4);
 
-	dev->type		= ARPHRD_IPGRE;
 	dev->flags		= IFF_NOARP;
 	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
 	dev->addr_len		= 4;
@@ -648,6 +649,7 @@ static void ipgre_tap_setup(struct net_device *dev)
 {
 	ether_setup(dev);
 	dev->netdev_ops		= &gre_tap_netdev_ops;
+	dev->priv_flags 	|= IFF_LIVE_ADDR_CHANGE;
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 054a3e97d82..3d4da2c16b6 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -314,7 +314,7 @@ static int ip_rcv_finish(struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 
-	if (sysctl_ip_early_demux && !skb_dst(skb)) {
+	if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
 		const struct net_protocol *ipprot;
 		int protocol = iph->protocol;
 
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ec7264514a8..ad382499bac 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -167,7 +167,7 @@ int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb)
 		soffset -= 4;
 		if (soffset > 3) {
 			memcpy(&faddr, &start[soffset-1], 4);
-			for (soffset-=4, doffset=4; soffset > 3; soffset-=4, doffset+=4)
+			for (soffset -= 4, doffset = 4; soffset > 3; soffset -= 4, doffset += 4)
 				memcpy(&dptr[doffset-1], &start[soffset-1], 4);
 			/*
 			 * RFC1812 requires to fix illegal source routes.
@@ -227,7 +227,7 @@ void ip_options_fragment(struct sk_buff *skb)
 			continue;
 		}
 		optlen = optptr[1];
-		if (optlen<2 || optlen>l)
+		if (optlen < 2 || optlen > l)
 		  return;
 		if (!IPOPT_COPIED(*optptr))
 			memset(optptr, IPOPT_NOOP, optlen);
@@ -275,27 +275,31 @@ int ip_options_compile(struct net *net,
 
 	for (l = opt->optlen; l > 0; ) {
 		switch (*optptr) {
-		      case IPOPT_END:
-			for (optptr++, l--; l>0; optptr++, l--) {
+		case IPOPT_END:
+			for (optptr++, l--; l > 0; optptr++, l--) {
 				if (*optptr != IPOPT_END) {
 					*optptr = IPOPT_END;
 					opt->is_changed = 1;
 				}
 			}
 			goto eol;
-		      case IPOPT_NOOP:
+		case IPOPT_NOOP:
 			l--;
 			optptr++;
 			continue;
 		}
+		if (unlikely(l < 2)) {
+			pp_ptr = optptr;
+			goto error;
+		}
 		optlen = optptr[1];
-		if (optlen<2 || optlen>l) {
+		if (optlen < 2 || optlen > l) {
 			pp_ptr = optptr;
 			goto error;
 		}
 		switch (*optptr) {
-		      case IPOPT_SSRR:
-		      case IPOPT_LSRR:
+		case IPOPT_SSRR:
+		case IPOPT_LSRR:
 			if (optlen < 3) {
 				pp_ptr = optptr + 1;
 				goto error;
@@ -321,7 +325,7 @@ int ip_options_compile(struct net *net,
 			opt->is_strictroute = (optptr[0] == IPOPT_SSRR);
 			opt->srr = optptr - iph;
 			break;
-		      case IPOPT_RR:
+		case IPOPT_RR:
 			if (opt->rr) {
 				pp_ptr = optptr;
 				goto error;
@@ -349,7 +353,7 @@ int ip_options_compile(struct net *net,
 			}
 			opt->rr = optptr - iph;
 			break;
-		      case IPOPT_TIMESTAMP:
+		case IPOPT_TIMESTAMP:
 			if (opt->ts) {
 				pp_ptr = optptr;
 				goto error;
@@ -364,19 +368,19 @@ int ip_options_compile(struct net *net,
 			}
 			if (optptr[2] <= optlen) {
 				unsigned char *timeptr = NULL;
-				if (optptr[2]+3 > optptr[1]) {
+				if (optptr[2]+3 > optlen) {
 					pp_ptr = optptr + 2;
 					goto error;
 				}
 				switch (optptr[3]&0xF) {
-				      case IPOPT_TS_TSONLY:
+				case IPOPT_TS_TSONLY:
 					if (skb)
 						timeptr = &optptr[optptr[2]-1];
 					opt->ts_needtime = 1;
 					optptr[2] += 4;
 					break;
-				      case IPOPT_TS_TSANDADDR:
-					if (optptr[2]+7 > optptr[1]) {
+				case IPOPT_TS_TSANDADDR:
+					if (optptr[2]+7 > optlen) {
 						pp_ptr = optptr + 2;
 						goto error;
 					}
@@ -389,8 +393,8 @@ int ip_options_compile(struct net *net,
 					opt->ts_needtime = 1;
 					optptr[2] += 8;
 					break;
-				      case IPOPT_TS_PRESPEC:
-					if (optptr[2]+7 > optptr[1]) {
+				case IPOPT_TS_PRESPEC:
+					if (optptr[2]+7 > optlen) {
 						pp_ptr = optptr + 2;
 						goto error;
 					}
@@ -405,7 +409,7 @@ int ip_options_compile(struct net *net,
 					opt->ts_needtime = 1;
 					optptr[2] += 8;
 					break;
-				      default:
+				default:
 					if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) {
 						pp_ptr = optptr + 3;
 						goto error;
@@ -433,7 +437,7 @@ int ip_options_compile(struct net *net,
 			}
 			opt->ts = optptr - iph;
 			break;
-		      case IPOPT_RA:
+		case IPOPT_RA:
 			if (optlen < 4) {
 				pp_ptr = optptr + 1;
 				goto error;
@@ -441,7 +445,7 @@ int ip_options_compile(struct net *net,
 			if (optptr[2] == 0 && optptr[3] == 0)
 				opt->router_alert = optptr - iph;
 			break;
-		      case IPOPT_CIPSO:
+		case IPOPT_CIPSO:
 			if ((!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) || opt->cipso) {
 				pp_ptr = optptr;
 				goto error;
@@ -452,9 +456,9 @@ int ip_options_compile(struct net *net,
 				goto error;
 			}
 			break;
-		      case IPOPT_SEC:
-		      case IPOPT_SID:
-		      default:
+		case IPOPT_SEC:
+		case IPOPT_SID:
+		default:
 			if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) {
 				pp_ptr = optptr;
 				goto error;
@@ -572,7 +576,7 @@ void ip_forward_options(struct sk_buff *skb)
 
 		optptr = raw + opt->srr;
 
-		for ( srrptr=optptr[2], srrspace = optptr[1];
+		for ( srrptr = optptr[2], srrspace = optptr[1];
 		     srrptr <= srrspace;
 		     srrptr += 4
 		     ) {
@@ -628,7 +632,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 	if (rt->rt_type != RTN_LOCAL)
 		return -EINVAL;
 
-	for (srrptr=optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4) {
+	for (srrptr = optptr[2], srrspace = optptr[1]; srrptr <= srrspace; srrptr += 4) {
 		if (srrptr + 3 > srrspace) {
 			icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((opt->srr+2)<<24));
 			return -EINVAL;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 912402752f2..8d3b6b0e985 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -101,17 +101,17 @@ int __ip_local_out(struct sk_buff *skb)
 		       skb_dst(skb)->dev, dst_output);
 }
 
-int ip_local_out(struct sk_buff *skb)
+int ip_local_out_sk(struct sock *sk, struct sk_buff *skb)
 {
 	int err;
 
 	err = __ip_local_out(skb);
 	if (likely(err == 1))
-		err = dst_output(skb);
+		err = dst_output_sk(sk, skb);
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(ip_local_out);
+EXPORT_SYMBOL_GPL(ip_local_out_sk);
 
 static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
 {
@@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
 	iph->protocol = sk->sk_protocol;
-	ip_select_ident(skb, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt && opt->opt.optlen) {
 		iph->ihl += opt->opt.optlen>>2;
@@ -211,6 +211,48 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	return -EINVAL;
 }
 
+static int ip_finish_output_gso(struct sk_buff *skb)
+{
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	/* common case: locally created skb or seglen is <= mtu */
+	if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
+	      skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
+		return ip_finish_output2(skb);
+
+	/* Slowpath -  GSO segment length is exceeding the dst MTU.
+	 *
+	 * This can happen in two cases:
+	 * 1) TCP GRO packet, DF bit not set
+	 * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
+	 * from host network stack.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = ip_fragment(segs, ip_finish_output2);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
+
+	return ret;
+}
+
 static int ip_finish_output(struct sk_buff *skb)
 {
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
@@ -220,15 +262,17 @@ static int ip_finish_output(struct sk_buff *skb)
 		return dst_output(skb);
 	}
 #endif
-	if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
+	if (skb_is_gso(skb))
+		return ip_finish_output_gso(skb);
+
+	if (skb->len > ip_skb_dst_mtu(skb))
 		return ip_fragment(skb, ip_finish_output2);
-	else
-		return ip_finish_output2(skb);
+
+	return ip_finish_output2(skb);
 }
 
-int ip_mc_output(struct sk_buff *skb)
+int ip_mc_output(struct sock *sk, struct sk_buff *skb)
 {
-	struct sock *sk = skb->sk;
 	struct rtable *rt = skb_rtable(skb);
 	struct net_device *dev = rt->dst.dev;
 
@@ -287,7 +331,7 @@ int ip_mc_output(struct sk_buff *skb)
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
-int ip_output(struct sk_buff *skb)
+int ip_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb_dst(skb)->dev;
 
@@ -315,9 +359,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
 	       sizeof(fl4->saddr) + sizeof(fl4->daddr));
 }
 
-int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
+/* Note: skb->sk can be different from sk, in case of tunnels */
+int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 {
-	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
 	struct ip_options_rcu *inet_opt;
 	struct flowi4 *fl4;
@@ -371,7 +415,7 @@ packet_routed:
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
 	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
-	if (ip_dont_fragment(sk, &rt->dst) && !skb->local_df)
+	if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df)
 		iph->frag_off = htons(IP_DF);
 	else
 		iph->frag_off = 0;
@@ -386,9 +430,9 @@ packet_routed:
 		ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
 	}
 
-	ip_select_ident_more(skb, &rt->dst, sk,
-			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
 
+	/* TODO : should we use skb->sk here instead of sk ? */
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 
@@ -422,9 +466,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-	to->nf_trace = from->nf_trace;
-#endif
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	to->ipvs_property = from->ipvs_property;
 #endif
@@ -458,12 +499,13 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 	iph = ip_hdr(skb);
 
-	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) ||
+	mtu = ip_skb_dst_mtu(skb);
+	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
 		     (IPCB(skb)->frag_max_size &&
-		      IPCB(skb)->frag_max_size > dst_mtu(&rt->dst)))) {
+		      IPCB(skb)->frag_max_size > mtu))) {
 		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-			  htonl(ip_skb_dst_mtu(skb)));
+			  htonl(mtu));
 		kfree_skb(skb);
 		return -EMSGSIZE;
 	}
@@ -473,7 +515,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	 */
 
 	hlen = iph->ihl * 4;
-	mtu = dst_mtu(&rt->dst) - hlen;	/* Size of data space */
+	mtu = mtu - hlen;	/* Size of data space */
 #ifdef CONFIG_BRIDGE_NETFILTER
 	if (skb->nf_bridge)
 		mtu -= nf_bridge_mtu_reduction(skb);
@@ -823,12 +865,11 @@ static int __ip_append_data(struct sock *sk,
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
-	maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
-			 mtu : 0xFFFF;
+	maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
 
 	if (cork->length + length > maxnonfragsize - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
-			       mtu-exthdrlen);
+			       mtu - (opt ? opt->optlen : 0));
 		return -EMSGSIZE;
 	}
 
@@ -1147,11 +1188,11 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
-	maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
-			 mtu : 0xFFFF;
+	maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
 
 	if (cork->length + size > maxnonfragsize - fragheaderlen) {
-		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
+		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
+			       mtu - (opt ? opt->optlen : 0));
 		return -EMSGSIZE;
 	}
 
@@ -1308,11 +1349,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	 * to fragment the frame generated here. No matter, what transforms
 	 * how transforms change size of the packet, it will come out.
 	 */
-	if (inet->pmtudisc < IP_PMTUDISC_DO)
-		skb->local_df = 1;
+	skb->ignore_df = ip_sk_ignore_df(sk);
 
 	/* DF bit is set when we want to see DF on outgoing frames.
-	 * If local_df is set too, we still allow to fragment this frame
+	 * If ignore_df is set too, we still allow to fragment this frame
 	 * locally. */
 	if (inet->pmtudisc == IP_PMTUDISC_DO ||
 	    inet->pmtudisc == IP_PMTUDISC_PROBE ||
@@ -1338,7 +1378,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
 	ip_copy_addrs(iph, fl4);
-	ip_select_ident(skb, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt) {
 		iph->ihl += opt->optlen>>2;
@@ -1505,7 +1545,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 			daddr = replyopts.opt.opt.faddr;
 	}
 
-	flowi4_init_output(&fl4, arg->bound_dev_if, 0,
+	flowi4_init_output(&fl4, arg->bound_dev_if,
+			   IP4_REPLY_MARK(net, skb->mark),
 			   RT_TOS(arg->tos),
 			   RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
 			   ip_reply_arg_flowi_flags(arg),
@@ -1550,7 +1591,7 @@ void __init ip_init(void)
 	ip_rt_init();
 	inet_initpeers();
 
-#if defined(CONFIG_IP_MULTICAST) && defined(CONFIG_PROC_FS)
-	igmp_mc_proc_init();
+#if defined(CONFIG_IP_MULTICAST)
+	igmp_mc_init();
 #endif
 }
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index ddf32a6bc41..64741b93863 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -56,7 +56,6 @@
 /*
  *	SOL_IP control messages.
  */
-#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb))
 
 static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 {
@@ -187,7 +186,8 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(ip_cmsg_recv);
 
-int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
+int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
+		 bool allow_ipv6)
 {
 	int err, val;
 	struct cmsghdr *cmsg;
@@ -195,6 +195,22 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
 	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
 		if (!CMSG_OK(msg, cmsg))
 			return -EINVAL;
+#if defined(CONFIG_IPV6)
+		if (allow_ipv6 &&
+		    cmsg->cmsg_level == SOL_IPV6 &&
+		    cmsg->cmsg_type == IPV6_PKTINFO) {
+			struct in6_pktinfo *src_info;
+
+			if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info)))
+				return -EINVAL;
+			src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
+			if (!ipv6_addr_v4mapped(&src_info->ipi6_addr))
+				return -EINVAL;
+			ipc->oif = src_info->ipi6_ifindex;
+			ipc->addr = src_info->ipi6_addr.s6_addr32[3];
+			continue;
+		}
+#endif
 		if (cmsg->cmsg_level != SOL_IP)
 			continue;
 		switch (cmsg->cmsg_type) {
@@ -390,7 +406,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct sock_exterr_skb *serr;
 	struct sk_buff *skb, *skb2;
-	struct sockaddr_in *sin;
+	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct {
 		struct sock_extended_err ee;
 		struct sockaddr_in	 offender;
@@ -416,7 +432,6 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	sin = (struct sockaddr_in *)msg->msg_name;
 	if (sin) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
@@ -628,7 +643,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 		inet->nodefrag = val ? 1 : 0;
 		break;
 	case IP_MTU_DISCOVER:
-		if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_INTERFACE)
+		if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
 			goto e_inval;
 		inet->pmtudisc = val;
 		break;
@@ -1051,14 +1066,15 @@ e_inval:
  *
  * To support IP_CMSG_PKTINFO option, we store rt_iif and specific
  * destination in skb->cb[] before dst drop.
- * This way, receiver doesnt make cache line misses to read rtable.
+ * This way, receiver doesn't make cache line misses to read rtable.
  */
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 {
 	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
+	bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) ||
+		       ipv6_sk_rxinfo(sk);
 
-	if ((inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) &&
-	    skb_rtable(skb)) {
+	if (prepare && skb_rtable(skb)) {
 		pktinfo->ipi_ifindex = inet_iif(skb);
 		pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
 	} else {
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 90ff9570d7d..6f9de61dce5 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -40,6 +40,7 @@
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
 #include <linux/rculist.h>
+#include <linux/err.h>
 
 #include <net/sock.h>
 #include <net/ip.h>
@@ -61,57 +62,59 @@
 #include <net/ip6_route.h>
 #endif
 
-static unsigned int ip_tunnel_hash(struct ip_tunnel_net *itn,
-				   __be32 key, __be32 remote)
+static unsigned int ip_tunnel_hash(__be32 key, __be32 remote)
 {
 	return hash_32((__force u32)key ^ (__force u32)remote,
 			 IP_TNL_HASH_BITS);
 }
 
-/* Often modified stats are per cpu, other are shared (netdev->stats) */
-struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
-						struct rtnl_link_stats64 *tot)
+static void __tunnel_dst_set(struct ip_tunnel_dst *idst,
+			     struct dst_entry *dst)
 {
-	int i;
+	struct dst_entry *old_dst;
 
-	for_each_possible_cpu(i) {
-		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
-		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
-		unsigned int start;
-
-		do {
-			start = u64_stats_fetch_begin_bh(&tstats->syncp);
-			rx_packets = tstats->rx_packets;
-			tx_packets = tstats->tx_packets;
-			rx_bytes = tstats->rx_bytes;
-			tx_bytes = tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
-		tot->rx_packets += rx_packets;
-		tot->tx_packets += tx_packets;
-		tot->rx_bytes   += rx_bytes;
-		tot->tx_bytes   += tx_bytes;
-	}
+	dst_clone(dst);
+	old_dst = xchg((__force struct dst_entry **)&idst->dst, dst);
+	dst_release(old_dst);
+}
 
-	tot->multicast = dev->stats.multicast;
+static void tunnel_dst_set(struct ip_tunnel *t, struct dst_entry *dst)
+{
+	__tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst);
+}
 
-	tot->rx_crc_errors = dev->stats.rx_crc_errors;
-	tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
-	tot->rx_length_errors = dev->stats.rx_length_errors;
-	tot->rx_frame_errors = dev->stats.rx_frame_errors;
-	tot->rx_errors = dev->stats.rx_errors;
+static void tunnel_dst_reset(struct ip_tunnel *t)
+{
+	tunnel_dst_set(t, NULL);
+}
 
-	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
-	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
-	tot->tx_dropped = dev->stats.tx_dropped;
-	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
-	tot->tx_errors = dev->stats.tx_errors;
+void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
+{
+	int i;
 
-	tot->collisions  = dev->stats.collisions;
+	for_each_possible_cpu(i)
+		__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
+}
+EXPORT_SYMBOL(ip_tunnel_dst_reset_all);
 
-	return tot;
+static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
+{
+	struct dst_entry *dst;
+
+	rcu_read_lock();
+	dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst);
+	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+		dst = NULL;
+	if (dst) {
+		if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
+			tunnel_dst_reset(t);
+			dst_release(dst);
+			dst = NULL;
+		}
+	}
+	rcu_read_unlock();
+	return (struct rtable *)dst;
 }
-EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
 
 static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
 				__be16 flags, __be32 key)
@@ -146,7 +149,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 	struct ip_tunnel *t, *cand = NULL;
 	struct hlist_head *head;
 
-	hash = ip_tunnel_hash(itn, key, remote);
+	hash = ip_tunnel_hash(key, remote);
 	head = &itn->tunnels[hash];
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
@@ -166,6 +169,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (remote != t->parms.iph.daddr ||
+		    t->parms.iph.saddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
@@ -178,14 +182,15 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 			cand = t;
 	}
 
-	hash = ip_tunnel_hash(itn, key, 0);
+	hash = ip_tunnel_hash(key, 0);
 	head = &itn->tunnels[hash];
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
-		if ((local != t->parms.iph.saddr &&
-		     (local != t->parms.iph.daddr ||
-		      !ipv4_is_multicast(local))) ||
-		    !(t->dev->flags & IFF_UP))
+		if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) &&
+		    (local != t->parms.iph.daddr || !ipv4_is_multicast(local)))
+			continue;
+
+		if (!(t->dev->flags & IFF_UP))
 			continue;
 
 		if (!ip_tunnel_key_match(&t->parms, flags, key))
@@ -202,6 +207,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (t->parms.i_key != key ||
+		    t->parms.iph.saddr != 0 ||
+		    t->parms.iph.daddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
@@ -228,13 +235,17 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn,
 {
 	unsigned int h;
 	__be32 remote;
+	__be32 i_key = parms->i_key;
 
 	if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr))
 		remote = parms->iph.daddr;
 	else
 		remote = 0;
 
-	h = ip_tunnel_hash(itn, parms->i_key, remote);
+	if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI))
+		i_key = 0;
+
+	h = ip_tunnel_hash(i_key, remote);
 	return &itn->tunnels[h];
 }
 
@@ -257,6 +268,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
 	__be32 remote = parms->iph.daddr;
 	__be32 local = parms->iph.saddr;
 	__be32 key = parms->i_key;
+	__be16 flags = parms->i_flags;
 	int link = parms->link;
 	struct ip_tunnel *t = NULL;
 	struct hlist_head *head = ip_bucket(itn, parms);
@@ -264,9 +276,9 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
-		    key == t->parms.i_key &&
 		    link == t->parms.link &&
-		    type == t->dev->type)
+		    type == t->dev->type &&
+		    ip_tunnel_key_match(&t->parms, flags, key))
 			break;
 	}
 	return t;
@@ -318,11 +330,10 @@ failed:
 	return ERR_PTR(err);
 }
 
-static inline struct rtable *ip_route_output_tunnel(struct net *net,
-						    struct flowi4 *fl4,
-						    int proto,
-						    __be32 daddr, __be32 saddr,
-						    __be32 key, __u8 tos, int oif)
+static inline void init_tunnel_flow(struct flowi4 *fl4,
+				    int proto,
+				    __be32 daddr, __be32 saddr,
+				    __be32 key, __u8 tos, int oif)
 {
 	memset(fl4, 0, sizeof(*fl4));
 	fl4->flowi4_oif = oif;
@@ -331,7 +342,6 @@ static inline struct rtable *ip_route_output_tunnel(struct net *net,
 	fl4->flowi4_tos = tos;
 	fl4->flowi4_proto = proto;
 	fl4->fl4_gre_key = key;
-	return ip_route_output_key(net, fl4);
 }
 
 static int ip_tunnel_bind_dev(struct net_device *dev)
@@ -350,14 +360,14 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 		struct flowi4 fl4;
 		struct rtable *rt;
 
-		rt = ip_route_output_tunnel(tunnel->net, &fl4,
-					    tunnel->parms.iph.protocol,
-					    iph->daddr, iph->saddr,
-					    tunnel->parms.o_key,
-					    RT_TOS(iph->tos),
-					    tunnel->parms.link);
+		init_tunnel_flow(&fl4, iph->protocol, iph->daddr,
+				 iph->saddr, tunnel->parms.o_key,
+				 RT_TOS(iph->tos), tunnel->parms.link);
+		rt = ip_route_output_key(tunnel->net, &fl4);
+
 		if (!IS_ERR(rt)) {
 			tdev = rt->dst.dev;
+			tunnel_dst_set(tunnel, &rt->dst);
 			ip_rt_put(rt);
 		}
 		if (dev->type != ARPHRD_ETHER)
@@ -386,14 +396,13 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 					  struct ip_tunnel_net *itn,
 					  struct ip_tunnel_parm *parms)
 {
-	struct ip_tunnel *nt, *fbt;
+	struct ip_tunnel *nt;
 	struct net_device *dev;
 
 	BUG_ON(!itn->fb_tunnel_dev);
-	fbt = netdev_priv(itn->fb_tunnel_dev);
 	dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
 	if (IS_ERR(dev))
-		return NULL;
+		return ERR_CAST(dev);
 
 	dev->mtu = ip_tunnel_bind_dev(dev);
 
@@ -405,15 +414,12 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  const struct tnl_ptk_info *tpi, bool log_ecn_error)
 {
-	struct pcpu_tstats *tstats;
+	struct pcpu_sw_netstats *tstats;
 	const struct iphdr *iph = ip_hdr(skb);
 	int err;
 
 #ifdef CONFIG_NET_IPGRE_BROADCAST
 	if (ipv4_is_multicast(iph->daddr)) {
-		/* Looped back packet, drop it! */
-		if (rt_is_output_route(skb_rtable(skb)))
-			goto drop;
 		tunnel->dev->stats.multicast++;
 		skb->pkt_type = PACKET_BROADCAST;
 	}
@@ -436,6 +442,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		tunnel->i_seqno = ntohl(tpi->seq) + 1;
 	}
 
+	skb_reset_network_header(skb);
+
 	err = IP_ECN_decapsulate(iph, skb);
 	if (unlikely(err)) {
 		if (log_ecn_error)
@@ -532,8 +540,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	unsigned int max_headroom;	/* The extra header space needed */
 	__be32 dst;
 	int err;
+	bool connected;
 
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+	connected = (tunnel->parms.iph.daddr != 0);
 
 	dst = tnl_params->daddr;
 	if (dst == 0) {
@@ -581,27 +591,38 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 #endif
 		else
 			goto tx_error;
+
+		connected = false;
 	}
 
 	tos = tnl_params->tos;
 	if (tos & 0x1) {
 		tos &= ~0x1;
-		if (skb->protocol == htons(ETH_P_IP))
+		if (skb->protocol == htons(ETH_P_IP)) {
 			tos = inner_iph->tos;
-		else if (skb->protocol == htons(ETH_P_IPV6))
+			connected = false;
+		} else if (skb->protocol == htons(ETH_P_IPV6)) {
 			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
+			connected = false;
+		}
 	}
 
-	rt = ip_route_output_tunnel(tunnel->net, &fl4,
-				    protocol,
-				    dst, tnl_params->saddr,
-				    tunnel->parms.o_key,
-				    RT_TOS(tos),
-				    tunnel->parms.link);
-	if (IS_ERR(rt)) {
-		dev->stats.tx_carrier_errors++;
-		goto tx_error;
+	init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
+			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
+
+	rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL;
+
+	if (!rt) {
+		rt = ip_route_output_key(tunnel->net, &fl4);
+
+		if (IS_ERR(rt)) {
+			dev->stats.tx_carrier_errors++;
+			goto tx_error;
+		}
+		if (connected)
+			tunnel_dst_set(tunnel, &rt->dst);
 	}
+
 	if (rt->dst.dev == dev) {
 		ip_rt_put(rt);
 		dev->stats.collisions++;
@@ -618,6 +639,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
 			tunnel->err_count--;
 
+			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			dst_link_failure(skb);
 		} else
 			tunnel->err_count = 0;
@@ -646,12 +668,13 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		dev->needed_headroom = max_headroom;
 
 	if (skb_cow_head(skb, dev->needed_headroom)) {
+		ip_rt_put(rt);
 		dev->stats.tx_dropped++;
-		dev_kfree_skb(skb);
+		kfree_skb(skb);
 		return;
 	}
 
-	err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, protocol,
+	err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, protocol,
 			    tos, ttl, df, !net_eq(tunnel->net, dev_net(dev)));
 	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 
@@ -663,7 +686,7 @@ tx_error_icmp:
 #endif
 tx_error:
 	dev->stats.tx_errors++;
-	dev_kfree_skb(skb);
+	kfree_skb(skb);
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_xmit);
 
@@ -696,25 +719,25 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
 		if (set_mtu)
 			dev->mtu = mtu;
 	}
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(dev);
 }
 
 int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 {
 	int err = 0;
-	struct ip_tunnel *t;
-	struct net *net = dev_net(dev);
-	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
+	struct ip_tunnel *t = netdev_priv(dev);
+	struct net *net = t->net;
+	struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id);
 
 	BUG_ON(!itn->fb_tunnel_dev);
 	switch (cmd) {
 	case SIOCGETTUNNEL:
-		t = NULL;
-		if (dev == itn->fb_tunnel_dev)
+		if (dev == itn->fb_tunnel_dev) {
 			t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
-		if (t == NULL)
-			t = netdev_priv(dev);
+			if (t == NULL)
+				t = netdev_priv(dev);
+		}
 		memcpy(p, &t->parms, sizeof(*p));
 		break;
 
@@ -725,16 +748,20 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 			goto done;
 		if (p->iph.ttl)
 			p->iph.frag_off |= htons(IP_DF);
-		if (!(p->i_flags&TUNNEL_KEY))
-			p->i_key = 0;
-		if (!(p->o_flags&TUNNEL_KEY))
-			p->o_key = 0;
+		if (!(p->i_flags & VTI_ISVTI)) {
+			if (!(p->i_flags & TUNNEL_KEY))
+				p->i_key = 0;
+			if (!(p->o_flags & TUNNEL_KEY))
+				p->o_key = 0;
+		}
 
 		t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
 
-		if (!t && (cmd == SIOCADDTUNNEL))
+		if (!t && (cmd == SIOCADDTUNNEL)) {
 			t = ip_tunnel_create(net, itn, p);
-
+			err = PTR_ERR_OR_ZERO(t);
+			break;
+		}
 		if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
 			if (t != NULL) {
 				if (t->dev != dev) {
@@ -761,8 +788,9 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 		if (t) {
 			err = 0;
 			ip_tunnel_update(itn, t, dev, p, true);
-		} else
-			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
+		} else {
+			err = -ENOENT;
+		}
 		break;
 
 	case SIOCDELTUNNEL:
@@ -811,6 +839,7 @@ static void ip_tunnel_dev_free(struct net_device *dev)
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 
 	gro_cells_destroy(&tunnel->gro_cells);
+	free_percpu(tunnel->dst_cache);
 	free_percpu(dev->tstats);
 	free_netdev(dev);
 }
@@ -855,11 +884,12 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 	 */
 	if (!IS_ERR(itn->fb_tunnel_dev)) {
 		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
 		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
 	}
 	rtnl_unlock();
 
-	return PTR_RET(itn->fb_tunnel_dev);
+	return PTR_ERR_OR_ZERO(itn->fb_tunnel_dev);
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
 
@@ -976,21 +1006,22 @@ int ip_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
-	int i, err;
+	int err;
 
 	dev->destructor	= ip_tunnel_dev_free;
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_tstats *ipt_stats;
-		ipt_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ipt_stats->syncp);
+	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+	if (!tunnel->dst_cache) {
+		free_percpu(dev->tstats);
+		return -ENOMEM;
 	}
 
 	err = gro_cells_init(&tunnel->gro_cells, dev);
 	if (err) {
+		free_percpu(tunnel->dst_cache);
 		free_percpu(dev->tstats);
 		return err;
 	}
@@ -1015,6 +1046,8 @@ void ip_tunnel_uninit(struct net_device *dev)
 	/* fb_tunnel_dev will be unregisted in net-exit call. */
 	if (itn->fb_tunnel_dev != dev)
 		ip_tunnel_del(netdev_priv(dev));
+
+	ip_tunnel_dst_reset_all(tunnel);
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_uninit);
 
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 42ffbc8d65c..f4c987bb7e9 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -46,7 +46,7 @@
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
 
-int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
+int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 		  __be32 src, __be32 dst, __u8 proto,
 		  __u8 tos, __u8 ttl, __be16 df, bool xnet)
 {
@@ -56,7 +56,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
 
 	skb_scrub_packet(skb, xnet);
 
-	skb->rxhash = 0;
+	skb_clear_hash(skb);
 	skb_dst_set(skb, &rt->dst);
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
@@ -74,9 +74,9 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
 	iph->daddr	=	dst;
 	iph->saddr	=	src;
 	iph->ttl	=	ttl;
-	__ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
 
-	err = ip_local_out(skb);
+	err = ip_local_out_sk(sk, skb);
 	if (unlikely(net_xmit_eval(err)))
 		pkt_len = 0;
 	return pkt_len;
@@ -107,8 +107,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
 
 	nf_reset(skb);
 	secpath_reset(skb);
-	if (!skb->l4_rxhash)
-		skb->rxhash = 0;
+	skb_clear_hash_if_not_l4(skb);
 	skb_dst_drop(skb);
 	skb->vlan_tci = 0;
 	skb_set_queue_mapping(skb, 0);
@@ -136,6 +135,14 @@ struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb,
 		return skb;
 	}
 
+	/* If packet is not gso and we are resolving any partial checksum,
+	 * clear encapsulation flag. This allows setting CHECKSUM_PARTIAL
+	 * on the outer header without confusing devices that implement
+	 * NETIF_F_IP_CSUM with encapsulation.
+	 */
+	if (csum_help)
+		skb->encapsulation = 0;
+
 	if (skb->ip_summed == CHECKSUM_PARTIAL && csum_help) {
 		err = skb_checksum_help(skb);
 		if (unlikely(err))
@@ -149,3 +156,49 @@ error:
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
+
+/* Often modified stats are per cpu, other are shared (netdev->stats) */
+struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
+						struct rtnl_link_stats64 *tot)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		const struct pcpu_sw_netstats *tstats =
+						   per_cpu_ptr(dev->tstats, i);
+		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&tstats->syncp);
+			rx_packets = tstats->rx_packets;
+			tx_packets = tstats->tx_packets;
+			rx_bytes = tstats->rx_bytes;
+			tx_bytes = tstats->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
+
+		tot->rx_packets += rx_packets;
+		tot->tx_packets += tx_packets;
+		tot->rx_bytes   += rx_bytes;
+		tot->tx_bytes   += tx_bytes;
+	}
+
+	tot->multicast = dev->stats.multicast;
+
+	tot->rx_crc_errors = dev->stats.rx_crc_errors;
+	tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
+	tot->rx_length_errors = dev->stats.rx_length_errors;
+	tot->rx_frame_errors = dev->stats.rx_frame_errors;
+	tot->rx_errors = dev->stats.rx_errors;
+
+	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
+	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
+	tot->tx_dropped = dev->stats.tx_dropped;
+	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
+	tot->tx_errors = dev->stats.tx_errors;
+
+	tot->collisions  = dev->stats.collisions;
+
+	return tot;
+}
+EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 52b802a0cd8..b8960f3527f 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -34,6 +34,7 @@
 #include <linux/init.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/if_ether.h>
+#include <linux/icmpv6.h>
 
 #include <net/sock.h>
 #include <net/ip.h>
@@ -49,8 +50,8 @@ static struct rtnl_link_ops vti_link_ops __read_mostly;
 static int vti_net_id __read_mostly;
 static int vti_tunnel_init(struct net_device *dev);
 
-/* We dont digest the packet therefore let the packet pass */
-static int vti_rcv(struct sk_buff *skb)
+static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
+		     int encap_type)
 {
 	struct ip_tunnel *tunnel;
 	const struct iphdr *iph = ip_hdr(skb);
@@ -60,79 +61,120 @@ static int vti_rcv(struct sk_buff *skb)
 	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 				  iph->saddr, iph->daddr, 0);
 	if (tunnel != NULL) {
-		struct pcpu_tstats *tstats;
-		u32 oldmark = skb->mark;
-		int ret;
-
-
-		/* temporarily mark the skb with the tunnel o_key, to
-		 * only match policies with this mark.
-		 */
-		skb->mark = be32_to_cpu(tunnel->parms.o_key);
-		ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb);
-		skb->mark = oldmark;
-		if (!ret)
-			return -1;
-
-		tstats = this_cpu_ptr(tunnel->dev->tstats);
-		u64_stats_update_begin(&tstats->syncp);
-		tstats->rx_packets++;
-		tstats->rx_bytes += skb->len;
-		u64_stats_update_end(&tstats->syncp);
-
-		secpath_reset(skb);
-		skb->dev = tunnel->dev;
+		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+			goto drop;
+
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+		skb->mark = be32_to_cpu(tunnel->parms.i_key);
+
+		return xfrm_input(skb, nexthdr, spi, encap_type);
+	}
+
+	return -EINVAL;
+drop:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int vti_rcv(struct sk_buff *skb)
+{
+	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+	return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
+}
+
+static int vti_rcv_cb(struct sk_buff *skb, int err)
+{
+	unsigned short family;
+	struct net_device *dev;
+	struct pcpu_sw_netstats *tstats;
+	struct xfrm_state *x;
+	struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
+
+	if (!tunnel)
 		return 1;
+
+	dev = tunnel->dev;
+
+	if (err) {
+		dev->stats.rx_errors++;
+		dev->stats.rx_dropped++;
+
+		return 0;
 	}
 
-	return -1;
+	x = xfrm_input_state(skb);
+	family = x->inner_mode->afinfo->family;
+
+	if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+		return -EPERM;
+
+	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
+	skb->dev = dev;
+
+	tstats = this_cpu_ptr(dev->tstats);
+
+	u64_stats_update_begin(&tstats->syncp);
+	tstats->rx_packets++;
+	tstats->rx_bytes += skb->len;
+	u64_stats_update_end(&tstats->syncp);
+
+	return 0;
 }
 
-/* This function assumes it is being called from dev_queue_xmit()
- * and that skb is filled properly by that function.
- */
+static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src)
+{
+	xfrm_address_t *daddr = (xfrm_address_t *)&dst;
+	xfrm_address_t *saddr = (xfrm_address_t *)&src;
 
-static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+	/* if there is no transform then this tunnel is not functional.
+	 * Or if the xfrm is not mode tunnel.
+	 */
+	if (!x || x->props.mode != XFRM_MODE_TUNNEL ||
+	    x->props.family != AF_INET)
+		return false;
+
+	if (!dst)
+		return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET);
+
+	if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET))
+		return false;
+
+	return true;
+}
+
+static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
+			    struct flowi *fl)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct iphdr  *tiph = &tunnel->parms.iph;
-	u8     tos;
-	struct rtable *rt;		/* Route to the other host */
+	struct ip_tunnel_parm *parms = &tunnel->parms;
+	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;	/* Device to other host */
-	struct iphdr  *old_iph = ip_hdr(skb);
-	__be32 dst = tiph->daddr;
-	struct flowi4 fl4;
 	int err;
 
-	if (skb->protocol != htons(ETH_P_IP))
-		goto tx_error;
-
-	tos = old_iph->tos;
+	if (!dst) {
+		dev->stats.tx_carrier_errors++;
+		goto tx_error_icmp;
+	}
 
-	memset(&fl4, 0, sizeof(fl4));
-	flowi4_init_output(&fl4, tunnel->parms.link,
-			   be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos),
-			   RT_SCOPE_UNIVERSE,
-			   IPPROTO_IPIP, 0,
-			   dst, tiph->saddr, 0, 0);
-	rt = ip_route_output_key(dev_net(dev), &fl4);
-	if (IS_ERR(rt)) {
+	dst_hold(dst);
+	dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0);
+	if (IS_ERR(dst)) {
 		dev->stats.tx_carrier_errors++;
 		goto tx_error_icmp;
 	}
-	/* if there is no transform then this tunnel is not functional.
-	 * Or if the xfrm is not mode tunnel.
-	 */
-	if (!rt->dst.xfrm ||
-	    rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) {
+
+	if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
 		dev->stats.tx_carrier_errors++;
-		ip_rt_put(rt);
+		dst_release(dst);
 		goto tx_error_icmp;
 	}
-	tdev = rt->dst.dev;
+
+	tdev = dst->dev;
 
 	if (tdev == dev) {
-		ip_rt_put(rt);
+		dst_release(dst);
 		dev->stats.collisions++;
 		goto tx_error;
 	}
@@ -146,10 +188,8 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 			tunnel->err_count = 0;
 	}
 
-	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-	skb_dst_drop(skb);
-	skb_dst_set(skb, &rt->dst);
-	nf_reset(skb);
+	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
+	skb_dst_set(skb, dst);
 	skb->dev = skb_dst(skb)->dev;
 
 	err = dst_output(skb);
@@ -162,10 +202,102 @@ tx_error_icmp:
 	dst_link_failure(skb);
 tx_error:
 	dev->stats.tx_errors++;
-	dev_kfree_skb(skb);
+	kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
 
+/* This function assumes it is being called from dev_queue_xmit()
+ * and that skb is filled properly by that function.
+ */
+static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	struct flowi fl;
+
+	memset(&fl, 0, sizeof(fl));
+
+	skb->mark = be32_to_cpu(tunnel->parms.o_key);
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		xfrm_decode_session(skb, &fl, AF_INET);
+		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+		break;
+	case htons(ETH_P_IPV6):
+		xfrm_decode_session(skb, &fl, AF_INET6);
+		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		break;
+	default:
+		dev->stats.tx_errors++;
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
+	return vti_xmit(skb, dev, &fl);
+}
+
+static int vti4_err(struct sk_buff *skb, u32 info)
+{
+	__be32 spi;
+	__u32 mark;
+	struct xfrm_state *x;
+	struct ip_tunnel *tunnel;
+	struct ip_esp_hdr *esph;
+	struct ip_auth_hdr *ah ;
+	struct ip_comp_hdr *ipch;
+	struct net *net = dev_net(skb->dev);
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
+	int protocol = iph->protocol;
+	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+				  iph->daddr, iph->saddr, 0);
+	if (!tunnel)
+		return -1;
+
+	mark = be32_to_cpu(tunnel->parms.o_key);
+
+	switch (protocol) {
+	case IPPROTO_ESP:
+		esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
+		spi = esph->spi;
+		break;
+	case IPPROTO_AH:
+		ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
+		spi = ah->spi;
+		break;
+	case IPPROTO_COMP:
+		ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
+		spi = htonl(ntohs(ipch->cpi));
+		break;
+	default:
+		return 0;
+	}
+
+	switch (icmp_hdr(skb)->type) {
+	case ICMP_DEST_UNREACH:
+		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+			return 0;
+	case ICMP_REDIRECT:
+		break;
+	default:
+		return 0;
+	}
+
+	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
+			      spi, protocol, AF_INET);
+	if (!x)
+		return 0;
+
+	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+		ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
+	else
+		ipv4_redirect(skb, net, 0, 0, protocol, 0);
+	xfrm_state_put(x);
+
+	return 0;
+}
+
 static int
 vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
@@ -181,12 +313,19 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			return -EINVAL;
 	}
 
+	if (!(p.i_flags & GRE_KEY))
+		p.i_key = 0;
+	if (!(p.o_flags & GRE_KEY))
+		p.o_key = 0;
+
+	p.i_flags = VTI_ISVTI;
+
 	err = ip_tunnel_ioctl(dev, &p, cmd);
 	if (err)
 		return err;
 
 	if (cmd != SIOCDELTUNNEL) {
-		p.i_flags |= GRE_KEY | VTI_ISVTI;
+		p.i_flags |= GRE_KEY;
 		p.o_flags |= GRE_KEY;
 	}
 
@@ -207,6 +346,7 @@ static const struct net_device_ops vti_netdev_ops = {
 static void vti_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &vti_netdev_ops;
+	dev->type		= ARPHRD_TUNNEL;
 	ip_tunnel_setup(dev, vti_net_id);
 }
 
@@ -218,13 +358,11 @@ static int vti_tunnel_init(struct net_device *dev)
 	memcpy(dev->dev_addr, &iph->saddr, 4);
 	memcpy(dev->broadcast, &iph->daddr, 4);
 
-	dev->type		= ARPHRD_TUNNEL;
 	dev->hard_header_len	= LL_MAX_HEADER + sizeof(struct iphdr);
 	dev->mtu		= ETH_DATA_LEN;
 	dev->flags		= IFF_NOARP;
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
-	dev->features		|= NETIF_F_NETNS_LOCAL;
 	dev->features		|= NETIF_F_LLTX;
 	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
 
@@ -241,9 +379,28 @@ static void __net_init vti_fb_tunnel_init(struct net_device *dev)
 	iph->ihl		= 5;
 }
 
-static struct xfrm_tunnel_notifier vti_handler __read_mostly = {
+static struct xfrm4_protocol vti_esp4_protocol __read_mostly = {
 	.handler	=	vti_rcv,
-	.priority	=	1,
+	.input_handler	=	vti_input,
+	.cb_handler	=	vti_rcv_cb,
+	.err_handler	=	vti4_err,
+	.priority	=	100,
+};
+
+static struct xfrm4_protocol vti_ah4_protocol __read_mostly = {
+	.handler	=	vti_rcv,
+	.input_handler	=	vti_input,
+	.cb_handler	=	vti_rcv_cb,
+	.err_handler	=	vti4_err,
+	.priority	=	100,
+};
+
+static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
+	.handler	=	vti_rcv,
+	.input_handler	=	vti_input,
+	.cb_handler	=	vti_rcv_cb,
+	.err_handler	=	vti4_err,
+	.priority	=	100,
 };
 
 static int __net_init vti_init_net(struct net *net)
@@ -287,6 +444,8 @@ static void vti_netlink_parms(struct nlattr *data[],
 	if (!data)
 		return;
 
+	parms->i_flags = VTI_ISVTI;
+
 	if (data[IFLA_VTI_LINK])
 		parms->link = nla_get_u32(data[IFLA_VTI_LINK]);
 
@@ -382,10 +541,31 @@ static int __init vti_init(void)
 	err = register_pernet_device(&vti_net_ops);
 	if (err < 0)
 		return err;
-	err = xfrm4_mode_tunnel_input_register(&vti_handler);
+	err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP);
 	if (err < 0) {
 		unregister_pernet_device(&vti_net_ops);
 		pr_info("vti init: can't register tunnel\n");
+
+		return err;
+	}
+
+	err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH);
+	if (err < 0) {
+		xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
+		unregister_pernet_device(&vti_net_ops);
+		pr_info("vti init: can't register tunnel\n");
+
+		return err;
+	}
+
+	err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP);
+	if (err < 0) {
+		xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
+		xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
+		unregister_pernet_device(&vti_net_ops);
+		pr_info("vti init: can't register tunnel\n");
+
+		return err;
 	}
 
 	err = rtnl_link_register(&vti_link_ops);
@@ -395,7 +575,9 @@ static int __init vti_init(void)
 	return err;
 
 rtnl_link_failed:
-	xfrm4_mode_tunnel_input_deregister(&vti_handler);
+	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
+	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
 	unregister_pernet_device(&vti_net_ops);
 	return err;
 }
@@ -403,8 +585,13 @@ rtnl_link_failed:
 static void __exit vti_fini(void)
 {
 	rtnl_link_unregister(&vti_link_ops);
-	if (xfrm4_mode_tunnel_input_deregister(&vti_handler))
+	if (xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP))
 		pr_info("vti close: can't deregister tunnel\n");
+	if (xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH))
+		pr_info("vti close: can't deregister tunnel\n");
+	if (xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP))
+		pr_info("vti close: can't deregister tunnel\n");
+
 
 	unregister_pernet_device(&vti_net_ops);
 }
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 826be4cb482..c0855d50a3f 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -23,7 +23,7 @@
 #include <net/protocol.h>
 #include <net/sock.h>
 
-static void ipcomp4_err(struct sk_buff *skb, u32 info)
+static int ipcomp4_err(struct sk_buff *skb, u32 info)
 {
 	struct net *net = dev_net(skb->dev);
 	__be32 spi;
@@ -34,24 +34,26 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info)
 	switch (icmp_hdr(skb)->type) {
 	case ICMP_DEST_UNREACH:
 		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
-			return;
+			return 0;
 	case ICMP_REDIRECT:
 		break;
 	default:
-		return;
+		return 0;
 	}
 
 	spi = htonl(ntohs(ipch->cpi));
 	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
 			      spi, IPPROTO_COMP, AF_INET);
 	if (!x)
-		return;
+		return 0;
 
 	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
 		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
 	else
 		ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
 	xfrm_state_put(x);
+
+	return 0;
 }
 
 /* We always hold one tunnel user reference to indicate a tunnel */
@@ -147,6 +149,11 @@ out:
 	return err;
 }
 
+static int ipcomp4_rcv_cb(struct sk_buff *skb, int err)
+{
+	return 0;
+}
+
 static const struct xfrm_type ipcomp_type = {
 	.description	= "IPCOMP4",
 	.owner		= THIS_MODULE,
@@ -157,11 +164,12 @@ static const struct xfrm_type ipcomp_type = {
 	.output		= ipcomp_output
 };
 
-static const struct net_protocol ipcomp4_protocol = {
+static struct xfrm4_protocol ipcomp4_protocol = {
 	.handler	=	xfrm4_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	ipcomp4_rcv_cb,
 	.err_handler	=	ipcomp4_err,
-	.no_policy	=	1,
-	.netns_ok	=	1,
+	.priority	=	0,
 };
 
 static int __init ipcomp4_init(void)
@@ -170,7 +178,7 @@ static int __init ipcomp4_init(void)
 		pr_info("%s: can't add xfrm type\n", __func__);
 		return -EAGAIN;
 	}
-	if (inet_add_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) {
+	if (xfrm4_protocol_register(&ipcomp4_protocol, IPPROTO_COMP) < 0) {
 		pr_info("%s: can't add protocol\n", __func__);
 		xfrm_unregister_type(&ipcomp_type, AF_INET);
 		return -EAGAIN;
@@ -180,7 +188,7 @@ static int __init ipcomp4_init(void)
 
 static void __exit ipcomp4_fini(void)
 {
-	if (inet_del_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0)
+	if (xfrm4_protocol_deregister(&ipcomp4_protocol, IPPROTO_COMP) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
 	if (xfrm_unregister_type(&ipcomp_type, AF_INET) < 0)
 		pr_info("%s: can't remove xfrm type\n", __func__);
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index efa1138fa52..b3e86ea7b71 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -273,7 +273,7 @@ static int __init ic_open_devs(void)
 
 		msleep(1);
 
-		if time_before(jiffies, next_msg)
+		if (time_before(jiffies, next_msg))
 			continue;
 
 		elapsed = jiffies_to_msecs(jiffies - start);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index fe3e9f7f1f0..62eaa005e14 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -149,13 +149,13 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPIP, 0);
+				 t->parms.link, 0, IPPROTO_IPIP, 0);
 		err = 0;
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPIP, 0);
 		err = 0;
 		goto out;
@@ -228,7 +228,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 
 tx_error:
-	dev_kfree_skb(skb);
+	kfree_skb(skb);
 out:
 	dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
@@ -486,4 +486,5 @@ static void __exit ipip_fini(void)
 module_init(ipip_init);
 module_exit(ipip_fini);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ipip");
 MODULE_ALIAS_NETDEV("tunl0");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 421a24934ff..65bcaa78904 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -157,9 +157,12 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id)
 static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4,
 			   struct mr_table **mrt)
 {
-	struct ipmr_result res;
-	struct fib_lookup_arg arg = { .result = &res, };
 	int err;
+	struct ipmr_result res;
+	struct fib_lookup_arg arg = {
+		.result = &res,
+		.flags = FIB_LOOKUP_NOREF,
+	};
 
 	err = fib_rules_lookup(net->ipv4.mr_rules_ops,
 			       flowi4_to_flowi(flp4), 0, &arg);
@@ -452,7 +455,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct mr_table *mrt;
 	struct flowi4 fl4 = {
 		.flowi4_oif	= dev->ifindex,
-		.flowi4_iif	= skb->skb_iif,
+		.flowi4_iif	= skb->skb_iif ? : LOOPBACK_IFINDEX,
 		.flowi4_mark	= skb->mark,
 	};
 	int err;
@@ -481,7 +484,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->type		= ARPHRD_PIMREG;
 	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr) - 8;
 	dev->flags		= IFF_NOARP;
-	dev->netdev_ops		= &reg_vif_netdev_ops,
+	dev->netdev_ops		= &reg_vif_netdev_ops;
 	dev->destructor		= free_netdev;
 	dev->features		|= NETIF_F_NETNS_LOCAL;
 }
@@ -1660,7 +1663,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr)
 	iph->protocol	=	IPPROTO_IPIP;
 	iph->ihl	=	5;
 	iph->tot_len	=	htons(skb->len);
-	ip_select_ident(skb, skb_dst(skb), NULL);
+	ip_select_ident(skb, NULL);
 	ip_send_check(iph);
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -2252,13 +2255,14 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 }
 
 static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
-			    u32 portid, u32 seq, struct mfc_cache *c, int cmd)
+			    u32 portid, u32 seq, struct mfc_cache *c, int cmd,
+			    int flags)
 {
 	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
 	int err;
 
-	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -2326,7 +2330,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 	if (skb == NULL)
 		goto errout;
 
-	err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+	err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
 	if (err < 0)
 		goto errout;
 
@@ -2365,7 +2369,8 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 				if (ipmr_fill_mroute(mrt, skb,
 						     NETLINK_CB(cb->skb).portid,
 						     cb->nlh->nlmsg_seq,
-						     mfc, RTM_NEWROUTE) < 0)
+						     mfc, RTM_NEWROUTE,
+						     NLM_F_MULTI) < 0)
 					goto done;
 next_entry:
 				e++;
@@ -2379,7 +2384,8 @@ next_entry:
 			if (ipmr_fill_mroute(mrt, skb,
 					     NETLINK_CB(cb->skb).portid,
 					     cb->nlh->nlmsg_seq,
-					     mfc, RTM_NEWROUTE) < 0) {
+					     mfc, RTM_NEWROUTE,
+					     NLM_F_MULTI) < 0) {
 				spin_unlock_bh(&mfc_unres_lock);
 				goto done;
 			}
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index c3e0adea9c2..7ebd6e37875 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -61,7 +61,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type)
 		skb_dst_set(skb, NULL);
 		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
 		if (IS_ERR(dst))
-			return PTR_ERR(dst);;
+			return PTR_ERR(dst);
 		skb_dst_set(skb, dst);
 	}
 #endif
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 40d56073cd1..a26ce035e3f 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -39,23 +39,38 @@ config NF_CONNTRACK_PROC_COMPAT
 config NF_TABLES_IPV4
 	depends on NF_TABLES
 	tristate "IPv4 nf_tables support"
-
-config NFT_REJECT_IPV4
-	depends on NF_TABLES_IPV4
-	tristate "nf_tables IPv4 reject support"
+	help
+	  This option enables the IPv4 support for nf_tables.
 
 config NFT_CHAIN_ROUTE_IPV4
 	depends on NF_TABLES_IPV4
 	tristate "IPv4 nf_tables route chain support"
+	help
+	  This option enables the "route" chain for IPv4 in nf_tables. This
+	  chain type is used to force packet re-routing after mangling header
+	  fields such as the source, destination, type of service and
+	  the packet mark.
 
 config NFT_CHAIN_NAT_IPV4
 	depends on NF_TABLES_IPV4
 	depends on NF_NAT_IPV4 && NFT_NAT
 	tristate "IPv4 nf_tables nat chain support"
+	help
+	  This option enables the "nat" chain for IPv4 in nf_tables. This
+	  chain type is used to perform Network Address Translation (NAT)
+	  packet transformations such as the source, destination address and
+	  source and destination ports.
+
+config NFT_REJECT_IPV4
+	depends on NF_TABLES_IPV4
+	default NFT_REJECT
+	tristate
 
 config NF_TABLES_ARP
 	depends on NF_TABLES
 	tristate "ARP nf_tables support"
+	help
+	  This option enables the ARP support for nf_tables.
 
 config IP_NF_IPTABLES
 	tristate "IP tables support (required for filtering/masq/NAT)"
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 19df72b7ba8..90b82405331 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -28,9 +28,9 @@ obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
 obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
 
 obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
-obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
+obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
 obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # generic IP tables 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 59da7cde072..f95b6f93814 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1044,8 +1044,10 @@ static int __do_replace(struct net *net, const char *name,
 
 	xt_free_table_info(oldinfo);
 	if (copy_to_user(counters_ptr, counters,
-			 sizeof(struct xt_counters) * num_counters) != 0)
-		ret = -EFAULT;
+			 sizeof(struct xt_counters) * num_counters) != 0) {
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("arptables: counters copy to user failed while replacing table\n");
+	}
 	vfree(counters);
 	xt_table_unlock(t);
 	return ret;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 718dfbd30cb..99e810f8467 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1231,8 +1231,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 
 	xt_free_table_info(oldinfo);
 	if (copy_to_user(counters_ptr, counters,
-			 sizeof(struct xt_counters) * num_counters) != 0)
-		ret = -EFAULT;
+			 sizeof(struct xt_counters) * num_counters) != 0) {
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n");
+	}
 	vfree(counters);
 	xt_table_unlock(t);
 	return ret;
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index b969131ad1c..5b6e0df4ccf 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -17,10 +17,6 @@
 #include <linux/udp.h>
 #include <linux/icmp.h>
 #include <net/icmp.h>
-#include <net/ip.h>
-#include <net/tcp.h>
-#include <net/route.h>
-#include <net/dst.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_REJECT.h>
@@ -28,128 +24,12 @@
 #include <linux/netfilter_bridge.h>
 #endif
 
+#include <net/netfilter/ipv4/nf_reject.h>
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
 MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv4");
 
-/* Send RST reply */
-static void send_reset(struct sk_buff *oldskb, int hook)
-{
-	struct sk_buff *nskb;
-	const struct iphdr *oiph;
-	struct iphdr *niph;
-	const struct tcphdr *oth;
-	struct tcphdr _otcph, *tcph;
-
-	/* IP header checks: fragment. */
-	if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
-		return;
-
-	oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
-				 sizeof(_otcph), &_otcph);
-	if (oth == NULL)
-		return;
-
-	/* No RST for RST. */
-	if (oth->rst)
-		return;
-
-	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
-		return;
-
-	/* Check checksum */
-	if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
-		return;
-	oiph = ip_hdr(oldskb);
-
-	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
-			 LL_MAX_HEADER, GFP_ATOMIC);
-	if (!nskb)
-		return;
-
-	skb_reserve(nskb, LL_MAX_HEADER);
-
-	skb_reset_network_header(nskb);
-	niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
-	niph->version	= 4;
-	niph->ihl	= sizeof(struct iphdr) / 4;
-	niph->tos	= 0;
-	niph->id	= 0;
-	niph->frag_off	= htons(IP_DF);
-	niph->protocol	= IPPROTO_TCP;
-	niph->check	= 0;
-	niph->saddr	= oiph->daddr;
-	niph->daddr	= oiph->saddr;
-
-	skb_reset_transport_header(nskb);
-	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
-	memset(tcph, 0, sizeof(*tcph));
-	tcph->source	= oth->dest;
-	tcph->dest	= oth->source;
-	tcph->doff	= sizeof(struct tcphdr) / 4;
-
-	if (oth->ack)
-		tcph->seq = oth->ack_seq;
-	else {
-		tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
-				      oldskb->len - ip_hdrlen(oldskb) -
-				      (oth->doff << 2));
-		tcph->ack = 1;
-	}
-
-	tcph->rst	= 1;
-	tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
-				    niph->daddr, 0);
-	nskb->ip_summed = CHECKSUM_PARTIAL;
-	nskb->csum_start = (unsigned char *)tcph - nskb->head;
-	nskb->csum_offset = offsetof(struct tcphdr, check);
-
-	/* ip_route_me_harder expects skb->dst to be set */
-	skb_dst_set_noref(nskb, skb_dst(oldskb));
-
-	nskb->protocol = htons(ETH_P_IP);
-	if (ip_route_me_harder(nskb, RTN_UNSPEC))
-		goto free_nskb;
-
-	niph->ttl	= ip4_dst_hoplimit(skb_dst(nskb));
-
-	/* "Never happens" */
-	if (nskb->len > dst_mtu(skb_dst(nskb)))
-		goto free_nskb;
-
-	nf_ct_attach(nskb, oldskb);
-
-#ifdef CONFIG_BRIDGE_NETFILTER
-	/* If we use ip_local_out for bridged traffic, the MAC source on
-	 * the RST will be ours, instead of the destination's.  This confuses
-	 * some routers/firewalls, and they drop the packet.  So we need to
-	 * build the eth header using the original destination's MAC as the
-	 * source, and send the RST packet directly.
-	 */
-	if (oldskb->nf_bridge) {
-		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
-		niph->tot_len = htons(nskb->len);
-		ip_send_check(niph);
-		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
-				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
-			goto free_nskb;
-		dev_queue_xmit(nskb);
-	} else
-#endif
-		ip_local_out(nskb);
-
-	return;
-
- free_nskb:
-	kfree_skb(nskb);
-}
-
-static inline void send_unreach(struct sk_buff *skb_in, int code)
-{
-	icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
-}
-
 static unsigned int
 reject_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
@@ -157,28 +37,28 @@ reject_tg(struct sk_buff *skb, const struct xt_action_param *par)
 
 	switch (reject->with) {
 	case IPT_ICMP_NET_UNREACHABLE:
-		send_unreach(skb, ICMP_NET_UNREACH);
+		nf_send_unreach(skb, ICMP_NET_UNREACH);
 		break;
 	case IPT_ICMP_HOST_UNREACHABLE:
-		send_unreach(skb, ICMP_HOST_UNREACH);
+		nf_send_unreach(skb, ICMP_HOST_UNREACH);
 		break;
 	case IPT_ICMP_PROT_UNREACHABLE:
-		send_unreach(skb, ICMP_PROT_UNREACH);
+		nf_send_unreach(skb, ICMP_PROT_UNREACH);
 		break;
 	case IPT_ICMP_PORT_UNREACHABLE:
-		send_unreach(skb, ICMP_PORT_UNREACH);
+		nf_send_unreach(skb, ICMP_PORT_UNREACH);
 		break;
 	case IPT_ICMP_NET_PROHIBITED:
-		send_unreach(skb, ICMP_NET_ANO);
+		nf_send_unreach(skb, ICMP_NET_ANO);
 		break;
 	case IPT_ICMP_HOST_PROHIBITED:
-		send_unreach(skb, ICMP_HOST_ANO);
+		nf_send_unreach(skb, ICMP_HOST_ANO);
 		break;
 	case IPT_ICMP_ADMIN_PROHIBITED:
-		send_unreach(skb, ICMP_PKT_FILTERED);
+		nf_send_unreach(skb, ICMP_PKT_FILTERED);
 		break;
 	case IPT_TCP_RESET:
-		send_reset(skb, par->hooknum);
+		nf_send_reset(skb, par->hooknum);
 	case IPT_ICMP_ECHOREPLY:
 		/* Doesn't happen. */
 		break;
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index f13bd91d9a5..a313c3fbeb4 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -423,6 +423,7 @@ static void synproxy_tg4_destroy(const struct xt_tgdtor_param *par)
 static struct xt_target synproxy_tg4_reg __read_mostly = {
 	.name		= "SYNPROXY",
 	.family		= NFPROTO_IPV4,
+	.hooks		= (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD),
 	.target		= synproxy_tg4,
 	.targetsize	= sizeof(struct xt_synproxy_info),
 	.checkentry	= synproxy_tg4_check,
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index c49dcd0284a..4bfaedf9b34 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -89,11 +89,8 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	if (ipv4_is_multicast(iph->daddr)) {
 		if (ipv4_is_zeronet(iph->saddr))
 			return ipv4_is_local_multicast(iph->daddr) ^ invert;
-		flow.flowi4_iif = 0;
-	} else {
-		flow.flowi4_iif = LOOPBACK_IFINDEX;
 	}
-
+	flow.flowi4_iif = LOOPBACK_IFINDEX;
 	flow.daddr = iph->saddr;
 	flow.saddr = rpfilter_get_saddr(iph->daddr);
 	flow.flowi4_oif = 0;
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index ee2886126e3..f1787c04a4d 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -91,17 +91,9 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops,
 	if (nf_ct_is_untracked(ct))
 		return NF_ACCEPT;
 
-	nat = nfct_nat(ct);
-	if (!nat) {
-		/* NAT module was loaded late. */
-		if (nf_ct_is_confirmed(ct))
-			return NF_ACCEPT;
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL) {
-			pr_debug("failed to add NAT extension\n");
-			return NF_ACCEPT;
-		}
-	}
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index ecd8bec411c..8127dc80286 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -548,9 +548,3 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void)
 
 module_init(nf_conntrack_l3proto_ipv4_init);
 module_exit(nf_conntrack_l3proto_ipv4_fini);
-
-void need_ipv4_conntrack(void)
-{
-	return;
-}
-EXPORT_SYMBOL_GPL(need_ipv4_conntrack);
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 12e13bd82b5..b8f6381c7d0 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -22,7 +22,6 @@
 #endif
 #include <net/netfilter/nf_conntrack_zones.h>
 
-/* Returns new sk_buff, or NULL */
 static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 {
 	int err;
@@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 	err = ip_defrag(skb, user);
 	local_bh_enable();
 
-	if (!err)
+	if (!err) {
 		ip_send_check(ip_hdr(skb));
+		skb->ignore_df = 1;
+	}
 
 	return err;
 }
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index 9eea059dd62..574f7ebba0b 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -229,7 +229,10 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
 			ret = nf_ct_expect_related(rtcp_exp);
 			if (ret == 0)
 				break;
-			else if (ret != -EBUSY) {
+			else if (ret == -EBUSY) {
+				nf_ct_unexpect_related(rtp_exp);
+				continue;
+			} else if (ret < 0) {
 				nf_ct_unexpect_related(rtp_exp);
 				nated_port = 0;
 				break;
diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c
index 61a942265e8..7c676671329 100644
--- a/net/ipv4/netfilter/nf_nat_snmp_basic.c
+++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c
@@ -461,14 +461,14 @@ static unsigned char asn1_oid_decode(struct asn1_ctx *ctx,
 	}
 
 	if (subid < 40) {
-		optr [0] = 0;
-		optr [1] = subid;
+		optr[0] = 0;
+		optr[1] = subid;
 	} else if (subid < 80) {
-		optr [0] = 1;
-		optr [1] = subid - 40;
+		optr[0] = 1;
+		optr[1] = subid - 40;
 	} else {
-		optr [0] = 2;
-		optr [1] = subid - 80;
+		optr[0] = 2;
+		optr[1] = subid - 80;
 	}
 
 	*len = 2;
@@ -1198,8 +1198,8 @@ static int snmp_translate(struct nf_conn *ct,
 		map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
 	} else {
 		/* DNAT replies */
-		map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip);
-		map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip);
+		map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip);
+		map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip);
 	}
 
 	if (map.from == map.to)
diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c
index 3e67ef1c676..19412a4063f 100644
--- a/net/ipv4/netfilter/nf_tables_arp.c
+++ b/net/ipv4/netfilter/nf_tables_arp.c
@@ -14,10 +14,30 @@
 #include <linux/netfilter_arp.h>
 #include <net/netfilter/nf_tables.h>
 
+static unsigned int
+nft_do_chain_arp(const struct nf_hook_ops *ops,
+		  struct sk_buff *skb,
+		  const struct net_device *in,
+		  const struct net_device *out,
+		  int (*okfn)(struct sk_buff *))
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo(&pkt, ops, skb, in, out);
+
+	return nft_do_chain(&pkt, ops);
+}
+
 static struct nft_af_info nft_af_arp __read_mostly = {
 	.family		= NFPROTO_ARP,
 	.nhooks		= NF_ARP_NUMHOOKS,
 	.owner		= THIS_MODULE,
+	.nops		= 1,
+	.hooks		= {
+		[NF_ARP_IN]		= nft_do_chain_arp,
+		[NF_ARP_OUT]		= nft_do_chain_arp,
+		[NF_ARP_FORWARD]	= nft_do_chain_arp,
+	},
 };
 
 static int nf_tables_arp_init_net(struct net *net)
@@ -48,32 +68,14 @@ static struct pernet_operations nf_tables_arp_net_ops = {
 	.exit   = nf_tables_arp_exit_net,
 };
 
-static unsigned int
-nft_do_chain_arp(const struct nf_hook_ops *ops,
-		  struct sk_buff *skb,
-		  const struct net_device *in,
-		  const struct net_device *out,
-		  int (*okfn)(struct sk_buff *))
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo(&pkt, ops, skb, in, out);
-
-	return nft_do_chain_pktinfo(&pkt, ops);
-}
-
-static struct nf_chain_type filter_arp = {
-	.family		= NFPROTO_ARP,
+static const struct nf_chain_type filter_arp = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_ARP,
+	.owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_ARP_IN) |
 			  (1 << NF_ARP_OUT) |
 			  (1 << NF_ARP_FORWARD),
-	.fn		= {
-		[NF_ARP_IN]		= nft_do_chain_arp,
-		[NF_ARP_OUT]		= nft_do_chain_arp,
-		[NF_ARP_FORWARD]	= nft_do_chain_arp,
-	},
 };
 
 static int __init nf_tables_arp_init(void)
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
index 0f4cbfeb19b..6820c8c4084 100644
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -18,14 +18,25 @@
 #include <net/ip.h>
 #include <net/netfilter/nf_tables_ipv4.h>
 
+static unsigned int nft_do_chain_ipv4(const struct nf_hook_ops *ops,
+				      struct sk_buff *skb,
+				      const struct net_device *in,
+				      const struct net_device *out,
+				      int (*okfn)(struct sk_buff *))
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
+
+	return nft_do_chain(&pkt, ops);
+}
+
 static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
 				    struct sk_buff *skb,
 				    const struct net_device *in,
 				    const struct net_device *out,
 				    int (*okfn)(struct sk_buff *))
 {
-	struct nft_pktinfo pkt;
-
 	if (unlikely(skb->len < sizeof(struct iphdr) ||
 		     ip_hdr(skb)->ihl < sizeof(struct iphdr) / 4)) {
 		if (net_ratelimit())
@@ -33,19 +44,24 @@ static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
 				"packet\n");
 		return NF_ACCEPT;
 	}
-	nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
 
-	return nft_do_chain_pktinfo(&pkt, ops);
+	return nft_do_chain_ipv4(ops, skb, in, out, okfn);
 }
 
-static struct nft_af_info nft_af_ipv4 __read_mostly = {
+struct nft_af_info nft_af_ipv4 __read_mostly = {
 	.family		= NFPROTO_IPV4,
 	.nhooks		= NF_INET_NUMHOOKS,
 	.owner		= THIS_MODULE,
+	.nops		= 1,
 	.hooks		= {
+		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv4,
 		[NF_INET_LOCAL_OUT]	= nft_ipv4_output,
+		[NF_INET_FORWARD]	= nft_do_chain_ipv4,
+		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv4,
+		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv4,
 	},
 };
+EXPORT_SYMBOL_GPL(nft_af_ipv4);
 
 static int nf_tables_ipv4_init_net(struct net *net)
 {
@@ -75,42 +91,28 @@ static struct pernet_operations nf_tables_ipv4_net_ops = {
 	.exit	= nf_tables_ipv4_exit_net,
 };
 
-static unsigned int
-nft_do_chain_ipv4(const struct nf_hook_ops *ops,
-		  struct sk_buff *skb,
-		  const struct net_device *in,
-		  const struct net_device *out,
-		  int (*okfn)(struct sk_buff *))
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
-
-	return nft_do_chain_pktinfo(&pkt, ops);
-}
-
-static struct nf_chain_type filter_ipv4 = {
-	.family		= NFPROTO_IPV4,
+static const struct nf_chain_type filter_ipv4 = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_IPV4,
+	.owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
 			  (1 << NF_INET_LOCAL_OUT) |
 			  (1 << NF_INET_FORWARD) |
 			  (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_POST_ROUTING),
-	.fn		= {
-		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv4,
-		[NF_INET_LOCAL_OUT]	= nft_ipv4_output,
-		[NF_INET_FORWARD]	= nft_do_chain_ipv4,
-		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv4,
-		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv4,
-	},
 };
 
 static int __init nf_tables_ipv4_init(void)
 {
+	int ret;
+
 	nft_register_chain_type(&filter_ipv4);
-	return register_pernet_subsys(&nf_tables_ipv4_net_ops);
+	ret = register_pernet_subsys(&nf_tables_ipv4_net_ops);
+	if (ret < 0)
+		nft_unregister_chain_type(&filter_ipv4);
+
+	return ret;
 }
 
 static void __exit nf_tables_ipv4_exit(void)
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index cf2c792cd97..3964157d826 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -48,15 +48,9 @@ static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
 
 	NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
 
-	nat = nfct_nat(ct);
-	if (nat == NULL) {
-		/* Conntrack module was loaded late, can't add extension. */
-		if (nf_ct_is_confirmed(ct))
-			return NF_ACCEPT;
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL)
-			return NF_ACCEPT;
-	}
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
@@ -75,7 +69,7 @@ static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
 
 		nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
 
-		ret = nft_do_chain_pktinfo(&pkt, ops);
+		ret = nft_do_chain(&pkt, ops);
 		if (ret != NF_ACCEPT)
 			return ret;
 		if (!nf_nat_initialized(ct, maniptype)) {
@@ -164,21 +158,21 @@ static unsigned int nf_nat_output(const struct nf_hook_ops *ops,
 	return ret;
 }
 
-static struct nf_chain_type nft_chain_nat_ipv4 = {
-	.family		= NFPROTO_IPV4,
+static const struct nf_chain_type nft_chain_nat_ipv4 = {
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,
+	.family		= NFPROTO_IPV4,
+	.owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_POST_ROUTING) |
 			  (1 << NF_INET_LOCAL_OUT) |
 			  (1 << NF_INET_LOCAL_IN),
-	.fn		= {
+	.hooks		= {
 		[NF_INET_PRE_ROUTING]	= nf_nat_prerouting,
 		[NF_INET_POST_ROUTING]	= nf_nat_postrouting,
 		[NF_INET_LOCAL_OUT]	= nf_nat_output,
 		[NF_INET_LOCAL_IN]	= nf_nat_fn,
 	},
-	.me		= THIS_MODULE,
 };
 
 static int __init nft_chain_nat_init(void)
diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
index 4e6bf9a3d7a..125b66766c0 100644
--- a/net/ipv4/netfilter/nft_chain_route_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c
@@ -47,7 +47,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 	daddr = iph->daddr;
 	tos = iph->tos;
 
-	ret = nft_do_chain_pktinfo(&pkt, ops);
+	ret = nft_do_chain(&pkt, ops);
 	if (ret != NF_DROP && ret != NF_QUEUE) {
 		iph = ip_hdr(skb);
 
@@ -61,15 +61,15 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 	return ret;
 }
 
-static struct nf_chain_type nft_chain_route_ipv4 = {
-	.family		= NFPROTO_IPV4,
+static const struct nf_chain_type nft_chain_route_ipv4 = {
 	.name		= "route",
 	.type		= NFT_CHAIN_T_ROUTE,
+	.family		= NFPROTO_IPV4,
+	.owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_INET_LOCAL_OUT),
-	.fn		= {
+	.hooks		= {
 		[NF_INET_LOCAL_OUT]	= nf_route_table_hook,
 	},
-	.me		= THIS_MODULE,
 };
 
 static int __init nft_chain_route_init(void)
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index fff5ba1a33b..e79718a382f 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -16,108 +17,59 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/icmp.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/nft_reject.h>
 
-struct nft_reject {
-	enum nft_reject_types	type:8;
-	u8			icmp_code;
-};
-
-static void nft_reject_eval(const struct nft_expr *expr,
-			      struct nft_data data[NFT_REG_MAX + 1],
-			      const struct nft_pktinfo *pkt)
+void nft_reject_ipv4_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt)
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
 
 	switch (priv->type) {
 	case NFT_REJECT_ICMP_UNREACH:
-		icmp_send(pkt->skb, ICMP_DEST_UNREACH, priv->icmp_code, 0);
+		nf_send_unreach(pkt->skb, priv->icmp_code);
 		break;
 	case NFT_REJECT_TCP_RST:
+		nf_send_reset(pkt->skb, pkt->ops->hooknum);
 		break;
 	}
 
 	data[NFT_REG_VERDICT].verdict = NF_DROP;
 }
+EXPORT_SYMBOL_GPL(nft_reject_ipv4_eval);
 
-static const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
-	[NFTA_REJECT_TYPE]		= { .type = NLA_U32 },
-	[NFTA_REJECT_ICMP_CODE]		= { .type = NLA_U8 },
-};
-
-static int nft_reject_init(const struct nft_ctx *ctx,
-			   const struct nft_expr *expr,
-			   const struct nlattr * const tb[])
-{
-	struct nft_reject *priv = nft_expr_priv(expr);
-
-	if (tb[NFTA_REJECT_TYPE] == NULL)
-		return -EINVAL;
-
-	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
-	switch (priv->type) {
-	case NFT_REJECT_ICMP_UNREACH:
-		if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
-			return -EINVAL;
-		priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
-	case NFT_REJECT_TCP_RST:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
-{
-	const struct nft_reject *priv = nft_expr_priv(expr);
-
-	if (nla_put_be32(skb, NFTA_REJECT_TYPE, priv->type))
-		goto nla_put_failure;
-
-	switch (priv->type) {
-	case NFT_REJECT_ICMP_UNREACH:
-		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
-			goto nla_put_failure;
-		break;
-	}
-
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static struct nft_expr_type nft_reject_type;
-static const struct nft_expr_ops nft_reject_ops = {
-	.type		= &nft_reject_type,
+static struct nft_expr_type nft_reject_ipv4_type;
+static const struct nft_expr_ops nft_reject_ipv4_ops = {
+	.type		= &nft_reject_ipv4_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
-	.eval		= nft_reject_eval,
+	.eval		= nft_reject_ipv4_eval,
 	.init		= nft_reject_init,
 	.dump		= nft_reject_dump,
 };
 
-static struct nft_expr_type nft_reject_type __read_mostly = {
+static struct nft_expr_type nft_reject_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
 	.name		= "reject",
-	.ops		= &nft_reject_ops,
+	.ops		= &nft_reject_ipv4_ops,
 	.policy		= nft_reject_policy,
 	.maxattr	= NFTA_REJECT_MAX,
 	.owner		= THIS_MODULE,
 };
 
-static int __init nft_reject_module_init(void)
+static int __init nft_reject_ipv4_module_init(void)
 {
-	return nft_register_expr(&nft_reject_type);
+	return nft_register_expr(&nft_reject_ipv4_type);
 }
 
-static void __exit nft_reject_module_exit(void)
+static void __exit nft_reject_ipv4_module_exit(void)
 {
-	nft_unregister_expr(&nft_reject_type);
+	nft_unregister_expr(&nft_reject_ipv4_type);
 }
 
-module_init(nft_reject_module_init);
-module_exit(nft_reject_module_exit);
+module_init(nft_reject_ipv4_module_init);
+module_exit(nft_reject_ipv4_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_EXPR("reject");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject");
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 242e7f4ed6f..044a0ddf6a7 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -53,8 +53,12 @@
 #include <net/transp_v6.h>
 #endif
 
+struct ping_table {
+	struct hlist_nulls_head	hash[PING_HTABLE_SIZE];
+	rwlock_t		lock;
+};
 
-struct ping_table ping_table;
+static struct ping_table ping_table;
 struct pingv6_ops pingv6_ops;
 EXPORT_SYMBOL_GPL(pingv6_ops);
 
@@ -232,15 +236,15 @@ exit:
 static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
 					  kgid_t *high)
 {
-	kgid_t *data = net->ipv4.sysctl_ping_group_range;
+	kgid_t *data = net->ipv4.ping_group_range.range;
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
 }
 
 
@@ -248,26 +252,33 @@ int ping_init_sock(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
 	kgid_t group = current_egid();
-	struct group_info *group_info = get_current_groups();
-	int i, j, count = group_info->ngroups;
+	struct group_info *group_info;
+	int i, j, count;
 	kgid_t low, high;
+	int ret = 0;
 
 	inet_get_ping_group_range_net(net, &low, &high);
 	if (gid_lte(low, group) && gid_lte(group, high))
 		return 0;
 
+	group_info = get_current_groups();
+	count = group_info->ngroups;
 	for (i = 0; i < group_info->nblocks; i++) {
 		int cp_count = min_t(int, NGROUPS_PER_BLOCK, count);
 		for (j = 0; j < cp_count; j++) {
 			kgid_t gid = group_info->blocks[i][j];
 			if (gid_lte(low, gid) && gid_lte(gid, high))
-				return 0;
+				goto out_release_group;
 		}
 
 		count -= cp_count;
 	}
 
-	return -EACCES;
+	ret = -EACCES;
+
+out_release_group:
+	put_group_info(group_info);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(ping_init_sock);
 
@@ -316,6 +327,9 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 		if (addr_len < sizeof(*addr))
 			return -EINVAL;
 
+		if (addr->sin6_family != AF_INET6)
+			return -EINVAL;
+
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
 			 sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));
 
@@ -668,8 +682,8 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 }
 EXPORT_SYMBOL_GPL(ping_common_sendmsg);
 
-int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		    size_t len)
+static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+			   size_t len)
 {
 	struct net *net = sock_net(sk);
 	struct flowi4 fl4;
@@ -696,7 +710,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	 */
 
 	if (msg->msg_name) {
-		struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
 		if (msg->msg_namelen < sizeof(*usin))
 			return -EINVAL;
 		if (usin->sin_family != AF_INET)
@@ -720,7 +734,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	sock_tx_timestamp(sk, &ipc.tx_flags);
 
 	if (msg->msg_controllen) {
-		err = ip_cmsg_send(sock_net(sk), msg, &ipc);
+		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
 		if (err)
 			return err;
 		if (ipc.opt)
@@ -869,7 +883,7 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	/* Copy the address and add cmsg data. */
 	if (family == AF_INET) {
-		struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 
 		if (sin) {
 			sin->sin_family = AF_INET;
@@ -886,8 +900,7 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	} else if (family == AF_INET6) {
 		struct ipv6_pinfo *np = inet6_sk(sk);
 		struct ipv6hdr *ip6 = ipv6_hdr(skb);
-		struct sockaddr_in6 *sin6 =
-			(struct sockaddr_in6 *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 
 		if (sin6) {
 			sin6->sin6_family = AF_INET6;
@@ -903,7 +916,12 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		}
 
 		if (inet6_sk(sk)->rxopt.all)
-			pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb);
+			pingv6_ops.ip6_datagram_recv_common_ctl(sk, msg, skb);
+		if (skb->protocol == htons(ETH_P_IPV6) &&
+		    inet6_sk(sk)->rxopt.all)
+			pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb);
+		else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags)
+			ip_cmsg_recv(msg, skb);
 #endif
 	} else {
 		BUG();
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 8ecd7ad959b..ae0af9386f7 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -273,6 +273,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK),
 	SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE),
 	SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE),
+	SNMP_MIB_ITEM("TCPFastOpenActiveFail", LINUX_MIB_TCPFASTOPENACTIVEFAIL),
 	SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE),
 	SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL),
 	SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
@@ -280,6 +281,11 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
 	SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS),
 	SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING),
+	SNMP_MIB_ITEM("TCPFromZeroWindowAdv", LINUX_MIB_TCPFROMZEROWINDOWADV),
+	SNMP_MIB_ITEM("TCPToZeroWindowAdv", LINUX_MIB_TCPTOZEROWINDOWADV),
+	SNMP_MIB_ITEM("TCPWantZeroWindowAdv", LINUX_MIB_TCPWANTZEROWINDOWADV),
+	SNMP_MIB_ITEM("TCPSynRetrans", LINUX_MIB_TCPSYNRETRANS),
+	SNMP_MIB_ITEM("TCPOrigDataSent", LINUX_MIB_TCPORIGDATASENT),
 	SNMP_MIB_SENTINEL
 };
 
@@ -333,22 +339,22 @@ static void icmp_put(struct seq_file *seq)
 	atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs;
 
 	seq_puts(seq, "\nIcmp: InMsgs InErrors InCsumErrors");
-	for (i=0; icmpmibmap[i].name != NULL; i++)
+	for (i = 0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " In%s", icmpmibmap[i].name);
 	seq_printf(seq, " OutMsgs OutErrors");
-	for (i=0; icmpmibmap[i].name != NULL; i++)
+	for (i = 0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " Out%s", icmpmibmap[i].name);
 	seq_printf(seq, "\nIcmp: %lu %lu %lu",
-		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INMSGS),
-		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INERRORS),
-		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_CSUMERRORS));
-	for (i=0; icmpmibmap[i].name != NULL; i++)
+		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INMSGS),
+		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INERRORS),
+		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_CSUMERRORS));
+	for (i = 0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
 			   atomic_long_read(ptr + icmpmibmap[i].index));
 	seq_printf(seq, " %lu %lu",
-		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTMSGS),
-		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTERRORS));
-	for (i=0; icmpmibmap[i].name != NULL; i++)
+		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTMSGS),
+		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTERRORS));
+	for (i = 0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
 			   atomic_long_read(ptr + (icmpmibmap[i].index | 0x100)));
 }
@@ -373,7 +379,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 	BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0);
 	for (i = 0; snmp4_ipstats_list[i].name != NULL; i++)
 		seq_printf(seq, " %llu",
-			   snmp_fold_field64((void __percpu **)net->mib.ip_statistics,
+			   snmp_fold_field64(net->mib.ip_statistics,
 					     snmp4_ipstats_list[i].entry,
 					     offsetof(struct ipstats_mib, syncp)));
 
@@ -389,11 +395,11 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 		/* MaxConn field is signed, RFC 2012 */
 		if (snmp4_tcp_list[i].entry == TCP_MIB_MAXCONN)
 			seq_printf(seq, " %ld",
-				   snmp_fold_field((void __percpu **)net->mib.tcp_statistics,
+				   snmp_fold_field(net->mib.tcp_statistics,
 						   snmp4_tcp_list[i].entry));
 		else
 			seq_printf(seq, " %lu",
-				   snmp_fold_field((void __percpu **)net->mib.tcp_statistics,
+				   snmp_fold_field(net->mib.tcp_statistics,
 						   snmp4_tcp_list[i].entry));
 	}
 
@@ -404,7 +410,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\nUdp:");
 	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
-			   snmp_fold_field((void __percpu **)net->mib.udp_statistics,
+			   snmp_fold_field(net->mib.udp_statistics,
 					   snmp4_udp_list[i].entry));
 
 	/* the UDP and UDP-Lite MIBs are the same */
@@ -415,7 +421,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\nUdpLite:");
 	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
-			   snmp_fold_field((void __percpu **)net->mib.udplite_statistics,
+			   snmp_fold_field(net->mib.udplite_statistics,
 					   snmp4_udp_list[i].entry));
 
 	seq_putc(seq, '\n');
@@ -452,7 +458,7 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\nTcpExt:");
 	for (i = 0; snmp4_net_list[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
-			   snmp_fold_field((void __percpu **)net->mib.net_statistics,
+			   snmp_fold_field(net->mib.net_statistics,
 					   snmp4_net_list[i].entry));
 
 	seq_puts(seq, "\nIpExt:");
@@ -462,7 +468,7 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\nIpExt:");
 	for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++)
 		seq_printf(seq, " %llu",
-			   snmp_fold_field64((void __percpu **)net->mib.ip_statistics,
+			   snmp_fold_field64(net->mib.ip_statistics,
 					     snmp4_ipextstats_list[i].entry,
 					     offsetof(struct ipstats_mib, syncp)));
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 23c3e5b5bb5..2c65160565e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -389,7 +389,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		iph->check   = 0;
 		iph->tot_len = htons(length);
 		if (!iph->id)
-			ip_select_ident(skb, &rt->dst, NULL);
+			ip_select_ident(skb, NULL);
 
 		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
 	}
@@ -493,7 +493,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	 */
 
 	if (msg->msg_namelen) {
-		struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
 		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(*usin))
 			goto out;
@@ -524,7 +524,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	ipc.oif = sk->sk_bound_dev_if;
 
 	if (msg->msg_controllen) {
-		err = ip_cmsg_send(sock_net(sk), msg, &ipc);
+		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
 		if (err)
 			goto out;
 		if (ipc.opt)
@@ -575,7 +575,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
 			   RT_SCOPE_UNIVERSE,
 			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
-			   inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP |
+			   inet_sk_flowi_flags(sk) |
 			    (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
 			   daddr, saddr, 0, 0);
 
@@ -690,7 +690,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	struct inet_sock *inet = inet_sk(sk);
 	size_t copied = 0;
 	int err = -EOPNOTSUPP;
-	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct sk_buff *skb;
 
 	if (flags & MSG_OOB)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f8da2827801..190199851c9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -89,6 +89,7 @@
 #include <linux/rcupdate.h>
 #include <linux/times.h>
 #include <linux/slab.h>
+#include <linux/jhash.h>
 #include <net/dst.h>
 #include <net/net_namespace.h>
 #include <net/protocol.h>
@@ -112,9 +113,6 @@
 #define RT_FL_TOS(oldflp4) \
 	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
 
-/* IPv4 datagram length is stored into 16bit field (tot_len) */
-#define IP_MAX_MTU	0xFFFF
-
 #define RT_GC_TIMEOUT (300*HZ)
 
 static int ip_rt_max_size;
@@ -142,11 +140,6 @@ static void		 ip_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static void		ipv4_dst_destroy(struct dst_entry *dst);
 
-static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
-			    int how)
-{
-}
-
 static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old)
 {
 	WARN_ON(1);
@@ -165,7 +158,6 @@ static struct dst_ops ipv4_dst_ops = {
 	.mtu =			ipv4_mtu,
 	.cow_metrics =		ipv4_cow_metrics,
 	.destroy =		ipv4_dst_destroy,
-	.ifdown =		ipv4_dst_ifdown,
 	.negative_advice =	ipv4_negative_advice,
 	.link_failure =		ipv4_link_failure,
 	.update_pmtu =		ip_rt_update_pmtu,
@@ -197,7 +189,7 @@ const __u8 ip_tos2prio[16] = {
 EXPORT_SYMBOL(ip_tos2prio);
 
 static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
-#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)
+#define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field)
 
 #ifdef CONFIG_PROC_FS
 static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
@@ -465,39 +457,45 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 	return neigh_create(&arp_tbl, pkey, dev);
 }
 
-/*
- * Peer allocation may fail only in serious out-of-memory conditions.  However
- * we still can generate some output.
- * Random ID selection looks a bit dangerous because we have no chances to
- * select ID being unique in a reasonable period of time.
- * But broken packet identifier may be better than no packet at all.
+#define IP_IDENTS_SZ 2048u
+struct ip_ident_bucket {
+	atomic_t	id;
+	u32		stamp32;
+};
+
+static struct ip_ident_bucket *ip_idents __read_mostly;
+
+/* In order to protect privacy, we add a perturbation to identifiers
+ * if one generator is seldom used. This makes hard for an attacker
+ * to infer how many packets were sent between two points in time.
  */
-static void ip_select_fb_ident(struct iphdr *iph)
+u32 ip_idents_reserve(u32 hash, int segs)
 {
-	static DEFINE_SPINLOCK(ip_fb_id_lock);
-	static u32 ip_fallback_id;
-	u32 salt;
+	struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ;
+	u32 old = ACCESS_ONCE(bucket->stamp32);
+	u32 now = (u32)jiffies;
+	u32 delta = 0;
 
-	spin_lock_bh(&ip_fb_id_lock);
-	salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
-	iph->id = htons(salt & 0xFFFF);
-	ip_fallback_id = salt;
-	spin_unlock_bh(&ip_fb_id_lock);
+	if (old != now && cmpxchg(&bucket->stamp32, old, now) == old)
+		delta = prandom_u32_max(now - old);
+
+	return atomic_add_return(segs + delta, &bucket->id) - segs;
 }
+EXPORT_SYMBOL(ip_idents_reserve);
 
-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
+void __ip_select_ident(struct iphdr *iph, int segs)
 {
-	struct net *net = dev_net(dst->dev);
-	struct inet_peer *peer;
+	static u32 ip_idents_hashrnd __read_mostly;
+	u32 hash, id;
 
-	peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1);
-	if (peer) {
-		iph->id = htons(inet_getid(peer, more));
-		inet_putpeer(peer);
-		return;
-	}
+	net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));
 
-	ip_select_fb_ident(iph);
+	hash = jhash_3words((__force u32)iph->daddr,
+			    (__force u32)iph->saddr,
+			    iph->protocol,
+			    ip_idents_hashrnd);
+	id = ip_idents_reserve(hash, segs);
+	iph->id = htons(id);
 }
 EXPORT_SYMBOL(__ip_select_ident);
 
@@ -700,7 +698,6 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 
 out_unlock:
 	spin_unlock_bh(&fnhe_lock);
-	return;
 }
 
 static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4,
@@ -1003,6 +1000,9 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
 	struct flowi4 fl4;
 	struct rtable *rt;
 
+	if (!mark)
+		mark = IP4_REPLY_MARK(net, skb->mark);
+
 	__build_flow_key(&fl4, NULL, iph, oif,
 			 RT_TOS(iph->tos), protocol, mark, flow_flags);
 	rt = __ip_route_output_key(net, &fl4);
@@ -1020,6 +1020,10 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	struct rtable *rt;
 
 	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+
+	if (!fl4.flowi4_mark)
+		fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark);
+
 	rt = __ip_route_output_key(sock_net(sk), &fl4);
 	if (!IS_ERR(rt)) {
 		__ip_rt_update_pmtu(rt, &fl4, mtu);
@@ -1032,7 +1036,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	const struct iphdr *iph = (const struct iphdr *) skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
-	struct dst_entry *dst;
+	struct dst_entry *odst = NULL;
 	bool new = false;
 
 	bh_lock_sock(sk);
@@ -1040,16 +1044,17 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	if (!ip_sk_accept_pmtu(sk))
 		goto out;
 
-	rt = (struct rtable *) __sk_dst_get(sk);
+	odst = sk_dst_get(sk);
 
-	if (sock_owned_by_user(sk) || !rt) {
+	if (sock_owned_by_user(sk) || !odst) {
 		__ipv4_sk_update_pmtu(skb, sk, mtu);
 		goto out;
 	}
 
 	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
 
-	if (!__sk_dst_check(sk, 0)) {
+	rt = (struct rtable *)odst;
+	if (odst->obsolete && odst->ops->check(odst, 0) == NULL) {
 		rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
 		if (IS_ERR(rt))
 			goto out;
@@ -1059,8 +1064,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 
 	__ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu);
 
-	dst = dst_check(&rt->dst, 0);
-	if (!dst) {
+	if (!dst_check(&rt->dst, 0)) {
 		if (new)
 			dst_release(&rt->dst);
 
@@ -1072,10 +1076,11 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	}
 
 	if (new)
-		__sk_dst_set(sk, &rt->dst);
+		sk_dst_set(sk, &rt->dst);
 
 out:
 	bh_unlock_sock(sk);
+	dst_release(odst);
 }
 EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
 
@@ -1139,7 +1144,7 @@ static void ipv4_link_failure(struct sk_buff *skb)
 		dst_set_expires(&rt->dst, 0);
 }
 
-static int ip_rt_bug(struct sk_buff *skb)
+static int ip_rt_bug(struct sock *sk, struct sk_buff *skb)
 {
 	pr_debug("%s: %pI4 -> %pI4, %s\n",
 		 __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
@@ -1529,7 +1534,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct in_device *out_dev;
 	unsigned int flags = 0;
 	bool do_cache;
-	u32 itag;
+	u32 itag = 0;
 
 	/* get a working reference to the output device */
 	out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
@@ -1600,6 +1605,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	RT_CACHE_STAT_INC(in_slow_tot);
 
 	rth->dst.input = ip_forward;
 	rth->dst.output = ip_output;
@@ -1698,25 +1704,27 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
 	err = fib_lookup(net, &fl4, &res);
-	if (err != 0)
+	if (err != 0) {
+		if (!IN_DEV_FORWARD(in_dev))
+			err = -EHOSTUNREACH;
 		goto no_route;
-
-	RT_CACHE_STAT_INC(in_slow_tot);
+	}
 
 	if (res.type == RTN_BROADCAST)
 		goto brd_input;
 
 	if (res.type == RTN_LOCAL) {
 		err = fib_validate_source(skb, saddr, daddr, tos,
-					  LOOPBACK_IFINDEX,
-					  dev, in_dev, &itag);
+					  0, dev, in_dev, &itag);
 		if (err < 0)
 			goto martian_source_keep_err;
 		goto local_input;
 	}
 
-	if (!IN_DEV_FORWARD(in_dev))
+	if (!IN_DEV_FORWARD(in_dev)) {
+		err = -EHOSTUNREACH;
 		goto no_route;
+	}
 	if (res.type != RTN_UNICAST)
 		goto martian_destination;
 
@@ -1771,6 +1779,7 @@ local_input:
 	rth->rt_gateway	= 0;
 	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
+	RT_CACHE_STAT_INC(in_slow_tot);
 	if (res.type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;
 		rth->dst.error= -err;
@@ -2223,7 +2232,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 
 		new->__use = 1;
 		new->input = dst_discard;
-		new->output = dst_discard;
+		new->output = dst_discard_sk;
 
 		new->dev = ort->dst.dev;
 		if (new->dev)
@@ -2362,7 +2371,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 			}
 		} else
 #endif
-			if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
+			if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex))
 				goto nla_put_failure;
 	}
 
@@ -2473,11 +2482,6 @@ errout_free:
 	goto errout;
 }
 
-int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
-{
-	return skb->len;
-}
-
 void ip_rt_multicast_event(struct in_device *in_dev)
 {
 	rt_cache_flush(dev_net(in_dev->dev));
@@ -2715,6 +2719,12 @@ int __init ip_rt_init(void)
 {
 	int rc = 0;
 
+	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
+	if (!ip_idents)
+		panic("IP: failed to allocate ip_idents\n");
+
+	prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b95331e6c07..c86624b36a6 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -121,7 +121,7 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
 	cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
 
 	/* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */
-	diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS);
+	diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
 	if (diff >= MAX_SYNCOOKIE_AGE)
 		return (__u32)-1;
 
@@ -303,6 +303,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	ireq->ir_rmt_port	= th->source;
 	ireq->ir_loc_addr	= ip_hdr(skb)->daddr;
 	ireq->ir_rmt_addr	= ip_hdr(skb)->saddr;
+	ireq->ir_mark		= inet_request_mark(sk, skb);
 	ireq->ecn_ok		= ecn_ok;
 	ireq->snd_wscale	= tcp_opt.snd_wscale;
 	ireq->sack_ok		= tcp_opt.sack_ok;
@@ -339,7 +340,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	 * hasn't changed since we received the original syn, but I see
 	 * no easy way to do this.
 	 */
-	flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
+	flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
 			   inet_sk_flowi_flags(sk),
 			   (opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 38c8ec90ff6..79a007c5255 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 /* Update system visible IP port range */
 static void set_local_port_range(struct net *net, int range[2])
 {
-	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
-	net->ipv4.sysctl_local_ports.range[0] = range[0];
-	net->ipv4.sysctl_local_ports.range[1] = range[1];
-	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
+	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	net->ipv4.ip_local_ports.range[0] = range[0];
+	net->ipv4.ip_local_ports.range[1] = range[1];
+	write_sequnlock(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -57,7 +57,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 				 size_t *lenp, loff_t *ppos)
 {
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_local_ports.range);
+		container_of(table->data, struct net, ipv4.ip_local_ports.range);
 	int ret;
 	int range[2];
 	struct ctl_table tmp = {
@@ -87,14 +87,14 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
 {
 	kgid_t *data = table->data;
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
+		container_of(table->data, struct net, ipv4.ping_group_range.range);
 	unsigned int seq;
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
 }
 
 /* Update system visible IP port range */
@@ -102,11 +102,11 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
 {
 	kgid_t *data = table->data;
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
-	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
+		container_of(table->data, struct net, ipv4.ping_group_range.range);
+	write_seqlock(&net->ipv4.ip_local_ports.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
+	write_sequnlock(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -286,13 +286,6 @@ static struct ctl_table ipv4_table[] = {
 		.extra2		= &ip_ttl_max,
 	},
 	{
-		.procname	= "ip_no_pmtu_disc",
-		.data		= &ipv4_config.no_pmtu_disc,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
-	{
 		.procname	= "ip_nonlocal_bind",
 		.data		= &sysctl_ip_nonlocal_bind,
 		.maxlen		= sizeof(int),
@@ -444,13 +437,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
-		.procname	= "ip_local_reserved_ports",
-		.data		= NULL, /* initialized in sysctl_ipv4_init */
-		.maxlen		= 65536,
-		.mode		= 0644,
-		.proc_handler	= proc_do_large_bitmap,
-	},
-	{
 		.procname	= "igmp_max_memberships",
 		.data		= &sysctl_igmp_max_memberships,
 		.maxlen		= sizeof(int),
@@ -707,7 +693,7 @@ static struct ctl_table ipv4_table[] = {
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec
 	},
-        {
+	{
 		.procname       = "tcp_thin_dupack",
 		.data           = &sysctl_tcp_thin_dupack,
 		.maxlen         = sizeof(int),
@@ -812,7 +798,7 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 	{
 		.procname	= "ping_group_range",
-		.data		= &init_net.ipv4.sysctl_ping_group_range,
+		.data		= &init_net.ipv4.ping_group_range.range,
 		.maxlen		= sizeof(gid_t)*2,
 		.mode		= 0644,
 		.proc_handler	= ipv4_ping_group_range,
@@ -826,11 +812,46 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 	{
 		.procname	= "ip_local_port_range",
-		.maxlen		= sizeof(init_net.ipv4.sysctl_local_ports.range),
-		.data		= &init_net.ipv4.sysctl_local_ports.range,
+		.maxlen		= sizeof(init_net.ipv4.ip_local_ports.range),
+		.data		= &init_net.ipv4.ip_local_ports.range,
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
+	{
+		.procname	= "ip_local_reserved_ports",
+		.data		= &init_net.ipv4.sysctl_local_reserved_ports,
+		.maxlen		= 65536,
+		.mode		= 0644,
+		.proc_handler	= proc_do_large_bitmap,
+	},
+	{
+		.procname	= "ip_no_pmtu_disc",
+		.data		= &init_net.ipv4.sysctl_ip_no_pmtu_disc,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "ip_forward_use_pmtu",
+		.data		= &init_net.ipv4.sysctl_ip_fwd_use_pmtu,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "fwmark_reflect",
+		.data		= &init_net.ipv4.sysctl_fwmark_reflect,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_fwmark_accept",
+		.data		= &init_net.ipv4.sysctl_tcp_fwmark_accept,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{ }
 };
 
@@ -851,26 +872,18 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 			table[i].data += (void *)net - (void *)&init_net;
 	}
 
-	/*
-	 * Sane defaults - nobody may create ping sockets.
-	 * Boot scripts should set this to distro-specific group.
-	 */
-	net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
-	net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
-
-	/*
-	 * Set defaults for local port range
-	 */
-	seqlock_init(&net->ipv4.sysctl_local_ports.lock);
-	net->ipv4.sysctl_local_ports.range[0] =  32768;
-	net->ipv4.sysctl_local_ports.range[1] =  61000;
-
 	net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
 	if (net->ipv4.ipv4_hdr == NULL)
 		goto err_reg;
 
+	net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
+	if (!net->ipv4.sysctl_local_reserved_ports)
+		goto err_ports;
+
 	return 0;
 
+err_ports:
+	unregister_net_sysctl_table(net->ipv4.ipv4_hdr);
 err_reg:
 	if (!net_eq(net, &init_net))
 		kfree(table);
@@ -882,6 +895,7 @@ static __net_exit void ipv4_sysctl_exit_net(struct net *net)
 {
 	struct ctl_table *table;
 
+	kfree(net->ipv4.sysctl_local_reserved_ports);
 	table = net->ipv4.ipv4_hdr->ctl_table_arg;
 	unregister_net_sysctl_table(net->ipv4.ipv4_hdr);
 	kfree(table);
@@ -895,16 +909,6 @@ static __net_initdata struct pernet_operations ipv4_sysctl_ops = {
 static __init int sysctl_ipv4_init(void)
 {
 	struct ctl_table_header *hdr;
-	struct ctl_table *i;
-
-	for (i = ipv4_table; i->procname; i++) {
-		if (strcmp(i->procname, "ip_local_reserved_ports") == 0) {
-			i->data = sysctl_local_reserved_ports;
-			break;
-		}
-	}
-	if (!i->procname)
-		return -EINVAL;
 
 	hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table);
 	if (hdr == NULL)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0ca87547bec..9d2118e5fbc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -381,13 +381,13 @@ void tcp_init_sock(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	skb_queue_head_init(&tp->out_of_order_queue);
+	__skb_queue_head_init(&tp->out_of_order_queue);
 	tcp_init_xmit_timers(sk);
 	tcp_prequeue_init(tp);
 	INIT_LIST_HEAD(&tp->tsq_node);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
-	tp->mdev = TCP_TIMEOUT_INIT;
+	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 
 	/* So many TCP implementations out there (incorrectly) count the
 	 * initial SYN frame in their delayed-ACK and congestion control
@@ -622,19 +622,21 @@ static inline void tcp_mark_urg(struct tcp_sock *tp, int flags)
 }
 
 /* If a not yet filled skb is pushed, do not send it if
- * we have packets in Qdisc or NIC queues :
+ * we have data packets in Qdisc or NIC queues :
  * Because TX completion will happen shortly, it gives a chance
  * to coalesce future sendmsg() payload into this skb, without
  * need for a timer, and with no latency trade off.
  * As packets containing data payload have a bigger truesize
- * than pure acks (dataless) packets, the last check prevents
- * autocorking if we only have an ACK in Qdisc/NIC queues.
+ * than pure acks (dataless) packets, the last checks prevent
+ * autocorking if we only have an ACK in Qdisc/NIC queues,
+ * or if TX completion was delayed after we processed ACK packet.
  */
 static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
 				int size_goal)
 {
 	return skb->len < size_goal &&
 	       sysctl_tcp_autocorking &&
+	       skb != tcp_write_queue_head(sk) &&
 	       atomic_read(&sk->sk_wmem_alloc) > skb->truesize;
 }
 
@@ -660,7 +662,11 @@ static void tcp_push(struct sock *sk, int flags, int mss_now,
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
 		}
-		return;
+		/* It is possible TX completion already happened
+		 * before we set TSQ_THROTTLED.
+		 */
+		if (atomic_read(&sk->sk_wmem_alloc) > skb->truesize)
+			return;
 	}
 
 	if (flags & MSG_MORE)
@@ -1038,7 +1044,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp)
 	}
 }
 
-static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
+				int *copied, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int err, flags;
@@ -1053,11 +1060,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
 	if (unlikely(tp->fastopen_req == NULL))
 		return -ENOBUFS;
 	tp->fastopen_req->data = msg;
+	tp->fastopen_req->size = size;
 
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
 	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
 				    msg->msg_namelen, flags);
-	*size = tp->fastopen_req->copied;
+	*copied = tp->fastopen_req->copied;
 	tcp_free_fastopen_req(tp);
 	return err;
 }
@@ -1077,7 +1085,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	flags = msg->msg_flags;
 	if (flags & MSG_FASTOPEN) {
-		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
 		else if (err)
@@ -1100,7 +1108,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (unlikely(tp->repair)) {
 		if (tp->repair_queue == TCP_RECV_QUEUE) {
 			copied = tcp_send_rcvq(sk, msg, size);
-			goto out;
+			goto out_nopush;
 		}
 
 		err = -EINVAL;
@@ -1274,6 +1282,7 @@ wait_for_memory:
 out:
 	if (copied)
 		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+out_nopush:
 	release_sock(sk);
 	return copied + copied_syn;
 
@@ -1660,11 +1669,11 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		    (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
 		    !sysctl_tcp_low_latency &&
 		    net_dma_find_channel()) {
-			preempt_enable_no_resched();
+			preempt_enable();
 			tp->ucopy.pinned_list =
 					dma_pin_iovec_pages(msg->msg_iov, len);
 		} else {
-			preempt_enable_no_resched();
+			preempt_enable();
 		}
 	}
 #endif
@@ -2223,7 +2232,7 @@ adjudge_to_death:
 	/*	This is a (useful) BSD violating of the RFC. There is a
 	 *	problem with TCP as specified in that the other end could
 	 *	keep a socket open forever with no application left this end.
-	 *	We use a 3 minute timeout (about the same as BSD) then kill
+	 *	We use a 1 minute timeout (about the same as BSD) then kill
 	 *	our end. If they send after that then tough - BUT: long enough
 	 *	that we won't make the old 4*rto = almost no time - whoops
 	 *	reset mistake.
@@ -2333,7 +2342,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	sk->sk_shutdown = 0;
 	sock_reset_flag(sk, SOCK_DONE);
-	tp->srtt = 0;
+	tp->srtt_us = 0;
 	if ((tp->write_seq += tp->max_window + 2) == 0)
 		tp->write_seq = 1;
 	icsk->icsk_backoff = 0;
@@ -2777,8 +2786,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 
 	info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
 	info->tcpi_rcv_ssthresh = tp->rcv_ssthresh;
-	info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3;
-	info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2;
+	info->tcpi_rtt = tp->srtt_us >> 3;
+	info->tcpi_rttvar = tp->mdev_us >> 2;
 	info->tcpi_snd_ssthresh = tp->snd_ssthresh;
 	info->tcpi_snd_cwnd = tp->snd_cwnd;
 	info->tcpi_advmss = tp->advmss;
@@ -2788,6 +2797,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 	info->tcpi_rcv_space = tp->rcvq_space.space;
 
 	info->tcpi_total_retrans = tp->total_retrans;
+
+	info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ?
+					sk->sk_pacing_rate : ~0ULL;
+	info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ?
+					sk->sk_max_pacing_rate : ~0ULL;
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 
@@ -2903,6 +2917,14 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 	case TCP_USER_TIMEOUT:
 		val = jiffies_to_msecs(icsk->icsk_user_timeout);
 		break;
+
+	case TCP_FASTOPEN:
+		if (icsk->icsk_accept_queue.fastopenq != NULL)
+			val = icsk->icsk_accept_queue.fastopenq->max_qlen;
+		else
+			val = 0;
+		break;
+
 	case TCP_TIMESTAMP:
 		val = tcp_time_stamp + tp->tsoffset;
 		break;
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index 821846fb0a7..d5de69bc04f 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -140,13 +140,12 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 		ca->cnt = 1;
 }
 
-static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-			      u32 in_flight)
+static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index ad37bf18ae4..7b09d8b49fa 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -276,27 +276,6 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 	return err;
 }
 
-/* RFC2861 Check whether we are limited by application or congestion window
- * This is the inverse of cwnd check in tcp_tso_should_defer
- */
-bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
-	u32 left;
-
-	if (in_flight >= tp->snd_cwnd)
-		return true;
-
-	left = tp->snd_cwnd - in_flight;
-	if (sk_can_gso(sk) &&
-	    left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
-	    left * tp->mss_cache < sk->sk_gso_max_size &&
-	    left < sk->sk_gso_max_segs)
-		return true;
-	return left <= tcp_max_tso_deferred_mss(tp);
-}
-EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited);
-
 /* Slow start is used when congestion window is no greater than the slow start
  * threshold. We base on RFC2581 and also handle stretch ACKs properly.
  * We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but
@@ -338,11 +317,11 @@ EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
 /* This is Jacobson's slow start and congestion avoidance.
  * SIGCOMM '88, p. 328.
  */
-void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
+void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	/* In "safe" area, increase. */
@@ -362,21 +341,12 @@ u32 tcp_reno_ssthresh(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(tcp_reno_ssthresh);
 
-/* Lower bound on congestion window with halving. */
-u32 tcp_reno_min_cwnd(const struct sock *sk)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
-	return tp->snd_ssthresh/2;
-}
-EXPORT_SYMBOL_GPL(tcp_reno_min_cwnd);
-
 struct tcp_congestion_ops tcp_reno = {
 	.flags		= TCP_CONG_NON_RESTRICTED,
 	.name		= "reno",
 	.owner		= THIS_MODULE,
 	.ssthresh	= tcp_reno_ssthresh,
 	.cong_avoid	= tcp_reno_cong_avoid,
-	.min_cwnd	= tcp_reno_min_cwnd,
 };
 
 /* Initial congestion control used (until SYN)
@@ -388,6 +358,5 @@ struct tcp_congestion_ops tcp_init_congestion_ops  = {
 	.owner		= THIS_MODULE,
 	.ssthresh	= tcp_reno_ssthresh,
 	.cong_avoid	= tcp_reno_cong_avoid,
-	.min_cwnd	= tcp_reno_min_cwnd,
 };
 EXPORT_SYMBOL_GPL(tcp_init_congestion_ops);
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 828e4c3ffba..a9bd8a4828a 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -304,13 +304,12 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 		ca->cnt = 1;
 }
 
-static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-			      u32 in_flight)
+static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh) {
@@ -409,7 +408,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 		ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
 		ratio += cnt;
 
-		ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT);
+		ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
 	}
 
 	/* Some calls are for duplicates without timetamps */
@@ -476,10 +475,6 @@ static int __init cubictcp_register(void)
 	/* divide by bic_scale and by constant Srtt (100ms) */
 	do_div(cube_factor, bic_scale * 10);
 
-	/* hystart needs ms clock resolution */
-	if (hystart && HZ < 1000)
-		cubictcp.flags |= TCP_CONG_RTT_STAMP;
-
 	return tcp_register_congestion_control(&cubictcp);
 }
 
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f195d9316e5..9771563ab56 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -72,25 +72,224 @@ error:		kfree(ctx);
 	return err;
 }
 
-/* Computes the fastopen cookie for the IP path.
- * The path is a 128 bits long (pad with zeros for IPv4).
- *
- * The caller must check foc->len to determine if a valid cookie
- * has been generated successfully.
-*/
-void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
-			     struct tcp_fastopen_cookie *foc)
+static bool __tcp_fastopen_cookie_gen(const void *path,
+				      struct tcp_fastopen_cookie *foc)
 {
-	__be32 path[4] = { src, dst, 0, 0 };
 	struct tcp_fastopen_context *ctx;
+	bool ok = false;
 
 	tcp_fastopen_init_key_once(true);
 
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
-		crypto_cipher_encrypt_one(ctx->tfm, foc->val, (__u8 *)path);
+		crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
 		foc->len = TCP_FASTOPEN_COOKIE_SIZE;
+		ok = true;
 	}
 	rcu_read_unlock();
+	return ok;
+}
+
+/* Generate the fastopen cookie by doing aes128 encryption on both
+ * the source and destination addresses. Pad 0s for IPv4 or IPv4-mapped-IPv6
+ * addresses. For the longer IPv6 addresses use CBC-MAC.
+ *
+ * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
+ */
+static bool tcp_fastopen_cookie_gen(struct request_sock *req,
+				    struct sk_buff *syn,
+				    struct tcp_fastopen_cookie *foc)
+{
+	if (req->rsk_ops->family == AF_INET) {
+		const struct iphdr *iph = ip_hdr(syn);
+
+		__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
+		return __tcp_fastopen_cookie_gen(path, foc);
+	}
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (req->rsk_ops->family == AF_INET6) {
+		const struct ipv6hdr *ip6h = ipv6_hdr(syn);
+		struct tcp_fastopen_cookie tmp;
+
+		if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
+			struct in6_addr *buf = (struct in6_addr *) tmp.val;
+			int i = 4;
+
+			for (i = 0; i < 4; i++)
+				buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
+			return __tcp_fastopen_cookie_gen(buf, foc);
+		}
+	}
+#endif
+	return false;
+}
+
+static bool tcp_fastopen_create_child(struct sock *sk,
+				      struct sk_buff *skb,
+				      struct dst_entry *dst,
+				      struct request_sock *req)
+{
+	struct tcp_sock *tp;
+	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
+	struct sock *child;
+
+	req->num_retrans = 0;
+	req->num_timeout = 0;
+	req->sk = NULL;
+
+	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
+	if (child == NULL)
+		return false;
+
+	spin_lock(&queue->fastopenq->lock);
+	queue->fastopenq->qlen++;
+	spin_unlock(&queue->fastopenq->lock);
+
+	/* Initialize the child socket. Have to fix some values to take
+	 * into account the child is a Fast Open socket and is created
+	 * only out of the bits carried in the SYN packet.
+	 */
+	tp = tcp_sk(child);
+
+	tp->fastopen_rsk = req;
+	/* Do a hold on the listner sk so that if the listener is being
+	 * closed, the child that has been accepted can live on and still
+	 * access listen_lock.
+	 */
+	sock_hold(sk);
+	tcp_rsk(req)->listener = sk;
+
+	/* RFC1323: The window in SYN & SYN/ACK segments is never
+	 * scaled. So correct it appropriately.
+	 */
+	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
+
+	/* Activate the retrans timer so that SYNACK can be retransmitted.
+	 * The request socket is not added to the SYN table of the parent
+	 * because it's been added to the accept queue directly.
+	 */
+	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
+				  TCP_TIMEOUT_INIT, TCP_RTO_MAX);
+
+	/* Add the child socket directly into the accept queue */
+	inet_csk_reqsk_queue_add(sk, req, child);
+
+	/* Now finish processing the fastopen child socket. */
+	inet_csk(child)->icsk_af_ops->rebuild_header(child);
+	tcp_init_congestion_control(child);
+	tcp_mtup_init(child);
+	tcp_init_metrics(child);
+	tcp_init_buffer_space(child);
+
+	/* Queue the data carried in the SYN packet. We need to first
+	 * bump skb's refcnt because the caller will attempt to free it.
+	 *
+	 * XXX (TFO) - we honor a zero-payload TFO request for now,
+	 * (any reason not to?) but no need to queue the skb since
+	 * there is no data. How about SYN+FIN?
+	 */
+	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1) {
+		skb = skb_get(skb);
+		skb_dst_drop(skb);
+		__skb_pull(skb, tcp_hdr(skb)->doff * 4);
+		skb_set_owner_r(skb, child);
+		__skb_queue_tail(&child->sk_receive_queue, skb);
+		tp->syn_data_acked = 1;
+	}
+	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+	sk->sk_data_ready(sk);
+	bh_unlock_sock(child);
+	sock_put(child);
+	WARN_ON(req->sk == NULL);
+	return true;
+}
+EXPORT_SYMBOL(tcp_fastopen_create_child);
+
+static bool tcp_fastopen_queue_check(struct sock *sk)
+{
+	struct fastopen_queue *fastopenq;
+
+	/* Make sure the listener has enabled fastopen, and we don't
+	 * exceed the max # of pending TFO requests allowed before trying
+	 * to validating the cookie in order to avoid burning CPU cycles
+	 * unnecessarily.
+	 *
+	 * XXX (TFO) - The implication of checking the max_qlen before
+	 * processing a cookie request is that clients can't differentiate
+	 * between qlen overflow causing Fast Open to be disabled
+	 * temporarily vs a server not supporting Fast Open at all.
+	 */
+	fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
+	if (fastopenq == NULL || fastopenq->max_qlen == 0)
+		return false;
+
+	if (fastopenq->qlen >= fastopenq->max_qlen) {
+		struct request_sock *req1;
+		spin_lock(&fastopenq->lock);
+		req1 = fastopenq->rskq_rst_head;
+		if ((req1 == NULL) || time_after(req1->expires, jiffies)) {
+			spin_unlock(&fastopenq->lock);
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
+			return false;
+		}
+		fastopenq->rskq_rst_head = req1->dl_next;
+		fastopenq->qlen--;
+		spin_unlock(&fastopenq->lock);
+		reqsk_free(req1);
+	}
+	return true;
+}
+
+/* Returns true if we should perform Fast Open on the SYN. The cookie (foc)
+ * may be updated and return the client in the SYN-ACK later. E.g., Fast Open
+ * cookie request (foc->len == 0).
+ */
+bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
+		      struct request_sock *req,
+		      struct tcp_fastopen_cookie *foc,
+		      struct dst_entry *dst)
+{
+	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
+	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
+
+	if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+	      (syn_data || foc->len >= 0) &&
+	      tcp_fastopen_queue_check(sk))) {
+		foc->len = -1;
+		return false;
+	}
+
+	if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+		goto fastopen;
+
+	if (tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
+	    foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
+	    foc->len == valid_foc.len &&
+	    !memcmp(foc->val, valid_foc.val, foc->len)) {
+		/* Cookie is valid. Create a (full) child socket to accept
+		 * the data in SYN before returning a SYN-ACK to ack the
+		 * data. If we fail to create the socket, fall back and
+		 * ack the ISN only but includes the same cookie.
+		 *
+		 * Note: Data-less SYN with valid cookie is allowed to send
+		 * data in SYN_RECV state.
+		 */
+fastopen:
+		if (tcp_fastopen_create_child(sk, skb, dst, req)) {
+			foc->len = -1;
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPFASTOPENPASSIVE);
+			return true;
+		}
+	}
+
+	NET_INC_STATS_BH(sock_net(sk), foc->len ?
+			 LINUX_MIB_TCPFASTOPENPASSIVEFAIL :
+			 LINUX_MIB_TCPFASTOPENCOOKIEREQD);
+	*foc = valid_foc;
+	return false;
 }
+EXPORT_SYMBOL(tcp_try_fastopen);
diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c
index 8ed9305dfdf..1c4908280d9 100644
--- a/net/ipv4/tcp_highspeed.c
+++ b/net/ipv4/tcp_highspeed.c
@@ -109,12 +109,12 @@ static void hstcp_init(struct sock *sk)
 	tp->snd_cwnd_clamp = min_t(u32, tp->snd_cwnd_clamp, 0xffffffff/128);
 }
 
-static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
+static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct hstcp *ca = inet_csk_ca(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
@@ -162,7 +162,6 @@ static struct tcp_congestion_ops tcp_highspeed __read_mostly = {
 	.init		= hstcp_init,
 	.ssthresh	= hstcp_ssthresh,
 	.cong_avoid	= hstcp_cong_avoid,
-	.min_cwnd	= tcp_reno_min_cwnd,
 
 	.owner		= THIS_MODULE,
 	.name		= "highspeed"
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 4a194acfd92..031361311a8 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -227,12 +227,12 @@ static u32 htcp_recalc_ssthresh(struct sock *sk)
 	return max((tp->snd_cwnd * ca->beta) >> 7, 2U);
 }
 
-static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
+static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct htcp *ca = inet_csk_ca(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c
index 478fe82611b..d8f8f05a495 100644
--- a/net/ipv4/tcp_hybla.c
+++ b/net/ipv4/tcp_hybla.c
@@ -21,7 +21,7 @@ struct hybla {
 	u32   rho2;	      /* Rho * Rho, integer part */
 	u32   rho_3ls;	      /* Rho parameter, <<3 */
 	u32   rho2_7ls;	      /* Rho^2, <<7	*/
-	u32   minrtt;	      /* Minimum smoothed round trip time value seen */
+	u32   minrtt_us;      /* Minimum smoothed round trip time value seen */
 };
 
 /* Hybla reference round trip time (default= 1/40 sec = 25 ms), in ms */
@@ -35,7 +35,9 @@ static inline void hybla_recalc_param (struct sock *sk)
 {
 	struct hybla *ca = inet_csk_ca(sk);
 
-	ca->rho_3ls = max_t(u32, tcp_sk(sk)->srtt / msecs_to_jiffies(rtt0), 8);
+	ca->rho_3ls = max_t(u32,
+			    tcp_sk(sk)->srtt_us / (rtt0 * USEC_PER_MSEC),
+			    8U);
 	ca->rho = ca->rho_3ls >> 3;
 	ca->rho2_7ls = (ca->rho_3ls * ca->rho_3ls) << 1;
 	ca->rho2 = ca->rho2_7ls >> 7;
@@ -59,7 +61,7 @@ static void hybla_init(struct sock *sk)
 	hybla_recalc_param(sk);
 
 	/* set minimum rtt as this is the 1st ever seen */
-	ca->minrtt = tp->srtt;
+	ca->minrtt_us = tp->srtt_us;
 	tp->snd_cwnd = ca->rho;
 }
 
@@ -85,8 +87,7 @@ static inline u32 hybla_fraction(u32 odds)
  *     o Give cwnd a new value based on the model proposed
  *     o remember increments <1
  */
-static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-			     u32 in_flight)
+static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct hybla *ca = inet_csk_ca(sk);
@@ -94,16 +95,16 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 	int is_slowstart = 0;
 
 	/*  Recalculate rho only if this srtt is the lowest */
-	if (tp->srtt < ca->minrtt){
+	if (tp->srtt_us < ca->minrtt_us) {
 		hybla_recalc_param(sk);
-		ca->minrtt = tp->srtt;
+		ca->minrtt_us = tp->srtt_us;
 	}
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (!ca->hybla_en) {
-		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked);
 		return;
 	}
 
@@ -166,7 +167,6 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 static struct tcp_congestion_ops tcp_hybla __read_mostly = {
 	.init		= hybla_init,
 	.ssthresh	= tcp_reno_ssthresh,
-	.min_cwnd	= tcp_reno_min_cwnd,
 	.cong_avoid	= hybla_cong_avoid,
 	.set_state	= hybla_state,
 
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 8a520996f3d..5999b3972e6 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -23,7 +23,6 @@
 #define ALPHA_MIN	((3*ALPHA_SCALE)/10)	/* ~0.3 */
 #define ALPHA_MAX	(10*ALPHA_SCALE)	/* 10.0 */
 #define ALPHA_BASE	ALPHA_SCALE		/* 1.0 */
-#define U32_MAX		((u32)~0U)
 #define RTT_MAX		(U32_MAX / ALPHA_MAX)	/* 3.3 secs */
 
 #define BETA_SHIFT	6
@@ -256,8 +255,7 @@ static void tcp_illinois_state(struct sock *sk, u8 new_state)
 /*
  * Increase window in response to successful acknowledgment.
  */
-static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-				    u32 in_flight)
+static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct illinois *ca = inet_csk_ca(sk);
@@ -266,7 +264,7 @@ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 		update_params(sk);
 
 	/* RFC2861 only increase cwnd if fully utilized */
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	/* In slow start */
@@ -326,10 +324,8 @@ static void tcp_illinois_info(struct sock *sk, u32 ext,
 }
 
 static struct tcp_congestion_ops tcp_illinois __read_mostly = {
-	.flags		= TCP_CONG_RTT_STAMP,
 	.init		= tcp_illinois_init,
 	.ssthresh	= tcp_illinois_ssthresh,
-	.min_cwnd	= tcp_reno_min_cwnd,
 	.cong_avoid	= tcp_illinois_cong_avoid,
 	.set_state	= tcp_illinois_state,
 	.get_info	= tcp_illinois_info,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c53b7f35c51..40639c288dc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -667,10 +667,11 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
  * To save cycles in the RFC 1323 implementation it was better to break
  * it up into three procedures. -- erics
  */
-static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
+static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	long m = mrtt; /* RTT */
+	long m = mrtt_us; /* RTT */
+	u32 srtt = tp->srtt_us;
 
 	/*	The following amusing code comes from Jacobson's
 	 *	article in SIGCOMM '88.  Note that rtt and mdev
@@ -688,14 +689,12 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
 	 * does not matter how to _calculate_ it. Seems, it was trap
 	 * that VJ failed to avoid. 8)
 	 */
-	if (m == 0)
-		m = 1;
-	if (tp->srtt != 0) {
-		m -= (tp->srtt >> 3);	/* m is now error in rtt est */
-		tp->srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
+	if (srtt != 0) {
+		m -= (srtt >> 3);	/* m is now error in rtt est */
+		srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
 		if (m < 0) {
 			m = -m;		/* m is now abs(error) */
-			m -= (tp->mdev >> 2);   /* similar update on mdev */
+			m -= (tp->mdev_us >> 2);   /* similar update on mdev */
 			/* This is similar to one of Eifel findings.
 			 * Eifel blocks mdev updates when rtt decreases.
 			 * This solution is a bit different: we use finer gain
@@ -707,27 +706,29 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
 			if (m > 0)
 				m >>= 3;
 		} else {
-			m -= (tp->mdev >> 2);   /* similar update on mdev */
+			m -= (tp->mdev_us >> 2);   /* similar update on mdev */
 		}
-		tp->mdev += m;	    	/* mdev = 3/4 mdev + 1/4 new */
-		if (tp->mdev > tp->mdev_max) {
-			tp->mdev_max = tp->mdev;
-			if (tp->mdev_max > tp->rttvar)
-				tp->rttvar = tp->mdev_max;
+		tp->mdev_us += m;		/* mdev = 3/4 mdev + 1/4 new */
+		if (tp->mdev_us > tp->mdev_max_us) {
+			tp->mdev_max_us = tp->mdev_us;
+			if (tp->mdev_max_us > tp->rttvar_us)
+				tp->rttvar_us = tp->mdev_max_us;
 		}
 		if (after(tp->snd_una, tp->rtt_seq)) {
-			if (tp->mdev_max < tp->rttvar)
-				tp->rttvar -= (tp->rttvar - tp->mdev_max) >> 2;
+			if (tp->mdev_max_us < tp->rttvar_us)
+				tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2;
 			tp->rtt_seq = tp->snd_nxt;
-			tp->mdev_max = tcp_rto_min(sk);
+			tp->mdev_max_us = tcp_rto_min_us(sk);
 		}
 	} else {
 		/* no previous measure. */
-		tp->srtt = m << 3;	/* take the measured time to be rtt */
-		tp->mdev = m << 1;	/* make sure rto = 3*rtt */
-		tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
+		srtt = m << 3;		/* take the measured time to be rtt */
+		tp->mdev_us = m << 1;	/* make sure rto = 3*rtt */
+		tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk));
+		tp->mdev_max_us = tp->rttvar_us;
 		tp->rtt_seq = tp->snd_nxt;
 	}
+	tp->srtt_us = max(1U, srtt);
 }
 
 /* Set the sk_pacing_rate to allow proper sizing of TSO packets.
@@ -742,18 +743,12 @@ static void tcp_update_pacing_rate(struct sock *sk)
 	u64 rate;
 
 	/* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
-	rate = (u64)tp->mss_cache * 2 * (HZ << 3);
+	rate = (u64)tp->mss_cache * 2 * (USEC_PER_SEC << 3);
 
 	rate *= max(tp->snd_cwnd, tp->packets_out);
 
-	/* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
-	 * be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
-	 * We probably need usec resolution in the future.
-	 * Note: This also takes care of possible srtt=0 case,
-	 * when tcp_rtt_estimator() was not yet called.
-	 */
-	if (tp->srtt > 8 + 2)
-		do_div(rate, tp->srtt);
+	if (likely(tp->srtt_us))
+		do_div(rate, tp->srtt_us);
 
 	/* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate
 	 * without any lock. We want to make sure compiler wont store
@@ -766,7 +761,7 @@ static void tcp_update_pacing_rate(struct sock *sk)
 /* Calculate rto without backoff.  This is the second half of Van Jacobson's
  * routine referred to above.
  */
-void tcp_set_rto(struct sock *sk)
+static void tcp_set_rto(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	/* Old crap is replaced with new one. 8)
@@ -1111,7 +1106,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
 	}
 
 	/* D-SACK for already forgotten data... Do dumb counting. */
-	if (dup_sack && tp->undo_marker && tp->undo_retrans &&
+	if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
 	    !after(end_seq_0, prior_snd_una) &&
 	    after(end_seq_0, tp->undo_marker))
 		tp->undo_retrans--;
@@ -1120,10 +1115,10 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
 }
 
 struct tcp_sacktag_state {
-	int reord;
-	int fack_count;
-	int flag;
-	s32 rtt; /* RTT measured by SACKing never-retransmitted data */
+	int	reord;
+	int	fack_count;
+	long	rtt_us; /* RTT measured by SACKing never-retransmitted data */
+	int	flag;
 };
 
 /* Check if skb is fully within the SACK block. In presence of GSO skbs,
@@ -1167,12 +1162,12 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 			unsigned int new_len = (pkt_len / mss) * mss;
 			if (!in_sack && new_len < pkt_len) {
 				new_len += mss;
-				if (new_len > skb->len)
+				if (new_len >= skb->len)
 					return 0;
 			}
 			pkt_len = new_len;
 		}
-		err = tcp_fragment(sk, skb, pkt_len, mss);
+		err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC);
 		if (err < 0)
 			return err;
 	}
@@ -1184,14 +1179,15 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 static u8 tcp_sacktag_one(struct sock *sk,
 			  struct tcp_sacktag_state *state, u8 sacked,
 			  u32 start_seq, u32 end_seq,
-			  int dup_sack, int pcount, u32 xmit_time)
+			  int dup_sack, int pcount,
+			  const struct skb_mstamp *xmit_time)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int fack_count = state->fack_count;
 
 	/* Account D-SACK for retransmitted packet. */
 	if (dup_sack && (sacked & TCPCB_RETRANS)) {
-		if (tp->undo_marker && tp->undo_retrans &&
+		if (tp->undo_marker && tp->undo_retrans > 0 &&
 		    after(end_seq, tp->undo_marker))
 			tp->undo_retrans--;
 		if (sacked & TCPCB_SACKED_ACKED)
@@ -1225,8 +1221,13 @@ static u8 tcp_sacktag_one(struct sock *sk,
 				if (!after(end_seq, tp->high_seq))
 					state->flag |= FLAG_ORIG_SACK_ACKED;
 				/* Pick the earliest sequence sacked for RTT */
-				if (state->rtt < 0)
-					state->rtt = tcp_time_stamp - xmit_time;
+				if (state->rtt_us < 0) {
+					struct skb_mstamp now;
+
+					skb_mstamp_get(&now);
+					state->rtt_us = skb_mstamp_us_delta(&now,
+								xmit_time);
+				}
 			}
 
 			if (sacked & TCPCB_LOST) {
@@ -1285,7 +1286,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	 */
 	tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
 			start_seq, end_seq, dup_sack, pcount,
-			TCP_SKB_CB(skb)->when);
+			&skb->skb_mstamp);
 
 	if (skb == tp->lost_skb_hint)
 		tp->lost_cnt_hint += pcount;
@@ -1563,7 +1564,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 						TCP_SKB_CB(skb)->end_seq,
 						dup_sack,
 						tcp_skb_pcount(skb),
-						TCP_SKB_CB(skb)->when);
+						&skb->skb_mstamp);
 
 			if (!before(TCP_SKB_CB(skb)->seq,
 				    tcp_highest_sack_seq(tp)))
@@ -1620,7 +1621,7 @@ static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_bl
 
 static int
 tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
-			u32 prior_snd_una, s32 *sack_rtt)
+			u32 prior_snd_una, long *sack_rtt_us)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	const unsigned char *ptr = (skb_transport_header(ack_skb) +
@@ -1638,7 +1639,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 
 	state.flag = 0;
 	state.reord = tp->packets_out;
-	state.rtt = -1;
+	state.rtt_us = -1L;
 
 	if (!tp->sacked_out) {
 		if (WARN_ON(tp->fackets_out))
@@ -1822,7 +1823,7 @@ out:
 	WARN_ON((int)tp->retrans_out < 0);
 	WARN_ON((int)tcp_packets_in_flight(tp) < 0);
 #endif
-	*sack_rtt = state.rtt;
+	*sack_rtt_us = state.rtt_us;
 	return state.flag;
 }
 
@@ -1892,7 +1893,7 @@ static void tcp_clear_retrans_partial(struct tcp_sock *tp)
 	tp->lost_out = 0;
 
 	tp->undo_marker = 0;
-	tp->undo_retrans = 0;
+	tp->undo_retrans = -1;
 }
 
 void tcp_clear_retrans(struct tcp_sock *tp)
@@ -1943,8 +1944,9 @@ void tcp_enter_loss(struct sock *sk, int how)
 		if (skb == tcp_send_head(sk))
 			break;
 
-		if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS)
+		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
 			tp->undo_marker = 0;
+
 		TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
 		if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) {
 			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
@@ -2032,10 +2034,12 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag)
 	 * available, or RTO is scheduled to fire first.
 	 */
 	if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 ||
-	    (flag & FLAG_ECE) || !tp->srtt)
+	    (flag & FLAG_ECE) || !tp->srtt_us)
 		return false;
 
-	delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2));
+	delay = max(usecs_to_jiffies(tp->srtt_us >> 5),
+		    msecs_to_jiffies(2));
+
 	if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay)))
 		return false;
 
@@ -2237,7 +2241,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 				break;
 
 			mss = skb_shinfo(skb)->gso_size;
-			err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, mss);
+			err = tcp_fragment(sk, skb, (packets - oldcnt) * mss,
+					   mss, GFP_ATOMIC);
 			if (err < 0)
 				break;
 			cnt = packets;
@@ -2660,7 +2665,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 
 	tp->prior_ssthresh = 0;
 	tp->undo_marker = tp->snd_una;
-	tp->undo_retrans = tp->retrans_out;
+	tp->undo_retrans = tp->retrans_out ? : -1;
 
 	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
 		if (!ece_ack)
@@ -2680,13 +2685,12 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
 	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
-		if (flag & FLAG_ORIG_SACK_ACKED) {
-			/* Step 3.b. A timeout is spurious if not all data are
-			 * lost, i.e., never-retransmitted data are (s)acked.
-			 */
-			tcp_try_undo_loss(sk, true);
+		/* Step 3.b. A timeout is spurious if not all data are
+		 * lost, i.e., never-retransmitted data are (s)acked.
+		 */
+		if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
 			return;
-		}
+
 		if (after(tp->snd_nxt, tp->high_seq) &&
 		    (flag & FLAG_DATA_SACKED || is_dupack)) {
 			tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
@@ -2882,7 +2886,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 }
 
 static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
-				      s32 seq_rtt, s32 sack_rtt)
+				      long seq_rtt_us, long sack_rtt_us)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
@@ -2892,10 +2896,10 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	 * is acked (RFC6298).
 	 */
 	if (flag & FLAG_RETRANS_DATA_ACKED)
-		seq_rtt = -1;
+		seq_rtt_us = -1L;
 
-	if (seq_rtt < 0)
-		seq_rtt = sack_rtt;
+	if (seq_rtt_us < 0)
+		seq_rtt_us = sack_rtt_us;
 
 	/* RTTM Rule: A TSecr value received in a segment is used to
 	 * update the averaged RTT measurement only if the segment
@@ -2903,14 +2907,14 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	 * left edge of the send window.
 	 * See draft-ietf-tcplw-high-performance-00, section 3.3.
 	 */
-	if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
+	if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
 	    flag & FLAG_ACKED)
-		seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
+		seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr);
 
-	if (seq_rtt < 0)
+	if (seq_rtt_us < 0)
 		return false;
 
-	tcp_rtt_estimator(sk, seq_rtt);
+	tcp_rtt_estimator(sk, seq_rtt_us);
 	tcp_set_rto(sk);
 
 	/* RFC6298: only reset backoff on valid RTT measurement. */
@@ -2922,22 +2926,23 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	s32 seq_rtt = -1;
+	long seq_rtt_us = -1L;
 
 	if (synack_stamp && !tp->total_retrans)
-		seq_rtt = tcp_time_stamp - synack_stamp;
+		seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - synack_stamp);
 
 	/* If the ACK acks both the SYNACK and the (Fast Open'd) data packets
 	 * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack()
 	 */
-	if (!tp->srtt)
-		tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1);
+	if (!tp->srtt_us)
+		tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L);
 }
 
-static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
+static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	icsk->icsk_ca_ops->cong_avoid(sk, ack, acked, in_flight);
+
+	icsk->icsk_ca_ops->cong_avoid(sk, ack, acked);
 	tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp;
 }
 
@@ -3020,26 +3025,27 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
  * arrived at the other end.
  */
 static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
-			       u32 prior_snd_una, s32 sack_rtt)
+			       u32 prior_snd_una, long sack_rtt_us)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	struct sk_buff *skb;
-	u32 now = tcp_time_stamp;
+	struct skb_mstamp first_ackt, last_ackt, now;
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 prior_sacked = tp->sacked_out;
+	u32 reord = tp->packets_out;
 	bool fully_acked = true;
-	int flag = 0;
+	long ca_seq_rtt_us = -1L;
+	long seq_rtt_us = -1L;
+	struct sk_buff *skb;
 	u32 pkts_acked = 0;
-	u32 reord = tp->packets_out;
-	u32 prior_sacked = tp->sacked_out;
-	s32 seq_rtt = -1;
-	s32 ca_seq_rtt = -1;
-	ktime_t last_ackt = net_invalid_timestamp();
 	bool rtt_update;
+	int flag = 0;
+
+	first_ackt.v64 = 0;
 
 	while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
-		u32 acked_pcount;
 		u8 sacked = scb->sacked;
+		u32 acked_pcount;
 
 		/* Determine how many packets and what bytes were acked, tso and else */
 		if (after(scb->end_seq, tp->snd_una)) {
@@ -3061,11 +3067,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 				tp->retrans_out -= acked_pcount;
 			flag |= FLAG_RETRANS_DATA_ACKED;
 		} else {
-			ca_seq_rtt = now - scb->when;
-			last_ackt = skb->tstamp;
-			if (seq_rtt < 0) {
-				seq_rtt = ca_seq_rtt;
-			}
+			last_ackt = skb->skb_mstamp;
+			WARN_ON_ONCE(last_ackt.v64 == 0);
+			if (!first_ackt.v64)
+				first_ackt = last_ackt;
+
 			if (!(sacked & TCPCB_SACKED_ACKED))
 				reord = min(pkts_acked, reord);
 			if (!after(scb->end_seq, tp->high_seq))
@@ -3111,7 +3117,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 	if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
 		flag |= FLAG_SACK_RENEGING;
 
-	rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt);
+	skb_mstamp_get(&now);
+	if (first_ackt.v64) {
+		seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt);
+		ca_seq_rtt_us = skb_mstamp_us_delta(&now, &last_ackt);
+	}
+
+	rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us);
 
 	if (flag & FLAG_ACKED) {
 		const struct tcp_congestion_ops *ca_ops
@@ -3139,25 +3151,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 		tp->fackets_out -= min(pkts_acked, tp->fackets_out);
 
-		if (ca_ops->pkts_acked) {
-			s32 rtt_us = -1;
-
-			/* Is the ACK triggering packet unambiguous? */
-			if (!(flag & FLAG_RETRANS_DATA_ACKED)) {
-				/* High resolution needed and available? */
-				if (ca_ops->flags & TCP_CONG_RTT_STAMP &&
-				    !ktime_equal(last_ackt,
-						 net_invalid_timestamp()))
-					rtt_us = ktime_us_delta(ktime_get_real(),
-								last_ackt);
-				else if (ca_seq_rtt >= 0)
-					rtt_us = jiffies_to_usecs(ca_seq_rtt);
-			}
+		if (ca_ops->pkts_acked)
+			ca_ops->pkts_acked(sk, pkts_acked, ca_seq_rtt_us);
 
-			ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
-		}
-	} else if (skb && rtt_update && sack_rtt >= 0 &&
-		   sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) {
+	} else if (skb && rtt_update && sack_rtt_us >= 0 &&
+		   sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) {
 		/* Do not re-arm RTO if the sack RTT is measured from data sent
 		 * after when the head was last (re)transmitted. Otherwise the
 		 * timeout may continue to extend in loss recovery.
@@ -3367,12 +3365,11 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 	bool is_dupack = false;
-	u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
 	u32 prior_fackets;
 	int prior_packets = tp->packets_out;
 	const int prior_unsacked = tp->packets_out - tp->sacked_out;
 	int acked = 0; /* Number of packets newly acked */
-	s32 sack_rtt = -1;
+	long sack_rtt_us = -1L;
 
 	/* If the ack is older than previous acks
 	 * then we can probably ignore it.
@@ -3400,7 +3397,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		flag |= FLAG_SND_UNA_ADVANCED;
 
 	prior_fackets = tp->fackets_out;
-	prior_in_flight = tcp_packets_in_flight(tp);
 
 	/* ts_recent update must be made after we are sure that the packet
 	 * is in window.
@@ -3430,7 +3426,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 		if (TCP_SKB_CB(skb)->sacked)
 			flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
-							&sack_rtt);
+							&sack_rtt_us);
 
 		if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
 			flag |= FLAG_ECE;
@@ -3449,12 +3445,13 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	/* See if we can take anything off of the retransmit queue. */
 	acked = tp->packets_out;
-	flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt);
+	flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una,
+				    sack_rtt_us);
 	acked -= tp->packets_out;
 
 	/* Advance cwnd if state allows */
 	if (tcp_may_raise_cwnd(sk, flag))
-		tcp_cong_avoid(sk, ack, acked, prior_in_flight);
+		tcp_cong_avoid(sk, ack, acked);
 
 	if (tcp_ack_is_dubious(sk, flag)) {
 		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
@@ -3472,8 +3469,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS)
 		tcp_schedule_loss_probe(sk);
-	if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
-		tcp_update_pacing_rate(sk);
+	tcp_update_pacing_rate(sk);
 	return 1;
 
 no_queue:
@@ -3502,7 +3498,7 @@ old_ack:
 	 */
 	if (TCP_SKB_CB(skb)->sacked) {
 		flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
-						&sack_rtt);
+						&sack_rtt_us);
 		tcp_fastretrans_alert(sk, acked, prior_unsacked,
 				      is_dupack, flag);
 	}
@@ -3686,7 +3682,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
 		int opcode = *ptr++;
 		int opsize;
 
-		switch(opcode) {
+		switch (opcode) {
 		case TCPOPT_EOL:
 			return NULL;
 		case TCPOPT_NOP:
@@ -4046,7 +4042,7 @@ static void tcp_sack_remove(struct tcp_sock *tp)
 			WARN_ON(before(tp->rcv_nxt, sp->end_seq));
 
 			/* Zap this SACK, by moving forward any other SACKS. */
-			for (i=this_sack+1; i < num_sacks; i++)
+			for (i = this_sack+1; i < num_sacks; i++)
 				tp->selective_acks[i-1] = tp->selective_acks[i];
 			num_sacks--;
 			continue;
@@ -4416,7 +4412,7 @@ queue_and_out:
 		if (eaten > 0)
 			kfree_skb_partial(skb, fragstolen);
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk, 0);
+			sk->sk_data_ready(sk);
 		return;
 	}
 
@@ -4706,28 +4702,6 @@ static int tcp_prune_queue(struct sock *sk)
 	return -1;
 }
 
-/* RFC2861, slow part. Adjust cwnd, after it was not full during one rto.
- * As additional protections, we do not touch cwnd in retransmission phases,
- * and if application hit its sndbuf limit recently.
- */
-void tcp_cwnd_application_limited(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
-	    sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
-		/* Limited by application or receiver window. */
-		u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk));
-		u32 win_used = max(tp->snd_cwnd_used, init_win);
-		if (win_used < tp->snd_cwnd) {
-			tp->snd_ssthresh = tcp_current_ssthresh(sk);
-			tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1;
-		}
-		tp->snd_cwnd_used = 0;
-	}
-	tp->snd_cwnd_stamp = tcp_time_stamp;
-}
-
 static bool tcp_should_expand_sndbuf(const struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -4917,7 +4891,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
 				BUG();
 			tp->urg_data = TCP_URG_VALID | tmp;
 			if (!sock_flag(sk, SOCK_DEAD))
-				sk->sk_data_ready(sk, 0);
+				sk->sk_data_ready(sk);
 		}
 	}
 }
@@ -5003,11 +4977,11 @@ static bool tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb,
 		    (tcp_flag_word(tcp_hdr(skb)) & TCP_FLAG_PSH) ||
 		    (atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1))) {
 			tp->ucopy.wakeup = 1;
-			sk->sk_data_ready(sk, 0);
+			sk->sk_data_ready(sk);
 		}
 	} else if (chunk > 0) {
 		tp->ucopy.wakeup = 1;
-		sk->sk_data_ready(sk, 0);
+		sk->sk_data_ready(sk);
 	}
 out:
 	return copied_early;
@@ -5278,7 +5252,7 @@ no_ack:
 #endif
 			if (eaten)
 				kfree_skb_partial(skb, fragstolen);
-			sk->sk_data_ready(sk, 0);
+			sk->sk_data_ready(sk);
 			return;
 		}
 	}
@@ -5398,9 +5372,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 				break;
 		}
 		tcp_rearm_rto(sk);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL);
 		return true;
 	}
 	tp->syn_data_acked = tp->syn_data;
+	if (tp->syn_data_acked)
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
 	return false;
 }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 06721392475..77cccda1ad0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -173,7 +173,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
 			      RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
 			      IPPROTO_TCP,
-			      orig_sport, orig_dport, sk, true);
+			      orig_sport, orig_dport, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		if (err == -ENETUNREACH)
@@ -336,8 +336,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	const int code = icmp_hdr(icmp_skb)->code;
 	struct sock *sk;
 	struct sk_buff *skb;
-	struct request_sock *req;
-	__u32 seq;
+	struct request_sock *fastopen;
+	__u32 seq, snd_una;
 	__u32 remaining;
 	int err;
 	struct net *net = dev_net(icmp_skb->dev);
@@ -378,12 +378,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	icsk = inet_csk(sk);
 	tp = tcp_sk(sk);
-	req = tp->fastopen_rsk;
 	seq = ntohl(th->seq);
+	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
+	fastopen = tp->fastopen_rsk;
+	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
-	    !between(seq, tp->snd_una, tp->snd_nxt) &&
-	    (req == NULL || seq != tcp_rsk(req)->snt_isn)) {
-		/* For a Fast Open socket, allow seq to be snt_isn. */
+	    !between(seq, snd_una, tp->snd_nxt)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 		goto out;
 	}
@@ -426,16 +426,14 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH)
 			break;
 		if (seq != tp->snd_una  || !icsk->icsk_retransmits ||
-		    !icsk->icsk_backoff)
+		    !icsk->icsk_backoff || fastopen)
 			break;
 
-		/* XXX (TFO) - revisit the following logic for TFO */
-
 		if (sock_owned_by_user(sk))
 			break;
 
 		icsk->icsk_backoff--;
-		inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) :
+		inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) :
 			TCP_TIMEOUT_INIT) << icsk->icsk_backoff;
 		tcp_bound_rto(sk);
 
@@ -462,14 +460,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		goto out;
 	}
 
-	/* XXX (TFO) - if it's a TFO socket and has been accepted, rather
-	 * than following the TCP_SYN_RECV case and closing the socket,
-	 * we ignore the ICMP error and keep trying like a fully established
-	 * socket. Is this the right thing to do?
-	 */
-	if (req && req->sk == NULL)
-		goto out;
-
 	switch (sk->sk_state) {
 		struct request_sock *req, **prev;
 	case TCP_LISTEN:
@@ -502,10 +492,13 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		goto out;
 
 	case TCP_SYN_SENT:
-	case TCP_SYN_RECV:  /* Cannot happen.
-			       It can f.e. if SYNs crossed,
-			       or Fast Open.
-			     */
+	case TCP_SYN_RECV:
+		/* Only in fast or simultaneous open. If a fast open socket is
+		 * is already accepted it is treated as a connected one below.
+		 */
+		if (fastopen && fastopen->sk == NULL)
+			break;
+
 		if (!sock_owned_by_user(sk)) {
 			sk->sk_err = err;
 
@@ -822,18 +815,19 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
  */
 static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 			      struct request_sock *req,
-			      u16 queue_mapping)
+			      u16 queue_mapping,
+			      struct tcp_fastopen_cookie *foc)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct flowi4 fl4;
 	int err = -1;
-	struct sk_buff * skb;
+	struct sk_buff *skb;
 
 	/* First, grab a route. */
 	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
 		return -1;
 
-	skb = tcp_make_synack(sk, dst, req, NULL);
+	skb = tcp_make_synack(sk, dst, req, foc);
 
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
@@ -852,10 +846,12 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 
 static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req)
 {
-	int res = tcp_v4_send_synack(sk, NULL, req, 0);
+	int res = tcp_v4_send_synack(sk, NULL, req, 0, NULL);
 
-	if (!res)
+	if (!res) {
 		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+	}
 	return res;
 }
 
@@ -878,8 +874,6 @@ bool tcp_syn_flood_action(struct sock *sk,
 	bool want_cookie = false;
 	struct listen_sock *lopt;
 
-
-
 #ifdef CONFIG_SYN_COOKIES
 	if (sysctl_tcp_syncookies) {
 		msg = "Sending cookies";
@@ -1260,187 +1254,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 };
 #endif
 
-static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
-			       struct request_sock *req,
-			       struct tcp_fastopen_cookie *foc,
-			       struct tcp_fastopen_cookie *valid_foc)
-{
-	bool skip_cookie = false;
-	struct fastopen_queue *fastopenq;
-
-	if (likely(!fastopen_cookie_present(foc))) {
-		/* See include/net/tcp.h for the meaning of these knobs */
-		if ((sysctl_tcp_fastopen & TFO_SERVER_ALWAYS) ||
-		    ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD) &&
-		    (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1)))
-			skip_cookie = true; /* no cookie to validate */
-		else
-			return false;
-	}
-	fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
-	/* A FO option is present; bump the counter. */
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE);
-
-	/* Make sure the listener has enabled fastopen, and we don't
-	 * exceed the max # of pending TFO requests allowed before trying
-	 * to validating the cookie in order to avoid burning CPU cycles
-	 * unnecessarily.
-	 *
-	 * XXX (TFO) - The implication of checking the max_qlen before
-	 * processing a cookie request is that clients can't differentiate
-	 * between qlen overflow causing Fast Open to be disabled
-	 * temporarily vs a server not supporting Fast Open at all.
-	 */
-	if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) == 0 ||
-	    fastopenq == NULL || fastopenq->max_qlen == 0)
-		return false;
-
-	if (fastopenq->qlen >= fastopenq->max_qlen) {
-		struct request_sock *req1;
-		spin_lock(&fastopenq->lock);
-		req1 = fastopenq->rskq_rst_head;
-		if ((req1 == NULL) || time_after(req1->expires, jiffies)) {
-			spin_unlock(&fastopenq->lock);
-			NET_INC_STATS_BH(sock_net(sk),
-			    LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
-			/* Avoid bumping LINUX_MIB_TCPFASTOPENPASSIVEFAIL*/
-			foc->len = -1;
-			return false;
-		}
-		fastopenq->rskq_rst_head = req1->dl_next;
-		fastopenq->qlen--;
-		spin_unlock(&fastopenq->lock);
-		reqsk_free(req1);
-	}
-	if (skip_cookie) {
-		tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-		return true;
-	}
-
-	if (foc->len == TCP_FASTOPEN_COOKIE_SIZE) {
-		if ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_CHKED) == 0) {
-			tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
-						ip_hdr(skb)->daddr, valid_foc);
-			if ((valid_foc->len != TCP_FASTOPEN_COOKIE_SIZE) ||
-			    memcmp(&foc->val[0], &valid_foc->val[0],
-			    TCP_FASTOPEN_COOKIE_SIZE) != 0)
-				return false;
-			valid_foc->len = -1;
-		}
-		/* Acknowledge the data received from the peer. */
-		tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-		return true;
-	} else if (foc->len == 0) { /* Client requesting a cookie */
-		tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
-					ip_hdr(skb)->daddr, valid_foc);
-		NET_INC_STATS_BH(sock_net(sk),
-		    LINUX_MIB_TCPFASTOPENCOOKIEREQD);
-	} else {
-		/* Client sent a cookie with wrong size. Treat it
-		 * the same as invalid and return a valid one.
-		 */
-		tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
-					ip_hdr(skb)->daddr, valid_foc);
-	}
-	return false;
-}
-
-static int tcp_v4_conn_req_fastopen(struct sock *sk,
-				    struct sk_buff *skb,
-				    struct sk_buff *skb_synack,
-				    struct request_sock *req)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
-	const struct inet_request_sock *ireq = inet_rsk(req);
-	struct sock *child;
-	int err;
-
-	req->num_retrans = 0;
-	req->num_timeout = 0;
-	req->sk = NULL;
-
-	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
-	if (child == NULL) {
-		NET_INC_STATS_BH(sock_net(sk),
-				 LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
-		kfree_skb(skb_synack);
-		return -1;
-	}
-	err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
-				    ireq->ir_rmt_addr, ireq->opt);
-	err = net_xmit_eval(err);
-	if (!err)
-		tcp_rsk(req)->snt_synack = tcp_time_stamp;
-	/* XXX (TFO) - is it ok to ignore error and continue? */
-
-	spin_lock(&queue->fastopenq->lock);
-	queue->fastopenq->qlen++;
-	spin_unlock(&queue->fastopenq->lock);
-
-	/* Initialize the child socket. Have to fix some values to take
-	 * into account the child is a Fast Open socket and is created
-	 * only out of the bits carried in the SYN packet.
-	 */
-	tp = tcp_sk(child);
-
-	tp->fastopen_rsk = req;
-	/* Do a hold on the listner sk so that if the listener is being
-	 * closed, the child that has been accepted can live on and still
-	 * access listen_lock.
-	 */
-	sock_hold(sk);
-	tcp_rsk(req)->listener = sk;
-
-	/* RFC1323: The window in SYN & SYN/ACK segments is never
-	 * scaled. So correct it appropriately.
-	 */
-	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
-
-	/* Activate the retrans timer so that SYNACK can be retransmitted.
-	 * The request socket is not added to the SYN table of the parent
-	 * because it's been added to the accept queue directly.
-	 */
-	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
-	    TCP_TIMEOUT_INIT, TCP_RTO_MAX);
-
-	/* Add the child socket directly into the accept queue */
-	inet_csk_reqsk_queue_add(sk, req, child);
-
-	/* Now finish processing the fastopen child socket. */
-	inet_csk(child)->icsk_af_ops->rebuild_header(child);
-	tcp_init_congestion_control(child);
-	tcp_mtup_init(child);
-	tcp_init_metrics(child);
-	tcp_init_buffer_space(child);
-
-	/* Queue the data carried in the SYN packet. We need to first
-	 * bump skb's refcnt because the caller will attempt to free it.
-	 *
-	 * XXX (TFO) - we honor a zero-payload TFO request for now.
-	 * (Any reason not to?)
-	 */
-	if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq + 1) {
-		/* Don't queue the skb if there is no payload in SYN.
-		 * XXX (TFO) - How about SYN+FIN?
-		 */
-		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-	} else {
-		skb = skb_get(skb);
-		skb_dst_drop(skb);
-		__skb_pull(skb, tcp_hdr(skb)->doff * 4);
-		skb_set_owner_r(skb, child);
-		__skb_queue_tail(&child->sk_receive_queue, skb);
-		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-		tp->syn_data_acked = 1;
-	}
-	sk->sk_data_ready(sk, 0);
-	bh_unlock_sock(child);
-	sock_put(child);
-	WARN_ON(req->sk == NULL);
-	return 0;
-}
-
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_options_received tmp_opt;
@@ -1451,12 +1264,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	__be32 saddr = ip_hdr(skb)->saddr;
 	__be32 daddr = ip_hdr(skb)->daddr;
 	__u32 isn = TCP_SKB_CB(skb)->when;
-	bool want_cookie = false;
+	bool want_cookie = false, fastopen;
 	struct flowi4 fl4;
 	struct tcp_fastopen_cookie foc = { .len = -1 };
-	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
-	struct sk_buff *skb_synack;
-	int do_fastopen;
+	int err;
 
 	/* Never answer to SYNs send to broadcast or multicast */
 	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
@@ -1507,6 +1318,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	ireq->ir_rmt_addr = saddr;
 	ireq->no_srccheck = inet_sk(sk)->transparent;
 	ireq->opt = tcp_v4_save_options(skb);
+	ireq->ir_mark = inet_request_mark(sk, skb);
 
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_free;
@@ -1555,52 +1367,24 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 
 		isn = tcp_v4_init_sequence(skb);
 	}
-	tcp_rsk(req)->snt_isn = isn;
-
-	if (dst == NULL) {
-		dst = inet_csk_route_req(sk, &fl4, req);
-		if (dst == NULL)
-			goto drop_and_free;
-	}
-	do_fastopen = tcp_fastopen_check(sk, skb, req, &foc, &valid_foc);
-
-	/* We don't call tcp_v4_send_synack() directly because we need
-	 * to make sure a child socket can be created successfully before
-	 * sending back synack!
-	 *
-	 * XXX (TFO) - Ideally one would simply call tcp_v4_send_synack()
-	 * (or better yet, call tcp_send_synack() in the child context
-	 * directly, but will have to fix bunch of other code first)
-	 * after syn_recv_sock() except one will need to first fix the
-	 * latter to remove its dependency on the current implementation
-	 * of tcp_v4_send_synack()->tcp_select_initial_window().
-	 */
-	skb_synack = tcp_make_synack(sk, dst, req,
-	    fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL);
-
-	if (skb_synack) {
-		__tcp_v4_send_check(skb_synack, ireq->ir_loc_addr, ireq->ir_rmt_addr);
-		skb_set_queue_mapping(skb_synack, skb_get_queue_mapping(skb));
-	} else
+	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
 		goto drop_and_free;
 
-	if (likely(!do_fastopen)) {
-		int err;
-		err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
-		     ireq->ir_rmt_addr, ireq->opt);
-		err = net_xmit_eval(err);
+	tcp_rsk(req)->snt_isn = isn;
+	tcp_rsk(req)->snt_synack = tcp_time_stamp;
+	tcp_openreq_init_rwin(req, sk, dst);
+	fastopen = !want_cookie &&
+		   tcp_try_fastopen(sk, skb, req, &foc, dst);
+	err = tcp_v4_send_synack(sk, dst, req,
+				 skb_get_queue_mapping(skb), &foc);
+	if (!fastopen) {
 		if (err || want_cookie)
 			goto drop_and_free;
 
 		tcp_rsk(req)->snt_synack = tcp_time_stamp;
 		tcp_rsk(req)->listener = NULL;
-		/* Add the request_sock to the SYN table */
 		inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
-		if (fastopen_cookie_present(&foc) && foc.len != 0)
-			NET_INC_STATS_BH(sock_net(sk),
-			    LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
-	} else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req))
-		goto drop_and_free;
+	}
 
 	return 0;
 
@@ -1668,7 +1452,6 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	}
 	sk_setup_caps(newsk, dst);
 
-	tcp_mtup_init(newsk);
 	tcp_sync_mss(newsk, dst_mtu(dst));
 	newtp->advmss = dst_metric_advmss(dst);
 	if (tcp_sk(sk)->rx_opt.user_mss &&
@@ -1745,28 +1528,6 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 	return sk;
 }
 
-static __sum16 tcp_v4_checksum_init(struct sk_buff *skb)
-{
-	const struct iphdr *iph = ip_hdr(skb);
-
-	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		if (!tcp_v4_check(skb->len, iph->saddr,
-				  iph->daddr, skb->csum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			return 0;
-		}
-	}
-
-	skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-				       skb->len, IPPROTO_TCP, 0);
-
-	if (skb->len <= 76) {
-		return __skb_checksum_complete(skb);
-	}
-	return 0;
-}
-
-
 /* The socket must have it's spinlock held when we get
  * here.
  *
@@ -1961,7 +1722,8 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	 * Packet length and doff are validated by header prediction,
 	 * provided case of th->doff==0 is eliminated.
 	 * So, we defer the checks. */
-	if (!skb_csum_unnecessary(skb) && tcp_v4_checksum_init(skb))
+
+	if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo))
 		goto csum_error;
 
 	th = tcp_hdr(skb);
@@ -2629,7 +2391,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw,
 {
 	__be32 dest, src;
 	__u16 destp, srcp;
-	long delta = tw->tw_ttd - jiffies;
+	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
 	dest  = tw->tw_daddr;
 	src   = tw->tw_rcv_saddr;
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 991d62a2f9b..1e70fa8fa79 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -115,13 +115,12 @@ static void tcp_lp_init(struct sock *sk)
  * Will only call newReno CA when away from inference.
  * From TCP-LP's paper, this will be handled in additive increasement.
  */
-static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-			      u32 in_flight)
+static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct lp *lp = inet_csk_ca(sk);
 
 	if (!(lp->flag & LP_WITHIN_INF))
-		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked);
 }
 
 /**
@@ -315,11 +314,9 @@ static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us)
 }
 
 static struct tcp_congestion_ops tcp_lp __read_mostly = {
-	.flags = TCP_CONG_RTT_STAMP,
 	.init = tcp_lp_init,
 	.ssthresh = tcp_reno_ssthresh,
 	.cong_avoid = tcp_lp_cong_avoid,
-	.min_cwnd = tcp_reno_min_cwnd,
 	.pkts_acked = tcp_lp_pkts_acked,
 
 	.owner = THIS_MODULE,
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index f7e522c558b..f7a2ec3ac58 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -102,17 +102,19 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	return 0;
 }
 
-static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			    const char *buffer)
+static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 	unsigned long long val;
 	int ret = 0;
 
-	switch (cft->private) {
+	buf = strstrip(buf);
+
+	switch (of_cft(of)->private) {
 	case RES_LIMIT:
 		/* see memcontrol.c */
-		ret = res_counter_memparse_write_strategy(buffer, &val);
+		ret = res_counter_memparse_write_strategy(buf, &val);
 		if (ret)
 			break;
 		ret = tcp_update_limit(memcg, val);
@@ -121,7 +123,7 @@ static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
 		ret = -EINVAL;
 		break;
 	}
-	return ret;
+	return ret ?: nbytes;
 }
 
 static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
@@ -168,17 +170,18 @@ static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
 	return val;
 }
 
-static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
+static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg;
 	struct cg_proto *cg_proto;
 
-	memcg = mem_cgroup_from_css(css);
+	memcg = mem_cgroup_from_css(of_css(of));
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
-		return 0;
+		return nbytes;
 
-	switch (event) {
+	switch (of_cft(of)->private) {
 	case RES_MAX_USAGE:
 		res_counter_reset_max(&cg_proto->memory_allocated);
 		break;
@@ -187,13 +190,13 @@ static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
 		break;
 	}
 
-	return 0;
+	return nbytes;
 }
 
 static struct cftype tcp_files[] = {
 	{
 		.name = "kmem.tcp.limit_in_bytes",
-		.write_string = tcp_cgroup_write,
+		.write = tcp_cgroup_write,
 		.read_u64 = tcp_cgroup_read,
 		.private = RES_LIMIT,
 	},
@@ -205,13 +208,13 @@ static struct cftype tcp_files[] = {
 	{
 		.name = "kmem.tcp.failcnt",
 		.private = RES_FAILCNT,
-		.trigger = tcp_cgroup_reset,
+		.write = tcp_cgroup_reset,
 		.read_u64 = tcp_cgroup_read,
 	},
 	{
 		.name = "kmem.tcp.max_usage_in_bytes",
 		.private = RES_MAX_USAGE,
-		.trigger = tcp_cgroup_reset,
+		.write = tcp_cgroup_reset,
 		.read_u64 = tcp_cgroup_read,
 	},
 	{ }	/* terminate */
@@ -219,7 +222,7 @@ static struct cftype tcp_files[] = {
 
 static int __init tcp_memcontrol_init(void)
 {
-	WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, tcp_files));
+	WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, tcp_files));
 	return 0;
 }
 __initcall(tcp_memcontrol_init);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 06493736fbc..4fe04180598 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -22,6 +22,10 @@
 
 int sysctl_tcp_nometrics_save __read_mostly;
 
+static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *saddr,
+						   const struct inetpeer_addr *daddr,
+						   struct net *net, unsigned int hash);
+
 struct tcp_fastopen_metrics {
 	u16	mss;
 	u16	syn_loss:10;		/* Recurring Fast Open SYN losses */
@@ -29,14 +33,20 @@ struct tcp_fastopen_metrics {
 	struct	tcp_fastopen_cookie	cookie;
 };
 
+/* TCP_METRIC_MAX includes 2 extra fields for userspace compatibility
+ * Kernel only stores RTT and RTTVAR in usec resolution
+ */
+#define TCP_METRIC_MAX_KERNEL (TCP_METRIC_MAX - 2)
+
 struct tcp_metrics_block {
 	struct tcp_metrics_block __rcu	*tcpm_next;
-	struct inetpeer_addr		tcpm_addr;
+	struct inetpeer_addr		tcpm_saddr;
+	struct inetpeer_addr		tcpm_daddr;
 	unsigned long			tcpm_stamp;
 	u32				tcpm_ts;
 	u32				tcpm_ts_stamp;
 	u32				tcpm_lock;
-	u32				tcpm_vals[TCP_METRIC_MAX + 1];
+	u32				tcpm_vals[TCP_METRIC_MAX_KERNEL + 1];
 	struct tcp_fastopen_metrics	tcpm_fastopen;
 
 	struct rcu_head			rcu_head;
@@ -54,12 +64,6 @@ static u32 tcp_metric_get(struct tcp_metrics_block *tm,
 	return tm->tcpm_vals[idx];
 }
 
-static u32 tcp_metric_get_jiffies(struct tcp_metrics_block *tm,
-				  enum tcp_metric_index idx)
-{
-	return msecs_to_jiffies(tm->tcpm_vals[idx]);
-}
-
 static void tcp_metric_set(struct tcp_metrics_block *tm,
 			   enum tcp_metric_index idx,
 			   u32 val)
@@ -67,13 +71,6 @@ static void tcp_metric_set(struct tcp_metrics_block *tm,
 	tm->tcpm_vals[idx] = val;
 }
 
-static void tcp_metric_set_msecs(struct tcp_metrics_block *tm,
-				 enum tcp_metric_index idx,
-				 u32 val)
-{
-	tm->tcpm_vals[idx] = jiffies_to_msecs(val);
-}
-
 static bool addr_same(const struct inetpeer_addr *a,
 		      const struct inetpeer_addr *b)
 {
@@ -96,9 +93,11 @@ struct tcpm_hash_bucket {
 
 static DEFINE_SPINLOCK(tcp_metrics_lock);
 
-static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
+static void tcpm_suck_dst(struct tcp_metrics_block *tm,
+			  const struct dst_entry *dst,
 			  bool fastopen_clear)
 {
+	u32 msval;
 	u32 val;
 
 	tm->tcpm_stamp = jiffies;
@@ -116,8 +115,11 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
 		val |= 1 << TCP_METRIC_REORDERING;
 	tm->tcpm_lock = val;
 
-	tm->tcpm_vals[TCP_METRIC_RTT] = dst_metric_raw(dst, RTAX_RTT);
-	tm->tcpm_vals[TCP_METRIC_RTTVAR] = dst_metric_raw(dst, RTAX_RTTVAR);
+	msval = dst_metric_raw(dst, RTAX_RTT);
+	tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC;
+
+	msval = dst_metric_raw(dst, RTAX_RTTVAR);
+	tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC;
 	tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
 	tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
 	tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
@@ -130,16 +132,42 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
 	}
 }
 
+#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
+
+static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
+{
+	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
+		tcpm_suck_dst(tm, dst, false);
+}
+
+#define TCP_METRICS_RECLAIM_DEPTH	5
+#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
+
 static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
-					  struct inetpeer_addr *addr,
-					  unsigned int hash,
-					  bool reclaim)
+					  struct inetpeer_addr *saddr,
+					  struct inetpeer_addr *daddr,
+					  unsigned int hash)
 {
 	struct tcp_metrics_block *tm;
 	struct net *net;
+	bool reclaim = false;
 
 	spin_lock_bh(&tcp_metrics_lock);
 	net = dev_net(dst->dev);
+
+	/* While waiting for the spin-lock the cache might have been populated
+	 * with this entry and so we have to check again.
+	 */
+	tm = __tcp_get_metrics(saddr, daddr, net, hash);
+	if (tm == TCP_METRICS_RECLAIM_PTR) {
+		reclaim = true;
+		tm = NULL;
+	}
+	if (tm) {
+		tcpm_check_stamp(tm, dst);
+		goto out_unlock;
+	}
+
 	if (unlikely(reclaim)) {
 		struct tcp_metrics_block *oldest;
 
@@ -155,7 +183,8 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
 		if (!tm)
 			goto out_unlock;
 	}
-	tm->tcpm_addr = *addr;
+	tm->tcpm_saddr = *saddr;
+	tm->tcpm_daddr = *daddr;
 
 	tcpm_suck_dst(tm, dst, true);
 
@@ -169,17 +198,6 @@ out_unlock:
 	return tm;
 }
 
-#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
-
-static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
-{
-	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
-		tcpm_suck_dst(tm, dst, false);
-}
-
-#define TCP_METRICS_RECLAIM_DEPTH	5
-#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
-
 static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth)
 {
 	if (tm)
@@ -189,7 +207,8 @@ static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, in
 	return NULL;
 }
 
-static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr,
+static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *saddr,
+						   const struct inetpeer_addr *daddr,
 						   struct net *net, unsigned int hash)
 {
 	struct tcp_metrics_block *tm;
@@ -197,7 +216,8 @@ static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *a
 
 	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
 	     tm = rcu_dereference(tm->tcpm_next)) {
-		if (addr_same(&tm->tcpm_addr, addr))
+		if (addr_same(&tm->tcpm_saddr, saddr) &&
+		    addr_same(&tm->tcpm_daddr, daddr))
 			break;
 		depth++;
 	}
@@ -208,19 +228,22 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 						       struct dst_entry *dst)
 {
 	struct tcp_metrics_block *tm;
-	struct inetpeer_addr addr;
+	struct inetpeer_addr saddr, daddr;
 	unsigned int hash;
 	struct net *net;
 
-	addr.family = req->rsk_ops->family;
-	switch (addr.family) {
+	saddr.family = req->rsk_ops->family;
+	daddr.family = req->rsk_ops->family;
+	switch (daddr.family) {
 	case AF_INET:
-		addr.addr.a4 = inet_rsk(req)->ir_rmt_addr;
-		hash = (__force unsigned int) addr.addr.a4;
+		saddr.addr.a4 = inet_rsk(req)->ir_loc_addr;
+		daddr.addr.a4 = inet_rsk(req)->ir_rmt_addr;
+		hash = (__force unsigned int) daddr.addr.a4;
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		*(struct in6_addr *)addr.addr.a6 = inet_rsk(req)->ir_v6_rmt_addr;
+		*(struct in6_addr *)saddr.addr.a6 = inet_rsk(req)->ir_v6_loc_addr;
+		*(struct in6_addr *)daddr.addr.a6 = inet_rsk(req)->ir_v6_rmt_addr;
 		hash = ipv6_addr_hash(&inet_rsk(req)->ir_v6_rmt_addr);
 		break;
 #endif
@@ -233,7 +256,8 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 
 	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
 	     tm = rcu_dereference(tm->tcpm_next)) {
-		if (addr_same(&tm->tcpm_addr, &addr))
+		if (addr_same(&tm->tcpm_saddr, &saddr) &&
+		    addr_same(&tm->tcpm_daddr, &daddr))
 			break;
 	}
 	tcpm_check_stamp(tm, dst);
@@ -243,32 +267,44 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)
 {
 	struct tcp_metrics_block *tm;
-	struct inetpeer_addr addr;
+	struct inetpeer_addr saddr, daddr;
 	unsigned int hash;
 	struct net *net;
 
-	addr.family = tw->tw_family;
-	switch (addr.family) {
-	case AF_INET:
-		addr.addr.a4 = tw->tw_daddr;
-		hash = (__force unsigned int) addr.addr.a4;
-		break;
+	if (tw->tw_family == AF_INET) {
+		saddr.family = AF_INET;
+		saddr.addr.a4 = tw->tw_rcv_saddr;
+		daddr.family = AF_INET;
+		daddr.addr.a4 = tw->tw_daddr;
+		hash = (__force unsigned int) daddr.addr.a4;
+	}
 #if IS_ENABLED(CONFIG_IPV6)
-	case AF_INET6:
-		*(struct in6_addr *)addr.addr.a6 = tw->tw_v6_daddr;
-		hash = ipv6_addr_hash(&tw->tw_v6_daddr);
-		break;
+	else if (tw->tw_family == AF_INET6) {
+		if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) {
+			saddr.family = AF_INET;
+			saddr.addr.a4 = tw->tw_rcv_saddr;
+			daddr.family = AF_INET;
+			daddr.addr.a4 = tw->tw_daddr;
+			hash = (__force unsigned int) daddr.addr.a4;
+		} else {
+			saddr.family = AF_INET6;
+			*(struct in6_addr *)saddr.addr.a6 = tw->tw_v6_rcv_saddr;
+			daddr.family = AF_INET6;
+			*(struct in6_addr *)daddr.addr.a6 = tw->tw_v6_daddr;
+			hash = ipv6_addr_hash(&tw->tw_v6_daddr);
+		}
+	}
 #endif
-	default:
+	else
 		return NULL;
-	}
 
 	net = twsk_net(tw);
 	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
 
 	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
 	     tm = rcu_dereference(tm->tcpm_next)) {
-		if (addr_same(&tm->tcpm_addr, &addr))
+		if (addr_same(&tm->tcpm_saddr, &saddr) &&
+		    addr_same(&tm->tcpm_daddr, &daddr))
 			break;
 	}
 	return tm;
@@ -279,38 +315,45 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 						 bool create)
 {
 	struct tcp_metrics_block *tm;
-	struct inetpeer_addr addr;
+	struct inetpeer_addr saddr, daddr;
 	unsigned int hash;
 	struct net *net;
-	bool reclaim;
 
-	addr.family = sk->sk_family;
-	switch (addr.family) {
-	case AF_INET:
-		addr.addr.a4 = inet_sk(sk)->inet_daddr;
-		hash = (__force unsigned int) addr.addr.a4;
-		break;
+	if (sk->sk_family == AF_INET) {
+		saddr.family = AF_INET;
+		saddr.addr.a4 = inet_sk(sk)->inet_saddr;
+		daddr.family = AF_INET;
+		daddr.addr.a4 = inet_sk(sk)->inet_daddr;
+		hash = (__force unsigned int) daddr.addr.a4;
+	}
 #if IS_ENABLED(CONFIG_IPV6)
-	case AF_INET6:
-		*(struct in6_addr *)addr.addr.a6 = sk->sk_v6_daddr;
-		hash = ipv6_addr_hash(&sk->sk_v6_daddr);
-		break;
+	else if (sk->sk_family == AF_INET6) {
+		if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) {
+			saddr.family = AF_INET;
+			saddr.addr.a4 = inet_sk(sk)->inet_saddr;
+			daddr.family = AF_INET;
+			daddr.addr.a4 = inet_sk(sk)->inet_daddr;
+			hash = (__force unsigned int) daddr.addr.a4;
+		} else {
+			saddr.family = AF_INET6;
+			*(struct in6_addr *)saddr.addr.a6 = sk->sk_v6_rcv_saddr;
+			daddr.family = AF_INET6;
+			*(struct in6_addr *)daddr.addr.a6 = sk->sk_v6_daddr;
+			hash = ipv6_addr_hash(&sk->sk_v6_daddr);
+		}
+	}
 #endif
-	default:
+	else
 		return NULL;
-	}
 
 	net = dev_net(dst->dev);
 	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
 
-	tm = __tcp_get_metrics(&addr, net, hash);
-	reclaim = false;
-	if (tm == TCP_METRICS_RECLAIM_PTR) {
-		reclaim = true;
+	tm = __tcp_get_metrics(&saddr, &daddr, net, hash);
+	if (tm == TCP_METRICS_RECLAIM_PTR)
 		tm = NULL;
-	}
 	if (!tm && create)
-		tm = tcpm_new(dst, &addr, hash, reclaim);
+		tm = tcpm_new(dst, &saddr, &daddr, hash);
 	else
 		tcpm_check_stamp(tm, dst);
 
@@ -338,7 +381,7 @@ void tcp_update_metrics(struct sock *sk)
 		dst_confirm(dst);
 
 	rcu_read_lock();
-	if (icsk->icsk_backoff || !tp->srtt) {
+	if (icsk->icsk_backoff || !tp->srtt_us) {
 		/* This session failed to estimate rtt. Why?
 		 * Probably, no packets returned in time.  Reset our
 		 * results.
@@ -353,8 +396,8 @@ void tcp_update_metrics(struct sock *sk)
 	if (!tm)
 		goto out_unlock;
 
-	rtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT);
-	m = rtt - tp->srtt;
+	rtt = tcp_metric_get(tm, TCP_METRIC_RTT);
+	m = rtt - tp->srtt_us;
 
 	/* If newly calculated rtt larger than stored one, store new
 	 * one. Otherwise, use EWMA. Remember, rtt overestimation is
@@ -362,10 +405,10 @@ void tcp_update_metrics(struct sock *sk)
 	 */
 	if (!tcp_metric_locked(tm, TCP_METRIC_RTT)) {
 		if (m <= 0)
-			rtt = tp->srtt;
+			rtt = tp->srtt_us;
 		else
 			rtt -= (m >> 3);
-		tcp_metric_set_msecs(tm, TCP_METRIC_RTT, rtt);
+		tcp_metric_set(tm, TCP_METRIC_RTT, rtt);
 	}
 
 	if (!tcp_metric_locked(tm, TCP_METRIC_RTTVAR)) {
@@ -376,16 +419,16 @@ void tcp_update_metrics(struct sock *sk)
 
 		/* Scale deviation to rttvar fixed point */
 		m >>= 1;
-		if (m < tp->mdev)
-			m = tp->mdev;
+		if (m < tp->mdev_us)
+			m = tp->mdev_us;
 
-		var = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR);
+		var = tcp_metric_get(tm, TCP_METRIC_RTTVAR);
 		if (m >= var)
 			var = m;
 		else
 			var -= (var - m) >> 2;
 
-		tcp_metric_set_msecs(tm, TCP_METRIC_RTTVAR, var);
+		tcp_metric_set(tm, TCP_METRIC_RTTVAR, var);
 	}
 
 	if (tcp_in_initial_slowstart(tp)) {
@@ -482,7 +525,7 @@ void tcp_init_metrics(struct sock *sk)
 		tp->reordering = val;
 	}
 
-	crtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT);
+	crtt = tcp_metric_get(tm, TCP_METRIC_RTT);
 	rcu_read_unlock();
 reset:
 	/* The initial RTT measurement from the SYN/SYN-ACK is not ideal
@@ -505,18 +548,20 @@ reset:
 	 * to low value, and then abruptly stops to do it and starts to delay
 	 * ACKs, wait for troubles.
 	 */
-	if (crtt > tp->srtt) {
+	if (crtt > tp->srtt_us) {
 		/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
-		crtt >>= 3;
+		crtt /= 8 * USEC_PER_MSEC;
 		inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
-	} else if (tp->srtt == 0) {
+	} else if (tp->srtt_us == 0) {
 		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
 		 * 3WHS. This is most likely due to retransmission,
 		 * including spurious one. Reset the RTO back to 3secs
 		 * from the more aggressive 1sec to avoid more spurious
 		 * retransmission.
 		 */
-		tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK;
+		tp->rttvar_us = jiffies_to_usecs(TCP_TIMEOUT_FALLBACK);
+		tp->mdev_us = tp->mdev_max_us = tp->rttvar_us;
+
 		inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK;
 	}
 	/* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
@@ -724,15 +769,21 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 	struct nlattr *nest;
 	int i;
 
-	switch (tm->tcpm_addr.family) {
+	switch (tm->tcpm_daddr.family) {
 	case AF_INET:
 		if (nla_put_be32(msg, TCP_METRICS_ATTR_ADDR_IPV4,
-				tm->tcpm_addr.addr.a4) < 0)
+				tm->tcpm_daddr.addr.a4) < 0)
+			goto nla_put_failure;
+		if (nla_put_be32(msg, TCP_METRICS_ATTR_SADDR_IPV4,
+				tm->tcpm_saddr.addr.a4) < 0)
 			goto nla_put_failure;
 		break;
 	case AF_INET6:
 		if (nla_put(msg, TCP_METRICS_ATTR_ADDR_IPV6, 16,
-			    tm->tcpm_addr.addr.a6) < 0)
+			    tm->tcpm_daddr.addr.a6) < 0)
+			goto nla_put_failure;
+		if (nla_put(msg, TCP_METRICS_ATTR_SADDR_IPV6, 16,
+			    tm->tcpm_saddr.addr.a6) < 0)
 			goto nla_put_failure;
 		break;
 	default:
@@ -757,10 +808,26 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 		nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS);
 		if (!nest)
 			goto nla_put_failure;
-		for (i = 0; i < TCP_METRIC_MAX + 1; i++) {
-			if (!tm->tcpm_vals[i])
+		for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) {
+			u32 val = tm->tcpm_vals[i];
+
+			if (!val)
 				continue;
-			if (nla_put_u32(msg, i + 1, tm->tcpm_vals[i]) < 0)
+			if (i == TCP_METRIC_RTT) {
+				if (nla_put_u32(msg, TCP_METRIC_RTT_US + 1,
+						val) < 0)
+					goto nla_put_failure;
+				n++;
+				val = max(val / 1000, 1U);
+			}
+			if (i == TCP_METRIC_RTTVAR) {
+				if (nla_put_u32(msg, TCP_METRIC_RTTVAR_US + 1,
+						val) < 0)
+					goto nla_put_failure;
+				n++;
+				val = max(val / 1000, 1U);
+			}
+			if (nla_put_u32(msg, i + 1, val) < 0)
 				goto nla_put_failure;
 			n++;
 		}
@@ -855,44 +922,66 @@ done:
 	return skb->len;
 }
 
-static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
-			 unsigned int *hash, int optional)
+static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
+			   unsigned int *hash, int optional, int v4, int v6)
 {
 	struct nlattr *a;
 
-	a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV4];
+	a = info->attrs[v4];
 	if (a) {
 		addr->family = AF_INET;
 		addr->addr.a4 = nla_get_be32(a);
-		*hash = (__force unsigned int) addr->addr.a4;
+		if (hash)
+			*hash = (__force unsigned int) addr->addr.a4;
 		return 0;
 	}
-	a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV6];
+	a = info->attrs[v6];
 	if (a) {
 		if (nla_len(a) != sizeof(struct in6_addr))
 			return -EINVAL;
 		addr->family = AF_INET6;
 		memcpy(addr->addr.a6, nla_data(a), sizeof(addr->addr.a6));
-		*hash = ipv6_addr_hash((struct in6_addr *) addr->addr.a6);
+		if (hash)
+			*hash = ipv6_addr_hash((struct in6_addr *) addr->addr.a6);
 		return 0;
 	}
 	return optional ? 1 : -EAFNOSUPPORT;
 }
 
+static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
+			 unsigned int *hash, int optional)
+{
+	return __parse_nl_addr(info, addr, hash, optional,
+			       TCP_METRICS_ATTR_ADDR_IPV4,
+			       TCP_METRICS_ATTR_ADDR_IPV6);
+}
+
+static int parse_nl_saddr(struct genl_info *info, struct inetpeer_addr *addr)
+{
+	return __parse_nl_addr(info, addr, NULL, 0,
+			       TCP_METRICS_ATTR_SADDR_IPV4,
+			       TCP_METRICS_ATTR_SADDR_IPV6);
+}
+
 static int tcp_metrics_nl_cmd_get(struct sk_buff *skb, struct genl_info *info)
 {
 	struct tcp_metrics_block *tm;
-	struct inetpeer_addr addr;
+	struct inetpeer_addr saddr, daddr;
 	unsigned int hash;
 	struct sk_buff *msg;
 	struct net *net = genl_info_net(info);
 	void *reply;
 	int ret;
+	bool src = true;
 
-	ret = parse_nl_addr(info, &addr, &hash, 0);
+	ret = parse_nl_addr(info, &daddr, &hash, 0);
 	if (ret < 0)
 		return ret;
 
+	ret = parse_nl_saddr(info, &saddr);
+	if (ret < 0)
+		src = false;
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
@@ -907,7 +996,8 @@ static int tcp_metrics_nl_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	rcu_read_lock();
 	for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
 	     tm = rcu_dereference(tm->tcpm_next)) {
-		if (addr_same(&tm->tcpm_addr, &addr)) {
+		if (addr_same(&tm->tcpm_daddr, &daddr) &&
+		    (!src || addr_same(&tm->tcpm_saddr, &saddr))) {
 			ret = tcp_metrics_fill_info(msg, tm);
 			break;
 		}
@@ -962,32 +1052,38 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct tcpm_hash_bucket *hb;
 	struct tcp_metrics_block *tm;
 	struct tcp_metrics_block __rcu **pp;
-	struct inetpeer_addr addr;
+	struct inetpeer_addr saddr, daddr;
 	unsigned int hash;
 	struct net *net = genl_info_net(info);
 	int ret;
+	bool src = true, found = false;
 
-	ret = parse_nl_addr(info, &addr, &hash, 1);
+	ret = parse_nl_addr(info, &daddr, &hash, 1);
 	if (ret < 0)
 		return ret;
 	if (ret > 0)
 		return tcp_metrics_flush_all(net);
+	ret = parse_nl_saddr(info, &saddr);
+	if (ret < 0)
+		src = false;
 
 	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
 	hb = net->ipv4.tcp_metrics_hash + hash;
 	pp = &hb->chain;
 	spin_lock_bh(&tcp_metrics_lock);
-	for (tm = deref_locked_genl(*pp); tm;
-	     pp = &tm->tcpm_next, tm = deref_locked_genl(*pp)) {
-		if (addr_same(&tm->tcpm_addr, &addr)) {
+	for (tm = deref_locked_genl(*pp); tm; tm = deref_locked_genl(*pp)) {
+		if (addr_same(&tm->tcpm_daddr, &daddr) &&
+		    (!src || addr_same(&tm->tcpm_saddr, &saddr))) {
 			*pp = tm->tcpm_next;
-			break;
+			kfree_rcu(tm, rcu_head);
+			found = true;
+		} else {
+			pp = &tm->tcpm_next;
 		}
 	}
 	spin_unlock_bh(&tcp_metrics_lock);
-	if (!tm)
+	if (!found)
 		return -ESRCH;
-	kfree_rcu(tm, rcu_head);
 	return 0;
 }
 
@@ -1063,10 +1159,7 @@ static void __net_exit tcp_net_metrics_exit(struct net *net)
 			tm = next;
 		}
 	}
-	if (is_vmalloc_addr(net->ipv4.tcp_metrics_hash))
-		vfree(net->ipv4.tcp_metrics_hash);
-	else
-		kfree(net->ipv4.tcp_metrics_hash);
+	kvfree(net->ipv4.tcp_metrics_hash);
 }
 
 static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 97b68415986..e68e0d4af6c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -297,6 +297,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 			tw->tw_v6_daddr = sk->sk_v6_daddr;
 			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 			tw->tw_tclass = np->tclass;
+			tw->tw_flowlabel = np->flow_label >> 12;
 			tw->tw_ipv6only = np->ipv6only;
 		}
 #endif
@@ -361,6 +362,37 @@ void tcp_twsk_destructor(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
 
+void tcp_openreq_init_rwin(struct request_sock *req,
+			   struct sock *sk, struct dst_entry *dst)
+{
+	struct inet_request_sock *ireq = inet_rsk(req);
+	struct tcp_sock *tp = tcp_sk(sk);
+	__u8 rcv_wscale;
+	int mss = dst_metric_advmss(dst);
+
+	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
+		mss = tp->rx_opt.user_mss;
+
+	/* Set this up on the first call only */
+	req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
+
+	/* limit the window selection if the user enforce a smaller rx buffer */
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+	    (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0))
+		req->window_clamp = tcp_full_space(sk);
+
+	/* tcp_full_space because it is guaranteed to be the first packet */
+	tcp_select_initial_window(tcp_full_space(sk),
+		mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
+		&req->rcv_wnd,
+		&req->window_clamp,
+		ireq->wscale_ok,
+		&rcv_wscale,
+		dst_metric(dst, RTAX_INITRWND));
+	ireq->rcv_wscale = rcv_wscale;
+}
+EXPORT_SYMBOL(tcp_openreq_init_rwin);
+
 static inline void TCP_ECN_openreq_child(struct tcp_sock *tp,
 					 struct request_sock *req)
 {
@@ -397,8 +429,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 
 		tcp_init_wl(newtp, treq->rcv_isn);
 
-		newtp->srtt = 0;
-		newtp->mdev = TCP_TIMEOUT_INIT;
+		newtp->srtt_us = 0;
+		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
 
 		newtp->packets_out = 0;
@@ -425,7 +457,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 
 		tcp_set_ca_state(newsk, TCP_CA_Open);
 		tcp_init_xmit_timers(newsk);
-		skb_queue_head_init(&newtp->out_of_order_queue);
+		__skb_queue_head_init(&newtp->out_of_order_queue);
 		newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
 
 		newtp->rx_opt.saw_tstamp = 0;
@@ -744,7 +776,7 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 					    skb->len);
 		/* Wakeup parent, send SIGIO */
 		if (state == TCP_SYN_RECV && child->sk_state != state)
-			parent->sk_data_ready(parent, 0);
+			parent->sk_data_ready(parent);
 	} else {
 		/* Alas, it is possible again, because we do lookup
 		 * in main socket hash table and lock on listening
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 05606353c7e..55046ecd083 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -57,10 +57,12 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_TCP_ECN |
 			       SKB_GSO_TCPV6 |
 			       SKB_GSO_GRE |
+			       SKB_GSO_GRE_CSUM |
 			       SKB_GSO_IPIP |
 			       SKB_GSO_SIT |
 			       SKB_GSO_MPLS |
 			       SKB_GSO_UDP_TUNNEL |
+			       SKB_GSO_UDP_TUNNEL_CSUM |
 			       0) ||
 			     !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
 			goto out;
@@ -97,9 +99,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 		th->check = newcheck;
 
 		if (skb->ip_summed != CHECKSUM_PARTIAL)
-			th->check =
-			     csum_fold(csum_partial(skb_transport_header(skb),
-						    thlen, skb->csum));
+			th->check = gso_make_checksum(skb, ~th->check);
 
 		seq += mss;
 		if (copy_destructor) {
@@ -133,12 +133,10 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
 				(__force u32)delta));
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
-		th->check = csum_fold(csum_partial(skb_transport_header(skb),
-						   thlen, skb->csum));
+		th->check = gso_make_checksum(skb, ~th->check);
 out:
 	return segs;
 }
-EXPORT_SYMBOL(tcp_gso_segment);
 
 struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 {
@@ -197,7 +195,8 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	goto out_check_final;
 
 found:
-	flush = NAPI_GRO_CB(p)->flush;
+	/* Include the IP ID check below from the inner most IP hdr */
+	flush = NAPI_GRO_CB(p)->flush | NAPI_GRO_CB(p)->flush_id;
 	flush |= (__force int)(flags & TCP_FLAG_CWR);
 	flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
 		  ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
@@ -230,17 +229,16 @@ out_check_final:
 		pp = head;
 
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	NAPI_GRO_CB(skb)->flush |= (flush != 0);
 
 	return pp;
 }
-EXPORT_SYMBOL(tcp_gro_receive);
 
 int tcp_gro_complete(struct sk_buff *skb)
 {
 	struct tcphdr *th = tcp_hdr(skb);
 
-	skb->csum_start = skb_transport_header(skb) - skb->head;
+	skb->csum_start = (unsigned char *)th - skb->head;
 	skb->csum_offset = offsetof(struct tcphdr, check);
 	skb->ip_summed = CHECKSUM_PARTIAL;
 
@@ -272,6 +270,7 @@ static int tcp_v4_gso_send_check(struct sk_buff *skb)
 
 static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 {
+	/* Use the IP hdr immediately proceeding for this transport */
 	const struct iphdr *iph = skb_gro_network_header(skb);
 	__wsum wsum;
 
@@ -279,7 +278,7 @@ static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *
 	if (NAPI_GRO_CB(skb)->flush)
 		goto skip_csum;
 
-	wsum = skb->csum;
+	wsum = NAPI_GRO_CB(skb)->csum;
 
 	switch (skb->ip_summed) {
 	case CHECKSUM_NONE:
@@ -303,14 +302,14 @@ skip_csum:
 	return tcp_gro_receive(head, skb);
 }
 
-static int tcp4_gro_complete(struct sk_buff *skb)
+static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
 
-	th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
-				  iph->saddr, iph->daddr, 0);
-	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+	th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr,
+				  iph->daddr, 0);
+	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
 
 	return tcp_gro_complete(skb);
 }
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 993da005e08..179b51e6bda 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -86,6 +86,9 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb)
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		tcp_rearm_rto(sk);
 	}
+
+	NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT,
+		      tcp_skb_pcount(skb));
 }
 
 /* SND.NXT, if window was not shrunk.
@@ -269,6 +272,7 @@ EXPORT_SYMBOL(tcp_select_initial_window);
 static u16 tcp_select_window(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	u32 old_win = tp->rcv_wnd;
 	u32 cur_win = tcp_receive_window(tp);
 	u32 new_win = __tcp_select_window(sk);
 
@@ -281,6 +285,9 @@ static u16 tcp_select_window(struct sock *sk)
 		 *
 		 * Relax Will Robinson.
 		 */
+		if (new_win == 0)
+			NET_INC_STATS(sock_net(sk),
+				      LINUX_MIB_TCPWANTZEROWINDOWADV);
 		new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale);
 	}
 	tp->rcv_wnd = new_win;
@@ -298,8 +305,14 @@ static u16 tcp_select_window(struct sock *sk)
 	new_win >>= tp->rx_opt.rcv_wscale;
 
 	/* If we advertise zero window, disable fast path. */
-	if (new_win == 0)
+	if (new_win == 0) {
 		tp->pred_flags = 0;
+		if (old_win)
+			NET_INC_STATS(sock_net(sk),
+				      LINUX_MIB_TCPTOZEROWINDOWADV);
+	} else if (old_win == 0) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV);
+	}
 
 	return new_win;
 }
@@ -408,7 +421,7 @@ struct tcp_out_options {
  * Beware: Something in the Internet is very sensitive to the ordering of
  * TCP options, we learned this through the hard way, so be careful here.
  * Luckily we can at least blame others for their non-compliance but from
- * inter-operatibility perspective it seems that we're somewhat stuck with
+ * inter-operability perspective it seems that we're somewhat stuck with
  * the ordering which we have been using if we want to keep working with
  * those broken things (not that it currently hurts anybody as there isn't
  * particular reason why the ordering would need to be changed).
@@ -614,7 +627,7 @@ static unsigned int tcp_synack_options(struct sock *sk,
 		if (unlikely(!ireq->tstamp_ok))
 			remaining -= TCPOLEN_SACKPERM_ALIGNED;
 	}
-	if (foc != NULL) {
+	if (foc != NULL && foc->len >= 0) {
 		u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len;
 		need = (need + 3) & ~3U;  /* Align to 32 bits */
 		if (remaining >= need) {
@@ -681,7 +694,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
  *
  * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb
  * needs to be reallocated in a driver.
- * The invariant being skb->truesize substracted from sk->sk_wmem_alloc
+ * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc
  *
  * Since transmit from skb destructor is forbidden, we use a tasklet
  * to process all sockets that eventually need to send more skbs.
@@ -698,12 +711,13 @@ static void tcp_tsq_handler(struct sock *sk)
 	if ((1 << sk->sk_state) &
 	    (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
 	     TCPF_CLOSE_WAIT  | TCPF_LAST_ACK))
-		tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
+		tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+			       0, GFP_ATOMIC);
 }
 /*
- * One tasklest per cpu tries to send more skbs.
+ * One tasklet per cpu tries to send more skbs.
  * We run in tasklet context but need to disable irqs when
- * transfering tsq->head because tcp_wfree() might
+ * transferring tsq->head because tcp_wfree() might
  * interrupt us (non NAPI drivers)
  */
 static void tcp_tasklet_func(unsigned long data)
@@ -766,6 +780,17 @@ void tcp_release_cb(struct sock *sk)
 	if (flags & (1UL << TCP_TSQ_DEFERRED))
 		tcp_tsq_handler(sk);
 
+	/* Here begins the tricky part :
+	 * We are called from release_sock() with :
+	 * 1) BH disabled
+	 * 2) sk_lock.slock spinlock held
+	 * 3) socket owned by us (sk->sk_lock.owned == 1)
+	 *
+	 * But following code is meant to be called from BH handlers,
+	 * so we should keep BH disabled, but early release socket ownership
+	 */
+	sock_release_ownership(sk);
+
 	if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
 		tcp_write_timer_handler(sk);
 		__sock_put(sk);
@@ -797,7 +822,7 @@ void __init tcp_tasklet_init(void)
 
 /*
  * Write buffer destructor automatically called from kfree_skb.
- * We cant xmit new skbs from this context, as we might already
+ * We can't xmit new skbs from this context, as we might already
  * hold qdisc lock.
  */
 void tcp_wfree(struct sk_buff *skb)
@@ -853,18 +878,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	BUG_ON(!skb || !tcp_skb_pcount(skb));
 
 	if (clone_it) {
-		const struct sk_buff *fclone = skb + 1;
-
-		/* If congestion control is doing timestamping, we must
-		 * take such a timestamp before we potentially clone/copy.
-		 */
-		if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP)
-			__net_timestamp(skb);
-
-		if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
-			     fclone->fclone == SKB_FCLONE_CLONE))
-			NET_INC_STATS_BH(sock_net(sk),
-					 LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
+		skb_mstamp_get(&skb->skb_mstamp);
 
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
@@ -872,6 +886,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 			skb = skb_clone(skb, gfp_mask);
 		if (unlikely(!skb))
 			return -ENOBUFS;
+		/* Our usage of tstamp should remain private */
+		skb->tstamp.tv64 = 0;
 	}
 
 	inet = inet_sk(sk);
@@ -958,7 +974,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
 			      tcp_skb_pcount(skb));
 
-	err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl);
+	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
 	if (likely(err <= 0))
 		return err;
 
@@ -1058,7 +1074,7 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de
  * Remember, these are still headerless SKBs at this point.
  */
 int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
-		 unsigned int mss_now)
+		 unsigned int mss_now, gfp_t gfp)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *buff;
@@ -1073,11 +1089,11 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	if (nsize < 0)
 		nsize = 0;
 
-	if (skb_unclone(skb, GFP_ATOMIC))
+	if (skb_unclone(skb, gfp))
 		return -ENOMEM;
 
 	/* Get a new skb... force flag on. */
-	buff = sk_stream_alloc_skb(sk, nsize, GFP_ATOMIC);
+	buff = sk_stream_alloc_skb(sk, nsize, gfp);
 	if (buff == NULL)
 		return -ENOMEM; /* We'll just try again later. */
 
@@ -1364,12 +1380,43 @@ unsigned int tcp_current_mss(struct sock *sk)
 	return mss_now;
 }
 
-/* Congestion window validation. (RFC2861) */
-static void tcp_cwnd_validate(struct sock *sk)
+/* RFC2861, slow part. Adjust cwnd, after it was not full during one rto.
+ * As additional protections, we do not touch cwnd in retransmission phases,
+ * and if application hit its sndbuf limit recently.
+ */
+static void tcp_cwnd_application_limited(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
+	    sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
+		/* Limited by application or receiver window. */
+		u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk));
+		u32 win_used = max(tp->snd_cwnd_used, init_win);
+		if (win_used < tp->snd_cwnd) {
+			tp->snd_ssthresh = tcp_current_ssthresh(sk);
+			tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1;
+		}
+		tp->snd_cwnd_used = 0;
+	}
+	tp->snd_cwnd_stamp = tcp_time_stamp;
+}
+
+static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tp->packets_out >= tp->snd_cwnd) {
+	/* Track the maximum number of outstanding packets in each
+	 * window, and remember whether we were cwnd-limited then.
+	 */
+	if (!before(tp->snd_una, tp->max_packets_seq) ||
+	    tp->packets_out > tp->max_packets_out) {
+		tp->max_packets_out = tp->packets_out;
+		tp->max_packets_seq = tp->snd_nxt;
+		tp->is_cwnd_limited = is_cwnd_limited;
+	}
+
+	if (tcp_is_cwnd_limited(sk)) {
 		/* Network is feed fully. */
 		tp->snd_cwnd_used = 0;
 		tp->snd_cwnd_stamp = tcp_time_stamp;
@@ -1384,23 +1431,51 @@ static void tcp_cwnd_validate(struct sock *sk)
 	}
 }
 
-/* Returns the portion of skb which can be sent right away without
- * introducing MSS oddities to segment boundaries. In rare cases where
- * mss_now != mss_cache, we will request caller to create a small skb
- * per input skb which could be mostly avoided here (if desired).
- *
- * We explicitly want to create a request for splitting write queue tail
- * to a small skb for Nagle purposes while avoiding unnecessary modulos,
- * thus all the complexity (cwnd_len is always MSS multiple which we
- * return whenever allowed by the other factors). Basically we need the
- * modulo only when the receiver window alone is the limiting factor or
- * when we would be allowed to send the split-due-to-Nagle skb fully.
+/* Minshall's variant of the Nagle send check. */
+static bool tcp_minshall_check(const struct tcp_sock *tp)
+{
+	return after(tp->snd_sml, tp->snd_una) &&
+		!after(tp->snd_sml, tp->snd_nxt);
+}
+
+/* Update snd_sml if this skb is under mss
+ * Note that a TSO packet might end with a sub-mss segment
+ * The test is really :
+ * if ((skb->len % mss) != 0)
+ *        tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
+ * But we can avoid doing the divide again given we already have
+ *  skb_pcount = skb->len / mss_now
  */
-static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb,
-					unsigned int mss_now, unsigned int max_segs)
+static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now,
+				const struct sk_buff *skb)
+{
+	if (skb->len < tcp_skb_pcount(skb) * mss_now)
+		tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
+}
+
+/* Return false, if packet can be sent now without violation Nagle's rules:
+ * 1. It is full sized. (provided by caller in %partial bool)
+ * 2. Or it contains FIN. (already checked by caller)
+ * 3. Or TCP_CORK is not set, and TCP_NODELAY is set.
+ * 4. Or TCP_CORK is not set, and all sent packets are ACKed.
+ *    With Minshall's modification: all sent small packets are ACKed.
+ */
+static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
+			    int nonagle)
+{
+	return partial &&
+		((nonagle & TCP_NAGLE_CORK) ||
+		 (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
+}
+/* Returns the portion of skb which can be sent right away */
+static unsigned int tcp_mss_split_point(const struct sock *sk,
+					const struct sk_buff *skb,
+					unsigned int mss_now,
+					unsigned int max_segs,
+					int nonagle)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	u32 needed, window, max_len;
+	u32 partial, needed, window, max_len;
 
 	window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
 	max_len = mss_now * max_segs;
@@ -1413,7 +1488,15 @@ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_b
 	if (max_len <= needed)
 		return max_len;
 
-	return needed - needed % mss_now;
+	partial = needed % mss_now;
+	/* If last segment is not a full MSS, check if Nagle rules allow us
+	 * to include this last segment in this skb.
+	 * Otherwise, we'll split the skb at last MSS boundary
+	 */
+	if (tcp_nagle_check(partial != 0, tp, nonagle))
+		return needed - partial;
+
+	return needed;
 }
 
 /* Can at least one segment of SKB be sent right now, according to the
@@ -1453,28 +1536,6 @@ static int tcp_init_tso_segs(const struct sock *sk, struct sk_buff *skb,
 	return tso_segs;
 }
 
-/* Minshall's variant of the Nagle send check. */
-static inline bool tcp_minshall_check(const struct tcp_sock *tp)
-{
-	return after(tp->snd_sml, tp->snd_una) &&
-		!after(tp->snd_sml, tp->snd_nxt);
-}
-
-/* Return false, if packet can be sent now without violation Nagle's rules:
- * 1. It is full sized.
- * 2. Or it contains FIN. (already checked by caller)
- * 3. Or TCP_CORK is not set, and TCP_NODELAY is set.
- * 4. Or TCP_CORK is not set, and all sent packets are ACKed.
- *    With Minshall's modification: all sent small packets are ACKed.
- */
-static inline bool tcp_nagle_check(const struct tcp_sock *tp,
-				  const struct sk_buff *skb,
-				  unsigned int mss_now, int nonagle)
-{
-	return skb->len < mss_now &&
-		((nonagle & TCP_NAGLE_CORK) ||
-		 (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
-}
 
 /* Return true if the Nagle test allows this packet to be
  * sent now.
@@ -1495,7 +1556,7 @@ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buf
 	if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
 		return true;
 
-	if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
+	if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle))
 		return true;
 
 	return false;
@@ -1564,7 +1625,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 
 	/* All of a TSO frame must be composed of paged data.  */
 	if (skb->len != skb->data_len)
-		return tcp_fragment(sk, skb, len, mss_now);
+		return tcp_fragment(sk, skb, len, mss_now, gfp);
 
 	buff = sk_stream_alloc_skb(sk, 0, gfp);
 	if (unlikely(buff == NULL))
@@ -1607,7 +1668,8 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
  *
  * This algorithm is from John Heffner.
  */
-static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
+static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
+				 bool *is_cwnd_limited)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1671,6 +1733,9 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 	if (!tp->tso_deferred)
 		tp->tso_deferred = 1 | (jiffies << 1);
 
+	if (cong_win < send_win && cong_win < skb->len)
+		*is_cwnd_limited = true;
+
 	return true;
 
 send_now:
@@ -1831,6 +1896,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	unsigned int tso_segs, sent_pkts;
 	int cwnd_quota;
 	int result;
+	bool is_cwnd_limited = false;
 
 	sent_pkts = 0;
 
@@ -1855,6 +1921,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		cwnd_quota = tcp_cwnd_test(tp, skb);
 		if (!cwnd_quota) {
+			is_cwnd_limited = true;
 			if (push_one == 2)
 				/* Force out a loss probe pkt. */
 				cwnd_quota = 1;
@@ -1871,7 +1938,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 						      nonagle : TCP_NAGLE_PUSH))))
 				break;
 		} else {
-			if (!push_one && tcp_tso_should_defer(sk, skb))
+			if (!push_one &&
+			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited))
 				break;
 		}
 
@@ -1890,7 +1958,13 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
-			break;
+			/* It is possible TX completion already happened
+			 * before we set TSQ_THROTTLED, so we must
+			 * test again the condition.
+			 */
+			smp_mb__after_atomic();
+			if (atomic_read(&sk->sk_wmem_alloc) > limit)
+				break;
 		}
 
 		limit = mss_now;
@@ -1898,7 +1972,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			limit = tcp_mss_split_point(sk, skb, mss_now,
 						    min_t(unsigned int,
 							  cwnd_quota,
-							  sk->sk_gso_max_segs));
+							  sk->sk_gso_max_segs),
+						    nonagle);
 
 		if (skb->len > limit &&
 		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
@@ -1929,7 +2004,7 @@ repair:
 		/* Send one loss probe per tail loss episode. */
 		if (push_one != 2)
 			tcp_schedule_loss_probe(sk);
-		tcp_cwnd_validate(sk);
+		tcp_cwnd_validate(sk, is_cwnd_limited);
 		return false;
 	}
 	return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk));
@@ -1940,7 +2015,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 timeout, tlp_time_stamp, rto_time_stamp;
-	u32 rtt = tp->srtt >> 3;
+	u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3);
 
 	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS))
 		return false;
@@ -1962,7 +2037,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * in Open state, that are either limited by cwnd or application.
 	 */
-	if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out ||
+	if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out ||
 	    !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
 		return false;
 
@@ -1993,6 +2068,25 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	return true;
 }
 
+/* Thanks to skb fast clones, we can detect if a prior transmit of
+ * a packet is still in a qdisc or driver queue.
+ * In this case, there is very little point doing a retransmit !
+ * Note: This is called from BH context only.
+ */
+static bool skb_still_in_host_queue(const struct sock *sk,
+				    const struct sk_buff *skb)
+{
+	const struct sk_buff *fclone = skb + 1;
+
+	if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
+		     fclone->fclone == SKB_FCLONE_CLONE)) {
+		NET_INC_STATS_BH(sock_net(sk),
+				 LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
+		return true;
+	}
+	return false;
+}
+
 /* When probe timeout (PTO) fires, send a new segment if one exists, else
  * retransmit the last segment.
  */
@@ -2018,12 +2112,16 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (WARN_ON(!skb))
 		goto rearm_timer;
 
+	if (skb_still_in_host_queue(sk, skb))
+		goto rearm_timer;
+
 	pcount = tcp_skb_pcount(skb);
 	if (WARN_ON(!pcount))
 		goto rearm_timer;
 
 	if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) {
-		if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss)))
+		if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss,
+					  GFP_ATOMIC)))
 			goto rearm_timer;
 		skb = tcp_write_queue_tail(sk);
 	}
@@ -2031,9 +2129,7 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
 		goto rearm_timer;
 
-	/* Probe with zero data doesn't trigger fast recovery. */
-	if (skb->len > 0)
-		err = __tcp_retransmit_skb(sk, skb);
+	err = __tcp_retransmit_skb(sk, skb);
 
 	/* Record snd_nxt for loss detection. */
 	if (likely(!err))
@@ -2047,7 +2143,6 @@ rearm_timer:
 	if (likely(!err))
 		NET_INC_STATS_BH(sock_net(sk),
 				 LINUX_MIB_TCPLOSSPROBES);
-	return;
 }
 
 /* Push out any pending frames which were held back due to
@@ -2145,7 +2240,8 @@ u32 __tcp_select_window(struct sock *sk)
 	 */
 	int mss = icsk->icsk_ack.rcv_mss;
 	int free_space = tcp_space(sk);
-	int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk));
+	int allowed_space = tcp_full_space(sk);
+	int full_space = min_t(int, tp->window_clamp, allowed_space);
 	int window;
 
 	if (mss > full_space)
@@ -2158,7 +2254,19 @@ u32 __tcp_select_window(struct sock *sk)
 			tp->rcv_ssthresh = min(tp->rcv_ssthresh,
 					       4U * tp->advmss);
 
-		if (free_space < mss)
+		/* free_space might become our new window, make sure we don't
+		 * increase it due to wscale.
+		 */
+		free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale);
+
+		/* if free space is less than mss estimate, or is below 1/16th
+		 * of the maximum allowed, try to move to zero-window, else
+		 * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and
+		 * new incoming data is dropped due to memory limits.
+		 * With large window, mss test triggers way too late in order
+		 * to announce zero window in time before rmem limit kicks in.
+		 */
+		if (free_space < (allowed_space >> 4) || free_space < mss)
 			return 0;
 	}
 
@@ -2313,6 +2421,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned int cur_mss;
+	int err;
 
 	/* Inconslusive MTU probe */
 	if (icsk->icsk_mtup.probe_size) {
@@ -2326,6 +2435,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	    min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
 		return -EAGAIN;
 
+	if (skb_still_in_host_queue(sk, skb))
+		return -EBUSY;
+
 	if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
 		if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
 			BUG();
@@ -2348,7 +2460,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		return -EAGAIN;
 
 	if (skb->len > cur_mss) {
-		if (tcp_fragment(sk, skb, cur_mss, cur_mss))
+		if (tcp_fragment(sk, skb, cur_mss, cur_mss, GFP_ATOMIC))
 			return -ENOMEM; /* We'll try again later. */
 	} else {
 		int oldpcount = tcp_skb_pcount(skb);
@@ -2376,11 +2488,21 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
 						   GFP_ATOMIC);
-		return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-			      -ENOBUFS;
+		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+			     -ENOBUFS;
 	} else {
-		return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
+
+	if (likely(!err)) {
+		TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+		/* Update global TCP statistics. */
+		TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
+			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+		tp->total_retrans++;
+	}
+	return err;
 }
 
 int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
@@ -2389,11 +2511,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	int err = __tcp_retransmit_skb(sk, skb);
 
 	if (err == 0) {
-		/* Update global TCP statistics. */
-		TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
-
-		tp->total_retrans++;
-
 #if FASTRETRANS_DEBUG > 0
 		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
 			net_dbg_ratelimited("retrans_out leaked\n");
@@ -2408,15 +2525,17 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		if (!tp->retrans_stamp)
 			tp->retrans_stamp = TCP_SKB_CB(skb)->when;
 
-		tp->undo_retrans += tcp_skb_pcount(skb);
-
 		/* snd_nxt is stored to detect loss of retransmitted segment,
 		 * see tcp_input.c tcp_sacktag_write_queue().
 		 */
 		TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
-	} else {
+	} else if (err != -EBUSY) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
 	}
+
+	if (tp->undo_retrans < 0)
+		tp->undo_retrans = 0;
+	tp->undo_retrans += tcp_skb_pcount(skb);
 	return err;
 }
 
@@ -2677,7 +2796,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	int tcp_header_size;
 	int mss;
 
-	skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
+	skb = sock_wmalloc(sk, MAX_TCP_HEADER, 1, GFP_ATOMIC);
 	if (unlikely(!skb)) {
 		dst_release(dst);
 		return NULL;
@@ -2692,27 +2811,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
 		mss = tp->rx_opt.user_mss;
 
-	if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
-		__u8 rcv_wscale;
-		/* Set this up on the first call only */
-		req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
-
-		/* limit the window selection if the user enforce a smaller rx buffer */
-		if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
-		    (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0))
-			req->window_clamp = tcp_full_space(sk);
-
-		/* tcp_full_space because it is guaranteed to be the first packet */
-		tcp_select_initial_window(tcp_full_space(sk),
-			mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
-			&req->rcv_wnd,
-			&req->window_clamp,
-			ireq->wscale_ok,
-			&rcv_wscale,
-			dst_metric(dst, RTAX_INITRWND));
-		ireq->rcv_wscale = rcv_wscale;
-	}
-
 	memset(&opts, 0, sizeof(opts));
 #ifdef CONFIG_SYN_COOKIES
 	if (unlikely(req->cookie_ts))
@@ -2747,7 +2845,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	th->window = htons(min(req->rcv_wnd, 65535U));
 	tcp_options_write((__be32 *)(th + 1), tp, &opts);
 	th->doff = (tcp_header_size >> 2);
-	TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb));
+	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS);
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Okay, we have all we need - do the md5 hash if needed */
@@ -2762,7 +2860,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 EXPORT_SYMBOL(tcp_make_synack);
 
 /* Do all connect socket setups that can be done AF independent. */
-void tcp_connect_init(struct sock *sk)
+static void tcp_connect_init(struct sock *sk)
 {
 	const struct dst_entry *dst = __sk_dst_get(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -2884,7 +2982,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
 		MAX_TCP_OPTION_SPACE;
 
-	syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
+	space = min_t(size_t, space, fo->size);
+
+	/* limit to order-0 allocations */
+	space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
+
+	syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
 				   sk->sk_allocation);
 	if (syn_data == NULL)
 		goto fallback;
@@ -2914,9 +3017,15 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	tcp_connect_queue_skb(sk, data);
 	fo->copied = data->len;
 
+	/* syn_data is about to be sent, we need to take current time stamps
+	 * for the packets that are in write queue : SYN packet and DATA
+	 */
+	skb_mstamp_get(&syn->skb_mstamp);
+	data->skb_mstamp = syn->skb_mstamp;
+
 	if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
 		tp->syn_data = (fo->copied > 0);
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT);
 		goto done;
 	}
 	syn_data = NULL;
@@ -3004,8 +3113,9 @@ void tcp_send_delayed_ack(struct sock *sk)
 		 * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements
 		 * directly.
 		 */
-		if (tp->srtt) {
-			int rtt = max(tp->srtt >> 3, TCP_DELACK_MIN);
+		if (tp->srtt_us) {
+			int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3),
+					TCP_DELACK_MIN);
 
 			if (rtt < max_ato)
 				max_ato = rtt;
@@ -3133,7 +3243,7 @@ int tcp_write_wakeup(struct sock *sk)
 		    skb->len > mss) {
 			seg_size = min(seg_size, mss);
 			TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
-			if (tcp_fragment(sk, skb, seg_size, mss))
+			if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC))
 				return -1;
 		} else if (!tcp_skb_pcount(skb))
 			tcp_set_skb_tso_segs(sk, skb, mss);
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 8b97d71e193..3b66610d415 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -38,7 +38,7 @@ MODULE_DESCRIPTION("TCP cwnd snooper");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.1");
 
-static int port __read_mostly = 0;
+static int port __read_mostly;
 MODULE_PARM_DESC(port, "Port to match (0=all)");
 module_param(port, int, 0);
 
@@ -46,7 +46,7 @@ static unsigned int bufsize __read_mostly = 4096;
 MODULE_PARM_DESC(bufsize, "Log buffer size in packets (4096)");
 module_param(bufsize, uint, 0);
 
-static unsigned int fwmark __read_mostly = 0;
+static unsigned int fwmark __read_mostly;
 MODULE_PARM_DESC(fwmark, "skb mark to match (0=no mark)");
 module_param(fwmark, uint, 0);
 
@@ -154,7 +154,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			p->snd_wnd = tp->snd_wnd;
 			p->rcv_wnd = tp->rcv_wnd;
 			p->ssthresh = tcp_current_ssthresh(sk);
-			p->srtt = tp->srtt >> 3;
+			p->srtt = tp->srtt_us >> 3;
 
 			tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
 		}
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 19ea6c2951f..8250949b885 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -15,12 +15,11 @@
 #define TCP_SCALABLE_AI_CNT	50U
 #define TCP_SCALABLE_MD_SCALE	3
 
-static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-				    u32 in_flight)
+static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
@@ -39,7 +38,6 @@ static u32 tcp_scalable_ssthresh(struct sock *sk)
 static struct tcp_congestion_ops tcp_scalable __read_mostly = {
 	.ssthresh	= tcp_scalable_ssthresh,
 	.cong_avoid	= tcp_scalable_cong_avoid,
-	.min_cwnd	= tcp_reno_min_cwnd,
 
 	.owner		= THIS_MODULE,
 	.name		= "scalable",
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 64f0354c84c..286227abed1 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -165,6 +165,9 @@ static int tcp_write_timeout(struct sock *sk)
 			dst_negative_advice(sk);
 			if (tp->syn_fastopen || tp->syn_data)
 				tcp_fastopen_cache_set(sk, 0, NULL, true);
+			if (tp->syn_data)
+				NET_INC_STATS_BH(sock_net(sk),
+						 LINUX_MIB_TCPFASTOPENACTIVEFAIL);
 		}
 		retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
 		syn_set = true;
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 06cae62bf20..9a5e05f27f4 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -163,14 +163,13 @@ static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp)
 	return  min(tp->snd_ssthresh, tp->snd_cwnd-1);
 }
 
-static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-				 u32 in_flight)
+static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct vegas *vegas = inet_csk_ca(sk);
 
 	if (!vegas->doing_vegas_now) {
-		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked);
 		return;
 	}
 
@@ -195,7 +194,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 			/* We don't have enough RTT samples to do the Vegas
 			 * calculation, so we'll behave like Reno.
 			 */
-			tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+			tcp_reno_cong_avoid(sk, ack, acked);
 		} else {
 			u32 rtt, diff;
 			u64 target_cwnd;
@@ -306,11 +305,9 @@ void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
 EXPORT_SYMBOL_GPL(tcp_vegas_get_info);
 
 static struct tcp_congestion_ops tcp_vegas __read_mostly = {
-	.flags		= TCP_CONG_RTT_STAMP,
 	.init		= tcp_vegas_init,
 	.ssthresh	= tcp_reno_ssthresh,
 	.cong_avoid	= tcp_vegas_cong_avoid,
-	.min_cwnd	= tcp_reno_min_cwnd,
 	.pkts_acked	= tcp_vegas_pkts_acked,
 	.set_state	= tcp_vegas_state,
 	.cwnd_event	= tcp_vegas_cwnd_event,
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 326475a9486..27b9825753d 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -114,19 +114,18 @@ static void tcp_veno_cwnd_event(struct sock *sk, enum tcp_ca_event event)
 		tcp_veno_init(sk);
 }
 
-static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-				u32 in_flight)
+static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct veno *veno = inet_csk_ca(sk);
 
 	if (!veno->doing_veno_now) {
-		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked);
 		return;
 	}
 
 	/* limited by applications */
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	/* We do the Veno calculations only if we got enough rtt samples */
@@ -134,7 +133,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 		/* We don't have enough rtt samples to do the Veno
 		 * calculation, so we'll behave like Reno.
 		 */
-		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked);
 	} else {
 		u64 target_cwnd;
 		u32 rtt;
@@ -203,7 +202,6 @@ static u32 tcp_veno_ssthresh(struct sock *sk)
 }
 
 static struct tcp_congestion_ops tcp_veno __read_mostly = {
-	.flags		= TCP_CONG_RTT_STAMP,
 	.init		= tcp_veno_init,
 	.ssthresh	= tcp_veno_ssthresh,
 	.cong_avoid	= tcp_veno_cong_avoid,
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index 76a1e23259e..b94a04ae2ed 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -276,7 +276,6 @@ static struct tcp_congestion_ops tcp_westwood __read_mostly = {
 	.init		= tcp_westwood_init,
 	.ssthresh	= tcp_reno_ssthresh,
 	.cong_avoid	= tcp_reno_cong_avoid,
-	.min_cwnd	= tcp_westwood_bw_rttmin,
 	.cwnd_event	= tcp_westwood_event,
 	.get_info	= tcp_westwood_info,
 	.pkts_acked	= tcp_westwood_pkts_acked,
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index a347a078ee0..599b79b8eac 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -3,7 +3,7 @@
  *   YeAH TCP
  *
  * For further details look at:
- *    http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf
+ *   https://web.archive.org/web/20080316215752/http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf
  *
  */
 #include <linux/mm.h>
@@ -15,13 +15,13 @@
 
 #include "tcp_vegas.h"
 
-#define TCP_YEAH_ALPHA       80 //lin number of packets queued at the bottleneck
-#define TCP_YEAH_GAMMA        1 //lin fraction of queue to be removed per rtt
-#define TCP_YEAH_DELTA        3 //log minimum fraction of cwnd to be removed on loss
-#define TCP_YEAH_EPSILON      1 //log maximum fraction to be removed on early decongestion
-#define TCP_YEAH_PHY          8 //lin maximum delta from base
-#define TCP_YEAH_RHO         16 //lin minimum number of consecutive rtt to consider competition on loss
-#define TCP_YEAH_ZETA        50 //lin minimum number of state switchs to reset reno_count
+#define TCP_YEAH_ALPHA       80 /* number of packets queued at the bottleneck */
+#define TCP_YEAH_GAMMA        1 /* fraction of queue to be removed per rtt */
+#define TCP_YEAH_DELTA        3 /* log minimum fraction of cwnd to be removed on loss */
+#define TCP_YEAH_EPSILON      1 /* log maximum fraction to be removed on early decongestion */
+#define TCP_YEAH_PHY          8 /* maximum delta from base */
+#define TCP_YEAH_RHO         16 /* minimum number of consecutive rtt to consider competition on loss */
+#define TCP_YEAH_ZETA        50 /* minimum number of state switches to reset reno_count */
 
 #define TCP_SCALABLE_AI_CNT	 100U
 
@@ -69,13 +69,12 @@ static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, s32 rtt_us)
 	tcp_vegas_pkts_acked(sk, pkts_acked, rtt_us);
 }
 
-static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-				u32 in_flight)
+static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct yeah *yeah = inet_csk_ca(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
@@ -214,9 +213,9 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) {
 	if (yeah->doing_reno_now < TCP_YEAH_RHO) {
 		reduction = yeah->lastQ;
 
-		reduction = min( reduction, max(tp->snd_cwnd>>1, 2U) );
+		reduction = min(reduction, max(tp->snd_cwnd>>1, 2U));
 
-		reduction = max( reduction, tp->snd_cwnd >> TCP_YEAH_DELTA);
+		reduction = max(reduction, tp->snd_cwnd >> TCP_YEAH_DELTA);
 	} else
 		reduction = max(tp->snd_cwnd>>1, 2U);
 
@@ -227,11 +226,9 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) {
 }
 
 static struct tcp_congestion_ops tcp_yeah __read_mostly = {
-	.flags		= TCP_CONG_RTT_STAMP,
 	.init		= tcp_yeah_init,
 	.ssthresh	= tcp_yeah_ssthresh,
 	.cong_avoid	= tcp_yeah_cong_avoid,
-	.min_cwnd	= tcp_reno_min_cwnd,
 	.set_state	= tcp_vegas_state,
 	.cwnd_event	= tcp_vegas_cwnd_event,
 	.get_info	= tcp_vegas_get_info,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 44f6a20fa29..7d5a8661df7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -223,7 +223,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
 
-		rand = net_random();
+		rand = prandom_u32();
 		first = (((u64)rand * remaining) >> 32) + low;
 		/*
 		 * force rand to be an odd multiple of UDP_HTABLE_SIZE
@@ -246,7 +246,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 			do {
 				if (low <= snum && snum <= high &&
 				    !test_bit(snum >> udptable->log, bitmap) &&
-				    !inet_is_reserved_local_port(snum))
+				    !inet_is_local_reserved_port(net, snum))
 					goto found;
 				snum += rand;
 			} while (snum != first);
@@ -560,15 +560,11 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 						 __be16 sport, __be16 dport,
 						 struct udp_table *udptable)
 {
-	struct sock *sk;
 	const struct iphdr *iph = ip_hdr(skb);
 
-	if (unlikely(sk = skb_steal_sock(skb)))
-		return sk;
-	else
-		return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport,
-					 iph->daddr, dport, inet_iif(skb),
-					 udptable);
+	return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport,
+				 iph->daddr, dport, inet_iif(skb),
+				 udptable);
 }
 
 struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
@@ -731,13 +727,12 @@ EXPORT_SYMBOL(udp_flush_pending_frames);
 void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
 {
 	struct udphdr *uh = udp_hdr(skb);
-	struct sk_buff *frags = skb_shinfo(skb)->frag_list;
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
 	int hlen = len;
 	__wsum csum = 0;
 
-	if (!frags) {
+	if (!skb_has_frag_list(skb)) {
 		/*
 		 * Only one fragment on the socket.
 		 */
@@ -746,15 +741,17 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
 		uh->check = ~csum_tcpudp_magic(src, dst, len,
 					       IPPROTO_UDP, 0);
 	} else {
+		struct sk_buff *frags;
+
 		/*
 		 * HW-checksum won't work as there are two or more
 		 * fragments on the socket so that all csums of sk_buffs
 		 * should be together
 		 */
-		do {
+		skb_walk_frags(skb, frags) {
 			csum = csum_add(csum, frags->csum);
 			hlen -= frags->len;
-		} while ((frags = frags->next));
+		}
 
 		csum = skb_checksum(skb, offset, hlen, csum);
 		skb->ip_summed = CHECKSUM_NONE;
@@ -766,6 +763,43 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
 }
 EXPORT_SYMBOL_GPL(udp4_hwcsum);
 
+/* Function to set UDP checksum for an IPv4 UDP packet. This is intended
+ * for the simple case like when setting the checksum for a UDP tunnel.
+ */
+void udp_set_csum(bool nocheck, struct sk_buff *skb,
+		  __be32 saddr, __be32 daddr, int len)
+{
+	struct udphdr *uh = udp_hdr(skb);
+
+	if (nocheck)
+		uh->check = 0;
+	else if (skb_is_gso(skb))
+		uh->check = ~udp_v4_check(len, saddr, daddr, 0);
+	else if (skb_dst(skb) && skb_dst(skb)->dev &&
+		 (skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) {
+
+		BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL);
+
+		skb->ip_summed = CHECKSUM_PARTIAL;
+		skb->csum_start = skb_transport_header(skb) - skb->head;
+		skb->csum_offset = offsetof(struct udphdr, check);
+		uh->check = ~udp_v4_check(len, saddr, daddr, 0);
+	} else {
+		__wsum csum;
+
+		BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL);
+
+		uh->check = 0;
+		csum = skb_checksum(skb, 0, len, 0);
+		uh->check = udp_v4_check(len, saddr, daddr, csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
+}
+EXPORT_SYMBOL(udp_set_csum);
+
 static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 {
 	struct sock *sk = skb->sk;
@@ -789,7 +823,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 	if (is_udplite)  				 /*     UDP-Lite      */
 		csum = udplite_csum(skb);
 
-	else if (sk->sk_no_check == UDP_CSUM_NOXMIT) {   /* UDP csum disabled */
+	else if (sk->sk_no_check_tx) {   /* UDP csum disabled */
 
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
@@ -906,7 +940,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	 *	Get and verify the address.
 	 */
 	if (msg->msg_name) {
-		struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
 		if (msg->msg_namelen < sizeof(*usin))
 			return -EINVAL;
 		if (usin->sin_family != AF_INET) {
@@ -935,7 +969,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	sock_tx_timestamp(sk, &ipc.tx_flags);
 
 	if (msg->msg_controllen) {
-		err = ip_cmsg_send(sock_net(sk), msg, &ipc);
+		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
+				   sk->sk_family == AF_INET6);
 		if (err)
 			return err;
 		if (ipc.opt)
@@ -990,7 +1025,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		fl4 = &fl4_stack;
 		flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
 				   RT_SCOPE_UNIVERSE, sk->sk_protocol,
-				   inet_sk_flowi_flags(sk)|FLOWI_FLAG_CAN_SLEEP,
+				   inet_sk_flowi_flags(sk),
 				   faddr, saddr, dport, inet->inet_sport);
 
 		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
@@ -1230,7 +1265,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		size_t len, int noblock, int flags, int *addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
-	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct sk_buff *skb;
 	unsigned int ulen, copied;
 	int peeked, off = 0;
@@ -1498,6 +1533,10 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) {
 			int ret;
 
+			/* Verify checksum before giving to encap */
+			if (udp_lib_checksum_complete(skb))
+				goto csum_error;
+
 			ret = encap_rcv(sk, skb);
 			if (ret <= 0) {
 				UDP_INC_STATS_BH(sock_net(sk),
@@ -1549,8 +1588,11 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		goto csum_error;
 
 
-	if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf))
+	if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) {
+		UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
+				 is_udplite);
 		goto drop;
+	}
 
 	rc = 0;
 
@@ -1603,12 +1645,16 @@ static void flush_stack(struct sock **stack, unsigned int count,
 		kfree_skb(skb1);
 }
 
-static void udp_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+/* For TCP sockets, sk_rx_dst is protected by socket lock
+ * For UDP, we use xchg() to guard against concurrent changes.
+ */
+static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 {
-	struct dst_entry *dst = skb_dst(skb);
+	struct dst_entry *old;
 
 	dst_hold(dst);
-	sk->sk_rx_dst = dst;
+	old = xchg(&sk->sk_rx_dst, dst);
+	dst_release(old);
 }
 
 /*
@@ -1671,7 +1717,6 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 				 int proto)
 {
-	const struct iphdr *iph;
 	int err;
 
 	UDP_SKB_CB(skb)->partial_cov = 0;
@@ -1683,22 +1728,8 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 			return err;
 	}
 
-	iph = ip_hdr(skb);
-	if (uh->check == 0) {
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-	} else if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
-				      proto, skb->csum))
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-	}
-	if (!skb_csum_unnecessary(skb))
-		skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-					       skb->len, proto, 0);
-	/* Probably, we should checksum udp header (it should be in cache
-	 * in any case) and data in tiny packets (< rx copybreak).
-	 */
-
-	return 0;
+	return skb_checksum_init_zero_check(skb, proto, uh->check,
+					    inet_compute_pseudo);
 }
 
 /*
@@ -1739,15 +1770,16 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp4_csum_init(skb, uh, proto))
 		goto csum_error;
 
-	if (skb->sk) {
+	sk = skb_steal_sock(skb);
+	if (sk) {
+		struct dst_entry *dst = skb_dst(skb);
 		int ret;
-		sk = skb->sk;
 
-		if (unlikely(sk->sk_rx_dst == NULL))
-			udp_sk_rx_dst_set(sk, skb);
+		if (unlikely(sk->sk_rx_dst != dst))
+			udp_sk_rx_dst_set(sk, dst);
 
 		ret = udp_queue_rcv_skb(sk, skb);
-
+		sock_put(sk);
 		/* a return value > 0 means to resubmit the input, but
 		 * it wants the return to be -protocol, or 0
 		 */
@@ -1832,6 +1864,10 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 	unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
 	struct udp_hslot *hslot = &udp_table.hash[slot];
 
+	/* Do not bother scanning a too big list */
+	if (hslot->count > 10)
+		return NULL;
+
 	rcu_read_lock();
 begin:
 	count = 0;
@@ -1884,7 +1920,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 	unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
 	unsigned int slot2 = hash2 & udp_table.mask;
 	struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
-	INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr)
+	INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr);
 	const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
 
 	rcu_read_lock();
@@ -1913,17 +1949,20 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 
 void udp_v4_early_demux(struct sk_buff *skb)
 {
-	const struct iphdr *iph = ip_hdr(skb);
-	const struct udphdr *uh = udp_hdr(skb);
+	struct net *net = dev_net(skb->dev);
+	const struct iphdr *iph;
+	const struct udphdr *uh;
 	struct sock *sk;
 	struct dst_entry *dst;
-	struct net *net = dev_net(skb->dev);
 	int dif = skb->dev->ifindex;
 
 	/* validate the packet */
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
 		return;
 
+	iph = ip_hdr(skb);
+	uh = udp_hdr(skb);
+
 	if (skb->pkt_type == PACKET_BROADCAST ||
 	    skb->pkt_type == PACKET_MULTICAST)
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
@@ -1974,7 +2013,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		       int (*push_pending_frames)(struct sock *))
 {
 	struct udp_sock *up = udp_sk(sk);
-	int val;
+	int val, valbool;
 	int err = 0;
 	int is_udplite = IS_UDPLITE(sk);
 
@@ -1984,6 +2023,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 	if (get_user(val, (int __user *)optval))
 		return -EFAULT;
 
+	valbool = val ? 1 : 0;
+
 	switch (optname) {
 	case UDP_CORK:
 		if (val != 0) {
@@ -2013,6 +2054,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		}
 		break;
 
+	case UDP_NO_CHECK6_TX:
+		up->no_check6_tx = valbool;
+		break;
+
+	case UDP_NO_CHECK6_RX:
+		up->no_check6_rx = valbool;
+		break;
+
 	/*
 	 * 	UDP-Lite's partial checksum coverage (RFC 3828).
 	 */
@@ -2095,6 +2144,14 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
 		val = up->encap_type;
 		break;
 
+	case UDP_NO_CHECK6_TX:
+		val = up->no_check6_tx;
+		break;
+
+	case UDP_NO_CHECK6_RX:
+		val = up->no_check6_rx;
+		break;
+
 	/* The following two cannot be changed on UDP sockets, the return is
 	 * always 0 (which corresponds to the full checksum coverage of UDP). */
 	case UDPLITE_SEND_CSCOV:
@@ -2474,11 +2531,16 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	u16 mac_offset = skb->mac_header;
 	int mac_len = skb->mac_len;
 	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
 	__be16 protocol = skb->protocol;
 	netdev_features_t enc_features;
-	int outer_hlen;
+	int udp_offset, outer_hlen;
+	unsigned int oldlen;
+	bool need_csum;
+
+	oldlen = (u16)~skb->len;
 
 	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
 		goto out;
@@ -2490,17 +2552,25 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 	skb->mac_len = skb_inner_network_offset(skb);
 	skb->protocol = htons(ETH_P_TEB);
 
+	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
+	if (need_csum)
+		skb->encap_hdr_csum = 1;
+
 	/* segment inner packet. */
 	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
 	segs = skb_mac_gso_segment(skb, enc_features);
-	if (!segs || IS_ERR(segs))
+	if (!segs || IS_ERR(segs)) {
+		skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
+				     mac_len);
 		goto out;
+	}
 
 	outer_hlen = skb_tnl_header_len(skb);
+	udp_offset = outer_hlen - tnl_hlen;
 	skb = segs;
 	do {
 		struct udphdr *uh;
-		int udp_offset = outer_hlen - tnl_hlen;
+		int len;
 
 		skb_reset_inner_headers(skb);
 		skb->encapsulation = 1;
@@ -2511,31 +2581,20 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 		skb_reset_mac_header(skb);
 		skb_set_network_header(skb, mac_len);
 		skb_set_transport_header(skb, udp_offset);
+		len = skb->len - udp_offset;
 		uh = udp_hdr(skb);
-		uh->len = htons(skb->len - udp_offset);
+		uh->len = htons(len);
 
-		/* csum segment if tunnel sets skb with csum. */
-		if (protocol == htons(ETH_P_IP) && unlikely(uh->check)) {
-			struct iphdr *iph = ip_hdr(skb);
-
-			uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
-						       skb->len - udp_offset,
-						       IPPROTO_UDP, 0);
-			uh->check = csum_fold(skb_checksum(skb, udp_offset,
-							   skb->len - udp_offset, 0));
-			if (uh->check == 0)
-				uh->check = CSUM_MANGLED_0;
+		if (need_csum) {
+			__be32 delta = htonl(oldlen + len);
 
-		} else if (protocol == htons(ETH_P_IPV6)) {
-			struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-			u32 len = skb->len - udp_offset;
+			uh->check = ~csum_fold((__force __wsum)
+					       ((__force u32)uh->check +
+						(__force u32)delta));
+			uh->check = gso_make_checksum(skb, ~uh->check);
 
-			uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
-						     len, IPPROTO_UDP, 0);
-			uh->check = csum_fold(skb_checksum(skb, udp_offset, len, 0));
 			if (uh->check == 0)
 				uh->check = CSUM_MANGLED_0;
-			skb->ip_summed = CHECKSUM_NONE;
 		}
 
 		skb->protocol = protocol;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 83206de2bc7..546d2d439dd 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -14,6 +14,17 @@
 #include <net/udp.h>
 #include <net/protocol.h>
 
+static DEFINE_SPINLOCK(udp_offload_lock);
+static struct udp_offload_priv __rcu *udp_offload_base __read_mostly;
+
+#define udp_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&udp_offload_lock))
+
+struct udp_offload_priv {
+	struct udp_offload	*offload;
+	struct rcu_head		rcu;
+	struct udp_offload_priv __rcu *next;
+};
+
 static int udp4_ufo_send_check(struct sk_buff *skb)
 {
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
@@ -41,6 +52,15 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	unsigned int mss;
+	int offset;
+	__wsum csum;
+
+	if (skb->encapsulation &&
+	    (skb_shinfo(skb)->gso_type &
+	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
+		segs = skb_udp_tunnel_segment(skb, features);
+		goto out;
+	}
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
@@ -52,8 +72,10 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 
 		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
+				      SKB_GSO_UDP_TUNNEL_CSUM |
 				      SKB_GSO_IPIP |
-				      SKB_GSO_GRE | SKB_GSO_MPLS) ||
+				      SKB_GSO_GRE | SKB_GSO_GRE_CSUM |
+				      SKB_GSO_MPLS) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 
@@ -63,35 +85,162 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		goto out;
 	}
 
+	/* Do software UFO. Complete and fill in the UDP checksum as
+	 * HW cannot do checksum of UDP packets sent as multiple
+	 * IP fragments.
+	 */
+	offset = skb_checksum_start_offset(skb);
+	csum = skb_checksum(skb, offset, skb->len - offset, 0);
+	offset += skb->csum_offset;
+	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
+	skb->ip_summed = CHECKSUM_NONE;
+
 	/* Fragment the skb. IP headers of the fragments are updated in
 	 * inet_gso_segment()
 	 */
-	if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL)
-		segs = skb_udp_tunnel_segment(skb, features);
-	else {
-		int offset;
-		__wsum csum;
-
-		/* Do software UFO. Complete and fill in the UDP checksum as
-		 * HW cannot do checksum of UDP packets sent as multiple
-		 * IP fragments.
-		 */
-		offset = skb_checksum_start_offset(skb);
-		csum = skb_checksum(skb, offset, skb->len - offset, 0);
-		offset += skb->csum_offset;
-		*(__sum16 *)(skb->data + offset) = csum_fold(csum);
-		skb->ip_summed = CHECKSUM_NONE;
-
-		segs = skb_segment(skb, features);
-	}
+	segs = skb_segment(skb, features);
 out:
 	return segs;
 }
 
+int udp_add_offload(struct udp_offload *uo)
+{
+	struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_ATOMIC);
+
+	if (!new_offload)
+		return -ENOMEM;
+
+	new_offload->offload = uo;
+
+	spin_lock(&udp_offload_lock);
+	new_offload->next = udp_offload_base;
+	rcu_assign_pointer(udp_offload_base, new_offload);
+	spin_unlock(&udp_offload_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(udp_add_offload);
+
+static void udp_offload_free_routine(struct rcu_head *head)
+{
+	struct udp_offload_priv *ou_priv = container_of(head, struct udp_offload_priv, rcu);
+	kfree(ou_priv);
+}
+
+void udp_del_offload(struct udp_offload *uo)
+{
+	struct udp_offload_priv __rcu **head = &udp_offload_base;
+	struct udp_offload_priv *uo_priv;
+
+	spin_lock(&udp_offload_lock);
+
+	uo_priv = udp_deref_protected(*head);
+	for (; uo_priv != NULL;
+	     uo_priv = udp_deref_protected(*head)) {
+		if (uo_priv->offload == uo) {
+			rcu_assign_pointer(*head,
+					   udp_deref_protected(uo_priv->next));
+			goto unlock;
+		}
+		head = &uo_priv->next;
+	}
+	pr_warn("udp_del_offload: didn't find offload for port %d\n", ntohs(uo->port));
+unlock:
+	spin_unlock(&udp_offload_lock);
+	if (uo_priv != NULL)
+		call_rcu(&uo_priv->rcu, udp_offload_free_routine);
+}
+EXPORT_SYMBOL(udp_del_offload);
+
+static struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+	struct udp_offload_priv *uo_priv;
+	struct sk_buff *p, **pp = NULL;
+	struct udphdr *uh, *uh2;
+	unsigned int hlen, off;
+	int flush = 1;
+
+	if (NAPI_GRO_CB(skb)->udp_mark ||
+	    (!skb->encapsulation && skb->ip_summed != CHECKSUM_COMPLETE))
+		goto out;
+
+	/* mark that this skb passed once through the udp gro layer */
+	NAPI_GRO_CB(skb)->udp_mark = 1;
+
+	off  = skb_gro_offset(skb);
+	hlen = off + sizeof(*uh);
+	uh   = skb_gro_header_fast(skb, off);
+	if (skb_gro_header_hard(skb, hlen)) {
+		uh = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!uh))
+			goto out;
+	}
+
+	rcu_read_lock();
+	uo_priv = rcu_dereference(udp_offload_base);
+	for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) {
+		if (uo_priv->offload->port == uh->dest &&
+		    uo_priv->offload->callbacks.gro_receive)
+			goto unflush;
+	}
+	goto out_unlock;
+
+unflush:
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		uh2 = (struct udphdr   *)(p->data + off);
+		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+	}
+
+	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
+	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
+	pp = uo_priv->offload->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+	return pp;
+}
+
+static int udp_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct udp_offload_priv *uo_priv;
+	__be16 newlen = htons(skb->len - nhoff);
+	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
+	int err = -ENOSYS;
+
+	uh->len = newlen;
+
+	rcu_read_lock();
+
+	uo_priv = rcu_dereference(udp_offload_base);
+	for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) {
+		if (uo_priv->offload->port == uh->dest &&
+		    uo_priv->offload->callbacks.gro_complete)
+			break;
+	}
+
+	if (uo_priv != NULL)
+		err = uo_priv->offload->callbacks.gro_complete(skb, nhoff + sizeof(struct udphdr));
+
+	rcu_read_unlock();
+	return err;
+}
+
 static const struct net_offload udpv4_offload = {
 	.callbacks = {
 		.gso_send_check = udp4_ufo_send_check,
 		.gso_segment = udp4_ufo_fragment,
+		.gro_receive  =	udp_gro_receive,
+		.gro_complete =	udp_gro_complete,
 	},
 };
 
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 2c46acd4cc3..3b3efbda48e 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -70,7 +70,6 @@ static struct inet_protosw udplite4_protosw = {
 	.protocol	=  IPPROTO_UDPLITE,
 	.prot		=  &udplite_prot,
 	.ops		=  &inet_dgram_ops,
-	.no_check	=  0,		/* must checksum (RFC 3828) */
 	.flags		=  INET_PROTOSW_PERMANENT,
 };
 
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 1f12c8b4586..aac6197b7a7 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -37,15 +37,6 @@ drop:
 	return NET_RX_DROP;
 }
 
-int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
-		    int encap_type)
-{
-	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
-	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
-	return xfrm_input(skb, nexthdr, spi, encap_type);
-}
-EXPORT_SYMBOL(xfrm4_rcv_encap);
-
 int xfrm4_transport_finish(struct sk_buff *skb, int async)
 {
 	struct iphdr *iph = ip_hdr(skb);
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
index e3db3f91511..71acd0014f2 100644
--- a/net/ipv4/xfrm4_mode_beet.c
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -48,7 +48,7 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb)
 		hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4);
 
 	skb_set_network_header(skb, -x->props.header_len -
-			            hdrlen + (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph)));
+				    hdrlen + (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph)));
 	if (x->sel.family != AF_INET6)
 		skb->network_header += IPV4_BEET_PHMAXLEN;
 	skb->mac_header = skb->network_header +
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 31b18152528..91771a7c802 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -15,65 +15,6 @@
 #include <net/ip.h>
 #include <net/xfrm.h>
 
-/* Informational hook. The decap is still done here. */
-static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly;
-static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex);
-
-int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler)
-{
-	struct xfrm_tunnel_notifier __rcu **pprev;
-	struct xfrm_tunnel_notifier *t;
-	int ret = -EEXIST;
-	int priority = handler->priority;
-
-	mutex_lock(&xfrm4_mode_tunnel_input_mutex);
-
-	for (pprev = &rcv_notify_handlers;
-	     (t = rcu_dereference_protected(*pprev,
-	     lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL;
-	     pprev = &t->next) {
-		if (t->priority > priority)
-			break;
-		if (t->priority == priority)
-			goto err;
-
-	}
-
-	handler->next = *pprev;
-	rcu_assign_pointer(*pprev, handler);
-
-	ret = 0;
-
-err:
-	mutex_unlock(&xfrm4_mode_tunnel_input_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register);
-
-int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler)
-{
-	struct xfrm_tunnel_notifier __rcu **pprev;
-	struct xfrm_tunnel_notifier *t;
-	int ret = -ENOENT;
-
-	mutex_lock(&xfrm4_mode_tunnel_input_mutex);
-	for (pprev = &rcv_notify_handlers;
-	     (t = rcu_dereference_protected(*pprev,
-	     lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL;
-	     pprev = &t->next) {
-		if (t == handler) {
-			*pprev = handler->next;
-			ret = 0;
-			break;
-		}
-	}
-	mutex_unlock(&xfrm4_mode_tunnel_input_mutex);
-	synchronize_net();
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_deregister);
-
 static inline void ipip_ecn_decapsulate(struct sk_buff *skb)
 {
 	struct iphdr *inner_iph = ipip_hdr(skb);
@@ -117,24 +58,18 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
 		0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
-	ip_select_ident(skb, dst->child, NULL);
 
 	top_iph->ttl = ip4_dst_hoplimit(dst->child);
 
 	top_iph->saddr = x->props.saddr.a4;
 	top_iph->daddr = x->id.daddr.a4;
+	ip_select_ident(skb, NULL);
 
 	return 0;
 }
 
-#define for_each_input_rcu(head, handler)	\
-	for (handler = rcu_dereference(head);	\
-	     handler != NULL;			\
-	     handler = rcu_dereference(handler->next))
-
 static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-	struct xfrm_tunnel_notifier *handler;
 	int err = -EINVAL;
 
 	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
@@ -143,9 +78,6 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
 		goto out;
 
-	for_each_input_rcu(rcv_notify_handlers, handler)
-		handler->handler(skb);
-
 	err = skb_unclone(skb, GFP_ATOMIC);
 	if (err)
 		goto out;
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index baa0f63731f..d5f6bd9a210 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -25,7 +25,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
 	if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE)
 		goto out;
 
-	if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->local_df)
+	if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->ignore_df)
 		goto out;
 
 	mtu = dst_mtu(skb_dst(skb));
@@ -62,10 +62,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED;
-
-	skb->protocol = htons(ETH_P_IP);
+	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
 
 	return x->outer_mode->output2(x, skb);
 }
@@ -73,27 +70,34 @@ EXPORT_SYMBOL(xfrm4_prepare_output);
 
 int xfrm4_output_finish(struct sk_buff *skb)
 {
-#ifdef CONFIG_NETFILTER
-	if (!skb_dst(skb)->xfrm) {
-		IPCB(skb)->flags |= IPSKB_REROUTED;
-		return dst_output(skb);
-	}
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+	skb->protocol = htons(ETH_P_IP);
 
+#ifdef CONFIG_NETFILTER
 	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
 #endif
 
-	skb->protocol = htons(ETH_P_IP);
 	return xfrm_output(skb);
 }
 
-int xfrm4_output(struct sk_buff *skb)
+static int __xfrm4_output(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
-	struct xfrm_state *x = dst->xfrm;
+	struct xfrm_state *x = skb_dst(skb)->xfrm;
+
+#ifdef CONFIG_NETFILTER
+	if (!x) {
+		IPCB(skb)->flags |= IPSKB_REROUTED;
+		return dst_output(skb);
+	}
+#endif
 
+	return x->outer_mode->afinfo->output_finish(skb);
+}
+
+int xfrm4_output(struct sock *sk, struct sk_buff *skb)
+{
 	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb,
-			    NULL, dst->dev,
-			    x->outer_mode->afinfo->output_finish,
+			    NULL, skb_dst(skb)->dev, __xfrm4_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index e1a63930a96..6156f68a1e9 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -325,6 +325,7 @@ void __init xfrm4_init(void)
 
 	xfrm4_state_init();
 	xfrm4_policy_init();
+	xfrm4_protocol_init();
 #ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&xfrm4_net_ops);
 #endif
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
new file mode 100644
index 00000000000..a2ce0101eaa
--- /dev/null
+++ b/net/ipv4/xfrm4_protocol.c
@@ -0,0 +1,301 @@
+/* xfrm4_protocol.c - Generic xfrm protocol multiplexer.
+ *
+ * Copyright (C) 2013 secunet Security Networks AG
+ *
+ * Author:
+ * Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * Based on:
+ * net/ipv4/tunnel4.c
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/skbuff.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/protocol.h>
+#include <net/xfrm.h>
+
+static struct xfrm4_protocol __rcu *esp4_handlers __read_mostly;
+static struct xfrm4_protocol __rcu *ah4_handlers __read_mostly;
+static struct xfrm4_protocol __rcu *ipcomp4_handlers __read_mostly;
+static DEFINE_MUTEX(xfrm4_protocol_mutex);
+
+static inline struct xfrm4_protocol __rcu **proto_handlers(u8 protocol)
+{
+	switch (protocol) {
+	case IPPROTO_ESP:
+		return &esp4_handlers;
+	case IPPROTO_AH:
+		return &ah4_handlers;
+	case IPPROTO_COMP:
+		return &ipcomp4_handlers;
+	}
+
+	return NULL;
+}
+
+#define for_each_protocol_rcu(head, handler)		\
+	for (handler = rcu_dereference(head);		\
+	     handler != NULL;				\
+	     handler = rcu_dereference(handler->next))	\
+
+int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
+{
+	int ret;
+	struct xfrm4_protocol *handler;
+	struct xfrm4_protocol __rcu **head = proto_handlers(protocol);
+
+	if (!head)
+		return 0;
+
+	for_each_protocol_rcu(*head, handler)
+		if ((ret = handler->cb_handler(skb, err)) <= 0)
+			return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL(xfrm4_rcv_cb);
+
+int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
+		    int encap_type)
+{
+	int ret;
+	struct xfrm4_protocol *handler;
+	struct xfrm4_protocol __rcu **head = proto_handlers(nexthdr);
+
+	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+	if (!head)
+		goto out;
+
+	for_each_protocol_rcu(*head, handler)
+		if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
+			return ret;
+
+out:
+	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+	kfree_skb(skb);
+	return 0;
+}
+EXPORT_SYMBOL(xfrm4_rcv_encap);
+
+static int xfrm4_esp_rcv(struct sk_buff *skb)
+{
+	int ret;
+	struct xfrm4_protocol *handler;
+
+	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+
+	for_each_protocol_rcu(esp4_handlers, handler)
+		if ((ret = handler->handler(skb)) != -EINVAL)
+			return ret;
+
+	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static void xfrm4_esp_err(struct sk_buff *skb, u32 info)
+{
+	struct xfrm4_protocol *handler;
+
+	for_each_protocol_rcu(esp4_handlers, handler)
+		if (!handler->err_handler(skb, info))
+			break;
+}
+
+static int xfrm4_ah_rcv(struct sk_buff *skb)
+{
+	int ret;
+	struct xfrm4_protocol *handler;
+
+	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+
+	for_each_protocol_rcu(ah4_handlers, handler)
+		if ((ret = handler->handler(skb)) != -EINVAL)
+			return ret;;
+
+	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static void xfrm4_ah_err(struct sk_buff *skb, u32 info)
+{
+	struct xfrm4_protocol *handler;
+
+	for_each_protocol_rcu(ah4_handlers, handler)
+		if (!handler->err_handler(skb, info))
+			break;
+}
+
+static int xfrm4_ipcomp_rcv(struct sk_buff *skb)
+{
+	int ret;
+	struct xfrm4_protocol *handler;
+
+	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+
+	for_each_protocol_rcu(ipcomp4_handlers, handler)
+		if ((ret = handler->handler(skb)) != -EINVAL)
+			return ret;
+
+	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static void xfrm4_ipcomp_err(struct sk_buff *skb, u32 info)
+{
+	struct xfrm4_protocol *handler;
+
+	for_each_protocol_rcu(ipcomp4_handlers, handler)
+		if (!handler->err_handler(skb, info))
+			break;
+}
+
+static const struct net_protocol esp4_protocol = {
+	.handler	=	xfrm4_esp_rcv,
+	.err_handler	=	xfrm4_esp_err,
+	.no_policy	=	1,
+	.netns_ok	=	1,
+};
+
+static const struct net_protocol ah4_protocol = {
+	.handler	=	xfrm4_ah_rcv,
+	.err_handler	=	xfrm4_ah_err,
+	.no_policy	=	1,
+	.netns_ok	=	1,
+};
+
+static const struct net_protocol ipcomp4_protocol = {
+	.handler	=	xfrm4_ipcomp_rcv,
+	.err_handler	=	xfrm4_ipcomp_err,
+	.no_policy	=	1,
+	.netns_ok	=	1,
+};
+
+static struct xfrm_input_afinfo xfrm4_input_afinfo = {
+	.family		=	AF_INET,
+	.owner		=	THIS_MODULE,
+	.callback	=	xfrm4_rcv_cb,
+};
+
+static inline const struct net_protocol *netproto(unsigned char protocol)
+{
+	switch (protocol) {
+	case IPPROTO_ESP:
+		return &esp4_protocol;
+	case IPPROTO_AH:
+		return &ah4_protocol;
+	case IPPROTO_COMP:
+		return &ipcomp4_protocol;
+	}
+
+	return NULL;
+}
+
+int xfrm4_protocol_register(struct xfrm4_protocol *handler,
+			    unsigned char protocol)
+{
+	struct xfrm4_protocol __rcu **pprev;
+	struct xfrm4_protocol *t;
+	bool add_netproto = false;
+	int ret = -EEXIST;
+	int priority = handler->priority;
+
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
+	mutex_lock(&xfrm4_protocol_mutex);
+
+	if (!rcu_dereference_protected(*proto_handlers(protocol),
+				       lockdep_is_held(&xfrm4_protocol_mutex)))
+		add_netproto = true;
+
+	for (pprev = proto_handlers(protocol);
+	     (t = rcu_dereference_protected(*pprev,
+			lockdep_is_held(&xfrm4_protocol_mutex))) != NULL;
+	     pprev = &t->next) {
+		if (t->priority < priority)
+			break;
+		if (t->priority == priority)
+			goto err;
+	}
+
+	handler->next = *pprev;
+	rcu_assign_pointer(*pprev, handler);
+
+	ret = 0;
+
+err:
+	mutex_unlock(&xfrm4_protocol_mutex);
+
+	if (add_netproto) {
+		if (inet_add_protocol(netproto(protocol), protocol)) {
+			pr_err("%s: can't add protocol\n", __func__);
+			ret = -EAGAIN;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(xfrm4_protocol_register);
+
+int xfrm4_protocol_deregister(struct xfrm4_protocol *handler,
+			      unsigned char protocol)
+{
+	struct xfrm4_protocol __rcu **pprev;
+	struct xfrm4_protocol *t;
+	int ret = -ENOENT;
+
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
+	mutex_lock(&xfrm4_protocol_mutex);
+
+	for (pprev = proto_handlers(protocol);
+	     (t = rcu_dereference_protected(*pprev,
+			lockdep_is_held(&xfrm4_protocol_mutex))) != NULL;
+	     pprev = &t->next) {
+		if (t == handler) {
+			*pprev = handler->next;
+			ret = 0;
+			break;
+		}
+	}
+
+	if (!rcu_dereference_protected(*proto_handlers(protocol),
+				       lockdep_is_held(&xfrm4_protocol_mutex))) {
+		if (inet_del_protocol(netproto(protocol), protocol) < 0) {
+			pr_err("%s: can't remove protocol\n", __func__);
+			ret = -EAGAIN;
+		}
+	}
+
+	mutex_unlock(&xfrm4_protocol_mutex);
+
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL(xfrm4_protocol_deregister);
+
+void __init xfrm4_protocol_init(void)
+{
+	xfrm_input_register_afinfo(&xfrm4_input_afinfo);
+}
+EXPORT_SYMBOL(xfrm4_protocol_init);
diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c
index 0b2a0641526..542074c00c7 100644
--- a/net/ipv4/xfrm4_state.c
+++ b/net/ipv4/xfrm4_state.c
@@ -16,7 +16,7 @@
 
 static int xfrm4_init_flags(struct xfrm_state *x)
 {
-	if (ipv4_config.no_pmtu_disc)
+	if (xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)
 		x->props.flags |= XFRM_STATE_NOPMTUDISC;
 	return 0;
 }
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index d92e5586783..438a73aa777 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -138,6 +138,7 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION
 config IPV6_VTI
 tristate "Virtual (secure) IPv6: tunneling"
 	select IPV6_TUNNEL
+	select NET_IP_TUNNEL
 	depends on INET6_XFRM_MODE_TUNNEL
 	---help---
 	Tunneling means encapsulating data of one protocol type within
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 17bb830872d..2fe68364bb2 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -16,7 +16,7 @@ ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o
 ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o
 
 ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \
-	xfrm6_output.o
+	xfrm6_output.o xfrm6_protocol.o
 ipv6-$(CONFIG_NETFILTER) += netfilter.o
 ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o
 ipv6-$(CONFIG_PROC_FS) += proc.o
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index be4dbbd17d3..5667b3003af 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -133,10 +133,12 @@ static int ipv6_count_addresses(struct inet6_dev *idev);
 static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE];
 static DEFINE_SPINLOCK(addrconf_hash_lock);
 
-static void addrconf_verify(unsigned long);
+static void addrconf_verify(void);
+static void addrconf_verify_rtnl(void);
+static void addrconf_verify_work(struct work_struct *);
 
-static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0);
-static DEFINE_SPINLOCK(addrconf_verify_lock);
+static struct workqueue_struct *addrconf_wq;
+static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work);
 
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
@@ -151,7 +153,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 						  u32 flags, u32 noflags);
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp);
-static void addrconf_dad_timer(unsigned long data);
+static void addrconf_dad_work(struct work_struct *w);
 static void addrconf_dad_completed(struct inet6_ifaddr *ifp);
 static void addrconf_dad_run(struct inet6_dev *idev);
 static void addrconf_rs_timer(unsigned long data);
@@ -247,9 +249,9 @@ static void addrconf_del_rs_timer(struct inet6_dev *idev)
 		__in6_dev_put(idev);
 }
 
-static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp)
+static void addrconf_del_dad_work(struct inet6_ifaddr *ifp)
 {
-	if (del_timer(&ifp->dad_timer))
+	if (cancel_delayed_work(&ifp->dad_work))
 		__in6_ifa_put(ifp);
 }
 
@@ -261,31 +263,26 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev,
 	mod_timer(&idev->rs_timer, jiffies + when);
 }
 
-static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp,
-				   unsigned long when)
+static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
+				   unsigned long delay)
 {
-	if (!timer_pending(&ifp->dad_timer))
+	if (!delayed_work_pending(&ifp->dad_work))
 		in6_ifa_hold(ifp);
-	mod_timer(&ifp->dad_timer, jiffies + when);
+	mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
 }
 
 static int snmp6_alloc_dev(struct inet6_dev *idev)
 {
 	int i;
 
-	if (snmp_mib_init((void __percpu **)idev->stats.ipv6,
-			  sizeof(struct ipstats_mib),
-			  __alignof__(struct ipstats_mib)) < 0)
+	idev->stats.ipv6 = alloc_percpu(struct ipstats_mib);
+	if (!idev->stats.ipv6)
 		goto err_ip;
 
 	for_each_possible_cpu(i) {
 		struct ipstats_mib *addrconf_stats;
-		addrconf_stats = per_cpu_ptr(idev->stats.ipv6[0], i);
+		addrconf_stats = per_cpu_ptr(idev->stats.ipv6, i);
 		u64_stats_init(&addrconf_stats->syncp);
-#if SNMP_ARRAY_SZ == 2
-		addrconf_stats = per_cpu_ptr(idev->stats.ipv6[1], i);
-		u64_stats_init(&addrconf_stats->syncp);
-#endif
 	}
 
 
@@ -303,7 +300,7 @@ static int snmp6_alloc_dev(struct inet6_dev *idev)
 err_icmpmsg:
 	kfree(idev->stats.icmpv6dev);
 err_icmp:
-	snmp_mib_free((void __percpu **)idev->stats.ipv6);
+	free_percpu(idev->stats.ipv6);
 err_ip:
 	return -ENOMEM;
 }
@@ -442,6 +439,8 @@ static int inet6_netconf_msgsize_devconf(int type)
 	if (type == -1 || type == NETCONFA_MC_FORWARDING)
 		size += nla_total_size(4);
 #endif
+	if (type == -1 || type == NETCONFA_PROXY_NEIGH)
+		size += nla_total_size(4);
 
 	return size;
 }
@@ -475,6 +474,10 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 			devconf->mc_forwarding) < 0)
 		goto nla_put_failure;
 #endif
+	if ((type == -1 || type == NETCONFA_PROXY_NEIGH) &&
+	    nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0)
+		goto nla_put_failure;
+
 	return nlmsg_end(skb, nlh);
 
 nla_put_failure:
@@ -509,6 +512,7 @@ errout:
 static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = {
 	[NETCONFA_IFINDEX]	= { .len = sizeof(int) },
 	[NETCONFA_FORWARDING]	= { .len = sizeof(int) },
+	[NETCONFA_PROXY_NEIGH]	= { .len = sizeof(int) },
 };
 
 static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
@@ -744,8 +748,9 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
 
 	in6_dev_put(ifp->idev);
 
-	if (del_timer(&ifp->dad_timer))
-		pr_notice("Timer is still running, when freeing ifa=%p\n", ifp);
+	if (cancel_delayed_work(&ifp->dad_work))
+		pr_notice("delayed DAD work was pending while freeing ifa=%p\n",
+			  ifp);
 
 	if (ifp->state != INET6_IFADDR_STATE_DEAD) {
 		pr_warn("Freeing alive inet6 address %p\n", ifp);
@@ -842,8 +847,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 
 	spin_lock_init(&ifa->lock);
 	spin_lock_init(&ifa->state_lock);
-	setup_timer(&ifa->dad_timer, addrconf_dad_timer,
-		    (unsigned long)ifa);
+	INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work);
 	INIT_HLIST_NODE(&ifa->addr_lst);
 	ifa->scope = scope;
 	ifa->prefix_len = pfxlen;
@@ -893,15 +897,97 @@ out:
 	goto out2;
 }
 
+enum cleanup_prefix_rt_t {
+	CLEANUP_PREFIX_RT_NOP,    /* no cleanup action for prefix route */
+	CLEANUP_PREFIX_RT_DEL,    /* delete the prefix route */
+	CLEANUP_PREFIX_RT_EXPIRE, /* update the lifetime of the prefix route */
+};
+
+/*
+ * Check, whether the prefix for ifp would still need a prefix route
+ * after deleting ifp. The function returns one of the CLEANUP_PREFIX_RT_*
+ * constants.
+ *
+ * 1) we don't purge prefix if address was not permanent.
+ *    prefix is managed by its own lifetime.
+ * 2) we also don't purge, if the address was IFA_F_NOPREFIXROUTE.
+ * 3) if there are no addresses, delete prefix.
+ * 4) if there are still other permanent address(es),
+ *    corresponding prefix is still permanent.
+ * 5) if there are still other addresses with IFA_F_NOPREFIXROUTE,
+ *    don't purge the prefix, assume user space is managing it.
+ * 6) otherwise, update prefix lifetime to the
+ *    longest valid lifetime among the corresponding
+ *    addresses on the device.
+ *    Note: subsequent RA will update lifetime.
+ **/
+static enum cleanup_prefix_rt_t
+check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires)
+{
+	struct inet6_ifaddr *ifa;
+	struct inet6_dev *idev = ifp->idev;
+	unsigned long lifetime;
+	enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_DEL;
+
+	*expires = jiffies;
+
+	list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		if (ifa == ifp)
+			continue;
+		if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr,
+				       ifp->prefix_len))
+			continue;
+		if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE))
+			return CLEANUP_PREFIX_RT_NOP;
+
+		action = CLEANUP_PREFIX_RT_EXPIRE;
+
+		spin_lock(&ifa->lock);
+
+		lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ);
+		/*
+		 * Note: Because this address is
+		 * not permanent, lifetime <
+		 * LONG_MAX / HZ here.
+		 */
+		if (time_before(*expires, ifa->tstamp + lifetime * HZ))
+			*expires = ifa->tstamp + lifetime * HZ;
+		spin_unlock(&ifa->lock);
+	}
+
+	return action;
+}
+
+static void
+cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt)
+{
+	struct rt6_info *rt;
+
+	rt = addrconf_get_prefix_route(&ifp->addr,
+				       ifp->prefix_len,
+				       ifp->idev->dev,
+				       0, RTF_GATEWAY | RTF_DEFAULT);
+	if (rt) {
+		if (del_rt)
+			ip6_del_rt(rt);
+		else {
+			if (!(rt->rt6i_flags & RTF_EXPIRES))
+				rt6_set_expires(rt, expires);
+			ip6_rt_put(rt);
+		}
+	}
+}
+
+
 /* This function wants to get referenced ifp and releases it before return */
 
 static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 {
-	struct inet6_ifaddr *ifa, *ifn;
-	struct inet6_dev *idev = ifp->idev;
 	int state;
-	int deleted = 0, onlink = 0;
-	unsigned long expires = jiffies;
+	enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP;
+	unsigned long expires;
+
+	ASSERT_RTNL();
 
 	spin_lock_bh(&ifp->state_lock);
 	state = ifp->state;
@@ -915,7 +1001,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 	hlist_del_init_rcu(&ifp->addr_lst);
 	spin_unlock_bh(&addrconf_hash_lock);
 
-	write_lock_bh(&idev->lock);
+	write_lock_bh(&ifp->idev->lock);
 
 	if (ifp->flags&IFA_F_TEMPORARY) {
 		list_del(&ifp->tmp_list);
@@ -926,87 +1012,23 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 		__in6_ifa_put(ifp);
 	}
 
-	list_for_each_entry_safe(ifa, ifn, &idev->addr_list, if_list) {
-		if (ifa == ifp) {
-			list_del_init(&ifp->if_list);
-			__in6_ifa_put(ifp);
+	if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE))
+		action = check_cleanup_prefix_route(ifp, &expires);
 
-			if (!(ifp->flags & IFA_F_PERMANENT) || onlink > 0)
-				break;
-			deleted = 1;
-			continue;
-		} else if (ifp->flags & IFA_F_PERMANENT) {
-			if (ipv6_prefix_equal(&ifa->addr, &ifp->addr,
-					      ifp->prefix_len)) {
-				if (ifa->flags & IFA_F_PERMANENT) {
-					onlink = 1;
-					if (deleted)
-						break;
-				} else {
-					unsigned long lifetime;
-
-					if (!onlink)
-						onlink = -1;
-
-					spin_lock(&ifa->lock);
-
-					lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ);
-					/*
-					 * Note: Because this address is
-					 * not permanent, lifetime <
-					 * LONG_MAX / HZ here.
-					 */
-					if (time_before(expires,
-							ifa->tstamp + lifetime * HZ))
-						expires = ifa->tstamp + lifetime * HZ;
-					spin_unlock(&ifa->lock);
-				}
-			}
-		}
-	}
-	write_unlock_bh(&idev->lock);
+	list_del_init(&ifp->if_list);
+	__in6_ifa_put(ifp);
+
+	write_unlock_bh(&ifp->idev->lock);
 
-	addrconf_del_dad_timer(ifp);
+	addrconf_del_dad_work(ifp);
 
 	ipv6_ifa_notify(RTM_DELADDR, ifp);
 
 	inet6addr_notifier_call_chain(NETDEV_DOWN, ifp);
 
-	/*
-	 * Purge or update corresponding prefix
-	 *
-	 * 1) we don't purge prefix here if address was not permanent.
-	 *    prefix is managed by its own lifetime.
-	 * 2) if there're no addresses, delete prefix.
-	 * 3) if there're still other permanent address(es),
-	 *    corresponding prefix is still permanent.
-	 * 4) otherwise, update prefix lifetime to the
-	 *    longest valid lifetime among the corresponding
-	 *    addresses on the device.
-	 *    Note: subsequent RA will update lifetime.
-	 *
-	 * --yoshfuji
-	 */
-	if ((ifp->flags & IFA_F_PERMANENT) && onlink < 1) {
-		struct in6_addr prefix;
-		struct rt6_info *rt;
-
-		ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len);
-
-		rt = addrconf_get_prefix_route(&prefix,
-					       ifp->prefix_len,
-					       ifp->idev->dev,
-					       0, RTF_GATEWAY | RTF_DEFAULT);
-
-		if (rt) {
-			if (onlink == 0) {
-				ip6_del_rt(rt);
-				rt = NULL;
-			} else if (!(rt->rt6i_flags & RTF_EXPIRES)) {
-				rt6_set_expires(rt, expires);
-			}
-		}
-		ip6_rt_put(rt);
+	if (action != CLEANUP_PREFIX_RT_NOP) {
+		cleanup_prefix_route(ifp, expires,
+			action == CLEANUP_PREFIX_RT_DEL);
 	}
 
 	/* clean up prefsrc entries */
@@ -1080,8 +1102,11 @@ retry:
 	 * Lifetime is greater than REGEN_ADVANCE time units.  In particular,
 	 * an implementation must not create a temporary address with a zero
 	 * Preferred Lifetime.
+	 * Use age calculation as in addrconf_verify to avoid unnecessary
+	 * temporary addresses being generated.
 	 */
-	if (tmp_prefered_lft <= regen_advance) {
+	age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+	if (tmp_prefered_lft <= regen_advance + age) {
 		in6_ifa_put(ifp);
 		in6_dev_put(idev);
 		ret = -1;
@@ -1202,7 +1227,7 @@ static int ipv6_get_saddr_eval(struct net *net,
 		 *       |             d is scope of the destination.
 		 *  B-d  |  \
 		 *       |   \      <- smaller scope is better if
-		 *  B-15 |    \        if scope is enough for destinaion.
+		 *  B-15 |    \        if scope is enough for destination.
 		 *       |             ret = B - scope (-1 <= scope >= d <= 15).
 		 * d-C-1 | /
 		 *       |/         <- greater is better
@@ -1414,7 +1439,9 @@ int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
 	struct inet6_ifaddr *ifp;
 	int err = -EADDRNOTAVAIL;
 
-	list_for_each_entry(ifp, &idev->addr_list, if_list) {
+	list_for_each_entry_reverse(ifp, &idev->addr_list, if_list) {
+		if (ifp->scope > IFA_LINK)
+			break;
 		if (ifp->scope == IFA_LINK &&
 		    !(ifp->flags & banned_flags)) {
 			*addr = ifp->addr;
@@ -1576,7 +1603,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 {
 	if (ifp->flags&IFA_F_PERMANENT) {
 		spin_lock_bh(&ifp->lock);
-		addrconf_del_dad_timer(ifp);
+		addrconf_del_dad_work(ifp);
 		ifp->flags |= IFA_F_TENTATIVE;
 		if (dad_failed)
 			ifp->flags |= IFA_F_DADFAILED;
@@ -1597,20 +1624,21 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 			spin_unlock_bh(&ifp->lock);
 		}
 		ipv6_del_addr(ifp);
-	} else
+	} else {
 		ipv6_del_addr(ifp);
+	}
 }
 
 static int addrconf_dad_end(struct inet6_ifaddr *ifp)
 {
 	int err = -ENOENT;
 
-	spin_lock(&ifp->state_lock);
+	spin_lock_bh(&ifp->state_lock);
 	if (ifp->state == INET6_IFADDR_STATE_DAD) {
 		ifp->state = INET6_IFADDR_STATE_POSTDAD;
 		err = 0;
 	}
-	spin_unlock(&ifp->state_lock);
+	spin_unlock_bh(&ifp->state_lock);
 
 	return err;
 }
@@ -1643,7 +1671,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 		}
 	}
 
-	addrconf_dad_stop(ifp, 1);
+	spin_lock_bh(&ifp->state_lock);
+	/* transition from _POSTDAD to _ERRDAD */
+	ifp->state = INET6_IFADDR_STATE_ERRDAD;
+	spin_unlock_bh(&ifp->state_lock);
+
+	addrconf_mod_dad_work(ifp, 0);
 }
 
 /* Join to solicited addr multicast group. */
@@ -1652,6 +1685,8 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct in6_addr maddr;
 
+	ASSERT_RTNL();
+
 	if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))
 		return;
 
@@ -1663,6 +1698,8 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct in6_addr maddr;
 
+	ASSERT_RTNL();
+
 	if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP))
 		return;
 
@@ -1673,7 +1710,10 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
-	if (ifp->prefix_len == 127) /* RFC 6164 */
+
+	ASSERT_RTNL();
+
+	if (ifp->prefix_len >= 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
 	if (ipv6_addr_any(&addr))
@@ -1684,7 +1724,10 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
-	if (ifp->prefix_len == 127) /* RFC 6164 */
+
+	ASSERT_RTNL();
+
+	if (ifp->prefix_len >= 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
 	if (ipv6_addr_any(&addr))
@@ -1818,6 +1861,7 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev)
 		return addrconf_ifid_sit(eui, dev);
 	case ARPHRD_IPGRE:
 		return addrconf_ifid_gre(eui, dev);
+	case ARPHRD_6LOWPAN:
 	case ARPHRD_IEEE802154:
 		return addrconf_ifid_eui64(eui, dev);
 	case ARPHRD_IEEE1394:
@@ -1834,7 +1878,9 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev)
 	struct inet6_ifaddr *ifp;
 
 	read_lock_bh(&idev->lock);
-	list_for_each_entry(ifp, &idev->addr_list, if_list) {
+	list_for_each_entry_reverse(ifp, &idev->addr_list, if_list) {
+		if (ifp->scope > IFA_LINK)
+			break;
 		if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) {
 			memcpy(eui, ifp->addr.s6_addr+8, 8);
 			err = 0;
@@ -2240,11 +2286,13 @@ ok:
 				return;
 			}
 
-			ifp->flags |= IFA_F_MANAGETEMPADDR;
 			update_lft = 0;
 			create = 1;
+			spin_lock_bh(&ifp->lock);
+			ifp->flags |= IFA_F_MANAGETEMPADDR;
 			ifp->cstamp = jiffies;
 			ifp->tokenized = tokenized;
+			spin_unlock_bh(&ifp->lock);
 			addrconf_dad_start(ifp);
 		}
 
@@ -2295,7 +2343,7 @@ ok:
 					 create, now);
 
 			in6_ifa_put(ifp);
-			addrconf_verify(0);
+			addrconf_verify();
 		}
 	}
 	inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
@@ -2429,8 +2477,11 @@ static int inet6_addr_add(struct net *net, int ifindex,
 			    valid_lft, prefered_lft);
 
 	if (!IS_ERR(ifp)) {
-		addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
-				      expires, flags);
+		if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
+			addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
+					      expires, flags);
+		}
+
 		/*
 		 * Note that section 3.1 of RFC 4429 indicates
 		 * that the Optimistic flag should not be set for
@@ -2441,15 +2492,15 @@ static int inet6_addr_add(struct net *net, int ifindex,
 			manage_tempaddrs(idev, ifp, valid_lft, prefered_lft,
 					 true, jiffies);
 		in6_ifa_put(ifp);
-		addrconf_verify(0);
+		addrconf_verify_rtnl();
 		return 0;
 	}
 
 	return PTR_ERR(ifp);
 }
 
-static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *pfx,
-			  unsigned int plen)
+static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
+			  const struct in6_addr *pfx, unsigned int plen)
 {
 	struct inet6_ifaddr *ifp;
 	struct inet6_dev *idev;
@@ -2472,7 +2523,12 @@ static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *p
 			in6_ifa_hold(ifp);
 			read_unlock_bh(&idev->lock);
 
+			if (!(ifp->flags & IFA_F_TEMPORARY) &&
+			    (ifa_flags & IFA_F_MANAGETEMPADDR))
+				manage_tempaddrs(idev, ifp, 0, 0, false,
+						 jiffies);
 			ipv6_del_addr(ifp);
+			addrconf_verify_rtnl();
 			return 0;
 		}
 	}
@@ -2512,7 +2568,7 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg)
 		return -EFAULT;
 
 	rtnl_lock();
-	err = inet6_addr_del(net, ireq.ifr6_ifindex, &ireq.ifr6_addr,
+	err = inet6_addr_del(net, ireq.ifr6_ifindex, 0, &ireq.ifr6_addr,
 			     ireq.ifr6_prefixlen);
 	rtnl_unlock();
 	return err;
@@ -2524,7 +2580,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	struct inet6_ifaddr *ifp;
 
 	ifp = ipv6_add_addr(idev, addr, NULL, plen,
-			    scope, IFA_F_PERMANENT, 0, 0);
+			    scope, IFA_F_PERMANENT,
+			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
 	if (!IS_ERR(ifp)) {
 		spin_lock_bh(&ifp->lock);
 		ifp->flags &= ~IFA_F_TENTATIVE;
@@ -2625,8 +2682,18 @@ static void init_loopback(struct net_device *dev)
 			if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE))
 				continue;
 
-			if (sp_ifa->rt)
-				continue;
+			if (sp_ifa->rt) {
+				/* This dst has been added to garbage list when
+				 * lo device down, release this obsolete dst and
+				 * reallocate a new router for ifa.
+				 */
+				if (sp_ifa->rt->dst.obsolete > 0) {
+					ip6_rt_put(sp_ifa->rt);
+					sp_ifa->rt = NULL;
+				} else {
+					continue;
+				}
+			}
 
 			sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, false);
 
@@ -2652,7 +2719,8 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr
 #endif
 
 
-	ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, 0, 0);
+	ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags,
+			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
 	if (!IS_ERR(ifp)) {
 		addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0);
 		addrconf_dad_start(ifp);
@@ -2673,7 +2741,8 @@ static void addrconf_dev_config(struct net_device *dev)
 	    (dev->type != ARPHRD_INFINIBAND) &&
 	    (dev->type != ARPHRD_IEEE802154) &&
 	    (dev->type != ARPHRD_IEEE1394) &&
-	    (dev->type != ARPHRD_TUNNEL6)) {
+	    (dev->type != ARPHRD_TUNNEL6) &&
+	    (dev->type != ARPHRD_6LOWPAN)) {
 		/* Alas, we support only Ethernet autoconfiguration. */
 		return;
 	}
@@ -2739,21 +2808,11 @@ static void addrconf_gre_config(struct net_device *dev)
 	ipv6_addr_set(&addr,  htonl(0xFE800000), 0, 0, 0);
 	if (!ipv6_generate_eui64(addr.s6_addr + 8, dev))
 		addrconf_add_linklocal(idev, &addr);
+	else
+		addrconf_prefix_route(&addr, 64, dev, 0, 0);
 }
 #endif
 
-static inline int
-ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev)
-{
-	struct in6_addr lladdr;
-
-	if (!ipv6_get_lladdr(link_dev, &lladdr, IFA_F_TENTATIVE)) {
-		addrconf_add_linklocal(idev, &lladdr);
-		return 0;
-	}
-	return -1;
-}
-
 static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			   void *ptr)
 {
@@ -2870,7 +2929,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 		}
 
 		/*
-		 * MTU falled under IPV6_MIN_MTU.
+		 * if MTU under IPV6_MIN_MTU.
 		 * Stop IPv6 on this interface.
 		 */
 
@@ -2962,7 +3021,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 		hlist_for_each_entry_rcu(ifa, h, addr_lst) {
 			if (ifa->idev == idev) {
 				hlist_del_init_rcu(&ifa->addr_lst);
-				addrconf_del_dad_timer(ifa);
+				addrconf_del_dad_work(ifa);
 				goto restart;
 			}
 		}
@@ -3000,7 +3059,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	while (!list_empty(&idev->addr_list)) {
 		ifa = list_first_entry(&idev->addr_list,
 				       struct inet6_ifaddr, if_list);
-		addrconf_del_dad_timer(ifa);
+		addrconf_del_dad_work(ifa);
 
 		list_del(&ifa->if_list);
 
@@ -3096,20 +3155,20 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp)
 	if (ifp->flags & IFA_F_OPTIMISTIC)
 		rand_num = 0;
 	else
-		rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1);
+		rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1);
 
 	ifp->dad_probes = idev->cnf.dad_transmits;
-	addrconf_mod_dad_timer(ifp, rand_num);
+	addrconf_mod_dad_work(ifp, rand_num);
 }
 
-static void addrconf_dad_start(struct inet6_ifaddr *ifp)
+static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net_device *dev = idev->dev;
 
 	addrconf_join_solict(dev, &ifp->addr);
 
-	net_srandom(ifp->addr.s6_addr32[3]);
+	prandom_seed((__force u32) ifp->addr.s6_addr32[3]);
 
 	read_lock_bh(&idev->lock);
 	spin_lock(&ifp->lock);
@@ -3154,25 +3213,68 @@ out:
 	read_unlock_bh(&idev->lock);
 }
 
-static void addrconf_dad_timer(unsigned long data)
+static void addrconf_dad_start(struct inet6_ifaddr *ifp)
+{
+	bool begin_dad = false;
+
+	spin_lock_bh(&ifp->state_lock);
+	if (ifp->state != INET6_IFADDR_STATE_DEAD) {
+		ifp->state = INET6_IFADDR_STATE_PREDAD;
+		begin_dad = true;
+	}
+	spin_unlock_bh(&ifp->state_lock);
+
+	if (begin_dad)
+		addrconf_mod_dad_work(ifp, 0);
+}
+
+static void addrconf_dad_work(struct work_struct *w)
 {
-	struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data;
+	struct inet6_ifaddr *ifp = container_of(to_delayed_work(w),
+						struct inet6_ifaddr,
+						dad_work);
 	struct inet6_dev *idev = ifp->idev;
 	struct in6_addr mcaddr;
 
+	enum {
+		DAD_PROCESS,
+		DAD_BEGIN,
+		DAD_ABORT,
+	} action = DAD_PROCESS;
+
+	rtnl_lock();
+
+	spin_lock_bh(&ifp->state_lock);
+	if (ifp->state == INET6_IFADDR_STATE_PREDAD) {
+		action = DAD_BEGIN;
+		ifp->state = INET6_IFADDR_STATE_DAD;
+	} else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) {
+		action = DAD_ABORT;
+		ifp->state = INET6_IFADDR_STATE_POSTDAD;
+	}
+	spin_unlock_bh(&ifp->state_lock);
+
+	if (action == DAD_BEGIN) {
+		addrconf_dad_begin(ifp);
+		goto out;
+	} else if (action == DAD_ABORT) {
+		addrconf_dad_stop(ifp, 1);
+		goto out;
+	}
+
 	if (!ifp->dad_probes && addrconf_dad_end(ifp))
 		goto out;
 
-	write_lock(&idev->lock);
+	write_lock_bh(&idev->lock);
 	if (idev->dead || !(idev->if_flags & IF_READY)) {
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 		goto out;
 	}
 
 	spin_lock(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_DEAD) {
 		spin_unlock(&ifp->lock);
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 		goto out;
 	}
 
@@ -3183,7 +3285,7 @@ static void addrconf_dad_timer(unsigned long data)
 
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
 		spin_unlock(&ifp->lock);
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 
 		addrconf_dad_completed(ifp);
 
@@ -3191,16 +3293,35 @@ static void addrconf_dad_timer(unsigned long data)
 	}
 
 	ifp->dad_probes--;
-	addrconf_mod_dad_timer(ifp,
-			       NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
+	addrconf_mod_dad_work(ifp,
+			      NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
 	spin_unlock(&ifp->lock);
-	write_unlock(&idev->lock);
+	write_unlock_bh(&idev->lock);
 
 	/* send a neighbour solicitation for our addr */
 	addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
 	ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any);
 out:
 	in6_ifa_put(ifp);
+	rtnl_unlock();
+}
+
+/* ifp->idev must be at least read locked */
+static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp)
+{
+	struct inet6_ifaddr *ifpiter;
+	struct inet6_dev *idev = ifp->idev;
+
+	list_for_each_entry_reverse(ifpiter, &idev->addr_list, if_list) {
+		if (ifpiter->scope > IFA_LINK)
+			break;
+		if (ifp != ifpiter && ifpiter->scope == IFA_LINK &&
+		    (ifpiter->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE|
+				       IFA_F_OPTIMISTIC|IFA_F_DADFAILED)) ==
+		    IFA_F_PERMANENT)
+			return false;
+	}
+	return true;
 }
 
 static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
@@ -3209,7 +3330,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 	struct in6_addr lladdr;
 	bool send_rs, send_mld;
 
-	addrconf_del_dad_timer(ifp);
+	addrconf_del_dad_work(ifp);
 
 	/*
 	 *	Configure the address for reception. Now it is valid.
@@ -3222,14 +3343,11 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 	 */
 
 	read_lock_bh(&ifp->idev->lock);
-	spin_lock(&ifp->lock);
-	send_mld = ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL &&
-		   ifp->idev->valid_ll_addr_cnt == 1;
+	send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp);
 	send_rs = send_mld &&
 		  ipv6_accept_ra(ifp->idev) &&
 		  ifp->idev->cnf.rtr_solicits > 0 &&
 		  (dev->flags&IFF_LOOPBACK) == 0;
-	spin_unlock(&ifp->lock);
 	read_unlock_bh(&ifp->idev->lock);
 
 	/* While dad is in progress mld report's source address is in6_addrany.
@@ -3367,12 +3485,12 @@ static void if6_seq_stop(struct seq_file *seq, void *v)
 static int if6_seq_show(struct seq_file *seq, void *v)
 {
 	struct inet6_ifaddr *ifp = (struct inet6_ifaddr *)v;
-	seq_printf(seq, "%pi6 %02x %02x %02x %03x %8s\n",
+	seq_printf(seq, "%pi6 %02x %02x %02x %02x %8s\n",
 		   &ifp->addr,
 		   ifp->idev->dev->ifindex,
 		   ifp->prefix_len,
 		   ifp->scope,
-		   ifp->flags,
+		   (u8) ifp->flags,
 		   ifp->idev->dev->name);
 	return 0;
 }
@@ -3453,26 +3571,31 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
  *	Periodic address status verification
  */
 
-static void addrconf_verify(unsigned long foo)
+static void addrconf_verify_rtnl(void)
 {
 	unsigned long now, next, next_sec, next_sched;
 	struct inet6_ifaddr *ifp;
 	int i;
 
+	ASSERT_RTNL();
+
 	rcu_read_lock_bh();
-	spin_lock(&addrconf_verify_lock);
 	now = jiffies;
 	next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
 
-	del_timer(&addr_chk_timer);
+	cancel_delayed_work(&addr_chk_work);
 
 	for (i = 0; i < IN6_ADDR_HSIZE; i++) {
 restart:
-		hlist_for_each_entry_rcu_bh(ifp,
-					 &inet6_addr_lst[i], addr_lst) {
+		hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) {
 			unsigned long age;
 
-			if (ifp->flags & IFA_F_PERMANENT)
+			/* When setting preferred_lft to a value not zero or
+			 * infinity, while valid_lft is infinity
+			 * IFA_F_PERMANENT has a non-infinity life time.
+			 */
+			if ((ifp->flags & IFA_F_PERMANENT) &&
+			    (ifp->prefered_lft == INFINITY_LIFE_TIME))
 				continue;
 
 			spin_lock(&ifp->lock);
@@ -3497,7 +3620,8 @@ restart:
 					ifp->flags |= IFA_F_DEPRECATED;
 				}
 
-				if (time_before(ifp->tstamp + ifp->valid_lft * HZ, next))
+				if ((ifp->valid_lft != INFINITY_LIFE_TIME) &&
+				    (time_before(ifp->tstamp + ifp->valid_lft * HZ, next)))
 					next = ifp->tstamp + ifp->valid_lft * HZ;
 
 				spin_unlock(&ifp->lock);
@@ -3558,13 +3682,22 @@ restart:
 
 	ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n",
 	      now, next, next_sec, next_sched);
-
-	addr_chk_timer.expires = next_sched;
-	add_timer(&addr_chk_timer);
-	spin_unlock(&addrconf_verify_lock);
+	mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now);
 	rcu_read_unlock_bh();
 }
 
+static void addrconf_verify_work(struct work_struct *w)
+{
+	rtnl_lock();
+	addrconf_verify_rtnl();
+	rtnl_unlock();
+}
+
+static void addrconf_verify(void)
+{
+	mod_delayed_work(addrconf_wq, &addr_chk_work, 0);
+}
+
 static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local,
 				     struct in6_addr **peer_pfx)
 {
@@ -3598,6 +3731,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct ifaddrmsg *ifm;
 	struct nlattr *tb[IFA_MAX+1];
 	struct in6_addr *pfx, *peer_pfx;
+	u32 ifa_flags;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
@@ -3609,7 +3743,13 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (pfx == NULL)
 		return -EINVAL;
 
-	return inet6_addr_del(net, ifm->ifa_index, pfx, ifm->ifa_prefixlen);
+	ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags;
+
+	/* We ignore other flags so far. */
+	ifa_flags &= IFA_F_MANAGETEMPADDR;
+
+	return inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx,
+			      ifm->ifa_prefixlen);
 }
 
 static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
@@ -3619,6 +3759,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 	clock_t expires;
 	unsigned long timeout;
 	bool was_managetempaddr;
+	bool had_prefixroute;
+
+	ASSERT_RTNL();
 
 	if (!valid_lft || (prefered_lft > valid_lft))
 		return -EINVAL;
@@ -3647,8 +3790,11 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 
 	spin_lock_bh(&ifp->lock);
 	was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR;
+	had_prefixroute = ifp->flags & IFA_F_PERMANENT &&
+			  !(ifp->flags & IFA_F_NOPREFIXROUTE);
 	ifp->flags &= ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD |
-			IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR);
+			IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR |
+			IFA_F_NOPREFIXROUTE);
 	ifp->flags |= ifa_flags;
 	ifp->tstamp = jiffies;
 	ifp->valid_lft = valid_lft;
@@ -3658,8 +3804,22 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 	if (!(ifp->flags&IFA_F_TENTATIVE))
 		ipv6_ifa_notify(0, ifp);
 
-	addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev,
-			      expires, flags);
+	if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
+		addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev,
+				      expires, flags);
+	} else if (had_prefixroute) {
+		enum cleanup_prefix_rt_t action;
+		unsigned long rt_expires;
+
+		write_lock_bh(&ifp->idev->lock);
+		action = check_cleanup_prefix_route(ifp, &rt_expires);
+		write_unlock_bh(&ifp->idev->lock);
+
+		if (action != CLEANUP_PREFIX_RT_NOP) {
+			cleanup_prefix_route(ifp, rt_expires,
+				action == CLEANUP_PREFIX_RT_DEL);
+		}
+	}
 
 	if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) {
 		if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR))
@@ -3668,7 +3828,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 				 !was_managetempaddr, jiffies);
 	}
 
-	addrconf_verify(0);
+	addrconf_verify_rtnl();
 
 	return 0;
 }
@@ -3713,13 +3873,14 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags;
 
 	/* We ignore other flags so far. */
-	ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR;
+	ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR |
+		     IFA_F_NOPREFIXROUTE;
 
 	ifa = ipv6_get_ifaddr(net, pfx, dev, 1);
 	if (ifa == NULL) {
 		/*
 		 * It would be best to check for !NLM_F_CREATE here but
-		 * userspace alreay relies on not having to provide this.
+		 * userspace already relies on not having to provide this.
 		 */
 		return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx,
 				      ifm->ifa_prefixlen, ifa_flags,
@@ -3797,7 +3958,8 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 	put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope),
 		      ifa->idev->dev->ifindex);
 
-	if (!(ifa->flags&IFA_F_PERMANENT)) {
+	if (!((ifa->flags&IFA_F_PERMANENT) &&
+	      (ifa->prefered_lft == INFINITY_LIFE_TIME))) {
 		preferred = ifa->prefered_lft;
 		valid = ifa->valid_lft;
 		if (preferred != INFINITY_LIFE_TIME) {
@@ -4196,7 +4358,7 @@ static inline void __snmp6_fill_statsdev(u64 *stats, atomic_long_t *mib,
 	memset(&stats[items], 0, pad);
 }
 
-static inline void __snmp6_fill_stats64(u64 *stats, void __percpu **mib,
+static inline void __snmp6_fill_stats64(u64 *stats, void __percpu *mib,
 				      int items, int bytes, size_t syncpoff)
 {
 	int i;
@@ -4216,7 +4378,7 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
 {
 	switch (attrtype) {
 	case IFLA_INET6_STATS:
-		__snmp6_fill_stats64(stats, (void __percpu **)idev->stats.ipv6,
+		__snmp6_fill_stats64(stats, idev->stats.ipv6,
 				     IPSTATS_MIB_MAX, bytes, offsetof(struct ipstats_mib, syncp));
 		break;
 	case IFLA_INET6_ICMP6STATS:
@@ -4296,6 +4458,8 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 	bool update_rs = false;
 	struct in6_addr ll_addr;
 
+	ASSERT_RTNL();
+
 	if (token == NULL)
 		return -EINVAL;
 	if (ipv6_addr_any(token))
@@ -4344,7 +4508,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 	}
 
 	write_unlock_bh(&idev->lock);
-	addrconf_verify(0);
+	addrconf_verify_rtnl();
 	return 0;
 }
 
@@ -4542,29 +4706,17 @@ errout:
 		rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
 }
 
-static void update_valid_ll_addr_cnt(struct inet6_ifaddr *ifp, int count)
-{
-	write_lock_bh(&ifp->idev->lock);
-	spin_lock(&ifp->lock);
-	if (((ifp->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|
-			    IFA_F_DADFAILED)) == IFA_F_PERMANENT) &&
-	    (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL))
-		ifp->idev->valid_ll_addr_cnt += count;
-	WARN_ON(ifp->idev->valid_ll_addr_cnt < 0);
-	spin_unlock(&ifp->lock);
-	write_unlock_bh(&ifp->idev->lock);
-}
-
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 {
 	struct net *net = dev_net(ifp->idev->dev);
 
+	if (event)
+		ASSERT_RTNL();
+
 	inet6_ifa_notify(event ? : RTM_NEWADDR, ifp);
 
 	switch (event) {
 	case RTM_NEWADDR:
-		update_valid_ll_addr_cnt(ifp, 1);
-
 		/*
 		 * If the address was optimistic
 		 * we inserted the route at the start of
@@ -4580,8 +4732,6 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 					      ifp->idev->dev, 0, 0);
 		break;
 	case RTM_DELADDR:
-		update_valid_ll_addr_cnt(ifp, -1);
-
 		if (ifp->idev->cnf.forwarding)
 			addrconf_leave_anycast(ifp);
 		addrconf_leave_solict(ifp->idev, &ifp->addr);
@@ -4728,6 +4878,46 @@ int addrconf_sysctl_disable(struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static
+int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write,
+			      void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int *valp = ctl->data;
+	int ret;
+	int old, new;
+
+	old = *valp;
+	ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+	new = *valp;
+
+	if (write && old != new) {
+		struct net *net = ctl->extra2;
+
+		if (!rtnl_trylock())
+			return restart_syscall();
+
+		if (valp == &net->ipv6.devconf_dflt->proxy_ndp)
+			inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+						     NETCONFA_IFINDEX_DEFAULT,
+						     net->ipv6.devconf_dflt);
+		else if (valp == &net->ipv6.devconf_all->proxy_ndp)
+			inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+						     NETCONFA_IFINDEX_ALL,
+						     net->ipv6.devconf_all);
+		else {
+			struct inet6_dev *idev = ctl->extra1;
+
+			inet6_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
+						     idev->dev->ifindex,
+						     &idev->cnf);
+		}
+		rtnl_unlock();
+	}
+
+	return ret;
+}
+
+
 static struct addrconf_sysctl_table
 {
 	struct ctl_table_header *sysctl_header;
@@ -4914,7 +5104,7 @@ static struct addrconf_sysctl_table
 			.data		= &ipv6_devconf.proxy_ndp,
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
-			.proc_handler	= proc_dointvec,
+			.proc_handler	= addrconf_sysctl_proxy_ndp,
 		},
 		{
 			.procname	= "accept_source_route",
@@ -5131,6 +5321,12 @@ int __init addrconf_init(void)
 	if (err < 0)
 		goto out_addrlabel;
 
+	addrconf_wq = create_workqueue("ipv6_addrconf");
+	if (!addrconf_wq) {
+		err = -ENOMEM;
+		goto out_nowq;
+	}
+
 	/* The addrconf netdev notifier requires that loopback_dev
 	 * has it's ipv6 private information allocated and setup
 	 * before it can bring up and give link-local addresses
@@ -5161,11 +5357,9 @@ int __init addrconf_init(void)
 
 	register_netdevice_notifier(&ipv6_dev_notf);
 
-	addrconf_verify(0);
+	addrconf_verify();
 
-	err = rtnl_af_register(&inet6_ops);
-	if (err < 0)
-		goto errout_af;
+	rtnl_af_register(&inet6_ops);
 
 	err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo,
 			      NULL);
@@ -5189,9 +5383,10 @@ int __init addrconf_init(void)
 	return 0;
 errout:
 	rtnl_af_unregister(&inet6_ops);
-errout_af:
 	unregister_netdevice_notifier(&ipv6_dev_notf);
 errlo:
+	destroy_workqueue(addrconf_wq);
+out_nowq:
 	unregister_pernet_subsys(&addrconf_ops);
 out_addrlabel:
 	ipv6_addr_label_cleanup();
@@ -5227,7 +5422,8 @@ void addrconf_cleanup(void)
 	for (i = 0; i < IN6_ADDR_HSIZE; i++)
 		WARN_ON(!hlist_empty(&inet6_addr_lst[i]));
 	spin_unlock_bh(&addrconf_hash_lock);
-
-	del_timer(&addr_chk_timer);
+	cancel_delayed_work(&addr_chk_work);
 	rtnl_unlock();
+
+	destroy_workqueue(addrconf_wq);
 }
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 4c11cbcf830..e6960457f62 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -123,7 +123,7 @@ static void snmp6_free_dev(struct inet6_dev *idev)
 {
 	kfree(idev->stats.icmpv6msgdev);
 	kfree(idev->stats.icmpv6dev);
-	snmp_mib_free((void __percpu **)idev->stats.ipv6);
+	free_percpu(idev->stats.ipv6);
 }
 
 /* Nobody refers to this device, we may destroy it. */
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index b30ad3741b4..731e1e1722d 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -6,7 +6,7 @@
  */
 /*
  * Author:
- * 	YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org>
+ *	YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org>
  */
 
 #include <linux/kernel.h>
@@ -22,14 +22,13 @@
 #if 0
 #define ADDRLABEL(x...) printk(x)
 #else
-#define ADDRLABEL(x...) do { ; } while(0)
+#define ADDRLABEL(x...) do { ; } while (0)
 #endif
 
 /*
  * Policy Table
  */
-struct ip6addrlbl_entry
-{
+struct ip6addrlbl_entry {
 #ifdef CONFIG_NET_NS
 	struct net *lbl_net;
 #endif
@@ -88,39 +87,39 @@ static const __net_initconst struct ip6addrlbl_init_table
 	{	/* ::/0 */
 		.prefix = &in6addr_any,
 		.label = 1,
-	},{	/* fc00::/7 */
-		.prefix = &(struct in6_addr){{{ 0xfc }}},
+	}, {	/* fc00::/7 */
+		.prefix = &(struct in6_addr){ { { 0xfc } } } ,
 		.prefixlen = 7,
 		.label = 5,
-	},{	/* fec0::/10 */
-		.prefix = &(struct in6_addr){{{ 0xfe, 0xc0 }}},
+	}, {	/* fec0::/10 */
+		.prefix = &(struct in6_addr){ { { 0xfe, 0xc0 } } },
 		.prefixlen = 10,
 		.label = 11,
-	},{	/* 2002::/16 */
-		.prefix = &(struct in6_addr){{{ 0x20, 0x02 }}},
+	}, {	/* 2002::/16 */
+		.prefix = &(struct in6_addr){ { { 0x20, 0x02 } } },
 		.prefixlen = 16,
 		.label = 2,
-	},{	/* 3ffe::/16 */
-		.prefix = &(struct in6_addr){{{ 0x3f, 0xfe }}},
+	}, {	/* 3ffe::/16 */
+		.prefix = &(struct in6_addr){ { { 0x3f, 0xfe } } },
 		.prefixlen = 16,
 		.label = 12,
-	},{	/* 2001::/32 */
-		.prefix = &(struct in6_addr){{{ 0x20, 0x01 }}},
+	}, {	/* 2001::/32 */
+		.prefix = &(struct in6_addr){ { { 0x20, 0x01 } } },
 		.prefixlen = 32,
 		.label = 6,
-	},{	/* 2001:10::/28 */
-		.prefix = &(struct in6_addr){{{ 0x20, 0x01, 0x00, 0x10 }}},
+	}, {	/* 2001:10::/28 */
+		.prefix = &(struct in6_addr){ { { 0x20, 0x01, 0x00, 0x10 } } },
 		.prefixlen = 28,
 		.label = 7,
-	},{	/* ::ffff:0:0 */
-		.prefix = &(struct in6_addr){{{ [10] = 0xff, [11] = 0xff }}},
+	}, {	/* ::ffff:0:0 */
+		.prefix = &(struct in6_addr){ { { [10] = 0xff, [11] = 0xff } } },
 		.prefixlen = 96,
 		.label = 4,
-	},{	/* ::/96 */
+	}, {	/* ::/96 */
 		.prefix = &in6addr_any,
 		.prefixlen = 96,
 		.label = 3,
-	},{	/* ::1/128 */
+	}, {	/* ::1/128 */
 		.prefix = &in6addr_loopback,
 		.prefixlen = 128,
 		.label = 0,
@@ -441,7 +440,7 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (label == IPV6_ADDR_LABEL_DEFAULT)
 		return -EINVAL;
 
-	switch(nlh->nlmsg_type) {
+	switch (nlh->nlmsg_type) {
 	case RTM_NEWADDRLABEL:
 		if (ifal->ifal_index &&
 		    !__dev_get_by_index(net, ifal->ifal_index))
@@ -505,12 +504,13 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) {
 		if (idx >= s_idx &&
 		    net_eq(ip6addrlbl_net(p), net)) {
-			if ((err = ip6addrlbl_fill(skb, p,
-						   ip6addrlbl_table.seq,
-						   NETLINK_CB(cb->skb).portid,
-						   cb->nlh->nlmsg_seq,
-						   RTM_NEWADDRLABEL,
-						   NLM_F_MULTI)) <= 0)
+			err = ip6addrlbl_fill(skb, p,
+					      ip6addrlbl_table.seq,
+					      NETLINK_CB(cb->skb).portid,
+					      cb->nlh->nlmsg_seq,
+					      RTM_NEWADDRLABEL,
+					      NLM_F_MULTI);
+			if (err <= 0)
 				break;
 		}
 		idx++;
@@ -527,7 +527,7 @@ static inline int ip6addrlbl_msgsize(void)
 		+ nla_total_size(4);	/* IFAL_LABEL */
 }
 
-static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh)
+static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct ifaddrlblmsg *ifal;
@@ -568,7 +568,8 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh)
 		goto out;
 	}
 
-	if (!(skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL))) {
+	skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL);
+	if (!skb) {
 		ip6addrlbl_put(p);
 		return -ENOBUFS;
 	}
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 4fbdb7046d2..7cb4392690d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -106,7 +106,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
 	struct inet_protosw *answer;
 	struct proto *answer_prot;
 	unsigned char answer_flags;
-	char answer_no_check;
 	int try_loading_module = 0;
 	int err;
 
@@ -162,7 +161,6 @@ lookup_protocol:
 
 	sock->ops = answer->ops;
 	answer_prot = answer->prot;
-	answer_no_check = answer->no_check;
 	answer_flags = answer->flags;
 	rcu_read_unlock();
 
@@ -176,7 +174,6 @@ lookup_protocol:
 	sock_init_data(sock, sk);
 
 	err = 0;
-	sk->sk_no_check = answer_no_check;
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = SK_CAN_REUSE;
 
@@ -213,7 +210,7 @@ lookup_protocol:
 	inet->mc_list	= NULL;
 	inet->rcv_tos	= 0;
 
-	if (ipv4_config.no_pmtu_disc)
+	if (net->ipv4.sysctl_ip_no_pmtu_disc)
 		inet->pmtudisc = IP_PMTUDISC_DONT;
 	else
 		inet->pmtudisc = IP_PMTUDISC_WANT;
@@ -661,7 +658,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 
 		final_p = fl6_update_dst(&fl6, np->opt, &final);
 
-		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
+		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 		if (IS_ERR(dst)) {
 			sk->sk_route_caps = 0;
 			sk->sk_err_soft = -PTR_ERR(dst);
@@ -683,8 +680,7 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb)
 	if (np->rxopt.all) {
 		if ((opt->hop && (np->rxopt.bits.hopopts ||
 				  np->rxopt.bits.ohopopts)) ||
-		    ((IPV6_FLOWINFO_MASK &
-		      *(__be32 *)skb_network_header(skb)) &&
+		    (ip6_flowinfo((struct ipv6hdr *) skb_network_header(skb)) &&
 		     np->rxopt.bits.rxflow) ||
 		    (opt->srcrt && (np->rxopt.bits.srcrt ||
 		     np->rxopt.bits.osrcrt)) ||
@@ -716,33 +712,25 @@ static int __net_init ipv6_init_mibs(struct net *net)
 {
 	int i;
 
-	if (snmp_mib_init((void __percpu **)net->mib.udp_stats_in6,
-			  sizeof(struct udp_mib),
-			  __alignof__(struct udp_mib)) < 0)
+	net->mib.udp_stats_in6 = alloc_percpu(struct udp_mib);
+	if (!net->mib.udp_stats_in6)
 		return -ENOMEM;
-	if (snmp_mib_init((void __percpu **)net->mib.udplite_stats_in6,
-			  sizeof(struct udp_mib),
-			  __alignof__(struct udp_mib)) < 0)
+	net->mib.udplite_stats_in6 = alloc_percpu(struct udp_mib);
+	if (!net->mib.udplite_stats_in6)
 		goto err_udplite_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.ipv6_statistics,
-			  sizeof(struct ipstats_mib),
-			  __alignof__(struct ipstats_mib)) < 0)
+	net->mib.ipv6_statistics = alloc_percpu(struct ipstats_mib);
+	if (!net->mib.ipv6_statistics)
 		goto err_ip_mib;
 
 	for_each_possible_cpu(i) {
 		struct ipstats_mib *af_inet6_stats;
-		af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics[0], i);
+		af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics, i);
 		u64_stats_init(&af_inet6_stats->syncp);
-#if SNMP_ARRAY_SZ == 2
-		af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics[1], i);
-		u64_stats_init(&af_inet6_stats->syncp);
-#endif
 	}
 
 
-	if (snmp_mib_init((void __percpu **)net->mib.icmpv6_statistics,
-			  sizeof(struct icmpv6_mib),
-			  __alignof__(struct icmpv6_mib)) < 0)
+	net->mib.icmpv6_statistics = alloc_percpu(struct icmpv6_mib);
+	if (!net->mib.icmpv6_statistics)
 		goto err_icmp_mib;
 	net->mib.icmpv6msg_statistics = kzalloc(sizeof(struct icmpv6msg_mib),
 						GFP_KERNEL);
@@ -751,22 +739,22 @@ static int __net_init ipv6_init_mibs(struct net *net)
 	return 0;
 
 err_icmpmsg_mib:
-	snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics);
+	free_percpu(net->mib.icmpv6_statistics);
 err_icmp_mib:
-	snmp_mib_free((void __percpu **)net->mib.ipv6_statistics);
+	free_percpu(net->mib.ipv6_statistics);
 err_ip_mib:
-	snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6);
+	free_percpu(net->mib.udplite_stats_in6);
 err_udplite_mib:
-	snmp_mib_free((void __percpu **)net->mib.udp_stats_in6);
+	free_percpu(net->mib.udp_stats_in6);
 	return -ENOMEM;
 }
 
 static void ipv6_cleanup_mibs(struct net *net)
 {
-	snmp_mib_free((void __percpu **)net->mib.udp_stats_in6);
-	snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6);
-	snmp_mib_free((void __percpu **)net->mib.ipv6_statistics);
-	snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics);
+	free_percpu(net->mib.udp_stats_in6);
+	free_percpu(net->mib.udplite_stats_in6);
+	free_percpu(net->mib.ipv6_statistics);
+	free_percpu(net->mib.icmpv6_statistics);
 	kfree(net->mib.icmpv6msg_statistics);
 }
 
@@ -776,6 +764,7 @@ static int __net_init inet6_net_init(struct net *net)
 
 	net->ipv6.sysctl.bindv6only = 0;
 	net->ipv6.sysctl.icmpv6_time = 1*HZ;
+	net->ipv6.sysctl.flowlabel_consistency = 1;
 	atomic_set(&net->ipv6.rt_genid, 0);
 
 	err = ipv6_init_mibs(net);
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 81e496a2e00..72a4930bdc0 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -346,6 +346,10 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
 	struct ip_auth_hdr *ah;
 	struct ah_data *ahp;
 	struct tmp_ext *iph_ext;
+	int seqhi_len = 0;
+	__be32 *seqhi;
+	int sglists = 0;
+	struct scatterlist *seqhisg;
 
 	ahp = x->data;
 	ahash = ahp->ahash;
@@ -359,15 +363,22 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
 	if (extlen)
 		extlen += sizeof(*iph_ext);
 
+	if (x->props.flags & XFRM_STATE_ESN) {
+		sglists = 1;
+		seqhi_len = sizeof(*seqhi);
+	}
 	err = -ENOMEM;
-	iph_base = ah_alloc_tmp(ahash, nfrags, IPV6HDR_BASELEN + extlen);
+	iph_base = ah_alloc_tmp(ahash, nfrags + sglists, IPV6HDR_BASELEN +
+				extlen + seqhi_len);
 	if (!iph_base)
 		goto out;
 
 	iph_ext = ah_tmp_ext(iph_base);
-	icv = ah_tmp_icv(ahash, iph_ext, extlen);
+	seqhi = (__be32 *)((char *)iph_ext + extlen);
+	icv = ah_tmp_icv(ahash, seqhi, seqhi_len);
 	req = ah_tmp_req(ahash, icv);
 	sg = ah_req_sg(ahash, req);
+	seqhisg = sg + nfrags;
 
 	ah = ip_auth_hdr(skb);
 	memset(ah->auth_data, 0, ahp->icv_trunc_len);
@@ -411,10 +422,15 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
 	ah->spi = x->id.spi;
 	ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 
-	sg_init_table(sg, nfrags);
-	skb_to_sgvec(skb, sg, 0, skb->len);
+	sg_init_table(sg, nfrags + sglists);
+	skb_to_sgvec_nomark(skb, sg, 0, skb->len);
 
-	ahash_request_set_crypt(req, sg, icv, skb->len);
+	if (x->props.flags & XFRM_STATE_ESN) {
+		/* Attach seqhi sg right after packet payload */
+		*seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+		sg_set_buf(seqhisg, seqhi, seqhi_len);
+	}
+	ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
 	ahash_request_set_callback(req, 0, ah6_output_done, skb);
 
 	AH_SKB_CB(skb)->tmp = iph_base;
@@ -514,6 +530,10 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
 	int nexthdr;
 	int nfrags;
 	int err = -ENOMEM;
+	int seqhi_len = 0;
+	__be32 *seqhi;
+	int sglists = 0;
+	struct scatterlist *seqhisg;
 
 	if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr)))
 		goto out;
@@ -550,14 +570,22 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
 
 	skb_push(skb, hdr_len);
 
-	work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len);
+	if (x->props.flags & XFRM_STATE_ESN) {
+		sglists = 1;
+		seqhi_len = sizeof(*seqhi);
+	}
+
+	work_iph = ah_alloc_tmp(ahash, nfrags + sglists, hdr_len +
+				ahp->icv_trunc_len + seqhi_len);
 	if (!work_iph)
 		goto out;
 
-	auth_data = ah_tmp_auth(work_iph, hdr_len);
-	icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len);
+	auth_data = ah_tmp_auth((u8 *)work_iph, hdr_len);
+	seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len);
+	icv = ah_tmp_icv(ahash, seqhi, seqhi_len);
 	req = ah_tmp_req(ahash, icv);
 	sg = ah_req_sg(ahash, req);
+	seqhisg = sg + nfrags;
 
 	memcpy(work_iph, ip6h, hdr_len);
 	memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
@@ -572,10 +600,16 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
 	ip6h->flow_lbl[2] = 0;
 	ip6h->hop_limit   = 0;
 
-	sg_init_table(sg, nfrags);
-	skb_to_sgvec(skb, sg, 0, skb->len);
+	sg_init_table(sg, nfrags + sglists);
+	skb_to_sgvec_nomark(skb, sg, 0, skb->len);
+
+	if (x->props.flags & XFRM_STATE_ESN) {
+		/* Attach seqhi sg right after packet payload */
+		*seqhi = XFRM_SKB_CB(skb)->seq.input.hi;
+		sg_set_buf(seqhisg, seqhi, seqhi_len);
+	}
 
-	ahash_request_set_crypt(req, sg, icv, skb->len);
+	ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
 	ahash_request_set_callback(req, 0, ah6_input_done, skb);
 
 	AH_SKB_CB(skb)->tmp = work_iph;
@@ -609,8 +643,8 @@ out:
 	return err;
 }
 
-static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
-		    u8 type, u8 code, int offset, __be32 info)
+static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		   u8 type, u8 code, int offset, __be32 info)
 {
 	struct net *net = dev_net(skb->dev);
 	struct ipv6hdr *iph = (struct ipv6hdr*)skb->data;
@@ -619,17 +653,19 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	if (type != ICMPV6_PKT_TOOBIG &&
 	    type != NDISC_REDIRECT)
-		return;
+		return 0;
 
 	x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6);
 	if (!x)
-		return;
+		return 0;
 
 	if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 	else
 		ip6_update_pmtu(skb, net, info, 0, 0);
 	xfrm_state_put(x);
+
+	return 0;
 }
 
 static int ah6_init_state(struct xfrm_state *x)
@@ -714,6 +750,11 @@ static void ah6_destroy(struct xfrm_state *x)
 	kfree(ahp);
 }
 
+static int ah6_rcv_cb(struct sk_buff *skb, int err)
+{
+	return 0;
+}
+
 static const struct xfrm_type ah6_type =
 {
 	.description	= "AH6",
@@ -727,10 +768,11 @@ static const struct xfrm_type ah6_type =
 	.hdr_offset	= xfrm6_find_1stfragopt,
 };
 
-static const struct inet6_protocol ah6_protocol = {
+static struct xfrm6_protocol ah6_protocol = {
 	.handler	=	xfrm6_rcv,
+	.cb_handler	=	ah6_rcv_cb,
 	.err_handler	=	ah6_err,
-	.flags		=	INET6_PROTO_NOPOLICY,
+	.priority	=	0,
 };
 
 static int __init ah6_init(void)
@@ -740,7 +782,7 @@ static int __init ah6_init(void)
 		return -EAGAIN;
 	}
 
-	if (inet6_add_protocol(&ah6_protocol, IPPROTO_AH) < 0) {
+	if (xfrm6_protocol_register(&ah6_protocol, IPPROTO_AH) < 0) {
 		pr_info("%s: can't add protocol\n", __func__);
 		xfrm_unregister_type(&ah6_type, AF_INET6);
 		return -EAGAIN;
@@ -751,7 +793,7 @@ static int __init ah6_init(void)
 
 static void __exit ah6_fini(void)
 {
-	if (inet6_del_protocol(&ah6_protocol, IPPROTO_AH) < 0)
+	if (xfrm6_protocol_deregister(&ah6_protocol, IPPROTO_AH) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
 
 	if (xfrm_unregister_type(&ah6_type, AF_INET6) < 0)
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 5a80f15a9de..21018324468 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -383,6 +383,17 @@ bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
 	return found;
 }
 
+/*	check if this anycast address is link-local on given interface or
+ *	is global
+ */
+bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev,
+			     const struct in6_addr *addr)
+{
+	return ipv6_chk_acast_addr(net,
+				   (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL ?
+				    dev : NULL),
+				   addr);
+}
 
 #ifdef CONFIG_PROC_FS
 struct ac6_iter_state {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 8dfe1f4d3c1..c3bf2d2e519 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -73,7 +73,6 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
-			usin->sin6_addr = flowlabel->dst;
 		}
 	}
 
@@ -171,7 +170,7 @@ ipv4_connected:
 	opt = flowlabel ? flowlabel->opt : np->opt;
 	final_p = fl6_update_dst(&fl6, opt, &final);
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	err = 0;
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
@@ -206,6 +205,16 @@ out:
 }
 EXPORT_SYMBOL_GPL(ip6_datagram_connect);
 
+int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr,
+				 int addr_len)
+{
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, uaddr);
+	if (sin6->sin6_family != AF_INET6)
+		return -EAFNOSUPPORT;
+	return ip6_datagram_connect(sk, uaddr, addr_len);
+}
+EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only);
+
 void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
 		     __be16 port, u32 info, u8 *payload)
 {
@@ -323,7 +332,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sock_exterr_skb *serr;
 	struct sk_buff *skb, *skb2;
-	struct sockaddr_in6 *sin;
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name);
 	struct {
 		struct sock_extended_err ee;
 		struct sockaddr_in6	 offender;
@@ -349,7 +358,6 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	sin = (struct sockaddr_in6 *)msg->msg_name;
 	if (sin) {
 		const unsigned char *nh = skb_network_header(skb);
 		sin->sin6_family = AF_INET6;
@@ -379,10 +387,12 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
 		sin->sin6_port = 0;
+		if (np->rxopt.all)
+			ip6_datagram_recv_common_ctl(sk, msg, skb);
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			sin->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (np->rxopt.all)
-				ip6_datagram_recv_ctl(sk, msg, skb);
+				ip6_datagram_recv_specific_ctl(sk, msg, skb);
 			sin->sin6_scope_id =
 				ipv6_iface_scope_id(&sin->sin6_addr,
 						    IP6CB(skb)->iif);
@@ -430,8 +440,8 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sk_buff *skb;
-	struct sockaddr_in6 *sin;
 	struct ip6_mtuinfo mtu_info;
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name);
 	int err;
 	int copied;
 
@@ -453,7 +463,6 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
 
 	memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info));
 
-	sin = (struct sockaddr_in6 *)msg->msg_name;
 	if (sin) {
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
@@ -474,20 +483,34 @@ out:
 }
 
 
-int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
-			  struct sk_buff *skb)
+void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg,
+				 struct sk_buff *skb)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct inet6_skb_parm *opt = IP6CB(skb);
-	unsigned char *nh = skb_network_header(skb);
+	bool is_ipv6 = skb->protocol == htons(ETH_P_IPV6);
 
 	if (np->rxopt.bits.rxinfo) {
 		struct in6_pktinfo src_info;
 
-		src_info.ipi6_ifindex = opt->iif;
-		src_info.ipi6_addr = ipv6_hdr(skb)->daddr;
+		if (is_ipv6) {
+			src_info.ipi6_ifindex = IP6CB(skb)->iif;
+			src_info.ipi6_addr = ipv6_hdr(skb)->daddr;
+		} else {
+			src_info.ipi6_ifindex =
+				PKTINFO_SKB_CB(skb)->ipi_ifindex;
+			ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr,
+					       &src_info.ipi6_addr);
+		}
 		put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
 	}
+}
+
+void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
+				    struct sk_buff *skb)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct inet6_skb_parm *opt = IP6CB(skb);
+	unsigned char *nh = skb_network_header(skb);
 
 	if (np->rxopt.bits.rxhlim) {
 		int hlim = ipv6_hdr(skb)->hop_limit;
@@ -605,7 +628,13 @@ int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
 			put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6);
 		}
 	}
-	return 0;
+}
+
+void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
+			  struct sk_buff *skb)
+{
+	ip6_datagram_recv_common_ctl(sk, msg, skb);
+	ip6_datagram_recv_specific_ctl(sk, msg, skb);
 }
 EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl);
 
@@ -670,7 +699,9 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 				int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL;
 				if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) &&
 				    !ipv6_chk_addr(net, &src_info->ipi6_addr,
-						   strict ? dev : NULL, 0))
+						   strict ? dev : NULL, 0) &&
+				    !ipv6_chk_acast_addr_src(net, dev,
+							     &src_info->ipi6_addr))
 					err = -EINVAL;
 				else
 					fl6->saddr = src_info->ipi6_addr;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 6eef8a7e35f..d15da137714 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -421,8 +421,8 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu)
 		 net_adj) & ~(blksize - 1)) + net_adj - 2;
 }
 
-static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
-		     u8 type, u8 code, int offset, __be32 info)
+static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		    u8 type, u8 code, int offset, __be32 info)
 {
 	struct net *net = dev_net(skb->dev);
 	const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
@@ -431,18 +431,20 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	if (type != ICMPV6_PKT_TOOBIG &&
 	    type != NDISC_REDIRECT)
-		return;
+		return 0;
 
 	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
 			      esph->spi, IPPROTO_ESP, AF_INET6);
 	if (!x)
-		return;
+		return 0;
 
 	if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 	else
 		ip6_update_pmtu(skb, net, info, 0, 0);
 	xfrm_state_put(x);
+
+	return 0;
 }
 
 static void esp6_destroy(struct xfrm_state *x)
@@ -614,6 +616,11 @@ error:
 	return err;
 }
 
+static int esp6_rcv_cb(struct sk_buff *skb, int err)
+{
+	return 0;
+}
+
 static const struct xfrm_type esp6_type =
 {
 	.description	= "ESP6",
@@ -628,10 +635,11 @@ static const struct xfrm_type esp6_type =
 	.hdr_offset	= xfrm6_find_1stfragopt,
 };
 
-static const struct inet6_protocol esp6_protocol = {
-	.handler 	=	xfrm6_rcv,
+static struct xfrm6_protocol esp6_protocol = {
+	.handler	=	xfrm6_rcv,
+	.cb_handler	=	esp6_rcv_cb,
 	.err_handler	=	esp6_err,
-	.flags		=	INET6_PROTO_NOPOLICY,
+	.priority	=	0,
 };
 
 static int __init esp6_init(void)
@@ -640,7 +648,7 @@ static int __init esp6_init(void)
 		pr_info("%s: can't add xfrm type\n", __func__);
 		return -EAGAIN;
 	}
-	if (inet6_add_protocol(&esp6_protocol, IPPROTO_ESP) < 0) {
+	if (xfrm6_protocol_register(&esp6_protocol, IPPROTO_ESP) < 0) {
 		pr_info("%s: can't add protocol\n", __func__);
 		xfrm_unregister_type(&esp6_type, AF_INET6);
 		return -EAGAIN;
@@ -651,7 +659,7 @@ static int __init esp6_init(void)
 
 static void __exit esp6_fini(void)
 {
-	if (inet6_del_protocol(&esp6_protocol, IPPROTO_ESP) < 0)
+	if (xfrm6_protocol_deregister(&esp6_protocol, IPPROTO_ESP) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
 	if (xfrm_unregister_type(&esp6_type, AF_INET6) < 0)
 		pr_info("%s: can't remove xfrm type\n", __func__);
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 140748debc4..8af3eb57f43 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -212,7 +212,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 		found = (nexthdr == target);
 
 		if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
-			if (target < 0)
+			if (target < 0 || found)
 				break;
 			return -ENOENT;
 		}
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index cf77f3abfd0..447a7fbd1bb 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -25,11 +25,11 @@ int __init ipv6_exthdrs_offload_init(void)
 	int ret;
 
 	ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING);
-	if (!ret)
+	if (ret)
 		goto out;
 
 	ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS);
-	if (!ret)
+	if (ret)
 		goto out_rt;
 
 out:
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index e27591635f9..b4d5e1d97c1 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -122,7 +122,11 @@ out:
 static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
 {
 	struct rt6_info *rt = (struct rt6_info *) arg->result;
-	struct net_device *dev = rt->rt6i_idev->dev;
+	struct net_device *dev = NULL;
+
+	if (rt->rt6i_idev)
+		dev = rt->rt6i_idev->dev;
+
 	/* do not accept result if the route does
 	 * not meet the required prefix length
 	 */
@@ -165,7 +169,7 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
 			return 0;
 	}
 
-	if (r->tclass && r->tclass != ((ntohl(fl6->flowlabel) >> 20) & 0xff))
+	if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel))
 		return 0;
 
 	return 1;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index eef8d945b36..f6c84a6eb23 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -67,6 +67,7 @@
 #include <net/icmp.h>
 #include <net/xfrm.h>
 #include <net/inet_common.h>
+#include <net/dsfield.h>
 
 #include <asm/uaccess.h>
 
@@ -315,8 +316,10 @@ static void mip6_addr_swap(struct sk_buff *skb)
 static inline void mip6_addr_swap(struct sk_buff *skb) {}
 #endif
 
-struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
-				      struct sock *sk, struct flowi6 *fl6)
+static struct dst_entry *icmpv6_route_lookup(struct net *net,
+					     struct sk_buff *skb,
+					     struct sock *sk,
+					     struct flowi6 *fl6)
 {
 	struct dst_entry *dst, *dst2;
 	struct flowi6 fl2;
@@ -397,6 +400,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	int len;
 	int hlimit;
 	int err = 0;
+	u32 mark = IP6_REPLY_MARK(net, skb->mark);
 
 	if ((u8 *)hdr < skb->head ||
 	    (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb))
@@ -410,7 +414,8 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	 */
 	addr_type = ipv6_addr_type(&hdr->daddr);
 
-	if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0))
+	if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) ||
+	    ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr))
 		saddr = &hdr->daddr;
 
 	/*
@@ -462,6 +467,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	fl6.daddr = hdr->saddr;
 	if (saddr)
 		fl6.saddr = *saddr;
+	fl6.flowi6_mark = mark;
 	fl6.flowi6_oif = iif;
 	fl6.fl6_icmp_type = type;
 	fl6.fl6_icmp_code = code;
@@ -470,6 +476,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	sk = icmpv6_xmit_lock(net);
 	if (sk == NULL)
 		return;
+	sk->sk_mark = mark;
 	np = inet6_sk(sk);
 
 	if (!icmpv6_xrlim_allow(sk, type, &fl6))
@@ -489,12 +496,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	if (IS_ERR(dst))
 		goto out;
 
-	if (ipv6_addr_is_multicast(&fl6.daddr))
-		hlimit = np->mcast_hops;
-	else
-		hlimit = np->hop_limit;
-	if (hlimit < 0)
-		hlimit = ip6_dst_hoplimit(dst);
+	hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	msg.skb = skb;
 	msg.offset = skb_network_offset(skb);
@@ -516,7 +518,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 			      np->tclass, NULL, &fl6, (struct rt6_info *)dst,
 			      MSG_DONTWAIT, np->dontfrag);
 	if (err) {
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
 		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
@@ -551,10 +553,14 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	struct dst_entry *dst;
 	int err = 0;
 	int hlimit;
+	u8 tclass;
+	u32 mark = IP6_REPLY_MARK(net, skb->mark);
 
 	saddr = &ipv6_hdr(skb)->daddr;
 
-	if (!ipv6_unicast_destination(skb))
+	if (!ipv6_unicast_destination(skb) &&
+	    !(net->ipv6.sysctl.anycast_src_echo_reply &&
+	      ipv6_anycast_destination(skb)))
 		saddr = NULL;
 
 	memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
@@ -567,11 +573,13 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 		fl6.saddr = *saddr;
 	fl6.flowi6_oif = skb->dev->ifindex;
 	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
+	fl6.flowi6_mark = mark;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
 	if (sk == NULL)
 		return;
+	sk->sk_mark = mark;
 	np = inet6_sk(sk);
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
@@ -586,12 +594,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	if (IS_ERR(dst))
 		goto out;
 
-	if (ipv6_addr_is_multicast(&fl6.daddr))
-		hlimit = np->mcast_hops;
-	else
-		hlimit = np->hop_limit;
-	if (hlimit < 0)
-		hlimit = ip6_dst_hoplimit(dst);
+	hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	idev = __in6_dev_get(skb->dev);
 
@@ -599,8 +602,9 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	msg.offset = 0;
 	msg.type = ICMPV6_ECHO_REPLY;
 
+	tclass = ipv6_get_dsfield(ipv6_hdr(skb));
 	err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
-				sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl6,
+				sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl6,
 				(struct rt6_info *)dst, MSG_DONTWAIT,
 				np->dontfrag);
 
@@ -694,22 +698,11 @@ static int icmpv6_rcv(struct sk_buff *skb)
 	saddr = &ipv6_hdr(skb)->saddr;
 	daddr = &ipv6_hdr(skb)->daddr;
 
-	/* Perform checksum. */
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (!csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
-				     skb->csum))
-			break;
-		/* fall through */
-	case CHECKSUM_NONE:
-		skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len,
-					     IPPROTO_ICMPV6, 0));
-		if (__skb_checksum_complete(skb)) {
-			LIMIT_NETDEBUG(KERN_DEBUG
-				       "ICMPv6 checksum failed [%pI6c > %pI6c]\n",
-				       saddr, daddr);
-			goto csum_error;
-		}
+	if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) {
+		LIMIT_NETDEBUG(KERN_DEBUG
+			       "ICMPv6 checksum failed [%pI6c > %pI6c]\n",
+			       saddr, daddr);
+		goto csum_error;
 	}
 
 	if (!pskb_pull(skb, sizeof(*hdr)))
@@ -984,7 +977,7 @@ int icmpv6_err_convert(u8 type, u8 code, int *err)
 EXPORT_SYMBOL(icmpv6_err_convert);
 
 #ifdef CONFIG_SYSCTL
-struct ctl_table ipv6_icmp_table_template[] = {
+static struct ctl_table ipv6_icmp_table_template[] = {
 	{
 		.procname	= "ratelimit",
 		.data		= &init_net.ipv6.sysctl.icmpv6_time,
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 77bb8afb141..a245e5ddffb 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -81,12 +81,12 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	final_p = fl6_update_dst(fl6, np->opt, &final);
 	fl6->saddr = ireq->ir_v6_loc_addr;
 	fl6->flowi6_oif = ireq->ir_iif;
-	fl6->flowi6_mark = sk->sk_mark;
+	fl6->flowi6_mark = ireq->ir_mark;
 	fl6->fl6_dport = ireq->ir_rmt_port;
 	fl6->fl6_sport = htons(ireq->ir_num);
 	security_req_classify_flow(req, flowi6_to_flowi(fl6));
 
-	dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
+	dst = ip6_dst_lookup_flow(sk, fl6, final_p);
 	if (IS_ERR(dst))
 		return NULL;
 
@@ -216,7 +216,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
 	if (!dst) {
-		dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
+		dst = ip6_dst_lookup_flow(sk, fl6, final_p);
 
 		if (!IS_ERR(dst))
 			__inet6_csk_dst_store(sk, dst, NULL, NULL);
@@ -224,9 +224,8 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	return dst;
 }
 
-int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
+int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused)
 {
-	struct sock *sk = skb->sk;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct flowi6 fl6;
 	struct dst_entry *dst;
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index 72d198b8e4d..9a4d7322fb2 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -75,23 +75,50 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
 			return err;
 	}
 
-	if (uh->check == 0) {
-		/* RFC 2460 section 8.1 says that we SHOULD log
-		   this error. Well, it is reasonable.
-		 */
-		LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n");
-		return 1;
-	}
-	if (skb->ip_summed == CHECKSUM_COMPLETE &&
-	    !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
-			     skb->len, proto, skb->csum))
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	/* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels)
+	 * we accept a checksum of zero here. When we find the socket
+	 * for the UDP packet we'll check if that socket allows zero checksum
+	 * for IPv6 (set by socket option).
+	 */
+	return skb_checksum_init_zero_check(skb, proto, uh->check,
+					   ip6_compute_pseudo);
+}
+EXPORT_SYMBOL(udp6_csum_init);
+
+/* Function to set UDP checksum for an IPv6 UDP packet. This is intended
+ * for the simple case like when setting the checksum for a UDP tunnel.
+ */
+void udp6_set_csum(bool nocheck, struct sk_buff *skb,
+		   const struct in6_addr *saddr,
+		   const struct in6_addr *daddr, int len)
+{
+	struct udphdr *uh = udp_hdr(skb);
+
+	if (nocheck)
+		uh->check = 0;
+	else if (skb_is_gso(skb))
+		uh->check = ~udp_v6_check(len, saddr, daddr, 0);
+	else if (skb_dst(skb) && skb_dst(skb)->dev &&
+		 (skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) {
 
-	if (!skb_csum_unnecessary(skb))
-		skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-							 &ipv6_hdr(skb)->daddr,
-							 skb->len, proto, 0));
+		BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL);
 
-	return 0;
+		skb->ip_summed = CHECKSUM_PARTIAL;
+		skb->csum_start = skb_transport_header(skb) - skb->head;
+		skb->csum_offset = offsetof(struct udphdr, check);
+		uh->check = ~udp_v6_check(len, saddr, daddr, 0);
+	} else {
+		__wsum csum;
+
+		BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL);
+
+		uh->check = 0;
+		csum = skb_checksum(skb, 0, len, 0);
+		uh->check = udp_v6_check(len, saddr, daddr, csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
 }
-EXPORT_SYMBOL(udp6_csum_init);
+EXPORT_SYMBOL(udp6_set_csum);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 5550a8113a6..cb4459bd1d2 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -9,14 +9,12 @@
  *      modify it under the terms of the GNU General Public License
  *      as published by the Free Software Foundation; either version
  *      2 of the License, or (at your option) any later version.
- */
-
-/*
- * 	Changes:
- * 	Yuji SEKIYA @USAGI:	Support default route on router node;
- * 				remove ip6_null_entry from the top of
- * 				routing table.
- * 	Ville Nuorvala:		Fixed routing subtrees.
+ *
+ *	Changes:
+ *	Yuji SEKIYA @USAGI:	Support default route on router node;
+ *				remove ip6_null_entry from the top of
+ *				routing table.
+ *	Ville Nuorvala:		Fixed routing subtrees.
  */
 
 #define pr_fmt(fmt) "IPv6: " fmt
@@ -46,10 +44,9 @@
 #define RT6_TRACE(x...) do { ; } while (0)
 #endif
 
-static struct kmem_cache * fib6_node_kmem __read_mostly;
+static struct kmem_cache *fib6_node_kmem __read_mostly;
 
-enum fib_walk_state_t
-{
+enum fib_walk_state_t {
 #ifdef CONFIG_IPV6_SUBTREES
 	FWS_S,
 #endif
@@ -59,8 +56,7 @@ enum fib_walk_state_t
 	FWS_U
 };
 
-struct fib6_cleaner_t
-{
+struct fib6_cleaner_t {
 	struct fib6_walker_t w;
 	struct net *net;
 	int (*func)(struct rt6_info *, void *arg);
@@ -75,8 +71,7 @@ static DEFINE_RWLOCK(fib6_walker_lock);
 #define FWS_INIT FWS_L
 #endif
 
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
-			      struct rt6_info *rt);
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn);
 static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
 static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
 static int fib6_walk(struct fib6_walker_t *w);
@@ -138,7 +133,7 @@ static __inline__ __be32 addr_bit_set(const void *token, int fn_bit)
 	const __be32 *addr = token;
 	/*
 	 * Here,
-	 * 	1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)
+	 *	1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)
 	 * is optimized version of
 	 *	htonl(1 << ((~fn_bit)&0x1F))
 	 * See include/asm-generic/bitops/le.h.
@@ -147,7 +142,7 @@ static __inline__ __be32 addr_bit_set(const void *token, int fn_bit)
 	       addr[fn_bit >> 5];
 }
 
-static __inline__ struct fib6_node * node_alloc(void)
+static __inline__ struct fib6_node *node_alloc(void)
 {
 	struct fib6_node *fn;
 
@@ -156,7 +151,7 @@ static __inline__ struct fib6_node * node_alloc(void)
 	return fn;
 }
 
-static __inline__ void node_free(struct fib6_node * fn)
+static __inline__ void node_free(struct fib6_node *fn)
 {
 	kmem_cache_free(fib6_node_kmem, fn);
 }
@@ -292,7 +287,7 @@ static int fib6_dump_node(struct fib6_walker_t *w)
 
 static void fib6_dump_end(struct netlink_callback *cb)
 {
-	struct fib6_walker_t *w = (void*)cb->args[2];
+	struct fib6_walker_t *w = (void *)cb->args[2];
 
 	if (w) {
 		if (cb->args[4]) {
@@ -302,7 +297,7 @@ static void fib6_dump_end(struct netlink_callback *cb)
 		cb->args[2] = 0;
 		kfree(w);
 	}
-	cb->done = (void*)cb->args[3];
+	cb->done = (void *)cb->args[3];
 	cb->args[1] = 3;
 }
 
@@ -485,7 +480,7 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 		fn->fn_sernum = sernum;
 		dir = addr_bit_set(addr, fn->fn_bit);
 		pn = fn;
-		fn = dir ? fn->right: fn->left;
+		fn = dir ? fn->right : fn->left;
 	} while (fn);
 
 	if (!allow_create) {
@@ -638,12 +633,41 @@ static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt)
 	       RTF_GATEWAY;
 }
 
+static int fib6_commit_metrics(struct dst_entry *dst,
+			       struct nlattr *mx, int mx_len)
+{
+	struct nlattr *nla;
+	int remaining;
+	u32 *mp;
+
+	if (dst->flags & DST_HOST) {
+		mp = dst_metrics_write_ptr(dst);
+	} else {
+		mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+		if (!mp)
+			return -ENOMEM;
+		dst_init_metrics(dst, mp, 0);
+	}
+
+	nla_for_each_attr(nla, mx, mx_len, remaining) {
+		int type = nla_type(nla);
+
+		if (type) {
+			if (type > RTAX_MAX)
+				return -EINVAL;
+
+			mp[type - 1] = nla_get_u32(nla);
+		}
+	}
+	return 0;
+}
+
 /*
  *	Insert routing information in a node.
  */
 
 static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
-			    struct nl_info *info)
+			    struct nl_info *info, struct nlattr *mx, int mx_len)
 {
 	struct rt6_info *iter = NULL;
 	struct rt6_info **ins;
@@ -653,6 +677,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 		   (info->nlh->nlmsg_flags & NLM_F_CREATE));
 	int found = 0;
 	bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
+	int err;
 
 	ins = &fn->leaf;
 
@@ -751,6 +776,11 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			pr_warn("NLM_F_CREATE should be set when creating new route\n");
 
 add:
+		if (mx) {
+			err = fib6_commit_metrics(&rt->dst, mx, mx_len);
+			if (err)
+				return err;
+		}
 		rt->dst.rt6_next = iter;
 		*ins = rt;
 		rt->rt6i_node = fn;
@@ -770,6 +800,11 @@ add:
 			pr_warn("NLM_F_REPLACE set, but no existing node found!\n");
 			return -ENOENT;
 		}
+		if (mx) {
+			err = fib6_commit_metrics(&rt->dst, mx, mx_len);
+			if (err)
+				return err;
+		}
 		*ins = rt;
 		rt->rt6i_node = fn;
 		rt->dst.rt6_next = iter->dst.rt6_next;
@@ -806,7 +841,8 @@ void fib6_force_start_gc(struct net *net)
  *	with source addr info in sub-trees
  */
 
-int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
+int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
+	     struct nlattr *mx, int mx_len)
 {
 	struct fib6_node *fn, *pn = NULL;
 	int err = -ENOMEM;
@@ -900,11 +936,11 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
 	}
 #endif
 
-	err = fib6_add_rt2node(fn, rt, info);
+	err = fib6_add_rt2node(fn, rt, info, mx, mx_len);
 	if (!err) {
 		fib6_start_gc(info->nl_net, rt);
 		if (!(rt->rt6i_flags & RTF_CACHE))
-			fib6_prune_clones(info->nl_net, pn, rt);
+			fib6_prune_clones(info->nl_net, pn);
 	}
 
 out:
@@ -955,8 +991,8 @@ struct lookup_args {
 	const struct in6_addr	*addr;		/* search key			*/
 };
 
-static struct fib6_node * fib6_lookup_1(struct fib6_node *root,
-					struct lookup_args *args)
+static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
+				       struct lookup_args *args)
 {
 	struct fib6_node *fn;
 	__be32 dir;
@@ -1018,8 +1054,8 @@ backtrack:
 	return NULL;
 }
 
-struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
-			       const struct in6_addr *saddr)
+struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
+			      const struct in6_addr *saddr)
 {
 	struct fib6_node *fn;
 	struct lookup_args args[] = {
@@ -1051,9 +1087,9 @@ struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *da
  */
 
 
-static struct fib6_node * fib6_locate_1(struct fib6_node *root,
-					const struct in6_addr *addr,
-					int plen, int offset)
+static struct fib6_node *fib6_locate_1(struct fib6_node *root,
+				       const struct in6_addr *addr,
+				       int plen, int offset)
 {
 	struct fib6_node *fn;
 
@@ -1081,9 +1117,9 @@ static struct fib6_node * fib6_locate_1(struct fib6_node *root,
 	return NULL;
 }
 
-struct fib6_node * fib6_locate(struct fib6_node *root,
-			       const struct in6_addr *daddr, int dst_len,
-			       const struct in6_addr *saddr, int src_len)
+struct fib6_node *fib6_locate(struct fib6_node *root,
+			      const struct in6_addr *daddr, int dst_len,
+			      const struct in6_addr *saddr, int src_len)
 {
 	struct fib6_node *fn;
 
@@ -1151,8 +1187,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 
 		children = 0;
 		child = NULL;
-		if (fn->right) child = fn->right, children |= 1;
-		if (fn->left) child = fn->left, children |= 2;
+		if (fn->right)
+			child = fn->right, children |= 1;
+		if (fn->left)
+			child = fn->left, children |= 2;
 
 		if (children == 3 || FIB6_SUBTREE(fn)
 #ifdef CONFIG_IPV6_SUBTREES
@@ -1180,8 +1218,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 		} else {
 			WARN_ON(fn->fn_flags & RTN_ROOT);
 #endif
-			if (pn->right == fn) pn->right = child;
-			else if (pn->left == fn) pn->left = child;
+			if (pn->right == fn)
+				pn->right = child;
+			else if (pn->left == fn)
+				pn->left = child;
 #if RT6_DEBUG >= 2
 			else
 				WARN_ON(1);
@@ -1213,10 +1253,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 					w->node = child;
 					if (children&2) {
 						RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
-						w->state = w->state>=FWS_R ? FWS_U : FWS_INIT;
+						w->state = w->state >= FWS_R ? FWS_U : FWS_INIT;
 					} else {
 						RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state);
-						w->state = w->state>=FWS_C ? FWS_U : FWS_INIT;
+						w->state = w->state >= FWS_C ? FWS_U : FWS_INIT;
 					}
 				}
 			}
@@ -1314,7 +1354,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
 	struct rt6_info **rtp;
 
 #if RT6_DEBUG >= 2
-	if (rt->dst.obsolete>0) {
+	if (rt->dst.obsolete > 0) {
 		WARN_ON(fn != NULL);
 		return -ENOENT;
 	}
@@ -1334,7 +1374,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
 			pn = pn->parent;
 		}
 #endif
-		fib6_prune_clones(info->nl_net, pn, rt);
+		fib6_prune_clones(info->nl_net, pn);
 	}
 
 	/*
@@ -1418,7 +1458,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
 
 				if (w->skip) {
 					w->skip--;
-					continue;
+					goto skip;
 				}
 
 				err = w->func(w);
@@ -1428,6 +1468,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
 				w->count++;
 				continue;
 			}
+skip:
 			w->state = FWS_U;
 		case FWS_U:
 			if (fn == w->root)
@@ -1530,7 +1571,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 }
 
 void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
-		    int prune, void *arg)
+		    void *arg)
 {
 	struct fib6_table *table;
 	struct hlist_head *head;
@@ -1542,7 +1583,7 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
 			write_lock_bh(&table->tb6_lock);
 			fib6_clean_tree(net, &table->tb6_root,
-					func, prune, arg);
+					func, 0, arg);
 			write_unlock_bh(&table->tb6_lock);
 		}
 	}
@@ -1559,10 +1600,9 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg)
 	return 0;
 }
 
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
-			      struct rt6_info *rt)
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
 {
-	fib6_clean_tree(net, fn, fib6_prune_clone, 1, rt);
+	fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL);
 }
 
 /*
@@ -1636,7 +1676,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 
 	gc_args.more = icmp6_dst_gc();
 
-	fib6_clean_all(net, fib6_age, 0, NULL);
+	fib6_clean_all(net, fib6_age, NULL);
 	now = jiffies;
 	net->ipv6.ip6_rt_last_gc = now;
 
@@ -1707,7 +1747,7 @@ out_rt6_stats:
 	kfree(net->ipv6.rt6_stats);
 out_timer:
 	return -ENOMEM;
- }
+}
 
 static void fib6_net_exit(struct net *net)
 {
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index e7fb7106550..4052694c6f2 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -15,9 +15,7 @@
 #include <linux/socket.h>
 #include <linux/net.h>
 #include <linux/netdevice.h>
-#include <linux/if_arp.h>
 #include <linux/in6.h>
-#include <linux/route.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
@@ -28,12 +26,7 @@
 #include <net/sock.h>
 
 #include <net/ipv6.h>
-#include <net/ndisc.h>
-#include <net/protocol.h>
-#include <net/ip6_route.h>
-#include <net/addrconf.h>
 #include <net/rawv6.h>
-#include <net/icmp.h>
 #include <net/transp_v6.h>
 
 #include <asm/uaccess.h>
@@ -210,7 +203,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net,
 	spin_lock_bh(&ip6_fl_lock);
 	if (label == 0) {
 		for (;;) {
-			fl->label = htonl(net_random())&IPV6_FLOWLABEL_MASK;
+			fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK;
 			if (fl->label) {
 				lfl = __fl_lookup(net, fl->label);
 				if (lfl == NULL)
@@ -481,11 +474,22 @@ static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl,
 	spin_unlock_bh(&ip6_sk_fl_lock);
 }
 
-int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq)
+int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
+			   int flags)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct ipv6_fl_socklist *sfl;
 
+	if (flags & IPV6_FL_F_REMOTE) {
+		freq->flr_label = np->rcv_flowinfo & IPV6_FLOWLABEL_MASK;
+		return 0;
+	}
+
+	if (np->repflow) {
+		freq->flr_label = np->flow_label;
+		return 0;
+	}
+
 	rcu_read_lock_bh();
 
 	for_each_sk_fl_rcu(np, sfl) {
@@ -527,6 +531,15 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 
 	switch (freq.flr_action) {
 	case IPV6_FL_A_PUT:
+		if (freq.flr_flags & IPV6_FL_F_REFLECT) {
+			if (sk->sk_protocol != IPPROTO_TCP)
+				return -ENOPROTOOPT;
+			if (!np->repflow)
+				return -ESRCH;
+			np->flow_label = 0;
+			np->repflow = 0;
+			return 0;
+		}
 		spin_lock_bh(&ip6_sk_fl_lock);
 		for (sflp = &np->ipv6_fl_list;
 		     (sfl = rcu_dereference(*sflp))!=NULL;
@@ -567,6 +580,20 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 		return -ESRCH;
 
 	case IPV6_FL_A_GET:
+		if (freq.flr_flags & IPV6_FL_F_REFLECT) {
+			struct net *net = sock_net(sk);
+			if (net->ipv6.sysctl.flowlabel_consistency) {
+				net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n");
+				return -EPERM;
+			}
+
+			if (sk->sk_protocol != IPPROTO_TCP)
+				return -ENOPROTOOPT;
+
+			np->repflow = 1;
+			return 0;
+		}
+
 		if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
 			return -EINVAL;
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 8acb28621f9..3873181ed85 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -61,9 +61,6 @@ static bool log_ecn_error = true;
 module_param(log_ecn_error, bool, 0644);
 MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
 
-#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
-#define IPV6_TCLASS_SHIFT 20
-
 #define HASH_SIZE_SHIFT  5
 #define HASH_SIZE (1 << HASH_SIZE_SHIFT)
 
@@ -75,6 +72,7 @@ struct ip6gre_net {
 };
 
 static struct rtnl_link_ops ip6gre_link_ops __read_mostly;
+static struct rtnl_link_ops ip6gre_tap_ops __read_mostly;
 static int ip6gre_tunnel_init(struct net_device *dev);
 static void ip6gre_tunnel_setup(struct net_device *dev);
 static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t);
@@ -356,10 +354,10 @@ failed_free:
 
 static void ip6gre_tunnel_uninit(struct net_device *dev)
 {
-	struct net *net = dev_net(dev);
-	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 
-	ip6gre_tunnel_unlink(ign, netdev_priv(dev));
+	ip6gre_tunnel_unlink(ign, t);
 	dev_put(dev);
 }
 
@@ -470,17 +468,7 @@ static int ip6gre_rcv(struct sk_buff *skb)
 			goto drop;
 
 		if (flags&GRE_CSUM) {
-			switch (skb->ip_summed) {
-			case CHECKSUM_COMPLETE:
-				csum = csum_fold(skb->csum);
-				if (!csum)
-					break;
-				/* fall through */
-			case CHECKSUM_NONE:
-				skb->csum = 0;
-				csum = __skb_checksum_complete(skb);
-				skb->ip_summed = CHECKSUM_COMPLETE;
-			}
+			csum = skb_checksum_simple_validate(skb);
 			offset += 4;
 		}
 		if (flags&GRE_KEY) {
@@ -499,7 +487,7 @@ static int ip6gre_rcv(struct sk_buff *skb)
 					  &ipv6h->saddr, &ipv6h->daddr, key,
 					  gre_proto);
 	if (tunnel) {
-		struct pcpu_tstats *tstats;
+		struct pcpu_sw_netstats *tstats;
 
 		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
 			goto drop;
@@ -614,8 +602,8 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 			 int encap_limit,
 			 __u32 *pmtu)
 {
-	struct net *net = dev_net(dev);
 	struct ip6_tnl *tunnel = netdev_priv(dev);
+	struct net *net = tunnel->net;
 	struct net_device *tdev;    /* Device to other host */
 	struct ipv6hdr  *ipv6h;     /* Our new IP header */
 	unsigned int max_headroom = 0; /* The extra header space needed */
@@ -846,7 +834,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
 		fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
-		fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);
+		fl6.flowlabel |= ip6_flowlabel(ipv6h);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 		fl6.flowi6_mark = skb->mark;
 
@@ -982,7 +970,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
 		int strict = (ipv6_addr_type(&p->raddr) &
 			      (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
 
-		struct rt6_info *rt = rt6_lookup(dev_net(dev),
+		struct rt6_info *rt = rt6_lookup(t->net,
 						 &p->raddr, &p->laddr,
 						 p->link, strict);
 
@@ -1066,13 +1054,12 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev,
 	int err = 0;
 	struct ip6_tnl_parm2 p;
 	struct __ip6_tnl_parm p1;
-	struct ip6_tnl *t;
-	struct net *net = dev_net(dev);
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct net *net = t->net;
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 
 	switch (cmd) {
 	case SIOCGETTUNNEL:
-		t = NULL;
 		if (dev == ign->fb_tunnel_dev) {
 			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
 				err = -EFAULT;
@@ -1080,9 +1067,9 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev,
 			}
 			ip6gre_tnl_parm_from_user(&p1, &p);
 			t = ip6gre_tunnel_locate(net, &p1, 0);
+			if (t == NULL)
+				t = netdev_priv(dev);
 		}
-		if (t == NULL)
-			t = netdev_priv(dev);
 		memset(&p, 0, sizeof(p));
 		ip6gre_tnl_parm_to_user(&p, &t->parms);
 		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
@@ -1245,7 +1232,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
 	dev->flags |= IFF_NOARP;
 	dev->iflink = 0;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 }
 
@@ -1266,12 +1252,12 @@ static int ip6gre_tunnel_init(struct net_device *dev)
 	if (ipv6_addr_any(&tunnel->parms.raddr))
 		dev->header_ops = &ip6gre_header_ops;
 
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
 	for_each_possible_cpu(i) {
-		struct pcpu_tstats *ip6gre_tunnel_stats;
+		struct pcpu_sw_netstats *ip6gre_tunnel_stats;
 		ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i);
 		u64_stats_init(&ip6gre_tunnel_stats->syncp);
 	}
@@ -1300,11 +1286,17 @@ static struct inet6_protocol ip6gre_protocol __read_mostly = {
 	.flags       = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
-static void ip6gre_destroy_tunnels(struct ip6gre_net *ign,
-	struct list_head *head)
+static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
 {
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	struct net_device *dev, *aux;
 	int prio;
 
+	for_each_netdev_safe(net, dev, aux)
+		if (dev->rtnl_link_ops == &ip6gre_link_ops ||
+		    dev->rtnl_link_ops == &ip6gre_tap_ops)
+			unregister_netdevice_queue(dev, head);
+
 	for (prio = 0; prio < 4; prio++) {
 		int h;
 		for (h = 0; h < HASH_SIZE; h++) {
@@ -1313,7 +1305,12 @@ static void ip6gre_destroy_tunnels(struct ip6gre_net *ign,
 			t = rtnl_dereference(ign->tunnels[prio][h]);
 
 			while (t != NULL) {
-				unregister_netdevice_queue(t->dev, head);
+				/* If dev is in the same netns, it has already
+				 * been added to the list by the previous loop.
+				 */
+				if (!net_eq(dev_net(t->dev), net))
+					unregister_netdevice_queue(t->dev,
+								   head);
 				t = rtnl_dereference(t->next);
 			}
 		}
@@ -1332,6 +1329,11 @@ static int __net_init ip6gre_init_net(struct net *net)
 		goto err_alloc_dev;
 	}
 	dev_net_set(ign->fb_tunnel_dev, net);
+	/* FB netdevice is special: we have one, and only one per netns.
+	 * Allowing to move it to another netns is clearly unsafe.
+	 */
+	ign->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+
 
 	ip6gre_fb_tunnel_init(ign->fb_tunnel_dev);
 	ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops;
@@ -1352,12 +1354,10 @@ err_alloc_dev:
 
 static void __net_exit ip6gre_exit_net(struct net *net)
 {
-	struct ip6gre_net *ign;
 	LIST_HEAD(list);
 
-	ign = net_generic(net, ip6gre_net_id);
 	rtnl_lock();
-	ip6gre_destroy_tunnels(ign, &list);
+	ip6gre_destroy_tunnels(net, &list);
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
@@ -1457,7 +1457,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 static int ip6gre_tap_init(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
-	int i;
 
 	tunnel = netdev_priv(dev);
 
@@ -1467,16 +1466,10 @@ static int ip6gre_tap_init(struct net_device *dev)
 
 	ip6gre_tnl_link_config(tunnel, 1);
 
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_tstats *ip6gre_tap_stats;
-		ip6gre_tap_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ip6gre_tap_stats->syncp);
-	}
-
 	return 0;
 }
 
@@ -1541,15 +1534,14 @@ out:
 static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct nlattr *data[])
 {
-	struct ip6_tnl *t, *nt;
-	struct net *net = dev_net(dev);
+	struct ip6_tnl *t, *nt = netdev_priv(dev);
+	struct net *net = nt->net;
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 	struct __ip6_tnl_parm p;
 
 	if (dev == ign->fb_tunnel_dev)
 		return -EINVAL;
 
-	nt = netdev_priv(dev);
 	ip6gre_netlink_parms(data, &p);
 
 	t = ip6gre_tunnel_locate(net, &p, 0);
@@ -1569,6 +1561,15 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 	return 0;
 }
 
+static void ip6gre_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+
+	if (dev != ign->fb_tunnel_dev)
+		unregister_netdevice_queue(dev, head);
+}
+
 static size_t ip6gre_get_size(const struct net_device *dev)
 {
 	return
@@ -1646,6 +1647,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
 	.validate	= ip6gre_tunnel_validate,
 	.newlink	= ip6gre_newlink,
 	.changelink	= ip6gre_changelink,
+	.dellink	= ip6gre_dellink,
 	.get_size	= ip6gre_get_size,
 	.fill_info	= ip6gre_fill_info,
 };
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 302d6fb1ff2..51d54dc376f 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -49,7 +49,7 @@
 
 int ip6_rcv_finish(struct sk_buff *skb)
 {
-	if (sysctl_ip_early_demux && !skb_dst(skb)) {
+	if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
 		const struct inet6_protocol *ipprot;
 
 		ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 4b851692b1f..65eda2a8af4 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -89,7 +89,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	unsigned int unfrag_ip6hlen;
 	u8 *prevhdr;
 	int offset = 0;
-	bool tunnel;
+	bool encap, udpfrag;
 	int nhoff;
 
 	if (unlikely(skb_shinfo(skb)->gso_type &
@@ -97,9 +97,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
+		       SKB_GSO_GRE_CSUM |
 		       SKB_GSO_IPIP |
 		       SKB_GSO_SIT |
 		       SKB_GSO_UDP_TUNNEL |
+		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_MPLS |
 		       SKB_GSO_TCPV6 |
 		       0)))
@@ -110,8 +112,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
 		goto out;
 
-	tunnel = SKB_GSO_CB(skb)->encap_level > 0;
-	if (tunnel)
+	encap = SKB_GSO_CB(skb)->encap_level > 0;
+	if (encap)
 		features = skb->dev->hw_enc_features & netif_skb_features(skb);
 	SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
 
@@ -121,6 +123,12 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 	proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
 
+	if (skb->encapsulation &&
+	    skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+		udpfrag = proto == IPPROTO_UDP && encap;
+	else
+		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment)) {
 		skb_reset_transport_header(skb);
@@ -133,13 +141,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	for (skb = segs; skb; skb = skb->next) {
 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
 		ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h));
-		if (tunnel) {
-			skb_reset_inner_headers(skb);
-			skb->encapsulation = 1;
-		}
 		skb->network_header = (u8 *)ipv6h - skb->head;
 
-		if (!tunnel && proto == IPPROTO_UDP) {
+		if (udpfrag) {
 			unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
 			fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
 			fptr->frag_off = htons(offset);
@@ -148,12 +152,40 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 			offset += (ntohs(ipv6h->payload_len) -
 				   sizeof(struct frag_hdr));
 		}
+		if (encap)
+			skb_reset_inner_headers(skb);
 	}
 
 out:
 	return segs;
 }
 
+/* Return the total length of all the extension hdrs, following the same
+ * logic in ipv6_gso_pull_exthdrs() when parsing ext-hdrs.
+ */
+static int ipv6_exthdrs_len(struct ipv6hdr *iph,
+			    const struct net_offload **opps)
+{
+	struct ipv6_opt_hdr *opth = (void *)iph;
+	int len = 0, proto, optlen = sizeof(*iph);
+
+	proto = iph->nexthdr;
+	for (;;) {
+		if (proto != NEXTHDR_HOP) {
+			*opps = rcu_dereference(inet6_offloads[proto]);
+			if (unlikely(!(*opps)))
+				break;
+			if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR))
+				break;
+		}
+		opth = (void *)opth + optlen;
+		optlen = ipv6_optlen(opth);
+		len += optlen;
+		proto = opth->nexthdr;
+	}
+	return len;
+}
+
 static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 					 struct sk_buff *skb)
 {
@@ -164,9 +196,8 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	unsigned int nlen;
 	unsigned int hlen;
 	unsigned int off;
-	int flush = 1;
+	u16 flush = 1;
 	int proto;
-	__wsum csum;
 
 	off = skb_gro_offset(skb);
 	hlen = off + sizeof(*iph);
@@ -177,6 +208,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 			goto out;
 	}
 
+	skb_set_network_header(skb, off);
 	skb_gro_pull(skb, sizeof(*iph));
 	skb_set_transport_header(skb, skb_gro_offset(skb));
 
@@ -211,12 +243,16 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
-		iph2 = ipv6_hdr(p);
+		iph2 = (struct ipv6hdr *)(p->data + off);
 		first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ;
 
-		/* All fields must match except length and Traffic Class. */
-		if (nlen != skb_network_header_len(p) ||
-		    (first_word & htonl(0xF00FFFFF)) ||
+		/* All fields must match except length and Traffic Class.
+		 * XXX skbs on the gro_list have all been parsed and pulled
+		 * already so we don't need to compare nlen
+		 * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops)))
+		 * memcmp() alone below is suffcient, right?
+		 */
+		 if ((first_word & htonl(0xF00FFFFF)) ||
 		    memcmp(&iph->nexthdr, &iph2->nexthdr,
 			   nlen - offsetof(struct ipv6hdr, nexthdr))) {
 			NAPI_GRO_CB(p)->same_flow = 0;
@@ -229,13 +265,10 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 
 	NAPI_GRO_CB(skb)->flush |= flush;
 
-	csum = skb->csum;
-	skb_postpull_rcsum(skb, iph, skb_network_header_len(skb));
+	skb_gro_postpull_rcsum(skb, iph, nlen);
 
 	pp = ops->callbacks.gro_receive(head, skb);
 
-	skb->csum = csum;
-
 out_unlock:
 	rcu_read_unlock();
 
@@ -245,21 +278,21 @@ out:
 	return pp;
 }
 
-static int ipv6_gro_complete(struct sk_buff *skb)
+static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct net_offload *ops;
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
 	int err = -ENOSYS;
 
-	iph->payload_len = htons(skb->len - skb_network_offset(skb) -
-				 sizeof(*iph));
+	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
 
 	rcu_read_lock();
-	ops = rcu_dereference(inet6_offloads[NAPI_GRO_CB(skb)->proto]);
+
+	nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
 		goto out_unlock;
 
-	err = ops->callbacks.gro_complete(skb);
+	err = ops->callbacks.gro_complete(skb, nhoff);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9a311cc7967..45702b8cd14 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -132,7 +132,7 @@ static int ip6_finish_output(struct sk_buff *skb)
 		return ip6_finish_output2(skb);
 }
 
-int ip6_output(struct sk_buff *skb)
+int ip6_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb_dst(skb)->dev;
 	struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
@@ -219,7 +219,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	skb->mark = sk->sk_mark;
 
 	mtu = dst_mtu(dst);
-	if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) {
+	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
 		IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			      IPSTATS_MIB_OUT, skb->len);
 		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
@@ -321,6 +321,45 @@ static inline int ip6_forward_finish(struct sk_buff *skb)
 	return dst_output(skb);
 }
 
+static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
+{
+	unsigned int mtu;
+	struct inet6_dev *idev;
+
+	if (dst_metric_locked(dst, RTAX_MTU)) {
+		mtu = dst_metric_raw(dst, RTAX_MTU);
+		if (mtu)
+			return mtu;
+	}
+
+	mtu = IPV6_MIN_MTU;
+	rcu_read_lock();
+	idev = __in6_dev_get(dst->dev);
+	if (idev)
+		mtu = idev->cnf.mtu6;
+	rcu_read_unlock();
+
+	return mtu;
+}
+
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+	if (skb->len <= mtu)
+		return false;
+
+	/* ipv6 conntrack defrag sets max_frag_size + ignore_df */
+	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+		return true;
+
+	if (skb->ignore_df)
+		return false;
+
+	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+		return false;
+
+	return true;
+}
+
 int ip6_forward(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -332,6 +371,9 @@ int ip6_forward(struct sk_buff *skb)
 	if (net->ipv6.devconf_all->forwarding == 0)
 		goto error;
 
+	if (skb->pkt_type != PACKET_HOST)
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
@@ -341,9 +383,6 @@ int ip6_forward(struct sk_buff *skb)
 		goto drop;
 	}
 
-	if (skb->pkt_type != PACKET_HOST)
-		goto drop;
-
 	skb_forward_csum(skb);
 
 	/*
@@ -441,12 +480,11 @@ int ip6_forward(struct sk_buff *skb)
 		}
 	}
 
-	mtu = dst_mtu(dst);
+	mtu = ip6_dst_mtu_forward(dst);
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
-	    (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+	if (ip6_pkt_too_big(skb, mtu)) {
 		/* Again, force OUTPUT device used as source address */
 		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -496,12 +534,23 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->tc_index = from->tc_index;
 #endif
 	nf_copy(to, from);
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
-	to->nf_trace = from->nf_trace;
-#endif
 	skb_copy_secmark(to, from);
 }
 
+static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 hash, id;
+
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
+	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
+
+	id = ip_idents_reserve(hash, 1);
+	fhdr->identification = htonl(id);
+}
+
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
@@ -524,7 +573,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	/* We must not fragment if the socket is set to force MTU discovery
 	 * or if the skb it not generated by a local socket.
 	 */
-	if (unlikely(!skb->local_df && skb->len > mtu) ||
+	if (unlikely(!skb->ignore_df && skb->len > mtu) ||
 		     (IP6CB(skb)->frag_max_size &&
 		      IP6CB(skb)->frag_max_size > mtu)) {
 		if (skb->sk && dst_allfrag(skb_dst(skb)))
@@ -941,7 +990,6 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
  *	@sk: socket which provides route info
  *	@fl6: flow to lookup
  *	@final_dst: final destination address for ipsec lookup
- *	@can_sleep: we are in a sleepable context
  *
  *	This function performs a route lookup on the given flow.
  *
@@ -949,8 +997,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
  *	error code.
  */
 struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
-				      const struct in6_addr *final_dst,
-				      bool can_sleep)
+				      const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = NULL;
 	int err;
@@ -960,8 +1007,6 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 		return ERR_PTR(err);
 	if (final_dst)
 		fl6->daddr = *final_dst;
-	if (can_sleep)
-		fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
 
 	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
@@ -972,7 +1017,6 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
  *	@sk: socket which provides the dst cache and route info
  *	@fl6: flow to lookup
  *	@final_dst: final destination address for ipsec lookup
- *	@can_sleep: we are in a sleepable context
  *
  *	This function performs a route lookup on the given flow with the
  *	possibility of using the cached route in the socket if it is valid.
@@ -983,8 +1027,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
  *	error code.
  */
 struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
-					 const struct in6_addr *final_dst,
-					 bool can_sleep)
+					 const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
 	int err;
@@ -996,8 +1039,6 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 		return ERR_PTR(err);
 	if (final_dst)
 		fl6->daddr = *final_dst;
-	if (can_sleep)
-		fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
 
 	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
@@ -1078,21 +1119,19 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 				unsigned int fragheaderlen,
 				struct sk_buff *skb,
 				struct rt6_info *rt,
-				bool pmtuprobe)
+				unsigned int orig_mtu)
 {
 	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
 		if (skb == NULL) {
 			/* first fragment, reserve header_len */
-			*mtu = *mtu - rt->dst.header_len;
+			*mtu = orig_mtu - rt->dst.header_len;
 
 		} else {
 			/*
 			 * this fragment is not first, the headers
 			 * space is regarded as data space.
 			 */
-			*mtu = min(*mtu, pmtuprobe ?
-				   rt->dst.dev->mtu :
-				   dst_mtu(rt->dst.path));
+			*mtu = orig_mtu;
 		}
 		*maxfraglen = ((*mtu - fragheaderlen) & ~7)
 			      + fragheaderlen - sizeof(struct frag_hdr);
@@ -1109,7 +1148,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet_cork *cork;
 	struct sk_buff *skb, *skb_prev = NULL;
-	unsigned int maxfraglen, fragheaderlen, mtu;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
 	int exthdrlen;
 	int dst_exthdrlen;
 	int hh_len;
@@ -1165,10 +1204,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		np->cork.hop_limit = hlimit;
 		np->cork.tclass = tclass;
 		if (rt->dst.flags & DST_XFRM_TUNNEL)
-			mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
 			      rt->dst.dev->mtu : dst_mtu(&rt->dst);
 		else
-			mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
+			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
 			      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
 		if (np->frag_size < mtu) {
 			if (np->frag_size)
@@ -1191,16 +1230,43 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		dst_exthdrlen = 0;
 		mtu = cork->fragsize;
 	}
+	orig_mtu = mtu;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
 			(opt ? opt->opt_nflen : 0);
-	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
+	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
+		     sizeof(struct frag_hdr);
 
 	if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
-		if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
-			ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
+		unsigned int maxnonfragsize, headersize;
+
+		headersize = sizeof(struct ipv6hdr) +
+			     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
+			     (dst_allfrag(&rt->dst) ?
+			      sizeof(struct frag_hdr) : 0) +
+			     rt->rt6i_nfheader_len;
+
+		if (ip6_sk_ignore_df(sk))
+			maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+		else
+			maxnonfragsize = mtu;
+
+		/* dontfrag active */
+		if ((cork->length + length > mtu - headersize) && dontfrag &&
+		    (sk->sk_protocol == IPPROTO_UDP ||
+		     sk->sk_protocol == IPPROTO_RAW)) {
+			ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
+						   sizeof(struct ipv6hdr));
+			goto emsgsize;
+		}
+
+		if (cork->length + length > maxnonfragsize - headersize) {
+emsgsize:
+			ipv6_local_error(sk, EMSGSIZE, fl6,
+					 mtu - headersize +
+					 sizeof(struct ipv6hdr));
 			return -EMSGSIZE;
 		}
 	}
@@ -1225,12 +1291,6 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	 * --yoshfuji
 	 */
 
-	if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP ||
-					   sk->sk_protocol == IPPROTO_RAW)) {
-		ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
-		return -EMSGSIZE;
-	}
-
 	skb = skb_peek_tail(&sk->sk_write_queue);
 	cork->length += length;
 	if (((length > mtu) ||
@@ -1270,8 +1330,7 @@ alloc_new_skb:
 			if (skb == NULL || skb_prev == NULL)
 				ip6_append_data_mtu(&mtu, &maxfraglen,
 						    fragheaderlen, skb, rt,
-						    np->pmtudisc ==
-						    IPV6_PMTUDISC_PROBE);
+						    orig_mtu);
 
 			skb_prev = skb;
 
@@ -1499,8 +1558,7 @@ int ip6_push_pending_frames(struct sock *sk)
 	}
 
 	/* Allow local fragmentation. */
-	if (np->pmtudisc < IPV6_PMTUDISC_DO)
-		skb->local_df = 1;
+	skb->ignore_df = ip6_sk_ignore_df(sk);
 
 	*final_dst = fl6->daddr;
 	__skb_pull(skb, skb_network_header_len(skb));
@@ -1527,8 +1585,8 @@ int ip6_push_pending_frames(struct sock *sk)
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
 	err = ip6_local_out(skb);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index d6062325db0..afa08245836 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -29,7 +29,6 @@
 #include <linux/if.h>
 #include <linux/in.h>
 #include <linux/ip.h>
-#include <linux/if_tunnel.h>
 #include <linux/net.h>
 #include <linux/in6.h>
 #include <linux/netdevice.h>
@@ -62,6 +61,7 @@
 MODULE_AUTHOR("Ville Nuorvala");
 MODULE_DESCRIPTION("IPv6 tunneling device");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ip6tnl");
 MODULE_ALIAS_NETDEV("ip6tnl0");
 
 #ifdef IP6_TNL_DEBUG
@@ -70,9 +70,6 @@ MODULE_ALIAS_NETDEV("ip6tnl0");
 #define IP6_TNL_TRACE(x...) do {;} while(0)
 #endif
 
-#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
-#define IPV6_TCLASS_SHIFT 20
-
 #define HASH_SIZE_SHIFT  5
 #define HASH_SIZE (1 << HASH_SIZE_SHIFT)
 
@@ -103,16 +100,26 @@ struct ip6_tnl_net {
 
 static struct net_device_stats *ip6_get_stats(struct net_device *dev)
 {
-	struct pcpu_tstats sum = { 0 };
+	struct pcpu_sw_netstats tmp, sum = { 0 };
 	int i;
 
 	for_each_possible_cpu(i) {
-		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
-
-		sum.rx_packets += tstats->rx_packets;
-		sum.rx_bytes   += tstats->rx_bytes;
-		sum.tx_packets += tstats->tx_packets;
-		sum.tx_bytes   += tstats->tx_bytes;
+		unsigned int start;
+		const struct pcpu_sw_netstats *tstats =
+						   per_cpu_ptr(dev->tstats, i);
+
+		do {
+			start = u64_stats_fetch_begin_irq(&tstats->syncp);
+			tmp.rx_packets = tstats->rx_packets;
+			tmp.rx_bytes = tstats->rx_bytes;
+			tmp.tx_packets = tstats->tx_packets;
+			tmp.tx_bytes =  tstats->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
+
+		sum.rx_packets += tmp.rx_packets;
+		sum.rx_bytes   += tmp.rx_bytes;
+		sum.tx_packets += tmp.tx_packets;
+		sum.tx_bytes   += tmp.tx_bytes;
 	}
 	dev->stats.rx_packets = sum.rx_packets;
 	dev->stats.rx_bytes   = sum.rx_bytes;
@@ -785,7 +792,7 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
 
 	if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr,
 					&ipv6h->daddr)) != NULL) {
-		struct pcpu_tstats *tstats;
+		struct pcpu_sw_netstats *tstats;
 
 		if (t->parms.proto != ipproto && t->parms.proto != 0) {
 			rcu_read_unlock();
@@ -824,8 +831,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
 		}
 
 		tstats = this_cpu_ptr(t->dev->tstats);
+		u64_stats_update_begin(&tstats->syncp);
 		tstats->rx_packets++;
 		tstats->rx_bytes += skb->len;
+		u64_stats_update_end(&tstats->syncp);
 
 		netif_rx(skb);
 
@@ -1131,7 +1140,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
 		fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
-		fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);
+		fl6.flowlabel |= ip6_flowlabel(ipv6h);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 		fl6.flowi6_mark = skb->mark;
 
@@ -1332,8 +1341,8 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	int err = 0;
 	struct ip6_tnl_parm p;
 	struct __ip6_tnl_parm p1;
-	struct ip6_tnl *t = NULL;
-	struct net *net = dev_net(dev);
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct net *net = t->net;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 
 	switch (cmd) {
@@ -1345,11 +1354,11 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			}
 			ip6_tnl_parm_from_user(&p1, &p);
 			t = ip6_tnl_locate(net, &p1, 0);
+			if (t == NULL)
+				t = netdev_priv(dev);
 		} else {
 			memset(&p, 0, sizeof(p));
 		}
-		if (t == NULL)
-			t = netdev_priv(dev);
 		ip6_tnl_parm_to_user(&p, &t->parms);
 		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) {
 			err = -EFAULT;
@@ -1494,19 +1503,12 @@ static inline int
 ip6_tnl_dev_init_gen(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	int i;
 
 	t->dev = dev;
 	t->net = dev_net(dev);
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
-
-	for_each_possible_cpu(i) {
-		struct pcpu_tstats *ip6_tnl_stats;
-		ip6_tnl_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ip6_tnl_stats->syncp);
-	}
 	return 0;
 }
 
@@ -1556,7 +1558,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[])
 {
 	u8 proto;
 
-	if (!data)
+	if (!data || !data[IFLA_IPTUN_PROTO])
 		return 0;
 
 	proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index ed94ba61dda..9aaa6bb229e 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -24,7 +24,6 @@
 #include <linux/if.h>
 #include <linux/in.h>
 #include <linux/ip.h>
-#include <linux/if_tunnel.h>
 #include <linux/net.h>
 #include <linux/in6.h>
 #include <linux/netdevice.h>
@@ -75,26 +74,6 @@ struct vti6_net {
 	struct ip6_tnl __rcu **tnls[2];
 };
 
-static struct net_device_stats *vti6_get_stats(struct net_device *dev)
-{
-	struct pcpu_tstats sum = { 0 };
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
-
-		sum.rx_packets += tstats->rx_packets;
-		sum.rx_bytes   += tstats->rx_bytes;
-		sum.tx_packets += tstats->tx_packets;
-		sum.tx_bytes   += tstats->tx_bytes;
-	}
-	dev->stats.rx_packets = sum.rx_packets;
-	dev->stats.rx_bytes   = sum.rx_bytes;
-	dev->stats.tx_packets = sum.tx_packets;
-	dev->stats.tx_bytes   = sum.tx_bytes;
-	return &dev->stats;
-}
-
 #define for_each_vti6_tunnel_rcu(start) \
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
@@ -299,7 +278,6 @@ static void vti6_dev_uninit(struct net_device *dev)
 		RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL);
 	else
 		vti6_tnl_unlink(ip6n, t);
-	ip6_tnl_dst_reset(t);
 	dev_put(dev);
 }
 
@@ -309,11 +287,8 @@ static int vti6_rcv(struct sk_buff *skb)
 	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 
 	rcu_read_lock();
-
 	if ((t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr,
 				 &ipv6h->daddr)) != NULL) {
-		struct pcpu_tstats *tstats;
-
 		if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) {
 			rcu_read_unlock();
 			goto discard;
@@ -330,25 +305,58 @@ static int vti6_rcv(struct sk_buff *skb)
 			goto discard;
 		}
 
-		tstats = this_cpu_ptr(t->dev->tstats);
-		tstats->rx_packets++;
-		tstats->rx_bytes += skb->len;
-
-		skb->mark = 0;
-		secpath_reset(skb);
-		skb->dev = t->dev;
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
+		skb->mark = be32_to_cpu(t->parms.i_key);
 
 		rcu_read_unlock();
-		return 0;
+
+		return xfrm6_rcv(skb);
 	}
 	rcu_read_unlock();
-	return 1;
-
+	return -EINVAL;
 discard:
 	kfree_skb(skb);
 	return 0;
 }
 
+static int vti6_rcv_cb(struct sk_buff *skb, int err)
+{
+	unsigned short family;
+	struct net_device *dev;
+	struct pcpu_sw_netstats *tstats;
+	struct xfrm_state *x;
+	struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
+
+	if (!t)
+		return 1;
+
+	dev = t->dev;
+
+	if (err) {
+		dev->stats.rx_errors++;
+		dev->stats.rx_dropped++;
+
+		return 0;
+	}
+
+	x = xfrm_input_state(skb);
+	family = x->inner_mode->afinfo->family;
+
+	if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+		return -EPERM;
+
+	skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev)));
+	skb->dev = dev;
+
+	tstats = this_cpu_ptr(dev->tstats);
+	u64_stats_update_begin(&tstats->syncp);
+	tstats->rx_packets++;
+	tstats->rx_bytes += skb->len;
+	u64_stats_update_end(&tstats->syncp);
+
+	return 0;
+}
+
 /**
  * vti6_addr_conflict - compare packet addresses to tunnel's own
  *   @t: the outgoing tunnel device
@@ -368,44 +376,56 @@ vti6_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr)
 	return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
 }
 
+static bool vti6_state_check(const struct xfrm_state *x,
+			     const struct in6_addr *dst,
+			     const struct in6_addr *src)
+{
+	xfrm_address_t *daddr = (xfrm_address_t *)dst;
+	xfrm_address_t *saddr = (xfrm_address_t *)src;
+
+	/* if there is no transform then this tunnel is not functional.
+	 * Or if the xfrm is not mode tunnel.
+	 */
+	if (!x || x->props.mode != XFRM_MODE_TUNNEL ||
+	    x->props.family != AF_INET6)
+		return false;
+
+	if (ipv6_addr_any(dst))
+		return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET6);
+
+	if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET6))
+		return false;
+
+	return true;
+}
+
 /**
  * vti6_xmit - send a packet
  *   @skb: the outgoing socket buffer
  *   @dev: the outgoing tunnel device
+ *   @fl: the flow informations for the xfrm_lookup
  **/
-static int vti6_xmit(struct sk_buff *skb, struct net_device *dev)
+static int
+vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 {
-	struct net *net = dev_net(dev);
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net_device_stats *stats = &t->dev->stats;
-	struct dst_entry *dst = NULL, *ndst = NULL;
-	struct flowi6 fl6;
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;
 	int err = -1;
 
-	if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
-	    !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h))
-		return err;
-
-	dst = ip6_tnl_dst_check(t);
-	if (!dst) {
-		memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-
-		ndst = ip6_route_output(net, NULL, &fl6);
+	if (!dst)
+		goto tx_err_link_failure;
 
-		if (ndst->error)
-			goto tx_err_link_failure;
-		ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(&fl6), NULL, 0);
-		if (IS_ERR(ndst)) {
-			err = PTR_ERR(ndst);
-			ndst = NULL;
-			goto tx_err_link_failure;
-		}
-		dst = ndst;
+	dst_hold(dst);
+	dst = xfrm_lookup(t->net, dst, fl, NULL, 0);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
+		dst = NULL;
+		goto tx_err_link_failure;
 	}
 
-	if (!dst->xfrm || dst->xfrm->props.mode != XFRM_MODE_TUNNEL)
+	if (!vti6_state_check(dst->xfrm, &t->parms.raddr, &t->parms.laddr))
 		goto tx_err_link_failure;
 
 	tdev = dst->dev;
@@ -417,14 +437,21 @@ static int vti6_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto tx_err_dst_release;
 	}
 
-
-	skb_dst_drop(skb);
-	skb_dst_set_noref(skb, dst);
-
-	ip6tunnel_xmit(skb, dev);
-	if (ndst) {
-		dev->mtu = dst_mtu(ndst);
-		ip6_tnl_dst_store(t, ndst);
+	skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
+	skb_dst_set(skb, dst);
+	skb->dev = skb_dst(skb)->dev;
+
+	err = dst_output(skb);
+	if (net_xmit_eval(err) == 0) {
+		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+
+		u64_stats_update_begin(&tstats->syncp);
+		tstats->tx_bytes += skb->len;
+		tstats->tx_packets++;
+		u64_stats_update_end(&tstats->syncp);
+	} else {
+		stats->tx_errors++;
+		stats->tx_aborted_errors++;
 	}
 
 	return 0;
@@ -432,7 +459,7 @@ tx_err_link_failure:
 	stats->tx_carrier_errors++;
 	dst_link_failure(skb);
 tx_err_dst_release:
-	dst_release(ndst);
+	dst_release(dst);
 	return err;
 }
 
@@ -441,16 +468,33 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net_device_stats *stats = &t->dev->stats;
+	struct ipv6hdr *ipv6h;
+	struct flowi fl;
 	int ret;
 
+	memset(&fl, 0, sizeof(fl));
+	skb->mark = be32_to_cpu(t->parms.o_key);
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IPV6):
-		ret = vti6_xmit(skb, dev);
+		ipv6h = ipv6_hdr(skb);
+
+		if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
+		    !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h))
+			goto tx_err;
+
+		xfrm_decode_session(skb, &fl, AF_INET6);
+		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		break;
+	case htons(ETH_P_IP):
+		xfrm_decode_session(skb, &fl, AF_INET);
+		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 		break;
 	default:
 		goto tx_err;
 	}
 
+	ret = vti6_xmit(skb, dev, &fl);
 	if (ret < 0)
 		goto tx_err;
 
@@ -463,24 +507,69 @@ tx_err:
 	return NETDEV_TX_OK;
 }
 
+static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		    u8 type, u8 code, int offset, __be32 info)
+{
+	__be32 spi;
+	__u32 mark;
+	struct xfrm_state *x;
+	struct ip6_tnl *t;
+	struct ip_esp_hdr *esph;
+	struct ip_auth_hdr *ah;
+	struct ip_comp_hdr *ipch;
+	struct net *net = dev_net(skb->dev);
+	const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
+	int protocol = iph->nexthdr;
+
+	t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr);
+	if (!t)
+		return -1;
+
+	mark = be32_to_cpu(t->parms.o_key);
+
+	switch (protocol) {
+	case IPPROTO_ESP:
+		esph = (struct ip_esp_hdr *)(skb->data + offset);
+		spi = esph->spi;
+		break;
+	case IPPROTO_AH:
+		ah = (struct ip_auth_hdr *)(skb->data + offset);
+		spi = ah->spi;
+		break;
+	case IPPROTO_COMP:
+		ipch = (struct ip_comp_hdr *)(skb->data + offset);
+		spi = htonl(ntohs(ipch->cpi));
+		break;
+	default:
+		return 0;
+	}
+
+	if (type != ICMPV6_PKT_TOOBIG &&
+	    type != NDISC_REDIRECT)
+		return 0;
+
+	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
+			      spi, protocol, AF_INET6);
+	if (!x)
+		return 0;
+
+	if (type == NDISC_REDIRECT)
+		ip6_redirect(skb, net, skb->dev->ifindex, 0);
+	else
+		ip6_update_pmtu(skb, net, info, 0, 0);
+	xfrm_state_put(x);
+
+	return 0;
+}
+
 static void vti6_link_config(struct ip6_tnl *t)
 {
-	struct dst_entry *dst;
 	struct net_device *dev = t->dev;
 	struct __ip6_tnl_parm *p = &t->parms;
-	struct flowi6 *fl6 = &t->fl.u.ip6;
 
 	memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
 	memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
 
-	/* Set up flowi template */
-	fl6->saddr = p->laddr;
-	fl6->daddr = p->raddr;
-	fl6->flowi6_oif = p->link;
-	fl6->flowi6_mark = be32_to_cpu(p->i_key);
-	fl6->flowi6_proto = p->proto;
-	fl6->flowlabel = 0;
-
 	p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV |
 		      IP6_TNL_F_CAP_PER_PACKET);
 	p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr);
@@ -491,28 +580,6 @@ static void vti6_link_config(struct ip6_tnl *t)
 		dev->flags &= ~IFF_POINTOPOINT;
 
 	dev->iflink = p->link;
-
-	if (p->flags & IP6_TNL_F_CAP_XMIT) {
-
-		dst = ip6_route_output(dev_net(dev), NULL, fl6);
-		if (dst->error)
-			return;
-
-		dst = xfrm_lookup(dev_net(dev), dst, flowi6_to_flowi(fl6),
-				  NULL, 0);
-		if (IS_ERR(dst))
-			return;
-
-		if (dst->dev) {
-			dev->hard_header_len = dst->dev->hard_header_len;
-
-			dev->mtu = dst_mtu(dst);
-
-			if (dev->mtu < IPV6_MIN_MTU)
-				dev->mtu = IPV6_MIN_MTU;
-		}
-		dst_release(dst);
-	}
 }
 
 /**
@@ -716,7 +783,7 @@ static const struct net_device_ops vti6_netdev_ops = {
 	.ndo_start_xmit = vti6_tnl_xmit,
 	.ndo_do_ioctl	= vti6_ioctl,
 	.ndo_change_mtu = vti6_change_mtu,
-	.ndo_get_stats	= vti6_get_stats,
+	.ndo_get_stats64 = ip_tunnel_get_stats64,
 };
 
 /**
@@ -728,18 +795,14 @@ static const struct net_device_ops vti6_netdev_ops = {
  **/
 static void vti6_dev_setup(struct net_device *dev)
 {
-	struct ip6_tnl *t;
-
 	dev->netdev_ops = &vti6_netdev_ops;
 	dev->destructor = vti6_dev_free;
 
 	dev->type = ARPHRD_TUNNEL6;
 	dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
 	dev->mtu = ETH_DATA_LEN;
-	t = netdev_priv(dev);
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 }
 
@@ -753,7 +816,7 @@ static inline int vti6_dev_init_gen(struct net_device *dev)
 
 	t->dev = dev;
 	t->net = dev_net(dev);
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 	return 0;
@@ -927,11 +990,6 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = {
 	.fill_info	= vti6_fill_info,
 };
 
-static struct xfrm_tunnel_notifier vti6_handler __read_mostly = {
-	.handler	= vti6_rcv,
-	.priority	=	1,
-};
-
 static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n)
 {
 	int h;
@@ -1003,6 +1061,27 @@ static struct pernet_operations vti6_net_ops = {
 	.size = sizeof(struct vti6_net),
 };
 
+static struct xfrm6_protocol vti_esp6_protocol __read_mostly = {
+	.handler	=	vti6_rcv,
+	.cb_handler	=	vti6_rcv_cb,
+	.err_handler	=	vti6_err,
+	.priority	=	100,
+};
+
+static struct xfrm6_protocol vti_ah6_protocol __read_mostly = {
+	.handler	=	vti6_rcv,
+	.cb_handler	=	vti6_rcv_cb,
+	.err_handler	=	vti6_err,
+	.priority	=	100,
+};
+
+static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = {
+	.handler	=	vti6_rcv,
+	.cb_handler	=	vti6_rcv_cb,
+	.err_handler	=	vti6_err,
+	.priority	=	100,
+};
+
 /**
  * vti6_tunnel_init - register protocol and reserve needed resources
  *
@@ -1016,11 +1095,30 @@ static int __init vti6_tunnel_init(void)
 	if (err < 0)
 		goto out_pernet;
 
-	err = xfrm6_mode_tunnel_input_register(&vti6_handler);
+	err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP);
 	if (err < 0) {
-		pr_err("%s: can't register vti6\n", __func__);
+		pr_err("%s: can't register vti6 protocol\n", __func__);
+
+		goto out;
+	}
+
+	err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH);
+	if (err < 0) {
+		xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
+		pr_err("%s: can't register vti6 protocol\n", __func__);
+
 		goto out;
 	}
+
+	err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP);
+	if (err < 0) {
+		xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
+		xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
+		pr_err("%s: can't register vti6 protocol\n", __func__);
+
+		goto out;
+	}
+
 	err = rtnl_link_register(&vti6_link_ops);
 	if (err < 0)
 		goto rtnl_link_failed;
@@ -1028,7 +1126,9 @@ static int __init vti6_tunnel_init(void)
 	return 0;
 
 rtnl_link_failed:
-	xfrm6_mode_tunnel_input_deregister(&vti6_handler);
+	xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP);
+	xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
+	xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
 out:
 	unregister_pernet_device(&vti6_net_ops);
 out_pernet:
@@ -1041,8 +1141,12 @@ out_pernet:
 static void __exit vti6_tunnel_cleanup(void)
 {
 	rtnl_link_unregister(&vti6_link_ops);
-	if (xfrm6_mode_tunnel_input_deregister(&vti6_handler))
-		pr_info("%s: can't deregister vti6\n", __func__);
+	if (xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP))
+		pr_info("%s: can't deregister protocol\n", __func__);
+	if (xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH))
+		pr_info("%s: can't deregister protocol\n", __func__);
+	if (xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP))
+		pr_info("%s: can't deregister protocol\n", __func__);
 
 	unregister_pernet_device(&vti6_net_ops);
 }
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f365310bfcc..8250474ab7d 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -141,9 +141,12 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
 static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
 			    struct mr6_table **mrt)
 {
-	struct ip6mr_result res;
-	struct fib_lookup_arg arg = { .result = &res, };
 	int err;
+	struct ip6mr_result res;
+	struct fib_lookup_arg arg = {
+		.result = &res,
+		.flags = FIB_LOOKUP_NOREF,
+	};
 
 	err = fib_rules_lookup(net->ipv6.mr6_rules_ops,
 			       flowi6_to_flowi(flp6), 0, &arg);
@@ -697,7 +700,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 	struct mr6_table *mrt;
 	struct flowi6 fl6 = {
 		.flowi6_oif	= dev->ifindex,
-		.flowi6_iif	= skb->skb_iif,
+		.flowi6_iif	= skb->skb_iif ? : LOOPBACK_IFINDEX,
 		.flowi6_mark	= skb->mark,
 	};
 	int err;
@@ -1630,7 +1633,7 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb)
 {
 	struct mr6_table *mrt;
 	struct flowi6 fl6 = {
-		.flowi6_iif	= skb->skb_iif,
+		.flowi6_iif	= skb->skb_iif ? : LOOPBACK_IFINDEX,
 		.flowi6_oif	= skb->dev->ifindex,
 		.flowi6_mark	= skb->mark,
 	};
@@ -2346,13 +2349,14 @@ int ip6mr_get_route(struct net *net,
 }
 
 static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
-			     u32 portid, u32 seq, struct mfc6_cache *c, int cmd)
+			     u32 portid, u32 seq, struct mfc6_cache *c, int cmd,
+			     int flags)
 {
 	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
 	int err;
 
-	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
@@ -2420,7 +2424,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
 	if (skb == NULL)
 		goto errout;
 
-	err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+	err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
 	if (err < 0)
 		goto errout;
 
@@ -2459,7 +2463,8 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 				if (ip6mr_fill_mroute(mrt, skb,
 						      NETLINK_CB(cb->skb).portid,
 						      cb->nlh->nlmsg_seq,
-						      mfc, RTM_NEWROUTE) < 0)
+						      mfc, RTM_NEWROUTE,
+						      NLM_F_MULTI) < 0)
 					goto done;
 next_entry:
 				e++;
@@ -2473,7 +2478,8 @@ next_entry:
 			if (ip6mr_fill_mroute(mrt, skb,
 					      NETLINK_CB(cb->skb).portid,
 					      cb->nlh->nlmsg_seq,
-					      mfc, RTM_NEWROUTE) < 0) {
+					      mfc, RTM_NEWROUTE,
+					      NLM_F_MULTI) < 0) {
 				spin_unlock_bh(&mfc_unres_lock);
 				goto done;
 			}
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index da9becb42e8..d1c793cffcb 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -53,7 +53,7 @@
 #include <linux/icmpv6.h>
 #include <linux/mutex.h>
 
-static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 				u8 type, u8 code, int offset, __be32 info)
 {
 	struct net *net = dev_net(skb->dev);
@@ -65,19 +65,21 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	if (type != ICMPV6_PKT_TOOBIG &&
 	    type != NDISC_REDIRECT)
-		return;
+		return 0;
 
 	spi = htonl(ntohs(ipcomph->cpi));
 	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
 			      spi, IPPROTO_COMP, AF_INET6);
 	if (!x)
-		return;
+		return 0;
 
 	if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0);
 	else
 		ip6_update_pmtu(skb, net, info, 0, 0);
 	xfrm_state_put(x);
+
+	return 0;
 }
 
 static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x)
@@ -174,6 +176,11 @@ out:
 	return err;
 }
 
+static int ipcomp6_rcv_cb(struct sk_buff *skb, int err)
+{
+	return 0;
+}
+
 static const struct xfrm_type ipcomp6_type =
 {
 	.description	= "IPCOMP6",
@@ -186,11 +193,12 @@ static const struct xfrm_type ipcomp6_type =
 	.hdr_offset	= xfrm6_find_1stfragopt,
 };
 
-static const struct inet6_protocol ipcomp6_protocol =
+static struct xfrm6_protocol ipcomp6_protocol =
 {
 	.handler	= xfrm6_rcv,
+	.cb_handler	= ipcomp6_rcv_cb,
 	.err_handler	= ipcomp6_err,
-	.flags		= INET6_PROTO_NOPOLICY,
+	.priority	= 0,
 };
 
 static int __init ipcomp6_init(void)
@@ -199,7 +207,7 @@ static int __init ipcomp6_init(void)
 		pr_info("%s: can't add xfrm type\n", __func__);
 		return -EAGAIN;
 	}
-	if (inet6_add_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) {
+	if (xfrm6_protocol_register(&ipcomp6_protocol, IPPROTO_COMP) < 0) {
 		pr_info("%s: can't add protocol\n", __func__);
 		xfrm_unregister_type(&ipcomp6_type, AF_INET6);
 		return -EAGAIN;
@@ -209,7 +217,7 @@ static int __init ipcomp6_init(void)
 
 static void __exit ipcomp6_fini(void)
 {
-	if (inet6_del_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0)
+	if (xfrm6_protocol_deregister(&ipcomp6_protocol, IPPROTO_COMP) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
 	if (xfrm_unregister_type(&ipcomp6_type, AF_INET6) < 0)
 		pr_info("%s: can't remove xfrm type\n", __func__);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 1c6ce3119ff..edb58aff4ae 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -722,7 +722,7 @@ done:
 	case IPV6_MTU_DISCOVER:
 		if (optlen < sizeof(int))
 			goto e_inval;
-		if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE)
+		if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT)
 			goto e_inval;
 		np->pmtudisc = val;
 		retv = 0;
@@ -1002,10 +1002,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		release_sock(sk);
 
 		if (skb) {
-			int err = ip6_datagram_recv_ctl(sk, &msg, skb);
+			ip6_datagram_recv_ctl(sk, &msg, skb);
 			kfree_skb(skb);
-			if (err)
-				return err;
 		} else {
 			if (np->rxopt.bits.rxinfo) {
 				struct in6_pktinfo src_info;
@@ -1019,7 +1017,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
 			}
 			if (np->rxopt.bits.rxtclass) {
-				int tclass = np->rcv_tclass;
+				int tclass = (int)ip6_tclass(np->rcv_flowinfo);
+
 				put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass);
 			}
 			if (np->rxopt.bits.rxoinfo) {
@@ -1034,6 +1033,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				int hlim = np->mcast_hops;
 				put_cmsg(&msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim);
 			}
+			if (np->rxopt.bits.rxflow) {
+				__be32 flowinfo = np->rcv_flowinfo;
+
+				put_cmsg(&msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo);
+			}
 		}
 		len -= msg.msg_controllen;
 		return put_user(len, optlen);
@@ -1215,6 +1219,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	case IPV6_FLOWLABEL_MGR:
 	{
 		struct in6_flowlabel_req freq;
+		int flags;
 
 		if (len < sizeof(freq))
 			return -EINVAL;
@@ -1226,9 +1231,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 
 		len = sizeof(freq);
+		flags = freq.flr_flags;
+
 		memset(&freq, 0, sizeof(freq));
 
-		val = ipv6_flowlabel_opt_get(sk, &freq);
+		val = ipv6_flowlabel_opt_get(sk, &freq, flags);
 		if (val < 0)
 			return val;
 
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index d18f9f903db..617f0958e16 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -999,7 +999,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
 
 static void mld_gq_start_timer(struct inet6_dev *idev)
 {
-	unsigned long tv = net_random() % idev->mc_maxdelay;
+	unsigned long tv = prandom_u32() % idev->mc_maxdelay;
 
 	idev->mc_gq_running = 1;
 	if (!mod_timer(&idev->mc_gq_timer, jiffies+tv+2))
@@ -1015,7 +1015,7 @@ static void mld_gq_stop_timer(struct inet6_dev *idev)
 
 static void mld_ifc_start_timer(struct inet6_dev *idev, unsigned long delay)
 {
-	unsigned long tv = net_random() % delay;
+	unsigned long tv = prandom_u32() % delay;
 
 	if (!mod_timer(&idev->mc_ifc_timer, jiffies+tv+2))
 		in6_dev_hold(idev);
@@ -1030,7 +1030,7 @@ static void mld_ifc_stop_timer(struct inet6_dev *idev)
 
 static void mld_dad_start_timer(struct inet6_dev *idev, unsigned long delay)
 {
-	unsigned long tv = net_random() % delay;
+	unsigned long tv = prandom_u32() % delay;
 
 	if (!mod_timer(&idev->mc_dad_timer, jiffies+tv+2))
 		in6_dev_hold(idev);
@@ -1061,7 +1061,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime)
 	}
 
 	if (delay >= resptime)
-		delay = net_random() % resptime;
+		delay = prandom_u32() % resptime;
 
 	ma->mca_timer.expires = jiffies + delay;
 	if (!mod_timer(&ma->mca_timer, jiffies + delay))
@@ -1301,8 +1301,17 @@ int igmp6_event_query(struct sk_buff *skb)
 	len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr);
 	len -= skb_network_header_len(skb);
 
-	/* Drop queries with not link local source */
-	if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL))
+	/* RFC3810 6.2
+	 * Upon reception of an MLD message that contains a Query, the node
+	 * checks if the source address of the message is a valid link-local
+	 * address, if the Hop Limit is set to 1, and if the Router Alert
+	 * option is present in the Hop-By-Hop Options header of the IPv6
+	 * packet.  If any of these checks fails, the packet is dropped.
+	 */
+	if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL) ||
+	    ipv6_hdr(skb)->hop_limit != 1 ||
+	    !(IP6CB(skb)->flags & IP6SKB_ROUTERALERT) ||
+	    IP6CB(skb)->ra != htons(IPV6_OPT_ROUTERALERT_MLD))
 		return -EINVAL;
 
 	idev = __in6_dev_get(skb->dev);
@@ -1620,11 +1629,12 @@ static void mld_sendpack(struct sk_buff *skb)
 		      dst_output);
 out:
 	if (!err) {
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
-	} else
-		IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS);
+		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
+		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
+	} else {
+		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+	}
 
 	rcu_read_unlock();
 	return;
@@ -1665,7 +1675,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 	skb_tailroom(skb)) : 0)
 
 static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
-	int type, int gdeleted, int sdeleted)
+	int type, int gdeleted, int sdeleted, int crsend)
 {
 	struct inet6_dev *idev = pmc->idev;
 	struct net_device *dev = idev->dev;
@@ -1757,7 +1767,7 @@ empty_source:
 		if (type == MLD2_ALLOW_NEW_SOURCES ||
 		    type == MLD2_BLOCK_OLD_SOURCES)
 			return skb;
-		if (pmc->mca_crcount || isquery) {
+		if (pmc->mca_crcount || isquery || crsend) {
 			/* make sure we have room for group header */
 			if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)) {
 				mld_sendpack(skb);
@@ -1789,7 +1799,7 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc)
 				type = MLD2_MODE_IS_EXCLUDE;
 			else
 				type = MLD2_MODE_IS_INCLUDE;
-			skb = add_grec(skb, pmc, type, 0, 0);
+			skb = add_grec(skb, pmc, type, 0, 0, 0);
 			spin_unlock_bh(&pmc->mca_lock);
 		}
 	} else {
@@ -1798,7 +1808,7 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc)
 			type = MLD2_MODE_IS_EXCLUDE;
 		else
 			type = MLD2_MODE_IS_INCLUDE;
-		skb = add_grec(skb, pmc, type, 0, 0);
+		skb = add_grec(skb, pmc, type, 0, 0, 0);
 		spin_unlock_bh(&pmc->mca_lock);
 	}
 	read_unlock_bh(&idev->lock);
@@ -1843,13 +1853,13 @@ static void mld_send_cr(struct inet6_dev *idev)
 		if (pmc->mca_sfmode == MCAST_INCLUDE) {
 			type = MLD2_BLOCK_OLD_SOURCES;
 			dtype = MLD2_BLOCK_OLD_SOURCES;
-			skb = add_grec(skb, pmc, type, 1, 0);
-			skb = add_grec(skb, pmc, dtype, 1, 1);
+			skb = add_grec(skb, pmc, type, 1, 0, 0);
+			skb = add_grec(skb, pmc, dtype, 1, 1, 0);
 		}
 		if (pmc->mca_crcount) {
 			if (pmc->mca_sfmode == MCAST_EXCLUDE) {
 				type = MLD2_CHANGE_TO_INCLUDE;
-				skb = add_grec(skb, pmc, type, 1, 0);
+				skb = add_grec(skb, pmc, type, 1, 0, 0);
 			}
 			pmc->mca_crcount--;
 			if (pmc->mca_crcount == 0) {
@@ -1880,8 +1890,8 @@ static void mld_send_cr(struct inet6_dev *idev)
 			type = MLD2_ALLOW_NEW_SOURCES;
 			dtype = MLD2_BLOCK_OLD_SOURCES;
 		}
-		skb = add_grec(skb, pmc, type, 0, 0);
-		skb = add_grec(skb, pmc, dtype, 0, 1);	/* deleted sources */
+		skb = add_grec(skb, pmc, type, 0, 0, 0);
+		skb = add_grec(skb, pmc, dtype, 0, 1, 0);	/* deleted sources */
 
 		/* filter mode changes */
 		if (pmc->mca_crcount) {
@@ -1889,7 +1899,7 @@ static void mld_send_cr(struct inet6_dev *idev)
 				type = MLD2_CHANGE_TO_EXCLUDE;
 			else
 				type = MLD2_CHANGE_TO_INCLUDE;
-			skb = add_grec(skb, pmc, type, 0, 0);
+			skb = add_grec(skb, pmc, type, 0, 0, 0);
 			pmc->mca_crcount--;
 		}
 		spin_unlock_bh(&pmc->mca_lock);
@@ -1997,27 +2007,36 @@ err_out:
 	goto out;
 }
 
-static void mld_resend_report(struct inet6_dev *idev)
+static void mld_send_initial_cr(struct inet6_dev *idev)
 {
-	if (mld_in_v1_mode(idev)) {
-		struct ifmcaddr6 *mcaddr;
-		read_lock_bh(&idev->lock);
-		for (mcaddr = idev->mc_list; mcaddr; mcaddr = mcaddr->next) {
-			if (!(mcaddr->mca_flags & MAF_NOREPORT))
-				igmp6_send(&mcaddr->mca_addr, idev->dev,
-					   ICMPV6_MGM_REPORT);
-		}
-		read_unlock_bh(&idev->lock);
-	} else {
-		mld_send_report(idev, NULL);
+	struct sk_buff *skb;
+	struct ifmcaddr6 *pmc;
+	int type;
+
+	if (mld_in_v1_mode(idev))
+		return;
+
+	skb = NULL;
+	read_lock_bh(&idev->lock);
+	for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+		spin_lock_bh(&pmc->mca_lock);
+		if (pmc->mca_sfcount[MCAST_EXCLUDE])
+			type = MLD2_CHANGE_TO_EXCLUDE;
+		else
+			type = MLD2_CHANGE_TO_INCLUDE;
+		skb = add_grec(skb, pmc, type, 0, 0, 1);
+		spin_unlock_bh(&pmc->mca_lock);
 	}
+	read_unlock_bh(&idev->lock);
+	if (skb)
+		mld_sendpack(skb);
 }
 
 void ipv6_mc_dad_complete(struct inet6_dev *idev)
 {
 	idev->mc_dad_count = idev->mc_qrv;
 	if (idev->mc_dad_count) {
-		mld_resend_report(idev);
+		mld_send_initial_cr(idev);
 		idev->mc_dad_count--;
 		if (idev->mc_dad_count)
 			mld_dad_start_timer(idev, idev->mc_maxdelay);
@@ -2028,7 +2047,7 @@ static void mld_dad_timer_expire(unsigned long data)
 {
 	struct inet6_dev *idev = (struct inet6_dev *)data;
 
-	mld_resend_report(idev);
+	mld_send_initial_cr(idev);
 	if (idev->mc_dad_count) {
 		idev->mc_dad_count--;
 		if (idev->mc_dad_count)
@@ -2328,7 +2347,7 @@ static void igmp6_join_group(struct ifmcaddr6 *ma)
 
 	igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT);
 
-	delay = net_random() % unsolicited_report_interval(ma->idev);
+	delay = prandom_u32() % unsolicited_report_interval(ma->idev);
 
 	spin_lock_bh(&ma->mca_lock);
 	if (del_timer(&ma->mca_timer)) {
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 09a22f4f36c..ca8d4ea48a5 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -851,7 +851,7 @@ out:
 static void ndisc_recv_na(struct sk_buff *skb)
 {
 	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
-	const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
+	struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
 	const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
 	u8 *lladdr = NULL;
 	u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
@@ -944,10 +944,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
 			/*
 			 * Change: router to host
 			 */
-			struct rt6_info *rt;
-			rt = rt6_get_dflt_router(saddr, dev);
-			if (rt)
-				ip6_del_rt(rt);
+			rt6_clean_tohost(dev_net(dev),  saddr);
 		}
 
 out:
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 95f3f1da0d7..d38e6a8d8b9 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb)
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 	};
+	int err;
 
 	dst = ip6_route_output(net, skb->sk, &fl6);
-	if (dst->error) {
+	err = dst->error;
+	if (err) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 		LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
 		dst_release(dst);
-		return dst->error;
+		return err;
 	}
 
 	/* Drop old route. */
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 7702f9e90a0..4bff1f297e3 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -28,15 +28,32 @@ config NF_CONNTRACK_IPV6
 config NF_TABLES_IPV6
 	depends on NF_TABLES
 	tristate "IPv6 nf_tables support"
+	help
+	  This option enables the IPv6 support for nf_tables.
 
 config NFT_CHAIN_ROUTE_IPV6
 	depends on NF_TABLES_IPV6
 	tristate "IPv6 nf_tables route chain support"
+	help
+	  This option enables the "route" chain for IPv6 in nf_tables. This
+	  chain type is used to force packet re-routing after mangling header
+	  fields such as the source, destination, flowlabel, hop-limit and
+	  the packet mark.
 
 config NFT_CHAIN_NAT_IPV6
 	depends on NF_TABLES_IPV6
 	depends on NF_NAT_IPV6 && NFT_NAT
 	tristate "IPv6 nf_tables nat chain support"
+	help
+	  This option enables the "nat" chain for IPv6 in nf_tables. This
+	  chain type is used to perform Network Address Translation (NAT)
+	  packet transformations such as the source, destination address and
+	  source and destination ports.
+
+config NFT_REJECT_IPV6
+	depends on NF_TABLES_IPV6
+	default NFT_REJECT
+	tristate
 
 config IP6_NF_IPTABLES
 	tristate "IP6 tables support (required for filtering)"
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index d1b4928f34f..70d3dd66f2c 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
 obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
+obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 710238f58aa..e080fbbbc0e 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1241,8 +1241,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 
 	xt_free_table_info(oldinfo);
 	if (copy_to_user(counters_ptr, counters,
-			 sizeof(struct xt_counters) * num_counters) != 0)
-		ret = -EFAULT;
+			 sizeof(struct xt_counters) * num_counters) != 0) {
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n");
+	}
 	vfree(counters);
 	xt_table_unlock(t);
 	return ret;
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index da00a2ecde5..544b0a9da1b 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -23,181 +23,18 @@
 #include <linux/skbuff.h>
 #include <linux/icmpv6.h>
 #include <linux/netdevice.h>
-#include <net/ipv6.h>
-#include <net/tcp.h>
 #include <net/icmp.h>
-#include <net/ip6_checksum.h>
-#include <net/ip6_fib.h>
-#include <net/ip6_route.h>
 #include <net/flow.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #include <linux/netfilter_ipv6/ip6t_REJECT.h>
 
+#include <net/netfilter/ipv6/nf_reject.h>
+
 MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>");
 MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6");
 MODULE_LICENSE("GPL");
 
-/* Send RST reply */
-static void send_reset(struct net *net, struct sk_buff *oldskb, int hook)
-{
-	struct sk_buff *nskb;
-	struct tcphdr otcph, *tcph;
-	unsigned int otcplen, hh_len;
-	int tcphoff, needs_ack;
-	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
-	struct ipv6hdr *ip6h;
-#define DEFAULT_TOS_VALUE	0x0U
-	const __u8 tclass = DEFAULT_TOS_VALUE;
-	struct dst_entry *dst = NULL;
-	u8 proto;
-	__be16 frag_off;
-	struct flowi6 fl6;
-
-	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
-	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
-		pr_debug("addr is not unicast.\n");
-		return;
-	}
-
-	proto = oip6h->nexthdr;
-	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
-
-	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
-		pr_debug("Cannot get TCP header.\n");
-		return;
-	}
-
-	otcplen = oldskb->len - tcphoff;
-
-	/* IP header checks: fragment, too short. */
-	if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
-		pr_debug("proto(%d) != IPPROTO_TCP, "
-			 "or too short. otcplen = %d\n",
-			 proto, otcplen);
-		return;
-	}
-
-	if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
-		BUG();
-
-	/* No RST for RST. */
-	if (otcph.rst) {
-		pr_debug("RST is set\n");
-		return;
-	}
-
-	/* Check checksum. */
-	if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) {
-		pr_debug("TCP checksum is invalid\n");
-		return;
-	}
-
-	memset(&fl6, 0, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_TCP;
-	fl6.saddr = oip6h->daddr;
-	fl6.daddr = oip6h->saddr;
-	fl6.fl6_sport = otcph.dest;
-	fl6.fl6_dport = otcph.source;
-	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst == NULL || dst->error) {
-		dst_release(dst);
-		return;
-	}
-	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
-	if (IS_ERR(dst))
-		return;
-
-	hh_len = (dst->dev->hard_header_len + 15)&~15;
-	nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
-			 + sizeof(struct tcphdr) + dst->trailer_len,
-			 GFP_ATOMIC);
-
-	if (!nskb) {
-		net_dbg_ratelimited("cannot alloc skb\n");
-		dst_release(dst);
-		return;
-	}
-
-	skb_dst_set(nskb, dst);
-
-	skb_reserve(nskb, hh_len + dst->header_len);
-
-	skb_put(nskb, sizeof(struct ipv6hdr));
-	skb_reset_network_header(nskb);
-	ip6h = ipv6_hdr(nskb);
-	ip6_flow_hdr(ip6h, tclass, 0);
-	ip6h->hop_limit = ip6_dst_hoplimit(dst);
-	ip6h->nexthdr = IPPROTO_TCP;
-	ip6h->saddr = oip6h->daddr;
-	ip6h->daddr = oip6h->saddr;
-
-	skb_reset_transport_header(nskb);
-	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
-	/* Truncate to length (no data) */
-	tcph->doff = sizeof(struct tcphdr)/4;
-	tcph->source = otcph.dest;
-	tcph->dest = otcph.source;
-
-	if (otcph.ack) {
-		needs_ack = 0;
-		tcph->seq = otcph.ack_seq;
-		tcph->ack_seq = 0;
-	} else {
-		needs_ack = 1;
-		tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin
-				      + otcplen - (otcph.doff<<2));
-		tcph->seq = 0;
-	}
-
-	/* Reset flags */
-	((u_int8_t *)tcph)[13] = 0;
-	tcph->rst = 1;
-	tcph->ack = needs_ack;
-	tcph->window = 0;
-	tcph->urg_ptr = 0;
-	tcph->check = 0;
-
-	/* Adjust TCP checksum */
-	tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
-				      &ipv6_hdr(nskb)->daddr,
-				      sizeof(struct tcphdr), IPPROTO_TCP,
-				      csum_partial(tcph,
-						   sizeof(struct tcphdr), 0));
-
-	nf_ct_attach(nskb, oldskb);
-
-#ifdef CONFIG_BRIDGE_NETFILTER
-	/* If we use ip6_local_out for bridged traffic, the MAC source on
-	 * the RST will be ours, instead of the destination's.  This confuses
-	 * some routers/firewalls, and they drop the packet.  So we need to
-	 * build the eth header using the original destination's MAC as the
-	 * source, and send the RST packet directly.
-	 */
-	if (oldskb->nf_bridge) {
-		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
-		nskb->protocol = htons(ETH_P_IPV6);
-		ip6h->payload_len = htons(sizeof(struct tcphdr));
-		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
-				    oeth->h_source, oeth->h_dest, nskb->len) < 0)
-			return;
-		dev_queue_xmit(nskb);
-	} else
-#endif
-		ip6_local_out(nskb);
-}
-
-static inline void
-send_unreach(struct net *net, struct sk_buff *skb_in, unsigned char code,
-	     unsigned int hooknum)
-{
-	if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
-		skb_in->dev = net->loopback_dev;
-
-	icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
-}
 
 static unsigned int
 reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
@@ -208,25 +45,25 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 	pr_debug("%s: medium point\n", __func__);
 	switch (reject->with) {
 	case IP6T_ICMP6_NO_ROUTE:
-		send_unreach(net, skb, ICMPV6_NOROUTE, par->hooknum);
+		nf_send_unreach6(net, skb, ICMPV6_NOROUTE, par->hooknum);
 		break;
 	case IP6T_ICMP6_ADM_PROHIBITED:
-		send_unreach(net, skb, ICMPV6_ADM_PROHIBITED, par->hooknum);
+		nf_send_unreach6(net, skb, ICMPV6_ADM_PROHIBITED, par->hooknum);
 		break;
 	case IP6T_ICMP6_NOT_NEIGHBOUR:
-		send_unreach(net, skb, ICMPV6_NOT_NEIGHBOUR, par->hooknum);
+		nf_send_unreach6(net, skb, ICMPV6_NOT_NEIGHBOUR, par->hooknum);
 		break;
 	case IP6T_ICMP6_ADDR_UNREACH:
-		send_unreach(net, skb, ICMPV6_ADDR_UNREACH, par->hooknum);
+		nf_send_unreach6(net, skb, ICMPV6_ADDR_UNREACH, par->hooknum);
 		break;
 	case IP6T_ICMP6_PORT_UNREACH:
-		send_unreach(net, skb, ICMPV6_PORT_UNREACH, par->hooknum);
+		nf_send_unreach6(net, skb, ICMPV6_PORT_UNREACH, par->hooknum);
 		break;
 	case IP6T_ICMP6_ECHOREPLY:
 		/* Do nothing */
 		break;
 	case IP6T_TCP_RESET:
-		send_reset(net, skb, par->hooknum);
+		nf_send_reset6(net, skb, par->hooknum);
 		break;
 	default:
 		net_info_ratelimited("case %u not handled yet\n", reject->with);
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index f78f41aca8e..a0d17270117 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -446,6 +446,7 @@ static void synproxy_tg6_destroy(const struct xt_tgdtor_param *par)
 static struct xt_target synproxy_tg6_reg __read_mostly = {
 	.name		= "SYNPROXY",
 	.family		= NFPROTO_IPV6,
+	.hooks		= (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD),
 	.target		= synproxy_tg6,
 	.targetsize	= sizeof(struct xt_synproxy_info),
 	.checkentry	= synproxy_tg6_check,
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index e0983f3648a..790e0c6b19e 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -33,6 +33,7 @@ static bool rpfilter_lookup_reverse6(const struct sk_buff *skb,
 	struct ipv6hdr *iph = ipv6_hdr(skb);
 	bool ret = false;
 	struct flowi6 fl6 = {
+		.flowi6_iif = LOOPBACK_IFINDEX,
 		.flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK,
 		.flowi6_proto = iph->nexthdr,
 		.daddr = iph->saddr,
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 84c7f33d0cf..387d8b8fc18 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -90,17 +90,9 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
 	if (nf_ct_is_untracked(ct))
 		return NF_ACCEPT;
 
-	nat = nfct_nat(ct);
-	if (!nat) {
-		/* NAT module was loaded late. */
-		if (nf_ct_is_confirmed(ct))
-			return NF_ACCEPT;
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL) {
-			pr_debug("failed to add NAT extension\n");
-			return NF_ACCEPT;
-		}
-	}
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 767ab8da821..0d5279fd852 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -451,7 +451,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
 	}
 	sub_frag_mem_limit(&fq->q, head->truesize);
 
-	head->local_df = 1;
+	head->ignore_df = 1;
 	head->next = NULL;
 	head->dev = dev;
 	head->tstamp = fq->q.stamp;
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
index d77db8a1350..0d812b31277 100644
--- a/net/ipv6/netfilter/nf_tables_ipv6.c
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -16,34 +16,51 @@
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_ipv6.h>
 
+static unsigned int nft_do_chain_ipv6(const struct nf_hook_ops *ops,
+				      struct sk_buff *skb,
+				      const struct net_device *in,
+				      const struct net_device *out,
+				      int (*okfn)(struct sk_buff *))
+{
+	struct nft_pktinfo pkt;
+
+	/* malformed packet, drop it */
+	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
+		return NF_DROP;
+
+	return nft_do_chain(&pkt, ops);
+}
+
 static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops,
 				    struct sk_buff *skb,
 				    const struct net_device *in,
 				    const struct net_device *out,
 				    int (*okfn)(struct sk_buff *))
 {
-	struct nft_pktinfo pkt;
-
 	if (unlikely(skb->len < sizeof(struct ipv6hdr))) {
 		if (net_ratelimit())
 			pr_info("nf_tables_ipv6: ignoring short SOCK_RAW "
 				"packet\n");
 		return NF_ACCEPT;
 	}
-	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
-		return NF_DROP;
 
-	return nft_do_chain_pktinfo(&pkt, ops);
+	return nft_do_chain_ipv6(ops, skb, in, out, okfn);
 }
 
-static struct nft_af_info nft_af_ipv6 __read_mostly = {
+struct nft_af_info nft_af_ipv6 __read_mostly = {
 	.family		= NFPROTO_IPV6,
 	.nhooks		= NF_INET_NUMHOOKS,
 	.owner		= THIS_MODULE,
+	.nops		= 1,
 	.hooks		= {
+		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv6,
 		[NF_INET_LOCAL_OUT]	= nft_ipv6_output,
+		[NF_INET_FORWARD]	= nft_do_chain_ipv6,
+		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv6,
+		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv6,
 	},
 };
+EXPORT_SYMBOL_GPL(nft_af_ipv6);
 
 static int nf_tables_ipv6_init_net(struct net *net)
 {
@@ -73,44 +90,28 @@ static struct pernet_operations nf_tables_ipv6_net_ops = {
 	.exit	= nf_tables_ipv6_exit_net,
 };
 
-static unsigned int
-nft_do_chain_ipv6(const struct nf_hook_ops *ops,
-		  struct sk_buff *skb,
-		  const struct net_device *in,
-		  const struct net_device *out,
-		  int (*okfn)(struct sk_buff *))
-{
-	struct nft_pktinfo pkt;
-
-	/* malformed packet, drop it */
-	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
-		return NF_DROP;
-
-	return nft_do_chain_pktinfo(&pkt, ops);
-}
-
-static struct nf_chain_type filter_ipv6 = {
-	.family		= NFPROTO_IPV6,
+static const struct nf_chain_type filter_ipv6 = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_IPV6,
+	.owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
 			  (1 << NF_INET_LOCAL_OUT) |
 			  (1 << NF_INET_FORWARD) |
 			  (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_POST_ROUTING),
-	.fn		= {
-		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv6,
-		[NF_INET_LOCAL_OUT]	= nft_ipv6_output,
-		[NF_INET_FORWARD]	= nft_do_chain_ipv6,
-		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv6,
-		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv6,
-	},
 };
 
 static int __init nf_tables_ipv6_init(void)
 {
+	int ret;
+
 	nft_register_chain_type(&filter_ipv6);
-	return register_pernet_subsys(&nf_tables_ipv6_net_ops);
+	ret = register_pernet_subsys(&nf_tables_ipv6_net_ops);
+	if (ret < 0)
+		nft_unregister_chain_type(&filter_ipv6);
+
+	return ret;
 }
 
 static void __exit nf_tables_ipv6_exit(void)
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
index e86dcd70dc7..d189fcb437f 100644
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -47,15 +47,9 @@ static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
 	if (ct == NULL || nf_ct_is_untracked(ct))
 		return NF_ACCEPT;
 
-	nat = nfct_nat(ct);
-	if (nat == NULL) {
-		/* Conntrack module was loaded late, can't add extension. */
-		if (nf_ct_is_confirmed(ct))
-			return NF_ACCEPT;
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL)
-			return NF_ACCEPT;
-	}
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
@@ -79,7 +73,7 @@ static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
 
 		nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out);
 
-		ret = nft_do_chain_pktinfo(&pkt, ops);
+		ret = nft_do_chain(&pkt, ops);
 		if (ret != NF_ACCEPT)
 			return ret;
 		if (!nf_nat_initialized(ct, maniptype)) {
@@ -170,21 +164,21 @@ static unsigned int nf_nat_ipv6_output(const struct nf_hook_ops *ops,
 	return ret;
 }
 
-static struct nf_chain_type nft_chain_nat_ipv6 = {
-	.family		= NFPROTO_IPV6,
+static const struct nf_chain_type nft_chain_nat_ipv6 = {
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,
+	.family		= NFPROTO_IPV6,
+	.owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_POST_ROUTING) |
 			  (1 << NF_INET_LOCAL_OUT) |
 			  (1 << NF_INET_LOCAL_IN),
-	.fn		= {
+	.hooks		= {
 		[NF_INET_PRE_ROUTING]	= nf_nat_ipv6_prerouting,
 		[NF_INET_POST_ROUTING]	= nf_nat_ipv6_postrouting,
 		[NF_INET_LOCAL_OUT]	= nf_nat_ipv6_output,
 		[NF_INET_LOCAL_IN]	= nf_nat_ipv6_fn,
 	},
-	.me		= THIS_MODULE,
 };
 
 static int __init nft_chain_nat_ipv6_init(void)
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
index 3fe40f0456a..42031299585 100644
--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c
@@ -47,7 +47,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 	/* flowlabel and prio (includes version, which shouldn't change either */
 	flowlabel = *((u32 *)ipv6_hdr(skb));
 
-	ret = nft_do_chain_pktinfo(&pkt, ops);
+	ret = nft_do_chain(&pkt, ops);
 	if (ret != NF_DROP && ret != NF_QUEUE &&
 	    (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
 	     memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
@@ -59,15 +59,15 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 	return ret;
 }
 
-static struct nf_chain_type nft_chain_route_ipv6 = {
-	.family		= NFPROTO_IPV6,
+static const struct nf_chain_type nft_chain_route_ipv6 = {
 	.name		= "route",
 	.type		= NFT_CHAIN_T_ROUTE,
+	.family		= NFPROTO_IPV6,
+        .owner		= THIS_MODULE,
 	.hook_mask	= (1 << NF_INET_LOCAL_OUT),
-	.fn		= {
+	.hooks		= {
                 [NF_INET_LOCAL_OUT]	= nf_route_table_hook,
         },
-        .me		= THIS_MODULE,
 };
 
 static int __init nft_chain_route_init(void)
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
new file mode 100644
index 00000000000..0bc19fa8782
--- /dev/null
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
+
+void nft_reject_ipv6_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt)
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+	struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+		nf_send_unreach6(net, pkt->skb, priv->icmp_code,
+				 pkt->ops->hooknum);
+		break;
+	case NFT_REJECT_TCP_RST:
+		nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
+		break;
+	}
+
+	data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nft_reject_ipv6_eval);
+
+static struct nft_expr_type nft_reject_ipv6_type;
+static const struct nft_expr_ops nft_reject_ipv6_ops = {
+	.type		= &nft_reject_ipv6_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+	.eval		= nft_reject_ipv6_eval,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_ipv6_type __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.name		= "reject",
+	.ops		= &nft_reject_ipv6_ops,
+	.policy		= nft_reject_policy,
+	.maxattr	= NFTA_REJECT_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_reject_ipv6_module_init(void)
+{
+	return nft_register_expr(&nft_reject_ipv6_type);
+}
+
+static void __exit nft_reject_ipv6_module_exit(void)
+{
+	nft_unregister_expr(&nft_reject_ipv6_type);
+}
+
+module_init(nft_reject_ipv6_module_init);
+module_exit(nft_reject_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject");
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 827f795209c..5ec867e4a8b 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -6,35 +6,7 @@
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
 #include <net/addrconf.h>
-
-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
-	static atomic_t ipv6_fragmentation_id;
-	int old, new;
-
-#if IS_ENABLED(CONFIG_IPV6)
-	if (rt && !(rt->dst.flags & DST_NOPEER)) {
-		struct inet_peer *peer;
-		struct net *net;
-
-		net = dev_net(rt->dst.dev);
-		peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
-		if (peer) {
-			fhdr->identification = htonl(inet_getid(peer, 0));
-			inet_putpeer(peer);
-			return;
-		}
-	}
-#endif
-	do {
-		old = atomic_read(&ipv6_fragmentation_id);
-		new = old + 1;
-		if (!new)
-			new = 1;
-	} while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old);
-	fhdr->identification = htonl(new);
-}
-EXPORT_SYMBOL(ipv6_select_ident);
+#include <net/secure_seq.h>
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
@@ -106,6 +78,7 @@ int __ip6_local_out(struct sk_buff *skb)
 	if (len > IPV6_MAXPLEN)
 		len = 0;
 	ipv6_hdr(skb)->payload_len = htons(len);
+	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
 	return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
 		       skb_dst(skb)->dev, dst_output);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index a83243c3d65..5b7a1ed2aba 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -31,7 +31,7 @@ struct proto pingv6_prot = {
 	.owner =	THIS_MODULE,
 	.init =		ping_init_sock,
 	.close =	ping_close,
-	.connect =	ip6_datagram_connect,
+	.connect =	ip6_datagram_connect_v6_only,
 	.disconnect =	udp_disconnect,
 	.setsockopt =	ipv6_setsockopt,
 	.getsockopt =	ipv6_getsockopt,
@@ -51,7 +51,6 @@ static struct inet_protosw pingv6_protosw = {
 	.protocol =  IPPROTO_ICMPV6,
 	.prot =      &pingv6_prot,
 	.ops =       &inet6_dgram_ops,
-	.no_check =  UDP_CSUM_DEFAULT,
 	.flags =     INET_PROTOSW_REUSE,
 };
 
@@ -62,10 +61,9 @@ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
 {
 	return -EAFNOSUPPORT;
 }
-static int dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
+static void dummy_ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
 				       struct sk_buff *skb)
 {
-	return -EAFNOSUPPORT;
 }
 static int dummy_icmpv6_err_convert(u8 type, u8 code, int *err)
 {
@@ -103,7 +101,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		return err;
 
 	if (msg->msg_name) {
-		struct sockaddr_in6 *u = (struct sockaddr_in6 *) msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name);
 		if (msg->msg_namelen < sizeof(struct sockaddr_in6) ||
 		    u->sin6_family != AF_INET6) {
 			return -EINVAL;
@@ -136,6 +134,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	fl6.flowi6_proto = IPPROTO_ICMPV6;
 	fl6.saddr = np->saddr;
 	fl6.daddr = *daddr;
+	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_icmp_type = user_icmph.icmp6_type;
 	fl6.fl6_icmp_code = user_icmph.icmp6_code;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
@@ -145,7 +144,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
-	dst = ip6_sk_dst_lookup_flow(sk, &fl6,  daddr, 1);
+	dst = ip6_sk_dst_lookup_flow(sk, &fl6,  daddr);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
 	rt = (struct rt6_info *) dst;
@@ -168,12 +167,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	pfh.wcheck = 0;
 	pfh.family = AF_INET6;
 
-	if (ipv6_addr_is_multicast(&fl6.daddr))
-		hlimit = np->mcast_hops;
-	else
-		hlimit = np->hop_limit;
-	if (hlimit < 0)
-		hlimit = ip6_dst_hoplimit(dst);
+	hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	lock_sock(sk);
 	err = ip6_append_data(sk, ping_getfrag, &pfh, len,
@@ -182,8 +176,8 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			      MSG_DONTWAIT, np->dontfrag);
 
 	if (err) {
-		ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev,
-				   ICMP6_MIB_OUTERRORS);
+		ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev,
+				ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
 		err = icmpv6_push_pending_frames(sk, &fl6,
@@ -254,7 +248,9 @@ int __init pingv6_init(void)
 		return ret;
 #endif
 	pingv6_ops.ipv6_recv_error = ipv6_recv_error;
-	pingv6_ops.ip6_datagram_recv_ctl = ip6_datagram_recv_ctl;
+	pingv6_ops.ip6_datagram_recv_common_ctl = ip6_datagram_recv_common_ctl;
+	pingv6_ops.ip6_datagram_recv_specific_ctl =
+		ip6_datagram_recv_specific_ctl;
 	pingv6_ops.icmpv6_err_convert = icmpv6_err_convert;
 	pingv6_ops.ipv6_icmp_error = ipv6_icmp_error;
 	pingv6_ops.ipv6_chk_addr = ipv6_chk_addr;
@@ -267,7 +263,8 @@ int __init pingv6_init(void)
 void pingv6_exit(void)
 {
 	pingv6_ops.ipv6_recv_error = dummy_ipv6_recv_error;
-	pingv6_ops.ip6_datagram_recv_ctl = dummy_ip6_datagram_recv_ctl;
+	pingv6_ops.ip6_datagram_recv_common_ctl = dummy_ip6_datagram_recv_ctl;
+	pingv6_ops.ip6_datagram_recv_specific_ctl = dummy_ip6_datagram_recv_ctl;
 	pingv6_ops.icmpv6_err_convert = dummy_icmpv6_err_convert;
 	pingv6_ops.ipv6_icmp_error = dummy_ipv6_icmp_error;
 	pingv6_ops.ipv6_chk_addr = dummy_ipv6_chk_addr;
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 091d066a57b..3317440ea34 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -186,7 +186,7 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, atomic_long_t *smib)
 /* can be called either with percpu mib (pcpumib != NULL),
  * or shared one (smib != NULL)
  */
-static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **pcpumib,
+static void snmp6_seq_show_item(struct seq_file *seq, void __percpu *pcpumib,
 				atomic_long_t *smib,
 				const struct snmp_mib *itemlist)
 {
@@ -201,7 +201,7 @@ static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **pcpumib,
 	}
 }
 
-static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu **mib,
+static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib,
 				  const struct snmp_mib *itemlist, size_t syncpoff)
 {
 	int i;
@@ -215,14 +215,14 @@ static int snmp6_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = (struct net *)seq->private;
 
-	snmp6_seq_show_item64(seq, (void __percpu **)net->mib.ipv6_statistics,
+	snmp6_seq_show_item64(seq, net->mib.ipv6_statistics,
 			    snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp));
-	snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics,
+	snmp6_seq_show_item(seq, net->mib.icmpv6_statistics,
 			    NULL, snmp6_icmp6_list);
 	snmp6_seq_show_icmpv6msg(seq, net->mib.icmpv6msg_statistics->mibs);
-	snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6,
+	snmp6_seq_show_item(seq, net->mib.udp_stats_in6,
 			    NULL, snmp6_udp6_list);
-	snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6,
+	snmp6_seq_show_item(seq, net->mib.udplite_stats_in6,
 			    NULL, snmp6_udplite6_list);
 	return 0;
 }
@@ -245,7 +245,7 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v)
 	struct inet6_dev *idev = (struct inet6_dev *)seq->private;
 
 	seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex);
-	snmp6_seq_show_item64(seq, (void __percpu **)idev->stats.ipv6,
+	snmp6_seq_show_item64(seq, idev->stats.ipv6,
 			    snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp));
 	snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs,
 			    snmp6_icmp6_list);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 7fb4e14c467..b2dc60b0c76 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -250,6 +250,10 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	if (addr_len < SIN6_LEN_RFC2133)
 		return -EINVAL;
+
+	if (addr->sin6_family != AF_INET6)
+		return -EINVAL;
+
 	addr_type = ipv6_addr_type(&addr->sin6_addr);
 
 	/* Raw sockets are IPv6 only */
@@ -457,7 +461,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 		  int noblock, int flags, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct sk_buff *skb;
 	size_t copied;
 	int err;
@@ -734,7 +738,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		   struct msghdr *msg, size_t len)
 {
 	struct ipv6_txoptions opt_space;
-	struct sockaddr_in6 * sin6 = (struct sockaddr_in6 *) msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -792,7 +796,6 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 				flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 				if (flowlabel == NULL)
 					return -EINVAL;
-				daddr = &flowlabel->dst;
 			}
 		}
 
@@ -865,19 +868,13 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		fl6.flowi6_oif = np->ucast_oif;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto out;
 	}
-	if (hlimit < 0) {
-		if (ipv6_addr_is_multicast(&fl6.daddr))
-			hlimit = np->mcast_hops;
-		else
-			hlimit = np->hop_limit;
-		if (hlimit < 0)
-			hlimit = ip6_dst_hoplimit(dst);
-	}
+	if (hlimit < 0)
+		hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	if (tclass < 0)
 		tclass = np->tclass;
@@ -1210,7 +1207,7 @@ struct proto rawv6_prot = {
 	.owner		   = THIS_MODULE,
 	.close		   = rawv6_close,
 	.destroy	   = raw6_destroy,
-	.connect	   = ip6_datagram_connect,
+	.connect	   = ip6_datagram_connect_v6_only,
 	.disconnect	   = udp_disconnect,
 	.ioctl		   = rawv6_ioctl,
 	.init		   = rawv6_init_sk,
@@ -1325,7 +1322,6 @@ static struct inet_protosw rawv6_protosw = {
 	.protocol	= IPPROTO_IP,	/* wild card */
 	.prot		= &rawv6_prot,
 	.ops		= &inet6_sockraw_ops,
-	.no_check	= UDP_CSUM_DEFAULT,
 	.flags		= INET_PROTOSW_REUSE,
 };
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ddb9d41c8ee..f23fbd28a50 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -66,8 +66,9 @@
 #endif
 
 enum rt6_nud_state {
-	RT6_NUD_FAIL_HARD = -2,
-	RT6_NUD_FAIL_SOFT = -1,
+	RT6_NUD_FAIL_HARD = -3,
+	RT6_NUD_FAIL_PROBE = -2,
+	RT6_NUD_FAIL_DO_RR = -1,
 	RT6_NUD_SUCCEED = 1
 };
 
@@ -83,9 +84,9 @@ static void		ip6_dst_ifdown(struct dst_entry *,
 static int		 ip6_dst_gc(struct dst_ops *ops);
 
 static int		ip6_pkt_discard(struct sk_buff *skb);
-static int		ip6_pkt_discard_out(struct sk_buff *skb);
+static int		ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb);
 static int		ip6_pkt_prohibit(struct sk_buff *skb);
-static int		ip6_pkt_prohibit_out(struct sk_buff *skb);
+static int		ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
 static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 					   struct sk_buff *skb, u32 mtu);
@@ -103,6 +104,36 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 					   const struct in6_addr *gwaddr, int ifindex);
 #endif
 
+static void rt6_bind_peer(struct rt6_info *rt, int create)
+{
+	struct inet_peer_base *base;
+	struct inet_peer *peer;
+
+	base = inetpeer_base_ptr(rt->_rt6i_peer);
+	if (!base)
+		return;
+
+	peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
+	if (peer) {
+		if (!rt6_set_peer(rt, peer))
+			inet_putpeer(peer);
+	}
+}
+
+static struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create)
+{
+	if (rt6_has_peer(rt))
+		return rt6_peer_ptr(rt);
+
+	rt6_bind_peer(rt, create);
+	return (rt6_has_peer(rt) ? rt6_peer_ptr(rt) : NULL);
+}
+
+static struct inet_peer *rt6_get_peer_create(struct rt6_info *rt)
+{
+	return __rt6_get_peer(rt, 1);
+}
+
 static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
 {
 	struct rt6_info *rt = (struct rt6_info *) dst;
@@ -118,7 +149,8 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
 		unsigned long prev, new;
 
 		p = peer->metrics;
-		if (inet_metrics_new(peer))
+		if (inet_metrics_new(peer) ||
+		    (old & DST_METRICS_FORCE_OVERWRITE))
 			memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
 
 		new = (unsigned long) p;
@@ -258,7 +290,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
 		.obsolete	= DST_OBSOLETE_FORCE_CHK,
 		.error		= -EINVAL,
 		.input		= dst_discard,
-		.output		= dst_discard,
+		.output		= dst_discard_sk,
 	},
 	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
 	.rt6i_protocol  = RTPROT_KERNEL,
@@ -311,22 +343,6 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 	}
 }
 
-void rt6_bind_peer(struct rt6_info *rt, int create)
-{
-	struct inet_peer_base *base;
-	struct inet_peer *peer;
-
-	base = inetpeer_base_ptr(rt->_rt6i_peer);
-	if (!base)
-		return;
-
-	peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
-	if (peer) {
-		if (!rt6_set_peer(rt, peer))
-			inet_putpeer(peer);
-	}
-}
-
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 			   int how)
 {
@@ -358,12 +374,6 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 	return false;
 }
 
-static bool rt6_need_strict(const struct in6_addr *daddr)
-{
-	return ipv6_addr_type(daddr) &
-		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
-}
-
 /* Multipath route selection:
  *   Hash based function using packet header and flowlabel.
  * Adapted from fib_info_hashfn()
@@ -521,7 +531,7 @@ static void rt6_probe(struct rt6_info *rt)
 		work = kmalloc(sizeof(*work), GFP_ATOMIC);
 
 		if (neigh && work)
-			neigh->updated = jiffies;
+			__neigh_set_probe_once(neigh);
 
 		if (neigh)
 			write_unlock(&neigh->lock);
@@ -577,11 +587,13 @@ static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt)
 #ifdef CONFIG_IPV6_ROUTER_PREF
 		else if (!(neigh->nud_state & NUD_FAILED))
 			ret = RT6_NUD_SUCCEED;
+		else
+			ret = RT6_NUD_FAIL_PROBE;
 #endif
 		read_unlock(&neigh->lock);
 	} else {
 		ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ?
-		      RT6_NUD_SUCCEED : RT6_NUD_FAIL_SOFT;
+		      RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR;
 	}
 	rcu_read_unlock_bh();
 
@@ -618,16 +630,17 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
 		goto out;
 
 	m = rt6_score_route(rt, oif, strict);
-	if (m == RT6_NUD_FAIL_SOFT) {
+	if (m == RT6_NUD_FAIL_DO_RR) {
 		match_do_rr = true;
 		m = 0; /* lowest valid score */
-	} else if (m < 0) {
+	} else if (m == RT6_NUD_FAIL_HARD) {
 		goto out;
 	}
 
 	if (strict & RT6_LOOKUP_F_REACHABLE)
 		rt6_probe(rt);
 
+	/* note that m can be RT6_NUD_FAIL_PROBE at this point */
 	if (m > *mpri) {
 		*do_rr = match_do_rr;
 		*mpri = m;
@@ -839,14 +852,15 @@ EXPORT_SYMBOL(rt6_lookup);
    be destroyed.
  */
 
-static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info)
+static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
+			struct nlattr *mx, int mx_len)
 {
 	int err;
 	struct fib6_table *table;
 
 	table = rt->rt6i_table;
 	write_lock_bh(&table->tb6_lock);
-	err = fib6_add(&table->tb6_root, rt, info);
+	err = fib6_add(&table->tb6_root, rt, info, mx, mx_len);
 	write_unlock_bh(&table->tb6_lock);
 
 	return err;
@@ -857,7 +871,7 @@ int ip6_ins_rt(struct rt6_info *rt)
 	struct nl_info info = {
 		.nl_net = dev_net(rt->dst.dev),
 	};
-	return __ip6_ins_rt(rt, &info);
+	return __ip6_ins_rt(rt, &info, NULL, 0);
 }
 
 static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
@@ -1044,7 +1058,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 
 		new->__use = 1;
 		new->input = dst_discard;
-		new->output = dst_discard;
+		new->output = dst_discard_sk;
 
 		if (dst_metrics_read_only(&ort->dst))
 			new->_metrics = ort->dst._metrics;
@@ -1162,7 +1176,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_oif = oif;
-	fl6.flowi6_mark = mark;
+	fl6.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark);
 	fl6.daddr = iph->daddr;
 	fl6.saddr = iph->saddr;
 	fl6.flowlabel = ip6_flowinfo(iph);
@@ -1259,6 +1273,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
 	struct flowi6 fl6;
 
 	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_iif = LOOPBACK_IFINDEX;
 	fl6.flowi6_oif = oif;
 	fl6.flowi6_mark = mark;
 	fl6.daddr = iph->daddr;
@@ -1280,6 +1295,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
 	struct flowi6 fl6;
 
 	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_iif = LOOPBACK_IFINDEX;
 	fl6.flowi6_oif = oif;
 	fl6.flowi6_mark = mark;
 	fl6.daddr = msg->dest;
@@ -1324,7 +1340,7 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
 	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
 
 	if (mtu)
-		return mtu;
+		goto out;
 
 	mtu = IPV6_MIN_MTU;
 
@@ -1334,7 +1350,8 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
 		mtu = idev->cnf.mtu6;
 	rcu_read_unlock();
 
-	return mtu;
+out:
+	return min_t(unsigned int, mtu, IP6_MAX_MTU);
 }
 
 static struct dst_entry *icmp6_dst_gc_list;
@@ -1438,7 +1455,7 @@ static int ip6_dst_gc(struct dst_ops *ops)
 		goto out;
 
 	net->ipv6.ip6_rt_gc_expire++;
-	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, entries > rt_max_size);
+	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true);
 	entries = dst_entries_get_slow(ops);
 	if (entries < ops->gc_thresh)
 		net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
@@ -1495,7 +1512,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	if (!table)
 		goto out;
 
-	rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
+	rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table);
 
 	if (!rt) {
 		err = -ENOMEM;
@@ -1525,17 +1542,11 @@ int ip6_route_add(struct fib6_config *cfg)
 
 	ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
 	rt->rt6i_dst.plen = cfg->fc_dst_len;
-	if (rt->rt6i_dst.plen == 128)
-	       rt->dst.flags |= DST_HOST;
-
-	if (!(rt->dst.flags & DST_HOST) && cfg->fc_mx) {
-		u32 *metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
-		if (!metrics) {
-			err = -ENOMEM;
-			goto out;
-		}
-		dst_init_metrics(&rt->dst, metrics, 0);
+	if (rt->rt6i_dst.plen == 128) {
+		rt->dst.flags |= DST_HOST;
+		dst_metrics_set_force_overwrite(&rt->dst);
 	}
+
 #ifdef CONFIG_IPV6_SUBTREES
 	ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
 	rt->rt6i_src.plen = cfg->fc_src_len;
@@ -1568,7 +1579,7 @@ int ip6_route_add(struct fib6_config *cfg)
 		switch (cfg->fc_type) {
 		case RTN_BLACKHOLE:
 			rt->dst.error = -EINVAL;
-			rt->dst.output = dst_discard;
+			rt->dst.output = dst_discard_sk;
 			rt->dst.input = dst_discard;
 			break;
 		case RTN_PROHIBIT:
@@ -1654,31 +1665,13 @@ int ip6_route_add(struct fib6_config *cfg)
 	rt->rt6i_flags = cfg->fc_flags;
 
 install_route:
-	if (cfg->fc_mx) {
-		struct nlattr *nla;
-		int remaining;
-
-		nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
-			int type = nla_type(nla);
-
-			if (type) {
-				if (type > RTAX_MAX) {
-					err = -EINVAL;
-					goto out;
-				}
-
-				dst_metric_set(&rt->dst, type, nla_get_u32(nla));
-			}
-		}
-	}
-
 	rt->dst.dev = dev;
 	rt->rt6i_idev = idev;
 	rt->rt6i_table = table;
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
-	return __ip6_ins_rt(rt, &cfg->fc_nlinfo);
+	return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len);
 
 out:
 	if (dev)
@@ -1905,9 +1898,7 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 		else
 			rt->rt6i_gateway = *dest;
 		rt->rt6i_flags = ort->rt6i_flags;
-		if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
-		    (RTF_DEFAULT | RTF_ADDRCONF))
-			rt6_set_from(rt, ort);
+		rt6_set_from(rt, ort);
 		rt->rt6i_metric = 0;
 
 #ifdef CONFIG_IPV6_SUBTREES
@@ -2140,7 +2131,7 @@ static int ip6_pkt_discard(struct sk_buff *skb)
 	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES);
 }
 
-static int ip6_pkt_discard_out(struct sk_buff *skb)
+static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb)
 {
 	skb->dev = skb_dst(skb)->dev;
 	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
@@ -2151,7 +2142,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb)
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
 }
 
-static int ip6_pkt_prohibit_out(struct sk_buff *skb)
+static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb)
 {
 	skb->dev = skb_dst(skb)->dev;
 	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
@@ -2166,12 +2157,10 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    bool anycast)
 {
 	struct net *net = dev_net(idev->dev);
-	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL);
-
-	if (!rt) {
-		net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n");
+	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
+					    DST_NOCOUNT, NULL);
+	if (!rt)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	in6_dev_hold(idev);
 
@@ -2242,7 +2231,28 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 		.net = net,
 		.addr = &ifp->addr,
 	};
-	fib6_clean_all(net, fib6_remove_prefsrc, 0, &adni);
+	fib6_clean_all(net, fib6_remove_prefsrc, &adni);
+}
+
+#define RTF_RA_ROUTER		(RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
+#define RTF_CACHE_GATEWAY	(RTF_GATEWAY | RTF_CACHE)
+
+/* Remove routers and update dst entries when gateway turn into host. */
+static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
+{
+	struct in6_addr *gateway = (struct in6_addr *)arg;
+
+	if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) ||
+	     ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) &&
+	     ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
+		return -1;
+	}
+	return 0;
+}
+
+void rt6_clean_tohost(struct net *net, struct in6_addr *gateway)
+{
+	fib6_clean_all(net, fib6_clean_tohost, gateway);
 }
 
 struct arg_dev_net {
@@ -2269,7 +2279,7 @@ void rt6_ifdown(struct net *net, struct net_device *dev)
 		.net = net,
 	};
 
-	fib6_clean_all(net, fib6_ifdown, 0, &adn);
+	fib6_clean_all(net, fib6_ifdown, &adn);
 	icmp6_clean_all(fib6_ifdown, &adn);
 }
 
@@ -2324,7 +2334,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
 		.mtu = mtu,
 	};
 
-	fib6_clean_all(dev_net(dev), rt6_mtu_change_route, 0, &arg);
+	fib6_clean_all(dev_net(dev), rt6_mtu_change_route, &arg);
 }
 
 static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
@@ -2720,6 +2730,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh)
 	if (tb[RTA_OIF])
 		oif = nla_get_u32(tb[RTA_OIF]);
 
+	if (tb[RTA_MARK])
+		fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+
 	if (iif) {
 		struct net_device *dev;
 		int flags = 0;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 366fbba3359..4f408176dc6 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -475,6 +475,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
 		ipip6_tunnel_unlink(sitn, tunnel);
 		ipip6_tunnel_del_prl(tunnel, NULL);
 	}
+	ip_tunnel_dst_reset_all(tunnel);
 	dev_put(dev);
 }
 
@@ -559,12 +560,12 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPV6, 0);
+				 t->parms.link, 0, IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
@@ -671,7 +672,7 @@ static int ipip6_rcv(struct sk_buff *skb)
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
 				     iph->saddr, iph->daddr);
 	if (tunnel != NULL) {
-		struct pcpu_tstats *tstats;
+		struct pcpu_sw_netstats *tstats;
 
 		if (tunnel->parms.iph.protocol != IPPROTO_IPV6 &&
 		    tunnel->parms.iph.protocol != 0)
@@ -702,8 +703,10 @@ static int ipip6_rcv(struct sk_buff *skb)
 		}
 
 		tstats = this_cpu_ptr(tunnel->dev->tstats);
+		u64_stats_update_begin(&tstats->syncp);
 		tstats->rx_packets++;
 		tstats->rx_bytes += skb->len;
+		u64_stats_update_end(&tstats->syncp);
 
 		netif_rx(skb);
 
@@ -924,7 +927,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		if (tunnel->parms.iph.daddr && skb_dst(skb))
 			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
-		if (skb->len > mtu) {
+		if (skb->len > mtu && !skb_is_gso(skb)) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 			ip_rt_put(rt);
 			goto tx_error;
@@ -966,11 +969,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
 
 	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT);
-	if (IS_ERR(skb))
+	if (IS_ERR(skb)) {
+		ip_rt_put(rt);
 		goto out;
+	}
 
-	err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, IPPROTO_IPV6, tos,
-			    ttl, df, !net_eq(tunnel->net, dev_net(dev)));
+	err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr,
+			    IPPROTO_IPV6, tos, ttl, df,
+			    !net_eq(tunnel->net, dev_net(dev)));
 	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 	return NETDEV_TX_OK;
 
@@ -1078,6 +1084,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
 		t->parms.link = p->link;
 		ipip6_tunnel_bind_dev(t->dev);
 	}
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(t->dev);
 }
 
@@ -1108,6 +1115,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
 	t->ip6rd.relay_prefix = relay_prefix;
 	t->ip6rd.prefixlen = ip6rd->prefixlen;
 	t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen;
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(t->dev);
 	return 0;
 }
@@ -1119,8 +1127,8 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 	int err = 0;
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_prl prl;
-	struct ip_tunnel *t;
-	struct net *net = dev_net(dev);
+	struct ip_tunnel *t = netdev_priv(dev);
+	struct net *net = t->net;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel_6rd ip6rd;
@@ -1131,16 +1139,15 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 #ifdef CONFIG_IPV6_SIT_6RD
 	case SIOCGET6RD:
 #endif
-		t = NULL;
 		if (dev == sitn->fb_tunnel_dev) {
 			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
 				err = -EFAULT;
 				break;
 			}
 			t = ipip6_tunnel_locate(net, &p, 0);
+			if (t == NULL)
+				t = netdev_priv(dev);
 		}
-		if (t == NULL)
-			t = netdev_priv(dev);
 
 		err = -EFAULT;
 		if (cmd == SIOCGETTUNNEL) {
@@ -1236,9 +1243,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		err = -EINVAL;
 		if (dev == sitn->fb_tunnel_dev)
 			goto done;
-		err = -ENOENT;
-		if (!(t = netdev_priv(dev)))
-			goto done;
 		err = ipip6_tunnel_get_prl(t, ifr->ifr_ifru.ifru_data);
 		break;
 
@@ -1254,9 +1258,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		err = -EFAULT;
 		if (copy_from_user(&prl, ifr->ifr_ifru.ifru_data, sizeof(prl)))
 			goto done;
-		err = -ENOENT;
-		if (!(t = netdev_priv(dev)))
-			goto done;
 
 		switch (cmd) {
 		case SIOCDELPRL:
@@ -1267,6 +1268,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 			err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
 			break;
 		}
+		ip_tunnel_dst_reset_all(t);
 		netdev_state_change(dev);
 		break;
 
@@ -1283,8 +1285,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 				   sizeof(ip6rd)))
 			goto done;
 
-		t = netdev_priv(dev);
-
 		if (cmd != SIOCDEL6RD) {
 			err = ipip6_tunnel_update_6rd(t, &ip6rd);
 			if (err < 0)
@@ -1322,6 +1322,9 @@ static const struct net_device_ops ipip6_netdev_ops = {
 
 static void ipip6_dev_free(struct net_device *dev)
 {
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+
+	free_percpu(tunnel->dst_cache);
 	free_percpu(dev->tstats);
 	free_netdev(dev);
 }
@@ -1352,7 +1355,6 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 static int ipip6_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	int i;
 
 	tunnel->dev = dev;
 	tunnel->net = dev_net(dev);
@@ -1361,14 +1363,14 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
 
 	ipip6_tunnel_bind_dev(dev);
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_tstats *ipip6_tunnel_stats;
-		ipip6_tunnel_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ipip6_tunnel_stats->syncp);
+	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+	if (!tunnel->dst_cache) {
+		free_percpu(dev->tstats);
+		return -ENOMEM;
 	}
 
 	return 0;
@@ -1380,7 +1382,6 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 	struct iphdr *iph = &tunnel->parms.iph;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
-	int i;
 
 	tunnel->dev = dev;
 	tunnel->net = dev_net(dev);
@@ -1391,14 +1392,14 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 	iph->ihl		= 5;
 	iph->ttl		= 64;
 
-	dev->tstats = alloc_percpu(struct pcpu_tstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_tstats *ipip6_fb_stats;
-		ipip6_fb_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ipip6_fb_stats->syncp);
+	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
+	if (!tunnel->dst_cache) {
+		free_percpu(dev->tstats);
+		return -ENOMEM;
 	}
 
 	dev_hold(dev);
@@ -1827,4 +1828,5 @@ xfrm_tunnel_failed:
 module_init(sit_init);
 module_exit(sit_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("sit");
 MODULE_ALIAS_NETDEV("sit0");
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 535a3ad262f..a822b880689 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -216,6 +216,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
 		ireq->ir_iif = inet6_iif(skb);
 
+	ireq->ir_mark = inet_request_mark(sk, skb);
+
 	req->expires = 0UL;
 	req->num_retrans = 0;
 	ireq->ecn_ok		= ecn_ok;
@@ -242,12 +244,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		final_p = fl6_update_dst(&fl6, np->opt, &final);
 		fl6.saddr = ireq->ir_v6_loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
-		fl6.flowi6_mark = sk->sk_mark;
+		fl6.flowi6_mark = ireq->ir_mark;
 		fl6.fl6_dport = ireq->ir_rmt_port;
 		fl6.fl6_sport = inet_sk(sk)->inet_sport;
 		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
-		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
+		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 		if (IS_ERR(dst))
 			goto out_free;
 	}
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 107b2f1d90a..058f3eca2e5 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -24,6 +24,27 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "anycast_src_echo_reply",
+		.data		= &init_net.ipv6.sysctl.anycast_src_echo_reply,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "flowlabel_consistency",
+		.data		= &init_net.ipv6.sysctl.flowlabel_consistency,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "fwmark_reflect",
+		.data		= &init_net.ipv6.sysctl.fwmark_reflect,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 	{ }
 };
 
@@ -51,6 +72,8 @@ static int __net_init ipv6_sysctl_net_init(struct net *net)
 	if (!ipv6_table)
 		goto out;
 	ipv6_table[0].data = &net->ipv6.sysctl.bindv6only;
+	ipv6_table[1].data = &net->ipv6.sysctl.anycast_src_echo_reply;
+	ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency;
 
 	ipv6_route_table = ipv6_route_sysctl_init(net);
 	if (!ipv6_route_table)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 0740f93a114..229239ad96b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -39,7 +39,7 @@
 #include <linux/ipsec.h>
 #include <linux/times.h>
 #include <linux/slab.h>
-
+#include <linux/uaccess.h>
 #include <linux/ipv6.h>
 #include <linux/icmpv6.h>
 #include <linux/random.h>
@@ -65,8 +65,6 @@
 #include <net/tcp_memcontrol.h>
 #include <net/busy_poll.h>
 
-#include <asm/uaccess.h>
-
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
@@ -156,7 +154,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
-			usin->sin6_addr = flowlabel->dst;
 			fl6_sock_release(flowlabel);
 		}
 	}
@@ -165,12 +162,12 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	 *	connect() to INADDR_ANY means loopback (BSD'ism).
 	 */
 
-	if(ipv6_addr_any(&usin->sin6_addr))
+	if (ipv6_addr_any(&usin->sin6_addr))
 		usin->sin6_addr.s6_addr[15] = 0x1;
 
 	addr_type = ipv6_addr_type(&usin->sin6_addr);
 
-	if(addr_type & IPV6_ADDR_MULTICAST)
+	if (addr_type & IPV6_ADDR_MULTICAST)
 		return -ENETUNREACH;
 
 	if (addr_type&IPV6_ADDR_LINKLOCAL) {
@@ -258,7 +255,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto failure;
@@ -337,13 +334,14 @@ static void tcp_v6_mtu_reduced(struct sock *sk)
 static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		u8 type, u8 code, int offset, __be32 info)
 {
-	const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data;
+	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
 	const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
 	struct ipv6_pinfo *np;
 	struct sock *sk;
 	int err;
 	struct tcp_sock *tp;
-	__u32 seq;
+	struct request_sock *fastopen;
+	__u32 seq, snd_una;
 	struct net *net = dev_net(skb->dev);
 
 	sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr,
@@ -374,8 +372,11 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	tp = tcp_sk(sk);
 	seq = ntohl(th->seq);
+	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
+	fastopen = tp->fastopen_rsk;
+	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
-	    !between(seq, tp->snd_una, tp->snd_nxt)) {
+	    !between(seq, snd_una, tp->snd_nxt)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 		goto out;
 	}
@@ -398,6 +399,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (sk->sk_state == TCP_LISTEN)
 			goto out;
 
+		if (!ip6_sk_accept_pmtu(sk))
+			goto out;
+
 		tp->mtu_info = ntohl(info);
 		if (!sock_owned_by_user(sk))
 			tcp_v6_mtu_reduced(sk);
@@ -436,8 +440,13 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		goto out;
 
 	case TCP_SYN_SENT:
-	case TCP_SYN_RECV:  /* Cannot happen.
-			       It can, it SYNs are crossed. --ANK */
+	case TCP_SYN_RECV:
+		/* Only in fast or simultaneous open. If a fast open socket is
+		 * is already accepted it is treated as a connected one below.
+		 */
+		if (fastopen && fastopen->sk == NULL)
+			break;
+
 		if (!sock_owned_by_user(sk)) {
 			sk->sk_err = err;
 			sk->sk_error_report(sk);		/* Wake people up to see the error (see connect in sock.c) */
@@ -463,24 +472,28 @@ out:
 static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			      struct flowi6 *fl6,
 			      struct request_sock *req,
-			      u16 queue_mapping)
+			      u16 queue_mapping,
+			      struct tcp_fastopen_cookie *foc)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct sk_buff * skb;
+	struct sk_buff *skb;
 	int err = -ENOMEM;
 
 	/* First, grab a route. */
 	if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL)
 		goto done;
 
-	skb = tcp_make_synack(sk, dst, req, NULL);
+	skb = tcp_make_synack(sk, dst, req, foc);
 
 	if (skb) {
 		__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
 				    &ireq->ir_v6_rmt_addr);
 
 		fl6->daddr = ireq->ir_v6_rmt_addr;
+		if (np->repflow && (ireq->pktopts != NULL))
+			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
+
 		skb_set_queue_mapping(skb, queue_mapping);
 		err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
 		err = net_xmit_eval(err);
@@ -495,9 +508,11 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req)
 	struct flowi6 fl6;
 	int res;
 
-	res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0);
-	if (!res)
+	res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0, NULL);
+	if (!res) {
 		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+	}
 	return res;
 }
 
@@ -525,8 +540,8 @@ static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk,
 	return tcp_v6_md5_do_lookup(sk, &inet_rsk(req)->ir_v6_rmt_addr);
 }
 
-static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
-				  int optlen)
+static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval,
+				 int optlen)
 {
 	struct tcp_md5sig cmd;
 	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
@@ -710,7 +725,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
 	.send_ack	=	tcp_v6_reqsk_send_ack,
 	.destructor	=	tcp_v6_reqsk_destructor,
 	.send_reset	=	tcp_v6_send_reset,
-	.syn_ack_timeout = 	tcp_syn_ack_timeout,
+	.syn_ack_timeout =	tcp_syn_ack_timeout,
 };
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -721,8 +736,9 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 #endif
 
 static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
-				 u32 tsval, u32 tsecr,
-				 struct tcp_md5sig_key *key, int rst, u8 tclass)
+				 u32 tsval, u32 tsecr, int oif,
+				 struct tcp_md5sig_key *key, int rst, u8 tclass,
+				 u32 label)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct tcphdr *t1;
@@ -784,6 +800,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.daddr = ipv6_hdr(skb)->saddr;
 	fl6.saddr = ipv6_hdr(skb)->daddr;
+	fl6.flowlabel = label;
 
 	buff->ip_summed = CHECKSUM_PARTIAL;
 	buff->csum = 0;
@@ -791,8 +808,11 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 	__tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr);
 
 	fl6.flowi6_proto = IPPROTO_TCP;
-	if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
+	if (rt6_need_strict(&fl6.daddr) && !oif)
 		fl6.flowi6_oif = inet6_iif(skb);
+	else
+		fl6.flowi6_oif = oif;
+	fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
 	fl6.fl6_dport = t1->dest;
 	fl6.fl6_sport = t1->source;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
@@ -801,7 +821,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 	 * Underlying function will use this to retrieve the network
 	 * namespace
 	 */
-	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL, false);
+	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
 		ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass);
@@ -826,6 +846,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 	int genhash;
 	struct sock *sk1 = NULL;
 #endif
+	int oif;
 
 	if (th->rst)
 		return;
@@ -869,7 +890,8 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 		ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len -
 			  (th->doff << 2);
 
-	tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, key, 1, 0);
+	oif = sk ? sk->sk_bound_dev_if : 0;
+	tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
 
 #ifdef CONFIG_TCP_MD5SIG
 release_sk1:
@@ -881,10 +903,12 @@ release_sk1:
 }
 
 static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
-			    u32 win, u32 tsval, u32 tsecr,
-			    struct tcp_md5sig_key *key, u8 tclass)
+			    u32 win, u32 tsval, u32 tsecr, int oif,
+			    struct tcp_md5sig_key *key, u8 tclass,
+			    u32 label)
 {
-	tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, key, 0, tclass);
+	tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, oif, key, 0, tclass,
+			     label);
 }
 
 static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
@@ -895,8 +919,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
-			tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw),
-			tw->tw_tclass);
+			tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
+			tw->tw_tclass, (tw->tw_flowlabel << 12));
 
 	inet_twsk_put(tw);
 }
@@ -904,13 +928,19 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req)
 {
-	tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1,
-			req->rcv_wnd, tcp_time_stamp, req->ts_recent,
-			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0);
+	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
+	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
+	 */
+	tcp_v6_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
+			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+			tcp_rsk(req)->rcv_nxt,
+			req->rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
+			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
+			0, 0);
 }
 
 
-static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
+static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb)
 {
 	struct request_sock *req, **prev;
 	const struct tcphdr *th = tcp_hdr(skb);
@@ -955,8 +985,10 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	__u32 isn = TCP_SKB_CB(skb)->when;
 	struct dst_entry *dst = NULL;
+	struct tcp_fastopen_cookie foc = { .len = -1 };
+	bool want_cookie = false, fastopen;
 	struct flowi6 fl6;
-	bool want_cookie = false;
+	int err;
 
 	if (skb->protocol == htons(ETH_P_IP))
 		return tcp_v4_conn_request(sk, skb);
@@ -987,7 +1019,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_clear_options(&tmp_opt);
 	tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 	tmp_opt.user_mss = tp->rx_opt.user_mss;
-	tcp_parse_options(skb, &tmp_opt, 0, NULL);
+	tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);
 
 	if (want_cookie && !tmp_opt.saw_tstamp)
 		tcp_clear_options(&tmp_opt);
@@ -1002,6 +1034,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		TCP_ECN_create_request(req, skb, sock_net(sk));
 
 	ireq->ir_iif = sk->sk_bound_dev_if;
+	ireq->ir_mark = inet_request_mark(sk, skb);
 
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
@@ -1011,7 +1044,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (!isn) {
 		if (ipv6_opt_accepted(sk, skb) ||
 		    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
-		    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
+		    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim ||
+		    np->repflow) {
 			atomic_inc(&skb->users);
 			ireq->pktopts = skb;
 		}
@@ -1059,19 +1093,27 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		isn = tcp_v6_init_sequence(skb);
 	}
 have_isn:
-	tcp_rsk(req)->snt_isn = isn;
 
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_release;
 
-	if (tcp_v6_send_synack(sk, dst, &fl6, req,
-			       skb_get_queue_mapping(skb)) ||
-	    want_cookie)
+	if (!dst && (dst = inet6_csk_route_req(sk, &fl6, req)) == NULL)
 		goto drop_and_free;
 
+	tcp_rsk(req)->snt_isn = isn;
 	tcp_rsk(req)->snt_synack = tcp_time_stamp;
-	tcp_rsk(req)->listener = NULL;
-	inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+	tcp_openreq_init_rwin(req, sk, dst);
+	fastopen = !want_cookie &&
+		   tcp_try_fastopen(sk, skb, req, &foc, dst);
+	err = tcp_v6_send_synack(sk, dst, &fl6, req,
+				 skb_get_queue_mapping(skb), &foc);
+	if (!fastopen) {
+		if (err || want_cookie)
+			goto drop_and_free;
+
+		tcp_rsk(req)->listener = NULL;
+		inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+	}
 	return 0;
 
 drop_and_release:
@@ -1083,9 +1125,9 @@ drop:
 	return 0; /* don't send reset */
 }
 
-static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
-					  struct request_sock *req,
-					  struct dst_entry *dst)
+static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
+					 struct request_sock *req,
+					 struct dst_entry *dst)
 {
 	struct inet_request_sock *ireq;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
@@ -1135,7 +1177,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		newnp->opt	   = NULL;
 		newnp->mcast_oif   = inet6_iif(skb);
 		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
-		newnp->rcv_tclass  = ipv6_get_dsfield(ipv6_hdr(skb));
+		newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+		if (np->repflow)
+			newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
 
 		/*
 		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
@@ -1215,7 +1259,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newnp->opt	  = NULL;
 	newnp->mcast_oif  = inet6_iif(skb);
 	newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
-	newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb));
+	newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+	if (np->repflow)
+		newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
 
 	/* Clone native IPv6 options from listening socket (if any)
 
@@ -1231,7 +1277,6 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
 						     newnp->opt->opt_flen);
 
-	tcp_mtup_init(newsk);
 	tcp_sync_mss(newsk, dst_mtu(dst));
 	newtp->advmss = dst_metric_advmss(dst);
 	if (tcp_sk(sk)->rx_opt.user_mss &&
@@ -1245,7 +1290,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Copy over the MD5 key from the original socket */
-	if ((key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr)) != NULL) {
+	key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr);
+	if (key != NULL) {
 		/* We're using one, so create a matching key
 		 * on the newsk structure. If we fail to get
 		 * memory, then we end up not copying the key
@@ -1275,26 +1321,6 @@ out:
 	return NULL;
 }
 
-static __sum16 tcp_v6_checksum_init(struct sk_buff *skb)
-{
-	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		if (!tcp_v6_check(skb->len, &ipv6_hdr(skb)->saddr,
-				  &ipv6_hdr(skb)->daddr, skb->csum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			return 0;
-		}
-	}
-
-	skb->csum = ~csum_unfold(tcp_v6_check(skb->len,
-					      &ipv6_hdr(skb)->saddr,
-					      &ipv6_hdr(skb)->daddr, 0));
-
-	if (skb->len <= 76) {
-		return __skb_checksum_complete(skb);
-	}
-	return 0;
-}
-
 /* The socket must have it's spinlock held when we get
  * here.
  *
@@ -1321,7 +1347,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		return tcp_v4_do_rcv(sk, skb);
 
 #ifdef CONFIG_TCP_MD5SIG
-	if (tcp_v6_inbound_md5_hash (sk, skb))
+	if (tcp_v6_inbound_md5_hash(sk, skb))
 		goto discard;
 #endif
 
@@ -1380,7 +1406,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		 * otherwise we just shortcircuit this and continue with
 		 * the new socket..
 		 */
-		if(nsk != sk) {
+		if (nsk != sk) {
 			sock_rps_save_rxhash(nsk, skb);
 			if (tcp_child_process(sk, nsk, skb))
 				goto reset;
@@ -1425,8 +1451,10 @@ ipv6_pktoptions:
 			np->mcast_oif = inet6_iif(opt_skb);
 		if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
 			np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
-		if (np->rxopt.bits.rxtclass)
-			np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(opt_skb));
+		if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass)
+			np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb));
+		if (np->repflow)
+			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
 		if (ipv6_opt_accepted(sk, opt_skb)) {
 			skb_set_owner_r(opt_skb, sk);
 			opt_skb = xchg(&np->pktoptions, opt_skb);
@@ -1466,7 +1494,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	if (!pskb_may_pull(skb, th->doff*4))
 		goto discard_it;
 
-	if (!skb_csum_unnecessary(skb) && tcp_v6_checksum_init(skb))
+	if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo))
 		goto csum_error;
 
 	th = tcp_hdr(skb);
@@ -1586,7 +1614,8 @@ do_time_wait:
 		break;
 	case TCP_TW_RST:
 		goto no_tcp_socket;
-	case TCP_TW_SUCCESS:;
+	case TCP_TW_SUCCESS:
+		;
 	}
 	goto discard_it;
 }
@@ -1631,7 +1660,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
 static struct timewait_sock_ops tcp6_timewait_sock_ops = {
 	.twsk_obj_size	= sizeof(struct tcp6_timewait_sock),
 	.twsk_unique	= tcp_twsk_unique,
-	.twsk_destructor= tcp_twsk_destructor,
+	.twsk_destructor = tcp_twsk_destructor,
 };
 
 static const struct inet_connection_sock_af_ops ipv6_specific = {
@@ -1665,7 +1694,6 @@ static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = {
 /*
  *	TCP over IPv4 via INET6 API
  */
-
 static const struct inet_connection_sock_af_ops ipv6_mapped = {
 	.queue_xmit	   = ip_queue_xmit,
 	.send_check	   = tcp_v4_send_check,
@@ -1740,7 +1768,7 @@ static void get_openreq6(struct seq_file *seq,
 		   dest->s6_addr32[2], dest->s6_addr32[3],
 		   ntohs(inet_rsk(req)->ir_rmt_port),
 		   TCP_SYN_RECV,
-		   0,0, /* could print option size, but that is af dependent. */
+		   0, 0, /* could print option size, but that is af dependent. */
 		   1,   /* timers active (only the expire timer) */
 		   jiffies_to_clock_t(ttd),
 		   req->num_timeout,
@@ -1759,6 +1787,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	const struct inet_sock *inet = inet_sk(sp);
 	const struct tcp_sock *tp = tcp_sk(sp);
 	const struct inet_connection_sock *icsk = inet_csk(sp);
+	struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq;
 
 	dest  = &sp->sk_v6_daddr;
 	src   = &sp->sk_v6_rcv_saddr;
@@ -1799,9 +1828,11 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 		   atomic_read(&sp->sk_refcnt), sp,
 		   jiffies_to_clock_t(icsk->icsk_rto),
 		   jiffies_to_clock_t(icsk->icsk_ack.ato),
-		   (icsk->icsk_ack.quick << 1 ) | icsk->icsk_ack.pingpong,
+		   (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
 		   tp->snd_cwnd,
-		   tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh
+		   sp->sk_state == TCP_LISTEN ?
+			(fastopenq ? fastopenq->max_qlen : 0) :
+			(tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)
 		   );
 }
 
@@ -1961,7 +1992,6 @@ static struct inet_protosw tcpv6_protosw = {
 	.protocol	=	IPPROTO_TCP,
 	.prot		=	&tcpv6_prot,
 	.ops		=	&inet6_stream_ops,
-	.no_check	=	0,
 	.flags		=	INET_PROTOSW_PERMANENT |
 				INET_PROTOSW_ICSK,
 };
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 6d18157dc32..01b0ff9a0c2 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -42,7 +42,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
 	if (NAPI_GRO_CB(skb)->flush)
 		goto skip_csum;
 
-	wsum = skb->csum;
+	wsum = NAPI_GRO_CB(skb)->csum;
 
 	switch (skb->ip_summed) {
 	case CHECKSUM_NONE:
@@ -66,14 +66,14 @@ skip_csum:
 	return tcp_gro_receive(head, skb);
 }
 
-static int tcp6_gro_complete(struct sk_buff *skb)
+static int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
 
-	th->check = ~tcp_v6_check(skb->len - skb_transport_offset(skb),
-				  &iph->saddr, &iph->daddr, 0);
-	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+	th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr,
+				  &iph->daddr, 0);
+	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6;
 
 	return tcp_gro_complete(skb);
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index bcd5699313c..7092ff78fd8 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -460,9 +460,7 @@ try_again:
 
 	/* Copy the address. */
 	if (msg->msg_name) {
-		struct sockaddr_in6 *sin6;
-
-		sin6 = (struct sockaddr_in6 *) msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 		sin6->sin6_family = AF_INET6;
 		sin6->sin6_port = udp_hdr(skb)->source;
 		sin6->sin6_flowinfo = 0;
@@ -479,12 +477,16 @@ try_again:
 		}
 		*addr_len = sizeof(*sin6);
 	}
+
+	if (np->rxopt.all)
+		ip6_datagram_recv_common_ctl(sk, msg, skb);
+
 	if (is_udp4) {
 		if (inet->cmsg_flags)
 			ip_cmsg_recv(msg, skb);
 	} else {
 		if (np->rxopt.all)
-			ip6_datagram_recv_ctl(sk, msg, skb);
+			ip6_datagram_recv_specific_ctl(sk, msg, skb);
 	}
 
 	err = copied;
@@ -538,8 +540,11 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (sk == NULL)
 		return;
 
-	if (type == ICMPV6_PKT_TOOBIG)
+	if (type == ICMPV6_PKT_TOOBIG) {
+		if (!ip6_sk_accept_pmtu(sk))
+			goto out;
 		ip6_sk_update_pmtu(skb, sk, info);
+	}
 	if (type == NDISC_REDIRECT) {
 		ip6_sk_redirect(skb, sk);
 		goto out;
@@ -629,6 +634,10 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) {
 			int ret;
 
+			/* Verify checksum before giving to encap */
+			if (udp_lib_checksum_complete(skb))
+				goto csum_error;
+
 			ret = encap_rcv(sk, skb);
 			if (ret <= 0) {
 				UDP_INC_STATS_BH(sock_net(sk),
@@ -665,8 +674,11 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 			goto csum_error;
 	}
 
-	if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf))
+	if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) {
+		UDP6_INC_STATS_BH(sock_net(sk),
+				  UDP_MIB_RCVBUFERRORS, is_udplite);
 		goto drop;
+	}
 
 	skb_dst_drop(skb);
 
@@ -681,6 +693,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	bh_unlock_sock(sk);
 
 	return rc;
+
 csum_error:
 	UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
 drop:
@@ -696,17 +709,16 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
 				      int dif)
 {
 	struct hlist_nulls_node *node;
-	struct sock *s = sk;
 	unsigned short num = ntohs(loc_port);
 
-	sk_nulls_for_each_from(s, node) {
-		struct inet_sock *inet = inet_sk(s);
+	sk_nulls_for_each_from(sk, node) {
+		struct inet_sock *inet = inet_sk(sk);
 
-		if (!net_eq(sock_net(s), net))
+		if (!net_eq(sock_net(sk), net))
 			continue;
 
-		if (udp_sk(s)->udp_port_hash == num &&
-		    s->sk_family == PF_INET6) {
+		if (udp_sk(sk)->udp_port_hash == num &&
+		    sk->sk_family == PF_INET6) {
 			if (inet->inet_dport) {
 				if (inet->inet_dport != rmt_port)
 					continue;
@@ -715,16 +727,16 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
 			    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
 				continue;
 
-			if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)
+			if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
 				continue;
 
 			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
 				if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
 					continue;
 			}
-			if (!inet6_mc_check(s, loc_addr, rmt_addr))
+			if (!inet6_mc_check(sk, loc_addr, rmt_addr))
 				continue;
-			return s;
+			return sk;
 		}
 	}
 	return NULL;
@@ -755,6 +767,17 @@ static void flush_stack(struct sock **stack, unsigned int count,
 	if (unlikely(skb1))
 		kfree_skb(skb1);
 }
+
+static void udp6_csum_zero_error(struct sk_buff *skb)
+{
+	/* RFC 2460 section 8.1 says that we SHOULD log
+	 * this error. Well, it is reasonable.
+	 */
+	LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
+		       &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source),
+		       &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest));
+}
+
 /*
  * Note: called only from the BH handler context,
  * so we don't need to lock the hashes.
@@ -774,7 +797,12 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	dif = inet6_iif(skb);
 	sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif);
 	while (sk) {
-		stack[count++] = sk;
+		/* If zero checksum and no_check is not on for
+		 * the socket then skip it.
+		 */
+		if (uh->check || udp_sk(sk)->no_check6_rx)
+			stack[count++] = sk;
+
 		sk = udp_v6_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr,
 				       uh->source, saddr, dif);
 		if (unlikely(count == ARRAY_SIZE(stack))) {
@@ -862,6 +890,12 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (sk != NULL) {
 		int ret;
 
+		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
+			sock_put(sk);
+			udp6_csum_zero_error(skb);
+			goto csum_error;
+		}
+
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
@@ -874,6 +908,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		return 0;
 	}
 
+	if (!uh->check) {
+		udp6_csum_zero_error(skb);
+		goto csum_error;
+	}
+
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto discard;
 
@@ -1001,7 +1040,10 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 
 	if (is_udplite)
 		csum = udplite_csum_outgoing(sk, skb);
-	else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
+	else if (up->no_check6_tx) {   /* UDP csum disabled */
+		skb->ip_summed = CHECKSUM_NONE;
+		goto send;
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
 		udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr,
 				     up->len);
 		goto send;
@@ -1038,7 +1080,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	struct udp_sock *up = udp_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_txoptions *opt = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
@@ -1140,7 +1182,6 @@ do_udp_sendmsg:
 				flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 				if (flowlabel == NULL)
 					return -EINVAL;
-				daddr = &flowlabel->dst;
 			}
 		}
 
@@ -1221,21 +1262,15 @@ do_udp_sendmsg:
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, true);
+	dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		dst = NULL;
 		goto out;
 	}
 
-	if (hlimit < 0) {
-		if (ipv6_addr_is_multicast(&fl6.daddr))
-			hlimit = np->mcast_hops;
-		else
-			hlimit = np->hop_limit;
-		if (hlimit < 0)
-			hlimit = ip6_dst_hoplimit(dst);
-	}
+	if (hlimit < 0)
+		hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	if (tclass < 0)
 		tclass = np->tclass;
@@ -1475,7 +1510,6 @@ static struct inet_protosw udpv6_protosw = {
 	.protocol =  IPPROTO_UDP,
 	.prot =      &udpv6_prot,
 	.ops =       &inet6_dgram_ops,
-	.no_check =  UDP_CSUM_DEFAULT,
 	.flags =     INET_PROTOSW_PERMANENT,
 };
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index e7359f9eaa8..0ae3d98f83e 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -63,7 +63,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		if (unlikely(type & ~(SKB_GSO_UDP |
 				      SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
+				      SKB_GSO_UDP_TUNNEL_CSUM |
 				      SKB_GSO_GRE |
+				      SKB_GSO_GRE_CSUM |
 				      SKB_GSO_IPIP |
 				      SKB_GSO_SIT |
 				      SKB_GSO_MPLS) ||
@@ -76,7 +78,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		goto out;
 	}
 
-	if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL)
+	if (skb->encapsulation && skb_shinfo(skb)->gso_type &
+	    (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
 		segs = skb_udp_tunnel_segment(skb, features);
 	else {
 		/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
@@ -113,7 +116,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
 		fptr->nexthdr = nexthdr;
 		fptr->reserved = 0;
-		ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb));
+		fptr->identification = skb_shinfo(skb)->ip6_frag_id;
 
 		/* Fragment the skb. ipv6 header and the remaining fields of the
 		 * fragment header are updated in ipv6_gso_segment()
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index dfcc4be4689..9cf097e206e 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -64,7 +64,6 @@ static struct inet_protosw udplite6_protosw = {
 	.protocol	= IPPROTO_UDPLITE,
 	.prot		= &udplitev6_prot,
 	.ops		= &inet6_dgram_ops,
-	.no_check	= 0,
 	.flags		= INET_PROTOSW_PERMANENT,
 };
 
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index cb04f7a16b5..901ef6f8add 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -18,65 +18,6 @@
 #include <net/ipv6.h>
 #include <net/xfrm.h>
 
-/* Informational hook. The decap is still done here. */
-static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly;
-static DEFINE_MUTEX(xfrm6_mode_tunnel_input_mutex);
-
-int xfrm6_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler)
-{
-	struct xfrm_tunnel_notifier __rcu **pprev;
-	struct xfrm_tunnel_notifier *t;
-	int ret = -EEXIST;
-	int priority = handler->priority;
-
-	mutex_lock(&xfrm6_mode_tunnel_input_mutex);
-
-	for (pprev = &rcv_notify_handlers;
-	     (t = rcu_dereference_protected(*pprev,
-	     lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL;
-	     pprev = &t->next) {
-		if (t->priority > priority)
-			break;
-		if (t->priority == priority)
-			goto err;
-
-	}
-
-	handler->next = *pprev;
-	rcu_assign_pointer(*pprev, handler);
-
-	ret = 0;
-
-err:
-	mutex_unlock(&xfrm6_mode_tunnel_input_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_register);
-
-int xfrm6_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler)
-{
-	struct xfrm_tunnel_notifier __rcu **pprev;
-	struct xfrm_tunnel_notifier *t;
-	int ret = -ENOENT;
-
-	mutex_lock(&xfrm6_mode_tunnel_input_mutex);
-	for (pprev = &rcv_notify_handlers;
-	     (t = rcu_dereference_protected(*pprev,
-	     lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL;
-	     pprev = &t->next) {
-		if (t == handler) {
-			*pprev = handler->next;
-			ret = 0;
-			break;
-		}
-	}
-	mutex_unlock(&xfrm6_mode_tunnel_input_mutex);
-	synchronize_net();
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_deregister);
-
 static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
 {
 	const struct ipv6hdr *outer_iph = ipv6_hdr(skb);
@@ -130,7 +71,6 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-	struct xfrm_tunnel_notifier *handler;
 	int err = -EINVAL;
 
 	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6)
@@ -138,9 +78,6 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		goto out;
 
-	for_each_input_rcu(rcv_notify_handlers, handler)
-		handler->handler(skb);
-
 	err = skb_unclone(skb, GFP_ATOMIC);
 	if (err)
 		goto out;
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 6cd625e3770..433672d07d0 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -78,7 +78,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if (!skb->local_df && skb->len > mtu) {
+	if (!skb->ignore_df && skb->len > mtu) {
 		skb->dev = dst->dev;
 
 		if (xfrm6_local_dontfrag(skb))
@@ -114,13 +114,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
-#ifdef CONFIG_NETFILTER
-	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
-#endif
-
-	skb->protocol = htons(ETH_P_IPV6);
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	return x->outer_mode->output2(x, skb);
 }
@@ -128,11 +122,13 @@ EXPORT_SYMBOL(xfrm6_prepare_output);
 
 int xfrm6_output_finish(struct sk_buff *skb)
 {
+	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+	skb->protocol = htons(ETH_P_IPV6);
+
 #ifdef CONFIG_NETFILTER
 	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
 #endif
 
-	skb->protocol = htons(ETH_P_IPV6);
 	return xfrm_output(skb);
 }
 
@@ -142,6 +138,13 @@ static int __xfrm6_output(struct sk_buff *skb)
 	struct xfrm_state *x = dst->xfrm;
 	int mtu;
 
+#ifdef CONFIG_NETFILTER
+	if (!x) {
+		IP6CB(skb)->flags |= IP6SKB_REROUTED;
+		return dst_output(skb);
+	}
+#endif
+
 	if (skb->protocol == htons(ETH_P_IPV6))
 		mtu = ip6_skb_dst_mtu(skb);
 	else
@@ -150,7 +153,7 @@ static int __xfrm6_output(struct sk_buff *skb)
 	if (skb->len > mtu && xfrm6_local_dontfrag(skb)) {
 		xfrm6_local_rxpmtu(skb, mtu);
 		return -EMSGSIZE;
-	} else if (!skb->local_df && skb->len > mtu && skb->sk) {
+	} else if (!skb->ignore_df && skb->len > mtu && skb->sk) {
 		xfrm_local_error(skb, mtu);
 		return -EMSGSIZE;
 	}
@@ -163,8 +166,9 @@ static int __xfrm6_output(struct sk_buff *skb)
 	return x->outer_mode->afinfo->output_finish(skb);
 }
 
-int xfrm6_output(struct sk_buff *skb)
+int xfrm6_output(struct sock *sk, struct sk_buff *skb)
 {
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL,
-		       skb_dst(skb)->dev, __xfrm6_output);
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb,
+			    NULL, skb_dst(skb)->dev, __xfrm6_output,
+			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 5f8e128c512..2a0bbda2c76 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -389,11 +389,17 @@ int __init xfrm6_init(void)
 	if (ret)
 		goto out_policy;
 
+	ret = xfrm6_protocol_init();
+	if (ret)
+		goto out_state;
+
 #ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&xfrm6_net_ops);
 #endif
 out:
 	return ret;
+out_state:
+	xfrm6_state_fini();
 out_policy:
 	xfrm6_policy_fini();
 	goto out;
@@ -404,6 +410,7 @@ void xfrm6_fini(void)
 #ifdef CONFIG_SYSCTL
 	unregister_pernet_subsys(&xfrm6_net_ops);
 #endif
+	xfrm6_protocol_fini();
 	xfrm6_policy_fini();
 	xfrm6_state_fini();
 	dst_entries_destroy(&xfrm6_dst_ops);
diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c
new file mode 100644
index 00000000000..54d13f8dbba
--- /dev/null
+++ b/net/ipv6/xfrm6_protocol.c
@@ -0,0 +1,279 @@
+/* xfrm6_protocol.c - Generic xfrm protocol multiplexer for ipv6.
+ *
+ * Copyright (C) 2013 secunet Security Networks AG
+ *
+ * Author:
+ * Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * Based on:
+ * net/ipv4/xfrm4_protocol.c
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/skbuff.h>
+#include <linux/icmpv6.h>
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/xfrm.h>
+
+static struct xfrm6_protocol __rcu *esp6_handlers __read_mostly;
+static struct xfrm6_protocol __rcu *ah6_handlers __read_mostly;
+static struct xfrm6_protocol __rcu *ipcomp6_handlers __read_mostly;
+static DEFINE_MUTEX(xfrm6_protocol_mutex);
+
+static inline struct xfrm6_protocol __rcu **proto_handlers(u8 protocol)
+{
+	switch (protocol) {
+	case IPPROTO_ESP:
+		return &esp6_handlers;
+	case IPPROTO_AH:
+		return &ah6_handlers;
+	case IPPROTO_COMP:
+		return &ipcomp6_handlers;
+	}
+
+	return NULL;
+}
+
+#define for_each_protocol_rcu(head, handler)		\
+	for (handler = rcu_dereference(head);		\
+	     handler != NULL;				\
+	     handler = rcu_dereference(handler->next))	\
+
+int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
+{
+	int ret;
+	struct xfrm6_protocol *handler;
+	struct xfrm6_protocol __rcu **head = proto_handlers(protocol);
+
+	if (!head)
+		return 0;
+
+	for_each_protocol_rcu(*proto_handlers(protocol), handler)
+		if ((ret = handler->cb_handler(skb, err)) <= 0)
+			return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL(xfrm6_rcv_cb);
+
+static int xfrm6_esp_rcv(struct sk_buff *skb)
+{
+	int ret;
+	struct xfrm6_protocol *handler;
+
+	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+
+	for_each_protocol_rcu(esp6_handlers, handler)
+		if ((ret = handler->handler(skb)) != -EINVAL)
+			return ret;
+
+	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static void xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+			  u8 type, u8 code, int offset, __be32 info)
+{
+	struct xfrm6_protocol *handler;
+
+	for_each_protocol_rcu(esp6_handlers, handler)
+		if (!handler->err_handler(skb, opt, type, code, offset, info))
+			break;
+}
+
+static int xfrm6_ah_rcv(struct sk_buff *skb)
+{
+	int ret;
+	struct xfrm6_protocol *handler;
+
+	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+
+	for_each_protocol_rcu(ah6_handlers, handler)
+		if ((ret = handler->handler(skb)) != -EINVAL)
+			return ret;
+
+	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static void xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+			 u8 type, u8 code, int offset, __be32 info)
+{
+	struct xfrm6_protocol *handler;
+
+	for_each_protocol_rcu(ah6_handlers, handler)
+		if (!handler->err_handler(skb, opt, type, code, offset, info))
+			break;
+}
+
+static int xfrm6_ipcomp_rcv(struct sk_buff *skb)
+{
+	int ret;
+	struct xfrm6_protocol *handler;
+
+	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+
+	for_each_protocol_rcu(ipcomp6_handlers, handler)
+		if ((ret = handler->handler(skb)) != -EINVAL)
+			return ret;
+
+	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static void xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+			     u8 type, u8 code, int offset, __be32 info)
+{
+	struct xfrm6_protocol *handler;
+
+	for_each_protocol_rcu(ipcomp6_handlers, handler)
+		if (!handler->err_handler(skb, opt, type, code, offset, info))
+			break;
+}
+
+static const struct inet6_protocol esp6_protocol = {
+	.handler	=	xfrm6_esp_rcv,
+	.err_handler	=	xfrm6_esp_err,
+	.flags		=	INET6_PROTO_NOPOLICY,
+};
+
+static const struct inet6_protocol ah6_protocol = {
+	.handler	=	xfrm6_ah_rcv,
+	.err_handler	=	xfrm6_ah_err,
+	.flags		=	INET6_PROTO_NOPOLICY,
+};
+
+static const struct inet6_protocol ipcomp6_protocol = {
+	.handler	=	xfrm6_ipcomp_rcv,
+	.err_handler	=	xfrm6_ipcomp_err,
+	.flags		=	INET6_PROTO_NOPOLICY,
+};
+
+static struct xfrm_input_afinfo xfrm6_input_afinfo = {
+	.family		=	AF_INET6,
+	.owner		=	THIS_MODULE,
+	.callback	=	xfrm6_rcv_cb,
+};
+
+static inline const struct inet6_protocol *netproto(unsigned char protocol)
+{
+	switch (protocol) {
+	case IPPROTO_ESP:
+		return &esp6_protocol;
+	case IPPROTO_AH:
+		return &ah6_protocol;
+	case IPPROTO_COMP:
+		return &ipcomp6_protocol;
+	}
+
+	return NULL;
+}
+
+int xfrm6_protocol_register(struct xfrm6_protocol *handler,
+			    unsigned char protocol)
+{
+	struct xfrm6_protocol __rcu **pprev;
+	struct xfrm6_protocol *t;
+	bool add_netproto = false;
+	int ret = -EEXIST;
+	int priority = handler->priority;
+
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
+	mutex_lock(&xfrm6_protocol_mutex);
+
+	if (!rcu_dereference_protected(*proto_handlers(protocol),
+				       lockdep_is_held(&xfrm6_protocol_mutex)))
+		add_netproto = true;
+
+	for (pprev = proto_handlers(protocol);
+	     (t = rcu_dereference_protected(*pprev,
+			lockdep_is_held(&xfrm6_protocol_mutex))) != NULL;
+	     pprev = &t->next) {
+		if (t->priority < priority)
+			break;
+		if (t->priority == priority)
+			goto err;
+	}
+
+	handler->next = *pprev;
+	rcu_assign_pointer(*pprev, handler);
+
+	ret = 0;
+
+err:
+	mutex_unlock(&xfrm6_protocol_mutex);
+
+	if (add_netproto) {
+		if (inet6_add_protocol(netproto(protocol), protocol)) {
+			pr_err("%s: can't add protocol\n", __func__);
+			ret = -EAGAIN;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(xfrm6_protocol_register);
+
+int xfrm6_protocol_deregister(struct xfrm6_protocol *handler,
+			      unsigned char protocol)
+{
+	struct xfrm6_protocol __rcu **pprev;
+	struct xfrm6_protocol *t;
+	int ret = -ENOENT;
+
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
+	mutex_lock(&xfrm6_protocol_mutex);
+
+	for (pprev = proto_handlers(protocol);
+	     (t = rcu_dereference_protected(*pprev,
+			lockdep_is_held(&xfrm6_protocol_mutex))) != NULL;
+	     pprev = &t->next) {
+		if (t == handler) {
+			*pprev = handler->next;
+			ret = 0;
+			break;
+		}
+	}
+
+	if (!rcu_dereference_protected(*proto_handlers(protocol),
+				       lockdep_is_held(&xfrm6_protocol_mutex))) {
+		if (inet6_del_protocol(netproto(protocol), protocol) < 0) {
+			pr_err("%s: can't remove protocol\n", __func__);
+			ret = -EAGAIN;
+		}
+	}
+
+	mutex_unlock(&xfrm6_protocol_mutex);
+
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL(xfrm6_protocol_deregister);
+
+int __init xfrm6_protocol_init(void)
+{
+	return xfrm_input_register_afinfo(&xfrm6_input_afinfo);
+}
+
+void xfrm6_protocol_fini(void)
+{
+	xfrm_input_unregister_afinfo(&xfrm6_input_afinfo);
+}
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index e096025b477..91729b807c7 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -52,18 +52,12 @@
 #include <net/p8022.h>
 #include <net/psnap.h>
 #include <net/sock.h>
+#include <net/datalink.h>
 #include <net/tcp_states.h>
+#include <net/net_namespace.h>
 
 #include <asm/uaccess.h>
 
-#ifdef CONFIG_SYSCTL
-extern void ipx_register_sysctl(void);
-extern void ipx_unregister_sysctl(void);
-#else
-#define ipx_register_sysctl()
-#define ipx_unregister_sysctl()
-#endif
-
 /* Configuration Variables */
 static unsigned char ipxcfg_max_hops = 16;
 static char ipxcfg_auto_select_primary;
@@ -84,15 +78,6 @@ DEFINE_SPINLOCK(ipx_interfaces_lock);
 struct ipx_interface *ipx_primary_net;
 struct ipx_interface *ipx_internal_net;
 
-extern int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc,
-			    unsigned char *node);
-extern void ipxrtr_del_routes(struct ipx_interface *intrfc);
-extern int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
-			       struct iovec *iov, size_t len, int noblock);
-extern int ipxrtr_route_skb(struct sk_buff *skb);
-extern struct ipx_route *ipxrtr_lookup(__be32 net);
-extern int ipxrtr_ioctl(unsigned int cmd, void __user *arg);
-
 struct ipx_interface *ipx_interfaces_head(void)
 {
 	struct ipx_interface *rc = NULL;
@@ -1368,7 +1353,7 @@ static int ipx_create(struct net *net, struct socket *sock, int protocol,
 
 	sk_refcnt_debug_inc(sk);
 	sock_init_data(sock, sk);
-	sk->sk_no_check = 1;		/* Checksum off by default */
+	sk->sk_no_check_tx = 1;		/* Checksum off by default */
 	sock->ops = &ipx_dgram_ops;
 	rc = 0;
 out:
@@ -1383,6 +1368,7 @@ static int ipx_release(struct socket *sock)
 		goto out;
 
 	lock_sock(sk);
+	sk->sk_shutdown = SHUTDOWN_MASK;
 	if (!sock_flag(sk, SOCK_DEAD))
 		sk->sk_state_change(sk);
 
@@ -1707,7 +1693,7 @@ static int ipx_sendmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct ipx_sock *ipxs = ipx_sk(sk);
-	struct sockaddr_ipx *usipx = (struct sockaddr_ipx *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_ipx *, usipx, msg->msg_name);
 	struct sockaddr_ipx local_sipx;
 	int rc = -EINVAL;
 	int flags = msg->msg_flags;
@@ -1774,7 +1760,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct ipx_sock *ipxs = ipx_sk(sk);
-	struct sockaddr_ipx *sipx = (struct sockaddr_ipx *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_ipx *, sipx, msg->msg_name);
 	struct ipxhdr *ipx = NULL;
 	struct sk_buff *skb;
 	int copied, rc;
@@ -1806,8 +1792,11 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &rc);
-	if (!skb)
+	if (!skb) {
+		if (rc == -EAGAIN && (sk->sk_shutdown & RCV_SHUTDOWN))
+			rc = 0;
 		goto out;
+	}
 
 	ipx 	= ipx_hdr(skb);
 	copied 	= ntohs(ipx->ipx_pktsize) - sizeof(struct ipxhdr);
@@ -1937,6 +1926,26 @@ static int ipx_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long
 }
 #endif
 
+static int ipx_shutdown(struct socket *sock, int mode)
+{
+	struct sock *sk = sock->sk;
+
+	if (mode < SHUT_RD || mode > SHUT_RDWR)
+		return -EINVAL;
+	/* This maps:
+	 * SHUT_RD   (0) -> RCV_SHUTDOWN  (1)
+	 * SHUT_WR   (1) -> SEND_SHUTDOWN (2)
+	 * SHUT_RDWR (2) -> SHUTDOWN_MASK (3)
+	 */
+	++mode;
+
+	lock_sock(sk);
+	sk->sk_shutdown |= mode;
+	release_sock(sk);
+	sk->sk_state_change(sk);
+
+	return 0;
+}
 
 /*
  * Socket family declarations
@@ -1963,7 +1972,7 @@ static const struct proto_ops ipx_dgram_ops = {
 	.compat_ioctl	= ipx_compat_ioctl,
 #endif
 	.listen		= sock_no_listen,
-	.shutdown	= sock_no_shutdown, /* FIXME: support shutdown */
+	.shutdown	= ipx_shutdown,
 	.setsockopt	= ipx_setsockopt,
 	.getsockopt	= ipx_getsockopt,
 	.sendmsg	= ipx_sendmsg,
@@ -1986,9 +1995,6 @@ static struct notifier_block ipx_dev_notifier = {
 	.notifier_call	= ipxitf_device_event,
 };
 
-extern struct datalink_proto *make_EII_client(void);
-extern void destroy_EII_client(struct datalink_proto *);
-
 static const unsigned char ipx_8022_type = 0xE0;
 static const unsigned char ipx_snap_id[5] = { 0x0, 0x0, 0x0, 0x81, 0x37 };
 static const char ipx_EII_err_msg[] __initconst =
diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c
index 30f4519b092..67e7ad3d46b 100644
--- a/net/ipx/ipx_route.c
+++ b/net/ipx/ipx_route.c
@@ -20,15 +20,11 @@ DEFINE_RWLOCK(ipx_routes_lock);
 
 extern struct ipx_interface *ipx_internal_net;
 
-extern __be16 ipx_cksum(struct ipxhdr *packet, int length);
 extern struct ipx_interface *ipxitf_find_using_net(__be32 net);
 extern int ipxitf_demux_socket(struct ipx_interface *intrfc,
 			       struct sk_buff *skb, int copy);
 extern int ipxitf_demux_socket(struct ipx_interface *intrfc,
 			       struct sk_buff *skb, int copy);
-extern int ipxitf_send(struct ipx_interface *intrfc, struct sk_buff *skb,
-		       char *node);
-extern struct ipx_interface *ipxitf_find_using_net(__be32 net);
 
 struct ipx_route *ipxrtr_lookup(__be32 net)
 {
@@ -240,7 +236,8 @@ int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
 	}
 
 	/* Apply checksum. Not allowed on 802.3 links. */
-	if (sk->sk_no_check || intrfc->if_dlink_type == htons(IPX_FRAME_8023))
+	if (sk->sk_no_check_tx ||
+	    intrfc->if_dlink_type == htons(IPX_FRAME_8023))
 		ipx->ipx_checksum = htons(0xFFFF);
 	else
 		ipx->ipx_checksum = ipx_cksum(ipx, len + sizeof(struct ipxhdr));
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 73baf9b346b..54747c25c86 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1652,7 +1652,7 @@ static int irda_sendmsg_ultra(struct kiocb *iocb, struct socket *sock,
 
 	/* Check if an address was specified with sendto. Jean II */
 	if (msg->msg_name) {
-		struct sockaddr_irda *addr = (struct sockaddr_irda *) msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_irda *, addr, msg->msg_name);
 		err = -EINVAL;
 		/* Check address, extract pid. Jean II */
 		if (msg->msg_namelen < sizeof(*addr))
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index c4b7218058b..7a95fa4a3de 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -682,6 +682,18 @@ struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock)
 	return NULL;
 }
 
+static void __iucv_auto_name(struct iucv_sock *iucv)
+{
+	char name[12];
+
+	sprintf(name, "%08x", atomic_inc_return(&iucv_sk_list.autobind_name));
+	while (__iucv_get_sock_by_name(name)) {
+		sprintf(name, "%08x",
+			atomic_inc_return(&iucv_sk_list.autobind_name));
+	}
+	memcpy(iucv->src_name, name, 8);
+}
+
 /* Bind an unbound socket */
 static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr,
 			  int addr_len)
@@ -724,8 +736,12 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr,
 	rcu_read_lock();
 	for_each_netdev_rcu(&init_net, dev) {
 		if (!memcmp(dev->perm_addr, uid, 8)) {
-			memcpy(iucv->src_name, sa->siucv_name, 8);
 			memcpy(iucv->src_user_id, sa->siucv_user_id, 8);
+			/* Check for unitialized siucv_name */
+			if (strncmp(sa->siucv_name, "        ", 8) == 0)
+				__iucv_auto_name(iucv);
+			else
+				memcpy(iucv->src_name, sa->siucv_name, 8);
 			sk->sk_bound_dev_if = dev->ifindex;
 			iucv->hs_dev = dev;
 			dev_hold(dev);
@@ -763,7 +779,6 @@ done:
 static int iucv_sock_autobind(struct sock *sk)
 {
 	struct iucv_sock *iucv = iucv_sk(sk);
-	char name[12];
 	int err = 0;
 
 	if (unlikely(!pr_iucv))
@@ -772,17 +787,9 @@ static int iucv_sock_autobind(struct sock *sk)
 	memcpy(iucv->src_user_id, iucv_userid, 8);
 
 	write_lock_bh(&iucv_sk_list.lock);
-
-	sprintf(name, "%08x", atomic_inc_return(&iucv_sk_list.autobind_name));
-	while (__iucv_get_sock_by_name(name)) {
-		sprintf(name, "%08x",
-			atomic_inc_return(&iucv_sk_list.autobind_name));
-	}
-
+	__iucv_auto_name(iucv);
 	write_unlock_bh(&iucv_sk_list.lock);
 
-	memcpy(&iucv->src_name, name, 8);
-
 	if (!iucv->msglimit)
 		iucv->msglimit = IUCV_QUEUELEN_DEFAULT;
 
@@ -1382,6 +1389,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 		if (sk->sk_type == SOCK_STREAM) {
 			if (copied < rlen) {
 				IUCV_SKB_CB(skb)->offset = offset + copied;
+				skb_queue_head(&sk->sk_receive_queue, skb);
 				goto done;
 			}
 		}
@@ -1756,7 +1764,7 @@ static int iucv_callback_connreq(struct iucv_path *path,
 
 	/* Wake up accept */
 	nsk->sk_state = IUCV_CONNECTED;
-	sk->sk_data_ready(sk, 1);
+	sk->sk_data_ready(sk);
 	err = 0;
 fail:
 	bh_unlock_sock(sk);
@@ -1829,7 +1837,7 @@ static void iucv_callback_txdone(struct iucv_path *path,
 		spin_lock_irqsave(&list->lock, flags);
 
 		while (list_skb != (struct sk_buff *)list) {
-			if (msg->tag != IUCV_SKB_CB(list_skb)->tag) {
+			if (msg->tag == IUCV_SKB_CB(list_skb)->tag) {
 				this = list_skb;
 				break;
 			}
@@ -1935,11 +1943,10 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb)
 	    sk_acceptq_is_full(sk) ||
 	    !nsk) {
 		/* error on server socket - connection refused */
-		if (nsk)
-			sk_free(nsk);
 		afiucv_swap_src_dest(skb);
 		trans_hdr->flags = AF_IUCV_FLAG_SYN | AF_IUCV_FLAG_FIN;
 		err = dev_queue_xmit(skb);
+		iucv_sock_kill(nsk);
 		bh_unlock_sock(sk);
 		goto out;
 	}
@@ -1967,7 +1974,7 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb)
 	if (!err) {
 		iucv_accept_enqueue(sk, nsk);
 		nsk->sk_state = IUCV_CONNECTED;
-		sk->sk_data_ready(sk, 1);
+		sk->sk_data_ready(sk);
 	} else
 		iucv_sock_kill(nsk);
 	bh_unlock_sock(sk);
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index cd5b8ec9be0..da787930df0 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -621,6 +621,42 @@ static void iucv_disable(void)
 	put_online_cpus();
 }
 
+static void free_iucv_data(int cpu)
+{
+	kfree(iucv_param_irq[cpu]);
+	iucv_param_irq[cpu] = NULL;
+	kfree(iucv_param[cpu]);
+	iucv_param[cpu] = NULL;
+	kfree(iucv_irq_data[cpu]);
+	iucv_irq_data[cpu] = NULL;
+}
+
+static int alloc_iucv_data(int cpu)
+{
+	/* Note: GFP_DMA used to get memory below 2G */
+	iucv_irq_data[cpu] = kmalloc_node(sizeof(struct iucv_irq_data),
+			     GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
+	if (!iucv_irq_data[cpu])
+		goto out_free;
+
+	/* Allocate parameter blocks. */
+	iucv_param[cpu] = kmalloc_node(sizeof(union iucv_param),
+			  GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
+	if (!iucv_param[cpu])
+		goto out_free;
+
+	iucv_param_irq[cpu] = kmalloc_node(sizeof(union iucv_param),
+			  GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
+	if (!iucv_param_irq[cpu])
+		goto out_free;
+
+	return 0;
+
+out_free:
+	free_iucv_data(cpu);
+	return -ENOMEM;
+}
+
 static int iucv_cpu_notify(struct notifier_block *self,
 				     unsigned long action, void *hcpu)
 {
@@ -630,38 +666,14 @@ static int iucv_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		iucv_irq_data[cpu] = kmalloc_node(sizeof(struct iucv_irq_data),
-					GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
-		if (!iucv_irq_data[cpu])
-			return notifier_from_errno(-ENOMEM);
-
-		iucv_param[cpu] = kmalloc_node(sizeof(union iucv_param),
-				     GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
-		if (!iucv_param[cpu]) {
-			kfree(iucv_irq_data[cpu]);
-			iucv_irq_data[cpu] = NULL;
+		if (alloc_iucv_data(cpu))
 			return notifier_from_errno(-ENOMEM);
-		}
-		iucv_param_irq[cpu] = kmalloc_node(sizeof(union iucv_param),
-					GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
-		if (!iucv_param_irq[cpu]) {
-			kfree(iucv_param[cpu]);
-			iucv_param[cpu] = NULL;
-			kfree(iucv_irq_data[cpu]);
-			iucv_irq_data[cpu] = NULL;
-			return notifier_from_errno(-ENOMEM);
-		}
 		break;
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		kfree(iucv_param_irq[cpu]);
-		iucv_param_irq[cpu] = NULL;
-		kfree(iucv_param[cpu]);
-		iucv_param[cpu] = NULL;
-		kfree(iucv_irq_data[cpu]);
-		iucv_irq_data[cpu] = NULL;
+		free_iucv_data(cpu);
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
@@ -2016,7 +2028,7 @@ static int __init iucv_init(void)
 	rc = iucv_query_maxconn();
 	if (rc)
 		goto out_ctl;
-	rc = register_external_interrupt(0x4000, iucv_external_interrupt);
+	rc = register_external_irq(EXT_IRQ_IUCV, iucv_external_interrupt);
 	if (rc)
 		goto out_ctl;
 	iucv_root = root_device_register("iucv");
@@ -2025,33 +2037,20 @@ static int __init iucv_init(void)
 		goto out_int;
 	}
 
-	for_each_online_cpu(cpu) {
-		/* Note: GFP_DMA used to get memory below 2G */
-		iucv_irq_data[cpu] = kmalloc_node(sizeof(struct iucv_irq_data),
-				     GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
-		if (!iucv_irq_data[cpu]) {
-			rc = -ENOMEM;
-			goto out_free;
-		}
+	cpu_notifier_register_begin();
 
-		/* Allocate parameter blocks. */
-		iucv_param[cpu] = kmalloc_node(sizeof(union iucv_param),
-				  GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
-		if (!iucv_param[cpu]) {
-			rc = -ENOMEM;
-			goto out_free;
-		}
-		iucv_param_irq[cpu] = kmalloc_node(sizeof(union iucv_param),
-				  GFP_KERNEL|GFP_DMA, cpu_to_node(cpu));
-		if (!iucv_param_irq[cpu]) {
+	for_each_online_cpu(cpu) {
+		if (alloc_iucv_data(cpu)) {
 			rc = -ENOMEM;
 			goto out_free;
 		}
-
 	}
-	rc = register_hotcpu_notifier(&iucv_cpu_notifier);
+	rc = __register_hotcpu_notifier(&iucv_cpu_notifier);
 	if (rc)
 		goto out_free;
+
+	cpu_notifier_register_done();
+
 	rc = register_reboot_notifier(&iucv_reboot_notifier);
 	if (rc)
 		goto out_cpu;
@@ -2069,19 +2068,17 @@ static int __init iucv_init(void)
 out_reboot:
 	unregister_reboot_notifier(&iucv_reboot_notifier);
 out_cpu:
-	unregister_hotcpu_notifier(&iucv_cpu_notifier);
+	cpu_notifier_register_begin();
+	__unregister_hotcpu_notifier(&iucv_cpu_notifier);
 out_free:
-	for_each_possible_cpu(cpu) {
-		kfree(iucv_param_irq[cpu]);
-		iucv_param_irq[cpu] = NULL;
-		kfree(iucv_param[cpu]);
-		iucv_param[cpu] = NULL;
-		kfree(iucv_irq_data[cpu]);
-		iucv_irq_data[cpu] = NULL;
-	}
+	for_each_possible_cpu(cpu)
+		free_iucv_data(cpu);
+
+	cpu_notifier_register_done();
+
 	root_device_unregister(iucv_root);
 out_int:
-	unregister_external_interrupt(0x4000, iucv_external_interrupt);
+	unregister_external_irq(EXT_IRQ_IUCV, iucv_external_interrupt);
 out_ctl:
 	ctl_clear_bit(0, 1);
 out:
@@ -2105,18 +2102,14 @@ static void __exit iucv_exit(void)
 		kfree(p);
 	spin_unlock_irq(&iucv_queue_lock);
 	unregister_reboot_notifier(&iucv_reboot_notifier);
-	unregister_hotcpu_notifier(&iucv_cpu_notifier);
-	for_each_possible_cpu(cpu) {
-		kfree(iucv_param_irq[cpu]);
-		iucv_param_irq[cpu] = NULL;
-		kfree(iucv_param[cpu]);
-		iucv_param[cpu] = NULL;
-		kfree(iucv_irq_data[cpu]);
-		iucv_irq_data[cpu] = NULL;
-	}
+	cpu_notifier_register_begin();
+	__unregister_hotcpu_notifier(&iucv_cpu_notifier);
+	for_each_possible_cpu(cpu)
+		free_iucv_data(cpu);
+	cpu_notifier_register_done();
 	root_device_unregister(iucv_root);
 	bus_unregister(&iucv_bus);
-	unregister_external_interrupt(0x4000, iucv_external_interrupt);
+	unregister_external_irq(EXT_IRQ_IUCV, iucv_external_interrupt);
 }
 
 subsys_initcall(iucv_init);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 545f047868a..ba2a2f95911 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -205,7 +205,7 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2,
 		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) {
 			skb_set_owner_r(*skb2, sk);
 			skb_queue_tail(&sk->sk_receive_queue, *skb2);
-			sk->sk_data_ready(sk, (*skb2)->len);
+			sk->sk_data_ready(sk);
 			*skb2 = NULL;
 			err = 0;
 		}
@@ -365,6 +365,7 @@ static const u8 sadb_ext_min_len[] = {
 	[SADB_X_EXT_NAT_T_OA]		= (u8) sizeof(struct sadb_address),
 	[SADB_X_EXT_SEC_CTX]		= (u8) sizeof(struct sadb_x_sec_ctx),
 	[SADB_X_EXT_KMADDRESS]		= (u8) sizeof(struct sadb_x_kmaddress),
+	[SADB_X_EXT_FILTER]		= (u8) sizeof(struct sadb_x_filter),
 };
 
 /* Verify sadb_address_{len,prefixlen} against sa_family.  */
@@ -433,12 +434,13 @@ static inline int verify_sec_ctx_len(const void *p)
 	return 0;
 }
 
-static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx)
+static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx,
+								     gfp_t gfp)
 {
 	struct xfrm_user_sec_ctx *uctx = NULL;
 	int ctx_size = sec_ctx->sadb_x_ctx_len;
 
-	uctx = kmalloc((sizeof(*uctx)+ctx_size), GFP_KERNEL);
+	uctx = kmalloc((sizeof(*uctx)+ctx_size), gfp);
 
 	if (!uctx)
 		return NULL;
@@ -1124,7 +1126,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net,
 
 	sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1];
 	if (sec_ctx != NULL) {
-		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
+		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL);
 
 		if (!uctx)
 			goto out;
@@ -1340,6 +1342,12 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_
 		max_spi = range->sadb_spirange_max;
 	}
 
+	err = verify_spi_info(x->id.proto, min_spi, max_spi);
+	if (err) {
+		xfrm_state_put(x);
+		return err;
+	}
+
 	err = xfrm_alloc_spi(x, min_spi, max_spi);
 	resp_skb = err ? ERR_PTR(err) : pfkey_xfrm_state2msg(x);
 
@@ -1380,10 +1388,9 @@ static int pfkey_acquire(struct sock *sk, struct sk_buff *skb, const struct sadb
 		return 0;
 
 	spin_lock_bh(&x->lock);
-	if (x->km.state == XFRM_STATE_ACQ) {
+	if (x->km.state == XFRM_STATE_ACQ)
 		x->km.state = XFRM_STATE_ERROR;
-		wake_up(&net->xfrm.km_waitq);
-	}
+
 	spin_unlock_bh(&x->lock);
 	xfrm_state_put(x);
 	return 0;
@@ -1469,9 +1476,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, const struct sadb_msg
 	else
 		err = xfrm_state_update(x);
 
-	xfrm_audit_state_add(x, err ? 0 : 1,
-			     audit_get_loginuid(current),
-			     audit_get_sessionid(current), 0);
+	xfrm_audit_state_add(x, err ? 0 : 1, true);
 
 	if (err < 0) {
 		x->km.state = XFRM_STATE_DEAD;
@@ -1525,9 +1530,7 @@ static int pfkey_delete(struct sock *sk, struct sk_buff *skb, const struct sadb_
 	c.event = XFRM_MSG_DELSA;
 	km_state_notify(x, &c);
 out:
-	xfrm_audit_state_delete(x, err ? 0 : 1,
-				audit_get_loginuid(current),
-				audit_get_sessionid(current), 0);
+	xfrm_audit_state_delete(x, err ? 0 : 1, true);
 	xfrm_state_put(x);
 
 	return err;
@@ -1719,17 +1722,13 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m
 	struct net *net = sock_net(sk);
 	unsigned int proto;
 	struct km_event c;
-	struct xfrm_audit audit_info;
 	int err, err2;
 
 	proto = pfkey_satype2proto(hdr->sadb_msg_satype);
 	if (proto == 0)
 		return -EINVAL;
 
-	audit_info.loginuid = audit_get_loginuid(current);
-	audit_info.sessionid = audit_get_sessionid(current);
-	audit_info.secid = 0;
-	err = xfrm_state_flush(net, proto, &audit_info);
+	err = xfrm_state_flush(net, proto, true);
 	err2 = unicast_flush_resp(sk, hdr);
 	if (err || err2) {
 		if (err == -ESRCH) /* empty table - go quietly */
@@ -1785,12 +1784,15 @@ static int pfkey_dump_sa(struct pfkey_sock *pfk)
 
 static void pfkey_dump_sa_done(struct pfkey_sock *pfk)
 {
-	xfrm_state_walk_done(&pfk->dump.u.state);
+	struct net *net = sock_net(&pfk->sk);
+
+	xfrm_state_walk_done(&pfk->dump.u.state, net);
 }
 
 static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs)
 {
 	u8 proto;
+	struct xfrm_address_filter *filter = NULL;
 	struct pfkey_sock *pfk = pfkey_sk(sk);
 
 	if (pfk->dump.dump != NULL)
@@ -1800,11 +1802,27 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms
 	if (proto == 0)
 		return -EINVAL;
 
+	if (ext_hdrs[SADB_X_EXT_FILTER - 1]) {
+		struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1];
+
+		filter = kmalloc(sizeof(*filter), GFP_KERNEL);
+		if (filter == NULL)
+			return -ENOMEM;
+
+		memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr,
+		       sizeof(xfrm_address_t));
+		memcpy(&filter->daddr, &xfilter->sadb_x_filter_daddr,
+		       sizeof(xfrm_address_t));
+		filter->family = xfilter->sadb_x_filter_family;
+		filter->splen = xfilter->sadb_x_filter_splen;
+		filter->dplen = xfilter->sadb_x_filter_dplen;
+	}
+
 	pfk->dump.msg_version = hdr->sadb_msg_version;
 	pfk->dump.msg_portid = hdr->sadb_msg_pid;
 	pfk->dump.dump = pfkey_dump_sa;
 	pfk->dump.done = pfkey_dump_sa_done;
-	xfrm_state_walk_init(&pfk->dump.u.state, proto);
+	xfrm_state_walk_init(&pfk->dump.u.state, proto, filter);
 
 	return pfkey_do_dump(pfk);
 }
@@ -1861,7 +1879,7 @@ static u32 gen_reqid(struct net *net)
 			reqid = IPSEC_MANUAL_REQID_MAX+1;
 		xfrm_policy_walk_init(&walk, XFRM_POLICY_TYPE_MAIN);
 		rc = xfrm_policy_walk(net, &walk, check_reqid, (void*)&reqid);
-		xfrm_policy_walk_done(&walk);
+		xfrm_policy_walk_done(&walk, net);
 		if (rc != -EEXIST)
 			return reqid;
 	} while (reqid != start);
@@ -2224,14 +2242,14 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_
 
 	sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1];
 	if (sec_ctx != NULL) {
-		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
+		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL);
 
 		if (!uctx) {
 			err = -ENOBUFS;
 			goto out;
 		}
 
-		err = security_xfrm_policy_alloc(&xp->security, uctx);
+		err = security_xfrm_policy_alloc(&xp->security, uctx, GFP_KERNEL);
 		kfree(uctx);
 
 		if (err)
@@ -2262,9 +2280,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_
 	err = xfrm_policy_insert(pol->sadb_x_policy_dir-1, xp,
 				 hdr->sadb_msg_type != SADB_X_SPDUPDATE);
 
-	xfrm_audit_policy_add(xp, err ? 0 : 1,
-			      audit_get_loginuid(current),
-			      audit_get_sessionid(current), 0);
+	xfrm_audit_policy_add(xp, err ? 0 : 1, true);
 
 	if (err)
 		goto out;
@@ -2328,12 +2344,12 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa
 
 	sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1];
 	if (sec_ctx != NULL) {
-		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
+		struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL);
 
 		if (!uctx)
 			return -ENOMEM;
 
-		err = security_xfrm_policy_alloc(&pol_ctx, uctx);
+		err = security_xfrm_policy_alloc(&pol_ctx, uctx, GFP_KERNEL);
 		kfree(uctx);
 		if (err)
 			return err;
@@ -2346,9 +2362,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa
 	if (xp == NULL)
 		return -ENOENT;
 
-	xfrm_audit_policy_delete(xp, err ? 0 : 1,
-				 audit_get_loginuid(current),
-				 audit_get_sessionid(current), 0);
+	xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
 
 	if (err)
 		goto out;
@@ -2485,6 +2499,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb,
 	struct xfrm_selector sel;
 	struct xfrm_migrate m[XFRM_MAX_DEPTH];
 	struct xfrm_kmaddress k;
+	struct net *net = sock_net(sk);
 
 	if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC - 1],
 				     ext_hdrs[SADB_EXT_ADDRESS_DST - 1]) ||
@@ -2526,7 +2541,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb,
 		sel.sport_mask = htons(0xffff);
 
 	/* set destination address info of selector */
-	sa = ext_hdrs[SADB_EXT_ADDRESS_DST - 1],
+	sa = ext_hdrs[SADB_EXT_ADDRESS_DST - 1];
 	pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr);
 	sel.prefixlen_d = sa->sadb_address_prefixlen;
 	sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto);
@@ -2558,7 +2573,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb,
 	}
 
 	return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i,
-			    kma ? &k : NULL);
+			    kma ? &k : NULL, net);
 
  out:
 	return err;
@@ -2595,9 +2610,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_
 		return -ENOENT;
 
 	if (delete) {
-		xfrm_audit_policy_delete(xp, err ? 0 : 1,
-				audit_get_loginuid(current),
-				audit_get_sessionid(current), 0);
+		xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
 
 		if (err)
 			goto out;
@@ -2659,7 +2672,9 @@ static int pfkey_dump_sp(struct pfkey_sock *pfk)
 
 static void pfkey_dump_sp_done(struct pfkey_sock *pfk)
 {
-	xfrm_policy_walk_done(&pfk->dump.u.policy);
+	struct net *net = sock_net((struct sock *)pfk);
+
+	xfrm_policy_walk_done(&pfk->dump.u.policy, net);
 }
 
 static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs)
@@ -2704,13 +2719,9 @@ static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, const struct sad
 {
 	struct net *net = sock_net(sk);
 	struct km_event c;
-	struct xfrm_audit audit_info;
 	int err, err2;
 
-	audit_info.loginuid = audit_get_loginuid(current);
-	audit_info.sessionid = audit_get_sessionid(current);
-	audit_info.secid = 0;
-	err = xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, &audit_info);
+	err = xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, true);
 	err2 = unicast_flush_resp(sk, hdr);
 	if (err || err2) {
 		if (err == -ESRCH) /* empty table - old silent behavior */
@@ -3049,6 +3060,24 @@ static u32 get_acqseq(void)
 	return res;
 }
 
+static bool pfkey_is_alive(const struct km_event *c)
+{
+	struct netns_pfkey *net_pfkey = net_generic(c->net, pfkey_net_id);
+	struct sock *sk;
+	bool is_alive = false;
+
+	rcu_read_lock();
+	sk_for_each_rcu(sk, &net_pfkey->table) {
+		if (pfkey_sk(sk)->registered) {
+			is_alive = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return is_alive;
+}
+
 static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *xp)
 {
 	struct sk_buff *skb;
@@ -3229,8 +3258,8 @@ static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt,
 		}
 		if ((*dir = verify_sec_ctx_len(p)))
 			goto out;
-		uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx);
-		*dir = security_xfrm_policy_alloc(&xp->security, uctx);
+		uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_ATOMIC);
+		*dir = security_xfrm_policy_alloc(&xp->security, uctx, GFP_ATOMIC);
 		kfree(uctx);
 
 		if (*dir)
@@ -3569,6 +3598,7 @@ static int pfkey_sendmsg(struct kiocb *kiocb,
 	struct sk_buff *skb = NULL;
 	struct sadb_msg *hdr = NULL;
 	int err;
+	struct net *net = sock_net(sk);
 
 	err = -EOPNOTSUPP;
 	if (msg->msg_flags & MSG_OOB)
@@ -3591,9 +3621,9 @@ static int pfkey_sendmsg(struct kiocb *kiocb,
 	if (!hdr)
 		goto out;
 
-	mutex_lock(&xfrm_cfg_mutex);
+	mutex_lock(&net->xfrm.xfrm_cfg_mutex);
 	err = pfkey_process(sk, skb, hdr);
-	mutex_unlock(&xfrm_cfg_mutex);
+	mutex_unlock(&net->xfrm.xfrm_cfg_mutex);
 
 out:
 	if (err && hdr && pfkey_error(hdr, err, sk) == 0)
@@ -3773,6 +3803,7 @@ static struct xfrm_mgr pfkeyv2_mgr =
 	.new_mapping	= pfkey_send_new_mapping,
 	.notify_policy	= pfkey_send_policy_notify,
 	.migrate	= pfkey_send_migrate,
+	.is_alive	= pfkey_is_alive,
 };
 
 static int __net_init pfkey_net_init(struct net *net)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 9af77d9c0ec..bea25904320 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -112,7 +112,6 @@ struct l2tp_net {
 	spinlock_t l2tp_session_hlist_lock;
 };
 
-static void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
 
 static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk)
@@ -176,7 +175,7 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id)
  * owned by userspace.  A struct sock returned from this function must be
  * released using l2tp_tunnel_sock_put once you're done with it.
  */
-struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel)
+static struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel)
 {
 	int err = 0;
 	struct socket *sock = NULL;
@@ -202,10 +201,9 @@ struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel)
 out:
 	return sk;
 }
-EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_lookup);
 
 /* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */
-void l2tp_tunnel_sock_put(struct sock *sk)
+static void l2tp_tunnel_sock_put(struct sock *sk)
 {
 	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
 	if (tunnel) {
@@ -217,7 +215,6 @@ void l2tp_tunnel_sock_put(struct sock *sk)
 	}
 	sock_put(sk);
 }
-EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_put);
 
 /* Lookup a session by id in the global session list
  */
@@ -498,52 +495,6 @@ out:
 	spin_unlock_bh(&session->reorder_q.lock);
 }
 
-static inline int l2tp_verify_udp_checksum(struct sock *sk,
-					   struct sk_buff *skb)
-{
-	struct udphdr *uh = udp_hdr(skb);
-	u16 ulen = ntohs(uh->len);
-	__wsum psum;
-
-	if (sk->sk_no_check || skb_csum_unnecessary(skb))
-		return 0;
-
-#if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == PF_INET6 && !l2tp_tunnel(sk)->v4mapped) {
-		if (!uh->check) {
-			LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n");
-			return 1;
-		}
-		if ((skb->ip_summed == CHECKSUM_COMPLETE) &&
-		    !csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-				     &ipv6_hdr(skb)->daddr, ulen,
-				     IPPROTO_UDP, skb->csum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			return 0;
-		}
-		skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-							 &ipv6_hdr(skb)->daddr,
-							 skb->len, IPPROTO_UDP,
-							 0));
-	} else
-#endif
-	{
-		struct inet_sock *inet;
-		if (!uh->check)
-			return 0;
-		inet = inet_sk(sk);
-		psum = csum_tcpudp_nofold(inet->inet_saddr, inet->inet_daddr,
-					  ulen, IPPROTO_UDP, 0);
-
-		if ((skb->ip_summed == CHECKSUM_COMPLETE) &&
-		    !csum_fold(csum_add(psum, skb->csum)))
-			return 0;
-		skb->csum = psum;
-	}
-
-	return __skb_checksum_complete(skb);
-}
-
 static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr)
 {
 	u32 nws;
@@ -898,8 +849,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
 	u16 version;
 	int length;
 
-	if (tunnel->sock && l2tp_verify_udp_checksum(tunnel->sock, skb))
-		goto discard_bad_csum;
+	/* UDP has verifed checksum */
 
 	/* UDP always verifies the packet length. */
 	__skb_pull(skb, sizeof(struct udphdr));
@@ -982,14 +932,6 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
 
 	return 0;
 
-discard_bad_csum:
-	LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name);
-	UDP_INC_STATS_USER(tunnel->l2tp_net, UDP_MIB_INERRORS, 0);
-	atomic_long_inc(&tunnel->stats.rx_errors);
-	kfree_skb(skb);
-
-	return 0;
-
 error:
 	/* Put UDP header back */
 	__skb_push(skb, sizeof(struct udphdr));
@@ -1131,13 +1073,13 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 	}
 
 	/* Queue the packet to IP for output */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 #if IS_ENABLED(CONFIG_IPV6)
-	if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped)
-		error = inet6_csk_xmit(skb, NULL);
+	if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped)
+		error = inet6_csk_xmit(tunnel->sock, skb, NULL);
 	else
 #endif
-		error = ip_queue_xmit(skb, fl);
+		error = ip_queue_xmit(tunnel->sock, skb, fl);
 
 	/* Update stats */
 	if (error >= 0) {
@@ -1153,48 +1095,6 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 	return 0;
 }
 
-/* Automatically called when the skb is freed.
- */
-static void l2tp_sock_wfree(struct sk_buff *skb)
-{
-	sock_put(skb->sk);
-}
-
-/* For data skbs that we transmit, we associate with the tunnel socket
- * but don't do accounting.
- */
-static inline void l2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
-{
-	sock_hold(sk);
-	skb->sk = sk;
-	skb->destructor = l2tp_sock_wfree;
-}
-
-#if IS_ENABLED(CONFIG_IPV6)
-static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb,
-				int udp_len)
-{
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct udphdr *uh = udp_hdr(skb);
-
-	if (!skb_dst(skb) || !skb_dst(skb)->dev ||
-	    !(skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) {
-		__wsum csum = skb_checksum(skb, 0, udp_len, 0);
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		uh->check = csum_ipv6_magic(&np->saddr, &sk->sk_v6_daddr, udp_len,
-					    IPPROTO_UDP, csum);
-		if (uh->check == 0)
-			uh->check = CSUM_MANGLED_0;
-	} else {
-		skb->ip_summed = CHECKSUM_PARTIAL;
-		skb->csum_start = skb_transport_header(skb) - skb->head;
-		skb->csum_offset = offsetof(struct udphdr, check);
-		uh->check = ~csum_ipv6_magic(&np->saddr, &sk->sk_v6_daddr,
-					     udp_len, IPPROTO_UDP, 0);
-	}
-}
-#endif
-
 /* If caller requires the skb to have a ppp header, the header must be
  * inserted in the skb data before calling this function.
  */
@@ -1206,7 +1106,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 	struct flowi *fl;
 	struct udphdr *uh;
 	struct inet_sock *inet;
-	__wsum csum;
 	int headroom;
 	int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0;
 	int udp_len;
@@ -1223,7 +1122,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 		return NET_XMIT_DROP;
 	}
 
-	skb_orphan(skb);
 	/* Setup L2TP header */
 	session->build_header(session, __skb_push(skb, hdr_len));
 
@@ -1256,41 +1154,23 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 		uh->dest = inet->inet_dport;
 		udp_len = uhlen + hdr_len + data_len;
 		uh->len = htons(udp_len);
-		uh->check = 0;
 
 		/* Calculate UDP checksum if configured to do so */
 #if IS_ENABLED(CONFIG_IPV6)
 		if (sk->sk_family == PF_INET6 && !tunnel->v4mapped)
-			l2tp_xmit_ipv6_csum(sk, skb, udp_len);
+			udp6_set_csum(udp_get_no_check6_tx(sk),
+				      skb, &inet6_sk(sk)->saddr,
+				      &sk->sk_v6_daddr, udp_len);
 		else
 #endif
-		if (sk->sk_no_check == UDP_CSUM_NOXMIT)
-			skb->ip_summed = CHECKSUM_NONE;
-		else if ((skb_dst(skb) && skb_dst(skb)->dev) &&
-			 (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM))) {
-			skb->ip_summed = CHECKSUM_COMPLETE;
-			csum = skb_checksum(skb, 0, udp_len, 0);
-			uh->check = csum_tcpudp_magic(inet->inet_saddr,
-						      inet->inet_daddr,
-						      udp_len, IPPROTO_UDP, csum);
-			if (uh->check == 0)
-				uh->check = CSUM_MANGLED_0;
-		} else {
-			skb->ip_summed = CHECKSUM_PARTIAL;
-			skb->csum_start = skb_transport_header(skb) - skb->head;
-			skb->csum_offset = offsetof(struct udphdr, check);
-			uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
-						       inet->inet_daddr,
-						       udp_len, IPPROTO_UDP, 0);
-		}
+		udp_set_csum(sk->sk_no_check_tx, skb, inet->inet_saddr,
+			     inet->inet_daddr, udp_len);
 		break;
 
 	case L2TP_ENCAPTYPE_IP:
 		break;
 	}
 
-	l2tp_skb_set_owner_w(skb, sk);
-
 	l2tp_xmit_core(session, skb, fl, data_len);
 out_unlock:
 	bh_unlock_sock(sk);
@@ -1513,6 +1393,11 @@ static int l2tp_tunnel_sock_create(struct net *net,
 					     sizeof(udp6_addr), 0);
 			if (err < 0)
 				goto out;
+
+			if (cfg->udp6_zero_tx_checksums)
+				udp_set_no_check6_tx(sock->sk, true);
+			if (cfg->udp6_zero_rx_checksums)
+				udp_set_no_check6_rx(sock->sk, true);
 		} else
 #endif
 		{
@@ -1541,7 +1426,7 @@ static int l2tp_tunnel_sock_create(struct net *net,
 		}
 
 		if (!cfg->use_udp_checksums)
-			sock->sk->sk_no_check = UDP_CSUM_NOXMIT;
+			sock->sk->sk_no_check_tx = 1;
 
 		break;
 
@@ -1811,8 +1696,6 @@ void l2tp_session_free(struct l2tp_session *session)
 	}
 
 	kfree(session);
-
-	return;
 }
 EXPORT_SYMBOL_GPL(l2tp_session_free);
 
@@ -1865,7 +1748,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_delete);
 /* We come here whenever a session's send_seq, cookie_len or
  * l2specific_len parameters are set.
  */
-static void l2tp_session_set_header_len(struct l2tp_session *session, int version)
+void l2tp_session_set_header_len(struct l2tp_session *session, int version)
 {
 	if (version == L2TP_HDR_VER_2) {
 		session->hdr_len = 6;
@@ -1878,6 +1761,7 @@ static void l2tp_session_set_header_len(struct l2tp_session *session, int versio
 	}
 
 }
+EXPORT_SYMBOL_GPL(l2tp_session_set_header_len);
 
 struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
 {
@@ -2018,7 +1902,7 @@ static int __init l2tp_init(void)
 	if (rc)
 		goto out;
 
-	l2tp_wq = alloc_workqueue("l2tp", WQ_NON_REENTRANT | WQ_UNBOUND, 0);
+	l2tp_wq = alloc_workqueue("l2tp", WQ_UNBOUND, 0);
 	if (!l2tp_wq) {
 		pr_err("alloc_workqueue failed\n");
 		rc = -ENOMEM;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 1ee9f6965d6..68aa9ffd4ae 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -162,7 +162,9 @@ struct l2tp_tunnel_cfg {
 #endif
 	u16			local_udp_port;
 	u16			peer_udp_port;
-	unsigned int		use_udp_checksums:1;
+	unsigned int		use_udp_checksums:1,
+				udp6_zero_tx_checksums:1,
+				udp6_zero_rx_checksums:1;
 };
 
 struct l2tp_tunnel {
@@ -238,8 +240,6 @@ out:
 	return tunnel;
 }
 
-struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel);
-void l2tp_tunnel_sock_put(struct sock *sk);
 struct l2tp_session *l2tp_session_find(struct net *net,
 				       struct l2tp_tunnel *tunnel,
 				       u32 session_id);
@@ -265,6 +265,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		      int length, int (*payload_hook)(struct sk_buff *skb));
 int l2tp_session_queue_purge(struct l2tp_session *session);
 int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
+void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 
 int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb,
 		  int hdr_len);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index da1a1cee1a0..369a9822488 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -403,7 +403,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 
 	/* Get and verify the address. */
 	if (msg->msg_name) {
-		struct sockaddr_l2tpip *lip = (struct sockaddr_l2tpip *) msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_l2tpip *, lip, msg->msg_name);
 		rc = -EINVAL;
 		if (msg->msg_namelen < sizeof(*lip))
 			goto out;
@@ -487,7 +487,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 
 xmit:
 	/* Queue the packet to IP for output */
-	rc = ip_queue_xmit(skb, &inet->cork.fl);
+	rc = ip_queue_xmit(sk, skb, &inet->cork.fl);
 	rcu_read_unlock();
 
 error:
@@ -512,7 +512,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
 	struct inet_sock *inet = inet_sk(sk);
 	size_t copied = 0;
 	int err = -EOPNOTSUPP;
-	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct sk_buff *skb;
 
 	if (flags & MSG_OOB)
@@ -606,7 +606,6 @@ static struct inet_protosw l2tp_ip_protosw = {
 	.protocol	= IPPROTO_L2TP,
 	.prot		= &l2tp_ip_prot,
 	.ops		= &l2tp_ip_ops,
-	.no_check	= 0,
 };
 
 static struct net_protocol l2tp_ip_protocol __read_mostly = {
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index d9b437e5500..f3f98a156ce 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -371,6 +371,9 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (addr_len < sizeof(*lsa))
 		return -EINVAL;
 
+	if (usin->sin6_family != AF_INET6)
+		return -EINVAL;
+
 	addr_type = ipv6_addr_type(&usin->sin6_addr);
 	if (addr_type & IPV6_ADDR_MULTICAST)
 		return -EINVAL;
@@ -481,8 +484,7 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 			    struct msghdr *msg, size_t len)
 {
 	struct ipv6_txoptions opt_space;
-	struct sockaddr_l2tpip6 *lsa =
-		(struct sockaddr_l2tpip6 *) msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct ipv6_txoptions *opt = NULL;
@@ -528,7 +530,6 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 				flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 				if (flowlabel == NULL)
 					return -EINVAL;
-				daddr = &flowlabel->dst;
 			}
 		}
 
@@ -598,20 +599,14 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto out;
 	}
 
-	if (hlimit < 0) {
-		if (ipv6_addr_is_multicast(&fl6.daddr))
-			hlimit = np->mcast_hops;
-		else
-			hlimit = np->hop_limit;
-		if (hlimit < 0)
-			hlimit = ip6_dst_hoplimit(dst);
-	}
+	if (hlimit < 0)
+		hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	if (tclass < 0)
 		tclass = np->tclass;
@@ -653,7 +648,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk,
 			    int flags, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
 	size_t copied = 0;
 	int err = -EOPNOTSUPP;
 	struct sk_buff *skb;
@@ -760,7 +755,6 @@ static struct inet_protosw l2tp_ip6_protosw = {
 	.protocol	= IPPROTO_L2TP,
 	.prot		= &l2tp_ip6_prot,
 	.ops		= &l2tp_ip6_ops,
-	.no_check	= 0,
 };
 
 static struct inet6_protocol l2tp_ip6_protocol __read_mostly = {
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 4cfd722e915..0ac907adb2f 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -161,6 +161,13 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 			cfg.peer_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_DPORT]);
 		if (info->attrs[L2TP_ATTR_UDP_CSUM])
 			cfg.use_udp_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_CSUM]);
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX])
+			cfg.udp6_zero_tx_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX]);
+		if (info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX])
+			cfg.udp6_zero_rx_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX]);
+#endif
 	}
 
 	if (info->attrs[L2TP_ATTR_DEBUG])
@@ -297,8 +304,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	case L2TP_ENCAPTYPE_UDP:
 		if (nla_put_u16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)) ||
 		    nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)) ||
-		    nla_put_u8(skb, L2TP_ATTR_UDP_CSUM,
-			       (sk->sk_no_check != UDP_CSUM_NOXMIT)))
+		    nla_put_u8(skb, L2TP_ATTR_UDP_CSUM, !sk->sk_no_check_tx))
 			goto nla_put_failure;
 		/* NOBREAK */
 	case L2TP_ENCAPTYPE_IP:
@@ -578,8 +584,10 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 	if (info->attrs[L2TP_ATTR_RECV_SEQ])
 		session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]);
 
-	if (info->attrs[L2TP_ATTR_SEND_SEQ])
+	if (info->attrs[L2TP_ATTR_SEND_SEQ]) {
 		session->send_seq = nla_get_u8(info->attrs[L2TP_ATTR_SEND_SEQ]);
+		l2tp_session_set_header_len(session, session->tunnel->version);
+	}
 
 	if (info->attrs[L2TP_ATTR_LNS_MODE])
 		session->lns_mode = nla_get_u8(info->attrs[L2TP_ATTR_LNS_MODE]);
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index be5fadf3473..13752d96275 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -254,12 +254,14 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
 		po = pppox_sk(sk);
 		ppp_input(&po->chan, skb);
 	} else {
-		l2tp_info(session, PPPOL2TP_MSG_DATA, "%s: socket not bound\n",
-			  session->name);
+		l2tp_dbg(session, PPPOL2TP_MSG_DATA,
+			 "%s: recv %d byte data frame, passing to L2TP socket\n",
+			 session->name, data_len);
 
-		/* Not bound. Nothing we can do, so discard. */
-		atomic_long_inc(&session->stats.rx_errors);
-		kfree_skb(skb);
+		if (sock_queue_rcv_skb(sk, skb) < 0) {
+			atomic_long_inc(&session->stats.rx_errors);
+			kfree_skb(skb);
+		}
 	}
 
 	return;
@@ -454,13 +456,11 @@ static void pppol2tp_session_close(struct l2tp_session *session)
 
 	BUG_ON(session->magic != L2TP_SESSION_MAGIC);
 
-
 	if (sock) {
 		inet_shutdown(sock, 2);
 		/* Don't let the session go away before our socket does */
 		l2tp_session_inc_refcount(session);
 	}
-	return;
 }
 
 /* Really kill the session socket. (Called from sock_put() if
@@ -474,7 +474,6 @@ static void pppol2tp_session_destruct(struct sock *sk)
 		BUG_ON(session->magic != L2TP_SESSION_MAGIC);
 		l2tp_session_dec_refcount(session);
 	}
-	return;
 }
 
 /* Called when the PPPoX socket (session) is closed.
@@ -754,9 +753,9 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	session->deref = pppol2tp_session_sock_put;
 
 	/* If PMTU discovery was enabled, use the MTU that was discovered */
-	dst = sk_dst_get(sk);
+	dst = sk_dst_get(tunnel->sock);
 	if (dst != NULL) {
-		u32 pmtu = dst_mtu(__sk_dst_get(sk));
+		u32 pmtu = dst_mtu(__sk_dst_get(tunnel->sock));
 		if (pmtu != 0)
 			session->mtu = session->mru = pmtu -
 				PPPOL2TP_HEADER_OVERHEAD;
@@ -1312,6 +1311,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
 			po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
 				PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
 		}
+		l2tp_session_set_header_len(session, session->tunnel->version);
 		l2tp_info(session, PPPOL2TP_MSG_CONTROL,
 			  "%s: set send_seq=%d\n",
 			  session->name, session->send_seq);
@@ -1365,7 +1365,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
 	int err;
 
 	if (level != SOL_PPPOL2TP)
-		return udp_prot.setsockopt(sk, level, optname, optval, optlen);
+		return -EINVAL;
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
@@ -1491,7 +1491,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname,
 	struct pppol2tp_session *ps;
 
 	if (level != SOL_PPPOL2TP)
-		return udp_prot.getsockopt(sk, level, optname, optval, optlen);
+		return -EINVAL;
 
 	if (get_user(len, optlen))
 		return -EFAULT;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 7b01b9f5846..0080d2b0a8a 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -707,7 +707,7 @@ out:
 static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 			  struct msghdr *msg, size_t len, int flags)
 {
-	struct sockaddr_llc *uaddr = (struct sockaddr_llc *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_llc *, uaddr, msg->msg_name);
 	const int nonblock = flags & MSG_DONTWAIT;
 	struct sk_buff *skb = NULL;
 	struct sock *sk = sock->sk;
@@ -715,7 +715,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 	unsigned long cpu_flags;
 	size_t copied = 0;
 	u32 peek_seq = 0;
-	u32 *seq;
+	u32 *seq, skb_len;
 	unsigned long used;
 	int target;	/* Read at least this many bytes */
 	long timeo;
@@ -812,6 +812,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 		}
 		continue;
 	found_ok_skb:
+		skb_len = skb->len;
 		/* Ok so how much can we use? */
 		used = skb->len - offset;
 		if (len < used)
@@ -844,7 +845,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 		}
 
 		/* Partial read */
-		if (used + offset < skb->len)
+		if (used + offset < skb_len)
 			continue;
 	} while (len > 0);
 
@@ -883,7 +884,7 @@ static int llc_ui_sendmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc = llc_sk(sk);
-	struct sockaddr_llc *addr = (struct sockaddr_llc *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name);
 	int flags = msg->msg_flags;
 	int noblock = flags & MSG_DONTWAIT;
 	struct sk_buff *skb;
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index cd872417796..42dc2e45c92 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -753,7 +753,7 @@ void llc_sap_remove_socket(struct llc_sap *sap, struct sock *sk)
  *
  *	Sends received pdus to the connection state machine.
  */
-static int llc_conn_rcv(struct sock* sk, struct sk_buff *skb)
+static int llc_conn_rcv(struct sock *sk, struct sk_buff *skb)
 {
 	struct llc_conn_state_ev *ev = llc_conn_ev(skb);
 
@@ -891,7 +891,7 @@ out_kfree_skb:
  *
  *     Initializes a socket with default llc values.
  */
-static void llc_sk_init(struct sock* sk)
+static void llc_sk_init(struct sock *sk)
 {
 	struct llc_sock *llc = llc_sk(sk);
 
diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c
index 2bb0ddff8c0..842851cef69 100644
--- a/net/llc/llc_core.c
+++ b/net/llc/llc_core.c
@@ -23,7 +23,7 @@
 #include <net/llc.h>
 
 LIST_HEAD(llc_sap_list);
-DEFINE_SPINLOCK(llc_sap_list_lock);
+static DEFINE_SPINLOCK(llc_sap_list_lock);
 
 /**
  *	llc_sap_alloc - allocates and initializes sap.
@@ -48,7 +48,7 @@ static struct llc_sap *llc_sap_alloc(void)
 
 static struct llc_sap *__llc_sap_find(unsigned char sap_value)
 {
-	struct llc_sap* sap;
+	struct llc_sap *sap;
 
 	list_for_each_entry(sap, &llc_sap_list, node)
 		if (sap->laddr.lsap == sap_value)
@@ -159,7 +159,6 @@ module_init(llc_init);
 module_exit(llc_exit);
 
 EXPORT_SYMBOL(llc_sap_list);
-EXPORT_SYMBOL(llc_sap_list_lock);
 EXPORT_SYMBOL(llc_sap_find);
 EXPORT_SYMBOL(llc_sap_open);
 EXPORT_SYMBOL(llc_sap_close);
diff --git a/net/llc/llc_output.c b/net/llc/llc_output.c
index 2dae8a5df23..94425e42121 100644
--- a/net/llc/llc_output.c
+++ b/net/llc/llc_output.c
@@ -43,7 +43,7 @@ int llc_mac_hdr_init(struct sk_buff *skb,
 			rc = 0;
 		break;
 	default:
-		WARN(1, "device type not supported: %d\n", skb->dev->type);
+		break;
 	}
 	return rc;
 }
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index e5850699098..06033f6c845 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -66,7 +66,7 @@ struct sk_buff *llc_alloc_frame(struct sock *sk, struct net_device *dev,
 	return skb;
 }
 
-void llc_save_primitive(struct sock *sk, struct sk_buff* skb, u8 prim)
+void llc_save_primitive(struct sock *sk, struct sk_buff *skb, u8 prim)
 {
 	struct sockaddr_llc *addr;
 
@@ -114,7 +114,7 @@ void llc_sap_rtn_pdu(struct llc_sap *sap, struct sk_buff *skb)
  *	failure.
  */
 static struct llc_sap_state_trans *llc_find_sap_trans(struct llc_sap *sap,
-						      struct sk_buff* skb)
+						      struct sk_buff *skb)
 {
 	int i = 0;
 	struct llc_sap_state_trans *rc = NULL;
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index 9d7d840aac6..1e46ffa6916 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -25,7 +25,8 @@ mac80211-y := \
 	wme.o \
 	event.o \
 	chan.o \
-	trace.o mlme.o
+	trace.o mlme.o \
+	tdls.o
 
 mac80211-$(CONFIG_MAC80211_LEDS) += led.o
 mac80211-$(CONFIG_MAC80211_DEBUGFS) += \
diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c
index 7c7df475a40..ec24378caaa 100644
--- a/net/mac80211/aes_ccm.c
+++ b/net/mac80211/aes_ccm.c
@@ -23,12 +23,13 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 			       u8 *data, size_t data_len, u8 *mic)
 {
 	struct scatterlist assoc, pt, ct[2];
-	struct {
-		struct aead_request	req;
-		u8			priv[crypto_aead_reqsize(tfm)];
-	} aead_req;
 
-	memset(&aead_req, 0, sizeof(aead_req));
+	char aead_req_data[sizeof(struct aead_request) +
+			   crypto_aead_reqsize(tfm)]
+		__aligned(__alignof__(struct aead_request));
+	struct aead_request *aead_req = (void *) aead_req_data;
+
+	memset(aead_req, 0, sizeof(aead_req_data));
 
 	sg_init_one(&pt, data, data_len);
 	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
@@ -36,23 +37,23 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 	sg_set_buf(&ct[0], data, data_len);
 	sg_set_buf(&ct[1], mic, IEEE80211_CCMP_MIC_LEN);
 
-	aead_request_set_tfm(&aead_req.req, tfm);
-	aead_request_set_assoc(&aead_req.req, &assoc, assoc.length);
-	aead_request_set_crypt(&aead_req.req, &pt, ct, data_len, b_0);
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_assoc(aead_req, &assoc, assoc.length);
+	aead_request_set_crypt(aead_req, &pt, ct, data_len, b_0);
 
-	crypto_aead_encrypt(&aead_req.req);
+	crypto_aead_encrypt(aead_req);
 }
 
 int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 			      u8 *data, size_t data_len, u8 *mic)
 {
 	struct scatterlist assoc, pt, ct[2];
-	struct {
-		struct aead_request	req;
-		u8			priv[crypto_aead_reqsize(tfm)];
-	} aead_req;
+	char aead_req_data[sizeof(struct aead_request) +
+			   crypto_aead_reqsize(tfm)]
+		__aligned(__alignof__(struct aead_request));
+	struct aead_request *aead_req = (void *) aead_req_data;
 
-	memset(&aead_req, 0, sizeof(aead_req));
+	memset(aead_req, 0, sizeof(aead_req_data));
 
 	sg_init_one(&pt, data, data_len);
 	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
@@ -60,12 +61,12 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 	sg_set_buf(&ct[0], data, data_len);
 	sg_set_buf(&ct[1], mic, IEEE80211_CCMP_MIC_LEN);
 
-	aead_request_set_tfm(&aead_req.req, tfm);
-	aead_request_set_assoc(&aead_req.req, &assoc, assoc.length);
-	aead_request_set_crypt(&aead_req.req, ct, &pt,
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_assoc(aead_req, &assoc, assoc.length);
+	aead_request_set_crypt(aead_req, ct, &pt,
 			       data_len + IEEE80211_CCMP_MIC_LEN, b_0);
 
-	return crypto_aead_decrypt(&aead_req.req);
+	return crypto_aead_decrypt(aead_req);
 }
 
 struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[])
diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c
index 537488cbf94..9b9009f9955 100644
--- a/net/mac80211/aes_cmac.c
+++ b/net/mac80211/aes_cmac.c
@@ -111,7 +111,7 @@ void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad,
 }
 
 
-struct crypto_cipher * ieee80211_aes_cmac_key_setup(const u8 key[])
+struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[])
 {
 	struct crypto_cipher *tfm;
 
diff --git a/net/mac80211/aes_cmac.h b/net/mac80211/aes_cmac.h
index 20785a64725..0ce6487af79 100644
--- a/net/mac80211/aes_cmac.h
+++ b/net/mac80211/aes_cmac.h
@@ -11,7 +11,7 @@
 
 #include <linux/crypto.h>
 
-struct crypto_cipher * ieee80211_aes_cmac_key_setup(const u8 key[]);
+struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[]);
 void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad,
 			const u8 *data, size_t data_len, u8 *mic);
 void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm);
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 13b7683de5a..ce9633a3cfb 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -107,7 +107,7 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata,
 	mgmt->u.action.u.addba_req.start_seq_num =
 					cpu_to_le16(start_seq_num << 4);
 
-	ieee80211_tx_skb_tid(sdata, skb, tid);
+	ieee80211_tx_skb(sdata, skb);
 }
 
 void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn)
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index f80e8c4c6bc..592f4b152ba 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -109,6 +109,15 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
 static int ieee80211_start_p2p_device(struct wiphy *wiphy,
 				      struct wireless_dev *wdev)
 {
+	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
+	int ret;
+
+	mutex_lock(&sdata->local->chanctx_mtx);
+	ret = ieee80211_check_combinations(sdata, NULL, 0, 0);
+	mutex_unlock(&sdata->local->chanctx_mtx);
+	if (ret < 0)
+		return ret;
+
 	return ieee80211_do_open(wdev, true);
 }
 
@@ -301,9 +310,10 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
 		if (!sta)
 			goto out;
 
-		if (pairwise)
+		if (pairwise && key_idx < NUM_DEFAULT_KEYS)
 			key = rcu_dereference(sta->ptk[key_idx]);
-		else if (key_idx < NUM_DEFAULT_KEYS)
+		else if (!pairwise &&
+			 key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS)
 			key = rcu_dereference(sta->gtk[key_idx]);
 	} else
 		key = rcu_dereference(sdata->keys[key_idx]);
@@ -450,11 +460,11 @@ void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo)
 		rinfo->flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
 	if (sta->last_rx_rate_flag & RX_FLAG_SHORT_GI)
 		rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
-	if (sta->last_rx_rate_flag & RX_FLAG_80MHZ)
+	if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_80MHZ)
 		rinfo->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
-	if (sta->last_rx_rate_flag & RX_FLAG_80P80MHZ)
+	if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_80P80MHZ)
 		rinfo->flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH;
-	if (sta->last_rx_rate_flag & RX_FLAG_160MHZ)
+	if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_160MHZ)
 		rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
 }
 
@@ -462,10 +472,15 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 {
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct ieee80211_local *local = sdata->local;
+	struct rate_control_ref *ref = NULL;
 	struct timespec uptime;
 	u64 packets = 0;
+	u32 thr = 0;
 	int i, ac;
 
+	if (test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
+		ref = local->rate_ctrl;
+
 	sinfo->generation = sdata->local->sta_generation;
 
 	sinfo->filled = STATION_INFO_INACTIVE_TIME |
@@ -577,6 +592,17 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 		sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_ASSOCIATED);
 	if (test_sta_flag(sta, WLAN_STA_TDLS_PEER))
 		sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_TDLS_PEER);
+
+	/* check if the driver has a SW RC implementation */
+	if (ref && ref->ops->get_expected_throughput)
+		thr = ref->ops->get_expected_throughput(sta->rate_ctrl_priv);
+	else
+		thr = drv_get_expected_throughput(local, &sta->sta);
+
+	if (thr != 0) {
+		sinfo->filled |= STATION_INFO_EXPECTED_THROUGHPUT;
+		sinfo->expected_throughput = thr;
+	}
 }
 
 static const char ieee80211_gstrings_sta_stats[][ETH_GSTRING_LEN] = {
@@ -767,7 +793,7 @@ static void ieee80211_get_et_strings(struct wiphy *wiphy,
 }
 
 static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev,
-				 int idx, u8 *mac, struct station_info *sinfo)
+				  int idx, u8 *mac, struct station_info *sinfo)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
@@ -797,7 +823,7 @@ static int ieee80211_dump_survey(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev,
-				 u8 *mac, struct station_info *sinfo)
+				 const u8 *mac, struct station_info *sinfo)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
@@ -827,6 +853,7 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
 	if (cfg80211_chandef_identical(&local->monitor_chandef, chandef))
 		return 0;
 
+	mutex_lock(&local->mtx);
 	mutex_lock(&local->iflist_mtx);
 	if (local->use_chanctx) {
 		sdata = rcu_dereference_protected(
@@ -845,6 +872,7 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
 	if (ret == 0)
 		local->monitor_chandef = *chandef;
 	mutex_unlock(&local->iflist_mtx);
+	mutex_unlock(&local->mtx);
 
 	return ret;
 }
@@ -873,8 +901,8 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
-int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
-			    struct cfg80211_beacon_data *params)
+static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
+				   struct cfg80211_beacon_data *params)
 {
 	struct beacon_data *new, *old;
 	int new_head_len, new_tail_len;
@@ -950,6 +978,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 			      struct cfg80211_ap_settings *params)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
 	struct beacon_data *old;
 	struct ieee80211_sub_if_data *vlan;
 	u32 changed = BSS_CHANGED_BEACON_INT |
@@ -966,13 +995,15 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	/* TODO: make hostapd tell us what it wants */
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 	sdata->needed_rx_chains = sdata->local->rx_chains;
-	sdata->radar_required = params->radar_required;
 
+	mutex_lock(&local->mtx);
 	err = ieee80211_vif_use_channel(sdata, &params->chandef,
 					IEEE80211_CHANCTX_SHARED);
+	if (!err)
+		ieee80211_vif_copy_chanctx_to_vlans(sdata, false);
+	mutex_unlock(&local->mtx);
 	if (err)
 		return err;
-	ieee80211_vif_copy_chanctx_to_vlans(sdata, false);
 
 	/*
 	 * Apply control port protocol, this allows us to
@@ -1015,8 +1046,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 					IEEE80211_P2P_OPPPS_ENABLE_BIT;
 
 	err = ieee80211_assign_beacon(sdata, &params->beacon);
-	if (err < 0)
+	if (err < 0) {
+		ieee80211_vif_release_channel(sdata);
 		return err;
+	}
 	changed |= err;
 
 	err = drv_start_ap(sdata->local, sdata);
@@ -1026,9 +1059,11 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		if (old)
 			kfree_rcu(old, rcu_head);
 		RCU_INIT_POINTER(sdata->u.ap.beacon, NULL);
+		ieee80211_vif_release_channel(sdata);
 		return err;
 	}
 
+	ieee80211_recalc_dtim(local, sdata);
 	ieee80211_bss_info_change_notify(sdata, changed);
 
 	netif_carrier_on(dev);
@@ -1046,6 +1081,7 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
 	int err;
 
 	sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	sdata_assert_lock(sdata);
 
 	/* don't allow changing the beacon while CSA is in place - offset
 	 * of channel switch counter may change
@@ -1064,6 +1100,31 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
 	return 0;
 }
 
+bool ieee80211_csa_needs_block_tx(struct ieee80211_local *local)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	lockdep_assert_held(&local->mtx);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		if (!ieee80211_sdata_running(sdata))
+			continue;
+
+		if (!sdata->vif.csa_active)
+			continue;
+
+		if (!sdata->csa_block_tx)
+			continue;
+
+		rcu_read_unlock();
+		return true;
+	}
+	rcu_read_unlock();
+
+	return false;
+}
+
 static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
@@ -1073,18 +1134,25 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	struct probe_resp *old_probe_resp;
 	struct cfg80211_chan_def chandef;
 
+	sdata_assert_lock(sdata);
+
 	old_beacon = sdata_dereference(sdata->u.ap.beacon, sdata);
 	if (!old_beacon)
 		return -ENOENT;
 	old_probe_resp = sdata_dereference(sdata->u.ap.probe_resp, sdata);
 
 	/* abort any running channel switch */
+	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = false;
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
+
 	kfree(sdata->u.ap.next_beacon);
 	sdata->u.ap.next_beacon = NULL;
 
-	cancel_work_sync(&sdata->u.ap.request_smps_work);
-
 	/* turn off carrier for this interface and dependent VLANs */
 	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
 		netif_carrier_off(vlan->dev);
@@ -1096,18 +1164,10 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	kfree_rcu(old_beacon, rcu_head);
 	if (old_probe_resp)
 		kfree_rcu(old_probe_resp, rcu_head);
+	sdata->u.ap.driver_smps_mode = IEEE80211_SMPS_OFF;
 
-	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
-		sta_info_flush_defer(vlan);
-	sta_info_flush_defer(sdata);
-	synchronize_net();
-	rcu_barrier();
-	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) {
-		sta_info_flush_cleanup(vlan);
-		ieee80211_free_keys(vlan);
-	}
-	sta_info_flush_cleanup(sdata);
-	ieee80211_free_keys(sdata);
+	__sta_info_flush(sdata, true);
+	ieee80211_free_keys(sdata, true);
 
 	sdata->vif.bss_conf.enable_beacon = false;
 	sdata->vif.bss_conf.ssid_len = 0;
@@ -1128,8 +1188,10 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf);
 	skb_queue_purge(&sdata->u.ap.ps.bc_buf);
 
+	mutex_lock(&local->mtx);
 	ieee80211_vif_copy_chanctx_to_vlans(sdata, true);
 	ieee80211_vif_release_channel(sdata);
+	mutex_unlock(&local->mtx);
 
 	return 0;
 }
@@ -1341,6 +1403,15 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 		ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
 						    params->vht_capa, sta);
 
+	if (params->opmode_notif_used) {
+		/* returned value is only needed for rc update, but the
+		 * rc isn't initialized here yet, so ignore it
+		 */
+		__ieee80211_vht_handle_opmode(sdata, sta,
+					      params->opmode_notif,
+					      band, false);
+	}
+
 	if (ieee80211_vif_is_mesh(&sdata->vif)) {
 #ifdef CONFIG_MAC80211_MESH
 		u32 changed = 0;
@@ -1402,7 +1473,8 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 }
 
 static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
-				 u8 *mac, struct station_parameters *params)
+				 const u8 *mac,
+				 struct station_parameters *params)
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
 	struct sta_info *sta;
@@ -1436,6 +1508,8 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
 	if (!(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))) {
 		sta_info_pre_move_state(sta, IEEE80211_STA_AUTH);
 		sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC);
+	} else {
+		sta->sta.tdls = true;
 	}
 
 	err = sta_apply_parameters(local, sta, params);
@@ -1469,7 +1543,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev,
-				 u8 *mac)
+				 const u8 *mac)
 {
 	struct ieee80211_sub_if_data *sdata;
 
@@ -1483,7 +1557,7 @@ static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_change_station(struct wiphy *wiphy,
-				    struct net_device *dev, u8 *mac,
+				    struct net_device *dev, const u8 *mac,
 				    struct station_parameters *params)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
@@ -1552,7 +1626,7 @@ static int ieee80211_change_station(struct wiphy *wiphy,
 
 		if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
 		    sta->sdata->u.vlan.sta) {
-			rcu_assign_pointer(sta->sdata->u.vlan.sta, NULL);
+			RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL);
 			prev_4addr = true;
 		}
 
@@ -1608,7 +1682,7 @@ out_err:
 
 #ifdef CONFIG_MAC80211_MESH
 static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev,
-				 u8 *dst, u8 *next_hop)
+			       const u8 *dst, const u8 *next_hop)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct mesh_path *mpath;
@@ -1636,7 +1710,7 @@ static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_del_mpath(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *dst)
+			       const u8 *dst)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 
@@ -1647,9 +1721,8 @@ static int ieee80211_del_mpath(struct wiphy *wiphy, struct net_device *dev,
 	return 0;
 }
 
-static int ieee80211_change_mpath(struct wiphy *wiphy,
-				    struct net_device *dev,
-				    u8 *dst, u8 *next_hop)
+static int ieee80211_change_mpath(struct wiphy *wiphy, struct net_device *dev,
+				  const u8 *dst, const u8 *next_hop)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct mesh_path *mpath;
@@ -1741,8 +1814,8 @@ static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_dump_mpath(struct wiphy *wiphy, struct net_device *dev,
-				 int idx, u8 *dst, u8 *next_hop,
-				 struct mpath_info *pinfo)
+				int idx, u8 *dst, u8 *next_hop,
+				struct mpath_info *pinfo)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct mesh_path *mpath;
@@ -1952,8 +2025,10 @@ static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev,
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 	sdata->needed_rx_chains = sdata->local->rx_chains;
 
+	mutex_lock(&sdata->local->mtx);
 	err = ieee80211_vif_use_channel(sdata, &setup->chandef,
 					IEEE80211_CHANCTX_SHARED);
+	mutex_unlock(&sdata->local->mtx);
 	if (err)
 		return err;
 
@@ -1965,7 +2040,9 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev)
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 
 	ieee80211_stop_mesh(sdata);
+	mutex_lock(&sdata->local->mtx);
 	ieee80211_vif_release_channel(sdata);
+	mutex_unlock(&sdata->local->mtx);
 
 	return 0;
 }
@@ -2587,8 +2664,8 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy,
 		int j;
 
 		sdata->rc_rateidx_mask[i] = mask->control[i].legacy;
-		memcpy(sdata->rc_rateidx_mcs_mask[i], mask->control[i].mcs,
-		       sizeof(mask->control[i].mcs));
+		memcpy(sdata->rc_rateidx_mcs_mask[i], mask->control[i].ht_mcs,
+		       sizeof(mask->control[i].ht_mcs));
 
 		sdata->rc_has_mcs_mask[i] = false;
 		if (!sband)
@@ -2624,6 +2701,18 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 	if (!roc)
 		return -ENOMEM;
 
+	/*
+	 * If the duration is zero, then the driver
+	 * wouldn't actually do anything. Set it to
+	 * 10 for now.
+	 *
+	 * TODO: cancel the off-channel operation
+	 *       when we get the SKB's TX status and
+	 *       the wait time was zero before.
+	 */
+	if (!duration)
+		duration = 10;
+
 	roc->chan = channel;
 	roc->duration = duration;
 	roc->req_duration = duration;
@@ -2634,6 +2723,24 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 	INIT_DELAYED_WORK(&roc->work, ieee80211_sw_roc_work);
 	INIT_LIST_HEAD(&roc->dependents);
 
+	/*
+	 * cookie is either the roc cookie (for normal roc)
+	 * or the SKB (for mgmt TX)
+	 */
+	if (!txskb) {
+		/* local->mtx protects this */
+		local->roc_cookie_counter++;
+		roc->cookie = local->roc_cookie_counter;
+		/* wow, you wrapped 64 bits ... more likely a bug */
+		if (WARN_ON(roc->cookie == 0)) {
+			roc->cookie = 1;
+			local->roc_cookie_counter++;
+		}
+		*cookie = roc->cookie;
+	} else {
+		*cookie = (unsigned long)txskb;
+	}
+
 	/* if there's one pending or we're scanning, queue this one */
 	if (!list_empty(&local->roc_list) ||
 	    local->scanning || local->radar_detect_enabled)
@@ -2647,18 +2754,6 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 
 	/* otherwise actually kick it off here (for error handling) */
 
-	/*
-	 * If the duration is zero, then the driver
-	 * wouldn't actually do anything. Set it to
-	 * 10 for now.
-	 *
-	 * TODO: cancel the off-channel operation
-	 *       when we get the SKB's TX status and
-	 *       the wait time was zero before.
-	 */
-	if (!duration)
-		duration = 10;
-
 	ret = drv_remain_on_channel(local, sdata, channel, duration, type);
 	if (ret) {
 		kfree(roc);
@@ -2768,24 +2863,6 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local,
 	if (!queued)
 		list_add_tail(&roc->list, &local->roc_list);
 
-	/*
-	 * cookie is either the roc cookie (for normal roc)
-	 * or the SKB (for mgmt TX)
-	 */
-	if (!txskb) {
-		/* local->mtx protects this */
-		local->roc_cookie_counter++;
-		roc->cookie = local->roc_cookie_counter;
-		/* wow, you wrapped 64 bits ... more likely a bug */
-		if (WARN_ON(roc->cookie == 0)) {
-			roc->cookie = 1;
-			local->roc_cookie_counter++;
-		}
-		*cookie = roc->cookie;
-	} else {
-		*cookie = (unsigned long)txskb;
-	}
-
 	return 0;
 }
 
@@ -2896,33 +2973,35 @@ static int ieee80211_cancel_remain_on_channel(struct wiphy *wiphy,
 
 static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 					   struct net_device *dev,
-					   struct cfg80211_chan_def *chandef)
+					   struct cfg80211_chan_def *chandef,
+					   u32 cac_time_ms)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
-	unsigned long timeout;
 	int err;
 
-	if (!list_empty(&local->roc_list) || local->scanning)
-		return -EBUSY;
+	mutex_lock(&local->mtx);
+	if (!list_empty(&local->roc_list) || local->scanning) {
+		err = -EBUSY;
+		goto out_unlock;
+	}
 
 	/* whatever, but channel contexts should not complain about that one */
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 	sdata->needed_rx_chains = local->rx_chains;
-	sdata->radar_required = true;
 
-	mutex_lock(&local->iflist_mtx);
 	err = ieee80211_vif_use_channel(sdata, chandef,
 					IEEE80211_CHANCTX_SHARED);
-	mutex_unlock(&local->iflist_mtx);
 	if (err)
-		return err;
+		goto out_unlock;
 
-	timeout = msecs_to_jiffies(IEEE80211_DFS_MIN_CAC_TIME_MS);
 	ieee80211_queue_delayed_work(&sdata->local->hw,
-				     &sdata->dfs_cac_timer_work, timeout);
+				     &sdata->dfs_cac_timer_work,
+				     msecs_to_jiffies(cac_time_ms));
 
-	return 0;
+ out_unlock:
+	mutex_unlock(&local->mtx);
+	return err;
 }
 
 static struct cfg80211_beacon_data *
@@ -2981,134 +3060,179 @@ cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon)
 	return new_beacon;
 }
 
-void ieee80211_csa_finalize_work(struct work_struct *work)
+void ieee80211_csa_finish(struct ieee80211_vif *vif)
 {
-	struct ieee80211_sub_if_data *sdata =
-		container_of(work, struct ieee80211_sub_if_data,
-			     csa_finalize_work);
-	struct ieee80211_local *local = sdata->local;
-	int err, changed = 0;
-
-	sdata_lock(sdata);
-	/* AP might have been stopped while waiting for the lock. */
-	if (!sdata->vif.csa_active)
-		goto unlock;
-
-	if (!ieee80211_sdata_running(sdata))
-		goto unlock;
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 
-	sdata->radar_required = sdata->csa_radar_required;
-	err = ieee80211_vif_change_channel(sdata, &changed);
-	if (WARN_ON(err < 0))
-		goto unlock;
-
-	if (!local->use_chanctx) {
-		local->_oper_chandef = sdata->csa_chandef;
-		ieee80211_hw_config(local, 0);
-	}
+	ieee80211_queue_work(&sdata->local->hw,
+			     &sdata->csa_finalize_work);
+}
+EXPORT_SYMBOL(ieee80211_csa_finish);
 
-	ieee80211_bss_info_change_notify(sdata, changed);
+static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata,
+					  u32 *changed)
+{
+	int err;
 
-	sdata->vif.csa_active = false;
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP:
 		err = ieee80211_assign_beacon(sdata, sdata->u.ap.next_beacon);
-		if (err < 0)
-			goto unlock;
-
-		changed |= err;
 		kfree(sdata->u.ap.next_beacon);
 		sdata->u.ap.next_beacon = NULL;
 
-		ieee80211_bss_info_change_notify(sdata, err);
+		if (err < 0)
+			return err;
+		*changed |= err;
 		break;
 	case NL80211_IFTYPE_ADHOC:
-		ieee80211_ibss_finish_csa(sdata);
+		err = ieee80211_ibss_finish_csa(sdata);
+		if (err < 0)
+			return err;
+		*changed |= err;
 		break;
 #ifdef CONFIG_MAC80211_MESH
 	case NL80211_IFTYPE_MESH_POINT:
 		err = ieee80211_mesh_finish_csa(sdata);
 		if (err < 0)
-			goto unlock;
+			return err;
+		*changed |= err;
 		break;
 #endif
 	default:
 		WARN_ON(1);
-		goto unlock;
+		return -EINVAL;
 	}
 
-	ieee80211_wake_queues_by_reason(&sdata->local->hw,
+	return 0;
+}
+
+static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	u32 changed = 0;
+	int err;
+
+	sdata_assert_lock(sdata);
+	lockdep_assert_held(&local->mtx);
+
+	sdata->radar_required = sdata->csa_radar_required;
+	err = ieee80211_vif_change_channel(sdata, &changed);
+	if (err < 0)
+		return err;
+
+	if (!local->use_chanctx) {
+		local->_oper_chandef = sdata->csa_chandef;
+		ieee80211_hw_config(local, 0);
+	}
+
+	sdata->vif.csa_active = false;
+
+	err = ieee80211_set_after_csa_beacon(sdata, &changed);
+	if (err)
+		return err;
+
+	ieee80211_bss_info_change_notify(sdata, changed);
+	cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef);
+
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
 					IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_CSA);
 
-	cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef);
+	return 0;
+}
 
-unlock:
-	sdata_unlock(sdata);
+static void ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
+{
+	if (__ieee80211_csa_finalize(sdata)) {
+		sdata_info(sdata, "failed to finalize CSA, disconnecting\n");
+		cfg80211_stop_iface(sdata->local->hw.wiphy, &sdata->wdev,
+				    GFP_KERNEL);
+	}
 }
 
-static int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
-				    struct cfg80211_csa_settings *params)
+void ieee80211_csa_finalize_work(struct work_struct *work)
 {
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_sub_if_data *sdata =
+		container_of(work, struct ieee80211_sub_if_data,
+			     csa_finalize_work);
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_chanctx_conf *chanctx_conf;
-	struct ieee80211_chanctx *chanctx;
-	struct ieee80211_if_mesh __maybe_unused *ifmsh;
-	int err, num_chanctx;
-
-	lockdep_assert_held(&sdata->wdev.mtx);
-
-	if (!list_empty(&local->roc_list) || local->scanning)
-		return -EBUSY;
 
-	if (sdata->wdev.cac_started)
-		return -EBUSY;
+	sdata_lock(sdata);
+	mutex_lock(&local->mtx);
 
-	if (cfg80211_chandef_identical(&params->chandef,
-				       &sdata->vif.bss_conf.chandef))
-		return -EINVAL;
+	/* AP might have been stopped while waiting for the lock. */
+	if (!sdata->vif.csa_active)
+		goto unlock;
 
-	rcu_read_lock();
-	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
-	if (!chanctx_conf) {
-		rcu_read_unlock();
-		return -EBUSY;
-	}
+	if (!ieee80211_sdata_running(sdata))
+		goto unlock;
 
-	/* don't handle for multi-VIF cases */
-	chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf);
-	if (chanctx->refcount > 1) {
-		rcu_read_unlock();
-		return -EBUSY;
-	}
-	num_chanctx = 0;
-	list_for_each_entry_rcu(chanctx, &local->chanctx_list, list)
-		num_chanctx++;
-	rcu_read_unlock();
+	ieee80211_csa_finalize(sdata);
 
-	if (num_chanctx > 1)
-		return -EBUSY;
+unlock:
+	mutex_unlock(&local->mtx);
+	sdata_unlock(sdata);
+}
 
-	/* don't allow another channel switch if one is already active. */
-	if (sdata->vif.csa_active)
-		return -EBUSY;
+static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
+				    struct cfg80211_csa_settings *params,
+				    u32 *changed)
+{
+	int err;
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP:
-		sdata->csa_counter_offset_beacon =
-			params->counter_offset_beacon;
-		sdata->csa_counter_offset_presp = params->counter_offset_presp;
 		sdata->u.ap.next_beacon =
 			cfg80211_beacon_dup(&params->beacon_after);
 		if (!sdata->u.ap.next_beacon)
 			return -ENOMEM;
 
+		/*
+		 * With a count of 0, we don't have to wait for any
+		 * TBTT before switching, so complete the CSA
+		 * immediately.  In theory, with a count == 1 we
+		 * should delay the switch until just before the next
+		 * TBTT, but that would complicate things so we switch
+		 * immediately too.  If we would delay the switch
+		 * until the next TBTT, we would have to set the probe
+		 * response here.
+		 *
+		 * TODO: A channel switch with count <= 1 without
+		 * sending a CSA action frame is kind of useless,
+		 * because the clients won't know we're changing
+		 * channels.  The action frame must be implemented
+		 * either here or in the userspace.
+		 */
+		if (params->count <= 1)
+			break;
+
+		if ((params->n_counter_offsets_beacon >
+		     IEEE80211_MAX_CSA_COUNTERS_NUM) ||
+		    (params->n_counter_offsets_presp >
+		     IEEE80211_MAX_CSA_COUNTERS_NUM))
+			return -EINVAL;
+
+		/* make sure we don't have garbage in other counters */
+		memset(sdata->csa_counter_offset_beacon, 0,
+		       sizeof(sdata->csa_counter_offset_beacon));
+		memset(sdata->csa_counter_offset_presp, 0,
+		       sizeof(sdata->csa_counter_offset_presp));
+
+		memcpy(sdata->csa_counter_offset_beacon,
+		       params->counter_offsets_beacon,
+		       params->n_counter_offsets_beacon * sizeof(u16));
+		memcpy(sdata->csa_counter_offset_presp,
+		       params->counter_offsets_presp,
+		       params->n_counter_offsets_presp * sizeof(u16));
+
 		err = ieee80211_assign_beacon(sdata, &params->beacon_csa);
 		if (err < 0) {
 			kfree(sdata->u.ap.next_beacon);
 			return err;
 		}
+		*changed |= err;
+
 		break;
 	case NL80211_IFTYPE_ADHOC:
 		if (!sdata->vif.bss_conf.ibss_joined)
@@ -3136,16 +3260,20 @@ static int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		    params->chandef.chan->band)
 			return -EINVAL;
 
-		err = ieee80211_ibss_csa_beacon(sdata, params);
-		if (err < 0)
-			return err;
+		/* see comments in the NL80211_IFTYPE_AP block */
+		if (params->count > 1) {
+			err = ieee80211_ibss_csa_beacon(sdata, params);
+			if (err < 0)
+				return err;
+			*changed |= err;
+		}
+
+		ieee80211_send_action_csa(sdata, params);
+
 		break;
 #ifdef CONFIG_MAC80211_MESH
-	case NL80211_IFTYPE_MESH_POINT:
-		ifmsh = &sdata->u.mesh;
-
-		if (!ifmsh->mesh_id)
-			return -EINVAL;
+	case NL80211_IFTYPE_MESH_POINT: {
+		struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
 
 		if (params->chandef.width != sdata->vif.bss_conf.chandef.width)
 			return -EINVAL;
@@ -3155,39 +3283,126 @@ static int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		    params->chandef.chan->band)
 			return -EINVAL;
 
-		ifmsh->chsw_init = true;
-		if (!ifmsh->pre_value)
-			ifmsh->pre_value = 1;
-		else
-			ifmsh->pre_value++;
+		if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_NONE) {
+			ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_INIT;
+			if (!ifmsh->pre_value)
+				ifmsh->pre_value = 1;
+			else
+				ifmsh->pre_value++;
+		}
 
-		err = ieee80211_mesh_csa_beacon(sdata, params, true);
-		if (err < 0) {
-			ifmsh->chsw_init = false;
-			return err;
+		/* see comments in the NL80211_IFTYPE_AP block */
+		if (params->count > 1) {
+			err = ieee80211_mesh_csa_beacon(sdata, params);
+			if (err < 0) {
+				ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE;
+				return err;
+			}
+			*changed |= err;
 		}
+
+		if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_INIT)
+			ieee80211_send_action_csa(sdata, params);
+
 		break;
+		}
 #endif
 	default:
 		return -EOPNOTSUPP;
 	}
 
-	sdata->csa_radar_required = params->radar_required;
+	return 0;
+}
 
-	if (params->block_tx)
-		ieee80211_stop_queues_by_reason(&local->hw,
-				IEEE80211_MAX_QUEUE_MAP,
-				IEEE80211_QUEUE_STOP_REASON_CSA);
+static int
+__ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
+			   struct cfg80211_csa_settings *params)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx_conf *conf;
+	struct ieee80211_chanctx *chanctx;
+	int err, num_chanctx, changed = 0;
+
+	sdata_assert_lock(sdata);
+	lockdep_assert_held(&local->mtx);
+
+	if (!list_empty(&local->roc_list) || local->scanning)
+		return -EBUSY;
+
+	if (sdata->wdev.cac_started)
+		return -EBUSY;
+
+	if (cfg80211_chandef_identical(&params->chandef,
+				       &sdata->vif.bss_conf.chandef))
+		return -EINVAL;
+
+	mutex_lock(&local->chanctx_mtx);
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
+	if (!conf) {
+		mutex_unlock(&local->chanctx_mtx);
+		return -EBUSY;
+	}
+
+	/* don't handle for multi-VIF cases */
+	chanctx = container_of(conf, struct ieee80211_chanctx, conf);
+	if (ieee80211_chanctx_refcount(local, chanctx) > 1) {
+		mutex_unlock(&local->chanctx_mtx);
+		return -EBUSY;
+	}
+	num_chanctx = 0;
+	list_for_each_entry_rcu(chanctx, &local->chanctx_list, list)
+		num_chanctx++;
+	mutex_unlock(&local->chanctx_mtx);
+
+	if (num_chanctx > 1)
+		return -EBUSY;
+
+	/* don't allow another channel switch if one is already active. */
+	if (sdata->vif.csa_active)
+		return -EBUSY;
+
+	err = ieee80211_set_csa_beacon(sdata, params, &changed);
+	if (err)
+		return err;
 
+	sdata->csa_radar_required = params->radar_required;
 	sdata->csa_chandef = params->chandef;
+	sdata->csa_block_tx = params->block_tx;
+	sdata->csa_current_counter = params->count;
 	sdata->vif.csa_active = true;
 
-	ieee80211_bss_info_change_notify(sdata, err);
-	drv_channel_switch_beacon(sdata, &params->chandef);
+	if (sdata->csa_block_tx)
+		ieee80211_stop_queues_by_reason(&local->hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
+
+	if (changed) {
+		ieee80211_bss_info_change_notify(sdata, changed);
+		drv_channel_switch_beacon(sdata, &params->chandef);
+	} else {
+		/* if the beacon didn't change, we can finalize immediately */
+		ieee80211_csa_finalize(sdata);
+	}
 
 	return 0;
 }
 
+int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
+			     struct cfg80211_csa_settings *params)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+	int err;
+
+	mutex_lock(&local->mtx);
+	err = __ieee80211_channel_switch(wiphy, dev, params);
+	mutex_unlock(&local->mtx);
+
+	return err;
+}
+
 static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 			     struct cfg80211_mgmt_tx_params *params,
 			     u64 *cookie)
@@ -3200,6 +3415,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 	bool need_offchan = false;
 	u32 flags;
 	int ret;
+	u8 *data;
 
 	if (params->dont_wait_for_ack)
 		flags = IEEE80211_TX_CTL_NO_ACK;
@@ -3293,7 +3509,20 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 	}
 	skb_reserve(skb, local->hw.extra_tx_headroom);
 
-	memcpy(skb_put(skb, params->len), params->buf, params->len);
+	data = skb_put(skb, params->len);
+	memcpy(data, params->buf, params->len);
+
+	/* Update CSA counters */
+	if (sdata->vif.csa_active &&
+	    (sdata->vif.type == NL80211_IFTYPE_AP ||
+	     sdata->vif.type == NL80211_IFTYPE_ADHOC) &&
+	    params->n_csa_offsets) {
+		int i;
+		u8 c = sdata->csa_current_counter;
+
+		for (i = 0; i < params->n_csa_offsets; i++)
+			data[params->csa_offsets[i]] = c;
+	}
 
 	IEEE80211_SKB_CB(skb)->flags = flags;
 
@@ -3402,320 +3631,6 @@ static int ieee80211_set_rekey_data(struct wiphy *wiphy,
 	return 0;
 }
 
-static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb)
-{
-	u8 *pos = (void *)skb_put(skb, 7);
-
-	*pos++ = WLAN_EID_EXT_CAPABILITY;
-	*pos++ = 5; /* len */
-	*pos++ = 0x0;
-	*pos++ = 0x0;
-	*pos++ = 0x0;
-	*pos++ = 0x0;
-	*pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED;
-}
-
-static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata)
-{
-	struct ieee80211_local *local = sdata->local;
-	u16 capab;
-
-	capab = 0;
-	if (ieee80211_get_sdata_band(sdata) != IEEE80211_BAND_2GHZ)
-		return capab;
-
-	if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE))
-		capab |= WLAN_CAPABILITY_SHORT_SLOT_TIME;
-	if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE))
-		capab |= WLAN_CAPABILITY_SHORT_PREAMBLE;
-
-	return capab;
-}
-
-static void ieee80211_tdls_add_link_ie(struct sk_buff *skb, u8 *src_addr,
-				       u8 *peer, u8 *bssid)
-{
-	struct ieee80211_tdls_lnkie *lnkid;
-
-	lnkid = (void *)skb_put(skb, sizeof(struct ieee80211_tdls_lnkie));
-
-	lnkid->ie_type = WLAN_EID_LINK_ID;
-	lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2;
-
-	memcpy(lnkid->bssid, bssid, ETH_ALEN);
-	memcpy(lnkid->init_sta, src_addr, ETH_ALEN);
-	memcpy(lnkid->resp_sta, peer, ETH_ALEN);
-}
-
-static int
-ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *peer, u8 action_code, u8 dialog_token,
-			       u16 status_code, struct sk_buff *skb)
-{
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
-	struct ieee80211_tdls_data *tf;
-
-	tf = (void *)skb_put(skb, offsetof(struct ieee80211_tdls_data, u));
-
-	memcpy(tf->da, peer, ETH_ALEN);
-	memcpy(tf->sa, sdata->vif.addr, ETH_ALEN);
-	tf->ether_type = cpu_to_be16(ETH_P_TDLS);
-	tf->payload_type = WLAN_TDLS_SNAP_RFTYPE;
-
-	switch (action_code) {
-	case WLAN_TDLS_SETUP_REQUEST:
-		tf->category = WLAN_CATEGORY_TDLS;
-		tf->action_code = WLAN_TDLS_SETUP_REQUEST;
-
-		skb_put(skb, sizeof(tf->u.setup_req));
-		tf->u.setup_req.dialog_token = dialog_token;
-		tf->u.setup_req.capability =
-			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
-
-		ieee80211_add_srates_ie(sdata, skb, false, band);
-		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
-		ieee80211_tdls_add_ext_capab(skb);
-		break;
-	case WLAN_TDLS_SETUP_RESPONSE:
-		tf->category = WLAN_CATEGORY_TDLS;
-		tf->action_code = WLAN_TDLS_SETUP_RESPONSE;
-
-		skb_put(skb, sizeof(tf->u.setup_resp));
-		tf->u.setup_resp.status_code = cpu_to_le16(status_code);
-		tf->u.setup_resp.dialog_token = dialog_token;
-		tf->u.setup_resp.capability =
-			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
-
-		ieee80211_add_srates_ie(sdata, skb, false, band);
-		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
-		ieee80211_tdls_add_ext_capab(skb);
-		break;
-	case WLAN_TDLS_SETUP_CONFIRM:
-		tf->category = WLAN_CATEGORY_TDLS;
-		tf->action_code = WLAN_TDLS_SETUP_CONFIRM;
-
-		skb_put(skb, sizeof(tf->u.setup_cfm));
-		tf->u.setup_cfm.status_code = cpu_to_le16(status_code);
-		tf->u.setup_cfm.dialog_token = dialog_token;
-		break;
-	case WLAN_TDLS_TEARDOWN:
-		tf->category = WLAN_CATEGORY_TDLS;
-		tf->action_code = WLAN_TDLS_TEARDOWN;
-
-		skb_put(skb, sizeof(tf->u.teardown));
-		tf->u.teardown.reason_code = cpu_to_le16(status_code);
-		break;
-	case WLAN_TDLS_DISCOVERY_REQUEST:
-		tf->category = WLAN_CATEGORY_TDLS;
-		tf->action_code = WLAN_TDLS_DISCOVERY_REQUEST;
-
-		skb_put(skb, sizeof(tf->u.discover_req));
-		tf->u.discover_req.dialog_token = dialog_token;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int
-ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev,
-			   u8 *peer, u8 action_code, u8 dialog_token,
-			   u16 status_code, struct sk_buff *skb)
-{
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
-	struct ieee80211_mgmt *mgmt;
-
-	mgmt = (void *)skb_put(skb, 24);
-	memset(mgmt, 0, 24);
-	memcpy(mgmt->da, peer, ETH_ALEN);
-	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
-	memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN);
-
-	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
-					  IEEE80211_STYPE_ACTION);
-
-	switch (action_code) {
-	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
-		skb_put(skb, 1 + sizeof(mgmt->u.action.u.tdls_discover_resp));
-		mgmt->u.action.category = WLAN_CATEGORY_PUBLIC;
-		mgmt->u.action.u.tdls_discover_resp.action_code =
-			WLAN_PUB_ACTION_TDLS_DISCOVER_RES;
-		mgmt->u.action.u.tdls_discover_resp.dialog_token =
-			dialog_token;
-		mgmt->u.action.u.tdls_discover_resp.capability =
-			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
-
-		ieee80211_add_srates_ie(sdata, skb, false, band);
-		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
-		ieee80211_tdls_add_ext_capab(skb);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *peer, u8 action_code, u8 dialog_token,
-			       u16 status_code, const u8 *extra_ies,
-			       size_t extra_ies_len)
-{
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-	struct ieee80211_local *local = sdata->local;
-	struct sk_buff *skb = NULL;
-	bool send_direct;
-	int ret;
-
-	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
-		return -ENOTSUPP;
-
-	/* make sure we are in managed mode, and associated */
-	if (sdata->vif.type != NL80211_IFTYPE_STATION ||
-	    !sdata->u.mgd.associated)
-		return -EINVAL;
-
-	tdls_dbg(sdata, "TDLS mgmt action %d peer %pM\n",
-		 action_code, peer);
-
-	skb = dev_alloc_skb(local->hw.extra_tx_headroom +
-			    max(sizeof(struct ieee80211_mgmt),
-				sizeof(struct ieee80211_tdls_data)) +
-			    50 + /* supported rates */
-			    7 + /* ext capab */
-			    extra_ies_len +
-			    sizeof(struct ieee80211_tdls_lnkie));
-	if (!skb)
-		return -ENOMEM;
-
-	skb_reserve(skb, local->hw.extra_tx_headroom);
-
-	switch (action_code) {
-	case WLAN_TDLS_SETUP_REQUEST:
-	case WLAN_TDLS_SETUP_RESPONSE:
-	case WLAN_TDLS_SETUP_CONFIRM:
-	case WLAN_TDLS_TEARDOWN:
-	case WLAN_TDLS_DISCOVERY_REQUEST:
-		ret = ieee80211_prep_tdls_encap_data(wiphy, dev, peer,
-						     action_code, dialog_token,
-						     status_code, skb);
-		send_direct = false;
-		break;
-	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
-		ret = ieee80211_prep_tdls_direct(wiphy, dev, peer, action_code,
-						 dialog_token, status_code,
-						 skb);
-		send_direct = true;
-		break;
-	default:
-		ret = -ENOTSUPP;
-		break;
-	}
-
-	if (ret < 0)
-		goto fail;
-
-	if (extra_ies_len)
-		memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len);
-
-	/* the TDLS link IE is always added last */
-	switch (action_code) {
-	case WLAN_TDLS_SETUP_REQUEST:
-	case WLAN_TDLS_SETUP_CONFIRM:
-	case WLAN_TDLS_TEARDOWN:
-	case WLAN_TDLS_DISCOVERY_REQUEST:
-		/* we are the initiator */
-		ieee80211_tdls_add_link_ie(skb, sdata->vif.addr, peer,
-					   sdata->u.mgd.bssid);
-		break;
-	case WLAN_TDLS_SETUP_RESPONSE:
-	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
-		/* we are the responder */
-		ieee80211_tdls_add_link_ie(skb, peer, sdata->vif.addr,
-					   sdata->u.mgd.bssid);
-		break;
-	default:
-		ret = -ENOTSUPP;
-		goto fail;
-	}
-
-	if (send_direct) {
-		ieee80211_tx_skb(sdata, skb);
-		return 0;
-	}
-
-	/*
-	 * According to 802.11z: Setup req/resp are sent in AC_BK, otherwise
-	 * we should default to AC_VI.
-	 */
-	switch (action_code) {
-	case WLAN_TDLS_SETUP_REQUEST:
-	case WLAN_TDLS_SETUP_RESPONSE:
-		skb_set_queue_mapping(skb, IEEE80211_AC_BK);
-		skb->priority = 2;
-		break;
-	default:
-		skb_set_queue_mapping(skb, IEEE80211_AC_VI);
-		skb->priority = 5;
-		break;
-	}
-
-	/* disable bottom halves when entering the Tx path */
-	local_bh_disable();
-	ret = ieee80211_subif_start_xmit(skb, dev);
-	local_bh_enable();
-
-	return ret;
-
-fail:
-	dev_kfree_skb(skb);
-	return ret;
-}
-
-static int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *peer, enum nl80211_tdls_operation oper)
-{
-	struct sta_info *sta;
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-
-	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
-		return -ENOTSUPP;
-
-	if (sdata->vif.type != NL80211_IFTYPE_STATION)
-		return -EINVAL;
-
-	tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer);
-
-	switch (oper) {
-	case NL80211_TDLS_ENABLE_LINK:
-		rcu_read_lock();
-		sta = sta_info_get(sdata, peer);
-		if (!sta) {
-			rcu_read_unlock();
-			return -ENOLINK;
-		}
-
-		set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH);
-		rcu_read_unlock();
-		break;
-	case NL80211_TDLS_DISABLE_LINK:
-		return sta_info_destroy_addr(sdata, peer);
-	case NL80211_TDLS_TEARDOWN:
-	case NL80211_TDLS_SETUP:
-	case NL80211_TDLS_DISCOVERY_REQ:
-		/* We don't support in-driver setup/teardown/discovery */
-		return -ENOTSUPP;
-	default:
-		return -ENOTSUPP;
-	}
-
-	return 0;
-}
-
 static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
 				  const u8 *peer, u64 *cookie)
 {
@@ -3829,7 +3744,47 @@ static void ieee80211_set_wakeup(struct wiphy *wiphy, bool enabled)
 }
 #endif
 
-struct cfg80211_ops mac80211_config_ops = {
+static int ieee80211_set_qos_map(struct wiphy *wiphy,
+				 struct net_device *dev,
+				 struct cfg80211_qos_map *qos_map)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct mac80211_qos_map *new_qos_map, *old_qos_map;
+
+	if (qos_map) {
+		new_qos_map = kzalloc(sizeof(*new_qos_map), GFP_KERNEL);
+		if (!new_qos_map)
+			return -ENOMEM;
+		memcpy(&new_qos_map->qos_map, qos_map, sizeof(*qos_map));
+	} else {
+		/* A NULL qos_map was passed to disable QoS mapping */
+		new_qos_map = NULL;
+	}
+
+	old_qos_map = sdata_dereference(sdata->qos_map, sdata);
+	rcu_assign_pointer(sdata->qos_map, new_qos_map);
+	if (old_qos_map)
+		kfree_rcu(old_qos_map, rcu_head);
+
+	return 0;
+}
+
+static int ieee80211_set_ap_chanwidth(struct wiphy *wiphy,
+				      struct net_device *dev,
+				      struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	int ret;
+	u32 changed = 0;
+
+	ret = ieee80211_vif_change_bandwidth(sdata, chandef, &changed);
+	if (ret == 0)
+		ieee80211_bss_info_change_notify(sdata, changed);
+
+	return ret;
+}
+
+const struct cfg80211_ops mac80211_config_ops = {
 	.add_virtual_intf = ieee80211_add_iface,
 	.del_virtual_intf = ieee80211_del_iface,
 	.change_virtual_intf = ieee80211_change_iface,
@@ -3908,4 +3863,6 @@ struct cfg80211_ops mac80211_config_ops = {
 	.get_channel = ieee80211_cfg_get_channel,
 	.start_radar_detection = ieee80211_start_radar_detection,
 	.channel_switch = ieee80211_channel_switch,
+	.set_qos_map = ieee80211_set_qos_map,
+	.set_ap_chanwidth = ieee80211_set_ap_chanwidth,
 };
diff --git a/net/mac80211/cfg.h b/net/mac80211/cfg.h
index 7d7879f5b00..2d51f62dc76 100644
--- a/net/mac80211/cfg.h
+++ b/net/mac80211/cfg.h
@@ -4,6 +4,6 @@
 #ifndef __CFG_H
 #define __CFG_H
 
-extern struct cfg80211_ops mac80211_config_ops;
+extern const struct cfg80211_ops mac80211_config_ops;
 
 #endif /* __CFG_H */
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index a57d5d9466b..a310e33972d 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -9,6 +9,170 @@
 #include "ieee80211_i.h"
 #include "driver-ops.h"
 
+static int ieee80211_chanctx_num_assigned(struct ieee80211_local *local,
+					  struct ieee80211_chanctx *ctx)
+{
+	struct ieee80211_sub_if_data *sdata;
+	int num = 0;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(sdata, &ctx->assigned_vifs, assigned_chanctx_list)
+		num++;
+
+	return num;
+}
+
+static int ieee80211_chanctx_num_reserved(struct ieee80211_local *local,
+					  struct ieee80211_chanctx *ctx)
+{
+	struct ieee80211_sub_if_data *sdata;
+	int num = 0;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(sdata, &ctx->reserved_vifs, reserved_chanctx_list)
+		num++;
+
+	return num;
+}
+
+int ieee80211_chanctx_refcount(struct ieee80211_local *local,
+			       struct ieee80211_chanctx *ctx)
+{
+	return ieee80211_chanctx_num_assigned(local, ctx) +
+	       ieee80211_chanctx_num_reserved(local, ctx);
+}
+
+static int ieee80211_num_chanctx(struct ieee80211_local *local)
+{
+	struct ieee80211_chanctx *ctx;
+	int num = 0;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(ctx, &local->chanctx_list, list)
+		num++;
+
+	return num;
+}
+
+static bool ieee80211_can_create_new_chanctx(struct ieee80211_local *local)
+{
+	lockdep_assert_held(&local->chanctx_mtx);
+	return ieee80211_num_chanctx(local) < ieee80211_max_num_channels(local);
+}
+
+static const struct cfg80211_chan_def *
+ieee80211_chanctx_reserved_chandef(struct ieee80211_local *local,
+				   struct ieee80211_chanctx *ctx,
+				   const struct cfg80211_chan_def *compat)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(sdata, &ctx->reserved_vifs,
+			    reserved_chanctx_list) {
+		if (!compat)
+			compat = &sdata->reserved_chandef;
+
+		compat = cfg80211_chandef_compatible(&sdata->reserved_chandef,
+						     compat);
+		if (!compat)
+			break;
+	}
+
+	return compat;
+}
+
+static const struct cfg80211_chan_def *
+ieee80211_chanctx_non_reserved_chandef(struct ieee80211_local *local,
+				       struct ieee80211_chanctx *ctx,
+				       const struct cfg80211_chan_def *compat)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(sdata, &ctx->assigned_vifs,
+			    assigned_chanctx_list) {
+		if (sdata->reserved_chanctx != NULL)
+			continue;
+
+		if (!compat)
+			compat = &sdata->vif.bss_conf.chandef;
+
+		compat = cfg80211_chandef_compatible(
+				&sdata->vif.bss_conf.chandef, compat);
+		if (!compat)
+			break;
+	}
+
+	return compat;
+}
+
+static const struct cfg80211_chan_def *
+ieee80211_chanctx_combined_chandef(struct ieee80211_local *local,
+				   struct ieee80211_chanctx *ctx,
+				   const struct cfg80211_chan_def *compat)
+{
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	compat = ieee80211_chanctx_reserved_chandef(local, ctx, compat);
+	if (!compat)
+		return NULL;
+
+	compat = ieee80211_chanctx_non_reserved_chandef(local, ctx, compat);
+	if (!compat)
+		return NULL;
+
+	return compat;
+}
+
+static bool
+ieee80211_chanctx_can_reserve_chandef(struct ieee80211_local *local,
+				      struct ieee80211_chanctx *ctx,
+				      const struct cfg80211_chan_def *def)
+{
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	if (ieee80211_chanctx_combined_chandef(local, ctx, def))
+		return true;
+
+	if (!list_empty(&ctx->reserved_vifs) &&
+	    ieee80211_chanctx_reserved_chandef(local, ctx, def))
+		return true;
+
+	return false;
+}
+
+static struct ieee80211_chanctx *
+ieee80211_find_reservation_chanctx(struct ieee80211_local *local,
+				   const struct cfg80211_chan_def *chandef,
+				   enum ieee80211_chanctx_mode mode)
+{
+	struct ieee80211_chanctx *ctx;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	if (mode == IEEE80211_CHANCTX_EXCLUSIVE)
+		return NULL;
+
+	list_for_each_entry(ctx, &local->chanctx_list, list) {
+		if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE)
+			continue;
+
+		if (!ieee80211_chanctx_can_reserve_chandef(local, ctx,
+							   chandef))
+			continue;
+
+		return ctx;
+	}
+
+	return NULL;
+}
+
 static enum nl80211_chan_width ieee80211_get_sta_bw(struct ieee80211_sta *sta)
 {
 	switch (sta->bandwidth) {
@@ -100,6 +264,12 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local,
 		}
 		max_bw = max(max_bw, width);
 	}
+
+	/* use the configured bandwidth in case of monitor interface */
+	sdata = rcu_dereference(local->monitor_sdata);
+	if (sdata && rcu_access_pointer(sdata->vif.chanctx_conf) == conf)
+		max_bw = max(max_bw, conf->def.width);
+
 	rcu_read_unlock();
 
 	return max_bw;
@@ -184,6 +354,11 @@ ieee80211_find_chanctx(struct ieee80211_local *local,
 		if (!compat)
 			continue;
 
+		compat = ieee80211_chanctx_reserved_chandef(local, ctx,
+							    compat);
+		if (!compat)
+			continue;
+
 		ieee80211_change_chanctx(local, ctx, compat);
 
 		return ctx;
@@ -196,6 +371,8 @@ static bool ieee80211_is_radar_required(struct ieee80211_local *local)
 {
 	struct ieee80211_sub_if_data *sdata;
 
+	lockdep_assert_held(&local->mtx);
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
 		if (sdata->radar_required) {
@@ -209,67 +386,91 @@ static bool ieee80211_is_radar_required(struct ieee80211_local *local)
 }
 
 static struct ieee80211_chanctx *
-ieee80211_new_chanctx(struct ieee80211_local *local,
-		      const struct cfg80211_chan_def *chandef,
-		      enum ieee80211_chanctx_mode mode)
+ieee80211_alloc_chanctx(struct ieee80211_local *local,
+			const struct cfg80211_chan_def *chandef,
+			enum ieee80211_chanctx_mode mode)
 {
 	struct ieee80211_chanctx *ctx;
-	u32 changed;
-	int err;
 
 	lockdep_assert_held(&local->chanctx_mtx);
 
 	ctx = kzalloc(sizeof(*ctx) + local->hw.chanctx_data_size, GFP_KERNEL);
 	if (!ctx)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
+	INIT_LIST_HEAD(&ctx->assigned_vifs);
+	INIT_LIST_HEAD(&ctx->reserved_vifs);
 	ctx->conf.def = *chandef;
 	ctx->conf.rx_chains_static = 1;
 	ctx->conf.rx_chains_dynamic = 1;
 	ctx->mode = mode;
 	ctx->conf.radar_enabled = ieee80211_is_radar_required(local);
 	ieee80211_recalc_chanctx_min_def(local, ctx);
+
+	return ctx;
+}
+
+static int ieee80211_add_chanctx(struct ieee80211_local *local,
+				 struct ieee80211_chanctx *ctx)
+{
+	u32 changed;
+	int err;
+
+	lockdep_assert_held(&local->mtx);
+	lockdep_assert_held(&local->chanctx_mtx);
+
 	if (!local->use_chanctx)
 		local->hw.conf.radar_enabled = ctx->conf.radar_enabled;
 
-	/* acquire mutex to prevent idle from changing */
-	mutex_lock(&local->mtx);
 	/* turn idle off *before* setting channel -- some drivers need that */
 	changed = ieee80211_idle_off(local);
 	if (changed)
 		ieee80211_hw_config(local, changed);
 
 	if (!local->use_chanctx) {
-		local->_oper_chandef = *chandef;
-		ieee80211_hw_config(local, 0);
+		local->_oper_chandef = ctx->conf.def;
+		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL);
 	} else {
 		err = drv_add_chanctx(local, ctx);
 		if (err) {
-			kfree(ctx);
-			ctx = ERR_PTR(err);
-
 			ieee80211_recalc_idle(local);
-			goto out;
+			return err;
 		}
 	}
 
-	/* and keep the mutex held until the new chanctx is on the list */
-	list_add_rcu(&ctx->list, &local->chanctx_list);
+	return 0;
+}
 
- out:
-	mutex_unlock(&local->mtx);
+static struct ieee80211_chanctx *
+ieee80211_new_chanctx(struct ieee80211_local *local,
+		      const struct cfg80211_chan_def *chandef,
+		      enum ieee80211_chanctx_mode mode)
+{
+	struct ieee80211_chanctx *ctx;
+	int err;
+
+	lockdep_assert_held(&local->mtx);
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	ctx = ieee80211_alloc_chanctx(local, chandef, mode);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
+
+	err = ieee80211_add_chanctx(local, ctx);
+	if (err) {
+		kfree(ctx);
+		return ERR_PTR(err);
+	}
 
+	list_add_rcu(&ctx->list, &local->chanctx_list);
 	return ctx;
 }
 
-static void ieee80211_free_chanctx(struct ieee80211_local *local,
-				   struct ieee80211_chanctx *ctx)
+static void ieee80211_del_chanctx(struct ieee80211_local *local,
+				  struct ieee80211_chanctx *ctx)
 {
-	bool check_single_channel = false;
 	lockdep_assert_held(&local->chanctx_mtx);
 
-	WARN_ON_ONCE(ctx->refcount != 0);
-
 	if (!local->use_chanctx) {
 		struct cfg80211_chan_def *chandef = &local->_oper_chandef;
 		chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
@@ -279,50 +480,29 @@ static void ieee80211_free_chanctx(struct ieee80211_local *local,
 		/* NOTE: Disabling radar is only valid here for
 		 * single channel context. To be sure, check it ...
 		 */
-		if (local->hw.conf.radar_enabled)
-			check_single_channel = true;
+		WARN_ON(local->hw.conf.radar_enabled &&
+			!list_empty(&local->chanctx_list));
+
 		local->hw.conf.radar_enabled = false;
 
-		ieee80211_hw_config(local, 0);
+		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL);
 	} else {
 		drv_remove_chanctx(local, ctx);
 	}
 
-	list_del_rcu(&ctx->list);
-	kfree_rcu(ctx, rcu_head);
-
-	/* throw a warning if this wasn't the only channel context. */
-	WARN_ON(check_single_channel && !list_empty(&local->chanctx_list));
-
-	mutex_lock(&local->mtx);
 	ieee80211_recalc_idle(local);
-	mutex_unlock(&local->mtx);
 }
 
-static int ieee80211_assign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
-					struct ieee80211_chanctx *ctx)
+static void ieee80211_free_chanctx(struct ieee80211_local *local,
+				   struct ieee80211_chanctx *ctx)
 {
-	struct ieee80211_local *local = sdata->local;
-	int ret;
-
 	lockdep_assert_held(&local->chanctx_mtx);
 
-	ret = drv_assign_vif_chanctx(local, sdata, ctx);
-	if (ret)
-		return ret;
-
-	rcu_assign_pointer(sdata->vif.chanctx_conf, &ctx->conf);
-	ctx->refcount++;
-
-	ieee80211_recalc_txpower(sdata);
-	ieee80211_recalc_chanctx_min_def(local, ctx);
-	sdata->vif.bss_conf.idle = false;
-
-	if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
-	    sdata->vif.type != NL80211_IFTYPE_MONITOR)
-		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IDLE);
+	WARN_ON_ONCE(ieee80211_chanctx_refcount(local, ctx) != 0);
 
-	return 0;
+	list_del_rcu(&ctx->list);
+	ieee80211_del_chanctx(local, ctx);
+	kfree_rcu(ctx, rcu_head);
 }
 
 static void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local,
@@ -358,73 +538,106 @@ static void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local,
 	ieee80211_change_chanctx(local, ctx, compat);
 }
 
-static void ieee80211_unassign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
-					   struct ieee80211_chanctx *ctx)
+static void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local,
+					   struct ieee80211_chanctx *chanctx)
 {
-	struct ieee80211_local *local = sdata->local;
+	bool radar_enabled;
 
 	lockdep_assert_held(&local->chanctx_mtx);
+	/* for setting local->radar_detect_enabled */
+	lockdep_assert_held(&local->mtx);
 
-	ctx->refcount--;
-	rcu_assign_pointer(sdata->vif.chanctx_conf, NULL);
-
-	sdata->vif.bss_conf.idle = true;
+	radar_enabled = ieee80211_is_radar_required(local);
 
-	if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
-	    sdata->vif.type != NL80211_IFTYPE_MONITOR)
-		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IDLE);
+	if (radar_enabled == chanctx->conf.radar_enabled)
+		return;
 
-	drv_unassign_vif_chanctx(local, sdata, ctx);
+	chanctx->conf.radar_enabled = radar_enabled;
+	local->radar_detect_enabled = chanctx->conf.radar_enabled;
 
-	if (ctx->refcount > 0) {
-		ieee80211_recalc_chanctx_chantype(sdata->local, ctx);
-		ieee80211_recalc_smps_chanctx(local, ctx);
-		ieee80211_recalc_radar_chanctx(local, ctx);
-		ieee80211_recalc_chanctx_min_def(local, ctx);
+	if (!local->use_chanctx) {
+		local->hw.conf.radar_enabled = chanctx->conf.radar_enabled;
+		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL);
 	}
+
+	drv_change_chanctx(local, chanctx, IEEE80211_CHANCTX_CHANGE_RADAR);
 }
 
-static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
+static int ieee80211_assign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
+					struct ieee80211_chanctx *new_ctx)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_chanctx_conf *conf;
-	struct ieee80211_chanctx *ctx;
-
-	lockdep_assert_held(&local->chanctx_mtx);
+	struct ieee80211_chanctx *curr_ctx = NULL;
+	int ret = 0;
 
 	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
 					 lockdep_is_held(&local->chanctx_mtx));
-	if (!conf)
-		return;
 
-	ctx = container_of(conf, struct ieee80211_chanctx, conf);
+	if (conf) {
+		curr_ctx = container_of(conf, struct ieee80211_chanctx, conf);
 
-	ieee80211_unassign_vif_chanctx(sdata, ctx);
-	if (ctx->refcount == 0)
-		ieee80211_free_chanctx(local, ctx);
+		drv_unassign_vif_chanctx(local, sdata, curr_ctx);
+		conf = NULL;
+		list_del(&sdata->assigned_chanctx_list);
+	}
+
+	if (new_ctx) {
+		ret = drv_assign_vif_chanctx(local, sdata, new_ctx);
+		if (ret)
+			goto out;
+
+		conf = &new_ctx->conf;
+		list_add(&sdata->assigned_chanctx_list,
+			 &new_ctx->assigned_vifs);
+	}
+
+out:
+	rcu_assign_pointer(sdata->vif.chanctx_conf, conf);
+
+	sdata->vif.bss_conf.idle = !conf;
+
+	if (curr_ctx && ieee80211_chanctx_num_assigned(local, curr_ctx) > 0) {
+		ieee80211_recalc_chanctx_chantype(local, curr_ctx);
+		ieee80211_recalc_smps_chanctx(local, curr_ctx);
+		ieee80211_recalc_radar_chanctx(local, curr_ctx);
+		ieee80211_recalc_chanctx_min_def(local, curr_ctx);
+	}
+
+	if (new_ctx && ieee80211_chanctx_num_assigned(local, new_ctx) > 0) {
+		ieee80211_recalc_txpower(sdata);
+		ieee80211_recalc_chanctx_min_def(local, new_ctx);
+	}
+
+	if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
+	    sdata->vif.type != NL80211_IFTYPE_MONITOR)
+		ieee80211_bss_info_change_notify(sdata,
+						 BSS_CHANGED_IDLE);
+
+	return ret;
 }
 
-void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local,
-				    struct ieee80211_chanctx *chanctx)
+static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
 {
-	bool radar_enabled;
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx_conf *conf;
+	struct ieee80211_chanctx *ctx;
 
 	lockdep_assert_held(&local->chanctx_mtx);
 
-	radar_enabled = ieee80211_is_radar_required(local);
-
-	if (radar_enabled == chanctx->conf.radar_enabled)
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
+	if (!conf)
 		return;
 
-	chanctx->conf.radar_enabled = radar_enabled;
-	local->radar_detect_enabled = chanctx->conf.radar_enabled;
+	ctx = container_of(conf, struct ieee80211_chanctx, conf);
 
-	if (!local->use_chanctx) {
-		local->hw.conf.radar_enabled = chanctx->conf.radar_enabled;
-		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL);
-	}
+	if (sdata->reserved_chanctx)
+		ieee80211_vif_unreserve_chanctx(sdata);
 
-	drv_change_chanctx(local, chanctx, IEEE80211_CHANCTX_CHANGE_RADAR);
+	ieee80211_assign_vif_chanctx(sdata, NULL);
+	if (ieee80211_chanctx_refcount(local, ctx) == 0)
+		ieee80211_free_chanctx(local, ctx);
 }
 
 void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
@@ -489,6 +702,13 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
 		rx_chains_static = max(rx_chains_static, needed_static);
 		rx_chains_dynamic = max(rx_chains_dynamic, needed_dynamic);
 	}
+
+	/* Disable SMPS for the monitor interface */
+	sdata = rcu_dereference(local->monitor_sdata);
+	if (sdata &&
+	    rcu_access_pointer(sdata->vif.chanctx_conf) == &chanctx->conf)
+		rx_chains_dynamic = rx_chains_static = local->rx_chains;
+
 	rcu_read_unlock();
 
 	if (!local->use_chanctx) {
@@ -516,11 +736,30 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_chanctx *ctx;
+	u8 radar_detect_width = 0;
 	int ret;
 
+	lockdep_assert_held(&local->mtx);
+
 	WARN_ON(sdata->dev && netif_carrier_ok(sdata->dev));
 
 	mutex_lock(&local->chanctx_mtx);
+
+	ret = cfg80211_chandef_dfs_required(local->hw.wiphy,
+					    chandef,
+					    sdata->wdev.iftype);
+	if (ret < 0)
+		goto out;
+	if (ret > 0)
+		radar_detect_width = BIT(chandef->width);
+
+	sdata->radar_required = ret;
+
+	ret = ieee80211_check_combinations(sdata, chandef, mode,
+					   radar_detect_width);
+	if (ret < 0)
+		goto out;
+
 	__ieee80211_vif_release_channel(sdata);
 
 	ctx = ieee80211_find_chanctx(local, chandef, mode);
@@ -536,7 +775,7 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 	ret = ieee80211_assign_vif_chanctx(sdata, ctx);
 	if (ret) {
 		/* if assign fails refcount stays the same */
-		if (ctx->refcount == 0)
+		if (ieee80211_chanctx_refcount(local, ctx) == 0)
 			ieee80211_free_chanctx(local, ctx);
 		goto out;
 	}
@@ -548,25 +787,142 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 	return ret;
 }
 
+static int __ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata,
+					  struct ieee80211_chanctx *ctx,
+					  u32 *changed)
+{
+	struct ieee80211_local *local = sdata->local;
+	const struct cfg80211_chan_def *chandef = &sdata->csa_chandef;
+	u32 chanctx_changed = 0;
+
+	if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef,
+				     IEEE80211_CHAN_DISABLED))
+		return -EINVAL;
+
+	if (ieee80211_chanctx_refcount(local, ctx) != 1)
+		return -EINVAL;
+
+	if (sdata->vif.bss_conf.chandef.width != chandef->width) {
+		chanctx_changed = IEEE80211_CHANCTX_CHANGE_WIDTH;
+		*changed |= BSS_CHANGED_BANDWIDTH;
+	}
+
+	sdata->vif.bss_conf.chandef = *chandef;
+	ctx->conf.def = *chandef;
+
+	chanctx_changed |= IEEE80211_CHANCTX_CHANGE_CHANNEL;
+	drv_change_chanctx(local, ctx, chanctx_changed);
+
+	ieee80211_recalc_chanctx_chantype(local, ctx);
+	ieee80211_recalc_smps_chanctx(local, ctx);
+	ieee80211_recalc_radar_chanctx(local, ctx);
+	ieee80211_recalc_chanctx_min_def(local, ctx);
+
+	return 0;
+}
+
 int ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata,
 				 u32 *changed)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_chanctx_conf *conf;
 	struct ieee80211_chanctx *ctx;
-	const struct cfg80211_chan_def *chandef = &sdata->csa_chandef;
 	int ret;
-	u32 chanctx_changed = 0;
+
+	lockdep_assert_held(&local->mtx);
 
 	/* should never be called if not performing a channel switch. */
 	if (WARN_ON(!sdata->vif.csa_active))
 		return -EINVAL;
 
-	if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef,
-				     IEEE80211_CHAN_DISABLED))
+	mutex_lock(&local->chanctx_mtx);
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
+	if (!conf) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ctx = container_of(conf, struct ieee80211_chanctx, conf);
+
+	ret = __ieee80211_vif_change_channel(sdata, ctx, changed);
+ out:
+	mutex_unlock(&local->chanctx_mtx);
+	return ret;
+}
+
+static void
+__ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata,
+				      bool clear)
+{
+	struct ieee80211_local *local __maybe_unused = sdata->local;
+	struct ieee80211_sub_if_data *vlan;
+	struct ieee80211_chanctx_conf *conf;
+
+	if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_AP))
+		return;
+
+	lockdep_assert_held(&local->mtx);
+
+	/* Check that conf exists, even when clearing this function
+	 * must be called with the AP's channel context still there
+	 * as it would otherwise cause VLANs to have an invalid
+	 * channel context pointer for a while, possibly pointing
+	 * to a channel context that has already been freed.
+	 */
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
+	WARN_ON(!conf);
+
+	if (clear)
+		conf = NULL;
+
+	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+		rcu_assign_pointer(vlan->vif.chanctx_conf, conf);
+}
+
+void ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata,
+					 bool clear)
+{
+	struct ieee80211_local *local = sdata->local;
+
+	mutex_lock(&local->chanctx_mtx);
+
+	__ieee80211_vif_copy_chanctx_to_vlans(sdata, clear);
+
+	mutex_unlock(&local->chanctx_mtx);
+}
+
+int ieee80211_vif_unreserve_chanctx(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_chanctx *ctx = sdata->reserved_chanctx;
+
+	lockdep_assert_held(&sdata->local->chanctx_mtx);
+
+	if (WARN_ON(!ctx))
 		return -EINVAL;
 
+	list_del(&sdata->reserved_chanctx_list);
+	sdata->reserved_chanctx = NULL;
+
+	if (ieee80211_chanctx_refcount(sdata->local, ctx) == 0)
+		ieee80211_free_chanctx(sdata->local, ctx);
+
+	return 0;
+}
+
+int ieee80211_vif_reserve_chanctx(struct ieee80211_sub_if_data *sdata,
+				  const struct cfg80211_chan_def *chandef,
+				  enum ieee80211_chanctx_mode mode,
+				  bool radar_required)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx_conf *conf;
+	struct ieee80211_chanctx *new_ctx, *curr_ctx;
+	int ret = 0;
+
 	mutex_lock(&local->chanctx_mtx);
+
 	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
 					 lockdep_is_held(&local->chanctx_mtx));
 	if (!conf) {
@@ -574,30 +930,108 @@ int ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	}
 
-	ctx = container_of(conf, struct ieee80211_chanctx, conf);
-	if (ctx->refcount != 1) {
+	curr_ctx = container_of(conf, struct ieee80211_chanctx, conf);
+
+	new_ctx = ieee80211_find_reservation_chanctx(local, chandef, mode);
+	if (!new_ctx) {
+		if (ieee80211_chanctx_refcount(local, curr_ctx) == 1 &&
+		    (local->hw.flags & IEEE80211_HW_CHANGE_RUNNING_CHANCTX)) {
+			/* if we're the only users of the chanctx and
+			 * the driver supports changing a running
+			 * context, reserve our current context
+			 */
+			new_ctx = curr_ctx;
+		} else if (ieee80211_can_create_new_chanctx(local)) {
+			/* create a new context and reserve it */
+			new_ctx = ieee80211_new_chanctx(local, chandef, mode);
+			if (IS_ERR(new_ctx)) {
+				ret = PTR_ERR(new_ctx);
+				goto out;
+			}
+		} else {
+			ret = -EBUSY;
+			goto out;
+		}
+	}
+
+	list_add(&sdata->reserved_chanctx_list, &new_ctx->reserved_vifs);
+	sdata->reserved_chanctx = new_ctx;
+	sdata->reserved_chandef = *chandef;
+	sdata->reserved_radar_required = radar_required;
+out:
+	mutex_unlock(&local->chanctx_mtx);
+	return ret;
+}
+
+int ieee80211_vif_use_reserved_context(struct ieee80211_sub_if_data *sdata,
+				       u32 *changed)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx *ctx;
+	struct ieee80211_chanctx *old_ctx;
+	struct ieee80211_chanctx_conf *conf;
+	int ret;
+	u32 tmp_changed = *changed;
+
+	/* TODO: need to recheck if the chandef is usable etc.? */
+
+	lockdep_assert_held(&local->mtx);
+
+	mutex_lock(&local->chanctx_mtx);
+
+	ctx = sdata->reserved_chanctx;
+	if (WARN_ON(!ctx)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (sdata->vif.bss_conf.chandef.width != chandef->width) {
-		chanctx_changed = IEEE80211_CHANCTX_CHANGE_WIDTH;
-		*changed |= BSS_CHANGED_BANDWIDTH;
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
+	if (!conf) {
+		ret = -EINVAL;
+		goto out;
 	}
 
-	sdata->vif.bss_conf.chandef = *chandef;
-	ctx->conf.def = *chandef;
+	old_ctx = container_of(conf, struct ieee80211_chanctx, conf);
 
-	chanctx_changed |= IEEE80211_CHANCTX_CHANGE_CHANNEL;
-	drv_change_chanctx(local, ctx, chanctx_changed);
+	if (sdata->vif.bss_conf.chandef.width != sdata->reserved_chandef.width)
+		tmp_changed |= BSS_CHANGED_BANDWIDTH;
+
+	sdata->vif.bss_conf.chandef = sdata->reserved_chandef;
+
+	/* unref our reservation */
+	sdata->reserved_chanctx = NULL;
+	sdata->radar_required = sdata->reserved_radar_required;
+	list_del(&sdata->reserved_chanctx_list);
+
+	if (old_ctx == ctx) {
+		/* This is our own context, just change it */
+		ret = __ieee80211_vif_change_channel(sdata, old_ctx,
+						     &tmp_changed);
+		if (ret)
+			goto out;
+	} else {
+		ret = ieee80211_assign_vif_chanctx(sdata, ctx);
+		if (ieee80211_chanctx_refcount(local, old_ctx) == 0)
+			ieee80211_free_chanctx(local, old_ctx);
+		if (ret) {
+			/* if assign fails refcount stays the same */
+			if (ieee80211_chanctx_refcount(local, ctx) == 0)
+				ieee80211_free_chanctx(local, ctx);
+			goto out;
+		}
+
+		if (sdata->vif.type == NL80211_IFTYPE_AP)
+			__ieee80211_vif_copy_chanctx_to_vlans(sdata, false);
+	}
+
+	*changed = tmp_changed;
 
 	ieee80211_recalc_chanctx_chantype(local, ctx);
 	ieee80211_recalc_smps_chanctx(local, ctx);
 	ieee80211_recalc_radar_chanctx(local, ctx);
 	ieee80211_recalc_chanctx_min_def(local, ctx);
-
-	ret = 0;
- out:
+out:
 	mutex_unlock(&local->chanctx_mtx);
 	return ret;
 }
@@ -655,6 +1089,8 @@ void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
 {
 	WARN_ON(sdata->dev && netif_carrier_ok(sdata->dev));
 
+	lockdep_assert_held(&sdata->local->mtx);
+
 	mutex_lock(&sdata->local->chanctx_mtx);
 	__ieee80211_vif_release_channel(sdata);
 	mutex_unlock(&sdata->local->chanctx_mtx);
@@ -679,40 +1115,6 @@ void ieee80211_vif_vlan_copy_chanctx(struct ieee80211_sub_if_data *sdata)
 	mutex_unlock(&local->chanctx_mtx);
 }
 
-void ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata,
-					 bool clear)
-{
-	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_sub_if_data *vlan;
-	struct ieee80211_chanctx_conf *conf;
-
-	ASSERT_RTNL();
-
-	if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_AP))
-		return;
-
-	mutex_lock(&local->chanctx_mtx);
-
-	/*
-	 * Check that conf exists, even when clearing this function
-	 * must be called with the AP's channel context still there
-	 * as it would otherwise cause VLANs to have an invalid
-	 * channel context pointer for a while, possibly pointing
-	 * to a channel context that has already been freed.
-	 */
-	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
-				lockdep_is_held(&local->chanctx_mtx));
-	WARN_ON(!conf);
-
-	if (clear)
-		conf = NULL;
-
-	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
-		rcu_assign_pointer(vlan->vif.chanctx_conf, conf);
-
-	mutex_unlock(&local->chanctx_mtx);
-}
-
 void ieee80211_iter_chan_contexts_atomic(
 	struct ieee80211_hw *hw,
 	void (*iter)(struct ieee80211_hw *hw,
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index fa16e54980a..0e963bc1cea 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -128,7 +128,7 @@ static ssize_t sta_tx_latency_stat_write(struct file *file,
 	if (!strcmp(buf, TX_LATENCY_DISABLED)) {
 		if (!tx_latency)
 			goto unlock;
-		rcu_assign_pointer(local->tx_latency, NULL);
+		RCU_INIT_POINTER(local->tx_latency, NULL);
 		synchronize_rcu();
 		kfree(tx_latency);
 		goto unlock;
diff --git a/net/mac80211/debugfs.h b/net/mac80211/debugfs.h
index 214ed4ecd73..60c35afee29 100644
--- a/net/mac80211/debugfs.h
+++ b/net/mac80211/debugfs.h
@@ -1,6 +1,8 @@
 #ifndef __MAC80211_DEBUGFS_H
 #define __MAC80211_DEBUGFS_H
 
+#include "ieee80211_i.h"
+
 #ifdef CONFIG_MAC80211_DEBUGFS
 void debugfs_hw_add(struct ieee80211_local *local);
 int __printf(4, 5) mac80211_format_buffer(char __user *userbuf, size_t count,
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 04b5a14c8a0..e205ebabfa5 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -34,8 +34,7 @@ static ssize_t ieee80211_if_read(
 	ssize_t ret = -EINVAL;
 
 	read_lock(&dev_base_lock);
-	if (sdata->dev->reg_state == NETREG_REGISTERED)
-		ret = (*format)(sdata, buf, sizeof(buf));
+	ret = (*format)(sdata, buf, sizeof(buf));
 	read_unlock(&dev_base_lock);
 
 	if (ret >= 0)
@@ -62,8 +61,7 @@ static ssize_t ieee80211_if_write(
 
 	ret = -ENODEV;
 	rtnl_lock();
-	if (sdata->dev->reg_state == NETREG_REGISTERED)
-		ret = (*write)(sdata, buf, count);
+	ret = (*write)(sdata, buf, count);
 	rtnl_unlock();
 
 	return ret;
@@ -133,7 +131,15 @@ static ssize_t ieee80211_if_fmt_##name(					\
 			 jiffies_to_msecs(sdata->field));		\
 }
 
-#define __IEEE80211_IF_FILE(name, _write)				\
+#define _IEEE80211_IF_FILE_OPS(name, _read, _write)			\
+static const struct file_operations name##_ops = {			\
+	.read = (_read),						\
+	.write = (_write),						\
+	.open = simple_open,						\
+	.llseek = generic_file_llseek,					\
+}
+
+#define _IEEE80211_IF_FILE_R_FN(name)					\
 static ssize_t ieee80211_if_read_##name(struct file *file,		\
 					char __user *userbuf,		\
 					size_t count, loff_t *ppos)	\
@@ -141,28 +147,34 @@ static ssize_t ieee80211_if_read_##name(struct file *file,		\
 	return ieee80211_if_read(file->private_data,			\
 				 userbuf, count, ppos,			\
 				 ieee80211_if_fmt_##name);		\
-}									\
-static const struct file_operations name##_ops = {			\
-	.read = ieee80211_if_read_##name,				\
-	.write = (_write),						\
-	.open = simple_open,						\
-	.llseek = generic_file_llseek,					\
 }
 
-#define __IEEE80211_IF_FILE_W(name)					\
+#define _IEEE80211_IF_FILE_W_FN(name)					\
 static ssize_t ieee80211_if_write_##name(struct file *file,		\
 					 const char __user *userbuf,	\
 					 size_t count, loff_t *ppos)	\
 {									\
 	return ieee80211_if_write(file->private_data, userbuf, count,	\
 				  ppos, ieee80211_if_parse_##name);	\
-}									\
-__IEEE80211_IF_FILE(name, ieee80211_if_write_##name)
+}
+
+#define IEEE80211_IF_FILE_R(name)					\
+	_IEEE80211_IF_FILE_R_FN(name)					\
+	_IEEE80211_IF_FILE_OPS(name, ieee80211_if_read_##name, NULL)
+
+#define IEEE80211_IF_FILE_W(name)					\
+	_IEEE80211_IF_FILE_W_FN(name)					\
+	_IEEE80211_IF_FILE_OPS(name, NULL, ieee80211_if_write_##name)
 
+#define IEEE80211_IF_FILE_RW(name)					\
+	_IEEE80211_IF_FILE_R_FN(name)					\
+	_IEEE80211_IF_FILE_W_FN(name)					\
+	_IEEE80211_IF_FILE_OPS(name, ieee80211_if_read_##name,		\
+			       ieee80211_if_write_##name)
 
 #define IEEE80211_IF_FILE(name, field, format)				\
-		IEEE80211_IF_FMT_##format(name, field)			\
-		__IEEE80211_IF_FILE(name, NULL)
+	IEEE80211_IF_FMT_##format(name, field)				\
+	IEEE80211_IF_FILE_R(name)
 
 /* common attributes */
 IEEE80211_IF_FILE(drop_unencrypted, drop_unencrypted, DEC);
@@ -199,7 +211,7 @@ ieee80211_if_fmt_hw_queues(const struct ieee80211_sub_if_data *sdata,
 
 	return len;
 }
-__IEEE80211_IF_FILE(hw_queues, NULL);
+IEEE80211_IF_FILE_R(hw_queues);
 
 /* STA attributes */
 IEEE80211_IF_FILE(bssid, u.mgd.bssid, MAC);
@@ -275,14 +287,7 @@ static ssize_t ieee80211_if_parse_smps(struct ieee80211_sub_if_data *sdata,
 
 	return -EINVAL;
 }
-
-__IEEE80211_IF_FILE_W(smps);
-
-static ssize_t ieee80211_if_fmt_tkip_mic_test(
-	const struct ieee80211_sub_if_data *sdata, char *buf, int buflen)
-{
-	return -EOPNOTSUPP;
-}
+IEEE80211_IF_FILE_RW(smps);
 
 static ssize_t ieee80211_if_parse_tkip_mic_test(
 	struct ieee80211_sub_if_data *sdata, const char *buf, int buflen)
@@ -349,8 +354,19 @@ static ssize_t ieee80211_if_parse_tkip_mic_test(
 
 	return buflen;
 }
+IEEE80211_IF_FILE_W(tkip_mic_test);
+
+static ssize_t ieee80211_if_parse_beacon_loss(
+	struct ieee80211_sub_if_data *sdata, const char *buf, int buflen)
+{
+	if (!ieee80211_sdata_running(sdata) || !sdata->vif.bss_conf.assoc)
+		return -ENOTCONN;
 
-__IEEE80211_IF_FILE_W(tkip_mic_test);
+	ieee80211_beacon_loss(&sdata->vif);
+
+	return buflen;
+}
+IEEE80211_IF_FILE_W(beacon_loss);
 
 static ssize_t ieee80211_if_fmt_uapsd_queues(
 	const struct ieee80211_sub_if_data *sdata, char *buf, int buflen)
@@ -378,7 +394,7 @@ static ssize_t ieee80211_if_parse_uapsd_queues(
 
 	return buflen;
 }
-__IEEE80211_IF_FILE_W(uapsd_queues);
+IEEE80211_IF_FILE_RW(uapsd_queues);
 
 static ssize_t ieee80211_if_fmt_uapsd_max_sp_len(
 	const struct ieee80211_sub_if_data *sdata, char *buf, int buflen)
@@ -406,7 +422,7 @@ static ssize_t ieee80211_if_parse_uapsd_max_sp_len(
 
 	return buflen;
 }
-__IEEE80211_IF_FILE_W(uapsd_max_sp_len);
+IEEE80211_IF_FILE_RW(uapsd_max_sp_len);
 
 /* AP attributes */
 IEEE80211_IF_FILE(num_mcast_sta, u.ap.num_mcast_sta, ATOMIC);
@@ -419,7 +435,7 @@ static ssize_t ieee80211_if_fmt_num_buffered_multicast(
 	return scnprintf(buf, buflen, "%u\n",
 			 skb_queue_len(&sdata->u.ap.ps.bc_buf));
 }
-__IEEE80211_IF_FILE(num_buffered_multicast, NULL);
+IEEE80211_IF_FILE_R(num_buffered_multicast);
 
 /* IBSS attributes */
 static ssize_t ieee80211_if_fmt_tsf(
@@ -468,9 +484,10 @@ static ssize_t ieee80211_if_parse_tsf(
 		}
 	}
 
+	ieee80211_recalc_dtim(local, sdata);
 	return buflen;
 }
-__IEEE80211_IF_FILE_W(tsf);
+IEEE80211_IF_FILE_RW(tsf);
 
 
 /* WDS attributes */
@@ -562,6 +579,7 @@ static void add_sta_files(struct ieee80211_sub_if_data *sdata)
 	DEBUGFS_ADD(beacon_timeout);
 	DEBUGFS_ADD_MODE(smps, 0600);
 	DEBUGFS_ADD_MODE(tkip_mic_test, 0200);
+	DEBUGFS_ADD_MODE(beacon_loss, 0200);
 	DEBUGFS_ADD_MODE(uapsd_queues, 0600);
 	DEBUGFS_ADD_MODE(uapsd_max_sp_len, 0600);
 }
diff --git a/net/mac80211/debugfs_netdev.h b/net/mac80211/debugfs_netdev.h
index 79025e79f4d..9f5501a9a79 100644
--- a/net/mac80211/debugfs_netdev.h
+++ b/net/mac80211/debugfs_netdev.h
@@ -3,6 +3,8 @@
 #ifndef __IEEE80211_DEBUGFS_NETDEV_H
 #define __IEEE80211_DEBUGFS_NETDEV_H
 
+#include "ieee80211_i.h"
+
 #ifdef CONFIG_MAC80211_DEBUGFS
 void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata);
 void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata);
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 80194b557a0..2ecb4deddb5 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -195,7 +195,7 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
 static ssize_t sta_agg_status_write(struct file *file, const char __user *userbuf,
 				    size_t count, loff_t *ppos)
 {
-	char _buf[12], *buf = _buf;
+	char _buf[12] = {}, *buf = _buf;
 	struct sta_info *sta = file->private_data;
 	bool start, tx;
 	unsigned long tid;
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 5d03c47c0a4..bd782dcffcc 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -5,11 +5,11 @@
 #include "ieee80211_i.h"
 #include "trace.h"
 
-static inline void check_sdata_in_driver(struct ieee80211_sub_if_data *sdata)
+static inline bool check_sdata_in_driver(struct ieee80211_sub_if_data *sdata)
 {
-	WARN(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER),
-	     "%s:  Failed check-sdata-in-driver check, flags: 0x%x\n",
-	     sdata->dev ? sdata->dev->name : sdata->name, sdata->flags);
+	return !WARN(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER),
+		     "%s:  Failed check-sdata-in-driver check, flags: 0x%x\n",
+		     sdata->dev ? sdata->dev->name : sdata->name, sdata->flags);
 }
 
 static inline struct ieee80211_sub_if_data *
@@ -168,7 +168,8 @@ static inline int drv_change_interface(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_change_interface(local, sdata, type, p2p);
 	ret = local->ops->change_interface(&local->hw, &sdata->vif, type, p2p);
@@ -181,7 +182,8 @@ static inline void drv_remove_interface(struct ieee80211_local *local,
 {
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_remove_interface(local, sdata);
 	local->ops->remove_interface(&local->hw, &sdata->vif);
@@ -219,7 +221,8 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local,
 			 sdata->vif.type == NL80211_IFTYPE_MONITOR))
 		return;
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_bss_info_changed(local, sdata, info, changed);
 	if (local->ops->bss_info_changed)
@@ -242,22 +245,6 @@ static inline u64 drv_prepare_multicast(struct ieee80211_local *local,
 	return ret;
 }
 
-static inline void drv_set_multicast_list(struct ieee80211_local *local,
-					  struct ieee80211_sub_if_data *sdata,
-					  struct netdev_hw_addr_list *mc_list)
-{
-	bool allmulti = sdata->flags & IEEE80211_SDATA_ALLMULTI;
-
-	trace_drv_set_multicast_list(local, sdata, mc_list->count);
-
-	check_sdata_in_driver(sdata);
-
-	if (local->ops->set_multicast_list)
-		local->ops->set_multicast_list(&local->hw, &sdata->vif,
-					       allmulti, mc_list);
-	trace_drv_return_void(local);
-}
-
 static inline void drv_configure_filter(struct ieee80211_local *local,
 					unsigned int changed_flags,
 					unsigned int *total_flags,
@@ -294,7 +281,8 @@ static inline int drv_set_key(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_set_key(local, cmd, sdata, sta, key);
 	ret = local->ops->set_key(&local->hw, cmd, &sdata->vif, sta, key);
@@ -314,7 +302,8 @@ static inline void drv_update_tkip_key(struct ieee80211_local *local,
 		ista = &sta->sta;
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_update_tkip_key(local, sdata, conf, ista, iv32);
 	if (local->ops->update_tkip_key)
@@ -331,7 +320,8 @@ static inline int drv_hw_scan(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_hw_scan(local, sdata);
 	ret = local->ops->hw_scan(&local->hw, &sdata->vif, req);
@@ -344,7 +334,8 @@ static inline void drv_cancel_hw_scan(struct ieee80211_local *local,
 {
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_cancel_hw_scan(local, sdata);
 	local->ops->cancel_hw_scan(&local->hw, &sdata->vif);
@@ -361,7 +352,8 @@ drv_sched_scan_start(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_sched_scan_start(local, sdata);
 	ret = local->ops->sched_scan_start(&local->hw, &sdata->vif,
@@ -370,16 +362,21 @@ drv_sched_scan_start(struct ieee80211_local *local,
 	return ret;
 }
 
-static inline void drv_sched_scan_stop(struct ieee80211_local *local,
-				       struct ieee80211_sub_if_data *sdata)
+static inline int drv_sched_scan_stop(struct ieee80211_local *local,
+				      struct ieee80211_sub_if_data *sdata)
 {
+	int ret;
+
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_sched_scan_stop(local, sdata);
-	local->ops->sched_scan_stop(&local->hw, &sdata->vif);
-	trace_drv_return_void(local);
+	ret = local->ops->sched_scan_stop(&local->hw, &sdata->vif);
+	trace_drv_return_int(local, ret);
+
+	return ret;
 }
 
 static inline void drv_sw_scan_start(struct ieee80211_local *local)
@@ -474,7 +471,8 @@ static inline void drv_sta_notify(struct ieee80211_local *local,
 				  struct ieee80211_sta *sta)
 {
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_sta_notify(local, sdata, cmd, sta);
 	if (local->ops->sta_notify)
@@ -491,7 +489,8 @@ static inline int drv_sta_add(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_sta_add(local, sdata, sta);
 	if (local->ops->sta_add)
@@ -509,7 +508,8 @@ static inline void drv_sta_remove(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_sta_remove(local, sdata, sta);
 	if (local->ops->sta_remove)
@@ -527,7 +527,8 @@ static inline void drv_sta_add_debugfs(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	if (local->ops->sta_add_debugfs)
 		local->ops->sta_add_debugfs(&local->hw, &sdata->vif,
@@ -550,6 +551,23 @@ static inline void drv_sta_remove_debugfs(struct ieee80211_local *local,
 }
 #endif
 
+static inline void drv_sta_pre_rcu_remove(struct ieee80211_local *local,
+					  struct ieee80211_sub_if_data *sdata,
+					  struct sta_info *sta)
+{
+	might_sleep();
+
+	sdata = get_bss_sdata(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	trace_drv_sta_pre_rcu_remove(local, sdata, &sta->sta);
+	if (local->ops->sta_pre_rcu_remove)
+		local->ops->sta_pre_rcu_remove(&local->hw, &sdata->vif,
+					       &sta->sta);
+	trace_drv_return_void(local);
+}
+
 static inline __must_check
 int drv_sta_state(struct ieee80211_local *local,
 		  struct ieee80211_sub_if_data *sdata,
@@ -562,7 +580,8 @@ int drv_sta_state(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_sta_state(local, sdata, &sta->sta, old_state, new_state);
 	if (local->ops->sta_state) {
@@ -586,7 +605,8 @@ static inline void drv_sta_rc_update(struct ieee80211_local *local,
 				     struct ieee80211_sta *sta, u32 changed)
 {
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	WARN_ON(changed & IEEE80211_RC_SUPP_RATES_CHANGED &&
 		(sdata->vif.type != NL80211_IFTYPE_ADHOC &&
@@ -608,7 +628,8 @@ static inline int drv_conf_tx(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_conf_tx(local, sdata, ac, params);
 	if (local->ops->conf_tx)
@@ -625,7 +646,8 @@ static inline u64 drv_get_tsf(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return ret;
 
 	trace_drv_get_tsf(local, sdata);
 	if (local->ops->get_tsf)
@@ -640,7 +662,8 @@ static inline void drv_set_tsf(struct ieee80211_local *local,
 {
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_set_tsf(local, sdata, tsf);
 	if (local->ops->set_tsf)
@@ -653,7 +676,8 @@ static inline void drv_reset_tsf(struct ieee80211_local *local,
 {
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_reset_tsf(local, sdata);
 	if (local->ops->reset_tsf)
@@ -685,7 +709,8 @@ static inline int drv_ampdu_action(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn, buf_size);
 
@@ -722,13 +747,19 @@ static inline void drv_rfkill_poll(struct ieee80211_local *local)
 }
 
 static inline void drv_flush(struct ieee80211_local *local,
+			     struct ieee80211_sub_if_data *sdata,
 			     u32 queues, bool drop)
 {
+	struct ieee80211_vif *vif = sdata ? &sdata->vif : NULL;
+
 	might_sleep();
 
+	if (sdata && !check_sdata_in_driver(sdata))
+		return;
+
 	trace_drv_flush(local, queues, drop);
 	if (local->ops->flush)
-		local->ops->flush(&local->hw, queues, drop);
+		local->ops->flush(&local->hw, vif, queues, drop);
 	trace_drv_return_void(local);
 }
 
@@ -844,7 +875,8 @@ static inline int drv_set_bitrate_mask(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_set_bitrate_mask(local, sdata, mask);
 	if (local->ops->set_bitrate_mask)
@@ -859,7 +891,8 @@ static inline void drv_set_rekey_data(struct ieee80211_local *local,
 				      struct ieee80211_sub_if_data *sdata,
 				      struct cfg80211_gtk_rekey_data *data)
 {
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_set_rekey_data(local, sdata, data);
 	if (local->ops->set_rekey_data)
@@ -927,7 +960,8 @@ static inline void drv_mgd_prepare_tx(struct ieee80211_local *local,
 {
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 	WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION);
 
 	trace_drv_mgd_prepare_tx(local, sdata);
@@ -954,6 +988,9 @@ static inline int drv_add_chanctx(struct ieee80211_local *local,
 static inline void drv_remove_chanctx(struct ieee80211_local *local,
 				      struct ieee80211_chanctx *ctx)
 {
+	if (WARN_ON(!ctx->driver_present))
+		return;
+
 	trace_drv_remove_chanctx(local, ctx);
 	if (local->ops->remove_chanctx)
 		local->ops->remove_chanctx(&local->hw, &ctx->conf);
@@ -979,7 +1016,8 @@ static inline int drv_assign_vif_chanctx(struct ieee80211_local *local,
 {
 	int ret = 0;
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_assign_vif_chanctx(local, sdata, ctx);
 	if (local->ops->assign_vif_chanctx) {
@@ -997,7 +1035,8 @@ static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local,
 					    struct ieee80211_sub_if_data *sdata,
 					    struct ieee80211_chanctx *ctx)
 {
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_unassign_vif_chanctx(local, sdata, ctx);
 	if (local->ops->unassign_vif_chanctx) {
@@ -1009,12 +1048,66 @@ static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline int
+drv_switch_vif_chanctx(struct ieee80211_local *local,
+		       struct ieee80211_vif_chanctx_switch *vifs,
+		       int n_vifs,
+		       enum ieee80211_chanctx_switch_mode mode)
+{
+	int ret = 0;
+	int i;
+
+	if (!local->ops->switch_vif_chanctx)
+		return -EOPNOTSUPP;
+
+	for (i = 0; i < n_vifs; i++) {
+		struct ieee80211_chanctx *new_ctx =
+			container_of(vifs[i].new_ctx,
+				     struct ieee80211_chanctx,
+				     conf);
+		struct ieee80211_chanctx *old_ctx =
+			container_of(vifs[i].old_ctx,
+				     struct ieee80211_chanctx,
+				     conf);
+
+		WARN_ON_ONCE(!old_ctx->driver_present);
+		WARN_ON_ONCE((mode == CHANCTX_SWMODE_SWAP_CONTEXTS &&
+			      new_ctx->driver_present) ||
+			     (mode == CHANCTX_SWMODE_REASSIGN_VIF &&
+			      !new_ctx->driver_present));
+	}
+
+	trace_drv_switch_vif_chanctx(local, vifs, n_vifs, mode);
+	ret = local->ops->switch_vif_chanctx(&local->hw,
+					     vifs, n_vifs, mode);
+	trace_drv_return_int(local, ret);
+
+	if (!ret && mode == CHANCTX_SWMODE_SWAP_CONTEXTS) {
+		for (i = 0; i < n_vifs; i++) {
+			struct ieee80211_chanctx *new_ctx =
+				container_of(vifs[i].new_ctx,
+					     struct ieee80211_chanctx,
+					     conf);
+			struct ieee80211_chanctx *old_ctx =
+				container_of(vifs[i].old_ctx,
+					     struct ieee80211_chanctx,
+					     conf);
+
+			new_ctx->driver_present = true;
+			old_ctx->driver_present = false;
+		}
+	}
+
+	return ret;
+}
+
 static inline int drv_start_ap(struct ieee80211_local *local,
 			       struct ieee80211_sub_if_data *sdata)
 {
 	int ret = 0;
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_start_ap(local, sdata, &sdata->vif.bss_conf);
 	if (local->ops->start_ap)
@@ -1026,7 +1119,8 @@ static inline int drv_start_ap(struct ieee80211_local *local,
 static inline void drv_stop_ap(struct ieee80211_local *local,
 			       struct ieee80211_sub_if_data *sdata)
 {
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_stop_ap(local, sdata);
 	if (local->ops->stop_ap)
@@ -1049,7 +1143,8 @@ drv_set_default_unicast_key(struct ieee80211_local *local,
 			    struct ieee80211_sub_if_data *sdata,
 			    int key_idx)
 {
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	WARN_ON_ONCE(key_idx < -1 || key_idx > 3);
 
@@ -1091,7 +1186,8 @@ static inline int drv_join_ibss(struct ieee80211_local *local,
 	int ret = 0;
 
 	might_sleep();
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_join_ibss(local, sdata, &sdata->vif.bss_conf);
 	if (local->ops->join_ibss)
@@ -1104,7 +1200,8 @@ static inline void drv_leave_ibss(struct ieee80211_local *local,
 				  struct ieee80211_sub_if_data *sdata)
 {
 	might_sleep();
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_leave_ibss(local, sdata);
 	if (local->ops->leave_ibss)
@@ -1112,4 +1209,17 @@ static inline void drv_leave_ibss(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline u32 drv_get_expected_throughput(struct ieee80211_local *local,
+					      struct ieee80211_sta *sta)
+{
+	u32 ret = 0;
+
+	trace_drv_get_expected_throughput(sta);
+	if (local->ops->get_expected_throughput)
+		ret = local->ops->get_expected_throughput(sta);
+	trace_drv_return_u32(local, ret);
+
+	return ret;
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index 9a8be8f6922..15702ff64a4 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -31,6 +31,18 @@ static void __check_htcap_disable(struct ieee80211_ht_cap *ht_capa,
 	}
 }
 
+static void __check_htcap_enable(struct ieee80211_ht_cap *ht_capa,
+				  struct ieee80211_ht_cap *ht_capa_mask,
+				  struct ieee80211_sta_ht_cap *ht_cap,
+				  u16 flag)
+{
+	__le16 le_flag = cpu_to_le16(flag);
+
+	if ((ht_capa_mask->cap_info & le_flag) &&
+	    (ht_capa->cap_info & le_flag))
+		ht_cap->cap |= flag;
+}
+
 void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
 				     struct ieee80211_sta_ht_cap *ht_cap)
 {
@@ -59,7 +71,7 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
 	smask = (u8 *)(&ht_capa_mask->mcs.rx_mask);
 
 	/* NOTE:  If you add more over-rides here, update register_hw
-	 * ht_capa_mod_msk logic in main.c as well.
+	 * ht_capa_mod_mask logic in main.c as well.
 	 * And, if this method can ever change ht_cap.ht_supported, fix
 	 * the check in ieee80211_add_ht_ie.
 	 */
@@ -86,6 +98,14 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
 	__check_htcap_disable(ht_capa, ht_capa_mask, ht_cap,
 			      IEEE80211_HT_CAP_MAX_AMSDU);
 
+	/* Allow user to disable LDPC */
+	__check_htcap_disable(ht_capa, ht_capa_mask, ht_cap,
+			      IEEE80211_HT_CAP_LDPC_CODING);
+
+	/* Allow user to enable 40 MHz intolerant bit. */
+	__check_htcap_enable(ht_capa, ht_capa_mask, ht_cap,
+			     IEEE80211_HT_CAP_40MHZ_INTOLERANT);
+
 	/* Allow user to decrease AMPDU factor */
 	if (ht_capa_mask->ampdu_params_info &
 	    IEEE80211_HT_AMPDU_PARM_FACTOR) {
@@ -375,7 +395,7 @@ void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata,
 	mgmt->u.action.u.delba.params = cpu_to_le16(params);
 	mgmt->u.action.u.delba.reason_code = cpu_to_le16(reason_code);
 
-	ieee80211_tx_skb_tid(sdata, skb, tid);
+	ieee80211_tx_skb(sdata, skb);
 }
 
 void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata,
@@ -466,7 +486,9 @@ void ieee80211_request_smps_ap_work(struct work_struct *work)
 			     u.ap.request_smps_work);
 
 	sdata_lock(sdata);
-	__ieee80211_request_smps_ap(sdata, sdata->u.ap.driver_smps_mode);
+	if (sdata_dereference(sdata->u.ap.beacon, sdata))
+		__ieee80211_request_smps_ap(sdata,
+					    sdata->u.ap.driver_smps_mode);
 	sdata_unlock(sdata);
 }
 
@@ -479,9 +501,6 @@ void ieee80211_request_smps(struct ieee80211_vif *vif,
 			 vif->type != NL80211_IFTYPE_AP))
 		return;
 
-	if (WARN_ON(smps_mode == IEEE80211_SMPS_OFF))
-		smps_mode = IEEE80211_SMPS_AUTOMATIC;
-
 	if (vif->type == NL80211_IFTYPE_STATION) {
 		if (sdata->u.mgd.driver_smps_mode == smps_mode)
 			return;
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 2eda7b13124..18ee0a256b1 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -143,7 +143,7 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata,
 		*pos++ = csa_settings->block_tx ? 1 : 0;
 		*pos++ = ieee80211_frequency_to_channel(
 				csa_settings->chandef.chan->center_freq);
-		sdata->csa_counter_offset_beacon = (pos - presp->head);
+		sdata->csa_counter_offset_beacon[0] = (pos - presp->head);
 		*pos++ = csa_settings->count;
 	}
 
@@ -220,7 +220,6 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_supported_band *sband;
 	struct ieee80211_mgmt *mgmt;
 	struct cfg80211_bss *bss;
 	u32 bss_change;
@@ -229,7 +228,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	struct beacon_data *presp;
 	enum nl80211_bss_scan_width scan_width;
 	bool have_higher_than_11mbit;
-	bool radar_required = false;
+	bool radar_required;
 	int err;
 
 	sdata_assert_lock(sdata);
@@ -254,7 +253,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 
 	presp = rcu_dereference_protected(ifibss->presp,
 					  lockdep_is_held(&sdata->wdev.mtx));
-	rcu_assign_pointer(ifibss->presp, NULL);
+	RCU_INIT_POINTER(ifibss->presp, NULL);
 	if (presp)
 		kfree_rcu(presp, rcu_head);
 
@@ -263,7 +262,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	/* make a copy of the chandef, it could be modified below. */
 	chandef = *req_chandef;
 	chan = chandef.chan;
-	if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef)) {
+	if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef,
+				     NL80211_IFTYPE_ADHOC)) {
 		if (chandef.width == NL80211_CHAN_WIDTH_5 ||
 		    chandef.width == NL80211_CHAN_WIDTH_10 ||
 		    chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
@@ -275,7 +275,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 		chandef.width = NL80211_CHAN_WIDTH_20;
 		chandef.center_freq1 = chan->center_freq;
 		/* check again for downgraded chandef */
-		if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef)) {
+		if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef,
+					     NL80211_IFTYPE_ADHOC)) {
 			sdata_info(sdata,
 				   "Failed to join IBSS, beacons forbidden\n");
 			return;
@@ -283,29 +284,34 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	}
 
 	err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy,
-					    &chandef);
-	if (err > 0) {
-		if (!ifibss->userspace_handles_dfs) {
-			sdata_info(sdata,
-				   "Failed to join IBSS, DFS channel without control program\n");
-			return;
-		}
-		radar_required = true;
+					    &chandef, NL80211_IFTYPE_ADHOC);
+	if (err < 0) {
+		sdata_info(sdata,
+			   "Failed to join IBSS, invalid chandef\n");
+		return;
+	}
+	if (err > 0 && !ifibss->userspace_handles_dfs) {
+		sdata_info(sdata,
+			   "Failed to join IBSS, DFS channel without control program\n");
+		return;
 	}
 
-	ieee80211_vif_release_channel(sdata);
+	radar_required = err;
+
+	mutex_lock(&local->mtx);
 	if (ieee80211_vif_use_channel(sdata, &chandef,
 				      ifibss->fixed_channel ?
 					IEEE80211_CHANCTX_SHARED :
 					IEEE80211_CHANCTX_EXCLUSIVE)) {
 		sdata_info(sdata, "Failed to join IBSS, no channel context\n");
+		mutex_unlock(&local->mtx);
 		return;
 	}
+	sdata->radar_required = radar_required;
+	mutex_unlock(&local->mtx);
 
 	memcpy(ifibss->bssid, bssid, ETH_ALEN);
 
-	sband = local->hw.wiphy->bands[chan->band];
-
 	presp = ieee80211_ibss_build_presp(sdata, beacon_int, basic_rates,
 					   capability, tsf, &chandef,
 					   &have_higher_than_11mbit, NULL);
@@ -315,7 +321,6 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	rcu_assign_pointer(ifibss->presp, presp);
 	mgmt = (void *)presp->head;
 
-	sdata->radar_required = radar_required;
 	sdata->vif.bss_conf.enable_beacon = true;
 	sdata->vif.bss_conf.beacon_int = beacon_int;
 	sdata->vif.bss_conf.basic_rates = basic_rates;
@@ -363,7 +368,9 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 		sdata->vif.bss_conf.ssid_len = 0;
 		RCU_INIT_POINTER(ifibss->presp, NULL);
 		kfree_rcu(presp, rcu_head);
+		mutex_lock(&local->mtx);
 		ieee80211_vif_release_channel(sdata);
+		mutex_unlock(&local->mtx);
 		sdata_info(sdata, "Failed to join IBSS, driver failure: %d\n",
 			   err);
 		return;
@@ -381,7 +388,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 					      presp->head_len, 0, GFP_KERNEL);
 	cfg80211_put_bss(local->hw.wiphy, bss);
 	netif_carrier_on(sdata->dev);
-	cfg80211_ibss_joined(sdata->dev, ifibss->bssid, GFP_KERNEL);
+	cfg80211_ibss_joined(sdata->dev, ifibss->bssid, chan, GFP_KERNEL);
 }
 
 static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
@@ -516,13 +523,7 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata,
 	if (old_presp)
 		kfree_rcu(old_presp, rcu_head);
 
-	/* it might not send the beacon for a while. send an action frame
-	 * immediately to announce the channel switch.
-	 */
-	if (csa_settings)
-		ieee80211_send_action_csa(sdata, csa_settings);
-
-	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON);
+	return BSS_CHANGED_BEACON;
  out:
 	return ret;
 }
@@ -531,10 +532,11 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
 	struct cfg80211_bss *cbss;
-	int err;
+	int err, changed = 0;
 	u16 capability;
 
-	sdata_lock(sdata);
+	sdata_assert_lock(sdata);
+
 	/* update cfg80211 bss information with the new channel */
 	if (!is_zero_ether_addr(ifibss->bssid)) {
 		capability = WLAN_CAPABILITY_IBSS;
@@ -559,11 +561,12 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata)
 
 	/* generate the beacon */
 	err = ieee80211_ibss_csa_beacon(sdata, NULL);
-	sdata_unlock(sdata);
 	if (err < 0)
 		return err;
 
-	return 0;
+	changed |= err;
+
+	return changed;
 }
 
 void ieee80211_ibss_stop(struct ieee80211_sub_if_data *sdata)
@@ -687,12 +690,9 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata)
 	struct cfg80211_bss *cbss;
 	struct beacon_data *presp;
 	struct sta_info *sta;
-	int active_ibss;
 	u16 capability;
 
-	active_ibss = ieee80211_sta_active_ibss(sdata);
-
-	if (!active_ibss && !is_zero_ether_addr(ifibss->bssid)) {
+	if (!is_zero_ether_addr(ifibss->bssid)) {
 		capability = WLAN_CAPABILITY_IBSS;
 
 		if (ifibss->privacy)
@@ -744,7 +744,9 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata)
 	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED |
 						BSS_CHANGED_IBSS);
 	drv_leave_ibss(local, sdata);
+	mutex_lock(&local->mtx);
 	ieee80211_vif_release_channel(sdata);
+	mutex_unlock(&local->mtx);
 }
 
 static void ieee80211_csa_connection_drop_work(struct work_struct *work)
@@ -753,12 +755,16 @@ static void ieee80211_csa_connection_drop_work(struct work_struct *work)
 		container_of(work, struct ieee80211_sub_if_data,
 			     u.ibss.csa_connection_drop_work);
 
+	sdata_lock(sdata);
+
 	ieee80211_ibss_disconnect(sdata);
 	synchronize_rcu();
 	skb_queue_purge(&sdata->skb_queue);
 
 	/* trigger a scan to find another IBSS network to join */
 	ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+
+	sdata_unlock(sdata);
 }
 
 static void ieee80211_ibss_csa_mark_radar(struct ieee80211_sub_if_data *sdata)
@@ -770,7 +776,8 @@ static void ieee80211_ibss_csa_mark_radar(struct ieee80211_sub_if_data *sdata)
 	 * unavailable.
 	 */
 	err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy,
-					    &ifibss->chandef);
+					    &ifibss->chandef,
+					    NL80211_IFTYPE_ADHOC);
 	if (err > 0)
 		cfg80211_radar_event(sdata->local->hw.wiphy, &ifibss->chandef,
 				     GFP_ATOMIC);
@@ -784,17 +791,11 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	struct cfg80211_csa_settings params;
 	struct ieee80211_csa_ie csa_ie;
 	struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
-	struct ieee80211_chanctx_conf *chanctx_conf;
-	struct ieee80211_chanctx *chanctx;
 	enum nl80211_channel_type ch_type;
-	int err, num_chanctx;
+	int err;
 	u32 sta_flags;
 
-	if (sdata->vif.csa_active)
-		return true;
-
-	if (!sdata->vif.bss_conf.ibss_joined)
-		return false;
+	sdata_assert_lock(sdata);
 
 	sta_flags = IEEE80211_STA_DISABLE_VHT;
 	switch (ifibss->chandef.width) {
@@ -830,9 +831,6 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	params.count = csa_ie.count;
 	params.chandef = csa_ie.chandef;
 
-	if (ifibss->chandef.chan->band != params.chandef.chan->band)
-		goto disconnect;
-
 	switch (ifibss->chandef.width) {
 	case NL80211_CHAN_WIDTH_20_NOHT:
 	case NL80211_CHAN_WIDTH_20:
@@ -865,7 +863,8 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 		goto disconnect;
 	}
 
-	if (!cfg80211_reg_can_beacon(sdata->local->hw.wiphy, &params.chandef)) {
+	if (!cfg80211_reg_can_beacon(sdata->local->hw.wiphy, &params.chandef,
+				     NL80211_IFTYPE_ADHOC)) {
 		sdata_info(sdata,
 			   "IBSS %pM switches to unsupported channel (%d MHz, width:%d, CF1/2: %d/%d MHz), disconnecting\n",
 			   ifibss->bssid,
@@ -877,39 +876,23 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	}
 
 	err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy,
-					    &params.chandef);
+					    &params.chandef,
+					    NL80211_IFTYPE_ADHOC);
 	if (err < 0)
 		goto disconnect;
-	if (err) {
+	if (err > 0 && !ifibss->userspace_handles_dfs) {
 		/* IBSS-DFS only allowed with a control program */
-		if (!ifibss->userspace_handles_dfs)
-			goto disconnect;
-
-		params.radar_required = true;
-	}
-
-	rcu_read_lock();
-	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
-	if (!chanctx_conf) {
-		rcu_read_unlock();
 		goto disconnect;
 	}
 
-	/* don't handle for multi-VIF cases */
-	chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf);
-	if (chanctx->refcount > 1) {
-		rcu_read_unlock();
-		goto disconnect;
-	}
-	num_chanctx = 0;
-	list_for_each_entry_rcu(chanctx, &sdata->local->chanctx_list, list)
-		num_chanctx++;
+	params.radar_required = err;
 
-	if (num_chanctx > 1) {
-		rcu_read_unlock();
-		goto disconnect;
+	if (cfg80211_chandef_identical(&params.chandef,
+				       &sdata->vif.bss_conf.chandef)) {
+		ibss_dbg(sdata,
+			 "received csa with an identical chandef, ignoring\n");
+		return true;
 	}
-	rcu_read_unlock();
 
 	/* all checks done, now perform the channel switch. */
 	ibss_dbg(sdata,
@@ -918,19 +901,9 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 
 	params.block_tx = !!csa_ie.mode;
 
-	ieee80211_ibss_csa_beacon(sdata, &params);
-	sdata->csa_radar_required = params.radar_required;
-
-	if (params.block_tx)
-		ieee80211_stop_queues_by_reason(&sdata->local->hw,
-				IEEE80211_MAX_QUEUE_MAP,
-				IEEE80211_QUEUE_STOP_REASON_CSA);
-
-	sdata->csa_chandef = params.chandef;
-	sdata->vif.csa_active = true;
-
-	ieee80211_bss_info_change_notify(sdata, err);
-	drv_channel_switch_beacon(sdata, &params.chandef);
+	if (ieee80211_channel_switch(sdata->local->hw.wiphy, sdata->dev,
+				     &params))
+		goto disconnect;
 
 	ieee80211_ibss_csa_mark_radar(sdata);
 
@@ -966,7 +939,8 @@ ieee80211_rx_mgmt_spectrum_mgmt(struct ieee80211_sub_if_data *sdata,
 	if (len < required_len)
 		return;
 
-	ieee80211_ibss_process_chanswitch(sdata, elems, false);
+	if (!sdata->vif.csa_active)
+		ieee80211_ibss_process_chanswitch(sdata, elems, false);
 }
 
 static void ieee80211_rx_mgmt_deauth_ibss(struct ieee80211_sub_if_data *sdata,
@@ -1020,7 +994,6 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 				  struct ieee802_11_elems *elems)
 {
 	struct ieee80211_local *local = sdata->local;
-	int freq;
 	struct cfg80211_bss *cbss;
 	struct ieee80211_bss *bss;
 	struct sta_info *sta;
@@ -1032,15 +1005,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band];
 	bool rates_updated = false;
 
-	if (elems->ds_params)
-		freq = ieee80211_channel_to_frequency(elems->ds_params[0],
-						      band);
-	else
-		freq = rx_status->freq;
-
-	channel = ieee80211_get_channel(local->hw.wiphy, freq);
-
-	if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
+	channel = ieee80211_get_channel(local->hw.wiphy, rx_status->freq);
+	if (!channel)
 		return;
 
 	if (sdata->vif.type == NL80211_IFTYPE_ADHOC &&
@@ -1147,7 +1113,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 		goto put_bss;
 
 	/* process channel switch */
-	if (ieee80211_ibss_process_chanswitch(sdata, elems, true))
+	if (sdata->vif.csa_active ||
+	    ieee80211_ibss_process_chanswitch(sdata, elems, true))
 		goto put_bss;
 
 	/* same BSSID */
@@ -1492,6 +1459,11 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata,
 	memcpy(((struct ieee80211_mgmt *) skb->data)->da, mgmt->sa, ETH_ALEN);
 	ibss_dbg(sdata, "Sending ProbeResp to %pM\n", mgmt->sa);
 	IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;
+
+	/* avoid excessive retries for probe request to wildcard SSIDs */
+	if (pos[1] == 0)
+		IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_NO_ACK;
+
 	ieee80211_tx_skb(sdata, skb);
 }
 
@@ -1667,7 +1639,33 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 	u32 changed = 0;
 	u32 rate_flags;
 	struct ieee80211_supported_band *sband;
+	enum ieee80211_chanctx_mode chanmode;
+	struct ieee80211_local *local = sdata->local;
+	int radar_detect_width = 0;
 	int i;
+	int ret;
+
+	ret = cfg80211_chandef_dfs_required(local->hw.wiphy,
+					    &params->chandef,
+					    sdata->wdev.iftype);
+	if (ret < 0)
+		return ret;
+
+	if (ret > 0) {
+		if (!params->userspace_handles_dfs)
+			return -EINVAL;
+		radar_detect_width = BIT(params->chandef.width);
+	}
+
+	chanmode = (params->channel_fixed && !ret) ?
+		IEEE80211_CHANCTX_SHARED : IEEE80211_CHANCTX_EXCLUSIVE;
+
+	mutex_lock(&local->chanctx_mtx);
+	ret = ieee80211_check_combinations(sdata, &params->chandef, chanmode,
+					   radar_detect_width);
+	mutex_unlock(&local->chanctx_mtx);
+	if (ret < 0)
+		return ret;
 
 	if (params->bssid) {
 		memcpy(sdata->u.ibss.bssid, params->bssid, ETH_ALEN);
@@ -1679,10 +1677,11 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 	sdata->u.ibss.control_port = params->control_port;
 	sdata->u.ibss.userspace_handles_dfs = params->userspace_handles_dfs;
 	sdata->u.ibss.basic_rates = params->basic_rates;
+	sdata->u.ibss.last_scan_completed = jiffies;
 
 	/* fix basic_rates if channel does not support these rates */
 	rate_flags = ieee80211_chandef_rate_flags(&params->chandef);
-	sband = sdata->local->hw.wiphy->bands[params->chandef.chan->band];
+	sband = local->hw.wiphy->bands[params->chandef.chan->band];
 	for (i = 0; i < sband->n_bitrates; i++) {
 		if ((rate_flags & sband->bitrates[i].flags) != rate_flags)
 			sdata->u.ibss.basic_rates &= ~BIT(i);
@@ -1731,9 +1730,9 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 	ieee80211_bss_info_change_notify(sdata, changed);
 
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
-	sdata->needed_rx_chains = sdata->local->rx_chains;
+	sdata->needed_rx_chains = local->rx_chains;
 
-	ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+	ieee80211_queue_work(&local->hw, &sdata->work);
 
 	return 0;
 }
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index ed5bf8b4b5c..ac9836e0aab 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -232,6 +232,7 @@ struct ieee80211_rx_data {
 struct beacon_data {
 	u8 *head, *tail;
 	int head_len, tail_len;
+	struct ieee80211_meshconf_ie *meshconf;
 	struct rcu_head rcu_head;
 };
 
@@ -245,7 +246,8 @@ struct ps_data {
 	/* yes, this looks ugly, but guarantees that we can later use
 	 * bitmap_empty :)
 	 * NB: don't touch this bitmap, use sta_info_{set,clear}_tim_bit */
-	u8 tim[sizeof(unsigned long) * BITS_TO_LONGS(IEEE80211_MAX_AID + 1)];
+	u8 tim[sizeof(unsigned long) * BITS_TO_LONGS(IEEE80211_MAX_AID + 1)]
+			__aligned(__alignof__(unsigned long));
 	struct sk_buff_head bc_buf;
 	atomic_t num_sta_ps; /* number of stations in PS mode */
 	int dtim_count;
@@ -258,7 +260,7 @@ struct ieee80211_if_ap {
 
 	/* to be used after channel switch. */
 	struct cfg80211_beacon_data *next_beacon;
-	struct list_head vlans;
+	struct list_head vlans; /* write-protected with RTNL and local->mtx */
 
 	struct ps_data ps;
 	atomic_t num_mcast_sta; /* number of stations receiving multicast */
@@ -274,7 +276,7 @@ struct ieee80211_if_wds {
 };
 
 struct ieee80211_if_vlan {
-	struct list_head list;
+	struct list_head list; /* write-protected with RTNL and local->mtx */
 
 	/* used for all tx if the VLAN is configured to 4-addr mode */
 	struct sta_info __rcu *sta;
@@ -315,6 +317,7 @@ struct ieee80211_roc_work {
 
 	bool started, abort, hw_begun, notified;
 	bool to_be_freed;
+	bool on_channel;
 
 	unsigned long hw_start_time;
 
@@ -540,7 +543,10 @@ struct ieee80211_mesh_sync_ops {
 			     struct ieee80211_mgmt *mgmt,
 			     struct ieee802_11_elems *elems,
 			     struct ieee80211_rx_status *rx_status);
-	void (*adjust_tbtt)(struct ieee80211_sub_if_data *sdata);
+
+	/* should be called with beacon_data under RCU read lock */
+	void (*adjust_tbtt)(struct ieee80211_sub_if_data *sdata,
+			    struct beacon_data *beacon);
 	/* add other framework functions here */
 };
 
@@ -611,9 +617,16 @@ struct ieee80211_if_mesh {
 	struct ps_data ps;
 	/* Channel Switching Support */
 	struct mesh_csa_settings __rcu *csa;
-	bool chsw_init;
+	enum {
+		IEEE80211_MESH_CSA_ROLE_NONE,
+		IEEE80211_MESH_CSA_ROLE_INIT,
+		IEEE80211_MESH_CSA_ROLE_REPEATER,
+	} csa_role;
 	u8 chsw_ttl;
 	u16 pre_value;
+
+	/* offset from skb->data while building IE */
+	int meshconf_offset;
 };
 
 #ifdef CONFIG_MAC80211_MESH
@@ -679,13 +692,20 @@ struct ieee80211_chanctx {
 	struct list_head list;
 	struct rcu_head rcu_head;
 
+	struct list_head assigned_vifs;
+	struct list_head reserved_vifs;
+
 	enum ieee80211_chanctx_mode mode;
-	int refcount;
 	bool driver_present;
 
 	struct ieee80211_chanctx_conf conf;
 };
 
+struct mac80211_qos_map {
+	struct cfg80211_qos_map qos_map;
+	struct rcu_head rcu_head;
+};
+
 struct ieee80211_sub_if_data {
 	struct list_head list;
 
@@ -731,13 +751,24 @@ struct ieee80211_sub_if_data {
 	int encrypt_headroom;
 
 	struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS];
+	struct mac80211_qos_map __rcu *qos_map;
 
 	struct work_struct csa_finalize_work;
-	int csa_counter_offset_beacon;
-	int csa_counter_offset_presp;
+	u16 csa_counter_offset_beacon[IEEE80211_MAX_CSA_COUNTERS_NUM];
+	u16 csa_counter_offset_presp[IEEE80211_MAX_CSA_COUNTERS_NUM];
 	bool csa_radar_required;
+	bool csa_block_tx; /* write-protected by sdata_lock and local->mtx */
 	struct cfg80211_chan_def csa_chandef;
 
+	struct list_head assigned_chanctx_list; /* protected by chanctx_mtx */
+	struct list_head reserved_chanctx_list; /* protected by chanctx_mtx */
+
+	/* context reservation -- protected with chanctx_mtx */
+	struct ieee80211_chanctx *reserved_chanctx;
+	struct cfg80211_chan_def reserved_chandef;
+	bool reserved_radar_required;
+	u8 csa_current_counter;
+
 	/* used to reconfigure hardware SM PS */
 	struct work_struct recalc_smps;
 
@@ -776,10 +807,6 @@ struct ieee80211_sub_if_data {
 		u32 mntr_flags;
 	} u;
 
-	spinlock_t cleanup_stations_lock;
-	struct list_head cleanup_stations;
-	struct work_struct cleanup_stations_wk;
-
 #ifdef CONFIG_MAC80211_DEBUGFS
 	struct {
 		struct dentry *subdir_stations;
@@ -1117,6 +1144,7 @@ struct ieee80211_local {
 
 	struct work_struct sched_scan_stopped_work;
 	struct ieee80211_sub_if_data __rcu *sched_scan_sdata;
+	struct cfg80211_sched_scan_request *sched_scan_req;
 
 	unsigned long leave_oper_channel_time;
 	enum mac80211_scan_state next_scan_state;
@@ -1227,6 +1255,8 @@ struct ieee80211_local {
 
 	struct ieee80211_sub_if_data __rcu *p2p_sdata;
 
+	struct napi_struct *napi;
+
 	/* virtual monitor interface */
 	struct ieee80211_sub_if_data __rcu *monitor_sdata;
 	struct cfg80211_chan_def monitor_chandef;
@@ -1374,6 +1404,7 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mgd_conn_tx_status(struct ieee80211_sub_if_data *sdata,
 				  __le16 fc, bool acked);
+void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata);
 
 /* IBSS code */
@@ -1397,8 +1428,7 @@ void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				   struct sk_buff *skb);
 int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata,
-			      struct cfg80211_csa_settings *csa_settings,
-			      bool csa_action);
+			      struct cfg80211_csa_settings *csa_settings);
 int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata);
 
 /* scan/BSS handling */
@@ -1425,9 +1455,13 @@ void ieee80211_rx_bss_put(struct ieee80211_local *local,
 			  struct ieee80211_bss *bss);
 
 /* scheduled scan handling */
+int
+__ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
+				     struct cfg80211_sched_scan_request *req);
 int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
 				       struct cfg80211_sched_scan_request *req);
 int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata);
+void ieee80211_sched_scan_end(struct ieee80211_local *local);
 void ieee80211_sched_scan_stopped_work(struct work_struct *work);
 
 /* off-channel helpers */
@@ -1442,7 +1476,10 @@ void ieee80211_sw_roc_work(struct work_struct *work);
 void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc);
 
 /* channel switch handling */
+bool ieee80211_csa_needs_block_tx(struct ieee80211_local *local);
 void ieee80211_csa_finalize_work(struct work_struct *work);
+int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
+			     struct cfg80211_csa_settings *params);
 
 /* interface handling */
 int ieee80211_iface_init(void);
@@ -1465,8 +1502,6 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local);
 
 bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata);
 void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata);
-int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
-			    struct cfg80211_beacon_data *params);
 
 static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata)
 {
@@ -1539,6 +1574,9 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 				    struct sta_info *sta);
 enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta);
 void ieee80211_sta_set_rx_nss(struct sta_info *sta);
+u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
+                                  struct sta_info *sta, u8 opmode,
+                                  enum ieee80211_band band, bool nss_only);
 void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
 				 struct sta_info *sta, u8 opmode,
 				 enum ieee80211_band band, bool nss_only);
@@ -1591,7 +1629,7 @@ static inline int __ieee80211_resume(struct ieee80211_hw *hw)
 }
 
 /* utility functions/constants */
-extern void *mac80211_wiphy_privid; /* for wiphy privid */
+extern const void *const mac80211_wiphy_privid; /* for wiphy privid */
 u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len,
 			enum nl80211_iftype type);
 int ieee80211_frame_duration(enum ieee80211_band band, size_t len,
@@ -1678,14 +1716,8 @@ void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue,
 void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue);
 void ieee80211_add_pending_skb(struct ieee80211_local *local,
 			       struct sk_buff *skb);
-void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local,
-				   struct sk_buff_head *skbs,
-				   void (*fn)(void *data), void *data);
-static inline void ieee80211_add_pending_skbs(struct ieee80211_local *local,
-					      struct sk_buff_head *skbs)
-{
-	ieee80211_add_pending_skbs_fn(local, skbs, NULL, NULL);
-}
+void ieee80211_add_pending_skbs(struct ieee80211_local *local,
+				struct sk_buff_head *skbs);
 void ieee80211_flush_queues(struct ieee80211_local *local,
 			    struct ieee80211_sub_if_data *sdata);
 
@@ -1754,6 +1786,16 @@ ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 			  const struct cfg80211_chan_def *chandef,
 			  enum ieee80211_chanctx_mode mode);
 int __must_check
+ieee80211_vif_reserve_chanctx(struct ieee80211_sub_if_data *sdata,
+			      const struct cfg80211_chan_def *chandef,
+			      enum ieee80211_chanctx_mode mode,
+			      bool radar_required);
+int __must_check
+ieee80211_vif_use_reserved_context(struct ieee80211_sub_if_data *sdata,
+				   u32 *changed);
+int ieee80211_vif_unreserve_chanctx(struct ieee80211_sub_if_data *sdata);
+
+int __must_check
 ieee80211_vif_change_bandwidth(struct ieee80211_sub_if_data *sdata,
 			       const struct cfg80211_chan_def *chandef,
 			       u32 *changed);
@@ -1765,11 +1807,11 @@ void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata);
 void ieee80211_vif_vlan_copy_chanctx(struct ieee80211_sub_if_data *sdata);
 void ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata,
 					 bool clear);
+int ieee80211_chanctx_refcount(struct ieee80211_local *local,
+			       struct ieee80211_chanctx *ctx);
 
 void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
 				   struct ieee80211_chanctx *chanctx);
-void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local,
-				    struct ieee80211_chanctx *chanctx);
 void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local,
 				      struct ieee80211_chanctx *ctx);
 
@@ -1788,6 +1830,22 @@ ieee80211_cs_get(struct ieee80211_local *local, u32 cipher,
 int ieee80211_cs_headroom(struct ieee80211_local *local,
 			  struct cfg80211_crypto_settings *crypto,
 			  enum nl80211_iftype iftype);
+void ieee80211_recalc_dtim(struct ieee80211_local *local,
+			   struct ieee80211_sub_if_data *sdata);
+int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
+				 const struct cfg80211_chan_def *chandef,
+				 enum ieee80211_chanctx_mode chanmode,
+				 u8 radar_detect);
+int ieee80211_max_num_channels(struct ieee80211_local *local);
+
+/* TDLS */
+int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
+			const u8 *peer, u8 action_code, u8 dialog_token,
+			u16 status_code, u32 peer_capability,
+			const u8 *extra_ies, size_t extra_ies_len);
+int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
+			const u8 *peer, enum nl80211_tdls_operation oper);
+
 
 #ifdef CONFIG_MAC80211_NOINLINE
 #define debug_noinline noinline
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 7aa9f9dea9d..388b863e821 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -101,9 +101,8 @@ static u32 __ieee80211_idle_on(struct ieee80211_local *local)
 static u32 __ieee80211_recalc_idle(struct ieee80211_local *local,
 				   bool force_active)
 {
-	bool working = false, scanning, active;
+	bool working, scanning, active;
 	unsigned int led_trig_start = 0, led_trig_stop = 0;
-	struct ieee80211_roc_work *roc;
 
 	lockdep_assert_held(&local->mtx);
 
@@ -111,12 +110,8 @@ static u32 __ieee80211_recalc_idle(struct ieee80211_local *local,
 		 !list_empty(&local->chanctx_list) ||
 		 local->monitors;
 
-	if (!local->ops->remain_on_channel) {
-		list_for_each_entry(roc, &local->roc_list, list) {
-			working = true;
-			break;
-		}
-	}
+	working = !local->ops->remain_on_channel &&
+		  !list_empty(&local->roc_list);
 
 	scanning = test_bit(SCAN_SW_SCANNING, &local->scanning) ||
 		   test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning);
@@ -255,6 +250,7 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_sub_if_data *nsdata;
+	int ret;
 
 	ASSERT_RTNL();
 
@@ -305,7 +301,10 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
-	return 0;
+	mutex_lock(&local->chanctx_mtx);
+	ret = ieee80211_check_combinations(sdata, NULL, 0, 0);
+	mutex_unlock(&local->chanctx_mtx);
+	return ret;
 }
 
 static int ieee80211_check_queues(struct ieee80211_sub_if_data *sdata,
@@ -400,6 +399,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
 	sdata->vif.type = NL80211_IFTYPE_MONITOR;
 	snprintf(sdata->name, IFNAMSIZ, "%s-monitor",
 		 wiphy_name(local->hw.wiphy));
+	sdata->wdev.iftype = NL80211_IFTYPE_MONITOR;
 
 	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
 
@@ -418,18 +418,24 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
 		return ret;
 	}
 
+	mutex_lock(&local->iflist_mtx);
+	rcu_assign_pointer(local->monitor_sdata, sdata);
+	mutex_unlock(&local->iflist_mtx);
+
+	mutex_lock(&local->mtx);
 	ret = ieee80211_vif_use_channel(sdata, &local->monitor_chandef,
 					IEEE80211_CHANCTX_EXCLUSIVE);
+	mutex_unlock(&local->mtx);
 	if (ret) {
+		mutex_lock(&local->iflist_mtx);
+		RCU_INIT_POINTER(local->monitor_sdata, NULL);
+		mutex_unlock(&local->iflist_mtx);
+		synchronize_net();
 		drv_remove_interface(local, sdata);
 		kfree(sdata);
 		return ret;
 	}
 
-	mutex_lock(&local->iflist_mtx);
-	rcu_assign_pointer(local->monitor_sdata, sdata);
-	mutex_unlock(&local->iflist_mtx);
-
 	return 0;
 }
 
@@ -451,12 +457,14 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local)
 		return;
 	}
 
-	rcu_assign_pointer(local->monitor_sdata, NULL);
+	RCU_INIT_POINTER(local->monitor_sdata, NULL);
 	mutex_unlock(&local->iflist_mtx);
 
 	synchronize_net();
 
+	mutex_lock(&local->mtx);
 	ieee80211_vif_release_channel(sdata);
+	mutex_unlock(&local->mtx);
 
 	drv_remove_interface(local, sdata);
 
@@ -489,7 +497,9 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		if (!sdata->bss)
 			return -ENOLINK;
 
+		mutex_lock(&local->mtx);
 		list_add(&sdata->u.vlan.list, &sdata->bss->vlans);
+		mutex_unlock(&local->mtx);
 
 		master = container_of(sdata->bss,
 				      struct ieee80211_sub_if_data, u.ap);
@@ -719,8 +729,11 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		drv_stop(local);
  err_del_bss:
 	sdata->bss = NULL;
-	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+		mutex_lock(&local->mtx);
 		list_del(&sdata->u.vlan.list);
+		mutex_unlock(&local->mtx);
+	}
 	/* might already be clear but that doesn't matter */
 	clear_bit(SDATA_STATE_RUNNING, &sdata->state);
 	return res;
@@ -766,12 +779,19 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 
 	ieee80211_roc_purge(local, sdata);
 
-	if (sdata->vif.type == NL80211_IFTYPE_STATION)
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_STATION:
 		ieee80211_mgd_stop(sdata);
-
-	if (sdata->vif.type == NL80211_IFTYPE_ADHOC)
+		break;
+	case NL80211_IFTYPE_ADHOC:
 		ieee80211_ibss_stop(sdata);
-
+		break;
+	case NL80211_IFTYPE_AP:
+		cancel_work_sync(&sdata->u.ap.request_smps_work);
+		break;
+	default:
+		break;
+	}
 
 	/*
 	 * Remove all stations associated with this interface.
@@ -786,10 +806,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	 * This is relevant only in WDS mode, in all other modes we've
 	 * already removed all stations when disconnecting or similar,
 	 * so warn otherwise.
-	 *
-	 * We call sta_info_flush_cleanup() later, to combine RCU waits.
 	 */
-	flushed = sta_info_flush_defer(sdata);
+	flushed = sta_info_flush(sdata);
 	WARN_ON_ONCE((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) ||
 		     (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1));
 
@@ -820,7 +838,16 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	cancel_work_sync(&local->dynamic_ps_enable_work);
 
 	cancel_work_sync(&sdata->recalc_smps);
+	sdata_lock(sdata);
+	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = false;
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
+	sdata_unlock(sdata);
+
 	cancel_work_sync(&sdata->csa_finalize_work);
 
 	cancel_delayed_work_sync(&sdata->dfs_cac_timer_work);
@@ -828,9 +855,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	if (sdata->wdev.cac_started) {
 		chandef = sdata->vif.bss_conf.chandef;
 		WARN_ON(local->suspended);
-		mutex_lock(&local->iflist_mtx);
+		mutex_lock(&local->mtx);
 		ieee80211_vif_release_channel(sdata);
-		mutex_unlock(&local->iflist_mtx);
+		mutex_unlock(&local->mtx);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_ABORTED,
 				   GFP_KERNEL);
@@ -865,8 +892,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP_VLAN:
+		mutex_lock(&local->mtx);
 		list_del(&sdata->u.vlan.list);
-		rcu_assign_pointer(sdata->vif.chanctx_conf, NULL);
+		mutex_unlock(&local->mtx);
+		RCU_INIT_POINTER(sdata->vif.chanctx_conf, NULL);
 		/* no need to tell driver */
 		break;
 	case NL80211_IFTYPE_MONITOR:
@@ -885,29 +914,21 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 		break;
 	case NL80211_IFTYPE_P2P_DEVICE:
 		/* relies on synchronize_rcu() below */
-		rcu_assign_pointer(local->p2p_sdata, NULL);
+		RCU_INIT_POINTER(local->p2p_sdata, NULL);
 		/* fall through */
 	default:
 		cancel_work_sync(&sdata->work);
 		/*
 		 * When we get here, the interface is marked down.
+		 * Free the remaining keys, if there are any
+		 * (shouldn't be, except maybe in WDS mode?)
 		 *
-		 * sta_info_flush_cleanup() requires rcu_barrier()
-		 * first to wait for the station call_rcu() calls
-		 * to complete, and we also need synchronize_rcu()
-		 * to wait for the RX path in case it is using the
-		 * interface and enqueuing frames at this very time on
+		 * Force the key freeing to always synchronize_net()
+		 * to wait for the RX path in case it is using this
+		 * interface enqueuing frames * at this very time on
 		 * another CPU.
 		 */
-		synchronize_rcu();
-		rcu_barrier();
-		sta_info_flush_cleanup(sdata);
-
-		/*
-		 * Free all remaining keys, there shouldn't be any,
-		 * except maybe in WDS mode?
-		 */
-		ieee80211_free_keys(sdata);
+		ieee80211_free_keys(sdata, true);
 
 		/* fall through */
 	case NL80211_IFTYPE_AP:
@@ -1018,17 +1039,6 @@ static void ieee80211_set_multicast_list(struct net_device *dev)
 			atomic_dec(&local->iff_promiscs);
 		sdata->flags ^= IEEE80211_SDATA_PROMISC;
 	}
-
-	/*
-	 * TODO: If somebody needs this on AP interfaces,
-	 *	 it can be enabled easily but multicast
-	 *	 addresses from VLANs need to be synced.
-	 */
-	if (sdata->vif.type != NL80211_IFTYPE_MONITOR &&
-	    sdata->vif.type != NL80211_IFTYPE_AP_VLAN &&
-	    sdata->vif.type != NL80211_IFTYPE_AP)
-		drv_set_multicast_list(local, sdata, &dev->mc);
-
 	spin_lock_bh(&local->filter_lock);
 	__hw_addr_sync(&local->mc_list, &dev->mc, dev->addr_len);
 	spin_unlock_bh(&local->filter_lock);
@@ -1044,7 +1054,7 @@ static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata)
 	int i;
 
 	/* free extra data */
-	ieee80211_free_keys(sdata);
+	ieee80211_free_keys(sdata, false);
 
 	ieee80211_debugfs_remove_netdev(sdata);
 
@@ -1062,7 +1072,9 @@ static void ieee80211_uninit(struct net_device *dev)
 }
 
 static u16 ieee80211_netdev_select_queue(struct net_device *dev,
-					 struct sk_buff *skb)
+					 struct sk_buff *skb,
+					 void *accel_priv,
+					 select_queue_fallback_t fallback)
 {
 	return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
 }
@@ -1079,7 +1091,9 @@ static const struct net_device_ops ieee80211_dataif_ops = {
 };
 
 static u16 ieee80211_monitor_select_queue(struct net_device *dev,
-					  struct sk_buff *skb)
+					  struct sk_buff *skb,
+					  void *accel_priv,
+					  select_queue_fallback_t fallback)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
@@ -1272,6 +1286,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	sdata->control_port_protocol = cpu_to_be16(ETH_P_PAE);
 	sdata->control_port_no_encrypt = false;
 	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
+	sdata->vif.bss_conf.idle = true;
 
 	sdata->noack_map = 0;
 
@@ -1285,6 +1300,8 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	INIT_WORK(&sdata->work, ieee80211_iface_work);
 	INIT_WORK(&sdata->recalc_smps, ieee80211_recalc_smps_work);
 	INIT_WORK(&sdata->csa_finalize_work, ieee80211_csa_finalize_work);
+	INIT_LIST_HEAD(&sdata->assigned_chanctx_list);
+	INIT_LIST_HEAD(&sdata->reserved_chanctx_list);
 
 	switch (type) {
 	case NL80211_IFTYPE_P2P_GO:
@@ -1497,8 +1514,8 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local,
 			bool used = false;
 
 			list_for_each_entry(sdata, &local->interfaces, list) {
-				if (memcmp(local->hw.wiphy->addresses[i].addr,
-					   sdata->vif.addr, ETH_ALEN) == 0) {
+				if (ether_addr_equal(local->hw.wiphy->addresses[i].addr,
+						     sdata->vif.addr)) {
 					used = true;
 					break;
 				}
@@ -1558,8 +1575,7 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local,
 			val += inc;
 
 			list_for_each_entry(sdata, &local->interfaces, list) {
-				if (memcmp(tmp_addr, sdata->vif.addr,
-							ETH_ALEN) == 0) {
+				if (ether_addr_equal(tmp_addr, sdata->vif.addr)) {
 					used = true;
 					break;
 				}
@@ -1579,15 +1595,6 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local,
 	mutex_unlock(&local->iflist_mtx);
 }
 
-static void ieee80211_cleanup_sdata_stas_wk(struct work_struct *wk)
-{
-	struct ieee80211_sub_if_data *sdata;
-
-	sdata = container_of(wk, struct ieee80211_sub_if_data, cleanup_stations_wk);
-
-	ieee80211_cleanup_sdata_stas(sdata);
-}
-
 int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 		     struct wireless_dev **new_wdev, enum nl80211_iftype type,
 		     struct vif_params *params)
@@ -1660,9 +1667,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 
 	INIT_LIST_HEAD(&sdata->key_list);
 
-	spin_lock_init(&sdata->cleanup_stations_lock);
-	INIT_LIST_HEAD(&sdata->cleanup_stations);
-	INIT_WORK(&sdata->cleanup_stations_wk, ieee80211_cleanup_sdata_stas_wk);
 	INIT_DELAYED_WORK(&sdata->dfs_cac_timer_work,
 			  ieee80211_dfs_cac_timer_work);
 	INIT_DELAYED_WORK(&sdata->dec_tailroom_needed_wk,
@@ -1776,7 +1780,6 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local)
 	}
 	mutex_unlock(&local->iflist_mtx);
 	unregister_netdevice_many(&unreg_list);
-	list_del(&unreg_list);
 
 	list_for_each_entry_safe(sdata, tmp, &wdev_list, list) {
 		list_del(&sdata->list);
@@ -1792,20 +1795,19 @@ static int netdev_notify(struct notifier_block *nb,
 	struct ieee80211_sub_if_data *sdata;
 
 	if (state != NETDEV_CHANGENAME)
-		return 0;
+		return NOTIFY_DONE;
 
 	if (!dev->ieee80211_ptr || !dev->ieee80211_ptr->wiphy)
-		return 0;
+		return NOTIFY_DONE;
 
 	if (dev->ieee80211_ptr->wiphy->privid != mac80211_wiphy_privid)
-		return 0;
+		return NOTIFY_DONE;
 
 	sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-
 	memcpy(sdata->name, dev->name, IFNAMSIZ);
-
 	ieee80211_debugfs_rename_netdev(sdata);
-	return 0;
+
+	return NOTIFY_OK;
 }
 
 static struct notifier_block mac80211_netdev_notifier = {
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index e568d98167d..16d97f044a2 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -325,7 +325,8 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 	struct ieee80211_key *key;
 	int i, j, err;
 
-	BUG_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS);
+	if (WARN_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS))
+		return ERR_PTR(-EINVAL);
 
 	key = kzalloc(sizeof(struct ieee80211_key) + key_len, GFP_KERNEL);
 	if (!key)
@@ -481,8 +482,8 @@ int ieee80211_key_link(struct ieee80211_key *key,
 	int idx, ret;
 	bool pairwise;
 
-	BUG_ON(!sdata);
-	BUG_ON(!key);
+	if (WARN_ON(!sdata || !key))
+		return -EINVAL;
 
 	pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE;
 	idx = key->conf.keyidx;
@@ -589,14 +590,10 @@ void ieee80211_iter_keys(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL(ieee80211_iter_keys);
 
-void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata)
+static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata,
+				      struct list_head *keys)
 {
 	struct ieee80211_key *key, *tmp;
-	LIST_HEAD(keys);
-
-	cancel_delayed_work_sync(&sdata->dec_tailroom_needed_wk);
-
-	mutex_lock(&sdata->local->key_mtx);
 
 	sdata->crypto_tx_tailroom_needed_cnt -=
 		sdata->crypto_tx_tailroom_pending_dec;
@@ -608,28 +605,51 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata)
 		ieee80211_key_replace(key->sdata, key->sta,
 				key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE,
 				key, NULL);
-		list_add_tail(&key->list, &keys);
+		list_add_tail(&key->list, keys);
 	}
 
 	ieee80211_debugfs_key_update_default(sdata);
+}
 
-	if (!list_empty(&keys)) {
-		synchronize_net();
-		list_for_each_entry_safe(key, tmp, &keys, list)
-			__ieee80211_key_destroy(key, false);
+void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata,
+			 bool force_synchronize)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_sub_if_data *vlan;
+	struct ieee80211_key *key, *tmp;
+	LIST_HEAD(keys);
+
+	cancel_delayed_work_sync(&sdata->dec_tailroom_needed_wk);
+
+	mutex_lock(&local->key_mtx);
+
+	ieee80211_free_keys_iface(sdata, &keys);
+
+	if (sdata->vif.type == NL80211_IFTYPE_AP) {
+		list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+			ieee80211_free_keys_iface(vlan, &keys);
 	}
 
+	if (!list_empty(&keys) || force_synchronize)
+		synchronize_net();
+	list_for_each_entry_safe(key, tmp, &keys, list)
+		__ieee80211_key_destroy(key, false);
+
 	WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt ||
 		     sdata->crypto_tx_tailroom_pending_dec);
+	if (sdata->vif.type == NL80211_IFTYPE_AP) {
+		list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+			WARN_ON_ONCE(vlan->crypto_tx_tailroom_needed_cnt ||
+				     vlan->crypto_tx_tailroom_pending_dec);
+	}
 
-	mutex_unlock(&sdata->local->key_mtx);
+	mutex_unlock(&local->key_mtx);
 }
 
 void ieee80211_free_sta_keys(struct ieee80211_local *local,
 			     struct sta_info *sta)
 {
-	struct ieee80211_key *key, *tmp;
-	LIST_HEAD(keys);
+	struct ieee80211_key *key;
 	int i;
 
 	mutex_lock(&local->key_mtx);
@@ -640,7 +660,7 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local,
 		ieee80211_key_replace(key->sdata, key->sta,
 				key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE,
 				key, NULL);
-		list_add(&key->list, &keys);
+		__ieee80211_key_destroy(key, true);
 	}
 
 	for (i = 0; i < NUM_DEFAULT_KEYS; i++) {
@@ -650,17 +670,8 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local,
 		ieee80211_key_replace(key->sdata, key->sta,
 				key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE,
 				key, NULL);
-		list_add(&key->list, &keys);
-	}
-
-	/*
-	 * NB: the station code relies on this being
-	 * done even if there aren't any keys
-	 */
-	synchronize_net();
-
-	list_for_each_entry_safe(key, tmp, &keys, list)
 		__ieee80211_key_destroy(key, true);
+	}
 
 	mutex_unlock(&local->key_mtx);
 }
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index 0aebb889cab..19db68663d7 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -136,7 +136,8 @@ void ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, int idx,
 			       bool uni, bool multi);
 void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata,
 				    int idx);
-void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata);
+void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata,
+			 bool force_synchronize);
 void ieee80211_free_sta_keys(struct ieee80211_local *local,
 			     struct sta_info *sta);
 void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index fa34cd2344b..d17c26d6e36 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -148,6 +148,8 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local)
 	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
 		if (!rcu_access_pointer(sdata->vif.chanctx_conf))
 			continue;
+		if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+			continue;
 		power = min(power, sdata->vif.bss_conf.txpower);
 	}
 	rcu_read_unlock();
@@ -199,7 +201,7 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_local *local = sdata->local;
 
-	if (!changed)
+	if (!changed || sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 		return;
 
 	drv_bss_info_changed(local, sdata, &sdata->vif.bss_conf, changed);
@@ -250,12 +252,8 @@ static void ieee80211_restart_work(struct work_struct *work)
 	/* wait for scan work complete */
 	flush_workqueue(local->workqueue);
 
-	mutex_lock(&local->mtx);
-	WARN(test_bit(SCAN_HW_SCANNING, &local->scanning) ||
-	     rcu_dereference_protected(local->sched_scan_sdata,
-				       lockdep_is_held(&local->mtx)),
-		"%s called with hardware scan in progress\n", __func__);
-	mutex_unlock(&local->mtx);
+	WARN(test_bit(SCAN_HW_SCANNING, &local->scanning),
+	     "%s called with hardware scan in progress\n", __func__);
 
 	rtnl_lock();
 	ieee80211_scan_cancel(local);
@@ -342,7 +340,7 @@ static int ieee80211_ifa_changed(struct notifier_block *nb,
 
 	sdata_unlock(sdata);
 
-	return NOTIFY_DONE;
+	return NOTIFY_OK;
 }
 #endif
 
@@ -373,7 +371,7 @@ static int ieee80211_ifa6_changed(struct notifier_block *nb,
 
 	drv_ipv6_addr_change(local, sdata, idev);
 
-	return NOTIFY_DONE;
+	return NOTIFY_OK;
 }
 #endif
 
@@ -448,7 +446,9 @@ static const struct ieee80211_ht_cap mac80211_ht_capa_mod_mask = {
 	.cap_info = cpu_to_le16(IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
 				IEEE80211_HT_CAP_MAX_AMSDU |
 				IEEE80211_HT_CAP_SGI_20 |
-				IEEE80211_HT_CAP_SGI_40),
+				IEEE80211_HT_CAP_SGI_40 |
+				IEEE80211_HT_CAP_LDPC_CODING |
+				IEEE80211_HT_CAP_40MHZ_INTOLERANT),
 	.mcs = {
 		.rx_mask = { 0xff, 0xff, 0xff, 0xff, 0xff,
 			     0xff, 0xff, 0xff, 0xff, 0xff, },
@@ -850,17 +850,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		/* TODO: consider VHT for RX chains, hopefully it's the same */
 	}
 
-	local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) +
-				      sizeof(void *) * channels, GFP_KERNEL);
-	if (!local->int_scan_req)
-		return -ENOMEM;
-
-	for (band = 0; band < IEEE80211_NUM_BANDS; band++) {
-		if (!local->hw.wiphy->bands[band])
-			continue;
-		local->int_scan_req->rates[band] = (u32) -1;
-	}
-
 	/* if low-level driver supports AP, we also support VLAN */
 	if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_AP)) {
 		hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_AP_VLAN);
@@ -884,6 +873,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 				return -EINVAL;
 	}
 
+	local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) +
+				      sizeof(void *) * channels, GFP_KERNEL);
+	if (!local->int_scan_req)
+		return -ENOMEM;
+
+	for (band = 0; band < IEEE80211_NUM_BANDS; band++) {
+		if (!local->hw.wiphy->bands[band])
+			continue;
+		local->int_scan_req->rates[band] = (u32) -1;
+	}
+
 #ifndef CONFIG_MAC80211_MESH
 	/* mesh depends on Kconfig, but drivers should set it if they want */
 	local->hw.wiphy->interface_modes &= ~BIT(NL80211_IFTYPE_MESH_POINT);
@@ -897,10 +897,15 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	/* mac80211 supports control port protocol changing */
 	local->hw.wiphy->flags |= WIPHY_FLAG_CONTROL_PORT_PROTOCOL;
 
-	if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM)
+	if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM) {
 		local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM;
-	else if (local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)
+	} else if (local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC) {
 		local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC;
+		if (hw->max_signal <= 0) {
+			result = -EINVAL;
+			goto fail_wiphy_register;
+		}
+	}
 
 	WARN((local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)
 	     && (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK),
@@ -951,6 +956,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	if (local->hw.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)
 		local->hw.wiphy->flags |= WIPHY_FLAG_TDLS_EXTERNAL_SETUP;
 
+	local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM;
+
 	result = wiphy_register(local->hw.wiphy);
 	if (result < 0)
 		goto fail_wiphy_register;
@@ -1075,6 +1082,18 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 }
 EXPORT_SYMBOL(ieee80211_register_hw);
 
+void ieee80211_napi_add(struct ieee80211_hw *hw, struct napi_struct *napi,
+			struct net_device *napi_dev,
+			int (*poll)(struct napi_struct *, int),
+			int weight)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+
+	netif_napi_add(napi_dev, napi, poll, weight);
+	local->napi = napi;
+}
+EXPORT_SYMBOL_GPL(ieee80211_napi_add);
+
 void ieee80211_unregister_hw(struct ieee80211_hw *hw)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 89df62b2b68..6495a3f0428 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -259,6 +259,9 @@ int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata,
 	*pos++ = WLAN_EID_MESH_CONFIG;
 	*pos++ = meshconf_len;
 
+	/* save a pointer for quick updates in pre-tbtt */
+	ifmsh->meshconf_offset = pos - skb->data;
+
 	/* Active path selection protocol ID */
 	*pos++ = ifmsh->mesh_pp_id;
 	/* Active path selection metric ID   */
@@ -363,20 +366,15 @@ int mesh_add_rsn_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb)
 		return 0;
 
 	/* find RSN IE */
-	data = ifmsh->ie;
-	while (data < ifmsh->ie + ifmsh->ie_len) {
-		if (*data == WLAN_EID_RSN) {
-			len = data[1] + 2;
-			break;
-		}
-		data++;
-	}
+	data = cfg80211_find_ie(WLAN_EID_RSN, ifmsh->ie, ifmsh->ie_len);
+	if (!data)
+		return 0;
 
-	if (len) {
-		if (skb_tailroom(skb) < len)
-			return -ENOMEM;
-		memcpy(skb_put(skb, len), data, len);
-	}
+	len = data[1] + 2;
+
+	if (skb_tailroom(skb) < len)
+		return -ENOMEM;
+	memcpy(skb_put(skb, len), data, len);
 
 	return 0;
 }
@@ -681,11 +679,11 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
 		*pos++ = 0x0;
 		*pos++ = ieee80211_frequency_to_channel(
 				csa->settings.chandef.chan->center_freq);
-		sdata->csa_counter_offset_beacon = hdr_len + 6;
+		sdata->csa_counter_offset_beacon[0] = hdr_len + 6;
 		*pos++ = csa->settings.count;
 		*pos++ = WLAN_EID_CHAN_SWITCH_PARAM;
 		*pos++ = 6;
-		if (ifmsh->chsw_init) {
+		if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_INIT) {
 			*pos++ = ifmsh->mshcfg.dot11MeshTTL;
 			*pos |= WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR;
 		} else {
@@ -723,6 +721,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
 
 	bcn->tail_len = skb->len;
 	memcpy(bcn->tail, skb->data, bcn->tail_len);
+	bcn->meshconf = (struct ieee80211_meshconf_ie *)
+					(bcn->tail + ifmsh->meshconf_offset);
 
 	dev_kfree_skb(skb);
 	rcu_assign_pointer(ifmsh->beacon, bcn);
@@ -802,6 +802,7 @@ int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata)
 		return -ENOMEM;
 	}
 
+	ieee80211_recalc_dtim(local, sdata);
 	ieee80211_bss_info_change_notify(sdata, changed);
 
 	netif_carrier_on(sdata->dev);
@@ -823,7 +824,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata)
 	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED);
 	bcn = rcu_dereference_protected(ifmsh->beacon,
 					lockdep_is_held(&sdata->wdev.mtx));
-	rcu_assign_pointer(ifmsh->beacon, NULL);
+	RCU_INIT_POINTER(ifmsh->beacon, NULL);
 	kfree_rcu(bcn, rcu_head);
 
 	/* flush STAs and mpaths on this iface */
@@ -853,18 +854,12 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata,
 {
 	struct cfg80211_csa_settings params;
 	struct ieee80211_csa_ie csa_ie;
-	struct ieee80211_chanctx_conf *chanctx_conf;
-	struct ieee80211_chanctx *chanctx;
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
 	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
-	int err, num_chanctx;
+	int err;
 	u32 sta_flags;
 
-	if (sdata->vif.csa_active)
-		return true;
-
-	if (!ifmsh->mesh_id)
-		return false;
+	sdata_assert_lock(sdata);
 
 	sta_flags = IEEE80211_STA_DISABLE_VHT;
 	switch (sdata->vif.bss_conf.chandef.width) {
@@ -890,10 +885,6 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata,
 	params.chandef = csa_ie.chandef;
 	params.count = csa_ie.count;
 
-	if (sdata->vif.bss_conf.chandef.chan->band !=
-	    params.chandef.chan->band)
-		return false;
-
 	if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, &params.chandef,
 				     IEEE80211_CHAN_DISABLED)) {
 		sdata_info(sdata,
@@ -907,33 +898,22 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata,
 	}
 
 	err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy,
-					    &params.chandef);
+					    &params.chandef,
+					    NL80211_IFTYPE_MESH_POINT);
 	if (err < 0)
 		return false;
-	if (err) {
-		params.radar_required = true;
+	if (err > 0)
 		/* TODO: DFS not (yet) supported */
 		return false;
-	}
-
-	rcu_read_lock();
-	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
-	if (!chanctx_conf)
-		goto failed_chswitch;
-
-	/* don't handle for multi-VIF cases */
-	chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf);
-	if (chanctx->refcount > 1)
-		goto failed_chswitch;
 
-	num_chanctx = 0;
-	list_for_each_entry_rcu(chanctx, &sdata->local->chanctx_list, list)
-		num_chanctx++;
+	params.radar_required = err;
 
-	if (num_chanctx > 1)
-		goto failed_chswitch;
-
-	rcu_read_unlock();
+	if (cfg80211_chandef_identical(&params.chandef,
+				       &sdata->vif.bss_conf.chandef)) {
+		mcsa_dbg(sdata,
+			 "received csa with an identical chandef, ignoring\n");
+		return true;
+	}
 
 	mcsa_dbg(sdata,
 		 "received channel switch announcement to go to channel %d MHz\n",
@@ -947,30 +927,16 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata,
 		ifmsh->pre_value = csa_ie.pre_value;
 	}
 
-	if (ifmsh->chsw_ttl < ifmsh->mshcfg.dot11MeshTTL) {
-		if (ieee80211_mesh_csa_beacon(sdata, &params, false) < 0)
-			return false;
-	} else {
+	if (ifmsh->chsw_ttl >= ifmsh->mshcfg.dot11MeshTTL)
 		return false;
-	}
 
-	sdata->csa_radar_required = params.radar_required;
+	ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_REPEATER;
 
-	if (params.block_tx)
-		ieee80211_stop_queues_by_reason(&sdata->local->hw,
-				IEEE80211_MAX_QUEUE_MAP,
-				IEEE80211_QUEUE_STOP_REASON_CSA);
-
-	sdata->csa_chandef = params.chandef;
-	sdata->vif.csa_active = true;
-
-	ieee80211_bss_info_change_notify(sdata, err);
-	drv_channel_switch_beacon(sdata, &params.chandef);
+	if (ieee80211_channel_switch(sdata->local->hw.wiphy, sdata->dev,
+				     &params) < 0)
+		return false;
 
 	return true;
-failed_chswitch:
-	rcu_read_unlock();
-	return false;
 }
 
 static void
@@ -1080,7 +1046,8 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
 		ifmsh->sync_ops->rx_bcn_presp(sdata,
 			stype, mgmt, &elems, rx_status);
 
-	if (!ifmsh->chsw_init)
+	if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT &&
+	    !sdata->vif.csa_active)
 		ieee80211_mesh_process_chnswitch(sdata, &elems, true);
 }
 
@@ -1089,29 +1056,30 @@ int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata)
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
 	struct mesh_csa_settings *tmp_csa_settings;
 	int ret = 0;
+	int changed = 0;
 
 	/* Reset the TTL value and Initiator flag */
-	ifmsh->chsw_init = false;
+	ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE;
 	ifmsh->chsw_ttl = 0;
 
 	/* Remove the CSA and MCSP elements from the beacon */
 	tmp_csa_settings = rcu_dereference(ifmsh->csa);
-	rcu_assign_pointer(ifmsh->csa, NULL);
-	kfree_rcu(tmp_csa_settings, rcu_head);
+	RCU_INIT_POINTER(ifmsh->csa, NULL);
+	if (tmp_csa_settings)
+		kfree_rcu(tmp_csa_settings, rcu_head);
 	ret = ieee80211_mesh_rebuild_beacon(sdata);
 	if (ret)
 		return -EINVAL;
 
-	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON);
+	changed |= BSS_CHANGED_BEACON;
 
 	mcsa_dbg(sdata, "complete switching to center freq %d MHz",
 		 sdata->vif.bss_conf.chandef.chan->center_freq);
-	return 0;
+	return changed;
 }
 
 int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata,
-			      struct cfg80211_csa_settings *csa_settings,
-			      bool csa_action)
+			      struct cfg80211_csa_settings *csa_settings)
 {
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
 	struct mesh_csa_settings *tmp_csa_settings;
@@ -1130,17 +1098,12 @@ int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata,
 	ret = ieee80211_mesh_rebuild_beacon(sdata);
 	if (ret) {
 		tmp_csa_settings = rcu_dereference(ifmsh->csa);
-		rcu_assign_pointer(ifmsh->csa, NULL);
+		RCU_INIT_POINTER(ifmsh->csa, NULL);
 		kfree_rcu(tmp_csa_settings, rcu_head);
 		return ret;
 	}
 
-	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON);
-
-	if (csa_action)
-		ieee80211_send_action_csa(sdata, csa_settings);
-
-	return 0;
+	return BSS_CHANGED_BEACON;
 }
 
 static int mesh_fwd_csa_frame(struct ieee80211_sub_if_data *sdata,
@@ -1204,7 +1167,8 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata,
 
 	ifmsh->pre_value = pre_value;
 
-	if (!ieee80211_mesh_process_chnswitch(sdata, &elems, false)) {
+	if (!sdata->vif.csa_active &&
+	    !ieee80211_mesh_process_chnswitch(sdata, &elems, false)) {
 		mcsa_dbg(sdata, "Failed to process CSA action frame");
 		return;
 	}
@@ -1251,7 +1215,7 @@ void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 	sdata_lock(sdata);
 
 	/* mesh already went down */
-	if (!sdata->wdev.mesh_id_len)
+	if (!sdata->u.mesh.mesh_id_len)
 		goto out;
 
 	rx_status = IEEE80211_SKB_RXCB(skb);
@@ -1304,7 +1268,7 @@ void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata)
 	sdata_lock(sdata);
 
 	/* mesh already went down */
-	if (!sdata->wdev.mesh_id_len)
+	if (!sdata->u.mesh.mesh_id_len)
 		goto out;
 
 	if (ifmsh->preq_queue_len &&
@@ -1359,7 +1323,7 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata)
 	mesh_rmc_init(sdata);
 	ifmsh->last_preq = jiffies;
 	ifmsh->next_perr = jiffies;
-	ifmsh->chsw_init = false;
+	ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE;
 	/* Allocate all mesh structures when creating the first mesh interface. */
 	if (!mesh_allocated)
 		ieee80211s_init();
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index f9514685d45..94758b9c9ed 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -37,7 +37,7 @@ static inline u32 u32_field_get(const u8 *preq_elem, int offset, bool ae)
 	return get_unaligned_le32(preq_elem + offset);
 }
 
-static inline u32 u16_field_get(const u8 *preq_elem, int offset, bool ae)
+static inline u16 u16_field_get(const u8 *preq_elem, int offset, bool ae)
 {
 	if (ae)
 		offset += 6;
@@ -544,9 +544,10 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
 		if (time_after(jiffies, ifmsh->last_sn_update +
 					net_traversal_jiffies(sdata)) ||
 		    time_before(jiffies, ifmsh->last_sn_update)) {
-			target_sn = ++ifmsh->sn;
+			++ifmsh->sn;
 			ifmsh->last_sn_update = jiffies;
 		}
+		target_sn = ifmsh->sn;
 	} else if (is_broadcast_ether_addr(target_addr) &&
 		   (target_flags & IEEE80211_PREQ_TO_FLAG)) {
 		rcu_read_lock();
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 7d050ed6fe5..cf032a8db9d 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -287,8 +287,10 @@ static void mesh_path_move_to_queue(struct mesh_path *gate_mpath,
 	struct sk_buff_head failq;
 	unsigned long flags;
 
-	BUG_ON(gate_mpath == from_mpath);
-	BUG_ON(!gate_mpath->next_hop);
+	if (WARN_ON(gate_mpath == from_mpath))
+		return;
+	if (WARN_ON(!gate_mpath->next_hop))
+		return;
 
 	__skb_queue_head_init(&failq);
 
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index cf83217103f..e8f60aa2e84 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -437,6 +437,7 @@ __mesh_sta_info_alloc(struct ieee80211_sub_if_data *sdata, u8 *hw_addr)
 	sta_info_pre_move_state(sta, IEEE80211_STA_AUTHORIZED);
 
 	set_sta_flag(sta, WLAN_STA_WME);
+	sta->sta.wme = true;
 
 	return sta;
 }
diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c
index 2802f9d9279..ad8b377b4b9 100644
--- a/net/mac80211/mesh_ps.c
+++ b/net/mac80211/mesh_ps.c
@@ -36,6 +36,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta)
 				      sdata->vif.addr);
 	nullfunc->frame_control = fc;
 	nullfunc->duration_id = 0;
+	nullfunc->seq_ctrl = 0;
 	/* no address resolution for this frame -> set addr 1 immediately */
 	memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
 	memset(skb_put(skb, 2), 0, 2); /* append QoS control field */
diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c
index d1cf2d55349..09625d6205c 100644
--- a/net/mac80211/mesh_sync.c
+++ b/net/mac80211/mesh_sync.c
@@ -164,12 +164,15 @@ no_sync:
 	rcu_read_unlock();
 }
 
-static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata)
+static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata,
+					 struct beacon_data *beacon)
 {
 	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+	u8 cap;
 
 	WARN_ON(ifmsh->mesh_sp_id != IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET);
-	BUG_ON(!rcu_read_lock_held());
+	WARN_ON(!rcu_read_lock_held());
+	cap = beacon->meshconf->meshconf_cap;
 
 	spin_lock_bh(&ifmsh->sync_offset_lock);
 
@@ -194,6 +197,10 @@ static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata)
 		ifmsh->adjusting_tbtt = false;
 	}
 	spin_unlock_bh(&ifmsh->sync_offset_lock);
+
+	beacon->meshconf->meshconf_cap = ifmsh->adjusting_tbtt ?
+			IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING | cap :
+			~IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING & cap;
 }
 
 static const struct sync_method sync_methods[] = {
diff --git a/net/mac80211/michael.h b/net/mac80211/michael.h
index 3b848dad958..0e4886f881f 100644
--- a/net/mac80211/michael.h
+++ b/net/mac80211/michael.h
@@ -11,6 +11,7 @@
 #define MICHAEL_H
 
 #include <linux/types.h>
+#include <linux/ieee80211.h>
 
 #define MICHAEL_MIC_LEN 8
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 900ead344f5..3345401be1b 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -131,13 +131,13 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata)
 	if (unlikely(!sdata->u.mgd.associated))
 		return;
 
+	ifmgd->probe_send_count = 0;
+
 	if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR)
 		return;
 
 	mod_timer(&sdata->u.mgd.conn_mon_timer,
 		  round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME));
-
-	ifmgd->probe_send_count = 0;
 }
 
 static int ecw2cw(int ecw)
@@ -222,6 +222,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	switch (vht_oper->chan_width) {
 	case IEEE80211_VHT_CHANWIDTH_USE_HT:
 		vht_chandef.width = chandef->width;
+		vht_chandef.center_freq1 = chandef->center_freq1;
 		break;
 	case IEEE80211_VHT_CHANWIDTH_80MHZ:
 		vht_chandef.width = NL80211_CHAN_WIDTH_80;
@@ -271,6 +272,28 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	ret = 0;
 
 out:
+	/*
+	 * When tracking the current AP, don't do any further checks if the
+	 * new chandef is identical to the one we're currently using for the
+	 * connection. This keeps us from playing ping-pong with regulatory,
+	 * without it the following can happen (for example):
+	 *  - connect to an AP with 80 MHz, world regdom allows 80 MHz
+	 *  - AP advertises regdom US
+	 *  - CRDA loads regdom US with 80 MHz prohibited (old database)
+	 *  - the code below detects an unsupported channel, downgrades, and
+	 *    we disconnect from the AP in the caller
+	 *  - disconnect causes CRDA to reload world regdomain and the game
+	 *    starts anew.
+	 * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881)
+	 *
+	 * It seems possible that there are still scenarios with CSA or real
+	 * bandwidth changes where a this could happen, but those cases are
+	 * less common and wouldn't completely prevent using the AP.
+	 */
+	if (tracking &&
+	    cfg80211_chandef_identical(chandef, &sdata->vif.bss_conf.chandef))
+		return ret;
+
 	/* don't print the message below for VHT mismatch if VHT is disabled */
 	if (ret & IEEE80211_STA_DISABLE_VHT)
 		vht_chandef = *chandef;
@@ -508,6 +531,7 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata,
 	u8 *pos;
 	u32 cap;
 	struct ieee80211_sta_vht_cap vht_cap;
+	u32 mask, ap_bf_sts, our_bf_sts;
 
 	BUILD_BUG_ON(sizeof(vht_cap) != sizeof(sband->vht_cap));
 
@@ -535,6 +559,16 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata,
 			cpu_to_le32(IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE)))
 		cap &= ~IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE;
 
+	mask = IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK;
+
+	ap_bf_sts = le32_to_cpu(ap_vht_cap->vht_cap_info) & mask;
+	our_bf_sts = cap & mask;
+
+	if (ap_bf_sts < our_bf_sts) {
+		cap &= ~mask;
+		cap |= ap_bf_sts;
+	}
+
 	/* reserve and fill IE */
 	pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2);
 	ieee80211_ie_build_vht_cap(pos, &vht_cap, cap);
@@ -745,6 +779,34 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		ieee80211_add_ht_ie(sdata, skb, assoc_data->ap_ht_param,
 				    sband, chan, sdata->smps_mode);
 
+	/* if present, add any custom IEs that go before VHT */
+	if (assoc_data->ie_len) {
+		static const u8 before_vht[] = {
+			WLAN_EID_SSID,
+			WLAN_EID_SUPP_RATES,
+			WLAN_EID_EXT_SUPP_RATES,
+			WLAN_EID_PWR_CAPABILITY,
+			WLAN_EID_SUPPORTED_CHANNELS,
+			WLAN_EID_RSN,
+			WLAN_EID_QOS_CAPA,
+			WLAN_EID_RRM_ENABLED_CAPABILITIES,
+			WLAN_EID_MOBILITY_DOMAIN,
+			WLAN_EID_SUPPORTED_REGULATORY_CLASSES,
+			WLAN_EID_HT_CAPABILITY,
+			WLAN_EID_BSS_COEX_2040,
+			WLAN_EID_EXT_CAPABILITY,
+			WLAN_EID_QOS_TRAFFIC_CAPA,
+			WLAN_EID_TIM_BCAST_REQ,
+			WLAN_EID_INTERWORKING,
+		};
+		noffset = ieee80211_ie_split(assoc_data->ie, assoc_data->ie_len,
+					     before_vht, ARRAY_SIZE(before_vht),
+					     offset);
+		pos = skb_put(skb, noffset - offset);
+		memcpy(pos, assoc_data->ie + offset, noffset - offset);
+		offset = noffset;
+	}
+
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
 		ieee80211_add_vht_ie(sdata, skb, sband,
 				     &assoc_data->ap_vht_cap);
@@ -888,7 +950,9 @@ static void ieee80211_chswitch_work(struct work_struct *work)
 	if (!ifmgd->associated)
 		goto out;
 
+	mutex_lock(&local->mtx);
 	ret = ieee80211_vif_change_channel(sdata, &changed);
+	mutex_unlock(&local->mtx);
 	if (ret) {
 		sdata_info(sdata,
 			   "vif channel switch failed, disconnecting\n");
@@ -911,16 +975,23 @@ static void ieee80211_chswitch_work(struct work_struct *work)
 	/* XXX: shouldn't really modify cfg80211-owned data! */
 	ifmgd->associated->channel = sdata->csa_chandef.chan;
 
+	ieee80211_bss_info_change_notify(sdata, changed);
+
+	mutex_lock(&local->mtx);
+	sdata->vif.csa_active = false;
 	/* XXX: wait for a beacon first? */
-	ieee80211_wake_queues_by_reason(&local->hw,
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
 					IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
 
-	ieee80211_bss_info_change_notify(sdata, changed);
-
- out:
-	sdata->vif.csa_active = false;
 	ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED;
+
+	ieee80211_sta_reset_beacon_monitor(sdata);
+	ieee80211_sta_reset_conn_monitor(sdata);
+
+out:
 	sdata_unlock(sdata);
 }
 
@@ -999,7 +1070,6 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	}
 
 	ifmgd->flags |= IEEE80211_STA_CSA_RECEIVED;
-	sdata->vif.csa_active = true;
 
 	mutex_lock(&local->chanctx_mtx);
 	if (local->use_chanctx) {
@@ -1026,7 +1096,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	}
 	chanctx = container_of(rcu_access_pointer(sdata->vif.chanctx_conf),
 			       struct ieee80211_chanctx, conf);
-	if (chanctx->refcount > 1) {
+	if (ieee80211_chanctx_refcount(local, chanctx) > 1) {
 		sdata_info(sdata,
 			   "channel switch with multiple interfaces on the same channel, disconnecting\n");
 		ieee80211_queue_work(&local->hw,
@@ -1038,10 +1108,15 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 
 	sdata->csa_chandef = csa_ie.chandef;
 
-	if (csa_ie.mode)
+	mutex_lock(&local->mtx);
+	sdata->vif.csa_active = true;
+	sdata->csa_block_tx = csa_ie.mode;
+
+	if (sdata->csa_block_tx)
 		ieee80211_stop_queues_by_reason(&local->hw,
-				IEEE80211_MAX_QUEUE_MAP,
-				IEEE80211_QUEUE_STOP_REASON_CSA);
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
 
 	if (local->ops->channel_switch) {
 		/* use driver's channel switch callback */
@@ -1401,10 +1476,14 @@ void ieee80211_dfs_cac_timer_work(struct work_struct *work)
 			     dfs_cac_timer_work);
 	struct cfg80211_chan_def chandef = sdata->vif.bss_conf.chandef;
 
-	ieee80211_vif_release_channel(sdata);
-	cfg80211_cac_event(sdata->dev, &chandef,
-			   NL80211_RADAR_CAC_FINISHED,
-			   GFP_KERNEL);
+	mutex_lock(&sdata->local->mtx);
+	if (sdata->wdev.cac_started) {
+		ieee80211_vif_release_channel(sdata);
+		cfg80211_cac_event(sdata->dev, &chandef,
+				   NL80211_RADAR_CAC_FINISHED,
+				   GFP_KERNEL);
+	}
+	mutex_unlock(&sdata->local->mtx);
 }
 
 /* MLME */
@@ -1698,7 +1777,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	memset(ifmgd->bssid, 0, ETH_ALEN);
 
 	/* remove AP and TDLS peers */
-	sta_info_flush_defer(sdata);
+	sta_info_flush(sdata);
 
 	/* finally reset all BSS / config parameters */
 	changed |= ieee80211_reset_erp_info(sdata);
@@ -1747,8 +1826,16 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	ifmgd->have_beacon = false;
 
 	ifmgd->flags = 0;
+	mutex_lock(&local->mtx);
 	ieee80211_vif_release_channel(sdata);
 
+	sdata->vif.csa_active = false;
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
+
 	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
 }
 
@@ -1975,6 +2062,7 @@ EXPORT_SYMBOL(ieee80211_ap_probereq_get);
 
 static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 {
+	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
 
@@ -1988,10 +2076,14 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 			       WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY,
 			       true, frame_buf);
 	ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED;
+
+	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = false;
-	ieee80211_wake_queues_by_reason(&sdata->local->hw,
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
 					IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
 
 	cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
 			      IEEE80211_DEAUTH_FRAME_LEN);
@@ -2070,7 +2162,9 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata,
 		memset(sdata->u.mgd.bssid, 0, ETH_ALEN);
 		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID);
 		sdata->u.mgd.flags = 0;
+		mutex_lock(&sdata->local->mtx);
 		ieee80211_vif_release_channel(sdata);
+		mutex_unlock(&sdata->local->mtx);
 	}
 
 	cfg80211_put_bss(sdata->local->hw.wiphy, auth_data->bss);
@@ -2200,6 +2294,62 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 	/* ignore frame -- wait for timeout */
 }
 
+#define case_WLAN(type) \
+	case WLAN_REASON_##type: return #type
+
+static const char *ieee80211_get_reason_code_string(u16 reason_code)
+{
+	switch (reason_code) {
+	case_WLAN(UNSPECIFIED);
+	case_WLAN(PREV_AUTH_NOT_VALID);
+	case_WLAN(DEAUTH_LEAVING);
+	case_WLAN(DISASSOC_DUE_TO_INACTIVITY);
+	case_WLAN(DISASSOC_AP_BUSY);
+	case_WLAN(CLASS2_FRAME_FROM_NONAUTH_STA);
+	case_WLAN(CLASS3_FRAME_FROM_NONASSOC_STA);
+	case_WLAN(DISASSOC_STA_HAS_LEFT);
+	case_WLAN(STA_REQ_ASSOC_WITHOUT_AUTH);
+	case_WLAN(DISASSOC_BAD_POWER);
+	case_WLAN(DISASSOC_BAD_SUPP_CHAN);
+	case_WLAN(INVALID_IE);
+	case_WLAN(MIC_FAILURE);
+	case_WLAN(4WAY_HANDSHAKE_TIMEOUT);
+	case_WLAN(GROUP_KEY_HANDSHAKE_TIMEOUT);
+	case_WLAN(IE_DIFFERENT);
+	case_WLAN(INVALID_GROUP_CIPHER);
+	case_WLAN(INVALID_PAIRWISE_CIPHER);
+	case_WLAN(INVALID_AKMP);
+	case_WLAN(UNSUPP_RSN_VERSION);
+	case_WLAN(INVALID_RSN_IE_CAP);
+	case_WLAN(IEEE8021X_FAILED);
+	case_WLAN(CIPHER_SUITE_REJECTED);
+	case_WLAN(DISASSOC_UNSPECIFIED_QOS);
+	case_WLAN(DISASSOC_QAP_NO_BANDWIDTH);
+	case_WLAN(DISASSOC_LOW_ACK);
+	case_WLAN(DISASSOC_QAP_EXCEED_TXOP);
+	case_WLAN(QSTA_LEAVE_QBSS);
+	case_WLAN(QSTA_NOT_USE);
+	case_WLAN(QSTA_REQUIRE_SETUP);
+	case_WLAN(QSTA_TIMEOUT);
+	case_WLAN(QSTA_CIPHER_NOT_SUPP);
+	case_WLAN(MESH_PEER_CANCELED);
+	case_WLAN(MESH_MAX_PEERS);
+	case_WLAN(MESH_CONFIG);
+	case_WLAN(MESH_CLOSE);
+	case_WLAN(MESH_MAX_RETRIES);
+	case_WLAN(MESH_CONFIRM_TIMEOUT);
+	case_WLAN(MESH_INVALID_GTK);
+	case_WLAN(MESH_INCONSISTENT_PARAM);
+	case_WLAN(MESH_INVALID_SECURITY);
+	case_WLAN(MESH_PATH_ERROR);
+	case_WLAN(MESH_PATH_NOFORWARD);
+	case_WLAN(MESH_PATH_DEST_UNREACHABLE);
+	case_WLAN(MAC_EXISTS_IN_MBSS);
+	case_WLAN(MESH_CHAN_REGULATORY);
+	case_WLAN(MESH_CHAN);
+	default: return "<unknown>";
+	}
+}
 
 static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata,
 				     struct ieee80211_mgmt *mgmt, size_t len)
@@ -2221,8 +2371,8 @@ static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata,
 
 	reason_code = le16_to_cpu(mgmt->u.deauth.reason_code);
 
-	sdata_info(sdata, "deauthenticated from %pM (Reason: %u)\n",
-		   bssid, reason_code);
+	sdata_info(sdata, "deauthenticated from %pM (Reason: %u=%s)\n",
+		   bssid, reason_code, ieee80211_get_reason_code_string(reason_code));
 
 	ieee80211_set_disassoc(sdata, 0, 0, false, NULL);
 
@@ -2319,7 +2469,9 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
 		memset(sdata->u.mgd.bssid, 0, ETH_ALEN);
 		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID);
 		sdata->u.mgd.flags = 0;
+		mutex_lock(&sdata->local->mtx);
 		ieee80211_vif_release_channel(sdata);
+		mutex_unlock(&sdata->local->mtx);
 	}
 
 	kfree(assoc_data);
@@ -2653,28 +2805,20 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 				  struct ieee802_11_elems *elems)
 {
 	struct ieee80211_local *local = sdata->local;
-	int freq;
 	struct ieee80211_bss *bss;
 	struct ieee80211_channel *channel;
 
 	sdata_assert_lock(sdata);
 
-	if (elems->ds_params)
-		freq = ieee80211_channel_to_frequency(elems->ds_params[0],
-						      rx_status->band);
-	else
-		freq = rx_status->freq;
-
-	channel = ieee80211_get_channel(local->hw.wiphy, freq);
-
-	if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
+	channel = ieee80211_get_channel(local->hw.wiphy, rx_status->freq);
+	if (!channel)
 		return;
 
 	bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems,
 					channel);
 	if (bss) {
-		ieee80211_rx_bss_put(local, bss);
 		sdata->vif.bss_conf.beacon_rate = bss->beacon_rate;
+		ieee80211_rx_bss_put(local, bss);
 	}
 }
 
@@ -3424,6 +3568,9 @@ static void ieee80211_sta_bcn_mon_timer(unsigned long data)
 	if (local->quiescing)
 		return;
 
+	if (sdata->vif.csa_active)
+		return;
+
 	sdata->u.mgd.connection_loss = false;
 	ieee80211_queue_work(&sdata->local->hw,
 			     &sdata->u.mgd.beacon_connection_loss_work);
@@ -3439,6 +3586,9 @@ static void ieee80211_sta_conn_mon_timer(unsigned long data)
 	if (local->quiescing)
 		return;
 
+	if (sdata->vif.csa_active)
+		return;
+
 	ieee80211_queue_work(&local->hw, &ifmgd->monitor_work);
 }
 
@@ -3469,6 +3619,38 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata)
 }
 
 #ifdef CONFIG_PM
+void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
+
+	sdata_lock(sdata);
+
+	if (ifmgd->auth_data || ifmgd->assoc_data) {
+		const u8 *bssid = ifmgd->auth_data ?
+				ifmgd->auth_data->bss->bssid :
+				ifmgd->assoc_data->bss->bssid;
+
+		/*
+		 * If we are trying to authenticate / associate while suspending,
+		 * cfg80211 won't know and won't actually abort those attempts,
+		 * thus we need to do that ourselves.
+		 */
+		ieee80211_send_deauth_disassoc(sdata, bssid,
+					       IEEE80211_STYPE_DEAUTH,
+					       WLAN_REASON_DEAUTH_LEAVING,
+					       false, frame_buf);
+		if (ifmgd->assoc_data)
+			ieee80211_destroy_assoc_data(sdata, false);
+		if (ifmgd->auth_data)
+			ieee80211_destroy_auth_data(sdata, false);
+		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
+				      IEEE80211_DEAUTH_FRAME_LEN);
+	}
+
+	sdata_unlock(sdata);
+}
+
 void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -3553,7 +3735,7 @@ int ieee80211_max_network_latency(struct notifier_block *nb,
 	ieee80211_recalc_ps(local, latency_usec);
 	mutex_unlock(&local->iflist_mtx);
 
-	return 0;
+	return NOTIFY_OK;
 }
 
 static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata,
@@ -3670,6 +3852,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	/* will change later if needed */
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 
+	mutex_lock(&local->mtx);
 	/*
 	 * If this fails (possibly due to channel context sharing
 	 * on incompatible channels, e.g. 80+80 and 160 sharing the
@@ -3681,13 +3864,15 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	/* don't downgrade for 5 and 10 MHz channels, though. */
 	if (chandef.width == NL80211_CHAN_WIDTH_5 ||
 	    chandef.width == NL80211_CHAN_WIDTH_10)
-		return ret;
+		goto out;
 
 	while (ret && chandef.width != NL80211_CHAN_WIDTH_20_NOHT) {
 		ifmgd->flags |= ieee80211_chandef_downgrade(&chandef);
 		ret = ieee80211_vif_use_channel(sdata, &chandef,
 						IEEE80211_CHANCTX_SHARED);
 	}
+ out:
+	mutex_unlock(&local->mtx);
 	return ret;
 }
 
@@ -3738,6 +3923,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 		if (WARN_ON(!chanctx_conf)) {
 			rcu_read_unlock();
+			sta_info_free(local, new_sta);
 			return -EINVAL;
 		}
 		rate_flags = ieee80211_chandef_rate_flags(&chanctx_conf->def);
@@ -4283,37 +4469,41 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
 	bool tx = !req->local_state_change;
-	bool report_frame = false;
 
-	sdata_info(sdata,
-		   "deauthenticating from %pM by local choice (reason=%d)\n",
-		   req->bssid, req->reason_code);
+	if (ifmgd->auth_data &&
+	    ether_addr_equal(ifmgd->auth_data->bss->bssid, req->bssid)) {
+		sdata_info(sdata,
+			   "aborting authentication with %pM by local choice (Reason: %u=%s)\n",
+			   req->bssid, req->reason_code,
+			   ieee80211_get_reason_code_string(req->reason_code));
 
-	if (ifmgd->auth_data) {
 		drv_mgd_prepare_tx(sdata->local, sdata);
 		ieee80211_send_deauth_disassoc(sdata, req->bssid,
 					       IEEE80211_STYPE_DEAUTH,
 					       req->reason_code, tx,
 					       frame_buf);
 		ieee80211_destroy_auth_data(sdata, false);
+		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
+				      IEEE80211_DEAUTH_FRAME_LEN);
 
-		report_frame = true;
-		goto out;
+		return 0;
 	}
 
 	if (ifmgd->associated &&
 	    ether_addr_equal(ifmgd->associated->bssid, req->bssid)) {
+		sdata_info(sdata,
+			   "deauthenticating from %pM by local choice (Reason: %u=%s)\n",
+			   req->bssid, req->reason_code,
+			   ieee80211_get_reason_code_string(req->reason_code));
+
 		ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH,
 				       req->reason_code, tx, frame_buf);
-		report_frame = true;
-	}
-
- out:
-	if (report_frame)
 		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
 				      IEEE80211_DEAUTH_FRAME_LEN);
+		return 0;
+	}
 
-	return 0;
+	return -ENOTCONN;
 }
 
 int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata,
@@ -4333,8 +4523,8 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata,
 		return -ENOLINK;
 
 	sdata_info(sdata,
-		   "disassociating from %pM by local choice (reason=%d)\n",
-		   req->bss->bssid, req->reason_code);
+		   "disassociating from %pM by local choice (Reason: %u=%s)\n",
+		   req->bss->bssid, req->reason_code, ieee80211_get_reason_code_string(req->reason_code));
 
 	memcpy(bssid, req->bss->bssid, ETH_ALEN);
 	ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DISASSOC,
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 0c2a29484c0..7a17decd27f 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -333,7 +333,7 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 		container_of(work, struct ieee80211_roc_work, work.work);
 	struct ieee80211_sub_if_data *sdata = roc->sdata;
 	struct ieee80211_local *local = sdata->local;
-	bool started;
+	bool started, on_channel;
 
 	mutex_lock(&local->mtx);
 
@@ -354,13 +354,26 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 	if (!roc->started) {
 		struct ieee80211_roc_work *dep;
 
-		/* start this ROC */
+		WARN_ON(local->use_chanctx);
+
+		/* If actually operating on the desired channel (with at least
+		 * 20 MHz channel width) don't stop all the operations but still
+		 * treat it as though the ROC operation started properly, so
+		 * other ROC operations won't interfere with this one.
+		 */
+		roc->on_channel = roc->chan == local->_oper_chandef.chan &&
+				  local->_oper_chandef.width != NL80211_CHAN_WIDTH_5 &&
+				  local->_oper_chandef.width != NL80211_CHAN_WIDTH_10;
 
-		/* switch channel etc */
+		/* start this ROC */
 		ieee80211_recalc_idle(local);
 
-		local->tmp_channel = roc->chan;
-		ieee80211_hw_config(local, 0);
+		if (!roc->on_channel) {
+			ieee80211_offchannel_stop_vifs(local);
+
+			local->tmp_channel = roc->chan;
+			ieee80211_hw_config(local, 0);
+		}
 
 		/* tell userspace or send frame */
 		ieee80211_handle_roc_started(roc);
@@ -379,9 +392,10 @@ void ieee80211_sw_roc_work(struct work_struct *work)
  finish:
 		list_del(&roc->list);
 		started = roc->started;
+		on_channel = roc->on_channel;
 		ieee80211_roc_notify_destroy(roc, !roc->abort);
 
-		if (started) {
+		if (started && !on_channel) {
 			ieee80211_flush_queues(local, NULL);
 
 			local->tmp_channel = NULL;
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 34012620434..d478b880a0a 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -37,9 +37,8 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 					IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_SUSPEND);
 
-	/* flush out all packets and station cleanup call_rcu()s */
+	/* flush out all packets */
 	synchronize_net();
-	rcu_barrier();
 
 	ieee80211_flush_queues(local, NULL);
 
@@ -101,10 +100,18 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 
 	/* remove all interfaces that were created in the driver */
 	list_for_each_entry(sdata, &local->interfaces, list) {
-		if (!ieee80211_sdata_running(sdata) ||
-		    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
-		    sdata->vif.type == NL80211_IFTYPE_MONITOR)
+		if (!ieee80211_sdata_running(sdata))
 			continue;
+		switch (sdata->vif.type) {
+		case NL80211_IFTYPE_AP_VLAN:
+		case NL80211_IFTYPE_MONITOR:
+			continue;
+		case NL80211_IFTYPE_STATION:
+			ieee80211_mgd_quiesce(sdata);
+			break;
+		default:
+			break;
+		}
 
 		drv_remove_interface(local, sdata);
 	}
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 22b223f13c9..8fdadfd94ba 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -10,15 +10,15 @@
 
 #include <linux/kernel.h>
 #include <linux/rtnetlink.h>
-#include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include "rate.h"
 #include "ieee80211_i.h"
 #include "debugfs.h"
 
 struct rate_control_alg {
 	struct list_head list;
-	struct rate_control_ops *ops;
+	const struct rate_control_ops *ops;
 };
 
 static LIST_HEAD(rate_ctrl_algs);
@@ -29,7 +29,7 @@ module_param(ieee80211_default_rc_algo, charp, 0644);
 MODULE_PARM_DESC(ieee80211_default_rc_algo,
 		 "Default rate control algorithm for mac80211 to use");
 
-int ieee80211_rate_control_register(struct rate_control_ops *ops)
+int ieee80211_rate_control_register(const struct rate_control_ops *ops)
 {
 	struct rate_control_alg *alg;
 
@@ -60,7 +60,7 @@ int ieee80211_rate_control_register(struct rate_control_ops *ops)
 }
 EXPORT_SYMBOL(ieee80211_rate_control_register);
 
-void ieee80211_rate_control_unregister(struct rate_control_ops *ops)
+void ieee80211_rate_control_unregister(const struct rate_control_ops *ops)
 {
 	struct rate_control_alg *alg;
 
@@ -76,32 +76,31 @@ void ieee80211_rate_control_unregister(struct rate_control_ops *ops)
 }
 EXPORT_SYMBOL(ieee80211_rate_control_unregister);
 
-static struct rate_control_ops *
+static const struct rate_control_ops *
 ieee80211_try_rate_control_ops_get(const char *name)
 {
 	struct rate_control_alg *alg;
-	struct rate_control_ops *ops = NULL;
+	const struct rate_control_ops *ops = NULL;
 
 	if (!name)
 		return NULL;
 
 	mutex_lock(&rate_ctrl_mutex);
 	list_for_each_entry(alg, &rate_ctrl_algs, list) {
-		if (!strcmp(alg->ops->name, name))
-			if (try_module_get(alg->ops->module)) {
-				ops = alg->ops;
-				break;
-			}
+		if (!strcmp(alg->ops->name, name)) {
+			ops = alg->ops;
+			break;
+		}
 	}
 	mutex_unlock(&rate_ctrl_mutex);
 	return ops;
 }
 
 /* Get the rate control algorithm. */
-static struct rate_control_ops *
+static const struct rate_control_ops *
 ieee80211_rate_control_ops_get(const char *name)
 {
-	struct rate_control_ops *ops;
+	const struct rate_control_ops *ops;
 	const char *alg_name;
 
 	kparam_block_sysfs_write(ieee80211_default_rc_algo);
@@ -111,10 +110,6 @@ ieee80211_rate_control_ops_get(const char *name)
 		alg_name = name;
 
 	ops = ieee80211_try_rate_control_ops_get(alg_name);
-	if (!ops) {
-		request_module("rc80211_%s", alg_name);
-		ops = ieee80211_try_rate_control_ops_get(alg_name);
-	}
 	if (!ops && name)
 		/* try default if specific alg requested but not found */
 		ops = ieee80211_try_rate_control_ops_get(ieee80211_default_rc_algo);
@@ -127,11 +122,6 @@ ieee80211_rate_control_ops_get(const char *name)
 	return ops;
 }
 
-static void ieee80211_rate_control_ops_put(struct rate_control_ops *ops)
-{
-	module_put(ops->module);
-}
-
 #ifdef CONFIG_MAC80211_DEBUGFS
 static ssize_t rcname_read(struct file *file, char __user *userbuf,
 			   size_t count, loff_t *ppos)
@@ -158,11 +148,11 @@ static struct rate_control_ref *rate_control_alloc(const char *name,
 
 	ref = kmalloc(sizeof(struct rate_control_ref), GFP_KERNEL);
 	if (!ref)
-		goto fail_ref;
+		return NULL;
 	ref->local = local;
 	ref->ops = ieee80211_rate_control_ops_get(name);
 	if (!ref->ops)
-		goto fail_ops;
+		goto free;
 
 #ifdef CONFIG_MAC80211_DEBUGFS
 	debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir);
@@ -172,14 +162,11 @@ static struct rate_control_ref *rate_control_alloc(const char *name,
 
 	ref->priv = ref->ops->alloc(&local->hw, debugfsdir);
 	if (!ref->priv)
-		goto fail_priv;
+		goto free;
 	return ref;
 
-fail_priv:
-	ieee80211_rate_control_ops_put(ref->ops);
-fail_ops:
+free:
 	kfree(ref);
-fail_ref:
 	return NULL;
 }
 
@@ -192,7 +179,6 @@ static void rate_control_free(struct rate_control_ref *ctrl_ref)
 	ctrl_ref->local->debugfs.rcdir = NULL;
 #endif
 
-	ieee80211_rate_control_ops_put(ctrl_ref->ops);
 	kfree(ctrl_ref);
 }
 
diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h
index b95e16c0708..9aa2a1190a8 100644
--- a/net/mac80211/rate.h
+++ b/net/mac80211/rate.h
@@ -21,7 +21,7 @@
 
 struct rate_control_ref {
 	struct ieee80211_local *local;
-	struct rate_control_ops *ops;
+	const struct rate_control_ops *ops;
 	void *priv;
 };
 
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index d2f19f7e709..1c1469c36dc 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -135,7 +135,7 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
 	u32 usecs;
 	int i;
 
-	for (i=0; i < MAX_THR_RATES; i++)
+	for (i = 0; i < MAX_THR_RATES; i++)
 	    tmp_tp_rate[i] = 0;
 
 	for (i = 0; i < mi->n_rates; i++) {
@@ -190,7 +190,7 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
 		 * choose the maximum throughput rate as max_prob_rate
 		 * (2) if all success probabilities < 95%, the rate with
 		 * highest success probability is choosen as max_prob_rate */
-		if (mr->probability >= MINSTREL_FRAC(95,100)) {
+		if (mr->probability >= MINSTREL_FRAC(95, 100)) {
 			if (mr->cur_tp >= mi->r[tmp_prob_rate].cur_tp)
 				tmp_prob_rate = i;
 		} else {
@@ -220,7 +220,7 @@ minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi)
 
 static void
 minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband,
-                   struct ieee80211_sta *sta, void *priv_sta,
+		   struct ieee80211_sta *sta, void *priv_sta,
 		   struct sk_buff *skb)
 {
 	struct minstrel_priv *mp = priv;
@@ -260,7 +260,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband,
 
 static inline unsigned int
 minstrel_get_retry_count(struct minstrel_rate *mr,
-                         struct ieee80211_tx_info *info)
+			 struct ieee80211_tx_info *info)
 {
 	unsigned int retry = mr->adjusted_retry_count;
 
@@ -657,7 +657,18 @@ minstrel_free(void *priv)
 	kfree(priv);
 }
 
-struct rate_control_ops mac80211_minstrel = {
+static u32 minstrel_get_expected_throughput(void *priv_sta)
+{
+	struct minstrel_sta_info *mi = priv_sta;
+	int idx = mi->max_tp_rate[0];
+
+	/* convert pkt per sec in kbps (1200 is the average pkt size used for
+	 * computing cur_tp
+	 */
+	return MINSTREL_TRUNC(mi->r[idx].cur_tp) * 1200 * 8 / 1024;
+}
+
+const struct rate_control_ops mac80211_minstrel = {
 	.name = "minstrel",
 	.tx_status = minstrel_tx_status,
 	.get_rate = minstrel_get_rate,
@@ -670,6 +681,7 @@ struct rate_control_ops mac80211_minstrel = {
 	.add_sta_debugfs = minstrel_add_sta_debugfs,
 	.remove_sta_debugfs = minstrel_remove_sta_debugfs,
 #endif
+	.get_expected_throughput = minstrel_get_expected_throughput,
 };
 
 int __init
diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h
index f4301f4b2e4..046d1bd598a 100644
--- a/net/mac80211/rc80211_minstrel.h
+++ b/net/mac80211/rc80211_minstrel.h
@@ -123,7 +123,7 @@ struct minstrel_debugfs_info {
 	char buf[];
 };
 
-extern struct rate_control_ops mac80211_minstrel;
+extern const struct rate_control_ops mac80211_minstrel;
 void minstrel_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir);
 void minstrel_remove_sta_debugfs(void *priv, void *priv_sta);
 
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index d2ed18d82fe..85c1e74b771 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -22,7 +22,7 @@
 #define MCS_NBITS (AVG_PKT_SIZE << 3)
 
 /* Number of symbols for a packet with (bps) bits per symbol */
-#define MCS_NSYMS(bps) ((MCS_NBITS + (bps) - 1) / (bps))
+#define MCS_NSYMS(bps) DIV_ROUND_UP(MCS_NBITS, (bps))
 
 /* Transmission time (nanoseconds) for a packet containing (syms) symbols */
 #define MCS_SYMBOL_TIME(sgi, syms)					\
@@ -63,7 +63,7 @@
 
 #define CCK_DURATION(_bitrate, _short, _len)		\
 	(1000 * (10 /* SIFS */ +			\
-	 (_short ? 72 + 24 : 144 + 48 ) +		\
+	 (_short ? 72 + 24 : 144 + 48) +		\
 	 (8 * (_len + 4) * 10) / (_bitrate)))
 
 #define CCK_ACK_DURATION(_bitrate, _short)			\
@@ -124,7 +124,7 @@ const struct mcs_group minstrel_mcs_groups[] = {
 
 #define MINSTREL_CCK_GROUP	(ARRAY_SIZE(minstrel_mcs_groups) - 1)
 
-static u8 sample_table[SAMPLE_COLUMNS][MCS_GROUP_RATES];
+static u8 sample_table[SAMPLE_COLUMNS][MCS_GROUP_RATES] __read_mostly;
 
 static void
 minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi);
@@ -226,8 +226,9 @@ minstrel_ht_calc_tp(struct minstrel_ht_sta *mi, int group, int rate)
 		nsecs = 1000 * mi->overhead / MINSTREL_TRUNC(mi->avg_ampdu_len);
 
 	nsecs += minstrel_mcs_groups[group].duration[rate];
-	tp = 1000000 * ((prob * 1000) / nsecs);
 
+	/* prob is scaled - see MINSTREL_FRAC above */
+	tp = 1000000 * ((prob * 1000) / nsecs);
 	mr->cur_tp = MINSTREL_TRUNC(tp);
 }
 
@@ -1031,7 +1032,23 @@ minstrel_ht_free(void *priv)
 	mac80211_minstrel.free(priv);
 }
 
-static struct rate_control_ops mac80211_minstrel_ht = {
+static u32 minstrel_ht_get_expected_throughput(void *priv_sta)
+{
+	struct minstrel_ht_sta_priv *msp = priv_sta;
+	struct minstrel_ht_sta *mi = &msp->ht;
+	int i, j;
+
+	if (!msp->is_ht)
+		return mac80211_minstrel.get_expected_throughput(priv_sta);
+
+	i = mi->max_tp_rate / MCS_GROUP_RATES;
+	j = mi->max_tp_rate % MCS_GROUP_RATES;
+
+	/* convert cur_tp from pkt per second in kbps */
+	return mi->groups[i].rates[j].cur_tp * AVG_PKT_SIZE * 8 / 1024;
+}
+
+static const struct rate_control_ops mac80211_minstrel_ht = {
 	.name = "minstrel_ht",
 	.tx_status = minstrel_ht_tx_status,
 	.get_rate = minstrel_ht_get_rate,
@@ -1045,11 +1062,11 @@ static struct rate_control_ops mac80211_minstrel_ht = {
 	.add_sta_debugfs = minstrel_ht_add_sta_debugfs,
 	.remove_sta_debugfs = minstrel_ht_remove_sta_debugfs,
 #endif
+	.get_expected_throughput = minstrel_ht_get_expected_throughput,
 };
 
 
-static void
-init_sample_table(void)
+static void __init init_sample_table(void)
 {
 	int col, i, new_idx;
 	u8 rnd[MCS_GROUP_RATES];
diff --git a/net/mac80211/rc80211_pid_algo.c b/net/mac80211/rc80211_pid_algo.c
index 958fad07b54..d0da2a70fe6 100644
--- a/net/mac80211/rc80211_pid_algo.c
+++ b/net/mac80211/rc80211_pid_algo.c
@@ -452,7 +452,7 @@ static void rate_control_pid_free_sta(void *priv, struct ieee80211_sta *sta,
 	kfree(priv_sta);
 }
 
-static struct rate_control_ops mac80211_rcpid = {
+static const struct rate_control_ops mac80211_rcpid = {
 	.name = "pid",
 	.tx_status = rate_control_pid_tx_status,
 	.get_rate = rate_control_pid_get_rate,
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 2dfa7552273..394e201cde6 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -40,8 +40,6 @@
 static struct sk_buff *remove_monitor_info(struct ieee80211_local *local,
 					   struct sk_buff *skb)
 {
-	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
-
 	if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) {
 		if (likely(skb->len > FCS_LEN))
 			__pskb_trim(skb, skb->len - FCS_LEN);
@@ -53,31 +51,28 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local,
 		}
 	}
 
-	if (status->vendor_radiotap_len)
-		__pskb_pull(skb, status->vendor_radiotap_len);
-
 	return skb;
 }
 
-static inline int should_drop_frame(struct sk_buff *skb, int present_fcs_len)
+static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len)
 {
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
-	struct ieee80211_hdr *hdr;
-
-	hdr = (void *)(skb->data + status->vendor_radiotap_len);
+	struct ieee80211_hdr *hdr = (void *)skb->data;
 
 	if (status->flag & (RX_FLAG_FAILED_FCS_CRC |
 			    RX_FLAG_FAILED_PLCP_CRC |
 			    RX_FLAG_AMPDU_IS_ZEROLEN))
-		return 1;
-	if (unlikely(skb->len < 16 + present_fcs_len +
-				status->vendor_radiotap_len))
-		return 1;
+		return true;
+
+	if (unlikely(skb->len < 16 + present_fcs_len))
+		return true;
+
 	if (ieee80211_is_ctl(hdr->frame_control) &&
 	    !ieee80211_is_pspoll(hdr->frame_control) &&
 	    !ieee80211_is_back_req(hdr->frame_control))
-		return 1;
-	return 0;
+		return true;
+
+	return false;
 }
 
 static int
@@ -90,8 +85,6 @@ ieee80211_rx_radiotap_space(struct ieee80211_local *local,
 	len = sizeof(struct ieee80211_radiotap_header) + 8;
 
 	/* allocate extra bitmaps */
-	if (status->vendor_radiotap_len)
-		len += 4;
 	if (status->chains)
 		len += 4 * hweight8(status->chains);
 
@@ -127,18 +120,6 @@ ieee80211_rx_radiotap_space(struct ieee80211_local *local,
 		len += 2 * hweight8(status->chains);
 	}
 
-	if (status->vendor_radiotap_len) {
-		if (WARN_ON_ONCE(status->vendor_radiotap_align == 0))
-			status->vendor_radiotap_align = 1;
-		/* align standard part of vendor namespace */
-		len = ALIGN(len, 2);
-		/* allocate standard part of vendor namespace */
-		len += 6;
-		/* align vendor-defined part */
-		len = ALIGN(len, status->vendor_radiotap_align);
-		/* vendor-defined part is already in skb */
-	}
-
 	return len;
 }
 
@@ -172,7 +153,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	it_present = &rthdr->it_present;
 
 	/* radiotap header, set always present flags */
-	rthdr->it_len = cpu_to_le16(rtap_len + status->vendor_radiotap_len);
+	rthdr->it_len = cpu_to_le16(rtap_len);
 	it_present_val = BIT(IEEE80211_RADIOTAP_FLAGS) |
 			 BIT(IEEE80211_RADIOTAP_CHANNEL) |
 			 BIT(IEEE80211_RADIOTAP_RX_FLAGS);
@@ -190,14 +171,6 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 				 BIT(IEEE80211_RADIOTAP_DBM_ANTSIGNAL);
 	}
 
-	if (status->vendor_radiotap_len) {
-		it_present_val |= BIT(IEEE80211_RADIOTAP_VENDOR_NAMESPACE) |
-				  BIT(IEEE80211_RADIOTAP_EXT);
-		put_unaligned_le32(it_present_val, it_present);
-		it_present++;
-		it_present_val = status->vendor_radiotap_bitmap;
-	}
-
 	put_unaligned_le32(it_present_val, it_present);
 
 	pos = (void *)(it_present + 1);
@@ -307,6 +280,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 			*pos |= IEEE80211_RADIOTAP_MCS_BW_40;
 		if (status->flag & RX_FLAG_HT_GF)
 			*pos |= IEEE80211_RADIOTAP_MCS_FMT_GF;
+		if (status->flag & RX_FLAG_LDPC)
+			*pos |= IEEE80211_RADIOTAP_MCS_FEC_LDPC;
 		stbc = (status->flag & RX_FLAG_STBC_MASK) >> RX_FLAG_STBC_SHIFT;
 		*pos |= stbc << IEEE80211_RADIOTAP_MCS_STBC_SHIFT;
 		pos++;
@@ -349,20 +324,25 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 
 		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT);
 		/* known field - how to handle 80+80? */
-		if (status->flag & RX_FLAG_80P80MHZ)
+		if (status->vht_flag & RX_VHT_FLAG_80P80MHZ)
 			known &= ~IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH;
 		put_unaligned_le16(known, pos);
 		pos += 2;
 		/* flags */
 		if (status->flag & RX_FLAG_SHORT_GI)
 			*pos |= IEEE80211_RADIOTAP_VHT_FLAG_SGI;
+		/* in VHT, STBC is binary */
+		if (status->flag & RX_FLAG_STBC_MASK)
+			*pos |= IEEE80211_RADIOTAP_VHT_FLAG_STBC;
+		if (status->vht_flag & RX_VHT_FLAG_BF)
+			*pos |= IEEE80211_RADIOTAP_VHT_FLAG_BEAMFORMED;
 		pos++;
 		/* bandwidth */
-		if (status->flag & RX_FLAG_80MHZ)
+		if (status->vht_flag & RX_VHT_FLAG_80MHZ)
 			*pos++ = 4;
-		else if (status->flag & RX_FLAG_80P80MHZ)
+		else if (status->vht_flag & RX_VHT_FLAG_80P80MHZ)
 			*pos++ = 0; /* marked not known above */
-		else if (status->flag & RX_FLAG_160MHZ)
+		else if (status->vht_flag & RX_VHT_FLAG_160MHZ)
 			*pos++ = 11;
 		else if (status->flag & RX_FLAG_40MHZ)
 			*pos++ = 1;
@@ -372,6 +352,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		*pos = (status->rate_idx << 4) | status->vht_nss;
 		pos += 4;
 		/* coding field */
+		if (status->flag & RX_FLAG_LDPC)
+			*pos |= IEEE80211_RADIOTAP_CODING_LDPC_USER0;
 		pos++;
 		/* group ID */
 		pos++;
@@ -383,21 +365,6 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		*pos++ = status->chain_signal[chain];
 		*pos++ = chain;
 	}
-
-	if (status->vendor_radiotap_len) {
-		/* ensure 2 byte alignment for the vendor field as required */
-		if ((pos - (u8 *)rthdr) & 1)
-			*pos++ = 0;
-		*pos++ = status->vendor_radiotap_oui[0];
-		*pos++ = status->vendor_radiotap_oui[1];
-		*pos++ = status->vendor_radiotap_oui[2];
-		*pos++ = status->vendor_radiotap_subns;
-		put_unaligned_le16(status->vendor_radiotap_len, pos);
-		pos += 2;
-		/* align the actual payload as requested */
-		while ((pos - (u8 *)rthdr) & (status->vendor_radiotap_align - 1))
-			*pos++ = 0;
-	}
 }
 
 /*
@@ -428,8 +395,8 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 	if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS)
 		present_fcs_len = FCS_LEN;
 
-	/* ensure hdr->frame_control and vendor radiotap data are in skb head */
-	if (!pskb_may_pull(origskb, 2 + status->vendor_radiotap_len)) {
+	/* ensure hdr->frame_control is in skb head */
+	if (!pskb_may_pull(origskb, 2)) {
 		dev_kfree_skb(origskb);
 		return NULL;
 	}
@@ -599,10 +566,10 @@ static int ieee80211_is_unicast_robust_mgmt_frame(struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 
-	if (skb->len < 24 || is_multicast_ether_addr(hdr->addr1))
+	if (is_multicast_ether_addr(hdr->addr1))
 		return 0;
 
-	return ieee80211_is_robust_mgmt_frame(hdr);
+	return ieee80211_is_robust_mgmt_frame(skb);
 }
 
 
@@ -610,10 +577,10 @@ static int ieee80211_is_multicast_robust_mgmt_frame(struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 
-	if (skb->len < 24 || !is_multicast_ether_addr(hdr->addr1))
+	if (!is_multicast_ether_addr(hdr->addr1))
 		return 0;
 
-	return ieee80211_is_robust_mgmt_frame(hdr);
+	return ieee80211_is_robust_mgmt_frame(skb);
 }
 
 
@@ -626,7 +593,7 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb)
 	if (skb->len < 24 + sizeof(*mmie) || !is_multicast_ether_addr(hdr->da))
 		return -1;
 
-	if (!ieee80211_is_robust_mgmt_frame((struct ieee80211_hdr *) hdr))
+	if (!ieee80211_is_robust_mgmt_frame(skb))
 		return -1; /* not a robust management frame */
 
 	mmie = (struct ieee80211_mmie *)
@@ -1128,6 +1095,13 @@ static void sta_ps_end(struct sta_info *sta)
 	       sta->sta.addr, sta->sta.aid);
 
 	if (test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+		/*
+		 * Clear the flag only if the other one is still set
+		 * so that the TX path won't start TX'ing new frames
+		 * directly ... In the case that the driver flag isn't
+		 * set ieee80211_sta_ps_deliver_wakeup() will clear it.
+		 */
+		clear_sta_flag(sta, WLAN_STA_PS_STA);
 		ps_dbg(sta->sdata, "STA %pM aid %d driver-ps-blocked\n",
 		       sta->sta.addr, sta->sta.aid);
 		return;
@@ -1258,9 +1232,11 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 		if (ether_addr_equal(bssid, rx->sdata->u.ibss.bssid) &&
 		    test_sta_flag(sta, WLAN_STA_AUTHORIZED)) {
 			sta->last_rx = jiffies;
-			if (ieee80211_is_data(hdr->frame_control)) {
+			if (ieee80211_is_data(hdr->frame_control) &&
+			    !is_multicast_ether_addr(hdr->addr1)) {
 				sta->last_rx_rate_idx = status->rate_idx;
 				sta->last_rx_rate_flag = status->flag;
+				sta->last_rx_rate_vht_flag = status->vht_flag;
 				sta->last_rx_rate_vht_nss = status->vht_nss;
 			}
 		}
@@ -1273,6 +1249,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 		if (ieee80211_is_data(hdr->frame_control)) {
 			sta->last_rx_rate_idx = status->rate_idx;
 			sta->last_rx_rate_flag = status->flag;
+			sta->last_rx_rate_vht_flag = status->vht_flag;
 			sta->last_rx_rate_vht_nss = status->vht_nss;
 		}
 	}
@@ -1311,18 +1288,15 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 	    !ieee80211_has_morefrags(hdr->frame_control) &&
 	    !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) &&
 	    (rx->sdata->vif.type == NL80211_IFTYPE_AP ||
-	     rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) {
+	     rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) &&
+	    /* PM bit is only checked in frames where it isn't reserved,
+	     * in AP mode it's reserved in non-bufferable management frames
+	     * (cf. IEEE 802.11-2012 8.2.4.1.7 Power Management field)
+	     */
+	    (!ieee80211_is_mgmt(hdr->frame_control) ||
+	     ieee80211_is_bufferable_mmpdu(hdr->frame_control))) {
 		if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
-			/*
-			 * Ignore doze->wake transitions that are
-			 * indicated by non-data frames, the standard
-			 * is unclear here, but for example going to
-			 * PS mode and then scanning would cause a
-			 * doze->wake transition for the probe request,
-			 * and that is clearly undesirable.
-			 */
-			if (ieee80211_is_data(hdr->frame_control) &&
-			    !ieee80211_has_pm(hdr->frame_control))
+			if (!ieee80211_has_pm(hdr->frame_control))
 				sta_ps_end(sta);
 		} else {
 			if (ieee80211_has_pm(hdr->frame_control))
@@ -1845,8 +1819,7 @@ static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx)
 		 * having configured keys.
 		 */
 		if (unlikely(ieee80211_is_action(fc) && !rx->key &&
-			     ieee80211_is_robust_mgmt_frame(
-				     (struct ieee80211_hdr *) rx->skb->data)))
+			     ieee80211_is_robust_mgmt_frame(rx->skb)))
 			return -EACCES;
 	}
 
@@ -1963,20 +1936,17 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
 		}
 	}
 
-	if (skb) {
-		int align __maybe_unused;
-
 #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-		/*
-		 * 'align' will only take the values 0 or 2 here
-		 * since all frames are required to be aligned
-		 * to 2-byte boundaries when being passed to
-		 * mac80211; the code here works just as well if
-		 * that isn't true, but mac80211 assumes it can
-		 * access fields as 2-byte aligned (e.g. for
-		 * compare_ether_addr)
+	if (skb) {
+		/* 'align' will only take the values 0 or 2 here since all
+		 * frames are required to be aligned to 2-byte boundaries
+		 * when being passed to mac80211; the code here works just
+		 * as well if that isn't true, but mac80211 assumes it can
+		 * access fields as 2-byte aligned (e.g. for ether_addr_equal)
 		 */
-		align = ((unsigned long)(skb->data + sizeof(struct ethhdr))) & 3;
+		int align;
+
+		align = (unsigned long)(skb->data + sizeof(struct ethhdr)) & 3;
 		if (align) {
 			if (WARN_ON(skb_headroom(skb) < 3)) {
 				dev_kfree_skb(skb);
@@ -1989,14 +1959,17 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
 				skb_set_tail_pointer(skb, len);
 			}
 		}
+	}
 #endif
 
-		if (skb) {
-			/* deliver to local stack */
-			skb->protocol = eth_type_trans(skb, dev);
-			memset(skb->cb, 0, sizeof(skb->cb));
+	if (skb) {
+		/* deliver to local stack */
+		skb->protocol = eth_type_trans(skb, dev);
+		memset(skb->cb, 0, sizeof(skb->cb));
+		if (rx->local->napi)
+			napi_gro_receive(rx->local->napi, skb);
+		else
 			netif_receive_skb(skb);
-		}
 	}
 
 	if (xmit_skb) {
@@ -3079,8 +3052,8 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid)
 
 /* main receive path */
 
-static int prepare_for_handlers(struct ieee80211_rx_data *rx,
-				struct ieee80211_hdr *hdr)
+static bool prepare_for_handlers(struct ieee80211_rx_data *rx,
+				 struct ieee80211_hdr *hdr)
 {
 	struct ieee80211_sub_if_data *sdata = rx->sdata;
 	struct sk_buff *skb = rx->skb;
@@ -3091,29 +3064,29 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx,
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_STATION:
 		if (!bssid && !sdata->u.mgd.use_4addr)
-			return 0;
+			return false;
 		if (!multicast &&
 		    !ether_addr_equal(sdata->vif.addr, hdr->addr1)) {
 			if (!(sdata->dev->flags & IFF_PROMISC) ||
 			    sdata->u.mgd.use_4addr)
-				return 0;
+				return false;
 			status->rx_flags &= ~IEEE80211_RX_RA_MATCH;
 		}
 		break;
 	case NL80211_IFTYPE_ADHOC:
 		if (!bssid)
-			return 0;
+			return false;
 		if (ether_addr_equal(sdata->vif.addr, hdr->addr2) ||
 		    ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2))
-			return 0;
+			return false;
 		if (ieee80211_is_beacon(hdr->frame_control)) {
-			return 1;
+			return true;
 		} else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) {
-			return 0;
+			return false;
 		} else if (!multicast &&
 			   !ether_addr_equal(sdata->vif.addr, hdr->addr1)) {
 			if (!(sdata->dev->flags & IFF_PROMISC))
-				return 0;
+				return false;
 			status->rx_flags &= ~IEEE80211_RX_RA_MATCH;
 		} else if (!rx->sta) {
 			int rate_idx;
@@ -3129,7 +3102,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx,
 		if (!multicast &&
 		    !ether_addr_equal(sdata->vif.addr, hdr->addr1)) {
 			if (!(sdata->dev->flags & IFF_PROMISC))
-				return 0;
+				return false;
 
 			status->rx_flags &= ~IEEE80211_RX_RA_MATCH;
 		}
@@ -3138,7 +3111,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx,
 	case NL80211_IFTYPE_AP:
 		if (!bssid) {
 			if (!ether_addr_equal(sdata->vif.addr, hdr->addr1))
-				return 0;
+				return false;
 		} else if (!ieee80211_bssid_match(bssid, sdata->vif.addr)) {
 			/*
 			 * Accept public action frames even when the
@@ -3148,26 +3121,26 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx,
 			 */
 			if (!multicast &&
 			    !ether_addr_equal(sdata->vif.addr, hdr->addr1))
-				return 0;
+				return false;
 			if (ieee80211_is_public_action(hdr, skb->len))
-				return 1;
+				return true;
 			if (!ieee80211_is_beacon(hdr->frame_control))
-				return 0;
+				return false;
 			status->rx_flags &= ~IEEE80211_RX_RA_MATCH;
 		}
 		break;
 	case NL80211_IFTYPE_WDS:
 		if (bssid || !ieee80211_is_data(hdr->frame_control))
-			return 0;
+			return false;
 		if (!ether_addr_equal(sdata->u.wds.remote_addr, hdr->addr2))
-			return 0;
+			return false;
 		break;
 	case NL80211_IFTYPE_P2P_DEVICE:
 		if (!ieee80211_is_public_action(hdr, skb->len) &&
 		    !ieee80211_is_probe_req(hdr->frame_control) &&
 		    !ieee80211_is_probe_resp(hdr->frame_control) &&
 		    !ieee80211_is_beacon(hdr->frame_control))
-			return 0;
+			return false;
 		if (!ether_addr_equal(sdata->vif.addr, hdr->addr1) &&
 		    !multicast)
 			status->rx_flags &= ~IEEE80211_RX_RA_MATCH;
@@ -3178,7 +3151,7 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx,
 		break;
 	}
 
-	return 1;
+	return true;
 }
 
 /*
@@ -3194,13 +3167,11 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx,
 	struct ieee80211_sub_if_data *sdata = rx->sdata;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 	struct ieee80211_hdr *hdr = (void *)skb->data;
-	int prepares;
 
 	rx->skb = skb;
 	status->rx_flags |= IEEE80211_RX_RA_MATCH;
-	prepares = prepare_for_handlers(rx, hdr);
 
-	if (!prepares)
+	if (!prepare_for_handlers(rx, hdr))
 		return false;
 
 	if (!consume) {
@@ -3221,7 +3192,7 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx,
 }
 
 /*
- * This is the actual Rx frames handler. as it blongs to Rx path it must
+ * This is the actual Rx frames handler. as it belongs to Rx path it must
  * be called with rcu_read_lock protection.
  */
 static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 4d73c46df86..f40661eb75b 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -271,10 +271,11 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local)
 	return true;
 }
 
-static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted,
-				       bool was_hw_scan)
+static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
+	bool hw_scan = local->ops->hw_scan;
+	bool was_scanning = local->scanning;
 
 	lockdep_assert_held(&local->mtx);
 
@@ -290,7 +291,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted,
 	if (WARN_ON(!local->scan_req))
 		return;
 
-	if (was_hw_scan && !aborted && ieee80211_prep_hw_scan(local)) {
+	if (hw_scan && !aborted && ieee80211_prep_hw_scan(local)) {
 		int rc;
 
 		rc = drv_hw_scan(local,
@@ -308,7 +309,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted,
 	if (local->scan_req != local->int_scan_req)
 		cfg80211_scan_done(local->scan_req, aborted);
 	local->scan_req = NULL;
-	rcu_assign_pointer(local->scan_sdata, NULL);
+	RCU_INIT_POINTER(local->scan_sdata, NULL);
 
 	local->scanning = 0;
 	local->scan_chandef.chan = NULL;
@@ -316,7 +317,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted,
 	/* Set power back to normal operating levels. */
 	ieee80211_hw_config(local, 0);
 
-	if (!was_hw_scan) {
+	if (!hw_scan) {
 		ieee80211_configure_filter(local);
 		drv_sw_scan_complete(local);
 		ieee80211_offchannel_return(local);
@@ -327,7 +328,8 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted,
 	ieee80211_mlme_notify_scan_completed(local);
 	ieee80211_ibss_notify_scan_completed(local);
 	ieee80211_mesh_notify_scan_completed(local);
-	ieee80211_start_next_roc(local);
+	if (was_scanning)
+		ieee80211_start_next_roc(local);
 }
 
 void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
@@ -470,9 +472,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 	if (local->ops->hw_scan) {
 		u8 *ies;
 
-		local->hw_scan_ies_bufsize = 2 + IEEE80211_MAX_SSID_LEN +
-					     local->scan_ies_len +
-					     req->ie_len;
+		local->hw_scan_ies_bufsize = local->scan_ies_len + req->ie_len;
 		local->hw_scan_req = kmalloc(
 				sizeof(*local->hw_scan_req) +
 				req->n_channels * sizeof(req->channels[0]) +
@@ -559,7 +559,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 		ieee80211_recalc_idle(local);
 
 		local->scan_req = NULL;
-		rcu_assign_pointer(local->scan_sdata, NULL);
+		RCU_INIT_POINTER(local->scan_sdata, NULL);
 	}
 
 	return rc;
@@ -747,7 +747,7 @@ void ieee80211_scan_work(struct work_struct *work)
 		container_of(work, struct ieee80211_local, scan_work.work);
 	struct ieee80211_sub_if_data *sdata;
 	unsigned long next_delay = 0;
-	bool aborted, hw_scan;
+	bool aborted;
 
 	mutex_lock(&local->mtx);
 
@@ -773,7 +773,7 @@ void ieee80211_scan_work(struct work_struct *work)
 		int rc;
 
 		local->scan_req = NULL;
-		rcu_assign_pointer(local->scan_sdata, NULL);
+		RCU_INIT_POINTER(local->scan_sdata, NULL);
 
 		rc = __ieee80211_start_scan(sdata, req);
 		if (rc) {
@@ -786,14 +786,6 @@ void ieee80211_scan_work(struct work_struct *work)
 	}
 
 	/*
-	 * Avoid re-scheduling when the sdata is going away.
-	 */
-	if (!ieee80211_sdata_running(sdata)) {
-		aborted = true;
-		goto out_complete;
-	}
-
-	/*
 	 * as long as no delay is required advance immediately
 	 * without scheduling a new work
 	 */
@@ -834,8 +826,7 @@ void ieee80211_scan_work(struct work_struct *work)
 	goto out;
 
 out_complete:
-	hw_scan = test_bit(SCAN_HW_SCANNING, &local->scanning);
-	__ieee80211_scan_completed(&local->hw, aborted, hw_scan);
+	__ieee80211_scan_completed(&local->hw, aborted);
 out:
 	mutex_unlock(&local->mtx);
 }
@@ -973,33 +964,25 @@ void ieee80211_scan_cancel(struct ieee80211_local *local)
 	 */
 	cancel_delayed_work(&local->scan_work);
 	/* and clean up */
-	__ieee80211_scan_completed(&local->hw, true, false);
+	__ieee80211_scan_completed(&local->hw, true);
 out:
 	mutex_unlock(&local->mtx);
 }
 
-int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
-				       struct cfg80211_sched_scan_request *req)
+int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
+					struct cfg80211_sched_scan_request *req)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_sched_scan_ies sched_scan_ies = {};
 	struct cfg80211_chan_def chandef;
 	int ret, i, iebufsz;
 
-	iebufsz = 2 + IEEE80211_MAX_SSID_LEN +
-		  local->scan_ies_len + req->ie_len;
+	iebufsz = local->scan_ies_len + req->ie_len;
 
-	mutex_lock(&local->mtx);
+	lockdep_assert_held(&local->mtx);
 
-	if (rcu_access_pointer(local->sched_scan_sdata)) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	if (!local->ops->sched_scan_start) {
-		ret = -ENOTSUPP;
-		goto out;
-	}
+	if (!local->ops->sched_scan_start)
+		return -ENOTSUPP;
 
 	for (i = 0; i < IEEE80211_NUM_BANDS; i++) {
 		if (!local->hw.wiphy->bands[i])
@@ -1020,13 +1003,39 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
 	}
 
 	ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies);
-	if (ret == 0)
+	if (ret == 0) {
 		rcu_assign_pointer(local->sched_scan_sdata, sdata);
+		local->sched_scan_req = req;
+	}
 
 out_free:
 	while (i > 0)
 		kfree(sched_scan_ies.ie[--i]);
-out:
+
+	if (ret) {
+		/* Clean in case of failure after HW restart or upon resume. */
+		RCU_INIT_POINTER(local->sched_scan_sdata, NULL);
+		local->sched_scan_req = NULL;
+	}
+
+	return ret;
+}
+
+int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
+				       struct cfg80211_sched_scan_request *req)
+{
+	struct ieee80211_local *local = sdata->local;
+	int ret;
+
+	mutex_lock(&local->mtx);
+
+	if (rcu_access_pointer(local->sched_scan_sdata)) {
+		mutex_unlock(&local->mtx);
+		return -EBUSY;
+	}
+
+	ret = __ieee80211_request_sched_scan_start(sdata, req);
+
 	mutex_unlock(&local->mtx);
 	return ret;
 }
@@ -1043,9 +1052,14 @@ int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata)
 		goto out;
 	}
 
-	if (rcu_access_pointer(local->sched_scan_sdata))
-		drv_sched_scan_stop(local, sdata);
+	/* We don't want to restart sched scan anymore. */
+	local->sched_scan_req = NULL;
 
+	if (rcu_access_pointer(local->sched_scan_sdata)) {
+		ret = drv_sched_scan_stop(local, sdata);
+		if (!ret)
+			rcu_assign_pointer(local->sched_scan_sdata, NULL);
+	}
 out:
 	mutex_unlock(&local->mtx);
 
@@ -1062,12 +1076,8 @@ void ieee80211_sched_scan_results(struct ieee80211_hw *hw)
 }
 EXPORT_SYMBOL(ieee80211_sched_scan_results);
 
-void ieee80211_sched_scan_stopped_work(struct work_struct *work)
+void ieee80211_sched_scan_end(struct ieee80211_local *local)
 {
-	struct ieee80211_local *local =
-		container_of(work, struct ieee80211_local,
-			     sched_scan_stopped_work);
-
 	mutex_lock(&local->mtx);
 
 	if (!rcu_access_pointer(local->sched_scan_sdata)) {
@@ -1075,13 +1085,25 @@ void ieee80211_sched_scan_stopped_work(struct work_struct *work)
 		return;
 	}
 
-	rcu_assign_pointer(local->sched_scan_sdata, NULL);
+	RCU_INIT_POINTER(local->sched_scan_sdata, NULL);
+
+	/* If sched scan was aborted by the driver. */
+	local->sched_scan_req = NULL;
 
 	mutex_unlock(&local->mtx);
 
 	cfg80211_sched_scan_stopped(local->hw.wiphy);
 }
 
+void ieee80211_sched_scan_stopped_work(struct work_struct *work)
+{
+	struct ieee80211_local *local =
+		container_of(work, struct ieee80211_local,
+			     sched_scan_stopped_work);
+
+	ieee80211_sched_scan_end(local);
+}
+
 void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 8ed97f76c3c..a9b46d8ea22 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -91,7 +91,7 @@ static int sta_info_hash_del(struct ieee80211_local *local,
 	return -ENOENT;
 }
 
-static void cleanup_single_sta(struct sta_info *sta)
+static void __cleanup_single_sta(struct sta_info *sta)
 {
 	int ac, i;
 	struct tid_ampdu_tx *tid_tx;
@@ -99,24 +99,8 @@ static void cleanup_single_sta(struct sta_info *sta)
 	struct ieee80211_local *local = sdata->local;
 	struct ps_data *ps;
 
-	/*
-	 * At this point, when being called as call_rcu callback,
-	 * neither mac80211 nor the driver can reference this
-	 * sta struct any more except by still existing timers
-	 * associated with this station that we clean up below.
-	 *
-	 * Note though that this still uses the sdata and even
-	 * calls the driver in AP and mesh mode, so interfaces
-	 * of those types mush use call sta_info_flush_cleanup()
-	 * (typically via sta_info_flush()) before deconfiguring
-	 * the driver.
-	 *
-	 * In station mode, nothing happens here so it doesn't
-	 * have to (and doesn't) do that, this is intentional to
-	 * speed up roaming.
-	 */
-
-	if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
+	if (test_sta_flag(sta, WLAN_STA_PS_STA) ||
+	    test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
 		if (sta->sdata->vif.type == NL80211_IFTYPE_AP ||
 		    sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 			ps = &sdata->bss->ps;
@@ -126,6 +110,7 @@ static void cleanup_single_sta(struct sta_info *sta)
 			return;
 
 		clear_sta_flag(sta, WLAN_STA_PS_STA);
+		clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
 
 		atomic_dec(&ps->num_sta_ps);
 		sta_info_recalc_tim(sta);
@@ -156,39 +141,15 @@ static void cleanup_single_sta(struct sta_info *sta)
 		ieee80211_purge_tx_queue(&local->hw, &tid_tx->pending);
 		kfree(tid_tx);
 	}
-
-	sta_info_free(local, sta);
 }
 
-void ieee80211_cleanup_sdata_stas(struct ieee80211_sub_if_data *sdata)
-{
-	struct sta_info *sta;
-
-	spin_lock_bh(&sdata->cleanup_stations_lock);
-	while (!list_empty(&sdata->cleanup_stations)) {
-		sta = list_first_entry(&sdata->cleanup_stations,
-				       struct sta_info, list);
-		list_del(&sta->list);
-		spin_unlock_bh(&sdata->cleanup_stations_lock);
-
-		cleanup_single_sta(sta);
-
-		spin_lock_bh(&sdata->cleanup_stations_lock);
-	}
-
-	spin_unlock_bh(&sdata->cleanup_stations_lock);
-}
-
-static void free_sta_rcu(struct rcu_head *h)
+static void cleanup_single_sta(struct sta_info *sta)
 {
-	struct sta_info *sta = container_of(h, struct sta_info, rcu_head);
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct ieee80211_local *local = sdata->local;
 
-	spin_lock(&sdata->cleanup_stations_lock);
-	list_add_tail(&sta->list, &sdata->cleanup_stations);
-	spin_unlock(&sdata->cleanup_stations_lock);
-
-	ieee80211_queue_work(&sdata->local->hw, &sdata->cleanup_stations_wk);
+	__cleanup_single_sta(sta);
+	sta_info_free(local, sta);
 }
 
 /* protected by RCU */
@@ -279,6 +240,7 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 
 	sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
 
+	kfree(rcu_dereference_raw(sta->sta.rates));
 	kfree(sta);
 }
 
@@ -348,7 +310,37 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	if (!sta)
 		return NULL;
 
+	rcu_read_lock();
+	tx_latency = rcu_dereference(local->tx_latency);
+	/* init stations Tx latency statistics && TID bins */
+	if (tx_latency) {
+		sta->tx_lat = kzalloc(IEEE80211_NUM_TIDS *
+				      sizeof(struct ieee80211_tx_latency_stat),
+				      GFP_ATOMIC);
+		if (!sta->tx_lat) {
+			rcu_read_unlock();
+			goto free;
+		}
+
+		if (tx_latency->n_ranges) {
+			for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
+				/* size of bins is size of the ranges +1 */
+				sta->tx_lat[i].bin_count =
+					tx_latency->n_ranges + 1;
+				sta->tx_lat[i].bins =
+					kcalloc(sta->tx_lat[i].bin_count,
+						sizeof(u32), GFP_ATOMIC);
+				if (!sta->tx_lat[i].bins) {
+					rcu_read_unlock();
+					goto free;
+				}
+			}
+		}
+	}
+	rcu_read_unlock();
+
 	spin_lock_init(&sta->lock);
+	spin_lock_init(&sta->ps_lock);
 	INIT_WORK(&sta->drv_unblock_wk, sta_unblock);
 	INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work);
 	mutex_init(&sta->ampdu_mlme.mtx);
@@ -372,10 +364,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	for (i = 0; i < ARRAY_SIZE(sta->chain_signal_avg); i++)
 		ewma_init(&sta->chain_signal_avg[i], 1024, 8);
 
-	if (sta_prepare_rate_control(local, sta, gfp)) {
-		kfree(sta);
-		return NULL;
-	}
+	if (sta_prepare_rate_control(local, sta, gfp))
+		goto free;
 
 	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
 		/*
@@ -419,34 +409,17 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
-	rcu_read_lock();
-
-	tx_latency = rcu_dereference(local->tx_latency);
-	/* init stations Tx latency statistics && TID bins */
-	if (tx_latency)
-		sta->tx_lat = kzalloc(IEEE80211_NUM_TIDS *
-				      sizeof(struct ieee80211_tx_latency_stat),
-				      GFP_ATOMIC);
-
-	/*
-	 * if Tx latency and bins are enabled and the previous allocation
-	 * succeeded
-	 */
-	if (tx_latency && tx_latency->n_ranges && sta->tx_lat)
-		for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
-			/* size of bins is size of the ranges +1 */
-			sta->tx_lat[i].bin_count =
-				tx_latency->n_ranges + 1;
-			sta->tx_lat[i].bins  = kcalloc(sta->tx_lat[i].bin_count,
-						       sizeof(u32),
-						       GFP_ATOMIC);
-		}
-
-	rcu_read_unlock();
-
 	sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr);
-
 	return sta;
+
+free:
+	if (sta->tx_lat) {
+		for (i = 0; i < IEEE80211_NUM_TIDS; i++)
+			kfree(sta->tx_lat[i].bins);
+		kfree(sta->tx_lat);
+	}
+	kfree(sta);
+	return NULL;
 }
 
 static int sta_info_insert_check(struct sta_info *sta)
@@ -525,21 +498,26 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 		goto out_err;
 	}
 
-	/* notify driver */
-	err = sta_info_insert_drv_state(local, sdata, sta);
-	if (err)
-		goto out_err;
-
 	local->num_sta++;
 	local->sta_generation++;
 	smp_mb();
 
+	/* simplify things and don't accept BA sessions yet */
+	set_sta_flag(sta, WLAN_STA_BLOCK_BA);
+
 	/* make the station visible */
 	sta_info_hash_add(local, sta);
 
 	list_add_rcu(&sta->list, &local->sta_list);
 
+	/* notify driver */
+	err = sta_info_insert_drv_state(local, sdata, sta);
+	if (err)
+		goto out_remove;
+
 	set_sta_flag(sta, WLAN_STA_INSERTED);
+	/* accept BA sessions now */
+	clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
 
 	ieee80211_recalc_min_chandef(sdata);
 	ieee80211_sta_debugfs_add(sta);
@@ -560,6 +538,12 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 		mesh_accept_plinks_update(sdata);
 
 	return 0;
+ out_remove:
+	sta_info_hash_del(local, sta);
+	list_del_rcu(&sta->list);
+	local->num_sta--;
+	synchronize_net();
+	__cleanup_single_sta(sta);
  out_err:
 	mutex_unlock(&local->sta_mtx);
 	rcu_read_lock();
@@ -569,7 +553,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU)
 {
 	struct ieee80211_local *local = sta->local;
-	int err = 0;
+	int err;
 
 	might_sleep();
 
@@ -587,7 +571,6 @@ int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU)
 
 	return 0;
  out_free:
-	BUG_ON(!err);
 	sta_info_free(local, sta);
 	return err;
 }
@@ -842,7 +825,7 @@ static bool sta_info_cleanup_expire_buffered(struct ieee80211_local *local,
 	return have_buffered;
 }
 
-int __must_check __sta_info_destroy(struct sta_info *sta)
+static int __must_check __sta_info_destroy_part1(struct sta_info *sta)
 {
 	struct ieee80211_local *local;
 	struct ieee80211_sub_if_data *sdata;
@@ -868,12 +851,35 @@ int __must_check __sta_info_destroy(struct sta_info *sta)
 	ieee80211_sta_tear_down_BA_sessions(sta, AGG_STOP_DESTROY_STA);
 
 	ret = sta_info_hash_del(local, sta);
-	if (ret)
+	if (WARN_ON(ret))
 		return ret;
 
 	list_del_rcu(&sta->list);
 
-	/* this always calls synchronize_net() */
+	drv_sta_pre_rcu_remove(local, sta->sdata, sta);
+
+	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
+	    rcu_access_pointer(sdata->u.vlan.sta) == sta)
+		RCU_INIT_POINTER(sdata->u.vlan.sta, NULL);
+
+	return 0;
+}
+
+static void __sta_info_destroy_part2(struct sta_info *sta)
+{
+	struct ieee80211_local *local = sta->local;
+	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	int ret;
+
+	/*
+	 * NOTE: This assumes at least synchronize_net() was done
+	 *	 after _part1 and before _part2!
+	 */
+
+	might_sleep();
+	lockdep_assert_held(&local->sta_mtx);
+
+	/* now keys can no longer be reached */
 	ieee80211_free_sta_keys(local, sta);
 
 	sta->dead = true;
@@ -881,9 +887,6 @@ int __must_check __sta_info_destroy(struct sta_info *sta)
 	local->num_sta--;
 	local->sta_generation++;
 
-	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
-		RCU_INIT_POINTER(sdata->u.vlan.sta, NULL);
-
 	while (sta->sta_state > IEEE80211_STA_NONE) {
 		ret = sta_info_move_state(sta, sta->sta_state - 1);
 		if (ret) {
@@ -906,7 +909,19 @@ int __must_check __sta_info_destroy(struct sta_info *sta)
 	ieee80211_sta_debugfs_remove(sta);
 	ieee80211_recalc_min_chandef(sdata);
 
-	call_rcu(&sta->rcu_head, free_sta_rcu);
+	cleanup_single_sta(sta);
+}
+
+int __must_check __sta_info_destroy(struct sta_info *sta)
+{
+	int err = __sta_info_destroy_part1(sta);
+
+	if (err)
+		return err;
+
+	synchronize_net();
+
+	__sta_info_destroy_part2(sta);
 
 	return 0;
 }
@@ -976,32 +991,38 @@ void sta_info_stop(struct ieee80211_local *local)
 }
 
 
-int sta_info_flush_defer(struct ieee80211_sub_if_data *sdata)
+int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct sta_info *sta, *tmp;
+	LIST_HEAD(free_list);
 	int ret = 0;
 
 	might_sleep();
 
+	WARN_ON(vlans && sdata->vif.type != NL80211_IFTYPE_AP);
+	WARN_ON(vlans && !sdata->bss);
+
 	mutex_lock(&local->sta_mtx);
 	list_for_each_entry_safe(sta, tmp, &local->sta_list, list) {
-		if (sdata == sta->sdata) {
-			WARN_ON(__sta_info_destroy(sta));
+		if (sdata == sta->sdata ||
+		    (vlans && sdata->bss == sta->sdata->bss)) {
+			if (!WARN_ON(__sta_info_destroy_part1(sta)))
+				list_add(&sta->free_list, &free_list);
 			ret++;
 		}
 	}
+
+	if (!list_empty(&free_list)) {
+		synchronize_net();
+		list_for_each_entry_safe(sta, tmp, &free_list, free_list)
+			__sta_info_destroy_part2(sta);
+	}
 	mutex_unlock(&local->sta_mtx);
 
 	return ret;
 }
 
-void sta_info_flush_cleanup(struct ieee80211_sub_if_data *sdata)
-{
-	ieee80211_cleanup_sdata_stas(sdata);
-	cancel_work_sync(&sdata->cleanup_stations_wk);
-}
-
 void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata,
 			  unsigned long exp_time)
 {
@@ -1071,10 +1092,14 @@ struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_vif *vif,
 }
 EXPORT_SYMBOL(ieee80211_find_sta);
 
-static void clear_sta_ps_flags(void *_sta)
+/* powersave support code */
+void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 {
-	struct sta_info *sta = _sta;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
+	struct ieee80211_local *local = sdata->local;
+	struct sk_buff_head pending;
+	int filtered = 0, buffered = 0, ac;
+	unsigned long flags;
 	struct ps_data *ps;
 
 	if (sdata->vif.type == NL80211_IFTYPE_AP ||
@@ -1085,20 +1110,6 @@ static void clear_sta_ps_flags(void *_sta)
 	else
 		return;
 
-	clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
-	if (test_and_clear_sta_flag(sta, WLAN_STA_PS_STA))
-		atomic_dec(&ps->num_sta_ps);
-}
-
-/* powersave support code */
-void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
-{
-	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	struct ieee80211_local *local = sdata->local;
-	struct sk_buff_head pending;
-	int filtered = 0, buffered = 0, ac;
-	unsigned long flags;
-
 	clear_sta_flag(sta, WLAN_STA_SP);
 
 	BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1);
@@ -1109,6 +1120,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 
 	skb_queue_head_init(&pending);
 
+	/* sync with ieee80211_tx_h_unicast_ps_buf */
+	spin_lock(&sta->ps_lock);
 	/* Send all buffered frames to the station */
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		int count = skb_queue_len(&pending), tmp;
@@ -1127,10 +1140,16 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 		buffered += tmp - count;
 	}
 
-	ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta);
+	ieee80211_add_pending_skbs(local, &pending);
+	clear_sta_flag(sta, WLAN_STA_PS_DRIVER);
+	clear_sta_flag(sta, WLAN_STA_PS_STA);
+	spin_unlock(&sta->ps_lock);
+
+	atomic_dec(&ps->num_sta_ps);
 
 	/* This station just woke up and isn't aware of our SMPS state */
-	if (!ieee80211_smps_is_restrictive(sta->known_smps_mode,
+	if (!ieee80211_vif_is_mesh(&sdata->vif) &&
+	    !ieee80211_smps_is_restrictive(sta->known_smps_mode,
 					   sdata->smps_mode) &&
 	    sta->known_smps_mode != sdata->bss->req_smps &&
 	    sta_info_tx_streams(sta) != 1) {
@@ -1153,7 +1172,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 
 static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 					 struct sta_info *sta, int tid,
-					 enum ieee80211_frame_release_type reason)
+					 enum ieee80211_frame_release_type reason,
+					 bool call_driver)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_qos_hdr *nullfunc;
@@ -1187,6 +1207,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 	memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
 	memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN);
 	memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN);
+	nullfunc->seq_ctrl = 0;
 
 	skb->priority = tid;
 	skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]);
@@ -1211,7 +1232,9 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 		       IEEE80211_TX_STATUS_EOSP |
 		       IEEE80211_TX_CTL_REQ_TX_STATUS;
 
-	drv_allow_buffered_frames(local, sta, BIT(tid), 1, reason, false);
+	if (call_driver)
+		drv_allow_buffered_frames(local, sta, BIT(tid), 1,
+					  reason, false);
 
 	skb->dev = sdata->dev;
 
@@ -1227,6 +1250,17 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 	rcu_read_unlock();
 }
 
+static int find_highest_prio_tid(unsigned long tids)
+{
+	/* lower 3 TIDs aren't ordered perfectly */
+	if (tids & 0xF8)
+		return fls(tids) - 1;
+	/* TID 0 is BE just like TID 3 */
+	if (tids & BIT(0))
+		return 0;
+	return fls(tids) - 1;
+}
+
 static void
 ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 				  int n_frames, u8 ignored_acs,
@@ -1234,7 +1268,6 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 {
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct ieee80211_local *local = sdata->local;
-	bool found = false;
 	bool more_data = false;
 	int ac;
 	unsigned long driver_release_tids = 0;
@@ -1245,9 +1278,7 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 
 	__skb_queue_head_init(&frames);
 
-	/*
-	 * Get response frame(s) and more data bit for it.
-	 */
+	/* Get response frame(s) and more data bit for the last one. */
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		unsigned long tids;
 
@@ -1256,43 +1287,48 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 
 		tids = ieee80211_tids_for_ac(ac);
 
-		if (!found) {
-			driver_release_tids = sta->driver_buffered_tids & tids;
-			if (driver_release_tids) {
-				found = true;
-			} else {
-				struct sk_buff *skb;
-
-				while (n_frames > 0) {
-					skb = skb_dequeue(&sta->tx_filtered[ac]);
-					if (!skb) {
-						skb = skb_dequeue(
-							&sta->ps_tx_buf[ac]);
-						if (skb)
-							local->total_ps_buffered--;
-					}
-					if (!skb)
-						break;
-					n_frames--;
-					found = true;
-					__skb_queue_tail(&frames, skb);
-				}
-			}
+		/* if we already have frames from software, then we can't also
+		 * release from hardware queues
+		 */
+		if (skb_queue_empty(&frames))
+			driver_release_tids |= sta->driver_buffered_tids & tids;
 
-			/*
-			 * If the driver has data on more than one TID then
+		if (driver_release_tids) {
+			/* If the driver has data on more than one TID then
 			 * certainly there's more data if we release just a
-			 * single frame now (from a single TID).
+			 * single frame now (from a single TID). This will
+			 * only happen for PS-Poll.
 			 */
 			if (reason == IEEE80211_FRAME_RELEASE_PSPOLL &&
 			    hweight16(driver_release_tids) > 1) {
 				more_data = true;
 				driver_release_tids =
-					BIT(ffs(driver_release_tids) - 1);
+					BIT(find_highest_prio_tid(
+						driver_release_tids));
 				break;
 			}
+		} else {
+			struct sk_buff *skb;
+
+			while (n_frames > 0) {
+				skb = skb_dequeue(&sta->tx_filtered[ac]);
+				if (!skb) {
+					skb = skb_dequeue(
+						&sta->ps_tx_buf[ac]);
+					if (skb)
+						local->total_ps_buffered--;
+				}
+				if (!skb)
+					break;
+				n_frames--;
+				__skb_queue_tail(&frames, skb);
+			}
 		}
 
+		/* If we have more frames buffered on this AC, then set the
+		 * more-data bit and abort the loop since we can't send more
+		 * data from other ACs before the buffered frames from this.
+		 */
 		if (!skb_queue_empty(&sta->tx_filtered[ac]) ||
 		    !skb_queue_empty(&sta->ps_tx_buf[ac])) {
 			more_data = true;
@@ -1300,7 +1336,7 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 		}
 	}
 
-	if (!found) {
+	if (skb_queue_empty(&frames) && !driver_release_tids) {
 		int tid;
 
 		/*
@@ -1321,15 +1357,13 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 		/* This will evaluate to 1, 3, 5 or 7. */
 		tid = 7 - ((ffs(~ignored_acs) - 1) << 1);
 
-		ieee80211_send_null_response(sdata, sta, tid, reason);
-		return;
-	}
-
-	if (!driver_release_tids) {
+		ieee80211_send_null_response(sdata, sta, tid, reason, true);
+	} else if (!driver_release_tids) {
 		struct sk_buff_head pending;
 		struct sk_buff *skb;
 		int num = 0;
 		u16 tids = 0;
+		bool need_null = false;
 
 		skb_queue_head_init(&pending);
 
@@ -1363,22 +1397,57 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 			    ieee80211_is_qos_nullfunc(hdr->frame_control))
 				qoshdr = ieee80211_get_qos_ctl(hdr);
 
-			/* end service period after last frame */
-			if (skb_queue_empty(&frames)) {
-				if (reason == IEEE80211_FRAME_RELEASE_UAPSD &&
-				    qoshdr)
-					*qoshdr |= IEEE80211_QOS_CTL_EOSP;
+			tids |= BIT(skb->priority);
+
+			__skb_queue_tail(&pending, skb);
+
+			/* end service period after last frame or add one */
+			if (!skb_queue_empty(&frames))
+				continue;
 
+			if (reason != IEEE80211_FRAME_RELEASE_UAPSD) {
+				/* for PS-Poll, there's only one frame */
 				info->flags |= IEEE80211_TX_STATUS_EOSP |
 					       IEEE80211_TX_CTL_REQ_TX_STATUS;
+				break;
 			}
 
-			if (qoshdr)
-				tids |= BIT(*qoshdr & IEEE80211_QOS_CTL_TID_MASK);
-			else
-				tids |= BIT(0);
+			/* For uAPSD, things are a bit more complicated. If the
+			 * last frame has a QoS header (i.e. is a QoS-data or
+			 * QoS-nulldata frame) then just set the EOSP bit there
+			 * and be done.
+			 * If the frame doesn't have a QoS header (which means
+			 * it should be a bufferable MMPDU) then we can't set
+			 * the EOSP bit in the QoS header; add a QoS-nulldata
+			 * frame to the list to send it after the MMPDU.
+			 *
+			 * Note that this code is only in the mac80211-release
+			 * code path, we assume that the driver will not buffer
+			 * anything but QoS-data frames, or if it does, will
+			 * create the QoS-nulldata frame by itself if needed.
+			 *
+			 * Cf. 802.11-2012 10.2.1.10 (c).
+			 */
+			if (qoshdr) {
+				*qoshdr |= IEEE80211_QOS_CTL_EOSP;
 
-			__skb_queue_tail(&pending, skb);
+				info->flags |= IEEE80211_TX_STATUS_EOSP |
+					       IEEE80211_TX_CTL_REQ_TX_STATUS;
+			} else {
+				/* The standard isn't completely clear on this
+				 * as it says the more-data bit should be set
+				 * if there are more BUs. The QoS-Null frame
+				 * we're about to send isn't buffered yet, we
+				 * only create it below, but let's pretend it
+				 * was buffered just in case some clients only
+				 * expect more-data=0 when eosp=1.
+				 */
+				hdr->frame_control |=
+					cpu_to_le16(IEEE80211_FCTL_MOREDATA);
+				need_null = true;
+				num++;
+			}
+			break;
 		}
 
 		drv_allow_buffered_frames(local, sta, tids, num,
@@ -1386,17 +1455,22 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 
 		ieee80211_add_pending_skbs(local, &pending);
 
+		if (need_null)
+			ieee80211_send_null_response(
+				sdata, sta, find_highest_prio_tid(tids),
+				reason, false);
+
 		sta_info_recalc_tim(sta);
 	} else {
 		/*
 		 * We need to release a frame that is buffered somewhere in the
 		 * driver ... it'll have to handle that.
-		 * Note that, as per the comment above, it'll also have to see
-		 * if there is more than just one frame on the specific TID that
-		 * we're releasing from, and it needs to set the more-data bit
-		 * accordingly if we tell it that there's no more data. If we do
-		 * tell it there's more data, then of course the more-data bit
-		 * needs to be set anyway.
+		 * Note that the driver also has to check the number of frames
+		 * on the TIDs we're releasing from - if there are more than
+		 * n_frames it has to set the more-data bit (if we didn't ask
+		 * it to set it anyway due to other buffered frames); if there
+		 * are fewer than n_frames it has to make sure to adjust that
+		 * to allow the service period to end properly.
 		 */
 		drv_release_buffered_frames(local, sta, driver_release_tids,
 					    n_frames, reason, more_data);
@@ -1404,9 +1478,9 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 		/*
 		 * Note that we don't recalculate the TIM bit here as it would
 		 * most likely have no effect at all unless the driver told us
-		 * that the TID became empty before returning here from the
+		 * that the TID(s) became empty before returning here from the
 		 * release function.
-		 * Either way, however, when the driver tells us that the TID
+		 * Either way, however, when the driver tells us that the TID(s)
 		 * became empty we'll do the TIM recalculation.
 		 */
 	}
@@ -1495,6 +1569,8 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta,
 	if (WARN_ON(tid >= IEEE80211_NUM_TIDS))
 		return;
 
+	trace_api_sta_set_buffered(sta->local, pubsta, tid, buffered);
+
 	if (buffered)
 		set_bit(tid, &sta->driver_buffered_tids);
 	else
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 0218caf5c14..4acc5fc402f 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -247,6 +247,7 @@ struct ieee80211_tx_latency_stat {
  * mac80211 is communicating with.
  *
  * @list: global linked list entry
+ * @free_list: list entry for keeping track of stations to free
  * @hnext: hash table linked list pointer
  * @local: pointer to the global information
  * @sdata: virtual interface this station belongs to
@@ -260,12 +261,14 @@ struct ieee80211_tx_latency_stat {
  *	"the" transmit rate
  * @last_rx_rate_idx: rx status rate index of the last data packet
  * @last_rx_rate_flag: rx status flag of the last data packet
+ * @last_rx_rate_vht_flag: rx status vht flag of the last data packet
  * @last_rx_rate_vht_nss: rx status nss of last data packet
  * @lock: used for locking all fields that require locking, see comments
  *	in the header file.
  * @drv_unblock_wk: used for driver PS unblocking
  * @listen_interval: listen interval of this station, when we're acting as AP
  * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly
+ * @ps_lock: used for powersave (when mac80211 is the AP) related locking
  * @ps_tx_buf: buffers (per AC) of frames to transmit to this station
  *	when it leaves power saving state or polls
  * @tx_filtered: buffers (per AC) of frames we already tried to
@@ -329,7 +332,7 @@ struct ieee80211_tx_latency_stat {
  */
 struct sta_info {
 	/* General information, mostly static */
-	struct list_head list;
+	struct list_head list, free_list;
 	struct rcu_head rcu_head;
 	struct sta_info __rcu *hnext;
 	struct ieee80211_local *local;
@@ -355,10 +358,8 @@ struct sta_info {
 	/* use the accessors defined below */
 	unsigned long _flags;
 
-	/*
-	 * STA powersave frame queues, no more than the internal
-	 * locking required.
-	 */
+	/* STA powersave lock and frame queues */
+	spinlock_t ps_lock;
 	struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS];
 	struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS];
 	unsigned long driver_buffered_tids;
@@ -396,6 +397,7 @@ struct sta_info {
 	struct ieee80211_tx_rate last_tx_rate;
 	int last_rx_rate_idx;
 	u32 last_rx_rate_flag;
+	u32 last_rx_rate_vht_flag;
 	u8 last_rx_rate_vht_nss;
 	u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1];
 
@@ -605,21 +607,6 @@ void sta_info_recalc_tim(struct sta_info *sta);
 
 void sta_info_init(struct ieee80211_local *local);
 void sta_info_stop(struct ieee80211_local *local);
-int sta_info_flush_defer(struct ieee80211_sub_if_data *sdata);
-
-/**
- * sta_info_flush_cleanup - flush the sta_info cleanup queue
- * @sdata: the interface
- *
- * Flushes the sta_info cleanup queue for a given interface;
- * this is necessary before the interface is removed or, for
- * AP/mesh interfaces, before it is deconfigured.
- *
- * Note an rcu_barrier() must precede the function, after all
- * stations have been flushed/removed to ensure the call_rcu()
- * calls that add stations to the cleanup queue have completed.
- */
-void sta_info_flush_cleanup(struct ieee80211_sub_if_data *sdata);
 
 /**
  * sta_info_flush - flush matching STA entries from the STA table
@@ -627,15 +614,13 @@ void sta_info_flush_cleanup(struct ieee80211_sub_if_data *sdata);
  * Returns the number of removed STA entries.
  *
  * @sdata: sdata to remove all stations from
+ * @vlans: if the given interface is an AP interface, also flush VLANs
  */
+int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans);
+
 static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata)
 {
-	int ret = sta_info_flush_defer(sdata);
-
-	rcu_barrier();
-	sta_info_flush_cleanup(sdata);
-
-	return ret;
+	return __sta_info_flush(sdata, false);
 }
 
 void sta_set_rate_info_tx(struct sta_info *sta,
@@ -651,6 +636,4 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta);
 void ieee80211_sta_ps_deliver_poll_response(struct sta_info *sta);
 void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta);
 
-void ieee80211_cleanup_sdata_stas(struct ieee80211_sub_if_data *sdata);
-
 #endif /* STA_INFO_H */
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 1ee85c40243..ba29ebc8614 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -314,10 +314,9 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local,
 	    !is_multicast_ether_addr(hdr->addr1))
 		txflags |= IEEE80211_RADIOTAP_F_TX_FAIL;
 
-	if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) ||
-	    (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT))
+	if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)
 		txflags |= IEEE80211_RADIOTAP_F_TX_CTS;
-	else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS)
+	if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS)
 		txflags |= IEEE80211_RADIOTAP_F_TX_RTS;
 
 	put_unaligned_le16(txflags, pos);
@@ -479,7 +478,7 @@ static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local,
 	u32 msrmnt;
 	u16 tid;
 	u8 *qc;
-	int i, bin_range_count, bin_count;
+	int i, bin_range_count;
 	u32 *bin_ranges;
 	__le16 fc;
 	struct ieee80211_tx_latency_stat *tx_lat;
@@ -522,7 +521,6 @@ static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local,
 	/* count how many Tx frames transmitted with the appropriate latency */
 	bin_range_count = tx_latency->n_ranges;
 	bin_ranges = tx_latency->ranges;
-	bin_count = tx_lat->bin_count;
 
 	for (i = 0; i < bin_range_count; i++) {
 		if (msrmnt <= bin_ranges[i]) {
@@ -543,6 +541,23 @@ static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local,
  */
 #define STA_LOST_PKT_THRESHOLD	50
 
+static void ieee80211_lost_packet(struct sta_info *sta, struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+	/* This packet was aggregated but doesn't carry status info */
+	if ((info->flags & IEEE80211_TX_CTL_AMPDU) &&
+	    !(info->flags & IEEE80211_TX_STAT_AMPDU))
+		return;
+
+	if (++sta->lost_packets < STA_LOST_PKT_THRESHOLD)
+		return;
+
+	cfg80211_cqm_pktloss_notify(sta->sdata->dev, sta->sta.addr,
+				    sta->lost_packets, GFP_ATOMIC);
+	sta->lost_packets = 0;
+}
+
 void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct sk_buff *skb2;
@@ -619,6 +634,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 					sta, true, acked);
 
 		if ((local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL) &&
+		    (ieee80211_is_data(hdr->frame_control)) &&
 		    (rates_idx != -1))
 			sta->last_tx_rate = info->status.rates[rates_idx];
 
@@ -681,12 +697,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 			if (info->flags & IEEE80211_TX_STAT_ACK) {
 				if (sta->lost_packets)
 					sta->lost_packets = 0;
-			} else if (++sta->lost_packets >= STA_LOST_PKT_THRESHOLD) {
-				cfg80211_cqm_pktloss_notify(sta->sdata->dev,
-							    sta->sta.addr,
-							    sta->lost_packets,
-							    GFP_ATOMIC);
-				sta->lost_packets = 0;
+			} else {
+				ieee80211_lost_packet(sta, skb);
 			}
 		}
 
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
new file mode 100644
index 00000000000..652813b2d3d
--- /dev/null
+++ b/net/mac80211/tdls.c
@@ -0,0 +1,325 @@
+/*
+ * mac80211 TDLS handling code
+ *
+ * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2014, Intel Corporation
+ *
+ * This file is GPLv2 as found in COPYING.
+ */
+
+#include <linux/ieee80211.h>
+#include "ieee80211_i.h"
+
+static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb)
+{
+	u8 *pos = (void *)skb_put(skb, 7);
+
+	*pos++ = WLAN_EID_EXT_CAPABILITY;
+	*pos++ = 5; /* len */
+	*pos++ = 0x0;
+	*pos++ = 0x0;
+	*pos++ = 0x0;
+	*pos++ = 0x0;
+	*pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED;
+}
+
+static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	u16 capab;
+
+	capab = 0;
+	if (ieee80211_get_sdata_band(sdata) != IEEE80211_BAND_2GHZ)
+		return capab;
+
+	if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE))
+		capab |= WLAN_CAPABILITY_SHORT_SLOT_TIME;
+	if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE))
+		capab |= WLAN_CAPABILITY_SHORT_PREAMBLE;
+
+	return capab;
+}
+
+static void ieee80211_tdls_add_link_ie(struct sk_buff *skb, const u8 *src_addr,
+				       const u8 *peer, const u8 *bssid)
+{
+	struct ieee80211_tdls_lnkie *lnkid;
+
+	lnkid = (void *)skb_put(skb, sizeof(struct ieee80211_tdls_lnkie));
+
+	lnkid->ie_type = WLAN_EID_LINK_ID;
+	lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2;
+
+	memcpy(lnkid->bssid, bssid, ETH_ALEN);
+	memcpy(lnkid->init_sta, src_addr, ETH_ALEN);
+	memcpy(lnkid->resp_sta, peer, ETH_ALEN);
+}
+
+static int
+ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
+			       const u8 *peer, u8 action_code, u8 dialog_token,
+			       u16 status_code, struct sk_buff *skb)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
+	struct ieee80211_tdls_data *tf;
+
+	tf = (void *)skb_put(skb, offsetof(struct ieee80211_tdls_data, u));
+
+	memcpy(tf->da, peer, ETH_ALEN);
+	memcpy(tf->sa, sdata->vif.addr, ETH_ALEN);
+	tf->ether_type = cpu_to_be16(ETH_P_TDLS);
+	tf->payload_type = WLAN_TDLS_SNAP_RFTYPE;
+
+	switch (action_code) {
+	case WLAN_TDLS_SETUP_REQUEST:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_SETUP_REQUEST;
+
+		skb_put(skb, sizeof(tf->u.setup_req));
+		tf->u.setup_req.dialog_token = dialog_token;
+		tf->u.setup_req.capability =
+			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
+
+		ieee80211_add_srates_ie(sdata, skb, false, band);
+		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
+		ieee80211_tdls_add_ext_capab(skb);
+		break;
+	case WLAN_TDLS_SETUP_RESPONSE:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_SETUP_RESPONSE;
+
+		skb_put(skb, sizeof(tf->u.setup_resp));
+		tf->u.setup_resp.status_code = cpu_to_le16(status_code);
+		tf->u.setup_resp.dialog_token = dialog_token;
+		tf->u.setup_resp.capability =
+			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
+
+		ieee80211_add_srates_ie(sdata, skb, false, band);
+		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
+		ieee80211_tdls_add_ext_capab(skb);
+		break;
+	case WLAN_TDLS_SETUP_CONFIRM:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_SETUP_CONFIRM;
+
+		skb_put(skb, sizeof(tf->u.setup_cfm));
+		tf->u.setup_cfm.status_code = cpu_to_le16(status_code);
+		tf->u.setup_cfm.dialog_token = dialog_token;
+		break;
+	case WLAN_TDLS_TEARDOWN:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_TEARDOWN;
+
+		skb_put(skb, sizeof(tf->u.teardown));
+		tf->u.teardown.reason_code = cpu_to_le16(status_code);
+		break;
+	case WLAN_TDLS_DISCOVERY_REQUEST:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_DISCOVERY_REQUEST;
+
+		skb_put(skb, sizeof(tf->u.discover_req));
+		tf->u.discover_req.dialog_token = dialog_token;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev,
+			   const u8 *peer, u8 action_code, u8 dialog_token,
+			   u16 status_code, struct sk_buff *skb)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
+	struct ieee80211_mgmt *mgmt;
+
+	mgmt = (void *)skb_put(skb, 24);
+	memset(mgmt, 0, 24);
+	memcpy(mgmt->da, peer, ETH_ALEN);
+	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
+	memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN);
+
+	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
+					  IEEE80211_STYPE_ACTION);
+
+	switch (action_code) {
+	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
+		skb_put(skb, 1 + sizeof(mgmt->u.action.u.tdls_discover_resp));
+		mgmt->u.action.category = WLAN_CATEGORY_PUBLIC;
+		mgmt->u.action.u.tdls_discover_resp.action_code =
+			WLAN_PUB_ACTION_TDLS_DISCOVER_RES;
+		mgmt->u.action.u.tdls_discover_resp.dialog_token =
+			dialog_token;
+		mgmt->u.action.u.tdls_discover_resp.capability =
+			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
+
+		ieee80211_add_srates_ie(sdata, skb, false, band);
+		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
+		ieee80211_tdls_add_ext_capab(skb);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
+			const u8 *peer, u8 action_code, u8 dialog_token,
+			u16 status_code, u32 peer_capability,
+			const u8 *extra_ies, size_t extra_ies_len)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+	struct sk_buff *skb = NULL;
+	bool send_direct;
+	int ret;
+
+	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
+		return -ENOTSUPP;
+
+	/* make sure we are in managed mode, and associated */
+	if (sdata->vif.type != NL80211_IFTYPE_STATION ||
+	    !sdata->u.mgd.associated)
+		return -EINVAL;
+
+	tdls_dbg(sdata, "TDLS mgmt action %d peer %pM\n",
+		 action_code, peer);
+
+	skb = dev_alloc_skb(local->hw.extra_tx_headroom +
+			    max(sizeof(struct ieee80211_mgmt),
+				sizeof(struct ieee80211_tdls_data)) +
+			    50 + /* supported rates */
+			    7 + /* ext capab */
+			    extra_ies_len +
+			    sizeof(struct ieee80211_tdls_lnkie));
+	if (!skb)
+		return -ENOMEM;
+
+	skb_reserve(skb, local->hw.extra_tx_headroom);
+
+	switch (action_code) {
+	case WLAN_TDLS_SETUP_REQUEST:
+	case WLAN_TDLS_SETUP_RESPONSE:
+	case WLAN_TDLS_SETUP_CONFIRM:
+	case WLAN_TDLS_TEARDOWN:
+	case WLAN_TDLS_DISCOVERY_REQUEST:
+		ret = ieee80211_prep_tdls_encap_data(wiphy, dev, peer,
+						     action_code, dialog_token,
+						     status_code, skb);
+		send_direct = false;
+		break;
+	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
+		ret = ieee80211_prep_tdls_direct(wiphy, dev, peer, action_code,
+						 dialog_token, status_code,
+						 skb);
+		send_direct = true;
+		break;
+	default:
+		ret = -ENOTSUPP;
+		break;
+	}
+
+	if (ret < 0)
+		goto fail;
+
+	if (extra_ies_len)
+		memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len);
+
+	/* the TDLS link IE is always added last */
+	switch (action_code) {
+	case WLAN_TDLS_SETUP_REQUEST:
+	case WLAN_TDLS_SETUP_CONFIRM:
+	case WLAN_TDLS_TEARDOWN:
+	case WLAN_TDLS_DISCOVERY_REQUEST:
+		/* we are the initiator */
+		ieee80211_tdls_add_link_ie(skb, sdata->vif.addr, peer,
+					   sdata->u.mgd.bssid);
+		break;
+	case WLAN_TDLS_SETUP_RESPONSE:
+	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
+		/* we are the responder */
+		ieee80211_tdls_add_link_ie(skb, peer, sdata->vif.addr,
+					   sdata->u.mgd.bssid);
+		break;
+	default:
+		ret = -ENOTSUPP;
+		goto fail;
+	}
+
+	if (send_direct) {
+		ieee80211_tx_skb(sdata, skb);
+		return 0;
+	}
+
+	/*
+	 * According to 802.11z: Setup req/resp are sent in AC_BK, otherwise
+	 * we should default to AC_VI.
+	 */
+	switch (action_code) {
+	case WLAN_TDLS_SETUP_REQUEST:
+	case WLAN_TDLS_SETUP_RESPONSE:
+		skb_set_queue_mapping(skb, IEEE80211_AC_BK);
+		skb->priority = 2;
+		break;
+	default:
+		skb_set_queue_mapping(skb, IEEE80211_AC_VI);
+		skb->priority = 5;
+		break;
+	}
+
+	/* disable bottom halves when entering the Tx path */
+	local_bh_disable();
+	ret = ieee80211_subif_start_xmit(skb, dev);
+	local_bh_enable();
+
+	return ret;
+
+fail:
+	dev_kfree_skb(skb);
+	return ret;
+}
+
+int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
+			const u8 *peer, enum nl80211_tdls_operation oper)
+{
+	struct sta_info *sta;
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+
+	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
+		return -ENOTSUPP;
+
+	if (sdata->vif.type != NL80211_IFTYPE_STATION)
+		return -EINVAL;
+
+	tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer);
+
+	switch (oper) {
+	case NL80211_TDLS_ENABLE_LINK:
+		rcu_read_lock();
+		sta = sta_info_get(sdata, peer);
+		if (!sta) {
+			rcu_read_unlock();
+			return -ENOLINK;
+		}
+
+		set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH);
+		rcu_read_unlock();
+		break;
+	case NL80211_TDLS_DISABLE_LINK:
+		return sta_info_destroy_addr(sdata, peer);
+	case NL80211_TDLS_TEARDOWN:
+	case NL80211_TDLS_SETUP:
+	case NL80211_TDLS_DISCOVERY_REQ:
+		/* We don't support in-driver setup/teardown/discovery */
+		return -ENOTSUPP;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return 0;
+}
diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c
index 124b1fdc20d..0ae207771a5 100644
--- a/net/mac80211/tkip.c
+++ b/net/mac80211/tkip.c
@@ -186,7 +186,7 @@ void ieee80211_get_tkip_p1k_iv(struct ieee80211_key_conf *keyconf,
 EXPORT_SYMBOL(ieee80211_get_tkip_p1k_iv);
 
 void ieee80211_get_tkip_rx_p1k(struct ieee80211_key_conf *keyconf,
-                               const u8 *ta, u32 iv32, u16 *p1k)
+			       const u8 *ta, u32 iv32, u16 *p1k)
 {
 	const u8 *tk = &keyconf->key[NL80211_TKIP_DATA_OFFSET_ENCR_KEY];
 	struct tkip_ctx ctx;
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index e9ccf22f6dd..cfe1a0688b5 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -21,10 +21,10 @@
 
 #define VIF_ENTRY	__field(enum nl80211_iftype, vif_type) __field(void *, sdata)	\
 			__field(bool, p2p)						\
-			__string(vif_name, sdata->dev ? sdata->dev->name : "<nodev>")
+			__string(vif_name, sdata->name)
 #define VIF_ASSIGN	__entry->vif_type = sdata->vif.type; __entry->sdata = sdata;	\
 			__entry->p2p = sdata->vif.p2p;					\
-			__assign_str(vif_name, sdata->dev ? sdata->dev->name : sdata->name)
+			__assign_str(vif_name, sdata->name)
 #define VIF_PR_FMT	" vif:%s(%d%s)"
 #define VIF_PR_ARG	__get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : ""
 
@@ -184,6 +184,20 @@ TRACE_EVENT(drv_return_bool,
 		  "true" : "false")
 );
 
+TRACE_EVENT(drv_return_u32,
+	TP_PROTO(struct ieee80211_local *local, u32 ret),
+	TP_ARGS(local, ret),
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		__field(u32, ret)
+	),
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		__entry->ret = ret;
+	),
+	TP_printk(LOCAL_PR_FMT " - %u", LOCAL_PR_ARG, __entry->ret)
+);
+
 TRACE_EVENT(drv_return_u64,
 	TP_PROTO(struct ieee80211_local *local, u64 ret),
 	TP_ARGS(local, ret),
@@ -443,30 +457,6 @@ TRACE_EVENT(drv_prepare_multicast,
 	)
 );
 
-TRACE_EVENT(drv_set_multicast_list,
-	TP_PROTO(struct ieee80211_local *local,
-		 struct ieee80211_sub_if_data *sdata, int mc_count),
-
-	TP_ARGS(local, sdata, mc_count),
-
-	TP_STRUCT__entry(
-		LOCAL_ENTRY
-		__field(bool, allmulti)
-		__field(int, mc_count)
-	),
-
-	TP_fast_assign(
-		LOCAL_ASSIGN;
-		__entry->allmulti = sdata->flags & IEEE80211_SDATA_ALLMULTI;
-		__entry->mc_count = mc_count;
-	),
-
-	TP_printk(
-		LOCAL_PR_FMT " configure mc filter, count=%d, allmulti=%d",
-		LOCAL_PR_ARG, __entry->mc_count, __entry->allmulti
-	)
-);
-
 TRACE_EVENT(drv_configure_filter,
 	TP_PROTO(struct ieee80211_local *local,
 		 unsigned int changed_flags,
@@ -577,7 +567,7 @@ TRACE_EVENT(drv_update_tkip_key,
 
 	TP_printk(
 		LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " iv32:%#x",
-		LOCAL_PR_ARG,VIF_PR_ARG,STA_PR_ARG, __entry->iv32
+		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->iv32
 	)
 );
 
@@ -790,7 +780,7 @@ TRACE_EVENT(drv_sta_rc_update,
 	)
 );
 
-TRACE_EVENT(drv_sta_add,
+DECLARE_EVENT_CLASS(sta_event,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
 		 struct ieee80211_sta *sta),
@@ -815,29 +805,25 @@ TRACE_EVENT(drv_sta_add,
 	)
 );
 
-TRACE_EVENT(drv_sta_remove,
+DEFINE_EVENT(sta_event, drv_sta_add,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
 		 struct ieee80211_sta *sta),
+	TP_ARGS(local, sdata, sta)
+);
 
-	TP_ARGS(local, sdata, sta),
-
-	TP_STRUCT__entry(
-		LOCAL_ENTRY
-		VIF_ENTRY
-		STA_ENTRY
-	),
-
-	TP_fast_assign(
-		LOCAL_ASSIGN;
-		VIF_ASSIGN;
-		STA_ASSIGN;
-	),
+DEFINE_EVENT(sta_event, drv_sta_remove,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta),
+	TP_ARGS(local, sdata, sta)
+);
 
-	TP_printk(
-		LOCAL_PR_FMT  VIF_PR_FMT  STA_PR_FMT,
-		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG
-	)
+DEFINE_EVENT(sta_event, drv_sta_pre_rcu_remove,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta),
+	TP_ARGS(local, sdata, sta)
 );
 
 TRACE_EVENT(drv_conf_tx,
@@ -1403,6 +1389,91 @@ TRACE_EVENT(drv_change_chanctx,
 	)
 );
 
+#if !defined(__TRACE_VIF_ENTRY)
+#define __TRACE_VIF_ENTRY
+struct trace_vif_entry {
+	enum nl80211_iftype vif_type;
+	bool p2p;
+	char vif_name[IFNAMSIZ];
+} __packed;
+
+struct trace_chandef_entry {
+	u32 control_freq;
+	u32 chan_width;
+	u32 center_freq1;
+	u32 center_freq2;
+} __packed;
+
+struct trace_switch_entry {
+	struct trace_vif_entry vif;
+	struct trace_chandef_entry old_chandef;
+	struct trace_chandef_entry new_chandef;
+} __packed;
+
+#define SWITCH_ENTRY_ASSIGN(to, from) local_vifs[i].to = vifs[i].from
+#endif
+
+TRACE_EVENT(drv_switch_vif_chanctx,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_vif_chanctx_switch *vifs,
+		 int n_vifs, enum ieee80211_chanctx_switch_mode mode),
+	    TP_ARGS(local, vifs, n_vifs, mode),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		__field(int, n_vifs)
+		__field(u32, mode)
+		__dynamic_array(u8, vifs,
+				sizeof(struct trace_switch_entry) * n_vifs)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		__entry->n_vifs = n_vifs;
+		__entry->mode = mode;
+		{
+			struct trace_switch_entry *local_vifs =
+				__get_dynamic_array(vifs);
+			int i;
+
+			for (i = 0; i < n_vifs; i++) {
+				struct ieee80211_sub_if_data *sdata;
+
+				sdata = container_of(vifs[i].vif,
+						struct ieee80211_sub_if_data,
+						vif);
+
+				SWITCH_ENTRY_ASSIGN(vif.vif_type, vif->type);
+				SWITCH_ENTRY_ASSIGN(vif.p2p, vif->p2p);
+				strncpy(local_vifs[i].vif.vif_name,
+					sdata->name,
+					sizeof(local_vifs[i].vif.vif_name));
+				SWITCH_ENTRY_ASSIGN(old_chandef.control_freq,
+						old_ctx->def.chan->center_freq);
+				SWITCH_ENTRY_ASSIGN(old_chandef.chan_width,
+						    old_ctx->def.width);
+				SWITCH_ENTRY_ASSIGN(old_chandef.center_freq1,
+						    old_ctx->def.center_freq1);
+				SWITCH_ENTRY_ASSIGN(old_chandef.center_freq2,
+						    old_ctx->def.center_freq2);
+				SWITCH_ENTRY_ASSIGN(new_chandef.control_freq,
+						new_ctx->def.chan->center_freq);
+				SWITCH_ENTRY_ASSIGN(new_chandef.chan_width,
+						    new_ctx->def.width);
+				SWITCH_ENTRY_ASSIGN(new_chandef.center_freq1,
+						    new_ctx->def.center_freq1);
+				SWITCH_ENTRY_ASSIGN(new_chandef.center_freq2,
+						    new_ctx->def.center_freq2);
+			}
+		}
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT " n_vifs:%d mode:%d",
+		LOCAL_PR_ARG, __entry->n_vifs, __entry->mode
+	)
+);
+
 DECLARE_EVENT_CLASS(local_sdata_chanctx,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
@@ -1527,6 +1598,24 @@ DEFINE_EVENT(local_sdata_evt, drv_leave_ibss,
 	TP_ARGS(local, sdata)
 );
 
+TRACE_EVENT(drv_get_expected_throughput,
+	TP_PROTO(struct ieee80211_sta *sta),
+
+	TP_ARGS(sta),
+
+	TP_STRUCT__entry(
+		STA_ENTRY
+	),
+
+	TP_fast_assign(
+		STA_ASSIGN;
+	),
+
+	TP_printk(
+		STA_PR_FMT, STA_PR_ARG
+	)
+);
+
 /*
  * Tracing for API calls that drivers call.
  */
@@ -1863,6 +1952,33 @@ TRACE_EVENT(api_eosp,
 	)
 );
 
+TRACE_EVENT(api_sta_set_buffered,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sta *sta,
+		 u8 tid, bool buffered),
+
+	TP_ARGS(local, sta, tid, buffered),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		STA_ENTRY
+		__field(u8, tid)
+		__field(bool, buffered)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		STA_ASSIGN;
+		__entry->tid = tid;
+		__entry->buffered = buffered;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT STA_PR_FMT " tid:%d buffered:%d",
+		LOCAL_PR_ARG, STA_PR_ARG, __entry->tid, __entry->buffered
+	)
+);
+
 /*
  * Tracing for internal functions
  * (which may also be called in response to driver calls)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 6d59e21cdb9..1a252c606ad 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -414,6 +414,9 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx)
 	if (ieee80211_has_order(hdr->frame_control))
 		return TX_CONTINUE;
 
+	if (ieee80211_is_probe_req(hdr->frame_control))
+		return TX_CONTINUE;
+
 	if (tx->local->hw.flags & IEEE80211_HW_QUEUE_CONTROL)
 		info->hw_queue = tx->sdata->vif.cab_queue;
 
@@ -452,8 +455,7 @@ static int ieee80211_use_mfp(__le16 fc, struct sta_info *sta,
 	if (sta == NULL || !test_sta_flag(sta, WLAN_STA_MFP))
 		return 0;
 
-	if (!ieee80211_is_robust_mgmt_frame((struct ieee80211_hdr *)
-					    skb->data))
+	if (!ieee80211_is_robust_mgmt_frame(skb))
 		return 0;
 
 	return 1;
@@ -475,11 +477,8 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		     !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) {
 		int ac = skb_get_queue_mapping(tx->skb);
 
-		/* only deauth, disassoc and action are bufferable MMPDUs */
 		if (ieee80211_is_mgmt(hdr->frame_control) &&
-		    !ieee80211_is_deauth(hdr->frame_control) &&
-		    !ieee80211_is_disassoc(hdr->frame_control) &&
-		    !ieee80211_is_action(hdr->frame_control)) {
+		    !ieee80211_is_bufferable_mmpdu(hdr->frame_control)) {
 			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
 			return TX_CONTINUE;
 		}
@@ -488,6 +487,20 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		       sta->sta.addr, sta->sta.aid, ac);
 		if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
 			purge_old_ps_buffers(tx->local);
+
+		/* sync with ieee80211_sta_ps_deliver_wakeup */
+		spin_lock(&sta->ps_lock);
+		/*
+		 * STA woke up the meantime and all the frames on ps_tx_buf have
+		 * been queued to pending queue. No reordering can happen, go
+		 * ahead and Tx the packet.
+		 */
+		if (!test_sta_flag(sta, WLAN_STA_PS_STA) &&
+		    !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+			spin_unlock(&sta->ps_lock);
+			return TX_CONTINUE;
+		}
+
 		if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) {
 			struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]);
 			ps_dbg(tx->sdata,
@@ -500,7 +513,9 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		info->control.jiffies = jiffies;
 		info->control.vif = &tx->sdata->vif;
 		info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+		info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 		skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
+		spin_unlock(&sta->ps_lock);
 
 		if (!timer_pending(&local->sta_cleanup))
 			mod_timer(&local->sta_cleanup,
@@ -563,7 +578,7 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 		tx->key = key;
 	else if (ieee80211_is_mgmt(hdr->frame_control) &&
 		 is_multicast_ether_addr(hdr->addr1) &&
-		 ieee80211_is_robust_mgmt_frame(hdr) &&
+		 ieee80211_is_robust_mgmt_frame(tx->skb) &&
 		 (key = rcu_dereference(tx->sdata->default_mgmt_key)))
 		tx->key = key;
 	else if (is_multicast_ether_addr(hdr->addr1) &&
@@ -578,12 +593,12 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 		tx->key = NULL;
 	else if (tx->skb->protocol == tx->sdata->control_port_protocol)
 		tx->key = NULL;
-	else if (ieee80211_is_robust_mgmt_frame(hdr) &&
+	else if (ieee80211_is_robust_mgmt_frame(tx->skb) &&
 		 !(ieee80211_is_action(hdr->frame_control) &&
 		   tx->sta && test_sta_flag(tx->sta, WLAN_STA_MFP)))
 		tx->key = NULL;
 	else if (ieee80211_is_mgmt(hdr->frame_control) &&
-		 !ieee80211_is_robust_mgmt_frame(hdr))
+		 !ieee80211_is_robust_mgmt_frame(tx->skb))
 		tx->key = NULL;
 	else {
 		I802_DEBUG_INC(tx->local->tx_handlers_drop_unencrypted);
@@ -874,7 +889,7 @@ static int ieee80211_fragment(struct ieee80211_tx_data *tx,
 	}
 
 	/* adjust first fragment's length */
-	skb->len = hdrlen + per_fragm;
+	skb_trim(skb, hdrlen + per_fragm);
 	return 0;
 }
 
@@ -1073,6 +1088,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
 			queued = true;
 			info->control.vif = &tx->sdata->vif;
 			info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+			info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 			__skb_queue_tail(&tid_tx->pending, skb);
 			if (skb_queue_len(&tid_tx->pending) > STA_MAX_TX_BUFFER)
 				purge_skb = __skb_dequeue(&tid_tx->pending);
@@ -2161,7 +2177,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 	if (ieee80211_is_data_qos(fc)) {
 		__le16 *qos_control;
 
-		qos_control = (__le16*) skb_push(skb, 2);
+		qos_control = (__le16 *) skb_push(skb, 2);
 		memcpy(skb_push(skb, hdrlen - 2), &hdr, hdrlen - 2);
 		/*
 		 * Maybe we could actually set some fields here, for now just
@@ -2312,7 +2328,8 @@ void ieee80211_tx_pending(unsigned long data)
 /* functions for drivers to get certain frames */
 
 static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
-				       struct ps_data *ps, struct sk_buff *skb)
+				       struct ps_data *ps, struct sk_buff *skb,
+				       bool is_template)
 {
 	u8 *pos, *tim;
 	int aid0 = 0;
@@ -2323,13 +2340,14 @@ static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
 	if (atomic_read(&ps->num_sta_ps) > 0)
 		/* in the hope that this is faster than
 		 * checking byte-for-byte */
-		have_bits = !bitmap_empty((unsigned long*)ps->tim,
+		have_bits = !bitmap_empty((unsigned long *)ps->tim,
 					  IEEE80211_MAX_AID+1);
-
-	if (ps->dtim_count == 0)
-		ps->dtim_count = sdata->vif.bss_conf.dtim_period - 1;
-	else
-		ps->dtim_count--;
+	if (!is_template) {
+		if (ps->dtim_count == 0)
+			ps->dtim_count = sdata->vif.bss_conf.dtim_period - 1;
+		else
+			ps->dtim_count--;
+	}
 
 	tim = pos = (u8 *) skb_put(skb, 6);
 	*pos++ = WLAN_EID_TIM;
@@ -2375,7 +2393,8 @@ static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
 }
 
 static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
-				    struct ps_data *ps, struct sk_buff *skb)
+				    struct ps_data *ps, struct sk_buff *skb,
+				    bool is_template)
 {
 	struct ieee80211_local *local = sdata->local;
 
@@ -2387,33 +2406,24 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
 	 * of the tim bitmap in mac80211 and the driver.
 	 */
 	if (local->tim_in_locked_section) {
-		__ieee80211_beacon_add_tim(sdata, ps, skb);
+		__ieee80211_beacon_add_tim(sdata, ps, skb, is_template);
 	} else {
 		spin_lock_bh(&local->tim_lock);
-		__ieee80211_beacon_add_tim(sdata, ps, skb);
+		__ieee80211_beacon_add_tim(sdata, ps, skb, is_template);
 		spin_unlock_bh(&local->tim_lock);
 	}
 
 	return 0;
 }
 
-void ieee80211_csa_finish(struct ieee80211_vif *vif)
-{
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
-
-	ieee80211_queue_work(&sdata->local->hw,
-			     &sdata->csa_finalize_work);
-}
-EXPORT_SYMBOL(ieee80211_csa_finish);
-
-static void ieee80211_update_csa(struct ieee80211_sub_if_data *sdata,
-				 struct beacon_data *beacon)
+static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata,
+			      struct beacon_data *beacon)
 {
 	struct probe_resp *resp;
-	int counter_offset_beacon = sdata->csa_counter_offset_beacon;
-	int counter_offset_presp = sdata->csa_counter_offset_presp;
 	u8 *beacon_data;
 	size_t beacon_data_len;
+	int i;
+	u8 count = sdata->csa_current_counter;
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP:
@@ -2431,36 +2441,57 @@ static void ieee80211_update_csa(struct ieee80211_sub_if_data *sdata,
 	default:
 		return;
 	}
-	if (WARN_ON(counter_offset_beacon >= beacon_data_len))
-		return;
 
-	/* warn if the driver did not check for/react to csa completeness */
-	if (WARN_ON(beacon_data[counter_offset_beacon] == 0))
-		return;
+	for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; ++i) {
+		u16 counter_offset_beacon =
+			sdata->csa_counter_offset_beacon[i];
+		u16 counter_offset_presp = sdata->csa_counter_offset_presp[i];
 
-	beacon_data[counter_offset_beacon]--;
+		if (counter_offset_beacon) {
+			if (WARN_ON(counter_offset_beacon >= beacon_data_len))
+				return;
 
-	if (sdata->vif.type == NL80211_IFTYPE_AP && counter_offset_presp) {
-		rcu_read_lock();
-		resp = rcu_dereference(sdata->u.ap.probe_resp);
+			beacon_data[counter_offset_beacon] = count;
+		}
 
-		/* if nl80211 accepted the offset, this should not happen. */
-		if (WARN_ON(!resp)) {
+		if (sdata->vif.type == NL80211_IFTYPE_AP &&
+		    counter_offset_presp) {
+			rcu_read_lock();
+			resp = rcu_dereference(sdata->u.ap.probe_resp);
+
+			/* If nl80211 accepted the offset, this should
+			 * not happen.
+			 */
+			if (WARN_ON(!resp)) {
+				rcu_read_unlock();
+				return;
+			}
+			resp->data[counter_offset_presp] = count;
 			rcu_read_unlock();
-			return;
 		}
-		resp->data[counter_offset_presp]--;
-		rcu_read_unlock();
 	}
 }
 
+u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif)
+{
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+
+	sdata->csa_current_counter--;
+
+	/* the counter should never reach 0 */
+	WARN_ON(!sdata->csa_current_counter);
+
+	return sdata->csa_current_counter;
+}
+EXPORT_SYMBOL(ieee80211_csa_update_counter);
+
 bool ieee80211_csa_is_complete(struct ieee80211_vif *vif)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct beacon_data *beacon = NULL;
 	u8 *beacon_data;
 	size_t beacon_data_len;
-	int counter_beacon = sdata->csa_counter_offset_beacon;
+	int counter_beacon = sdata->csa_counter_offset_beacon[0];
 	int ret = false;
 
 	if (!ieee80211_sdata_running(sdata))
@@ -2501,7 +2532,7 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif)
 	if (WARN_ON(counter_beacon > beacon_data_len))
 		goto out;
 
-	if (beacon_data[counter_beacon] == 0)
+	if (beacon_data[counter_beacon] == 1)
 		ret = true;
  out:
 	rcu_read_unlock();
@@ -2510,9 +2541,11 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif)
 }
 EXPORT_SYMBOL(ieee80211_csa_is_complete);
 
-struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
-					 struct ieee80211_vif *vif,
-					 u16 *tim_offset, u16 *tim_length)
+static struct sk_buff *
+__ieee80211_beacon_get(struct ieee80211_hw *hw,
+		       struct ieee80211_vif *vif,
+		       struct ieee80211_mutable_offsets *offs,
+		       bool is_template)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
 	struct sk_buff *skb = NULL;
@@ -2521,6 +2554,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 	enum ieee80211_band band;
 	struct ieee80211_tx_rate_control txrc;
 	struct ieee80211_chanctx_conf *chanctx_conf;
+	int csa_off_base = 0;
 
 	rcu_read_lock();
 
@@ -2530,18 +2564,20 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 	if (!ieee80211_sdata_running(sdata) || !chanctx_conf)
 		goto out;
 
-	if (tim_offset)
-		*tim_offset = 0;
-	if (tim_length)
-		*tim_length = 0;
+	if (offs)
+		memset(offs, 0, sizeof(*offs));
 
 	if (sdata->vif.type == NL80211_IFTYPE_AP) {
 		struct ieee80211_if_ap *ap = &sdata->u.ap;
 		struct beacon_data *beacon = rcu_dereference(ap->beacon);
 
 		if (beacon) {
-			if (sdata->vif.csa_active)
-				ieee80211_update_csa(sdata, beacon);
+			if (sdata->vif.csa_active) {
+				if (!is_template)
+					ieee80211_csa_update_counter(vif);
+
+				ieee80211_set_csa(sdata, beacon);
+			}
 
 			/*
 			 * headroom, head length,
@@ -2549,7 +2585,8 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 			 */
 			skb = dev_alloc_skb(local->tx_headroom +
 					    beacon->head_len +
-					    beacon->tail_len + 256);
+					    beacon->tail_len + 256 +
+					    local->hw.extra_beacon_tailroom);
 			if (!skb)
 				goto out;
 
@@ -2557,12 +2594,16 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 			memcpy(skb_put(skb, beacon->head_len), beacon->head,
 			       beacon->head_len);
 
-			ieee80211_beacon_add_tim(sdata, &ap->ps, skb);
+			ieee80211_beacon_add_tim(sdata, &ap->ps, skb,
+						 is_template);
 
-			if (tim_offset)
-				*tim_offset = beacon->head_len;
-			if (tim_length)
-				*tim_length = skb->len - beacon->head_len;
+			if (offs) {
+				offs->tim_offset = beacon->head_len;
+				offs->tim_length = skb->len - beacon->head_len;
+
+				/* for AP the csa offsets are from tail */
+				csa_off_base = skb->len;
+			}
 
 			if (beacon->tail)
 				memcpy(skb_put(skb, beacon->tail_len),
@@ -2577,11 +2618,15 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 		if (!presp)
 			goto out;
 
-		if (sdata->vif.csa_active)
-			ieee80211_update_csa(sdata, presp);
+		if (sdata->vif.csa_active) {
+			if (!is_template)
+				ieee80211_csa_update_counter(vif);
 
+			ieee80211_set_csa(sdata, presp);
+		}
 
-		skb = dev_alloc_skb(local->tx_headroom + presp->head_len);
+		skb = dev_alloc_skb(local->tx_headroom + presp->head_len +
+				    local->hw.extra_beacon_tailroom);
 		if (!skb)
 			goto out;
 		skb_reserve(skb, local->tx_headroom);
@@ -2598,28 +2643,57 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 		if (!bcn)
 			goto out;
 
-		if (sdata->vif.csa_active)
-			ieee80211_update_csa(sdata, bcn);
+		if (sdata->vif.csa_active) {
+			if (!is_template)
+				/* TODO: For mesh csa_counter is in TU, so
+				 * decrementing it by one isn't correct, but
+				 * for now we leave it consistent with overall
+				 * mac80211's behavior.
+				 */
+				ieee80211_csa_update_counter(vif);
+
+			ieee80211_set_csa(sdata, bcn);
+		}
 
 		if (ifmsh->sync_ops)
-			ifmsh->sync_ops->adjust_tbtt(
-						sdata);
+			ifmsh->sync_ops->adjust_tbtt(sdata, bcn);
 
 		skb = dev_alloc_skb(local->tx_headroom +
 				    bcn->head_len +
 				    256 + /* TIM IE */
-				    bcn->tail_len);
+				    bcn->tail_len +
+				    local->hw.extra_beacon_tailroom);
 		if (!skb)
 			goto out;
 		skb_reserve(skb, local->tx_headroom);
 		memcpy(skb_put(skb, bcn->head_len), bcn->head, bcn->head_len);
-		ieee80211_beacon_add_tim(sdata, &ifmsh->ps, skb);
+		ieee80211_beacon_add_tim(sdata, &ifmsh->ps, skb, is_template);
+
+		if (offs) {
+			offs->tim_offset = bcn->head_len;
+			offs->tim_length = skb->len - bcn->head_len;
+		}
+
 		memcpy(skb_put(skb, bcn->tail_len), bcn->tail, bcn->tail_len);
 	} else {
 		WARN_ON(1);
 		goto out;
 	}
 
+	/* CSA offsets */
+	if (offs) {
+		int i;
+
+		for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; i++) {
+			u16 csa_off = sdata->csa_counter_offset_beacon[i];
+
+			if (!csa_off)
+				continue;
+
+			offs->csa_counter_offs[i] = csa_off_base + csa_off;
+		}
+	}
+
 	band = chanctx_conf->def.chan->band;
 
 	info = IEEE80211_SKB_CB(skb);
@@ -2650,6 +2724,32 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
  out:
 	rcu_read_unlock();
 	return skb;
+
+}
+
+struct sk_buff *
+ieee80211_beacon_get_template(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_mutable_offsets *offs)
+{
+	return __ieee80211_beacon_get(hw, vif, offs, true);
+}
+EXPORT_SYMBOL(ieee80211_beacon_get_template);
+
+struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
+					 struct ieee80211_vif *vif,
+					 u16 *tim_offset, u16 *tim_length)
+{
+	struct ieee80211_mutable_offsets offs = {};
+	struct sk_buff *bcn = __ieee80211_beacon_get(hw, vif, &offs, false);
+
+	if (tim_offset)
+		*tim_offset = offs.tim_offset;
+
+	if (tim_length)
+		*tim_length = offs.tim_length;
+
+	return bcn;
 }
 EXPORT_SYMBOL(ieee80211_beacon_get_tim);
 
@@ -2887,7 +2987,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw,
 				cpu_to_le16(IEEE80211_FCTL_MOREDATA);
 		}
 
-		if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+		if (sdata->vif.type == NL80211_IFTYPE_AP)
 			sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev);
 		if (!ieee80211_tx_prepare(sdata, &tx, skb))
 			break;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 875e172c001..a6cda52ed92 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -34,7 +34,7 @@
 #include "wep.h"
 
 /* privid for wiphys to determine whether they belong to us or not */
-void *mac80211_wiphy_privid = &mac80211_wiphy_privid;
+const void *const mac80211_wiphy_privid = &mac80211_wiphy_privid;
 
 struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy)
 {
@@ -76,7 +76,7 @@ u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len,
 	}
 
 	if (ieee80211_is_ctl(fc)) {
-		if(ieee80211_is_pspoll(fc))
+		if (ieee80211_is_pspoll(fc))
 			return hdr->addr1;
 
 		if (ieee80211_is_back_req(fc)) {
@@ -435,9 +435,8 @@ void ieee80211_add_pending_skb(struct ieee80211_local *local,
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 }
 
-void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local,
-				   struct sk_buff_head *skbs,
-				   void (*fn)(void *data), void *data)
+void ieee80211_add_pending_skbs(struct ieee80211_local *local,
+				struct sk_buff_head *skbs)
 {
 	struct ieee80211_hw *hw = &local->hw;
 	struct sk_buff *skb;
@@ -461,9 +460,6 @@ void ieee80211_add_pending_skbs_fn(struct ieee80211_local *local,
 		__skb_queue_tail(&local->pending[queue], skb);
 	}
 
-	if (fn)
-		fn(data);
-
 	for (i = 0; i < hw->queues; i++)
 		__ieee80211_wake_queue(hw, i,
 			IEEE80211_QUEUE_STOP_REASON_SKB_ADD);
@@ -558,7 +554,7 @@ void ieee80211_flush_queues(struct ieee80211_local *local,
 	ieee80211_stop_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_FLUSH);
 
-	drv_flush(local, queues, false);
+	drv_flush(local, sdata, queues, false);
 
 	ieee80211_wake_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_FLUSH);
@@ -642,6 +638,17 @@ void ieee80211_iterate_active_interfaces_rtnl(
 }
 EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_rtnl);
 
+struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
+
+	if (!ieee80211_sdata_running(sdata) ||
+	    !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
+		return NULL;
+	return &sdata->vif;
+}
+EXPORT_SYMBOL_GPL(wdev_to_ieee80211_vif);
+
 /*
  * Nothing should have been stuffed into the workqueue during
  * the suspend->resume cycle. If this WARN is seen then there
@@ -1089,11 +1096,12 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 	int err;
 
 	/* 24 + 6 = header + auth_algo + auth_transaction + status_code */
-	skb = dev_alloc_skb(local->hw.extra_tx_headroom + 24 + 6 + extra_len);
+	skb = dev_alloc_skb(local->hw.extra_tx_headroom + IEEE80211_WEP_IV_LEN +
+			    24 + 6 + extra_len + IEEE80211_WEP_ICV_LEN);
 	if (!skb)
 		return;
 
-	skb_reserve(skb, local->hw.extra_tx_headroom);
+	skb_reserve(skb, local->hw.extra_tx_headroom + IEEE80211_WEP_IV_LEN);
 
 	mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24 + 6);
 	memset(mgmt, 0, 24 + 6);
@@ -1270,13 +1278,32 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
 	 * that calculates local->scan_ies_len.
 	 */
 
-	/* add any remaining custom IEs */
+	/* insert custom IEs that go before VHT */
 	if (ie && ie_len) {
-		noffset = ie_len;
+		static const u8 before_vht[] = {
+			WLAN_EID_SSID,
+			WLAN_EID_SUPP_RATES,
+			WLAN_EID_REQUEST,
+			WLAN_EID_EXT_SUPP_RATES,
+			WLAN_EID_DS_PARAMS,
+			WLAN_EID_SUPPORTED_REGULATORY_CLASSES,
+			WLAN_EID_HT_CAPABILITY,
+			WLAN_EID_BSS_COEX_2040,
+			WLAN_EID_EXT_CAPABILITY,
+			WLAN_EID_SSID_LIST,
+			WLAN_EID_CHANNEL_USAGE,
+			WLAN_EID_INTERWORKING,
+			/* mesh ID can't happen here */
+			/* 60 GHz can't happen here right now */
+		};
+		noffset = ieee80211_ie_split(ie, ie_len,
+					     before_vht, ARRAY_SIZE(before_vht),
+					     offset);
 		if (end - pos < noffset - offset)
 			goto out_err;
 		memcpy(pos, ie + offset, noffset - offset);
 		pos += noffset - offset;
+		offset = noffset;
 	}
 
 	if (sband->vht_cap.vht_supported) {
@@ -1286,6 +1313,15 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
 						 sband->vht_cap.cap);
 	}
 
+	/* add any remaining custom IEs */
+	if (ie && ie_len) {
+		noffset = ie_len;
+		if (end - pos < noffset - offset)
+			goto out_err;
+		memcpy(pos, ie + offset, noffset - offset);
+		pos += noffset - offset;
+	}
+
 	return pos - buffer;
  out_err:
 	WARN_ONCE(1, "not enough space for preq IEs\n");
@@ -1363,7 +1399,6 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
 			    enum ieee80211_band band, u32 *basic_rates)
 {
 	struct ieee80211_supported_band *sband;
-	struct ieee80211_rate *bitrates;
 	size_t num_rates;
 	u32 supp_rates, rate_flags;
 	int i, j, shift;
@@ -1375,7 +1410,6 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
 	if (WARN_ON(!sband))
 		return 1;
 
-	bitrates = sband->bitrates;
 	num_rates = sband->n_bitrates;
 	supp_rates = 0;
 	for (i = 0; i < elems->supp_rates_len +
@@ -1424,6 +1458,44 @@ void ieee80211_stop_device(struct ieee80211_local *local)
 	drv_stop(local);
 }
 
+static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local)
+{
+	struct ieee80211_sub_if_data *sdata;
+	struct ieee80211_chanctx *ctx;
+
+	/*
+	 * We get here if during resume the device can't be restarted properly.
+	 * We might also get here if this happens during HW reset, which is a
+	 * slightly different situation and we need to drop all connections in
+	 * the latter case.
+	 *
+	 * Ask cfg80211 to turn off all interfaces, this will result in more
+	 * warnings but at least we'll then get into a clean stopped state.
+	 */
+
+	local->resuming = false;
+	local->suspended = false;
+	local->started = false;
+
+	/* scheduled scan clearly can't be running any more, but tell
+	 * cfg80211 and clear local state
+	 */
+	ieee80211_sched_scan_end(local);
+
+	list_for_each_entry(sdata, &local->interfaces, list)
+		sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER;
+
+	/* Mark channel contexts as not being in the driver any more to avoid
+	 * removing them from the driver during the shutdown process...
+	 */
+	mutex_lock(&local->chanctx_mtx);
+	list_for_each_entry(ctx, &local->chanctx_list, list)
+		ctx->driver_present = false;
+	mutex_unlock(&local->chanctx_mtx);
+
+	cfg80211_shutdown_all_interfaces(local->hw.wiphy);
+}
+
 static void ieee80211_assign_chanctx(struct ieee80211_local *local,
 				     struct ieee80211_sub_if_data *sdata)
 {
@@ -1451,6 +1523,8 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	struct sta_info *sta;
 	int res, i;
 	bool reconfig_due_to_wowlan = false;
+	struct ieee80211_sub_if_data *sched_scan_sdata;
+	bool sched_scan_stopped = false;
 
 #ifdef CONFIG_PM
 	if (local->suspended)
@@ -1485,9 +1559,11 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	 */
 	res = drv_start(local);
 	if (res) {
-		WARN(local->suspended, "Hardware became unavailable "
-		     "upon resume. This could be a software issue "
-		     "prior to suspend or a hardware issue.\n");
+		if (local->suspended)
+			WARN(1, "Hardware became unavailable upon resume. This could be a software issue prior to suspend or a hardware issue.\n");
+		else
+			WARN(1, "Hardware became unavailable during restart.\n");
+		ieee80211_handle_reconfig_failure(local);
 		return res;
 	}
 
@@ -1511,7 +1587,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		WARN_ON(local->resuming);
 		res = drv_add_interface(local, sdata);
 		if (WARN_ON(res)) {
-			rcu_assign_pointer(local->monitor_sdata, NULL);
+			RCU_INIT_POINTER(local->monitor_sdata, NULL);
 			synchronize_net();
 			kfree(sdata);
 		}
@@ -1530,17 +1606,17 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		list_for_each_entry(ctx, &local->chanctx_list, list)
 			WARN_ON(drv_add_chanctx(local, ctx));
 		mutex_unlock(&local->chanctx_mtx);
-	}
 
-	list_for_each_entry(sdata, &local->interfaces, list) {
-		if (!ieee80211_sdata_running(sdata))
-			continue;
-		ieee80211_assign_chanctx(local, sdata);
-	}
+		list_for_each_entry(sdata, &local->interfaces, list) {
+			if (!ieee80211_sdata_running(sdata))
+				continue;
+			ieee80211_assign_chanctx(local, sdata);
+		}
 
-	sdata = rtnl_dereference(local->monitor_sdata);
-	if (sdata && ieee80211_sdata_running(sdata))
-		ieee80211_assign_chanctx(local, sdata);
+		sdata = rtnl_dereference(local->monitor_sdata);
+		if (sdata && ieee80211_sdata_running(sdata))
+			ieee80211_assign_chanctx(local, sdata);
+	}
 
 	/* add STAs back */
 	mutex_lock(&local->sta_mtx);
@@ -1636,13 +1712,10 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 			}
 			break;
 		case NL80211_IFTYPE_WDS:
-			break;
 		case NL80211_IFTYPE_AP_VLAN:
 		case NL80211_IFTYPE_MONITOR:
-			/* ignore virtual */
-			break;
 		case NL80211_IFTYPE_P2P_DEVICE:
-			changed = BSS_CHANGED_IDLE;
+			/* nothing to do */
 			break;
 		case NL80211_IFTYPE_UNSPECIFIED:
 		case NUM_NL80211_IFTYPES:
@@ -1728,6 +1801,26 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 					IEEE80211_QUEUE_STOP_REASON_SUSPEND);
 
 	/*
+	 * Reconfigure sched scan if it was interrupted by FW restart or
+	 * suspend.
+	 */
+	mutex_lock(&local->mtx);
+	sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata,
+						lockdep_is_held(&local->mtx));
+	if (sched_scan_sdata && local->sched_scan_req)
+		/*
+		 * Sched scan stopped, but we don't want to report it. Instead,
+		 * we're trying to reschedule.
+		 */
+		if (__ieee80211_request_sched_scan_start(sched_scan_sdata,
+							 local->sched_scan_req))
+			sched_scan_stopped = true;
+	mutex_unlock(&local->mtx);
+
+	if (sched_scan_stopped)
+		cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy);
+
+	/*
 	 * If this is for hw restart things are still running.
 	 * We may want to change that later, however.
 	 */
@@ -1754,6 +1847,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 #else
 	WARN_ON(1);
 #endif
+
 	return 0;
 }
 
@@ -2238,11 +2332,11 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		ri.nss = status->vht_nss;
 		if (status->flag & RX_FLAG_40MHZ)
 			ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
-		if (status->flag & RX_FLAG_80MHZ)
+		if (status->vht_flag & RX_VHT_FLAG_80MHZ)
 			ri.flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
-		if (status->flag & RX_FLAG_80P80MHZ)
+		if (status->vht_flag & RX_VHT_FLAG_80P80MHZ)
 			ri.flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH;
-		if (status->flag & RX_FLAG_160MHZ)
+		if (status->vht_flag & RX_VHT_FLAG_160MHZ)
 			ri.flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
 		if (status->flag & RX_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
@@ -2281,9 +2375,14 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 	struct ieee80211_sub_if_data *sdata;
 	struct cfg80211_chan_def chandef;
 
+	mutex_lock(&local->mtx);
 	mutex_lock(&local->iflist_mtx);
 	list_for_each_entry(sdata, &local->interfaces, list) {
-		cancel_delayed_work_sync(&sdata->dfs_cac_timer_work);
+		/* it might be waiting for the local->mtx, but then
+		 * by the time it gets it, sdata->wdev.cac_started
+		 * will no longer be true
+		 */
+		cancel_delayed_work(&sdata->dfs_cac_timer_work);
 
 		if (sdata->wdev.cac_started) {
 			chandef = sdata->vif.bss_conf.chandef;
@@ -2295,6 +2394,7 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 		}
 	}
 	mutex_unlock(&local->iflist_mtx);
+	mutex_unlock(&local->mtx);
 }
 
 void ieee80211_dfs_radar_detected_work(struct work_struct *work)
@@ -2554,3 +2654,302 @@ int ieee80211_cs_headroom(struct ieee80211_local *local,
 
 	return headroom;
 }
+
+static bool
+ieee80211_extend_noa_desc(struct ieee80211_noa_data *data, u32 tsf, int i)
+{
+	s32 end = data->desc[i].start + data->desc[i].duration - (tsf + 1);
+	int skip;
+
+	if (end > 0)
+		return false;
+
+	/* End time is in the past, check for repetitions */
+	skip = DIV_ROUND_UP(-end, data->desc[i].interval);
+	if (data->count[i] < 255) {
+		if (data->count[i] <= skip) {
+			data->count[i] = 0;
+			return false;
+		}
+
+		data->count[i] -= skip;
+	}
+
+	data->desc[i].start += skip * data->desc[i].interval;
+
+	return true;
+}
+
+static bool
+ieee80211_extend_absent_time(struct ieee80211_noa_data *data, u32 tsf,
+			     s32 *offset)
+{
+	bool ret = false;
+	int i;
+
+	for (i = 0; i < IEEE80211_P2P_NOA_DESC_MAX; i++) {
+		s32 cur;
+
+		if (!data->count[i])
+			continue;
+
+		if (ieee80211_extend_noa_desc(data, tsf + *offset, i))
+			ret = true;
+
+		cur = data->desc[i].start - tsf;
+		if (cur > *offset)
+			continue;
+
+		cur = data->desc[i].start + data->desc[i].duration - tsf;
+		if (cur > *offset)
+			*offset = cur;
+	}
+
+	return ret;
+}
+
+static u32
+ieee80211_get_noa_absent_time(struct ieee80211_noa_data *data, u32 tsf)
+{
+	s32 offset = 0;
+	int tries = 0;
+	/*
+	 * arbitrary limit, used to avoid infinite loops when combined NoA
+	 * descriptors cover the full time period.
+	 */
+	int max_tries = 5;
+
+	ieee80211_extend_absent_time(data, tsf, &offset);
+	do {
+		if (!ieee80211_extend_absent_time(data, tsf, &offset))
+			break;
+
+		tries++;
+	} while (tries < max_tries);
+
+	return offset;
+}
+
+void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf)
+{
+	u32 next_offset = BIT(31) - 1;
+	int i;
+
+	data->absent = 0;
+	data->has_next_tsf = false;
+	for (i = 0; i < IEEE80211_P2P_NOA_DESC_MAX; i++) {
+		s32 start;
+
+		if (!data->count[i])
+			continue;
+
+		ieee80211_extend_noa_desc(data, tsf, i);
+		start = data->desc[i].start - tsf;
+		if (start <= 0)
+			data->absent |= BIT(i);
+
+		if (next_offset > start)
+			next_offset = start;
+
+		data->has_next_tsf = true;
+	}
+
+	if (data->absent)
+		next_offset = ieee80211_get_noa_absent_time(data, tsf);
+
+	data->next_tsf = tsf + next_offset;
+}
+EXPORT_SYMBOL(ieee80211_update_p2p_noa);
+
+int ieee80211_parse_p2p_noa(const struct ieee80211_p2p_noa_attr *attr,
+			    struct ieee80211_noa_data *data, u32 tsf)
+{
+	int ret = 0;
+	int i;
+
+	memset(data, 0, sizeof(*data));
+
+	for (i = 0; i < IEEE80211_P2P_NOA_DESC_MAX; i++) {
+		const struct ieee80211_p2p_noa_desc *desc = &attr->desc[i];
+
+		if (!desc->count || !desc->duration)
+			continue;
+
+		data->count[i] = desc->count;
+		data->desc[i].start = le32_to_cpu(desc->start_time);
+		data->desc[i].duration = le32_to_cpu(desc->duration);
+		data->desc[i].interval = le32_to_cpu(desc->interval);
+
+		if (data->count[i] > 1 &&
+		    data->desc[i].interval < data->desc[i].duration)
+			continue;
+
+		ieee80211_extend_noa_desc(data, tsf, i);
+		ret++;
+	}
+
+	if (ret)
+		ieee80211_update_p2p_noa(data, tsf);
+
+	return ret;
+}
+EXPORT_SYMBOL(ieee80211_parse_p2p_noa);
+
+void ieee80211_recalc_dtim(struct ieee80211_local *local,
+			   struct ieee80211_sub_if_data *sdata)
+{
+	u64 tsf = drv_get_tsf(local, sdata);
+	u64 dtim_count = 0;
+	u16 beacon_int = sdata->vif.bss_conf.beacon_int * 1024;
+	u8 dtim_period = sdata->vif.bss_conf.dtim_period;
+	struct ps_data *ps;
+	u8 bcns_from_dtim;
+
+	if (tsf == -1ULL || !beacon_int || !dtim_period)
+		return;
+
+	if (sdata->vif.type == NL80211_IFTYPE_AP ||
+	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+		if (!sdata->bss)
+			return;
+
+		ps = &sdata->bss->ps;
+	} else if (ieee80211_vif_is_mesh(&sdata->vif)) {
+		ps = &sdata->u.mesh.ps;
+	} else {
+		return;
+	}
+
+	/*
+	 * actually finds last dtim_count, mac80211 will update in
+	 * __beacon_add_tim().
+	 * dtim_count = dtim_period - (tsf / bcn_int) % dtim_period
+	 */
+	do_div(tsf, beacon_int);
+	bcns_from_dtim = do_div(tsf, dtim_period);
+	/* just had a DTIM */
+	if (!bcns_from_dtim)
+		dtim_count = 0;
+	else
+		dtim_count = dtim_period - bcns_from_dtim;
+
+	ps->dtim_count = dtim_count;
+}
+
+int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
+				 const struct cfg80211_chan_def *chandef,
+				 enum ieee80211_chanctx_mode chanmode,
+				 u8 radar_detect)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_sub_if_data *sdata_iter;
+	enum nl80211_iftype iftype = sdata->wdev.iftype;
+	int num[NUM_NL80211_IFTYPES];
+	struct ieee80211_chanctx *ctx;
+	int num_different_channels = 0;
+	int total = 1;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	if (WARN_ON(hweight32(radar_detect) > 1))
+		return -EINVAL;
+
+	if (WARN_ON(chandef && chanmode == IEEE80211_CHANCTX_SHARED &&
+		    !chandef->chan))
+		return -EINVAL;
+
+	if (chandef)
+		num_different_channels = 1;
+
+	if (WARN_ON(iftype >= NUM_NL80211_IFTYPES))
+		return -EINVAL;
+
+	/* Always allow software iftypes */
+	if (local->hw.wiphy->software_iftypes & BIT(iftype)) {
+		if (radar_detect)
+			return -EINVAL;
+		return 0;
+	}
+
+	memset(num, 0, sizeof(num));
+
+	if (iftype != NL80211_IFTYPE_UNSPECIFIED)
+		num[iftype] = 1;
+
+	list_for_each_entry(ctx, &local->chanctx_list, list) {
+		if (ctx->conf.radar_enabled)
+			radar_detect |= BIT(ctx->conf.def.width);
+		if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) {
+			num_different_channels++;
+			continue;
+		}
+		if (chandef && chanmode == IEEE80211_CHANCTX_SHARED &&
+		    cfg80211_chandef_compatible(chandef,
+						&ctx->conf.def))
+			continue;
+		num_different_channels++;
+	}
+
+	list_for_each_entry_rcu(sdata_iter, &local->interfaces, list) {
+		struct wireless_dev *wdev_iter;
+
+		wdev_iter = &sdata_iter->wdev;
+
+		if (sdata_iter == sdata ||
+		    rcu_access_pointer(sdata_iter->vif.chanctx_conf) == NULL ||
+		    local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype))
+			continue;
+
+		num[wdev_iter->iftype]++;
+		total++;
+	}
+
+	if (total == 1 && !radar_detect)
+		return 0;
+
+	return cfg80211_check_combinations(local->hw.wiphy,
+					   num_different_channels,
+					   radar_detect, num);
+}
+
+static void
+ieee80211_iter_max_chans(const struct ieee80211_iface_combination *c,
+			 void *data)
+{
+	u32 *max_num_different_channels = data;
+
+	*max_num_different_channels = max(*max_num_different_channels,
+					  c->num_different_channels);
+}
+
+int ieee80211_max_num_channels(struct ieee80211_local *local)
+{
+	struct ieee80211_sub_if_data *sdata;
+	int num[NUM_NL80211_IFTYPES] = {};
+	struct ieee80211_chanctx *ctx;
+	int num_different_channels = 0;
+	u8 radar_detect = 0;
+	u32 max_num_different_channels = 1;
+	int err;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(ctx, &local->chanctx_list, list) {
+		num_different_channels++;
+
+		if (ctx->conf.radar_enabled)
+			radar_detect |= BIT(ctx->conf.def.width);
+	}
+
+	list_for_each_entry_rcu(sdata, &local->interfaces, list)
+		num[sdata->wdev.iftype]++;
+
+	err = cfg80211_iter_combinations(local->hw.wiphy,
+					 num_different_channels, radar_detect,
+					 num, ieee80211_iter_max_chans,
+					 &max_num_different_channels);
+	if (err < 0)
+		return err;
+
+	return max_num_different_channels;
+}
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index d75f35c6e1a..9265adfdabf 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -129,9 +129,12 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 	if (!vht_cap_ie || !sband->vht_cap.vht_supported)
 		return;
 
-	/* A VHT STA must support 40 MHz */
-	if (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40))
-		return;
+	/*
+	 * A VHT STA must support 40 MHz, but if we verify that here
+	 * then we break a few things - some APs (e.g. Netgear R6300v2
+	 * and others based on the BCM4360 chipset) will unset this
+	 * capability bit when operating in 20 MHz.
+	 */
 
 	vht_cap->vht_supported = true;
 
@@ -349,9 +352,9 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta)
 	sta->sta.rx_nss = max_t(u8, 1, ht_rx_nss);
 }
 
-void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
-				 struct sta_info *sta, u8 opmode,
-				 enum ieee80211_band band, bool nss_only)
+u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
+				  struct sta_info *sta, u8 opmode,
+				  enum ieee80211_band band, bool nss_only)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_supported_band *sband;
@@ -363,7 +366,7 @@ void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
 
 	/* ignore - no support for BF yet */
 	if (opmode & IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF)
-		return;
+		return 0;
 
 	nss = opmode & IEEE80211_OPMODE_NOTIF_RX_NSS_MASK;
 	nss >>= IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT;
@@ -375,7 +378,7 @@ void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (nss_only)
-		goto change;
+		return changed;
 
 	switch (opmode & IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK) {
 	case IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ:
@@ -398,7 +401,19 @@ void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
 		changed |= IEEE80211_RC_BW_CHANGED;
 	}
 
- change:
-	if (changed)
+	return changed;
+}
+
+void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
+				 struct sta_info *sta, u8 opmode,
+				 enum ieee80211_band band, bool nss_only)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band];
+
+	u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode,
+						    band, nss_only);
+
+	if (changed > 0)
 		rate_control_rate_update(local, sband, sta, changed);
 }
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index afba19cb6f8..d51422c778d 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -106,6 +106,7 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 	struct sta_info *sta = NULL;
 	const u8 *ra = NULL;
 	bool qos = false;
+	struct mac80211_qos_map *qos_map;
 
 	if (local->hw.queues < IEEE80211_NUM_ACS || skb->len < 6) {
 		skb->priority = 0; /* required for correct WPA/11i MIC */
@@ -153,9 +154,18 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 		return IEEE80211_AC_BE;
 	}
 
+	if (skb->protocol == sdata->control_port_protocol) {
+		skb->priority = 7;
+		return ieee80211_downgrade_queue(sdata, skb);
+	}
+
 	/* use the data classifier to determine what 802.1d tag the
 	 * data frame has */
-	skb->priority = cfg80211_classify8021d(skb);
+	rcu_read_lock();
+	qos_map = rcu_dereference(sdata->qos_map);
+	skb->priority = cfg80211_classify8021d(skb, qos_map ?
+					       &qos_map->qos_map : NULL);
+	rcu_read_unlock();
 
 	return ieee80211_downgrade_queue(sdata, skb);
 }
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 7313d379c0d..9b3dcc20114 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -127,7 +127,7 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx)
 		 * APs with pairwise keys should never receive Michael MIC
 		 * errors for non-zero keyidx because these are reserved for
 		 * group keys and only the AP is sending real multicast
-		 * frames in the BSS. (
+		 * frames in the BSS.
 		 */
 		return RX_DROP_UNUSABLE;
 	}
@@ -301,8 +301,7 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx)
 }
 
 
-static void ccmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *b_0, u8 *aad,
-				int encrypted)
+static void ccmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *b_0, u8 *aad)
 {
 	__le16 mask_fc;
 	int a4_included, mgmt;
@@ -407,7 +406,10 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
 
 	if (info->control.hw_key &&
 	    !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_GENERATE_IV) &&
-	    !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) {
+	    !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) &&
+	    !((info->control.hw_key->flags &
+	       IEEE80211_KEY_FLAG_GENERATE_IV_MGMT) &&
+	      ieee80211_is_mgmt(hdr->frame_control))) {
 		/*
 		 * hwaccel has no need for preallocated room for CCMP
 		 * header or MIC fields
@@ -456,7 +458,7 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
 		return 0;
 
 	pos += IEEE80211_CCMP_HDR_LEN;
-	ccmp_special_blocks(skb, pn, b_0, aad, 0);
+	ccmp_special_blocks(skb, pn, b_0, aad);
 	ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len,
 				  skb_put(skb, IEEE80211_CCMP_MIC_LEN));
 
@@ -495,7 +497,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx)
 	hdrlen = ieee80211_hdrlen(hdr->frame_control);
 
 	if (!ieee80211_is_data(hdr->frame_control) &&
-	    !ieee80211_is_robust_mgmt_frame(hdr))
+	    !ieee80211_is_robust_mgmt_frame(skb))
 		return RX_CONTINUE;
 
 	data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN -
@@ -524,7 +526,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx)
 		u8 aad[2 * AES_BLOCK_SIZE];
 		u8 b_0[AES_BLOCK_SIZE];
 		/* hardware didn't decrypt/verify MIC */
-		ccmp_special_blocks(skb, pn, b_0, aad, 1);
+		ccmp_special_blocks(skb, pn, b_0, aad);
 
 		if (ieee80211_aes_ccm_decrypt(
 			    key->u.ccmp.tfm, b_0, aad,
diff --git a/net/mac802154/Kconfig b/net/mac802154/Kconfig
index b33dd76d430..1818a99b308 100644
--- a/net/mac802154/Kconfig
+++ b/net/mac802154/Kconfig
@@ -2,6 +2,10 @@ config MAC802154
 	tristate "Generic IEEE 802.15.4 Soft Networking Stack (mac802154)"
 	depends on IEEE802154
 	select CRC_CCITT
+	select CRYPTO_AUTHENC
+	select CRYPTO_CCM
+	select CRYPTO_CTR
+	select CRYPTO_AES
 	---help---
 	  This option enables the hardware independent IEEE 802.15.4
 	  networking stack for SoftMAC devices (the ones implementing
diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile
index 57cf5d1a2e4..9723d6f3f3e 100644
--- a/net/mac802154/Makefile
+++ b/net/mac802154/Makefile
@@ -1,2 +1,5 @@
 obj-$(CONFIG_MAC802154)	+= mac802154.o
-mac802154-objs		:= ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o wpan.o
+mac802154-objs		:= ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o \
+			   monitor.o wpan.o llsec.o
+
+ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c
index 52ae6646a41..2cf66d885e6 100644
--- a/net/mac802154/ieee802154_dev.c
+++ b/net/mac802154/ieee802154_dev.c
@@ -27,6 +27,7 @@
 #include <net/netlink.h>
 #include <linux/nl802154.h>
 #include <net/mac802154.h>
+#include <net/ieee802154_netdev.h>
 #include <net/route.h>
 #include <net/wpan-phy.h>
 
@@ -35,9 +36,28 @@
 int mac802154_slave_open(struct net_device *dev)
 {
 	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct mac802154_sub_if_data *subif;
 	struct mac802154_priv *ipriv = priv->hw;
 	int res = 0;
 
+	ASSERT_RTNL();
+
+	if (priv->type == IEEE802154_DEV_WPAN) {
+		mutex_lock(&priv->hw->slaves_mtx);
+		list_for_each_entry(subif, &priv->hw->slaves, list) {
+			if (subif != priv && subif->type == priv->type &&
+			    subif->running) {
+				mutex_unlock(&priv->hw->slaves_mtx);
+				return -EBUSY;
+			}
+		}
+		mutex_unlock(&priv->hw->slaves_mtx);
+	}
+
+	mutex_lock(&priv->hw->slaves_mtx);
+	priv->running = true;
+	mutex_unlock(&priv->hw->slaves_mtx);
+
 	if (ipriv->open_count++ == 0) {
 		res = ipriv->ops->start(&ipriv->hw);
 		WARN_ON(res);
@@ -46,7 +66,9 @@ int mac802154_slave_open(struct net_device *dev)
 	}
 
 	if (ipriv->ops->ieee_addr) {
-		res = ipriv->ops->ieee_addr(&ipriv->hw, dev->dev_addr);
+		__le64 addr = ieee802154_devaddr_from_raw(dev->dev_addr);
+
+		res = ipriv->ops->ieee_addr(&ipriv->hw, addr);
 		WARN_ON(res);
 		if (res)
 			goto err;
@@ -66,8 +88,14 @@ int mac802154_slave_close(struct net_device *dev)
 	struct mac802154_sub_if_data *priv = netdev_priv(dev);
 	struct mac802154_priv *ipriv = priv->hw;
 
+	ASSERT_RTNL();
+
 	netif_stop_queue(dev);
 
+	mutex_lock(&priv->hw->slaves_mtx);
+	priv->running = false;
+	mutex_unlock(&priv->hw->slaves_mtx);
+
 	if (!--ipriv->open_count)
 		ipriv->ops->stop(&ipriv->hw);
 
@@ -165,6 +193,49 @@ err:
 	return ERR_PTR(err);
 }
 
+static int mac802154_set_txpower(struct wpan_phy *phy, int db)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	return priv->ops->set_txpower(&priv->hw, db);
+}
+
+static int mac802154_set_lbt(struct wpan_phy *phy, bool on)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	return priv->ops->set_lbt(&priv->hw, on);
+}
+
+static int mac802154_set_cca_mode(struct wpan_phy *phy, u8 mode)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	return priv->ops->set_cca_mode(&priv->hw, mode);
+}
+
+static int mac802154_set_cca_ed_level(struct wpan_phy *phy, s32 level)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	return priv->ops->set_cca_ed_level(&priv->hw, level);
+}
+
+static int mac802154_set_csma_params(struct wpan_phy *phy, u8 min_be,
+				     u8 max_be, u8 retries)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	return priv->ops->set_csma_params(&priv->hw, min_be, max_be, retries);
+}
+
+static int mac802154_set_frame_retries(struct wpan_phy *phy, s8 retries)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	return priv->ops->set_frame_retries(&priv->hw, retries);
+}
+
 struct ieee802154_dev *
 ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops)
 {
@@ -242,6 +313,18 @@ int ieee802154_register_device(struct ieee802154_dev *dev)
 
 	priv->phy->add_iface = mac802154_add_iface;
 	priv->phy->del_iface = mac802154_del_iface;
+	if (priv->ops->set_txpower)
+		priv->phy->set_txpower = mac802154_set_txpower;
+	if (priv->ops->set_lbt)
+		priv->phy->set_lbt = mac802154_set_lbt;
+	if (priv->ops->set_cca_mode)
+		priv->phy->set_cca_mode = mac802154_set_cca_mode;
+	if (priv->ops->set_cca_ed_level)
+		priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level;
+	if (priv->ops->set_csma_params)
+		priv->phy->set_csma_params = mac802154_set_csma_params;
+	if (priv->ops->set_frame_retries)
+		priv->phy->set_frame_retries = mac802154_set_frame_retries;
 
 	rc = wpan_phy_register(priv->phy);
 	if (rc < 0)
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
new file mode 100644
index 00000000000..1456f73b02b
--- /dev/null
+++ b/net/mac802154/llsec.c
@@ -0,0 +1,1070 @@
+/*
+ * Copyright (C) 2014 Fraunhofer ITWM
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Written by:
+ * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
+ */
+
+#include <linux/err.h>
+#include <linux/bug.h>
+#include <linux/completion.h>
+#include <net/ieee802154.h>
+#include <crypto/algapi.h>
+
+#include "mac802154.h"
+#include "llsec.h"
+
+static void llsec_key_put(struct mac802154_llsec_key *key);
+static bool llsec_key_id_equal(const struct ieee802154_llsec_key_id *a,
+			       const struct ieee802154_llsec_key_id *b);
+
+static void llsec_dev_free(struct mac802154_llsec_device *dev);
+
+void mac802154_llsec_init(struct mac802154_llsec *sec)
+{
+	memset(sec, 0, sizeof(*sec));
+
+	memset(&sec->params.default_key_source, 0xFF, IEEE802154_ADDR_LEN);
+
+	INIT_LIST_HEAD(&sec->table.security_levels);
+	INIT_LIST_HEAD(&sec->table.devices);
+	INIT_LIST_HEAD(&sec->table.keys);
+	hash_init(sec->devices_short);
+	hash_init(sec->devices_hw);
+	rwlock_init(&sec->lock);
+}
+
+void mac802154_llsec_destroy(struct mac802154_llsec *sec)
+{
+	struct ieee802154_llsec_seclevel *sl, *sn;
+	struct ieee802154_llsec_device *dev, *dn;
+	struct ieee802154_llsec_key_entry *key, *kn;
+
+	list_for_each_entry_safe(sl, sn, &sec->table.security_levels, list) {
+		struct mac802154_llsec_seclevel *msl;
+
+		msl = container_of(sl, struct mac802154_llsec_seclevel, level);
+		list_del(&sl->list);
+		kfree(msl);
+	}
+
+	list_for_each_entry_safe(dev, dn, &sec->table.devices, list) {
+		struct mac802154_llsec_device *mdev;
+
+		mdev = container_of(dev, struct mac802154_llsec_device, dev);
+		list_del(&dev->list);
+		llsec_dev_free(mdev);
+	}
+
+	list_for_each_entry_safe(key, kn, &sec->table.keys, list) {
+		struct mac802154_llsec_key *mkey;
+
+		mkey = container_of(key->key, struct mac802154_llsec_key, key);
+		list_del(&key->list);
+		llsec_key_put(mkey);
+		kfree(key);
+	}
+}
+
+
+
+int mac802154_llsec_get_params(struct mac802154_llsec *sec,
+			       struct ieee802154_llsec_params *params)
+{
+	read_lock_bh(&sec->lock);
+	*params = sec->params;
+	read_unlock_bh(&sec->lock);
+
+	return 0;
+}
+
+int mac802154_llsec_set_params(struct mac802154_llsec *sec,
+			       const struct ieee802154_llsec_params *params,
+			       int changed)
+{
+	write_lock_bh(&sec->lock);
+
+	if (changed & IEEE802154_LLSEC_PARAM_ENABLED)
+		sec->params.enabled = params->enabled;
+	if (changed & IEEE802154_LLSEC_PARAM_FRAME_COUNTER)
+		sec->params.frame_counter = params->frame_counter;
+	if (changed & IEEE802154_LLSEC_PARAM_OUT_LEVEL)
+		sec->params.out_level = params->out_level;
+	if (changed & IEEE802154_LLSEC_PARAM_OUT_KEY)
+		sec->params.out_key = params->out_key;
+	if (changed & IEEE802154_LLSEC_PARAM_KEY_SOURCE)
+		sec->params.default_key_source = params->default_key_source;
+	if (changed & IEEE802154_LLSEC_PARAM_PAN_ID)
+		sec->params.pan_id = params->pan_id;
+	if (changed & IEEE802154_LLSEC_PARAM_HWADDR)
+		sec->params.hwaddr = params->hwaddr;
+	if (changed & IEEE802154_LLSEC_PARAM_COORD_HWADDR)
+		sec->params.coord_hwaddr = params->coord_hwaddr;
+	if (changed & IEEE802154_LLSEC_PARAM_COORD_SHORTADDR)
+		sec->params.coord_shortaddr = params->coord_shortaddr;
+
+	write_unlock_bh(&sec->lock);
+
+	return 0;
+}
+
+
+
+static struct mac802154_llsec_key*
+llsec_key_alloc(const struct ieee802154_llsec_key *template)
+{
+	const int authsizes[3] = { 4, 8, 16 };
+	struct mac802154_llsec_key *key;
+	int i;
+
+	key = kzalloc(sizeof(*key), GFP_KERNEL);
+	if (!key)
+		return NULL;
+
+	kref_init(&key->ref);
+	key->key = *template;
+
+	BUILD_BUG_ON(ARRAY_SIZE(authsizes) != ARRAY_SIZE(key->tfm));
+
+	for (i = 0; i < ARRAY_SIZE(key->tfm); i++) {
+		key->tfm[i] = crypto_alloc_aead("ccm(aes)", 0,
+						CRYPTO_ALG_ASYNC);
+		if (!key->tfm[i])
+			goto err_tfm;
+		if (crypto_aead_setkey(key->tfm[i], template->key,
+				       IEEE802154_LLSEC_KEY_SIZE))
+			goto err_tfm;
+		if (crypto_aead_setauthsize(key->tfm[i], authsizes[i]))
+			goto err_tfm;
+	}
+
+	key->tfm0 = crypto_alloc_blkcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (!key->tfm0)
+		goto err_tfm;
+
+	if (crypto_blkcipher_setkey(key->tfm0, template->key,
+				    IEEE802154_LLSEC_KEY_SIZE))
+		goto err_tfm0;
+
+	return key;
+
+err_tfm0:
+	crypto_free_blkcipher(key->tfm0);
+err_tfm:
+	for (i = 0; i < ARRAY_SIZE(key->tfm); i++)
+		if (key->tfm[i])
+			crypto_free_aead(key->tfm[i]);
+
+	kfree(key);
+	return NULL;
+}
+
+static void llsec_key_release(struct kref *ref)
+{
+	struct mac802154_llsec_key *key;
+	int i;
+
+	key = container_of(ref, struct mac802154_llsec_key, ref);
+
+	for (i = 0; i < ARRAY_SIZE(key->tfm); i++)
+		crypto_free_aead(key->tfm[i]);
+
+	crypto_free_blkcipher(key->tfm0);
+	kfree(key);
+}
+
+static struct mac802154_llsec_key*
+llsec_key_get(struct mac802154_llsec_key *key)
+{
+	kref_get(&key->ref);
+	return key;
+}
+
+static void llsec_key_put(struct mac802154_llsec_key *key)
+{
+	kref_put(&key->ref, llsec_key_release);
+}
+
+static bool llsec_key_id_equal(const struct ieee802154_llsec_key_id *a,
+			       const struct ieee802154_llsec_key_id *b)
+{
+	if (a->mode != b->mode)
+		return false;
+
+	if (a->mode == IEEE802154_SCF_KEY_IMPLICIT)
+		return ieee802154_addr_equal(&a->device_addr, &b->device_addr);
+
+	if (a->id != b->id)
+		return false;
+
+	switch (a->mode) {
+	case IEEE802154_SCF_KEY_INDEX:
+		return true;
+	case IEEE802154_SCF_KEY_SHORT_INDEX:
+		return a->short_source == b->short_source;
+	case IEEE802154_SCF_KEY_HW_INDEX:
+		return a->extended_source == b->extended_source;
+	}
+
+	return false;
+}
+
+int mac802154_llsec_key_add(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_key_id *id,
+			    const struct ieee802154_llsec_key *key)
+{
+	struct mac802154_llsec_key *mkey = NULL;
+	struct ieee802154_llsec_key_entry *pos, *new;
+
+	if (!(key->frame_types & (1 << IEEE802154_FC_TYPE_MAC_CMD)) &&
+	    key->cmd_frame_ids)
+		return -EINVAL;
+
+	list_for_each_entry(pos, &sec->table.keys, list) {
+		if (llsec_key_id_equal(&pos->id, id))
+			return -EEXIST;
+
+		if (memcmp(pos->key->key, key->key,
+			   IEEE802154_LLSEC_KEY_SIZE))
+			continue;
+
+		mkey = container_of(pos->key, struct mac802154_llsec_key, key);
+
+		/* Don't allow multiple instances of the same AES key to have
+		 * different allowed frame types/command frame ids, as this is
+		 * not possible in the 802.15.4 PIB.
+		 */
+		if (pos->key->frame_types != key->frame_types ||
+		    pos->key->cmd_frame_ids != key->cmd_frame_ids)
+			return -EEXIST;
+
+		break;
+	}
+
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	if (!mkey)
+		mkey = llsec_key_alloc(key);
+	else
+		mkey = llsec_key_get(mkey);
+
+	if (!mkey)
+		goto fail;
+
+	new->id = *id;
+	new->key = &mkey->key;
+
+	list_add_rcu(&new->list, &sec->table.keys);
+
+	return 0;
+
+fail:
+	kfree(new);
+	return -ENOMEM;
+}
+
+int mac802154_llsec_key_del(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_key_id *key)
+{
+	struct ieee802154_llsec_key_entry *pos;
+
+	list_for_each_entry(pos, &sec->table.keys, list) {
+		struct mac802154_llsec_key *mkey;
+
+		mkey = container_of(pos->key, struct mac802154_llsec_key, key);
+
+		if (llsec_key_id_equal(&pos->id, key)) {
+			list_del_rcu(&pos->list);
+			llsec_key_put(mkey);
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+
+
+static bool llsec_dev_use_shortaddr(__le16 short_addr)
+{
+	return short_addr != cpu_to_le16(IEEE802154_ADDR_UNDEF) &&
+		short_addr != cpu_to_le16(0xffff);
+}
+
+static u32 llsec_dev_hash_short(__le16 short_addr, __le16 pan_id)
+{
+	return ((__force u16) short_addr) << 16 | (__force u16) pan_id;
+}
+
+static u64 llsec_dev_hash_long(__le64 hwaddr)
+{
+	return (__force u64) hwaddr;
+}
+
+static struct mac802154_llsec_device*
+llsec_dev_find_short(struct mac802154_llsec *sec, __le16 short_addr,
+		     __le16 pan_id)
+{
+	struct mac802154_llsec_device *dev;
+	u32 key = llsec_dev_hash_short(short_addr, pan_id);
+
+	hash_for_each_possible_rcu(sec->devices_short, dev, bucket_s, key) {
+		if (dev->dev.short_addr == short_addr &&
+		    dev->dev.pan_id == pan_id)
+			return dev;
+	}
+
+	return NULL;
+}
+
+static struct mac802154_llsec_device*
+llsec_dev_find_long(struct mac802154_llsec *sec, __le64 hwaddr)
+{
+	struct mac802154_llsec_device *dev;
+	u64 key = llsec_dev_hash_long(hwaddr);
+
+	hash_for_each_possible_rcu(sec->devices_hw, dev, bucket_hw, key) {
+		if (dev->dev.hwaddr == hwaddr)
+			return dev;
+	}
+
+	return NULL;
+}
+
+static void llsec_dev_free(struct mac802154_llsec_device *dev)
+{
+	struct ieee802154_llsec_device_key *pos, *pn;
+	struct mac802154_llsec_device_key *devkey;
+
+	list_for_each_entry_safe(pos, pn, &dev->dev.keys, list) {
+		devkey = container_of(pos, struct mac802154_llsec_device_key,
+				      devkey);
+
+		list_del(&pos->list);
+		kfree(devkey);
+	}
+
+	kfree(dev);
+}
+
+int mac802154_llsec_dev_add(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_device *dev)
+{
+	struct mac802154_llsec_device *entry;
+	u32 skey = llsec_dev_hash_short(dev->short_addr, dev->pan_id);
+	u64 hwkey = llsec_dev_hash_long(dev->hwaddr);
+
+	BUILD_BUG_ON(sizeof(hwkey) != IEEE802154_ADDR_LEN);
+
+	if ((llsec_dev_use_shortaddr(dev->short_addr) &&
+	     llsec_dev_find_short(sec, dev->short_addr, dev->pan_id)) ||
+	     llsec_dev_find_long(sec, dev->hwaddr))
+		return -EEXIST;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->dev = *dev;
+	spin_lock_init(&entry->lock);
+	INIT_LIST_HEAD(&entry->dev.keys);
+
+	if (llsec_dev_use_shortaddr(dev->short_addr))
+		hash_add_rcu(sec->devices_short, &entry->bucket_s, skey);
+	else
+		INIT_HLIST_NODE(&entry->bucket_s);
+
+	hash_add_rcu(sec->devices_hw, &entry->bucket_hw, hwkey);
+	list_add_tail_rcu(&entry->dev.list, &sec->table.devices);
+
+	return 0;
+}
+
+static void llsec_dev_free_rcu(struct rcu_head *rcu)
+{
+	llsec_dev_free(container_of(rcu, struct mac802154_llsec_device, rcu));
+}
+
+int mac802154_llsec_dev_del(struct mac802154_llsec *sec, __le64 device_addr)
+{
+	struct mac802154_llsec_device *pos;
+
+	pos = llsec_dev_find_long(sec, device_addr);
+	if (!pos)
+		return -ENOENT;
+
+	hash_del_rcu(&pos->bucket_s);
+	hash_del_rcu(&pos->bucket_hw);
+	call_rcu(&pos->rcu, llsec_dev_free_rcu);
+
+	return 0;
+}
+
+
+
+static struct mac802154_llsec_device_key*
+llsec_devkey_find(struct mac802154_llsec_device *dev,
+		  const struct ieee802154_llsec_key_id *key)
+{
+	struct ieee802154_llsec_device_key *devkey;
+
+	list_for_each_entry_rcu(devkey, &dev->dev.keys, list) {
+		if (!llsec_key_id_equal(key, &devkey->key_id))
+			continue;
+
+		return container_of(devkey, struct mac802154_llsec_device_key,
+				    devkey);
+	}
+
+	return NULL;
+}
+
+int mac802154_llsec_devkey_add(struct mac802154_llsec *sec,
+			       __le64 dev_addr,
+			       const struct ieee802154_llsec_device_key *key)
+{
+	struct mac802154_llsec_device *dev;
+	struct mac802154_llsec_device_key *devkey;
+
+	dev = llsec_dev_find_long(sec, dev_addr);
+
+	if (!dev)
+		return -ENOENT;
+
+	if (llsec_devkey_find(dev, &key->key_id))
+		return -EEXIST;
+
+	devkey = kmalloc(sizeof(*devkey), GFP_KERNEL);
+	if (!devkey)
+		return -ENOMEM;
+
+	devkey->devkey = *key;
+	list_add_tail_rcu(&devkey->devkey.list, &dev->dev.keys);
+	return 0;
+}
+
+int mac802154_llsec_devkey_del(struct mac802154_llsec *sec,
+			       __le64 dev_addr,
+			       const struct ieee802154_llsec_device_key *key)
+{
+	struct mac802154_llsec_device *dev;
+	struct mac802154_llsec_device_key *devkey;
+
+	dev = llsec_dev_find_long(sec, dev_addr);
+
+	if (!dev)
+		return -ENOENT;
+
+	devkey = llsec_devkey_find(dev, &key->key_id);
+	if (!devkey)
+		return -ENOENT;
+
+	list_del_rcu(&devkey->devkey.list);
+	kfree_rcu(devkey, rcu);
+	return 0;
+}
+
+
+
+static struct mac802154_llsec_seclevel*
+llsec_find_seclevel(const struct mac802154_llsec *sec,
+		    const struct ieee802154_llsec_seclevel *sl)
+{
+	struct ieee802154_llsec_seclevel *pos;
+
+	list_for_each_entry(pos, &sec->table.security_levels, list) {
+		if (pos->frame_type != sl->frame_type ||
+		    (pos->frame_type == IEEE802154_FC_TYPE_MAC_CMD &&
+		     pos->cmd_frame_id != sl->cmd_frame_id) ||
+		    pos->device_override != sl->device_override ||
+		    pos->sec_levels != sl->sec_levels)
+			continue;
+
+		return container_of(pos, struct mac802154_llsec_seclevel,
+				    level);
+	}
+
+	return NULL;
+}
+
+int mac802154_llsec_seclevel_add(struct mac802154_llsec *sec,
+				 const struct ieee802154_llsec_seclevel *sl)
+{
+	struct mac802154_llsec_seclevel *entry;
+
+	if (llsec_find_seclevel(sec, sl))
+		return -EEXIST;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->level = *sl;
+
+	list_add_tail_rcu(&entry->level.list, &sec->table.security_levels);
+
+	return 0;
+}
+
+int mac802154_llsec_seclevel_del(struct mac802154_llsec *sec,
+				 const struct ieee802154_llsec_seclevel *sl)
+{
+	struct mac802154_llsec_seclevel *pos;
+
+	pos = llsec_find_seclevel(sec, sl);
+	if (!pos)
+		return -ENOENT;
+
+	list_del_rcu(&pos->level.list);
+	kfree_rcu(pos, rcu);
+
+	return 0;
+}
+
+
+
+static int llsec_recover_addr(struct mac802154_llsec *sec,
+			      struct ieee802154_addr *addr)
+{
+	__le16 caddr = sec->params.coord_shortaddr;
+	addr->pan_id = sec->params.pan_id;
+
+	if (caddr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) {
+		return -EINVAL;
+	} else if (caddr == cpu_to_le16(IEEE802154_ADDR_UNDEF)) {
+		addr->extended_addr = sec->params.coord_hwaddr;
+		addr->mode = IEEE802154_ADDR_LONG;
+	} else {
+		addr->short_addr = sec->params.coord_shortaddr;
+		addr->mode = IEEE802154_ADDR_SHORT;
+	}
+
+	return 0;
+}
+
+static struct mac802154_llsec_key*
+llsec_lookup_key(struct mac802154_llsec *sec,
+		 const struct ieee802154_hdr *hdr,
+		 const struct ieee802154_addr *addr,
+		 struct ieee802154_llsec_key_id *key_id)
+{
+	struct ieee802154_addr devaddr = *addr;
+	u8 key_id_mode = hdr->sec.key_id_mode;
+	struct ieee802154_llsec_key_entry *key_entry;
+	struct mac802154_llsec_key *key;
+
+	if (key_id_mode == IEEE802154_SCF_KEY_IMPLICIT &&
+	    devaddr.mode == IEEE802154_ADDR_NONE) {
+		if (hdr->fc.type == IEEE802154_FC_TYPE_BEACON) {
+			devaddr.extended_addr = sec->params.coord_hwaddr;
+			devaddr.mode = IEEE802154_ADDR_LONG;
+		} else if (llsec_recover_addr(sec, &devaddr) < 0) {
+			return NULL;
+		}
+	}
+
+	list_for_each_entry_rcu(key_entry, &sec->table.keys, list) {
+		const struct ieee802154_llsec_key_id *id = &key_entry->id;
+
+		if (!(key_entry->key->frame_types & BIT(hdr->fc.type)))
+			continue;
+
+		if (id->mode != key_id_mode)
+			continue;
+
+		if (key_id_mode == IEEE802154_SCF_KEY_IMPLICIT) {
+			if (ieee802154_addr_equal(&devaddr, &id->device_addr))
+				goto found;
+		} else {
+			if (id->id != hdr->sec.key_id)
+				continue;
+
+			if ((key_id_mode == IEEE802154_SCF_KEY_INDEX) ||
+			    (key_id_mode == IEEE802154_SCF_KEY_SHORT_INDEX &&
+			     id->short_source == hdr->sec.short_src) ||
+			    (key_id_mode == IEEE802154_SCF_KEY_HW_INDEX &&
+			     id->extended_source == hdr->sec.extended_src))
+				goto found;
+		}
+	}
+
+	return NULL;
+
+found:
+	key = container_of(key_entry->key, struct mac802154_llsec_key, key);
+	if (key_id)
+		*key_id = key_entry->id;
+	return llsec_key_get(key);
+}
+
+
+static void llsec_geniv(u8 iv[16], __le64 addr,
+			const struct ieee802154_sechdr *sec)
+{
+	__be64 addr_bytes = (__force __be64) swab64((__force u64) addr);
+	__be32 frame_counter = (__force __be32) swab32((__force u32) sec->frame_counter);
+
+	iv[0] = 1; /* L' = L - 1 = 1 */
+	memcpy(iv + 1, &addr_bytes, sizeof(addr_bytes));
+	memcpy(iv + 9, &frame_counter, sizeof(frame_counter));
+	iv[13] = sec->level;
+	iv[14] = 0;
+	iv[15] = 1;
+}
+
+static int
+llsec_do_encrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec,
+			const struct ieee802154_hdr *hdr,
+			struct mac802154_llsec_key *key)
+{
+	u8 iv[16];
+	struct scatterlist src;
+	struct blkcipher_desc req = {
+		.tfm = key->tfm0,
+		.info = iv,
+		.flags = 0,
+	};
+
+	llsec_geniv(iv, sec->params.hwaddr, &hdr->sec);
+	sg_init_one(&src, skb->data, skb->len);
+	return crypto_blkcipher_encrypt_iv(&req, &src, &src, skb->len);
+}
+
+static struct crypto_aead*
+llsec_tfm_by_len(struct mac802154_llsec_key *key, int authlen)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(key->tfm); i++)
+		if (crypto_aead_authsize(key->tfm[i]) == authlen)
+			return key->tfm[i];
+
+	BUG();
+}
+
+static int
+llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
+		      const struct ieee802154_hdr *hdr,
+		      struct mac802154_llsec_key *key)
+{
+	u8 iv[16];
+	unsigned char *data;
+	int authlen, assoclen, datalen, rc;
+	struct scatterlist src, assoc[2], dst[2];
+	struct aead_request *req;
+
+	authlen = ieee802154_sechdr_authtag_len(&hdr->sec);
+	llsec_geniv(iv, sec->params.hwaddr, &hdr->sec);
+
+	req = aead_request_alloc(llsec_tfm_by_len(key, authlen), GFP_ATOMIC);
+	if (!req)
+		return -ENOMEM;
+
+	sg_init_table(assoc, 2);
+	sg_set_buf(&assoc[0], skb_mac_header(skb), skb->mac_len);
+	assoclen = skb->mac_len;
+
+	data = skb_mac_header(skb) + skb->mac_len;
+	datalen = skb_tail_pointer(skb) - data;
+
+	if (hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC) {
+		sg_set_buf(&assoc[1], data, 0);
+	} else {
+		sg_set_buf(&assoc[1], data, datalen);
+		assoclen += datalen;
+		datalen = 0;
+	}
+
+	sg_init_one(&src, data, datalen);
+
+	sg_init_table(dst, 2);
+	sg_set_buf(&dst[0], data, datalen);
+	sg_set_buf(&dst[1], skb_put(skb, authlen), authlen);
+
+	aead_request_set_callback(req, 0, NULL, NULL);
+	aead_request_set_assoc(req, assoc, assoclen);
+	aead_request_set_crypt(req, &src, dst, datalen, iv);
+
+	rc = crypto_aead_encrypt(req);
+
+	kfree(req);
+
+	return rc;
+}
+
+static int llsec_do_encrypt(struct sk_buff *skb,
+			    const struct mac802154_llsec *sec,
+			    const struct ieee802154_hdr *hdr,
+			    struct mac802154_llsec_key *key)
+{
+	if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC)
+		return llsec_do_encrypt_unauth(skb, sec, hdr, key);
+	else
+		return llsec_do_encrypt_auth(skb, sec, hdr, key);
+}
+
+int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb)
+{
+	struct ieee802154_hdr hdr;
+	int rc, authlen, hlen;
+	struct mac802154_llsec_key *key;
+	u32 frame_ctr;
+
+	hlen = ieee802154_hdr_pull(skb, &hdr);
+
+	if (hlen < 0 || hdr.fc.type != IEEE802154_FC_TYPE_DATA)
+		return -EINVAL;
+
+	if (!hdr.fc.security_enabled || hdr.sec.level == 0) {
+		skb_push(skb, hlen);
+		return 0;
+	}
+
+	authlen = ieee802154_sechdr_authtag_len(&hdr.sec);
+
+	if (skb->len + hlen + authlen + IEEE802154_MFR_SIZE > IEEE802154_MTU)
+		return -EMSGSIZE;
+
+	rcu_read_lock();
+
+	read_lock_bh(&sec->lock);
+
+	if (!sec->params.enabled) {
+		rc = -EINVAL;
+		goto fail_read;
+	}
+
+	key = llsec_lookup_key(sec, &hdr, &hdr.dest, NULL);
+	if (!key) {
+		rc = -ENOKEY;
+		goto fail_read;
+	}
+
+	read_unlock_bh(&sec->lock);
+
+	write_lock_bh(&sec->lock);
+
+	frame_ctr = be32_to_cpu(sec->params.frame_counter);
+	hdr.sec.frame_counter = cpu_to_le32(frame_ctr);
+	if (frame_ctr == 0xFFFFFFFF) {
+		write_unlock_bh(&sec->lock);
+		llsec_key_put(key);
+		rc = -EOVERFLOW;
+		goto fail;
+	}
+
+	sec->params.frame_counter = cpu_to_be32(frame_ctr + 1);
+
+	write_unlock_bh(&sec->lock);
+
+	rcu_read_unlock();
+
+	skb->mac_len = ieee802154_hdr_push(skb, &hdr);
+	skb_reset_mac_header(skb);
+
+	rc = llsec_do_encrypt(skb, sec, &hdr, key);
+	llsec_key_put(key);
+
+	return rc;
+
+fail_read:
+	read_unlock_bh(&sec->lock);
+fail:
+	rcu_read_unlock();
+	return rc;
+}
+
+
+
+static struct mac802154_llsec_device*
+llsec_lookup_dev(struct mac802154_llsec *sec,
+		 const struct ieee802154_addr *addr)
+{
+	struct ieee802154_addr devaddr = *addr;
+	struct mac802154_llsec_device *dev = NULL;
+
+	if (devaddr.mode == IEEE802154_ADDR_NONE &&
+	    llsec_recover_addr(sec, &devaddr) < 0)
+		return NULL;
+
+	if (devaddr.mode == IEEE802154_ADDR_SHORT) {
+		u32 key = llsec_dev_hash_short(devaddr.short_addr,
+					       devaddr.pan_id);
+
+		hash_for_each_possible_rcu(sec->devices_short, dev,
+					   bucket_s, key) {
+			if (dev->dev.pan_id == devaddr.pan_id &&
+			    dev->dev.short_addr == devaddr.short_addr)
+				return dev;
+		}
+	} else {
+		u64 key = llsec_dev_hash_long(devaddr.extended_addr);
+
+		hash_for_each_possible_rcu(sec->devices_hw, dev,
+					   bucket_hw, key) {
+			if (dev->dev.hwaddr == devaddr.extended_addr)
+				return dev;
+		}
+	}
+
+	return NULL;
+}
+
+static int
+llsec_lookup_seclevel(const struct mac802154_llsec *sec,
+		      u8 frame_type, u8 cmd_frame_id,
+		      struct ieee802154_llsec_seclevel *rlevel)
+{
+	struct ieee802154_llsec_seclevel *level;
+
+	list_for_each_entry_rcu(level, &sec->table.security_levels, list) {
+		if (level->frame_type == frame_type &&
+		    (frame_type != IEEE802154_FC_TYPE_MAC_CMD ||
+		     level->cmd_frame_id == cmd_frame_id)) {
+			*rlevel = *level;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int
+llsec_do_decrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec,
+			const struct ieee802154_hdr *hdr,
+			struct mac802154_llsec_key *key, __le64 dev_addr)
+{
+	u8 iv[16];
+	unsigned char *data;
+	int datalen;
+	struct scatterlist src;
+	struct blkcipher_desc req = {
+		.tfm = key->tfm0,
+		.info = iv,
+		.flags = 0,
+	};
+
+	llsec_geniv(iv, dev_addr, &hdr->sec);
+	data = skb_mac_header(skb) + skb->mac_len;
+	datalen = skb_tail_pointer(skb) - data;
+
+	sg_init_one(&src, data, datalen);
+
+	return crypto_blkcipher_decrypt_iv(&req, &src, &src, datalen);
+}
+
+static int
+llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
+		      const struct ieee802154_hdr *hdr,
+		      struct mac802154_llsec_key *key, __le64 dev_addr)
+{
+	u8 iv[16];
+	unsigned char *data;
+	int authlen, datalen, assoclen, rc;
+	struct scatterlist src, assoc[2];
+	struct aead_request *req;
+
+	authlen = ieee802154_sechdr_authtag_len(&hdr->sec);
+	llsec_geniv(iv, dev_addr, &hdr->sec);
+
+	req = aead_request_alloc(llsec_tfm_by_len(key, authlen), GFP_ATOMIC);
+	if (!req)
+		return -ENOMEM;
+
+	sg_init_table(assoc, 2);
+	sg_set_buf(&assoc[0], skb_mac_header(skb), skb->mac_len);
+	assoclen = skb->mac_len;
+
+	data = skb_mac_header(skb) + skb->mac_len;
+	datalen = skb_tail_pointer(skb) - data;
+
+	if (hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC) {
+		sg_set_buf(&assoc[1], data, 0);
+	} else {
+		sg_set_buf(&assoc[1], data, datalen - authlen);
+		assoclen += datalen - authlen;
+		data += datalen - authlen;
+		datalen = authlen;
+	}
+
+	sg_init_one(&src, data, datalen);
+
+	aead_request_set_callback(req, 0, NULL, NULL);
+	aead_request_set_assoc(req, assoc, assoclen);
+	aead_request_set_crypt(req, &src, &src, datalen, iv);
+
+	rc = crypto_aead_decrypt(req);
+
+	kfree(req);
+	skb_trim(skb, skb->len - authlen);
+
+	return rc;
+}
+
+static int
+llsec_do_decrypt(struct sk_buff *skb, const struct mac802154_llsec *sec,
+		 const struct ieee802154_hdr *hdr,
+		 struct mac802154_llsec_key *key, __le64 dev_addr)
+{
+	if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC)
+		return llsec_do_decrypt_unauth(skb, sec, hdr, key, dev_addr);
+	else
+		return llsec_do_decrypt_auth(skb, sec, hdr, key, dev_addr);
+}
+
+static int
+llsec_update_devkey_record(struct mac802154_llsec_device *dev,
+			   const struct ieee802154_llsec_key_id *in_key)
+{
+	struct mac802154_llsec_device_key *devkey;
+
+	devkey = llsec_devkey_find(dev, in_key);
+
+	if (!devkey) {
+		struct mac802154_llsec_device_key *next;
+
+		next = kzalloc(sizeof(*devkey), GFP_ATOMIC);
+		if (!next)
+			return -ENOMEM;
+
+		next->devkey.key_id = *in_key;
+
+		spin_lock_bh(&dev->lock);
+
+		devkey = llsec_devkey_find(dev, in_key);
+		if (!devkey)
+			list_add_rcu(&next->devkey.list, &dev->dev.keys);
+		else
+			kfree(next);
+
+		spin_unlock_bh(&dev->lock);
+	}
+
+	return 0;
+}
+
+static int
+llsec_update_devkey_info(struct mac802154_llsec_device *dev,
+			 const struct ieee802154_llsec_key_id *in_key,
+			 u32 frame_counter)
+{
+	struct mac802154_llsec_device_key *devkey = NULL;
+
+	if (dev->dev.key_mode == IEEE802154_LLSEC_DEVKEY_RESTRICT) {
+		devkey = llsec_devkey_find(dev, in_key);
+		if (!devkey)
+			return -ENOENT;
+	}
+
+	if (dev->dev.key_mode == IEEE802154_LLSEC_DEVKEY_RECORD) {
+		int rc = llsec_update_devkey_record(dev, in_key);
+
+		if (rc < 0)
+			return rc;
+	}
+
+	spin_lock_bh(&dev->lock);
+
+	if ((!devkey && frame_counter < dev->dev.frame_counter) ||
+	    (devkey && frame_counter < devkey->devkey.frame_counter)) {
+		spin_unlock_bh(&dev->lock);
+		return -EINVAL;
+	}
+
+	if (devkey)
+		devkey->devkey.frame_counter = frame_counter + 1;
+	else
+		dev->dev.frame_counter = frame_counter + 1;
+
+	spin_unlock_bh(&dev->lock);
+
+	return 0;
+}
+
+int mac802154_llsec_decrypt(struct mac802154_llsec *sec, struct sk_buff *skb)
+{
+	struct ieee802154_hdr hdr;
+	struct mac802154_llsec_key *key;
+	struct ieee802154_llsec_key_id key_id;
+	struct mac802154_llsec_device *dev;
+	struct ieee802154_llsec_seclevel seclevel;
+	int err;
+	__le64 dev_addr;
+	u32 frame_ctr;
+
+	if (ieee802154_hdr_peek(skb, &hdr) < 0)
+		return -EINVAL;
+	if (!hdr.fc.security_enabled)
+		return 0;
+	if (hdr.fc.version == 0)
+		return -EINVAL;
+
+	read_lock_bh(&sec->lock);
+	if (!sec->params.enabled) {
+		read_unlock_bh(&sec->lock);
+		return -EINVAL;
+	}
+	read_unlock_bh(&sec->lock);
+
+	rcu_read_lock();
+
+	key = llsec_lookup_key(sec, &hdr, &hdr.source, &key_id);
+	if (!key) {
+		err = -ENOKEY;
+		goto fail;
+	}
+
+	dev = llsec_lookup_dev(sec, &hdr.source);
+	if (!dev) {
+		err = -EINVAL;
+		goto fail_dev;
+	}
+
+	if (llsec_lookup_seclevel(sec, hdr.fc.type, 0, &seclevel) < 0) {
+		err = -EINVAL;
+		goto fail_dev;
+	}
+
+	if (!(seclevel.sec_levels & BIT(hdr.sec.level)) &&
+	    (hdr.sec.level == 0 && seclevel.device_override &&
+	     !dev->dev.seclevel_exempt)) {
+		err = -EINVAL;
+		goto fail_dev;
+	}
+
+	frame_ctr = le32_to_cpu(hdr.sec.frame_counter);
+
+	if (frame_ctr == 0xffffffff) {
+		err = -EOVERFLOW;
+		goto fail_dev;
+	}
+
+	err = llsec_update_devkey_info(dev, &key_id, frame_ctr);
+	if (err)
+		goto fail_dev;
+
+	dev_addr = dev->dev.hwaddr;
+
+	rcu_read_unlock();
+
+	err = llsec_do_decrypt(skb, sec, &hdr, key, dev_addr);
+	llsec_key_put(key);
+	return err;
+
+fail_dev:
+	llsec_key_put(key);
+fail:
+	rcu_read_unlock();
+	return err;
+}
diff --git a/net/mac802154/llsec.h b/net/mac802154/llsec.h
new file mode 100644
index 00000000000..950578e1d7b
--- /dev/null
+++ b/net/mac802154/llsec.h
@@ -0,0 +1,108 @@
+/*
+ * Copyright (C) 2014 Fraunhofer ITWM
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Written by:
+ * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
+ */
+
+#ifndef MAC802154_LLSEC_H
+#define MAC802154_LLSEC_H
+
+#include <linux/slab.h>
+#include <linux/hashtable.h>
+#include <linux/crypto.h>
+#include <linux/kref.h>
+#include <linux/spinlock.h>
+#include <net/af_ieee802154.h>
+#include <net/ieee802154_netdev.h>
+
+struct mac802154_llsec_key {
+	struct ieee802154_llsec_key key;
+
+	/* one tfm for each authsize (4/8/16) */
+	struct crypto_aead *tfm[3];
+	struct crypto_blkcipher *tfm0;
+
+	struct kref ref;
+};
+
+struct mac802154_llsec_device_key {
+	struct ieee802154_llsec_device_key devkey;
+
+	struct rcu_head rcu;
+};
+
+struct mac802154_llsec_device {
+	struct ieee802154_llsec_device dev;
+
+	struct hlist_node bucket_s;
+	struct hlist_node bucket_hw;
+
+	/* protects dev.frame_counter and the elements of dev.keys */
+	spinlock_t lock;
+
+	struct rcu_head rcu;
+};
+
+struct mac802154_llsec_seclevel {
+	struct ieee802154_llsec_seclevel level;
+
+	struct rcu_head rcu;
+};
+
+struct mac802154_llsec {
+	struct ieee802154_llsec_params params;
+	struct ieee802154_llsec_table table;
+
+	DECLARE_HASHTABLE(devices_short, 6);
+	DECLARE_HASHTABLE(devices_hw, 6);
+
+	/* protects params, all other fields are fine with RCU */
+	rwlock_t lock;
+};
+
+void mac802154_llsec_init(struct mac802154_llsec *sec);
+void mac802154_llsec_destroy(struct mac802154_llsec *sec);
+
+int mac802154_llsec_get_params(struct mac802154_llsec *sec,
+			       struct ieee802154_llsec_params *params);
+int mac802154_llsec_set_params(struct mac802154_llsec *sec,
+			       const struct ieee802154_llsec_params *params,
+			       int changed);
+
+int mac802154_llsec_key_add(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_key_id *id,
+			    const struct ieee802154_llsec_key *key);
+int mac802154_llsec_key_del(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_key_id *key);
+
+int mac802154_llsec_dev_add(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_device *dev);
+int mac802154_llsec_dev_del(struct mac802154_llsec *sec,
+			    __le64 device_addr);
+
+int mac802154_llsec_devkey_add(struct mac802154_llsec *sec,
+			       __le64 dev_addr,
+			       const struct ieee802154_llsec_device_key *key);
+int mac802154_llsec_devkey_del(struct mac802154_llsec *sec,
+			       __le64 dev_addr,
+			       const struct ieee802154_llsec_device_key *key);
+
+int mac802154_llsec_seclevel_add(struct mac802154_llsec *sec,
+				 const struct ieee802154_llsec_seclevel *sl);
+int mac802154_llsec_seclevel_del(struct mac802154_llsec *sec,
+				 const struct ieee802154_llsec_seclevel *sl);
+
+int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb);
+int mac802154_llsec_decrypt(struct mac802154_llsec *sec, struct sk_buff *skb);
+
+#endif /* MAC802154_LLSEC_H */
diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h
index d48422e2711..762a6f849c6 100644
--- a/net/mac802154/mac802154.h
+++ b/net/mac802154/mac802154.h
@@ -23,6 +23,12 @@
 #ifndef MAC802154_H
 #define MAC802154_H
 
+#include <linux/mutex.h>
+#include <net/mac802154.h>
+#include <net/ieee802154_netdev.h>
+
+#include "llsec.h"
+
 /* mac802154 device private data */
 struct mac802154_priv {
 	struct ieee802154_dev hw;
@@ -71,19 +77,30 @@ struct mac802154_sub_if_data {
 	struct net_device *dev;
 
 	int type;
+	bool running;
 
 	spinlock_t mib_lock;
 
 	__le16 pan_id;
 	__le16 short_addr;
+	__le64 extended_addr;
 
 	u8 chan;
 	u8 page;
 
+	struct ieee802154_mac_params mac_params;
+
 	/* MAC BSN field */
 	u8 bsn;
 	/* MAC DSN field */
 	u8 dsn;
+
+	/* protects sec from concurrent access by netlink. access by
+	 * encrypt/decrypt/header_create safe without additional protection.
+	 */
+	struct mutex sec_mtx;
+
+	struct mac802154_llsec sec;
 };
 
 #define mac802154_to_priv(_hw)	container_of(_hw, struct mac802154_priv, hw)
@@ -106,12 +123,50 @@ netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb,
 			 u8 page, u8 chan);
 
 /* MIB callbacks */
-void mac802154_dev_set_short_addr(struct net_device *dev, u16 val);
-u16 mac802154_dev_get_short_addr(const struct net_device *dev);
+void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val);
+__le16 mac802154_dev_get_short_addr(const struct net_device *dev);
 void mac802154_dev_set_ieee_addr(struct net_device *dev);
-u16 mac802154_dev_get_pan_id(const struct net_device *dev);
-void mac802154_dev_set_pan_id(struct net_device *dev, u16 val);
+__le16 mac802154_dev_get_pan_id(const struct net_device *dev);
+void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val);
 void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan);
 u8 mac802154_dev_get_dsn(const struct net_device *dev);
 
+int mac802154_set_mac_params(struct net_device *dev,
+			     const struct ieee802154_mac_params *params);
+void mac802154_get_mac_params(struct net_device *dev,
+			      struct ieee802154_mac_params *params);
+
+int mac802154_get_params(struct net_device *dev,
+			 struct ieee802154_llsec_params *params);
+int mac802154_set_params(struct net_device *dev,
+			 const struct ieee802154_llsec_params *params,
+			 int changed);
+
+int mac802154_add_key(struct net_device *dev,
+		      const struct ieee802154_llsec_key_id *id,
+		      const struct ieee802154_llsec_key *key);
+int mac802154_del_key(struct net_device *dev,
+		      const struct ieee802154_llsec_key_id *id);
+
+int mac802154_add_dev(struct net_device *dev,
+		      const struct ieee802154_llsec_device *llsec_dev);
+int mac802154_del_dev(struct net_device *dev, __le64 dev_addr);
+
+int mac802154_add_devkey(struct net_device *dev,
+			 __le64 device_addr,
+			 const struct ieee802154_llsec_device_key *key);
+int mac802154_del_devkey(struct net_device *dev,
+			 __le64 device_addr,
+			 const struct ieee802154_llsec_device_key *key);
+
+int mac802154_add_seclevel(struct net_device *dev,
+			   const struct ieee802154_llsec_seclevel *sl);
+int mac802154_del_seclevel(struct net_device *dev,
+			   const struct ieee802154_llsec_seclevel *sl);
+
+void mac802154_lock_table(struct net_device *dev);
+void mac802154_get_table(struct net_device *dev,
+			 struct ieee802154_llsec_table **t);
+void mac802154_unlock_table(struct net_device *dev);
+
 #endif /* MAC802154_H */
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index a99910d4d52..bf809131eef 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -40,19 +40,41 @@ static int mac802154_mlme_start_req(struct net_device *dev,
 				    u8 pan_coord, u8 blx,
 				    u8 coord_realign)
 {
-	BUG_ON(addr->addr_type != IEEE802154_ADDR_SHORT);
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	int rc = 0;
+
+	BUG_ON(addr->mode != IEEE802154_ADDR_SHORT);
 
 	mac802154_dev_set_pan_id(dev, addr->pan_id);
 	mac802154_dev_set_short_addr(dev, addr->short_addr);
 	mac802154_dev_set_ieee_addr(dev);
 	mac802154_dev_set_page_channel(dev, page, channel);
 
+	if (ops->llsec) {
+		struct ieee802154_llsec_params params;
+		int changed = 0;
+
+		params.coord_shortaddr = addr->short_addr;
+		changed |= IEEE802154_LLSEC_PARAM_COORD_SHORTADDR;
+
+		params.pan_id = addr->pan_id;
+		changed |= IEEE802154_LLSEC_PARAM_PAN_ID;
+
+		params.hwaddr = ieee802154_devaddr_from_raw(dev->dev_addr);
+		changed |= IEEE802154_LLSEC_PARAM_HWADDR;
+
+		params.coord_hwaddr = params.hwaddr;
+		changed |= IEEE802154_LLSEC_PARAM_COORD_HWADDR;
+
+		rc = ops->llsec->set_params(dev, &params, changed);
+	}
+
 	/* FIXME: add validation for unused parameters to be sane
 	 * for SoftMAC
 	 */
 	ieee802154_nl_start_confirm(dev, IEEE802154_SUCCESS);
 
-	return 0;
+	return rc;
 }
 
 static struct wpan_phy *mac802154_get_phy(const struct net_device *dev)
@@ -64,6 +86,22 @@ static struct wpan_phy *mac802154_get_phy(const struct net_device *dev)
 	return to_phy(get_device(&priv->hw->phy->dev));
 }
 
+static struct ieee802154_llsec_ops mac802154_llsec_ops = {
+	.get_params = mac802154_get_params,
+	.set_params = mac802154_set_params,
+	.add_key = mac802154_add_key,
+	.del_key = mac802154_del_key,
+	.add_dev = mac802154_add_dev,
+	.del_dev = mac802154_del_dev,
+	.add_devkey = mac802154_add_devkey,
+	.del_devkey = mac802154_del_devkey,
+	.add_seclevel = mac802154_add_seclevel,
+	.del_seclevel = mac802154_del_seclevel,
+	.lock_table = mac802154_lock_table,
+	.get_table = mac802154_get_table,
+	.unlock_table = mac802154_unlock_table,
+};
+
 struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced = {
 	.get_phy = mac802154_get_phy,
 };
@@ -74,4 +112,9 @@ struct ieee802154_mlme_ops mac802154_mlme_wpan = {
 	.get_pan_id = mac802154_dev_get_pan_id,
 	.get_short_addr = mac802154_dev_get_short_addr,
 	.get_dsn = mac802154_dev_get_dsn,
+
+	.llsec = &mac802154_llsec_ops,
+
+	.set_mac_params = mac802154_set_mac_params,
+	.get_mac_params = mac802154_get_mac_params,
 };
diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c
index 8ded97cf1c3..15aa2f2b03a 100644
--- a/net/mac802154/mib.c
+++ b/net/mac802154/mib.c
@@ -24,6 +24,7 @@
 #include <linux/if_arp.h>
 
 #include <net/mac802154.h>
+#include <net/ieee802154_netdev.h>
 #include <net/wpan-phy.h>
 
 #include "mac802154.h"
@@ -62,8 +63,6 @@ static void hw_addr_notify(struct work_struct *work)
 		pr_debug("failed changed mask %lx\n", nw->changed);
 
 	kfree(nw);
-
-	return;
 }
 
 static void set_hw_addr_filt(struct net_device *dev, unsigned long changed)
@@ -79,11 +78,9 @@ static void set_hw_addr_filt(struct net_device *dev, unsigned long changed)
 	work->dev = dev;
 	work->changed = changed;
 	queue_work(priv->hw->dev_workqueue, &work->work);
-
-	return;
 }
 
-void mac802154_dev_set_short_addr(struct net_device *dev, u16 val)
+void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val)
 {
 	struct mac802154_sub_if_data *priv = netdev_priv(dev);
 
@@ -100,10 +97,10 @@ void mac802154_dev_set_short_addr(struct net_device *dev, u16 val)
 	}
 }
 
-u16 mac802154_dev_get_short_addr(const struct net_device *dev)
+__le16 mac802154_dev_get_short_addr(const struct net_device *dev)
 {
 	struct mac802154_sub_if_data *priv = netdev_priv(dev);
-	u16 ret;
+	__le16 ret;
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
@@ -119,19 +116,19 @@ void mac802154_dev_set_ieee_addr(struct net_device *dev)
 	struct mac802154_sub_if_data *priv = netdev_priv(dev);
 	struct mac802154_priv *mac = priv->hw;
 
+	priv->extended_addr = ieee802154_devaddr_from_raw(dev->dev_addr);
+
 	if (mac->ops->set_hw_addr_filt &&
-	    memcmp(mac->hw.hw_filt.ieee_addr,
-		   dev->dev_addr, IEEE802154_ADDR_LEN)) {
-		memcpy(mac->hw.hw_filt.ieee_addr,
-		       dev->dev_addr, IEEE802154_ADDR_LEN);
+	    mac->hw.hw_filt.ieee_addr != priv->extended_addr) {
+		mac->hw.hw_filt.ieee_addr = priv->extended_addr;
 		set_hw_addr_filt(dev, IEEE802515_AFILT_IEEEADDR_CHANGED);
 	}
 }
 
-u16 mac802154_dev_get_pan_id(const struct net_device *dev)
+__le16 mac802154_dev_get_pan_id(const struct net_device *dev)
 {
 	struct mac802154_sub_if_data *priv = netdev_priv(dev);
-	u16 ret;
+	__le16 ret;
 
 	BUG_ON(dev->type != ARPHRD_IEEE802154);
 
@@ -142,7 +139,7 @@ u16 mac802154_dev_get_pan_id(const struct net_device *dev)
 	return ret;
 }
 
-void mac802154_dev_set_pan_id(struct net_device *dev, u16 val)
+void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val)
 {
 	struct mac802154_sub_if_data *priv = netdev_priv(dev);
 
@@ -216,3 +213,190 @@ void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan)
 	} else
 		mutex_unlock(&priv->hw->phy->pib_lock);
 }
+
+
+int mac802154_get_params(struct net_device *dev,
+			 struct ieee802154_llsec_params *params)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_get_params(&priv->sec, params);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+int mac802154_set_params(struct net_device *dev,
+			 const struct ieee802154_llsec_params *params,
+			 int changed)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_set_params(&priv->sec, params, changed);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+
+int mac802154_add_key(struct net_device *dev,
+		      const struct ieee802154_llsec_key_id *id,
+		      const struct ieee802154_llsec_key *key)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_key_add(&priv->sec, id, key);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+int mac802154_del_key(struct net_device *dev,
+		      const struct ieee802154_llsec_key_id *id)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_key_del(&priv->sec, id);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+
+int mac802154_add_dev(struct net_device *dev,
+		      const struct ieee802154_llsec_device *llsec_dev)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_dev_add(&priv->sec, llsec_dev);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+int mac802154_del_dev(struct net_device *dev, __le64 dev_addr)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_dev_del(&priv->sec, dev_addr);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+
+int mac802154_add_devkey(struct net_device *dev,
+			 __le64 device_addr,
+			 const struct ieee802154_llsec_device_key *key)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_devkey_add(&priv->sec, device_addr, key);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+int mac802154_del_devkey(struct net_device *dev,
+			 __le64 device_addr,
+			 const struct ieee802154_llsec_device_key *key)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_devkey_del(&priv->sec, device_addr, key);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+
+int mac802154_add_seclevel(struct net_device *dev,
+			   const struct ieee802154_llsec_seclevel *sl)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_seclevel_add(&priv->sec, sl);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+int mac802154_del_seclevel(struct net_device *dev,
+			   const struct ieee802154_llsec_seclevel *sl)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_seclevel_del(&priv->sec, sl);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+
+void mac802154_lock_table(struct net_device *dev)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+}
+
+void mac802154_get_table(struct net_device *dev,
+			 struct ieee802154_llsec_table **t)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	*t = &priv->sec.table;
+}
+
+void mac802154_unlock_table(struct net_device *dev)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_unlock(&priv->sec_mtx);
+}
diff --git a/net/mac802154/monitor.c b/net/mac802154/monitor.c
index 434a26f76a8..a68230e2b25 100644
--- a/net/mac802154/monitor.c
+++ b/net/mac802154/monitor.c
@@ -70,7 +70,8 @@ void mac802154_monitors_rx(struct mac802154_priv *priv, struct sk_buff *skb)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdata, &priv->slaves, list) {
-		if (sdata->type != IEEE802154_DEV_MONITOR)
+		if (sdata->type != IEEE802154_DEV_MONITOR ||
+		    !netif_running(sdata->dev))
 			continue;
 
 		skb2 = skb_clone(skb, GFP_ATOMIC);
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index 38548ec2098..7f820a108a9 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -59,28 +59,28 @@ mac802154_subif_rx(struct ieee802154_dev *hw, struct sk_buff *skb, u8 lqi)
 	skb->protocol = htons(ETH_P_IEEE802154);
 	skb_reset_mac_header(skb);
 
-	BUILD_BUG_ON(sizeof(struct ieee802154_mac_cb) > sizeof(skb->cb));
-
 	if (!(priv->hw.flags & IEEE802154_HW_OMIT_CKSUM)) {
 		u16 crc;
 
 		if (skb->len < 2) {
 			pr_debug("got invalid frame\n");
-			goto out;
+			goto fail;
 		}
 		crc = crc_ccitt(0, skb->data, skb->len);
 		if (crc) {
 			pr_debug("CRC mismatch\n");
-			goto out;
+			goto fail;
 		}
 		skb_trim(skb, skb->len - 2); /* CRC */
 	}
 
 	mac802154_monitors_rx(priv, skb);
 	mac802154_wpans_rx(priv, skb);
-out:
-	dev_kfree_skb(skb);
+
 	return;
+
+fail:
+	kfree_skb(skb);
 }
 
 static void mac802154_rx_worker(struct work_struct *work)
diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c
index e24bcf97729..3c3069fd697 100644
--- a/net/mac802154/wpan.c
+++ b/net/mac802154/wpan.c
@@ -35,33 +35,26 @@
 
 #include "mac802154.h"
 
-static inline int mac802154_fetch_skb_u8(struct sk_buff *skb, u8 *val)
+static int mac802154_wpan_update_llsec(struct net_device *dev)
 {
-	if (unlikely(!pskb_may_pull(skb, 1)))
-		return -EINVAL;
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	int rc = 0;
 
-	*val = skb->data[0];
-	skb_pull(skb, 1);
+	if (ops->llsec) {
+		struct ieee802154_llsec_params params;
+		int changed = 0;
 
-	return 0;
-}
+		params.pan_id = priv->pan_id;
+		changed |= IEEE802154_LLSEC_PARAM_PAN_ID;
 
-static inline int mac802154_fetch_skb_u16(struct sk_buff *skb, u16 *val)
-{
-	if (unlikely(!pskb_may_pull(skb, 2)))
-		return -EINVAL;
-
-	*val = skb->data[0] | (skb->data[1] << 8);
-	skb_pull(skb, 2);
+		params.hwaddr = priv->extended_addr;
+		changed |= IEEE802154_LLSEC_PARAM_HWADDR;
 
-	return 0;
-}
+		rc = ops->llsec->set_params(dev, &params, changed);
+	}
 
-static inline void mac802154_haddr_copy_swap(u8 *dest, const u8 *src)
-{
-	int i;
-	for (i = 0; i < IEEE802154_ADDR_LEN; i++)
-		dest[IEEE802154_ADDR_LEN - i - 1] = src[i];
+	return rc;
 }
 
 static int
@@ -76,19 +69,25 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 	switch (cmd) {
 	case SIOCGIFADDR:
-		if (priv->pan_id == IEEE802154_PANID_BROADCAST ||
-		    priv->short_addr == IEEE802154_ADDR_BROADCAST) {
+	{
+		u16 pan_id, short_addr;
+
+		pan_id = le16_to_cpu(priv->pan_id);
+		short_addr = le16_to_cpu(priv->short_addr);
+		if (pan_id == IEEE802154_PANID_BROADCAST ||
+		    short_addr == IEEE802154_ADDR_BROADCAST) {
 			err = -EADDRNOTAVAIL;
 			break;
 		}
 
 		sa->family = AF_IEEE802154;
 		sa->addr.addr_type = IEEE802154_ADDR_SHORT;
-		sa->addr.pan_id = priv->pan_id;
-		sa->addr.short_addr = priv->short_addr;
+		sa->addr.pan_id = pan_id;
+		sa->addr.short_addr = short_addr;
 
 		err = 0;
 		break;
+	}
 	case SIOCSIFADDR:
 		dev_warn(&dev->dev,
 			 "Using DEBUGing ioctl SIOCSIFADDR isn't recommened!\n");
@@ -101,10 +100,10 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			break;
 		}
 
-		priv->pan_id = sa->addr.pan_id;
-		priv->short_addr = sa->addr.short_addr;
+		priv->pan_id = cpu_to_le16(sa->addr.pan_id);
+		priv->short_addr = cpu_to_le16(sa->addr.short_addr);
 
-		err = 0;
+		err = mac802154_wpan_update_llsec(dev);
 		break;
 	}
 
@@ -122,193 +121,194 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p)
 	/* FIXME: validate addr */
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
 	mac802154_dev_set_ieee_addr(dev);
-	return 0;
+	return mac802154_wpan_update_llsec(dev);
 }
 
-static int mac802154_header_create(struct sk_buff *skb,
-				   struct net_device *dev,
-				   unsigned short type,
-				   const void *_daddr,
-				   const void *_saddr,
-				   unsigned len)
+int mac802154_set_mac_params(struct net_device *dev,
+			     const struct ieee802154_mac_params *params)
 {
-	const struct ieee802154_addr *saddr = _saddr;
-	const struct ieee802154_addr *daddr = _daddr;
-	struct ieee802154_addr dev_addr;
 	struct mac802154_sub_if_data *priv = netdev_priv(dev);
-	int pos = 2;
-	u8 head[MAC802154_FRAME_HARD_HEADER_LEN];
-	u16 fc;
 
-	if (!daddr)
-		return -EINVAL;
+	mutex_lock(&priv->hw->slaves_mtx);
+	priv->mac_params = *params;
+	mutex_unlock(&priv->hw->slaves_mtx);
 
-	head[pos++] = mac_cb(skb)->seq; /* DSN/BSN */
-	fc = mac_cb_type(skb);
-	if (mac_cb_is_ackreq(skb))
-		fc |= IEEE802154_FC_ACK_REQ;
+	return 0;
+}
 
-	if (!saddr) {
-		spin_lock_bh(&priv->mib_lock);
+void mac802154_get_mac_params(struct net_device *dev,
+			      struct ieee802154_mac_params *params)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
 
-		if (priv->short_addr == IEEE802154_ADDR_BROADCAST ||
-		    priv->short_addr == IEEE802154_ADDR_UNDEF ||
-		    priv->pan_id == IEEE802154_PANID_BROADCAST) {
-			dev_addr.addr_type = IEEE802154_ADDR_LONG;
-			memcpy(dev_addr.hwaddr, dev->dev_addr,
-			       IEEE802154_ADDR_LEN);
-		} else {
-			dev_addr.addr_type = IEEE802154_ADDR_SHORT;
-			dev_addr.short_addr = priv->short_addr;
-		}
+	mutex_lock(&priv->hw->slaves_mtx);
+	*params = priv->mac_params;
+	mutex_unlock(&priv->hw->slaves_mtx);
+}
 
-		dev_addr.pan_id = priv->pan_id;
-		saddr = &dev_addr;
+static int mac802154_wpan_open(struct net_device *dev)
+{
+	int rc;
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct wpan_phy *phy = priv->hw->phy;
 
-		spin_unlock_bh(&priv->mib_lock);
-	}
+	rc = mac802154_slave_open(dev);
+	if (rc < 0)
+		return rc;
 
-	if (daddr->addr_type != IEEE802154_ADDR_NONE) {
-		fc |= (daddr->addr_type << IEEE802154_FC_DAMODE_SHIFT);
+	mutex_lock(&phy->pib_lock);
 
-		head[pos++] = daddr->pan_id & 0xff;
-		head[pos++] = daddr->pan_id >> 8;
+	if (phy->set_txpower) {
+		rc = phy->set_txpower(phy, priv->mac_params.transmit_power);
+		if (rc < 0)
+			goto out;
+	}
 
-		if (daddr->addr_type == IEEE802154_ADDR_SHORT) {
-			head[pos++] = daddr->short_addr & 0xff;
-			head[pos++] = daddr->short_addr >> 8;
-		} else {
-			mac802154_haddr_copy_swap(head + pos, daddr->hwaddr);
-			pos += IEEE802154_ADDR_LEN;
-		}
+	if (phy->set_lbt) {
+		rc = phy->set_lbt(phy, priv->mac_params.lbt);
+		if (rc < 0)
+			goto out;
 	}
 
-	if (saddr->addr_type != IEEE802154_ADDR_NONE) {
-		fc |= (saddr->addr_type << IEEE802154_FC_SAMODE_SHIFT);
+	if (phy->set_cca_mode) {
+		rc = phy->set_cca_mode(phy, priv->mac_params.cca_mode);
+		if (rc < 0)
+			goto out;
+	}
 
-		if ((saddr->pan_id == daddr->pan_id) &&
-		    (saddr->pan_id != IEEE802154_PANID_BROADCAST)) {
-			/* PANID compression/intra PAN */
-			fc |= IEEE802154_FC_INTRA_PAN;
-		} else {
-			head[pos++] = saddr->pan_id & 0xff;
-			head[pos++] = saddr->pan_id >> 8;
-		}
+	if (phy->set_cca_ed_level) {
+		rc = phy->set_cca_ed_level(phy, priv->mac_params.cca_ed_level);
+		if (rc < 0)
+			goto out;
+	}
 
-		if (saddr->addr_type == IEEE802154_ADDR_SHORT) {
-			head[pos++] = saddr->short_addr & 0xff;
-			head[pos++] = saddr->short_addr >> 8;
-		} else {
-			mac802154_haddr_copy_swap(head + pos, saddr->hwaddr);
-			pos += IEEE802154_ADDR_LEN;
-		}
+	if (phy->set_csma_params) {
+		rc = phy->set_csma_params(phy, priv->mac_params.min_be,
+					  priv->mac_params.max_be,
+					  priv->mac_params.csma_retries);
+		if (rc < 0)
+			goto out;
 	}
 
-	head[0] = fc;
-	head[1] = fc >> 8;
+	if (phy->set_frame_retries) {
+		rc = phy->set_frame_retries(phy,
+					    priv->mac_params.frame_retries);
+		if (rc < 0)
+			goto out;
+	}
 
-	memcpy(skb_push(skb, pos), head, pos);
-	skb_reset_mac_header(skb);
-	skb->mac_len = pos;
+	mutex_unlock(&phy->pib_lock);
+	return 0;
 
-	return pos;
+out:
+	mutex_unlock(&phy->pib_lock);
+	return rc;
 }
 
-static int
-mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+static int mac802154_set_header_security(struct mac802154_sub_if_data *priv,
+					 struct ieee802154_hdr *hdr,
+					 const struct ieee802154_mac_cb *cb)
 {
-	const u8 *hdr = skb_mac_header(skb);
-	const u8 *tail = skb_tail_pointer(skb);
-	struct ieee802154_addr *addr = (struct ieee802154_addr *)haddr;
-	u16 fc;
-	int da_type;
+	struct ieee802154_llsec_params params;
+	u8 level;
 
-	if (hdr + 3 > tail)
-		goto malformed;
+	mac802154_llsec_get_params(&priv->sec, &params);
 
-	fc = hdr[0] | (hdr[1] << 8);
+	if (!params.enabled && cb->secen_override && cb->secen)
+		return -EINVAL;
+	if (!params.enabled ||
+	    (cb->secen_override && !cb->secen) ||
+	    !params.out_level)
+		return 0;
+	if (cb->seclevel_override && !cb->seclevel)
+		return -EINVAL;
 
-	hdr += 3;
+	level = cb->seclevel_override ? cb->seclevel : params.out_level;
 
-	da_type = IEEE802154_FC_DAMODE(fc);
-	addr->addr_type = IEEE802154_FC_SAMODE(fc);
+	hdr->fc.security_enabled = 1;
+	hdr->sec.level = level;
+	hdr->sec.key_id_mode = params.out_key.mode;
+	if (params.out_key.mode == IEEE802154_SCF_KEY_SHORT_INDEX)
+		hdr->sec.short_src = params.out_key.short_source;
+	else if (params.out_key.mode == IEEE802154_SCF_KEY_HW_INDEX)
+		hdr->sec.extended_src = params.out_key.extended_source;
+	hdr->sec.key_id = params.out_key.id;
 
-	switch (da_type) {
-	case IEEE802154_ADDR_NONE:
-		if (fc & IEEE802154_FC_INTRA_PAN)
-			goto malformed;
-		break;
-	case IEEE802154_ADDR_LONG:
-		if (fc & IEEE802154_FC_INTRA_PAN) {
-			if (hdr + 2 > tail)
-				goto malformed;
-			addr->pan_id = hdr[0] | (hdr[1] << 8);
-			hdr += 2;
-		}
+	return 0;
+}
 
-		if (hdr + IEEE802154_ADDR_LEN > tail)
-			goto malformed;
+static int mac802154_header_create(struct sk_buff *skb,
+				   struct net_device *dev,
+				   unsigned short type,
+				   const void *daddr,
+				   const void *saddr,
+				   unsigned len)
+{
+	struct ieee802154_hdr hdr;
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_mac_cb *cb = mac_cb(skb);
+	int hlen;
 
-		hdr += IEEE802154_ADDR_LEN;
-		break;
-	case IEEE802154_ADDR_SHORT:
-		if (fc & IEEE802154_FC_INTRA_PAN) {
-			if (hdr + 2 > tail)
-				goto malformed;
-			addr->pan_id = hdr[0] | (hdr[1] << 8);
-			hdr += 2;
-		}
+	if (!daddr)
+		return -EINVAL;
 
-		if (hdr + 2 > tail)
-			goto malformed;
+	memset(&hdr.fc, 0, sizeof(hdr.fc));
+	hdr.fc.type = cb->type;
+	hdr.fc.security_enabled = cb->secen;
+	hdr.fc.ack_request = cb->ackreq;
+	hdr.seq = ieee802154_mlme_ops(dev)->get_dsn(dev);
 
-		hdr += 2;
-		break;
-	default:
-		goto malformed;
+	if (mac802154_set_header_security(priv, &hdr, cb) < 0)
+		return -EINVAL;
 
-	}
+	if (!saddr) {
+		spin_lock_bh(&priv->mib_lock);
 
-	switch (addr->addr_type) {
-	case IEEE802154_ADDR_NONE:
-		break;
-	case IEEE802154_ADDR_LONG:
-		if (!(fc & IEEE802154_FC_INTRA_PAN)) {
-			if (hdr + 2 > tail)
-				goto malformed;
-			addr->pan_id = hdr[0] | (hdr[1] << 8);
-			hdr += 2;
+		if (priv->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) ||
+		    priv->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) ||
+		    priv->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) {
+			hdr.source.mode = IEEE802154_ADDR_LONG;
+			hdr.source.extended_addr = priv->extended_addr;
+		} else {
+			hdr.source.mode = IEEE802154_ADDR_SHORT;
+			hdr.source.short_addr = priv->short_addr;
 		}
 
-		if (hdr + IEEE802154_ADDR_LEN > tail)
-			goto malformed;
+		hdr.source.pan_id = priv->pan_id;
 
-		mac802154_haddr_copy_swap(addr->hwaddr, hdr);
-		hdr += IEEE802154_ADDR_LEN;
-		break;
-	case IEEE802154_ADDR_SHORT:
-		if (!(fc & IEEE802154_FC_INTRA_PAN)) {
-			if (hdr + 2 > tail)
-				goto malformed;
-			addr->pan_id = hdr[0] | (hdr[1] << 8);
-			hdr += 2;
-		}
+		spin_unlock_bh(&priv->mib_lock);
+	} else {
+		hdr.source = *(const struct ieee802154_addr *)saddr;
+	}
 
-		if (hdr + 2 > tail)
-			goto malformed;
+	hdr.dest = *(const struct ieee802154_addr *)daddr;
 
-		addr->short_addr = hdr[0] | (hdr[1] << 8);
-		hdr += 2;
-		break;
-	default:
-		goto malformed;
-	}
+	hlen = ieee802154_hdr_push(skb, &hdr);
+	if (hlen < 0)
+		return -EINVAL;
 
-	return sizeof(struct ieee802154_addr);
+	skb_reset_mac_header(skb);
+	skb->mac_len = hlen;
 
-malformed:
-	pr_debug("malformed packet\n");
-	return 0;
+	if (len > ieee802154_max_payload(&hdr))
+		return -EMSGSIZE;
+
+	return hlen;
+}
+
+static int
+mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+{
+	struct ieee802154_hdr hdr;
+	struct ieee802154_addr *addr = (struct ieee802154_addr *)haddr;
+
+	if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) {
+		pr_debug("malformed packet\n");
+		return 0;
+	}
+
+	*addr = hdr.source;
+	return sizeof(*addr);
 }
 
 static netdev_tx_t
@@ -316,6 +316,7 @@ mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mac802154_sub_if_data *priv;
 	u8 chan, page;
+	int rc;
 
 	priv = netdev_priv(dev);
 
@@ -331,6 +332,13 @@ mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
+	rc = mac802154_llsec_encrypt(&priv->sec, skb);
+	if (rc) {
+		pr_warn("encryption failed: %i\n", rc);
+		kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
 	skb->skb_iif = dev->ifindex;
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
@@ -344,13 +352,22 @@ static struct header_ops mac802154_header_ops = {
 };
 
 static const struct net_device_ops mac802154_wpan_ops = {
-	.ndo_open		= mac802154_slave_open,
+	.ndo_open		= mac802154_wpan_open,
 	.ndo_stop		= mac802154_slave_close,
 	.ndo_start_xmit		= mac802154_wpan_xmit,
 	.ndo_do_ioctl		= mac802154_wpan_ioctl,
 	.ndo_set_mac_address	= mac802154_wpan_mac_addr,
 };
 
+static void mac802154_wpan_free(struct net_device *dev)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+
+	mac802154_llsec_destroy(&priv->sec);
+
+	free_netdev(dev);
+}
+
 void mac802154_wpan_setup(struct net_device *dev)
 {
 	struct mac802154_sub_if_data *priv;
@@ -360,14 +377,14 @@ void mac802154_wpan_setup(struct net_device *dev)
 
 	dev->hard_header_len	= MAC802154_FRAME_HARD_HEADER_LEN;
 	dev->header_ops		= &mac802154_header_ops;
-	dev->needed_tailroom	= 2; /* FCS */
+	dev->needed_tailroom	= 2 + 16; /* FCS + MIC */
 	dev->mtu		= IEEE802154_MTU;
 	dev->tx_queue_len	= 300;
 	dev->type		= ARPHRD_IEEE802154;
 	dev->flags		= IFF_NOARP | IFF_BROADCAST;
 	dev->watchdog_timeo	= 0;
 
-	dev->destructor		= free_netdev;
+	dev->destructor		= mac802154_wpan_free;
 	dev->netdev_ops		= &mac802154_wpan_ops;
 	dev->ml_priv		= &mac802154_mlme_wpan;
 
@@ -378,12 +395,21 @@ void mac802154_wpan_setup(struct net_device *dev)
 	priv->page = 0;
 
 	spin_lock_init(&priv->mib_lock);
+	mutex_init(&priv->sec_mtx);
 
 	get_random_bytes(&priv->bsn, 1);
 	get_random_bytes(&priv->dsn, 1);
 
-	priv->pan_id = IEEE802154_PANID_BROADCAST;
-	priv->short_addr = IEEE802154_ADDR_BROADCAST;
+	/* defaults per 802.15.4-2011 */
+	priv->mac_params.min_be = 3;
+	priv->mac_params.max_be = 5;
+	priv->mac_params.csma_retries = 4;
+	priv->mac_params.frame_retries = -1; /* for compatibility, actual default is 3 */
+
+	priv->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
+	priv->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+
+	mac802154_llsec_init(&priv->sec);
 }
 
 static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb)
@@ -392,15 +418,22 @@ static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb)
 }
 
 static int
-mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb)
+mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb,
+		      const struct ieee802154_hdr *hdr)
 {
+	__le16 span, sshort;
+	int rc;
+
 	pr_debug("getting packet via slave interface %s\n", sdata->dev->name);
 
 	spin_lock_bh(&sdata->mib_lock);
 
-	switch (mac_cb(skb)->da.addr_type) {
+	span = sdata->pan_id;
+	sshort = sdata->short_addr;
+
+	switch (mac_cb(skb)->dest.mode) {
 	case IEEE802154_ADDR_NONE:
-		if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE)
+		if (mac_cb(skb)->dest.mode != IEEE802154_ADDR_NONE)
 			/* FIXME: check if we are PAN coordinator */
 			skb->pkt_type = PACKET_OTHERHOST;
 		else
@@ -408,23 +441,22 @@ mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb)
 			skb->pkt_type = PACKET_HOST;
 		break;
 	case IEEE802154_ADDR_LONG:
-		if (mac_cb(skb)->da.pan_id != sdata->pan_id &&
-		    mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST)
+		if (mac_cb(skb)->dest.pan_id != span &&
+		    mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST))
 			skb->pkt_type = PACKET_OTHERHOST;
-		else if (!memcmp(mac_cb(skb)->da.hwaddr, sdata->dev->dev_addr,
-				 IEEE802154_ADDR_LEN))
+		else if (mac_cb(skb)->dest.extended_addr == sdata->extended_addr)
 			skb->pkt_type = PACKET_HOST;
 		else
 			skb->pkt_type = PACKET_OTHERHOST;
 		break;
 	case IEEE802154_ADDR_SHORT:
-		if (mac_cb(skb)->da.pan_id != sdata->pan_id &&
-		    mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST)
+		if (mac_cb(skb)->dest.pan_id != span &&
+		    mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST))
 			skb->pkt_type = PACKET_OTHERHOST;
-		else if (mac_cb(skb)->da.short_addr == sdata->short_addr)
+		else if (mac_cb(skb)->dest.short_addr == sshort)
 			skb->pkt_type = PACKET_HOST;
-		else if (mac_cb(skb)->da.short_addr ==
-					IEEE802154_ADDR_BROADCAST)
+		else if (mac_cb(skb)->dest.short_addr ==
+			  cpu_to_le16(IEEE802154_ADDR_BROADCAST))
 			skb->pkt_type = PACKET_BROADCAST;
 		else
 			skb->pkt_type = PACKET_OTHERHOST;
@@ -437,111 +469,108 @@ mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb)
 
 	skb->dev = sdata->dev;
 
+	rc = mac802154_llsec_decrypt(&sdata->sec, skb);
+	if (rc) {
+		pr_debug("decryption failed: %i\n", rc);
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+
 	sdata->dev->stats.rx_packets++;
 	sdata->dev->stats.rx_bytes += skb->len;
 
-	switch (mac_cb_type(skb)) {
+	switch (mac_cb(skb)->type) {
 	case IEEE802154_FC_TYPE_DATA:
 		return mac802154_process_data(sdata->dev, skb);
 	default:
-		pr_warning("ieee802154: bad frame received (type = %d)\n",
-			   mac_cb_type(skb));
+		pr_warn("ieee802154: bad frame received (type = %d)\n",
+			mac_cb(skb)->type);
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
 }
 
-static int mac802154_parse_frame_start(struct sk_buff *skb)
+static void mac802154_print_addr(const char *name,
+				 const struct ieee802154_addr *addr)
 {
-	u8 *head = skb->data;
-	u16 fc;
-
-	if (mac802154_fetch_skb_u16(skb, &fc) ||
-	    mac802154_fetch_skb_u8(skb, &(mac_cb(skb)->seq)))
-		goto err;
-
-	pr_debug("fc: %04x dsn: %02x\n", fc, head[2]);
-
-	mac_cb(skb)->flags = IEEE802154_FC_TYPE(fc);
-	mac_cb(skb)->sa.addr_type = IEEE802154_FC_SAMODE(fc);
-	mac_cb(skb)->da.addr_type = IEEE802154_FC_DAMODE(fc);
-
-	if (fc & IEEE802154_FC_INTRA_PAN)
-		mac_cb(skb)->flags |= MAC_CB_FLAG_INTRAPAN;
+	if (addr->mode == IEEE802154_ADDR_NONE)
+		pr_debug("%s not present\n", name);
 
-	if (mac_cb(skb)->da.addr_type != IEEE802154_ADDR_NONE) {
-		if (mac802154_fetch_skb_u16(skb, &(mac_cb(skb)->da.pan_id)))
-			goto err;
+	pr_debug("%s PAN ID: %04x\n", name, le16_to_cpu(addr->pan_id));
+	if (addr->mode == IEEE802154_ADDR_SHORT) {
+		pr_debug("%s is short: %04x\n", name,
+			 le16_to_cpu(addr->short_addr));
+	} else {
+		u64 hw = swab64((__force u64) addr->extended_addr);
 
-		/* source PAN id compression */
-		if (mac_cb_is_intrapan(skb))
-			mac_cb(skb)->sa.pan_id = mac_cb(skb)->da.pan_id;
+		pr_debug("%s is hardware: %8phC\n", name, &hw);
+	}
+}
 
-		pr_debug("dest PAN addr: %04x\n", mac_cb(skb)->da.pan_id);
+static int mac802154_parse_frame_start(struct sk_buff *skb,
+				       struct ieee802154_hdr *hdr)
+{
+	int hlen;
+	struct ieee802154_mac_cb *cb = mac_cb_init(skb);
 
-		if (mac_cb(skb)->da.addr_type == IEEE802154_ADDR_SHORT) {
-			u16 *da = &(mac_cb(skb)->da.short_addr);
+	hlen = ieee802154_hdr_pull(skb, hdr);
+	if (hlen < 0)
+		return -EINVAL;
 
-			if (mac802154_fetch_skb_u16(skb, da))
-				goto err;
+	skb->mac_len = hlen;
 
-			pr_debug("destination address is short: %04x\n",
-				 mac_cb(skb)->da.short_addr);
-		} else {
-			if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN))
-				goto err;
+	pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr->fc),
+		 hdr->seq);
 
-			mac802154_haddr_copy_swap(mac_cb(skb)->da.hwaddr,
-						  skb->data);
-			skb_pull(skb, IEEE802154_ADDR_LEN);
+	cb->type = hdr->fc.type;
+	cb->ackreq = hdr->fc.ack_request;
+	cb->secen = hdr->fc.security_enabled;
 
-			pr_debug("destination address is hardware\n");
-		}
-	}
+	mac802154_print_addr("destination", &hdr->dest);
+	mac802154_print_addr("source", &hdr->source);
 
-	if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE) {
-		/* non PAN-compression, fetch source address id */
-		if (!(mac_cb_is_intrapan(skb))) {
-			u16 *sa_pan = &(mac_cb(skb)->sa.pan_id);
-
-			if (mac802154_fetch_skb_u16(skb, sa_pan))
-				goto err;
-		}
+	cb->source = hdr->source;
+	cb->dest = hdr->dest;
 
-		pr_debug("source PAN addr: %04x\n", mac_cb(skb)->da.pan_id);
+	if (hdr->fc.security_enabled) {
+		u64 key;
 
-		if (mac_cb(skb)->sa.addr_type == IEEE802154_ADDR_SHORT) {
-			u16 *sa = &(mac_cb(skb)->sa.short_addr);
+		pr_debug("seclevel %i\n", hdr->sec.level);
 
-			if (mac802154_fetch_skb_u16(skb, sa))
-				goto err;
+		switch (hdr->sec.key_id_mode) {
+		case IEEE802154_SCF_KEY_IMPLICIT:
+			pr_debug("implicit key\n");
+			break;
 
-			pr_debug("source address is short: %04x\n",
-				 mac_cb(skb)->sa.short_addr);
-		} else {
-			if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN))
-				goto err;
+		case IEEE802154_SCF_KEY_INDEX:
+			pr_debug("key %02x\n", hdr->sec.key_id);
+			break;
 
-			mac802154_haddr_copy_swap(mac_cb(skb)->sa.hwaddr,
-						  skb->data);
-			skb_pull(skb, IEEE802154_ADDR_LEN);
+		case IEEE802154_SCF_KEY_SHORT_INDEX:
+			pr_debug("key %04x:%04x %02x\n",
+				 le32_to_cpu(hdr->sec.short_src) >> 16,
+				 le32_to_cpu(hdr->sec.short_src) & 0xffff,
+				 hdr->sec.key_id);
+			break;
 
-			pr_debug("source address is hardware\n");
+		case IEEE802154_SCF_KEY_HW_INDEX:
+			key = swab64((__force u64) hdr->sec.extended_src);
+			pr_debug("key source %8phC %02x\n", &key,
+				 hdr->sec.key_id);
+			break;
 		}
 	}
 
 	return 0;
-err:
-	return -EINVAL;
 }
 
 void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb)
 {
 	int ret;
-	struct sk_buff *sskb;
 	struct mac802154_sub_if_data *sdata;
+	struct ieee802154_hdr hdr;
 
-	ret = mac802154_parse_frame_start(skb);
+	ret = mac802154_parse_frame_start(skb, &hdr);
 	if (ret) {
 		pr_debug("got invalid frame\n");
 		return;
@@ -549,12 +578,16 @@ void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdata, &priv->slaves, list) {
-		if (sdata->type != IEEE802154_DEV_WPAN)
+		if (sdata->type != IEEE802154_DEV_WPAN ||
+		    !netif_running(sdata->dev))
 			continue;
 
-		sskb = skb_clone(skb, GFP_ATOMIC);
-		if (sskb)
-			mac802154_subif_frame(sdata, sskb);
+		mac802154_subif_frame(sdata, skb, &hdr);
+		skb = NULL;
+		break;
 	}
 	rcu_read_unlock();
+
+	if (skb)
+		kfree_skb(skb);
 }
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index 851cd880b0c..6b38d083e1c 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -33,6 +33,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_DODGY |
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
+				  SKB_GSO_GRE_CSUM |
 				  SKB_GSO_IPIP |
 				  SKB_GSO_MPLS)))
 		goto out;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index c3398cd99b9..e9410d17619 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -414,47 +414,116 @@ config NETFILTER_SYNPROXY
 endif # NF_CONNTRACK
 
 config NF_TABLES
-	depends on NETFILTER_NETLINK
+	select NETFILTER_NETLINK
 	tristate "Netfilter nf_tables support"
+	help
+	  nftables is the new packet classification framework that intends to
+	  replace the existing {ip,ip6,arp,eb}_tables infrastructure. It
+	  provides a pseudo-state machine with an extensible instruction-set
+	  (also known as expressions) that the userspace 'nft' utility
+	  (http://www.netfilter.org/projects/nftables) uses to build the
+	  rule-set. It also comes with the generic set infrastructure that
+	  allows you to construct mappings between matchings and actions
+	  for performance lookups.
+
+	  To compile it as a module, choose M here.
+
+config NF_TABLES_INET
+	depends on NF_TABLES && IPV6
+	select NF_TABLES_IPV4
+	select NF_TABLES_IPV6
+	tristate "Netfilter nf_tables mixed IPv4/IPv6 tables support"
+	help
+	  This option enables support for a mixed IPv4/IPv6 "inet" table.
 
 config NFT_EXTHDR
 	depends on NF_TABLES
 	tristate "Netfilter nf_tables IPv6 exthdr module"
+	help
+	  This option adds the "exthdr" expression that you can use to match
+	  IPv6 extension headers.
 
 config NFT_META
 	depends on NF_TABLES
 	tristate "Netfilter nf_tables meta module"
+	help
+	  This option adds the "meta" expression that you can use to match and
+	  to set packet metainformation such as the packet mark.
 
 config NFT_CT
 	depends on NF_TABLES
 	depends on NF_CONNTRACK
 	tristate "Netfilter nf_tables conntrack module"
+	help
+	  This option adds the "meta" expression that you can use to match
+	  connection tracking information such as the flow state.
 
 config NFT_RBTREE
 	depends on NF_TABLES
 	tristate "Netfilter nf_tables rbtree set module"
+	help
+	  This option adds the "rbtree" set type (Red Black tree) that is used
+	  to build interval-based sets.
 
 config NFT_HASH
 	depends on NF_TABLES
 	tristate "Netfilter nf_tables hash set module"
+	help
+	  This option adds the "hash" set type that is used to build one-way
+	  mappings between matchings and actions.
 
 config NFT_COUNTER
 	depends on NF_TABLES
 	tristate "Netfilter nf_tables counter module"
+	help
+	  This option adds the "counter" expression that you can use to
+	  include packet and byte counters in a rule.
 
 config NFT_LOG
 	depends on NF_TABLES
 	tristate "Netfilter nf_tables log module"
+	help
+	  This option adds the "log" expression that you can use to log
+	  packets matching some criteria.
 
 config NFT_LIMIT
 	depends on NF_TABLES
 	tristate "Netfilter nf_tables limit module"
+	help
+	  This option adds the "limit" expression that you can use to
+	  ratelimit rule matchings.
 
 config NFT_NAT
 	depends on NF_TABLES
 	depends on NF_CONNTRACK
 	depends on NF_NAT
 	tristate "Netfilter nf_tables nat module"
+	help
+	  This option adds the "nat" expression that you can use to perform
+	  typical Network Address Translation (NAT) packet transformations.
+
+config NFT_QUEUE
+	depends on NF_TABLES
+	depends on NETFILTER_XTABLES
+	depends on NETFILTER_NETLINK_QUEUE
+	tristate "Netfilter nf_tables queue module"
+	help
+	  This is required if you intend to use the userspace queueing
+	  infrastructure (also known as NFQUEUE) from nftables.
+
+config NFT_REJECT
+	depends on NF_TABLES
+	default m if NETFILTER_ADVANCED=n
+	tristate "Netfilter nf_tables reject support"
+	help
+	  This option adds the "reject" expression that you can use to
+	  explicitly deny and notify via TCP reset/ICMP informational errors
+	  unallowed traffic.
+
+config NFT_REJECT_INET
+	depends on NF_TABLES_INET
+	default NFT_REJECT
+	tristate
 
 config NFT_COMPAT
 	depends on NF_TABLES
@@ -858,6 +927,16 @@ config NETFILTER_XT_MATCH_BPF
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NETFILTER_XT_MATCH_CGROUP
+	tristate '"control group" match support'
+	depends on NETFILTER_ADVANCED
+	depends on CGROUPS
+	select CGROUP_NET_CLASSID
+	---help---
+	Socket/process control group matching allows you to match locally
+	generated packets based on which net_cls control group processes
+	belong to.
+
 config NETFILTER_XT_MATCH_CLUSTER
 	tristate '"cluster" match support'
 	depends on NF_CONNTRACK
@@ -1035,6 +1114,15 @@ config NETFILTER_XT_MATCH_HL
 	in the IPv6 header, or the time-to-live field in the IPv4
 	header of the packet.
 
+config NETFILTER_XT_MATCH_IPCOMP
+	tristate '"ipcomp" match support'
+	depends on NETFILTER_ADVANCED
+	help
+	  This match extension allows you to match a range of CPIs(16 bits)
+	  inside IPComp header of IPSec packets.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config NETFILTER_XT_MATCH_IPRANGE
 	tristate '"iprange" address range match support'
 	depends on NETFILTER_ADVANCED
@@ -1055,6 +1143,16 @@ config NETFILTER_XT_MATCH_IPVS
 
 	  If unsure, say N.
 
+config NETFILTER_XT_MATCH_L2TP
+	tristate '"l2tp" match support'
+	depends on NETFILTER_ADVANCED
+	default L2TP
+	---help---
+	This option adds an "L2TP" match, which allows you to match against
+	L2TP protocol header fields.
+
+	To compile it as a module, choose M here. If unsure, say N.
+
 config NETFILTER_XT_MATCH_LENGTH
 	tristate '"length" match support'
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 394483b2c19..bffdad774da 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -70,13 +70,16 @@ nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o
 nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o
 
 obj-$(CONFIG_NF_TABLES)		+= nf_tables.o
+obj-$(CONFIG_NF_TABLES_INET)	+= nf_tables_inet.o
 obj-$(CONFIG_NFT_COMPAT)	+= nft_compat.o
 obj-$(CONFIG_NFT_EXTHDR)	+= nft_exthdr.o
 obj-$(CONFIG_NFT_META)		+= nft_meta.o
 obj-$(CONFIG_NFT_CT)		+= nft_ct.o
 obj-$(CONFIG_NFT_LIMIT)		+= nft_limit.o
 obj-$(CONFIG_NFT_NAT)		+= nft_nat.o
-#nf_tables-objs			+= nft_meta_target.o
+obj-$(CONFIG_NFT_QUEUE)		+= nft_queue.o
+obj-$(CONFIG_NFT_REJECT) 	+= nft_reject.o
+obj-$(CONFIG_NFT_REJECT_INET)	+= nft_reject_inet.o
 obj-$(CONFIG_NFT_RBTREE)	+= nft_rbtree.o
 obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
@@ -133,8 +136,10 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_IPCOMP) += xt_ipcomp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_IPVS) += xt_ipvs.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_L2TP) += xt_l2tp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o
@@ -142,6 +147,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_MULTIPORT) += xt_multiport.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_NFACCT) += xt_nfacct.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_OSF) += xt_osf.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_OWNER) += xt_owner.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_CGROUP) += xt_cgroup.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o
diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig
index a2d6263b6c6..2f7f5c32c6f 100644
--- a/net/netfilter/ipset/Kconfig
+++ b/net/netfilter/ipset/Kconfig
@@ -21,7 +21,7 @@ config IP_SET_MAX
 	  You can define here default value of the maximum number 
 	  of IP sets for the kernel.
 
-	  The value can be overriden by the 'max_sets' module
+	  The value can be overridden by the 'max_sets' module
 	  parameter of the 'ip_set' module.
 
 config IP_SET_BITMAP_IP
@@ -61,6 +61,15 @@ config IP_SET_HASH_IP
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config IP_SET_HASH_IPMARK
+	tristate "hash:ip,mark set support"
+	depends on IP_SET
+	help
+	  This option adds the hash:ip,mark set type support, by which one
+	  can store IPv4/IPv6 address and mark pairs.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config IP_SET_HASH_IPPORT
 	tristate "hash:ip,port set support"
 	depends on IP_SET
diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile
index 44b2d38476f..231f10196cb 100644
--- a/net/netfilter/ipset/Makefile
+++ b/net/netfilter/ipset/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_IP_SET_BITMAP_PORT) += ip_set_bitmap_port.o
 
 # hash types
 obj-$(CONFIG_IP_SET_HASH_IP) += ip_set_hash_ip.o
+obj-$(CONFIG_IP_SET_HASH_IPMARK) += ip_set_hash_ipmark.o
 obj-$(CONFIG_IP_SET_HASH_IPPORT) += ip_set_hash_ipport.o
 obj-$(CONFIG_IP_SET_HASH_IPPORTIP) += ip_set_hash_ipportip.o
 obj-$(CONFIG_IP_SET_HASH_IPPORTNET) += ip_set_hash_ipportnet.o
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index bac7e01df67..ec8114fae50 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -54,10 +54,10 @@ MODULE_DESCRIPTION("core IP set support");
 MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
 
 /* When the nfnl mutex is held: */
-#define nfnl_dereference(p)		\
+#define ip_set_dereference(p)		\
 	rcu_dereference_protected(p, 1)
-#define nfnl_set(inst, id)			\
-	nfnl_dereference((inst)->ip_set_list)[id]
+#define ip_set(inst, id)		\
+	ip_set_dereference((inst)->ip_set_list)[id]
 
 /*
  * The set types are implemented in modules and registered set types
@@ -271,10 +271,7 @@ ip_set_free(void *members)
 {
 	pr_debug("%p: free with %s\n", members,
 		 is_vmalloc_addr(members) ? "vfree" : "kfree");
-	if (is_vmalloc_addr(members))
-		vfree(members);
-	else
-		kfree(members);
+	kvfree(members);
 }
 EXPORT_SYMBOL_GPL(ip_set_free);
 
@@ -368,6 +365,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len)
 
 	if (tb[IPSET_ATTR_CADT_FLAGS])
 		cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+	if (cadt_flags & IPSET_FLAG_WITH_FORCEADD)
+		set->flags |= IPSET_CREATE_FLAG_FORCEADD;
 	for (id = 0; id < IPSET_EXT_ID_MAX; id++) {
 		if (!add_extension(id, cadt_flags, tb))
 			continue;
@@ -510,7 +509,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
 
 	if (opt->dim < set->type->dimension ||
 	    !(opt->family == set->family || set->family == NFPROTO_UNSPEC))
-		return 0;
+		return -IPSET_ERR_TYPE_MISMATCH;
 
 	write_lock_bh(&set->lock);
 	ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt);
@@ -533,7 +532,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
 
 	if (opt->dim < set->type->dimension ||
 	    !(opt->family == set->family || set->family == NFPROTO_UNSPEC))
-		return 0;
+		return -IPSET_ERR_TYPE_MISMATCH;
 
 	write_lock_bh(&set->lock);
 	ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt);
@@ -625,34 +624,6 @@ EXPORT_SYMBOL_GPL(ip_set_name_byindex);
  */
 
 /*
- * Find set by name, reference it once. The reference makes sure the
- * thing pointed to, does not go away under our feet.
- *
- * The nfnl mutex is used in the function.
- */
-ip_set_id_t
-ip_set_nfnl_get(struct net *net, const char *name)
-{
-	ip_set_id_t i, index = IPSET_INVALID_ID;
-	struct ip_set *s;
-	struct ip_set_net *inst = ip_set_pernet(net);
-
-	nfnl_lock(NFNL_SUBSYS_IPSET);
-	for (i = 0; i < inst->ip_set_max; i++) {
-		s = nfnl_set(inst, i);
-		if (s != NULL && STREQ(s->name, name)) {
-			__ip_set_get(s);
-			index = i;
-			break;
-		}
-	}
-	nfnl_unlock(NFNL_SUBSYS_IPSET);
-
-	return index;
-}
-EXPORT_SYMBOL_GPL(ip_set_nfnl_get);
-
-/*
  * Find set by index, reference it once. The reference makes sure the
  * thing pointed to, does not go away under our feet.
  *
@@ -668,7 +639,7 @@ ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index)
 		return IPSET_INVALID_ID;
 
 	nfnl_lock(NFNL_SUBSYS_IPSET);
-	set = nfnl_set(inst, index);
+	set = ip_set(inst, index);
 	if (set)
 		__ip_set_get(set);
 	else
@@ -694,7 +665,7 @@ ip_set_nfnl_put(struct net *net, ip_set_id_t index)
 
 	nfnl_lock(NFNL_SUBSYS_IPSET);
 	if (!inst->is_deleted) { /* already deleted from ip_set_net_exit() */
-		set = nfnl_set(inst, index);
+		set = ip_set(inst, index);
 		if (set != NULL)
 			__ip_set_put(set);
 	}
@@ -762,7 +733,7 @@ find_set_and_id(struct ip_set_net *inst, const char *name, ip_set_id_t *id)
 
 	*id = IPSET_INVALID_ID;
 	for (i = 0; i < inst->ip_set_max; i++) {
-		set = nfnl_set(inst, i);
+		set = ip_set(inst, i);
 		if (set != NULL && STREQ(set->name, name)) {
 			*id = i;
 			break;
@@ -788,7 +759,7 @@ find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index,
 
 	*index = IPSET_INVALID_ID;
 	for (i = 0;  i < inst->ip_set_max; i++) {
-		s = nfnl_set(inst, i);
+		s = ip_set(inst, i);
 		if (s == NULL) {
 			if (*index == IPSET_INVALID_ID)
 				*index = i;
@@ -911,7 +882,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 		if (!list)
 			goto cleanup;
 		/* nfnl mutex is held, both lists are valid */
-		tmp = nfnl_dereference(inst->ip_set_list);
+		tmp = ip_set_dereference(inst->ip_set_list);
 		memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max);
 		rcu_assign_pointer(inst->ip_set_list, list);
 		/* Make sure all current packets have passed through */
@@ -928,7 +899,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 	 * Finally! Add our shiny new set to the list, and be done.
 	 */
 	pr_debug("create: '%s' created with index %u!\n", set->name, index);
-	nfnl_set(inst, index) = set;
+	ip_set(inst, index) = set;
 
 	return ret;
 
@@ -953,10 +924,10 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = {
 static void
 ip_set_destroy_set(struct ip_set_net *inst, ip_set_id_t index)
 {
-	struct ip_set *set = nfnl_set(inst, index);
+	struct ip_set *set = ip_set(inst, index);
 
 	pr_debug("set: %s\n",  set->name);
-	nfnl_set(inst, index) = NULL;
+	ip_set(inst, index) = NULL;
 
 	/* Must call it without holding any lock */
 	set->variant->destroy(set);
@@ -990,7 +961,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
 	read_lock_bh(&ip_set_ref_lock);
 	if (!attr[IPSET_ATTR_SETNAME]) {
 		for (i = 0; i < inst->ip_set_max; i++) {
-			s = nfnl_set(inst, i);
+			s = ip_set(inst, i);
 			if (s != NULL && s->ref) {
 				ret = -IPSET_ERR_BUSY;
 				goto out;
@@ -998,7 +969,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
 		}
 		read_unlock_bh(&ip_set_ref_lock);
 		for (i = 0; i < inst->ip_set_max; i++) {
-			s = nfnl_set(inst, i);
+			s = ip_set(inst, i);
 			if (s != NULL)
 				ip_set_destroy_set(inst, i);
 		}
@@ -1048,7 +1019,7 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb,
 
 	if (!attr[IPSET_ATTR_SETNAME]) {
 		for (i = 0; i < inst->ip_set_max; i++) {
-			s = nfnl_set(inst, i);
+			s = ip_set(inst, i);
 			if (s != NULL)
 				ip_set_flush_set(s);
 		}
@@ -1102,7 +1073,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
 
 	name2 = nla_data(attr[IPSET_ATTR_SETNAME2]);
 	for (i = 0; i < inst->ip_set_max; i++) {
-		s = nfnl_set(inst, i);
+		s = ip_set(inst, i);
 		if (s != NULL && STREQ(s->name, name2)) {
 			ret = -IPSET_ERR_EXIST_SETNAME2;
 			goto out;
@@ -1162,8 +1133,8 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
 
 	write_lock_bh(&ip_set_ref_lock);
 	swap(from->ref, to->ref);
-	nfnl_set(inst, from_id) = to;
-	nfnl_set(inst, to_id) = from;
+	ip_set(inst, from_id) = to;
+	ip_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
 	return 0;
@@ -1185,7 +1156,7 @@ ip_set_dump_done(struct netlink_callback *cb)
 	struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET];
 	if (cb->args[IPSET_CB_ARG0]) {
 		pr_debug("release set %s\n",
-			 nfnl_set(inst, cb->args[IPSET_CB_INDEX])->name);
+			 ip_set(inst, cb->args[IPSET_CB_INDEX])->name);
 		__ip_set_put_byindex(inst,
 			(ip_set_id_t) cb->args[IPSET_CB_INDEX]);
 	}
@@ -1282,7 +1253,7 @@ dump_last:
 		 dump_type, dump_flags, cb->args[IPSET_CB_INDEX]);
 	for (; cb->args[IPSET_CB_INDEX] < max; cb->args[IPSET_CB_INDEX]++) {
 		index = (ip_set_id_t) cb->args[IPSET_CB_INDEX];
-		set = nfnl_set(inst, index);
+		set = ip_set(inst, index);
 		if (set == NULL) {
 			if (dump_type == DUMP_ONE) {
 				ret = -ENOENT;
@@ -1360,7 +1331,7 @@ next_set:
 release_refcount:
 	/* If there was an error or set is done, release set */
 	if (ret || !cb->args[IPSET_CB_ARG0]) {
-		pr_debug("release set %s\n", nfnl_set(inst, index)->name);
+		pr_debug("release set %s\n", ip_set(inst, index)->name);
 		__ip_set_put_byindex(inst, index);
 		cb->args[IPSET_CB_ARG0] = 0;
 	}
@@ -1915,7 +1886,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 		find_set_and_id(inst, req_get->set.name, &id);
 		req_get->set.index = id;
 		if (id != IPSET_INVALID_ID)
-			req_get->family = nfnl_set(inst, id)->family;
+			req_get->family = ip_set(inst, id)->family;
 		nfnl_unlock(NFNL_SUBSYS_IPSET);
 		goto copy;
 	}
@@ -1929,7 +1900,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 			goto done;
 		}
 		nfnl_lock(NFNL_SUBSYS_IPSET);
-		set = nfnl_set(inst, req_get->set.index);
+		set = ip_set(inst, req_get->set.index);
 		strncpy(req_get->set.name, set ? set->name : "",
 			IPSET_MAXNAMELEN);
 		nfnl_unlock(NFNL_SUBSYS_IPSET);
@@ -1973,7 +1944,6 @@ ip_set_net_init(struct net *net)
 		return -ENOMEM;
 	inst->is_deleted = 0;
 	rcu_assign_pointer(inst->ip_set_list, list);
-	pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL);
 	return 0;
 }
 
@@ -1988,7 +1958,7 @@ ip_set_net_exit(struct net *net)
 	inst->is_deleted = 1; /* flag for ip_set_nfnl_put */
 
 	for (i = 0; i < inst->ip_set_max; i++) {
-		set = nfnl_set(inst, i);
+		set = ip_set(inst, i);
 		if (set != NULL)
 			ip_set_destroy_set(inst, i);
 	}
@@ -2024,6 +1994,7 @@ ip_set_init(void)
 		nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
 		return ret;
 	}
+	pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL);
 	return 0;
 }
 
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index be6932ad3a8..61c7fb05280 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -263,6 +263,9 @@ struct htype {
 	u32 maxelem;		/* max elements in the hash */
 	u32 elements;		/* current element (vs timeout) */
 	u32 initval;		/* random jhash init value */
+#ifdef IP_SET_HASH_WITH_MARKMASK
+	u32 markmask;		/* markmask value for mark mask to store */
+#endif
 	struct timer_list gc;	/* garbage collection when timeout enabled */
 	struct mtype_elem next; /* temporary storage for uadd */
 #ifdef IP_SET_HASH_WITH_MULTI
@@ -454,6 +457,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b)
 #ifdef IP_SET_HASH_WITH_NETMASK
 	       x->netmask == y->netmask &&
 #endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+	       x->markmask == y->markmask &&
+#endif
 	       a->extensions == b->extensions;
 }
 
@@ -627,6 +633,18 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	bool flag_exist = flags & IPSET_FLAG_EXIST;
 	u32 key, multi = 0;
 
+	if (h->elements >= h->maxelem && SET_WITH_FORCEADD(set)) {
+		rcu_read_lock_bh();
+		t = rcu_dereference_bh(h->table);
+		key = HKEY(value, h->initval, t->htable_bits);
+		n = hbucket(t,key);
+		if (n->pos) {
+			/* Choosing the first entry in the array to replace */
+			j = 0;
+			goto reuse_slot;
+		}
+		rcu_read_unlock_bh();
+	}
 	if (SET_WITH_TIMEOUT(set) && h->elements >= h->maxelem)
 		/* FIXME: when set is full, we slow down here */
 		mtype_expire(set, h, NLEN(set->family), set->dsize);
@@ -908,6 +926,10 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	    nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask))
 		goto nla_put_failure;
 #endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+	if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask))
+		goto nla_put_failure;
+#endif
 	if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
 	    nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)))
 		goto nla_put_failure;
@@ -1016,6 +1038,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 			    struct nlattr *tb[], u32 flags)
 {
 	u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
+#ifdef IP_SET_HASH_WITH_MARKMASK
+	u32 markmask;
+#endif
 	u8 hbits;
 #ifdef IP_SET_HASH_WITH_NETMASK
 	u8 netmask;
@@ -1026,6 +1051,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 
 	if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
 		return -IPSET_ERR_INVALID_FAMILY;
+
+#ifdef IP_SET_HASH_WITH_MARKMASK
+	markmask = 0xffffffff;
+#endif
 #ifdef IP_SET_HASH_WITH_NETMASK
 	netmask = set->family == NFPROTO_IPV4 ? 32 : 128;
 	pr_debug("Create set %s with family %s\n",
@@ -1034,6 +1063,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 
 	if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
+#ifdef IP_SET_HASH_WITH_MARKMASK
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_MARKMASK) ||
+#endif
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
 		return -IPSET_ERR_PROTOCOL;
@@ -1057,6 +1089,14 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 			return -IPSET_ERR_INVALID_NETMASK;
 	}
 #endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+	if (tb[IPSET_ATTR_MARKMASK]) {
+		markmask = ntohl(nla_get_u32(tb[IPSET_ATTR_MARKMASK]));
+
+		if ((markmask > 4294967295u) || markmask == 0)
+			return -IPSET_ERR_INVALID_MARKMASK;
+	}
+#endif
 
 	hsize = sizeof(*h);
 #ifdef IP_SET_HASH_WITH_NETS
@@ -1071,6 +1111,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 #ifdef IP_SET_HASH_WITH_NETMASK
 	h->netmask = netmask;
 #endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+	h->markmask = markmask;
+#endif
 	get_random_bytes(&h->initval, sizeof(h->initval));
 	set->timeout = IPSET_NO_TIMEOUT;
 
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index e65fc2423d5..dd40607f878 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -25,7 +25,8 @@
 
 #define IPSET_TYPE_REV_MIN	0
 /*				1	   Counters support */
-#define IPSET_TYPE_REV_MAX	2	/* Comments support */
+/*				2	   Comments support */
+#define IPSET_TYPE_REV_MAX	3	/* Forceadd support */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
new file mode 100644
index 00000000000..4eff0a29725
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -0,0 +1,321 @@
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ * Copyright (C) 2013 Smoothwall Ltd. <vytas.dauksa@smoothwall.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the hash:ip,mark type */
+
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/netlink.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_hash.h>
+
+#define IPSET_TYPE_REV_MIN	0
+#define IPSET_TYPE_REV_MAX	1	/* Forceadd support */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>");
+IP_SET_MODULE_DESC("hash:ip,mark", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
+MODULE_ALIAS("ip_set_hash:ip,mark");
+
+/* Type specific function prefix */
+#define HTYPE		hash_ipmark
+#define IP_SET_HASH_WITH_MARKMASK
+
+/* IPv4 variant */
+
+/* Member elements */
+struct hash_ipmark4_elem {
+	__be32 ip;
+	__u32 mark;
+};
+
+/* Common functions */
+
+static inline bool
+hash_ipmark4_data_equal(const struct hash_ipmark4_elem *ip1,
+			const struct hash_ipmark4_elem *ip2,
+			u32 *multi)
+{
+	return ip1->ip == ip2->ip &&
+	       ip1->mark == ip2->mark;
+}
+
+static bool
+hash_ipmark4_data_list(struct sk_buff *skb,
+		       const struct hash_ipmark4_elem *data)
+{
+	if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) ||
+	    nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return 1;
+}
+
+static inline void
+hash_ipmark4_data_next(struct hash_ipmark4_elem *next,
+		       const struct hash_ipmark4_elem *d)
+{
+	next->ip = d->ip;
+}
+
+#define MTYPE           hash_ipmark4
+#define PF              4
+#define HOST_MASK       32
+#define HKEY_DATALEN	sizeof(struct hash_ipmark4_elem)
+#include "ip_set_hash_gen.h"
+
+static int
+hash_ipmark4_kadt(struct ip_set *set, const struct sk_buff *skb,
+		  const struct xt_action_param *par,
+		  enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+	const struct hash_ipmark *h = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	struct hash_ipmark4_elem e = { };
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+	e.mark = skb->mark;
+	e.mark &= h->markmask;
+
+	ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+	return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
+		  enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+	const struct hash_ipmark *h = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	struct hash_ipmark4_elem e = { };
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+	u32 ip, ip_to = 0;
+	int ret;
+
+	if (unlikely(!tb[IPSET_ATTR_IP] ||
+		     !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_LINENO])
+		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+	ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) ||
+	      ip_set_get_extensions(set, tb, &ext);
+	if (ret)
+		return ret;
+
+	e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK]));
+	e.mark &= h->markmask;
+
+	if (adt == IPSET_TEST ||
+	    !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) {
+		ret = adtfn(set, &e, &ext, &ext, flags);
+		return ip_set_eexist(ret, flags) ? 0 : ret;
+	}
+
+	ip_to = ip = ntohl(e.ip);
+	if (tb[IPSET_ATTR_IP_TO]) {
+		ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
+		if (ret)
+			return ret;
+		if (ip > ip_to)
+			swap(ip, ip_to);
+	} else if (tb[IPSET_ATTR_CIDR]) {
+		u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+		if (!cidr || cidr > 32)
+			return -IPSET_ERR_INVALID_CIDR;
+		ip_set_mask_from_to(ip, ip_to, cidr);
+	}
+
+	if (retried)
+		ip = ntohl(h->next.ip);
+	for (; !before(ip_to, ip); ip++) {
+		e.ip = htonl(ip);
+		ret = adtfn(set, &e, &ext, &ext, flags);
+
+		if (ret && !ip_set_eexist(ret, flags))
+			return ret;
+		else
+			ret = 0;
+	}
+	return ret;
+}
+
+/* IPv6 variant */
+
+struct hash_ipmark6_elem {
+	union nf_inet_addr ip;
+	__u32 mark;
+};
+
+/* Common functions */
+
+static inline bool
+hash_ipmark6_data_equal(const struct hash_ipmark6_elem *ip1,
+			const struct hash_ipmark6_elem *ip2,
+			u32 *multi)
+{
+	return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) &&
+	       ip1->mark == ip2->mark;
+}
+
+static bool
+hash_ipmark6_data_list(struct sk_buff *skb,
+		       const struct hash_ipmark6_elem *data)
+{
+	if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) ||
+	    nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return 1;
+}
+
+static inline void
+hash_ipmark6_data_next(struct hash_ipmark4_elem *next,
+		       const struct hash_ipmark6_elem *d)
+{
+}
+
+#undef MTYPE
+#undef PF
+#undef HOST_MASK
+#undef HKEY_DATALEN
+
+#define MTYPE		hash_ipmark6
+#define PF		6
+#define HOST_MASK	128
+#define HKEY_DATALEN	sizeof(struct hash_ipmark6_elem)
+#define	IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
+
+
+static int
+hash_ipmark6_kadt(struct ip_set *set, const struct sk_buff *skb,
+		  const struct xt_action_param *par,
+		  enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+	const struct hash_ipmark *h = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	struct hash_ipmark6_elem e = { };
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+	e.mark = skb->mark;
+	e.mark &= h->markmask;
+
+	ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+	return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_ipmark6_uadt(struct ip_set *set, struct nlattr *tb[],
+		  enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+	const struct hash_ipmark *h = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	struct hash_ipmark6_elem e = { };
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+	int ret;
+
+	if (unlikely(!tb[IPSET_ATTR_IP] ||
+		     !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) ||
+		     tb[IPSET_ATTR_IP_TO] ||
+		     tb[IPSET_ATTR_CIDR]))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_LINENO])
+		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+	ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+	      ip_set_get_extensions(set, tb, &ext);
+	if (ret)
+		return ret;
+
+	e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK]));
+	e.mark &= h->markmask;
+
+	if (adt == IPSET_TEST) {
+		ret = adtfn(set, &e, &ext, &ext, flags);
+		return ip_set_eexist(ret, flags) ? 0 : ret;
+	}
+
+	ret = adtfn(set, &e, &ext, &ext, flags);
+	if (ret && !ip_set_eexist(ret, flags))
+		return ret;
+	else
+		ret = 0;
+
+	return ret;
+}
+
+static struct ip_set_type hash_ipmark_type __read_mostly = {
+	.name		= "hash:ip,mark",
+	.protocol	= IPSET_PROTOCOL,
+	.features	= IPSET_TYPE_IP | IPSET_TYPE_MARK,
+	.dimension	= IPSET_DIM_TWO,
+	.family		= NFPROTO_UNSPEC,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create		= hash_ipmark_create,
+	.create_policy	= {
+		[IPSET_ATTR_MARKMASK]	= { .type = NLA_U32 },
+		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
+		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
+		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
+		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
+	},
+	.adt_policy	= {
+		[IPSET_ATTR_IP]		= { .type = NLA_NESTED },
+		[IPSET_ATTR_IP_TO]	= { .type = NLA_NESTED },
+		[IPSET_ATTR_MARK]	= { .type = NLA_U32 },
+		[IPSET_ATTR_CIDR]	= { .type = NLA_U8 },
+		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+		[IPSET_ATTR_LINENO]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BYTES]	= { .type = NLA_U64 },
+		[IPSET_ATTR_PACKETS]	= { .type = NLA_U64 },
+		[IPSET_ATTR_COMMENT]	= { .type = NLA_NUL_STRING },
+	},
+	.me		= THIS_MODULE,
+};
+
+static int __init
+hash_ipmark_init(void)
+{
+	return ip_set_type_register(&hash_ipmark_type);
+}
+
+static void __exit
+hash_ipmark_fini(void)
+{
+	ip_set_type_unregister(&hash_ipmark_type);
+}
+
+module_init(hash_ipmark_init);
+module_exit(hash_ipmark_fini);
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 525a595dd1f..7597b82a8b0 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -27,7 +27,8 @@
 #define IPSET_TYPE_REV_MIN	0
 /*				1    SCTP and UDPLITE support added */
 /*				2    Counters support added */
-#define IPSET_TYPE_REV_MAX	3 /* Comments support added */
+/*				3    Comments support added */
+#define IPSET_TYPE_REV_MAX	4 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index f5636631466..672655ffd57 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -27,7 +27,8 @@
 #define IPSET_TYPE_REV_MIN	0
 /*				1    SCTP and UDPLITE support added */
 /*				2    Counters support added */
-#define IPSET_TYPE_REV_MAX	3 /* Comments support added */
+/*				3    Comments support added */
+#define IPSET_TYPE_REV_MAX	4 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 5d87fe8a41f..7308d84f927 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -29,7 +29,8 @@
 /*				2    Range as input support for IPv4 added */
 /*				3    nomatch flag support added */
 /*				4    Counters support added */
-#define IPSET_TYPE_REV_MAX	5 /* Comments support added */
+/*				5    Comments support added */
+#define IPSET_TYPE_REV_MAX	6 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 8295cf4f9fd..4c7d495783a 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -26,7 +26,8 @@
 /*				1    Range as input support for IPv4 added */
 /*				2    nomatch flag support added */
 /*				3    Counters support added */
-#define IPSET_TYPE_REV_MAX	4 /* Comments support added */
+/*				4    Comments support added */
+#define IPSET_TYPE_REV_MAX	5 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 3f64a66bf5d..db2606805b3 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -27,7 +27,8 @@
 /*				1    nomatch flag support added */
 /*				2    /0 support added */
 /*				3    Counters support added */
-#define IPSET_TYPE_REV_MAX	4 /* Comments support added */
+/*				4    Comments support added */
+#define IPSET_TYPE_REV_MAX	5 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
@@ -46,31 +47,12 @@ struct iface_node {
 static void
 rbtree_destroy(struct rb_root *root)
 {
-	struct rb_node *p, *n = root->rb_node;
-	struct iface_node *node;
-
-	/* Non-recursive destroy, like in ext3 */
-	while (n) {
-		if (n->rb_left) {
-			n = n->rb_left;
-			continue;
-		}
-		if (n->rb_right) {
-			n = n->rb_right;
-			continue;
-		}
-		p = rb_parent(n);
-		node = rb_entry(n, struct iface_node, node);
-		if (!p)
-			*root = RB_ROOT;
-		else if (p->rb_left == n)
-			p->rb_left = NULL;
-		else if (p->rb_right == n)
-			p->rb_right = NULL;
+	struct iface_node *node, *next;
 
+	rbtree_postorder_for_each_entry_safe(node, next, root, node)
 		kfree(node);
-		n = p;
-	}
+
+	*root = RB_ROOT;
 }
 
 static int
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index 2bc2dec20b0..3e99987e4bf 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -24,7 +24,7 @@
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
 #define IPSET_TYPE_REV_MIN	0
-#define IPSET_TYPE_REV_MAX	0
+#define IPSET_TYPE_REV_MAX	1	/* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
@@ -59,7 +59,7 @@ hash_netnet4_data_equal(const struct hash_netnet4_elem *ip1,
 		     u32 *multi)
 {
 	return ip1->ipcmp == ip2->ipcmp &&
-	       ip2->ccmp == ip2->ccmp;
+	       ip1->ccmp == ip2->ccmp;
 }
 
 static inline int
@@ -112,10 +112,10 @@ hash_netnet4_data_list(struct sk_buff *skb,
 	    (flags &&
 	     nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
 		goto nla_put_failure;
-	return 0;
+	return false;
 
 nla_put_failure:
-	return 1;
+	return true;
 }
 
 static inline void
@@ -334,10 +334,10 @@ hash_netnet6_data_list(struct sk_buff *skb,
 	    (flags &&
 	     nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
 		goto nla_put_failure;
-	return 0;
+	return false;
 
 nla_put_failure:
-	return 1;
+	return true;
 }
 
 static inline void
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 7097fb0141b..1c645fbd09c 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -28,7 +28,8 @@
 /*				2    Range as input support for IPv4 added */
 /*				3    nomatch flag support added */
 /*				4    Counters support added */
-#define IPSET_TYPE_REV_MAX	5 /* Comments support added */
+/*				5    Comments support added */
+#define IPSET_TYPE_REV_MAX	6 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 703d1192a6a..c0d2ba73f8b 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -25,7 +25,8 @@
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
 #define IPSET_TYPE_REV_MIN	0
-#define IPSET_TYPE_REV_MAX	0 /* Comments support added */
+/*				0    Comments support added */
+#define IPSET_TYPE_REV_MAX	1 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
diff --git a/net/netfilter/ipset/pfxlen.c b/net/netfilter/ipset/pfxlen.c
index 4f29fa97044..04d15fdc99e 100644
--- a/net/netfilter/ipset/pfxlen.c
+++ b/net/netfilter/ipset/pfxlen.c
@@ -7,8 +7,8 @@
 
 #define E(a, b, c, d) \
 	{.ip6 = { \
-		__constant_htonl(a), __constant_htonl(b), \
-		__constant_htonl(c), __constant_htonl(d), \
+		htonl(a), htonl(b), \
+		htonl(c), htonl(d), \
 	} }
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 4c8e5c0aa1a..610e19c0e13 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -797,7 +797,6 @@ static void ip_vs_conn_expire(unsigned long data)
 			ip_vs_control_del(cp);
 
 		if (cp->flags & IP_VS_CONN_F_NFCT) {
-			ip_vs_conn_drop_conntrack(cp);
 			/* Do not access conntracks during subsys cleanup
 			 * because nf_conntrack_find_get can not be used after
 			 * conntrack cleanup for the net.
@@ -871,11 +870,11 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	cp->protocol	   = p->protocol;
 	ip_vs_addr_set(p->af, &cp->caddr, p->caddr);
 	cp->cport	   = p->cport;
-	ip_vs_addr_set(p->af, &cp->vaddr, p->vaddr);
-	cp->vport	   = p->vport;
-	/* proto should only be IPPROTO_IP if d_addr is a fwmark */
+	/* proto should only be IPPROTO_IP if p->vaddr is a fwmark */
 	ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
-		       &cp->daddr, daddr);
+		       &cp->vaddr, p->vaddr);
+	cp->vport	   = p->vport;
+	ip_vs_addr_set(p->af, &cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
 	cp->fwmark         = fwmark;
@@ -1209,7 +1208,7 @@ void ip_vs_random_dropentry(struct net *net)
 	 * Randomly scan 1/32 of the whole table every second
 	 */
 	for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) {
-		unsigned int hash = net_random() & ip_vs_conn_tab_mask;
+		unsigned int hash = prandom_u32() & ip_vs_conn_tab_mask;
 
 		hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
 			if (cp->flags & IP_VS_CONN_F_TEMPLATE)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 4f26ee46b51..e6836755c45 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -97,7 +97,7 @@ const char *ip_vs_proto_name(unsigned int proto)
 		return "ICMPv6";
 #endif
 	default:
-		sprintf(buf, "IP_%d", proto);
+		sprintf(buf, "IP_%u", proto);
 		return buf;
 	}
 }
@@ -1392,15 +1392,19 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	if (ipip) {
 		__be32 info = ic->un.gateway;
+		__u8 type = ic->type;
+		__u8 code = ic->code;
 
 		/* Update the MTU */
 		if (ic->type == ICMP_DEST_UNREACH &&
 		    ic->code == ICMP_FRAG_NEEDED) {
 			struct ip_vs_dest *dest = cp->dest;
 			u32 mtu = ntohs(ic->un.frag.mtu);
+			__be16 frag_off = cih->frag_off;
 
 			/* Strip outer IP and ICMP, go to IPIP header */
-			__skb_pull(skb, ihl + sizeof(_icmph));
+			if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL)
+				goto ignore_ipip;
 			offset2 -= ihl + sizeof(_icmph);
 			skb_reset_network_header(skb);
 			IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
@@ -1408,7 +1412,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 			ipv4_update_pmtu(skb, dev_net(skb->dev),
 					 mtu, 0, 0, 0, 0);
 			/* Client uses PMTUD? */
-			if (!(cih->frag_off & htons(IP_DF)))
+			if (!(frag_off & htons(IP_DF)))
 				goto ignore_ipip;
 			/* Prefer the resulting PMTU */
 			if (dest) {
@@ -1427,12 +1431,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 		/* Strip outer IP, ICMP and IPIP, go to IP header of
 		 * original request.
 		 */
-		__skb_pull(skb, offset2);
+		if (pskb_pull(skb, offset2) == NULL)
+			goto ignore_ipip;
 		skb_reset_network_header(skb);
 		IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
 			&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
-			ic->type, ic->code, ntohl(info));
-		icmp_send(skb, ic->type, ic->code, info);
+			type, code, ntohl(info));
+		icmp_send(skb, type, code, info);
 		/* ICMP can be shorter but anyways, account it */
 		ip_vs_out_stats(cp, skb);
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 35be035ee0c..581a6584ed0 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2177,10 +2177,10 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 		__u64 inbytes, outbytes;
 
 		do {
-			start = u64_stats_fetch_begin_bh(&u->syncp);
+			start = u64_stats_fetch_begin_irq(&u->syncp);
 			inbytes = u->ustats.inbytes;
 			outbytes = u->ustats.outbytes;
-		} while (u64_stats_fetch_retry_bh(&u->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&u->syncp, start));
 
 		seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n",
 			   i, u->ustats.conns, u->ustats.inpkts,
@@ -3580,7 +3580,7 @@ out:
 }
 
 
-static const struct genl_ops ip_vs_genl_ops[] __read_mostly = {
+static const struct genl_ops ip_vs_genl_ops[] = {
 	{
 		.cmd	= IPVS_CMD_NEW_SERVICE,
 		.flags	= GENL_ADMIN_PERM,
@@ -3778,6 +3778,7 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
 	cancel_delayed_work_sync(&ipvs->defense_work);
 	cancel_work_sync(&ipvs->defense_work.work);
 	unregister_net_sysctl_table(ipvs->sysctl_hdr);
+	ip_vs_stop_estimator(net, &ipvs->tot_stats);
 }
 
 #else
@@ -3840,7 +3841,6 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	ip_vs_trash_cleanup(net);
-	ip_vs_stop_estimator(net, &ipvs->tot_stats);
 	ip_vs_control_net_cleanup_sysctl(net);
 	remove_proc_entry("ip_vs_stats_percpu", net->proc_net);
 	remove_proc_entry("ip_vs_stats", net->proc_net);
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index ca056a331e6..547ff33c1ef 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -238,7 +238,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc)
 
 	spin_lock_bh(&svc->sched_lock);
 	tbl->dead = 1;
-	for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) {
+	for (i = 0; i < IP_VS_LBLC_TAB_SIZE; i++) {
 		hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) {
 			ip_vs_lblc_del(en);
 			atomic_dec(&tbl->entries);
@@ -265,7 +265,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
 	unsigned long now = jiffies;
 	int i, j;
 
-	for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
+	for (i = 0, j = tbl->rover; i < IP_VS_LBLC_TAB_SIZE; i++) {
 		j = (j + 1) & IP_VS_LBLC_TAB_MASK;
 
 		spin_lock(&svc->sched_lock);
@@ -321,7 +321,7 @@ static void ip_vs_lblc_check_expire(unsigned long data)
 	if (goal > tbl->max_size/2)
 		goal = tbl->max_size/2;
 
-	for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
+	for (i = 0, j = tbl->rover; i < IP_VS_LBLC_TAB_SIZE; i++) {
 		j = (j + 1) & IP_VS_LBLC_TAB_MASK;
 
 		spin_lock(&svc->sched_lock);
@@ -340,7 +340,7 @@ static void ip_vs_lblc_check_expire(unsigned long data)
 	tbl->rover = j;
 
   out:
-	mod_timer(&tbl->periodic_timer, jiffies+CHECK_EXPIRE_INTERVAL);
+	mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL);
 }
 
 
@@ -363,7 +363,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc)
 	/*
 	 *    Initialize the hash buckets
 	 */
-	for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) {
+	for (i = 0; i < IP_VS_LBLC_TAB_SIZE; i++) {
 		INIT_HLIST_HEAD(&tbl->bucket[i]);
 	}
 	tbl->max_size = IP_VS_LBLC_TAB_SIZE*16;
@@ -536,8 +536,7 @@ out:
 /*
  *      IPVS LBLC Scheduler structure
  */
-static struct ip_vs_scheduler ip_vs_lblc_scheduler =
-{
+static struct ip_vs_scheduler ip_vs_lblc_scheduler = {
 	.name =			"lblc",
 	.refcnt =		ATOMIC_INIT(0),
 	.module =		THIS_MODULE,
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index d5f41514f57..5882bbfd198 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -62,6 +62,7 @@
 #include <net/ip_vs.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 
@@ -96,6 +97,11 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin)
 	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
 		return;
 
+	/* Applications may adjust TCP seqs */
+	if (cp->app && nf_ct_protonum(ct) == IPPROTO_TCP &&
+	    !nfct_seqadj(ct) && !nfct_seqadj_ext_add(ct))
+		return;
+
 	/*
 	 * The connection is not yet in the hashtable, so we update it.
 	 * CIP->VIP will remain the same, so leave the tuple in
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index f63c2388f38..db801263ee9 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1637,7 +1637,10 @@ static int sync_thread_master(void *data)
 			continue;
 		}
 		while (ip_vs_send_sync_msg(tinfo->sock, sb->mesg) < 0) {
-			int ret = __wait_event_interruptible(*sk_sleep(sk),
+			/* (Ab)use interruptible sleep to avoid increasing
+			 * the load avg.
+			 */
+			__wait_event_interruptible(*sk_sleep(sk),
 						   sock_writeable(sk) ||
 						   kthread_should_stop());
 			if (unlikely(kthread_should_stop()))
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index c47444e4cf8..73ba1cc7a88 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -562,7 +562,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	ip_send_check(iph);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0);
 	rcu_read_unlock();
@@ -590,7 +590,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error;
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0);
 	rcu_read_unlock();
@@ -684,7 +684,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	   MTU problem. */
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local);
 	rcu_read_unlock();
@@ -774,7 +774,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	   MTU problem. */
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
 	rcu_read_unlock();
@@ -883,10 +883,10 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->daddr		=	cp->daddr.ip;
 	iph->saddr		=	saddr;
 	iph->ttl		=	old_iph->ttl;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ret = ip_vs_tunnel_xmit_prepare(skb, cp);
 	if (ret == NF_ACCEPT)
@@ -974,7 +974,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->hop_limit		=	old_iph->hop_limit;
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ret = ip_vs_tunnel_xmit_prepare(skb, cp);
 	if (ret == NF_ACCEPT)
@@ -1023,7 +1023,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	ip_send_check(ip_hdr(skb));
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0);
 	rcu_read_unlock();
@@ -1060,7 +1060,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	}
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0);
 	rcu_read_unlock();
@@ -1157,7 +1157,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	ip_vs_nat_icmp(skb, pp, cp, 0);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local);
 	rcu_read_unlock();
@@ -1249,7 +1249,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	ip_vs_nat_icmp_v6(skb, pp, cp, 0);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
 	rcu_read_unlock();
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 43549eb7a7b..1f4f954c4b4 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -60,14 +60,59 @@ int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct,
 				      const struct nlattr *attr) __read_mostly;
 EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook);
 
-int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb,
-			      struct nf_conn *ct,
-			      enum ip_conntrack_info ctinfo,
-			      unsigned int protoff);
-EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook);
+__cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
+EXPORT_SYMBOL_GPL(nf_conntrack_locks);
 
-DEFINE_SPINLOCK(nf_conntrack_lock);
-EXPORT_SYMBOL_GPL(nf_conntrack_lock);
+__cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock);
+EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);
+
+static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2)
+{
+	h1 %= CONNTRACK_LOCKS;
+	h2 %= CONNTRACK_LOCKS;
+	spin_unlock(&nf_conntrack_locks[h1]);
+	if (h1 != h2)
+		spin_unlock(&nf_conntrack_locks[h2]);
+}
+
+/* return true if we need to recompute hashes (in case hash table was resized) */
+static bool nf_conntrack_double_lock(struct net *net, unsigned int h1,
+				     unsigned int h2, unsigned int sequence)
+{
+	h1 %= CONNTRACK_LOCKS;
+	h2 %= CONNTRACK_LOCKS;
+	if (h1 <= h2) {
+		spin_lock(&nf_conntrack_locks[h1]);
+		if (h1 != h2)
+			spin_lock_nested(&nf_conntrack_locks[h2],
+					 SINGLE_DEPTH_NESTING);
+	} else {
+		spin_lock(&nf_conntrack_locks[h2]);
+		spin_lock_nested(&nf_conntrack_locks[h1],
+				 SINGLE_DEPTH_NESTING);
+	}
+	if (read_seqcount_retry(&net->ct.generation, sequence)) {
+		nf_conntrack_double_unlock(h1, h2);
+		return true;
+	}
+	return false;
+}
+
+static void nf_conntrack_all_lock(void)
+{
+	int i;
+
+	for (i = 0; i < CONNTRACK_LOCKS; i++)
+		spin_lock_nested(&nf_conntrack_locks[i], i);
+}
+
+static void nf_conntrack_all_unlock(void)
+{
+	int i;
+
+	for (i = 0; i < CONNTRACK_LOCKS; i++)
+		spin_unlock(&nf_conntrack_locks[i]);
+}
 
 unsigned int nf_conntrack_htable_size __read_mostly;
 EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
@@ -198,6 +243,50 @@ clean_from_lists(struct nf_conn *ct)
 	nf_ct_remove_expectations(ct);
 }
 
+/* must be called with local_bh_disable */
+static void nf_ct_add_to_dying_list(struct nf_conn *ct)
+{
+	struct ct_pcpu *pcpu;
+
+	/* add this conntrack to the (per cpu) dying list */
+	ct->cpu = smp_processor_id();
+	pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
+
+	spin_lock(&pcpu->lock);
+	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+			     &pcpu->dying);
+	spin_unlock(&pcpu->lock);
+}
+
+/* must be called with local_bh_disable */
+static void nf_ct_add_to_unconfirmed_list(struct nf_conn *ct)
+{
+	struct ct_pcpu *pcpu;
+
+	/* add this conntrack to the (per cpu) unconfirmed list */
+	ct->cpu = smp_processor_id();
+	pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
+
+	spin_lock(&pcpu->lock);
+	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+			     &pcpu->unconfirmed);
+	spin_unlock(&pcpu->lock);
+}
+
+/* must be called with local_bh_disable */
+static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
+{
+	struct ct_pcpu *pcpu;
+
+	/* We overload first tuple to link into unconfirmed or dying list.*/
+	pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
+
+	spin_lock(&pcpu->lock);
+	BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
+	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+	spin_unlock(&pcpu->lock);
+}
+
 static void
 destroy_conntrack(struct nf_conntrack *nfct)
 {
@@ -209,9 +298,6 @@ destroy_conntrack(struct nf_conntrack *nfct)
 	NF_CT_ASSERT(atomic_read(&nfct->use) == 0);
 	NF_CT_ASSERT(!timer_pending(&ct->timeout));
 
-	/* To make sure we don't get any weird locking issues here:
-	 * destroy_conntrack() MUST NOT be called with a write lock
-	 * to nf_conntrack_lock!!! -HW */
 	rcu_read_lock();
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
 	if (l4proto && l4proto->destroy)
@@ -219,19 +305,18 @@ destroy_conntrack(struct nf_conntrack *nfct)
 
 	rcu_read_unlock();
 
-	spin_lock_bh(&nf_conntrack_lock);
+	local_bh_disable();
 	/* Expectations will have been removed in clean_from_lists,
 	 * except TFTP can create an expectation on the first packet,
 	 * before connection is in the list, so we need to clean here,
-	 * too. */
+	 * too.
+	 */
 	nf_ct_remove_expectations(ct);
 
-	/* We overload first tuple to link into unconfirmed or dying list.*/
-	BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
-	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+	nf_ct_del_from_dying_or_unconfirmed_list(ct);
 
 	NF_CT_STAT_INC(net, delete);
-	spin_unlock_bh(&nf_conntrack_lock);
+	local_bh_enable();
 
 	if (ct->master)
 		nf_ct_put(ct->master);
@@ -243,17 +328,28 @@ destroy_conntrack(struct nf_conntrack *nfct)
 static void nf_ct_delete_from_lists(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
+	unsigned int hash, reply_hash;
+	u16 zone = nf_ct_zone(ct);
+	unsigned int sequence;
 
 	nf_ct_helper_destroy(ct);
-	spin_lock_bh(&nf_conntrack_lock);
-	/* Inside lock so preempt is disabled on module removal path.
-	 * Otherwise we can get spurious warnings. */
-	NF_CT_STAT_INC(net, delete_list);
+
+	local_bh_disable();
+	do {
+		sequence = read_seqcount_begin(&net->ct.generation);
+		hash = hash_conntrack(net, zone,
+				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+		reply_hash = hash_conntrack(net, zone,
+					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
+
 	clean_from_lists(ct);
-	/* add this conntrack to the dying list */
-	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
-			     &net->ct.dying);
-	spin_unlock_bh(&nf_conntrack_lock);
+	nf_conntrack_double_unlock(hash, reply_hash);
+
+	nf_ct_add_to_dying_list(ct);
+
+	NF_CT_STAT_INC(net, delete_list);
+	local_bh_enable();
 }
 
 static void death_by_event(unsigned long ul_conntrack)
@@ -318,12 +414,25 @@ static void death_by_timeout(unsigned long ul_conntrack)
 	nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0);
 }
 
+static inline bool
+nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
+			const struct nf_conntrack_tuple *tuple,
+			u16 zone)
+{
+	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+
+	/* A conntrack can be recreated with the equal tuple,
+	 * so we need to check that the conntrack is confirmed
+	 */
+	return nf_ct_tuple_equal(tuple, &h->tuple) &&
+		nf_ct_zone(ct) == zone &&
+		nf_ct_is_confirmed(ct);
+}
+
 /*
  * Warning :
  * - Caller must take a reference on returned object
  *   and recheck nf_ct_tuple_equal(tuple, &h->tuple)
- * OR
- * - Caller must lock nf_conntrack_lock before calling this function
  */
 static struct nf_conntrack_tuple_hash *
 ____nf_conntrack_find(struct net *net, u16 zone,
@@ -339,8 +448,7 @@ ____nf_conntrack_find(struct net *net, u16 zone,
 	local_bh_disable();
 begin:
 	hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) {
-		if (nf_ct_tuple_equal(tuple, &h->tuple) &&
-		    nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) {
+		if (nf_ct_key_equal(h, tuple, zone)) {
 			NF_CT_STAT_INC(net, found);
 			local_bh_enable();
 			return h;
@@ -361,15 +469,6 @@ begin:
 	return NULL;
 }
 
-struct nf_conntrack_tuple_hash *
-__nf_conntrack_find(struct net *net, u16 zone,
-		    const struct nf_conntrack_tuple *tuple)
-{
-	return ____nf_conntrack_find(net, zone, tuple,
-				     hash_conntrack_raw(tuple, zone));
-}
-EXPORT_SYMBOL_GPL(__nf_conntrack_find);
-
 /* Find a connection corresponding to a tuple. */
 static struct nf_conntrack_tuple_hash *
 __nf_conntrack_find_get(struct net *net, u16 zone,
@@ -387,8 +486,7 @@ begin:
 			     !atomic_inc_not_zero(&ct->ct_general.use)))
 			h = NULL;
 		else {
-			if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) ||
-				     nf_ct_zone(ct) != zone)) {
+			if (unlikely(!nf_ct_key_equal(h, tuple, zone))) {
 				nf_ct_put(ct);
 				goto begin;
 			}
@@ -410,32 +508,36 @@ EXPORT_SYMBOL_GPL(nf_conntrack_find_get);
 
 static void __nf_conntrack_hash_insert(struct nf_conn *ct,
 				       unsigned int hash,
-				       unsigned int repl_hash)
+				       unsigned int reply_hash)
 {
 	struct net *net = nf_ct_net(ct);
 
 	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
 			   &net->ct.hash[hash]);
 	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
-			   &net->ct.hash[repl_hash]);
+			   &net->ct.hash[reply_hash]);
 }
 
 int
 nf_conntrack_hash_check_insert(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
-	unsigned int hash, repl_hash;
+	unsigned int hash, reply_hash;
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
 	u16 zone;
+	unsigned int sequence;
 
 	zone = nf_ct_zone(ct);
-	hash = hash_conntrack(net, zone,
-			      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
-	repl_hash = hash_conntrack(net, zone,
-				   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
 
-	spin_lock_bh(&nf_conntrack_lock);
+	local_bh_disable();
+	do {
+		sequence = read_seqcount_begin(&net->ct.generation);
+		hash = hash_conntrack(net, zone,
+				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+		reply_hash = hash_conntrack(net, zone,
+					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
 
 	/* See if there's one in the list already, including reverse */
 	hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
@@ -443,32 +545,57 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 				      &h->tuple) &&
 		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
 			goto out;
-	hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
+	hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 				      &h->tuple) &&
 		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
 			goto out;
 
 	add_timer(&ct->timeout);
-	nf_conntrack_get(&ct->ct_general);
-	__nf_conntrack_hash_insert(ct, hash, repl_hash);
+	smp_wmb();
+	/* The caller holds a reference to this object */
+	atomic_set(&ct->ct_general.use, 2);
+	__nf_conntrack_hash_insert(ct, hash, reply_hash);
+	nf_conntrack_double_unlock(hash, reply_hash);
 	NF_CT_STAT_INC(net, insert);
-	spin_unlock_bh(&nf_conntrack_lock);
-
+	local_bh_enable();
 	return 0;
 
 out:
+	nf_conntrack_double_unlock(hash, reply_hash);
 	NF_CT_STAT_INC(net, insert_failed);
-	spin_unlock_bh(&nf_conntrack_lock);
+	local_bh_enable();
 	return -EEXIST;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
 
+/* deletion from this larval template list happens via nf_ct_put() */
+void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl)
+{
+	struct ct_pcpu *pcpu;
+
+	__set_bit(IPS_TEMPLATE_BIT, &tmpl->status);
+	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+	nf_conntrack_get(&tmpl->ct_general);
+
+	/* add this conntrack to the (per cpu) tmpl list */
+	local_bh_disable();
+	tmpl->cpu = smp_processor_id();
+	pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu);
+
+	spin_lock(&pcpu->lock);
+	/* Overload tuple linked list to put us in template list. */
+	hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+				 &pcpu->tmpl);
+	spin_unlock_bh(&pcpu->lock);
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert);
+
 /* Confirm a connection given skb; places it in hash table */
 int
 __nf_conntrack_confirm(struct sk_buff *skb)
 {
-	unsigned int hash, repl_hash;
+	unsigned int hash, reply_hash;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
 	struct nf_conn_help *help;
@@ -477,6 +604,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	enum ip_conntrack_info ctinfo;
 	struct net *net;
 	u16 zone;
+	unsigned int sequence;
 
 	ct = nf_ct_get(skb, &ctinfo);
 	net = nf_ct_net(ct);
@@ -489,31 +617,37 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 		return NF_ACCEPT;
 
 	zone = nf_ct_zone(ct);
-	/* reuse the hash saved before */
-	hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
-	hash = hash_bucket(hash, net);
-	repl_hash = hash_conntrack(net, zone,
-				   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+	local_bh_disable();
+
+	do {
+		sequence = read_seqcount_begin(&net->ct.generation);
+		/* reuse the hash saved before */
+		hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
+		hash = hash_bucket(hash, net);
+		reply_hash = hash_conntrack(net, zone,
+					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+
+	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
 
 	/* We're not in hash table, and we refuse to set up related
-	   connections for unconfirmed conns.  But packet copies and
-	   REJECT will give spurious warnings here. */
+	 * connections for unconfirmed conns.  But packet copies and
+	 * REJECT will give spurious warnings here.
+	 */
 	/* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */
 
 	/* No external references means no one else could have
-	   confirmed us. */
+	 * confirmed us.
+	 */
 	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
 	pr_debug("Confirming conntrack %p\n", ct);
-
-	spin_lock_bh(&nf_conntrack_lock);
-
 	/* We have to check the DYING flag inside the lock to prevent
 	   a race against nf_ct_get_next_corpse() possibly called from
 	   user context, else we insert an already 'dead' hash, blocking
 	   further use of that particular connection -JM */
 
 	if (unlikely(nf_ct_is_dying(ct))) {
-		spin_unlock_bh(&nf_conntrack_lock);
+		nf_conntrack_double_unlock(hash, reply_hash);
+		local_bh_enable();
 		return NF_ACCEPT;
 	}
 
@@ -525,14 +659,13 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 				      &h->tuple) &&
 		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
 			goto out;
-	hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
+	hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 				      &h->tuple) &&
 		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
 			goto out;
 
-	/* Remove from unconfirmed list */
-	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+	nf_ct_del_from_dying_or_unconfirmed_list(ct);
 
 	/* Timer relative to confirmation time, not original
 	   setting time, otherwise we'd get timer wrap in
@@ -555,9 +688,10 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	 * guarantee that no other CPU can find the conntrack before the above
 	 * stores are visible.
 	 */
-	__nf_conntrack_hash_insert(ct, hash, repl_hash);
+	__nf_conntrack_hash_insert(ct, hash, reply_hash);
+	nf_conntrack_double_unlock(hash, reply_hash);
 	NF_CT_STAT_INC(net, insert);
-	spin_unlock_bh(&nf_conntrack_lock);
+	local_bh_enable();
 
 	help = nfct_help(ct);
 	if (help && help->helper)
@@ -568,8 +702,9 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	return NF_ACCEPT;
 
 out:
+	nf_conntrack_double_unlock(hash, reply_hash);
 	NF_CT_STAT_INC(net, insert_failed);
-	spin_unlock_bh(&nf_conntrack_lock);
+	local_bh_enable();
 	return NF_DROP;
 }
 EXPORT_SYMBOL_GPL(__nf_conntrack_confirm);
@@ -612,39 +747,48 @@ EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken);
 
 /* There's a small race here where we may free a just-assured
    connection.  Too bad: we're in trouble anyway. */
-static noinline int early_drop(struct net *net, unsigned int hash)
+static noinline int early_drop(struct net *net, unsigned int _hash)
 {
 	/* Use oldest entry, which is roughly LRU */
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct = NULL, *tmp;
 	struct hlist_nulls_node *n;
-	unsigned int i, cnt = 0;
+	unsigned int i = 0, cnt = 0;
 	int dropped = 0;
+	unsigned int hash, sequence;
+	spinlock_t *lockp;
 
-	rcu_read_lock();
-	for (i = 0; i < net->ct.htable_size; i++) {
+	local_bh_disable();
+restart:
+	sequence = read_seqcount_begin(&net->ct.generation);
+	hash = hash_bucket(_hash, net);
+	for (; i < net->ct.htable_size; i++) {
+		lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS];
+		spin_lock(lockp);
+		if (read_seqcount_retry(&net->ct.generation, sequence)) {
+			spin_unlock(lockp);
+			goto restart;
+		}
 		hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash],
 					 hnnode) {
 			tmp = nf_ct_tuplehash_to_ctrack(h);
-			if (!test_bit(IPS_ASSURED_BIT, &tmp->status))
+			if (!test_bit(IPS_ASSURED_BIT, &tmp->status) &&
+			    !nf_ct_is_dying(tmp) &&
+			    atomic_inc_not_zero(&tmp->ct_general.use)) {
 				ct = tmp;
+				break;
+			}
 			cnt++;
 		}
 
-		if (ct != NULL) {
-			if (likely(!nf_ct_is_dying(ct) &&
-				   atomic_inc_not_zero(&ct->ct_general.use)))
-				break;
-			else
-				ct = NULL;
-		}
+		hash = (hash + 1) % net->ct.htable_size;
+		spin_unlock(lockp);
 
-		if (cnt >= NF_CT_EVICTION_RANGE)
+		if (ct || cnt >= NF_CT_EVICTION_RANGE)
 			break;
 
-		hash = (hash + 1) % net->ct.htable_size;
 	}
-	rcu_read_unlock();
+	local_bh_enable();
 
 	if (!ct)
 		return dropped;
@@ -693,7 +837,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
 
 	if (nf_conntrack_max &&
 	    unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {
-		if (!early_drop(net, hash_bucket(hash, net))) {
+		if (!early_drop(net, hash)) {
 			atomic_dec(&net->ct.count);
 			net_warn_ratelimited("nf_conntrack: table full, dropping packet\n");
 			return ERR_PTR(-ENOMEM);
@@ -735,11 +879,10 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
 		nf_ct_zone->id = zone;
 	}
 #endif
-	/*
-	 * changes to lookup keys must be done before setting refcnt to 1
+	/* Because we use RCU lookups, we set ct_general.use to zero before
+	 * this is inserted in any list.
 	 */
-	smp_wmb();
-	atomic_set(&ct->ct_general.use, 1);
+	atomic_set(&ct->ct_general.use, 0);
 	return ct;
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES
@@ -763,10 +906,15 @@ void nf_conntrack_free(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
 
+	/* A freed object has refcnt == 0, that's
+	 * the golden rule for SLAB_DESTROY_BY_RCU
+	 */
+	NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);
+
 	nf_ct_ext_destroy(ct);
 	nf_ct_ext_free(ct);
 	kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_dec(&net->ct.count);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_free);
@@ -786,7 +934,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	struct nf_conn_help *help;
 	struct nf_conntrack_tuple repl_tuple;
 	struct nf_conntrack_ecache *ecache;
-	struct nf_conntrack_expect *exp;
+	struct nf_conntrack_expect *exp = NULL;
 	u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
 	struct nf_conn_timeout *timeout_ext;
 	unsigned int *timeouts;
@@ -830,39 +978,44 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 				 ecache ? ecache->expmask : 0,
 			     GFP_ATOMIC);
 
-	spin_lock_bh(&nf_conntrack_lock);
-	exp = nf_ct_find_expectation(net, zone, tuple);
-	if (exp) {
-		pr_debug("conntrack: expectation arrives ct=%p exp=%p\n",
-			 ct, exp);
-		/* Welcome, Mr. Bond.  We've been expecting you... */
-		__set_bit(IPS_EXPECTED_BIT, &ct->status);
-		ct->master = exp->master;
-		if (exp->helper) {
-			help = nf_ct_helper_ext_add(ct, exp->helper,
-						    GFP_ATOMIC);
-			if (help)
-				rcu_assign_pointer(help->helper, exp->helper);
-		}
+	local_bh_disable();
+	if (net->ct.expect_count) {
+		spin_lock(&nf_conntrack_expect_lock);
+		exp = nf_ct_find_expectation(net, zone, tuple);
+		if (exp) {
+			pr_debug("conntrack: expectation arrives ct=%p exp=%p\n",
+				 ct, exp);
+			/* Welcome, Mr. Bond.  We've been expecting you... */
+			__set_bit(IPS_EXPECTED_BIT, &ct->status);
+			/* exp->master safe, refcnt bumped in nf_ct_find_expectation */
+			ct->master = exp->master;
+			if (exp->helper) {
+				help = nf_ct_helper_ext_add(ct, exp->helper,
+							    GFP_ATOMIC);
+				if (help)
+					rcu_assign_pointer(help->helper, exp->helper);
+			}
 
 #ifdef CONFIG_NF_CONNTRACK_MARK
-		ct->mark = exp->master->mark;
+			ct->mark = exp->master->mark;
 #endif
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
-		ct->secmark = exp->master->secmark;
+			ct->secmark = exp->master->secmark;
 #endif
-		nf_conntrack_get(&ct->master->ct_general);
-		NF_CT_STAT_INC(net, expect_new);
-	} else {
+			NF_CT_STAT_INC(net, expect_new);
+		}
+		spin_unlock(&nf_conntrack_expect_lock);
+	}
+	if (!exp) {
 		__nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
 		NF_CT_STAT_INC(net, new);
 	}
 
-	/* Overload tuple linked list to put us in unconfirmed list. */
-	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
-		       &net->ct.unconfirmed);
+	/* Now it is inserted into the unconfirmed list, bump refcount */
+	nf_conntrack_get(&ct->ct_general);
+	nf_ct_add_to_unconfirmed_list(ct);
 
-	spin_unlock_bh(&nf_conntrack_lock);
+	local_bh_enable();
 
 	if (exp) {
 		if (exp->expectfn)
@@ -1232,27 +1385,42 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
 	struct hlist_nulls_node *n;
+	int cpu;
+	spinlock_t *lockp;
 
-	spin_lock_bh(&nf_conntrack_lock);
 	for (; *bucket < net->ct.htable_size; (*bucket)++) {
-		hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
-			if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
-				continue;
+		lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
+		local_bh_disable();
+		spin_lock(lockp);
+		if (*bucket < net->ct.htable_size) {
+			hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
+				if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+					continue;
+				ct = nf_ct_tuplehash_to_ctrack(h);
+				if (iter(ct, data))
+					goto found;
+			}
+		}
+		spin_unlock(lockp);
+		local_bh_enable();
+	}
+
+	for_each_possible_cpu(cpu) {
+		struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+		spin_lock_bh(&pcpu->lock);
+		hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) {
 			ct = nf_ct_tuplehash_to_ctrack(h);
 			if (iter(ct, data))
-				goto found;
+				set_bit(IPS_DYING_BIT, &ct->status);
 		}
+		spin_unlock_bh(&pcpu->lock);
 	}
-	hlist_nulls_for_each_entry(h, n, &net->ct.unconfirmed, hnnode) {
-		ct = nf_ct_tuplehash_to_ctrack(h);
-		if (iter(ct, data))
-			set_bit(IPS_DYING_BIT, &ct->status);
-	}
-	spin_unlock_bh(&nf_conntrack_lock);
 	return NULL;
 found:
 	atomic_inc(&ct->ct_general.use);
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock(lockp);
+	local_bh_enable();
 	return ct;
 }
 
@@ -1301,14 +1469,19 @@ static void nf_ct_release_dying_list(struct net *net)
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
 	struct hlist_nulls_node *n;
+	int cpu;
 
-	spin_lock_bh(&nf_conntrack_lock);
-	hlist_nulls_for_each_entry(h, n, &net->ct.dying, hnnode) {
-		ct = nf_ct_tuplehash_to_ctrack(h);
-		/* never fails to remove them, no listeners at this point */
-		nf_ct_kill(ct);
+	for_each_possible_cpu(cpu) {
+		struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+		spin_lock_bh(&pcpu->lock);
+		hlist_nulls_for_each_entry(h, n, &pcpu->dying, hnnode) {
+			ct = nf_ct_tuplehash_to_ctrack(h);
+			/* never fails to remove them, no listeners at this point */
+			nf_ct_kill(ct);
+		}
+		spin_unlock_bh(&pcpu->lock);
 	}
-	spin_unlock_bh(&nf_conntrack_lock);
 }
 
 static int untrack_refs(void)
@@ -1395,6 +1568,7 @@ i_see_dead_people:
 		kmem_cache_destroy(net->ct.nf_conntrack_cachep);
 		kfree(net->ct.slabname);
 		free_percpu(net->ct.stat);
+		free_percpu(net->ct.pcpu_lists);
 	}
 }
 
@@ -1447,12 +1621,16 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	if (!hash)
 		return -ENOMEM;
 
+	local_bh_disable();
+	nf_conntrack_all_lock();
+	write_seqcount_begin(&init_net.ct.generation);
+
 	/* Lookups in the old hash might happen in parallel, which means we
 	 * might get false negatives during connection lookup. New connections
 	 * created because of a false negative won't make it into the hash
-	 * though since that required taking the lock.
+	 * though since that required taking the locks.
 	 */
-	spin_lock_bh(&nf_conntrack_lock);
+
 	for (i = 0; i < init_net.ct.htable_size; i++) {
 		while (!hlist_nulls_empty(&init_net.ct.hash[i])) {
 			h = hlist_nulls_entry(init_net.ct.hash[i].first,
@@ -1469,7 +1647,10 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 
 	init_net.ct.htable_size = nf_conntrack_htable_size = hashsize;
 	init_net.ct.hash = hash;
-	spin_unlock_bh(&nf_conntrack_lock);
+
+	write_seqcount_end(&init_net.ct.generation);
+	nf_conntrack_all_unlock();
+	local_bh_enable();
 
 	nf_ct_free_hashtable(old_hash, old_size);
 	return 0;
@@ -1491,7 +1672,10 @@ EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or);
 int nf_conntrack_init_start(void)
 {
 	int max_factor = 8;
-	int ret, cpu;
+	int i, ret, cpu;
+
+	for (i = 0; i < CONNTRACK_LOCKS; i++)
+		spin_lock_init(&nf_conntrack_locks[i]);
 
 	/* Idea from tcp.c: use 1/16384 of memory.  On i386: 32MB
 	 * machine has 512 buckets. >= 1GB machines have 16384 buckets. */
@@ -1607,37 +1791,44 @@ void nf_conntrack_init_end(void)
 
 int nf_conntrack_init_net(struct net *net)
 {
-	int ret;
+	int ret = -ENOMEM;
+	int cpu;
 
 	atomic_set(&net->ct.count, 0);
-	INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL);
-	INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL);
-	INIT_HLIST_NULLS_HEAD(&net->ct.tmpl, TEMPLATE_NULLS_VAL);
-	net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
-	if (!net->ct.stat) {
-		ret = -ENOMEM;
+	seqcount_init(&net->ct.generation);
+
+	net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu);
+	if (!net->ct.pcpu_lists)
 		goto err_stat;
+
+	for_each_possible_cpu(cpu) {
+		struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+		spin_lock_init(&pcpu->lock);
+		INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL);
+		INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL);
+		INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL);
 	}
 
+	net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
+	if (!net->ct.stat)
+		goto err_pcpu_lists;
+
 	net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net);
-	if (!net->ct.slabname) {
-		ret = -ENOMEM;
+	if (!net->ct.slabname)
 		goto err_slabname;
-	}
 
 	net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname,
 							sizeof(struct nf_conn), 0,
 							SLAB_DESTROY_BY_RCU, NULL);
 	if (!net->ct.nf_conntrack_cachep) {
 		printk(KERN_ERR "Unable to create nf_conn slab cache\n");
-		ret = -ENOMEM;
 		goto err_cache;
 	}
 
 	net->ct.htable_size = nf_conntrack_htable_size;
 	net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1);
 	if (!net->ct.hash) {
-		ret = -ENOMEM;
 		printk(KERN_ERR "Unable to create nf_conntrack_hash\n");
 		goto err_hash;
 	}
@@ -1679,6 +1870,8 @@ err_cache:
 	kfree(net->ct.slabname);
 err_slabname:
 	free_percpu(net->ct.stat);
+err_pcpu_lists:
+	free_percpu(net->ct.pcpu_lists);
 err_stat:
 	return ret;
 }
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 4fd1ca94fd4..f87e8f68ad4 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -66,9 +66,9 @@ static void nf_ct_expectation_timed_out(unsigned long ul_expect)
 {
 	struct nf_conntrack_expect *exp = (void *)ul_expect;
 
-	spin_lock_bh(&nf_conntrack_lock);
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	nf_ct_unlink_expect(exp);
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 	nf_ct_expect_put(exp);
 }
 
@@ -155,6 +155,18 @@ nf_ct_find_expectation(struct net *net, u16 zone,
 	if (!nf_ct_is_confirmed(exp->master))
 		return NULL;
 
+	/* Avoid race with other CPUs, that for exp->master ct, is
+	 * about to invoke ->destroy(), or nf_ct_delete() via timeout
+	 * or early_drop().
+	 *
+	 * The atomic_inc_not_zero() check tells:  If that fails, we
+	 * know that the ct is being destroyed.  If it succeeds, we
+	 * can be sure the ct cannot disappear underneath.
+	 */
+	if (unlikely(nf_ct_is_dying(exp->master) ||
+		     !atomic_inc_not_zero(&exp->master->ct_general.use)))
+		return NULL;
+
 	if (exp->flags & NF_CT_EXPECT_PERMANENT) {
 		atomic_inc(&exp->use);
 		return exp;
@@ -162,6 +174,8 @@ nf_ct_find_expectation(struct net *net, u16 zone,
 		nf_ct_unlink_expect(exp);
 		return exp;
 	}
+	/* Undo exp->master refcnt increase, if del_timer() failed */
+	nf_ct_put(exp->master);
 
 	return NULL;
 }
@@ -177,12 +191,14 @@ void nf_ct_remove_expectations(struct nf_conn *ct)
 	if (!help)
 		return;
 
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
 		if (del_timer(&exp->timeout)) {
 			nf_ct_unlink_expect(exp);
 			nf_ct_expect_put(exp);
 		}
 	}
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 }
 EXPORT_SYMBOL_GPL(nf_ct_remove_expectations);
 
@@ -217,12 +233,12 @@ static inline int expect_matches(const struct nf_conntrack_expect *a,
 /* Generally a bad idea to call this: could have matched already. */
 void nf_ct_unexpect_related(struct nf_conntrack_expect *exp)
 {
-	spin_lock_bh(&nf_conntrack_lock);
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	if (del_timer(&exp->timeout)) {
 		nf_ct_unlink_expect(exp);
 		nf_ct_expect_put(exp);
 	}
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 }
 EXPORT_SYMBOL_GPL(nf_ct_unexpect_related);
 
@@ -335,7 +351,7 @@ static int nf_ct_expect_insert(struct nf_conntrack_expect *exp)
 	setup_timer(&exp->timeout, nf_ct_expectation_timed_out,
 		    (unsigned long)exp);
 	helper = rcu_dereference_protected(master_help->helper,
-					   lockdep_is_held(&nf_conntrack_lock));
+					   lockdep_is_held(&nf_conntrack_expect_lock));
 	if (helper) {
 		exp->timeout.expires = jiffies +
 			helper->expect_policy[exp->class].timeout * HZ;
@@ -395,7 +411,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
 	}
 	/* Will be over limit? */
 	helper = rcu_dereference_protected(master_help->helper,
-					   lockdep_is_held(&nf_conntrack_lock));
+					   lockdep_is_held(&nf_conntrack_expect_lock));
 	if (helper) {
 		p = &helper->expect_policy[expect->class];
 		if (p->max_expected &&
@@ -417,12 +433,12 @@ out:
 	return ret;
 }
 
-int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, 
+int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
 				u32 portid, int report)
 {
 	int ret;
 
-	spin_lock_bh(&nf_conntrack_lock);
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	ret = __nf_ct_expect_check(expect);
 	if (ret <= 0)
 		goto out;
@@ -430,11 +446,11 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
 	ret = nf_ct_expect_insert(expect);
 	if (ret < 0)
 		goto out;
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 	nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report);
 	return ret;
 out:
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_related_report);
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 70866d192ef..3a3a60b126e 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -1476,7 +1476,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct,
 		nf_ct_refresh(ct, skb, info->timeout * HZ);
 
 		/* Set expect timeout */
-		spin_lock_bh(&nf_conntrack_lock);
+		spin_lock_bh(&nf_conntrack_expect_lock);
 		exp = find_expect(ct, &ct->tuplehash[dir].tuple.dst.u3,
 				  info->sig_port[!dir]);
 		if (exp) {
@@ -1486,7 +1486,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct,
 			nf_ct_dump_tuple(&exp->tuple);
 			set_expect_timeout(exp, info->timeout);
 		}
-		spin_unlock_bh(&nf_conntrack_lock);
+		spin_unlock_bh(&nf_conntrack_expect_lock);
 	}
 
 	return 0;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 974a2a4adef..5b3eae7d4c9 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -250,16 +250,14 @@ out:
 }
 EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper);
 
+/* appropiate ct lock protecting must be taken by caller */
 static inline int unhelp(struct nf_conntrack_tuple_hash *i,
 			 const struct nf_conntrack_helper *me)
 {
 	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i);
 	struct nf_conn_help *help = nfct_help(ct);
 
-	if (help && rcu_dereference_protected(
-			help->helper,
-			lockdep_is_held(&nf_conntrack_lock)
-			) == me) {
+	if (help && rcu_dereference_raw(help->helper) == me) {
 		nf_conntrack_event(IPCT_HELPER, ct);
 		RCU_INIT_POINTER(help->helper, NULL);
 	}
@@ -284,17 +282,17 @@ static LIST_HEAD(nf_ct_helper_expectfn_list);
 
 void nf_ct_helper_expectfn_register(struct nf_ct_helper_expectfn *n)
 {
-	spin_lock_bh(&nf_conntrack_lock);
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	list_add_rcu(&n->head, &nf_ct_helper_expectfn_list);
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_register);
 
 void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n)
 {
-	spin_lock_bh(&nf_conntrack_lock);
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	list_del_rcu(&n->head);
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 }
 EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister);
 
@@ -396,15 +394,17 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
 	const struct hlist_node *next;
 	const struct hlist_nulls_node *nn;
 	unsigned int i;
+	int cpu;
 
 	/* Get rid of expectations */
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	for (i = 0; i < nf_ct_expect_hsize; i++) {
 		hlist_for_each_entry_safe(exp, next,
 					  &net->ct.expect_hash[i], hnode) {
 			struct nf_conn_help *help = nfct_help(exp->master);
 			if ((rcu_dereference_protected(
 					help->helper,
-					lockdep_is_held(&nf_conntrack_lock)
+					lockdep_is_held(&nf_conntrack_expect_lock)
 					) == me || exp->helper == me) &&
 			    del_timer(&exp->timeout)) {
 				nf_ct_unlink_expect(exp);
@@ -412,14 +412,27 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
 			}
 		}
 	}
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 
 	/* Get rid of expecteds, set helpers to NULL. */
-	hlist_nulls_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode)
-		unhelp(h, me);
-	for (i = 0; i < net->ct.htable_size; i++) {
-		hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
+	for_each_possible_cpu(cpu) {
+		struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+		spin_lock_bh(&pcpu->lock);
+		hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode)
 			unhelp(h, me);
+		spin_unlock_bh(&pcpu->lock);
+	}
+	local_bh_disable();
+	for (i = 0; i < net->ct.htable_size; i++) {
+		spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
+		if (i < net->ct.htable_size) {
+			hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
+				unhelp(h, me);
+		}
+		spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
 	}
+	local_bh_enable();
 }
 
 void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
@@ -437,10 +450,8 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 	synchronize_rcu();
 
 	rtnl_lock();
-	spin_lock_bh(&nf_conntrack_lock);
 	for_each_net(net)
 		__nf_conntrack_helper_unregister(me, net);
-	spin_unlock_bh(&nf_conntrack_lock);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 08870b85904..300ed1eec72 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -597,6 +597,9 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */
 #endif
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	       + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE */
+#endif
 	       + ctnetlink_proto_size(ct)
 	       + ctnetlink_label_size(ct)
 	       ;
@@ -764,14 +767,23 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	u_int8_t l3proto = nfmsg->nfgen_family;
 	int res;
+	spinlock_t *lockp;
+
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	const struct ctnetlink_dump_filter *filter = cb->data;
 #endif
 
-	spin_lock_bh(&nf_conntrack_lock);
 	last = (struct nf_conn *)cb->args[1];
+
+	local_bh_disable();
 	for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) {
 restart:
+		lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS];
+		spin_lock(lockp);
+		if (cb->args[0] >= net->ct.htable_size) {
+			spin_unlock(lockp);
+			goto out;
+		}
 		hlist_nulls_for_each_entry(h, n, &net->ct.hash[cb->args[0]],
 					 hnnode) {
 			if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
@@ -803,16 +815,18 @@ restart:
 			if (res < 0) {
 				nf_conntrack_get(&ct->ct_general);
 				cb->args[1] = (unsigned long)ct;
+				spin_unlock(lockp);
 				goto out;
 			}
 		}
+		spin_unlock(lockp);
 		if (cb->args[1]) {
 			cb->args[1] = 0;
 			goto restart;
 		}
 	}
 out:
-	spin_unlock_bh(&nf_conntrack_lock);
+	local_bh_enable();
 	if (last)
 		nf_ct_put(last);
 
@@ -966,7 +980,6 @@ ctnetlink_parse_help(const struct nlattr *attr, char **helper_name,
 	return 0;
 }
 
-#define __CTA_LABELS_MAX_LENGTH ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE)
 static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
 	[CTA_TUPLE_ORIG]	= { .type = NLA_NESTED },
 	[CTA_TUPLE_REPLY]	= { .type = NLA_NESTED },
@@ -984,9 +997,9 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {
 	[CTA_ZONE]		= { .type = NLA_U16 },
 	[CTA_MARK_MASK]		= { .type = NLA_U32 },
 	[CTA_LABELS]		= { .type = NLA_BINARY,
-				    .len = __CTA_LABELS_MAX_LENGTH },
+				    .len = NF_CT_LABELS_MAX_SIZE },
 	[CTA_LABELS_MASK]	= { .type = NLA_BINARY,
-				    .len = __CTA_LABELS_MAX_LENGTH },
+				    .len = NF_CT_LABELS_MAX_SIZE },
 };
 
 static int
@@ -1138,8 +1151,7 @@ static int ctnetlink_done_list(struct netlink_callback *cb)
 }
 
 static int
-ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb,
-		    struct hlist_nulls_head *list)
+ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying)
 {
 	struct nf_conn *ct, *last;
 	struct nf_conntrack_tuple_hash *h;
@@ -1147,41 +1159,57 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb,
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	u_int8_t l3proto = nfmsg->nfgen_family;
 	int res;
+	int cpu;
+	struct hlist_nulls_head *list;
+	struct net *net = sock_net(skb->sk);
 
 	if (cb->args[2])
 		return 0;
 
-	spin_lock_bh(&nf_conntrack_lock);
 	last = (struct nf_conn *)cb->args[1];
-restart:
-	hlist_nulls_for_each_entry(h, n, list, hnnode) {
-		ct = nf_ct_tuplehash_to_ctrack(h);
-		if (l3proto && nf_ct_l3num(ct) != l3proto)
+
+	for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) {
+		struct ct_pcpu *pcpu;
+
+		if (!cpu_possible(cpu))
 			continue;
-		if (cb->args[1]) {
-			if (ct != last)
+
+		pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+		spin_lock_bh(&pcpu->lock);
+		list = dying ? &pcpu->dying : &pcpu->unconfirmed;
+restart:
+		hlist_nulls_for_each_entry(h, n, list, hnnode) {
+			ct = nf_ct_tuplehash_to_ctrack(h);
+			if (l3proto && nf_ct_l3num(ct) != l3proto)
 				continue;
-			cb->args[1] = 0;
+			if (cb->args[1]) {
+				if (ct != last)
+					continue;
+				cb->args[1] = 0;
+			}
+			rcu_read_lock();
+			res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
+						  cb->nlh->nlmsg_seq,
+						  NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
+						  ct);
+			rcu_read_unlock();
+			if (res < 0) {
+				if (!atomic_inc_not_zero(&ct->ct_general.use))
+					continue;
+				cb->args[0] = cpu;
+				cb->args[1] = (unsigned long)ct;
+				spin_unlock_bh(&pcpu->lock);
+				goto out;
+			}
 		}
-		rcu_read_lock();
-		res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid,
-					  cb->nlh->nlmsg_seq,
-					  NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
-					  ct);
-		rcu_read_unlock();
-		if (res < 0) {
-			nf_conntrack_get(&ct->ct_general);
-			cb->args[1] = (unsigned long)ct;
-			goto out;
+		if (cb->args[1]) {
+			cb->args[1] = 0;
+			goto restart;
 		}
+		spin_unlock_bh(&pcpu->lock);
 	}
-	if (cb->args[1]) {
-		cb->args[1] = 0;
-		goto restart;
-	} else
-		cb->args[2] = 1;
+	cb->args[2] = 1;
 out:
-	spin_unlock_bh(&nf_conntrack_lock);
 	if (last)
 		nf_ct_put(last);
 
@@ -1191,9 +1219,7 @@ out:
 static int
 ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct net *net = sock_net(skb->sk);
-
-	return ctnetlink_dump_list(skb, cb, &net->ct.dying);
+	return ctnetlink_dump_list(skb, cb, true);
 }
 
 static int
@@ -1215,9 +1241,7 @@ ctnetlink_get_ct_dying(struct sock *ctnl, struct sk_buff *skb,
 static int
 ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct net *net = sock_net(skb->sk);
-
-	return ctnetlink_dump_list(skb, cb, &net->ct.unconfirmed);
+	return ctnetlink_dump_list(skb, cb, false);
 }
 
 static int
@@ -1310,27 +1334,25 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[])
 }
 
 static int
-ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[])
+ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
 {
 #ifdef CONFIG_NF_NAT_NEEDED
 	int ret;
 
-	if (cda[CTA_NAT_DST]) {
-		ret = ctnetlink_parse_nat_setup(ct,
-						NF_NAT_MANIP_DST,
-						cda[CTA_NAT_DST]);
-		if (ret < 0)
-			return ret;
-	}
-	if (cda[CTA_NAT_SRC]) {
-		ret = ctnetlink_parse_nat_setup(ct,
-						NF_NAT_MANIP_SRC,
-						cda[CTA_NAT_SRC]);
-		if (ret < 0)
-			return ret;
-	}
-	return 0;
+	if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
+		return 0;
+
+	ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST,
+					cda[CTA_NAT_DST]);
+	if (ret < 0)
+		return ret;
+
+	ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC,
+					cda[CTA_NAT_SRC]);
+	return ret;
 #else
+	if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
+		return 0;
 	return -EOPNOTSUPP;
 #endif
 }
@@ -1366,14 +1388,14 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[])
 					    nf_ct_protonum(ct));
 	if (helper == NULL) {
 #ifdef CONFIG_MODULES
-		spin_unlock_bh(&nf_conntrack_lock);
+		spin_unlock_bh(&nf_conntrack_expect_lock);
 
 		if (request_module("nfct-helper-%s", helpname) < 0) {
-			spin_lock_bh(&nf_conntrack_lock);
+			spin_lock_bh(&nf_conntrack_expect_lock);
 			return -EOPNOTSUPP;
 		}
 
-		spin_lock_bh(&nf_conntrack_lock);
+		spin_lock_bh(&nf_conntrack_expect_lock);
 		helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
 						    nf_ct_protonum(ct));
 		if (helper)
@@ -1659,11 +1681,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
 			goto err2;
 	}
 
-	if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
-		err = ctnetlink_change_nat(ct, cda);
-		if (err < 0)
-			goto err2;
-	}
+	err = ctnetlink_setup_nat(ct, cda);
+	if (err < 0)
+		goto err2;
 
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
 	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
@@ -1811,9 +1831,9 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	err = -EEXIST;
 	ct = nf_ct_tuplehash_to_ctrack(h);
 	if (!(nlh->nlmsg_flags & NLM_F_EXCL)) {
-		spin_lock_bh(&nf_conntrack_lock);
+		spin_lock_bh(&nf_conntrack_expect_lock);
 		err = ctnetlink_change_conntrack(ct, cda);
-		spin_unlock_bh(&nf_conntrack_lock);
+		spin_unlock_bh(&nf_conntrack_expect_lock);
 		if (err == 0) {
 			nf_conntrack_eventmask_report((1 << IPCT_REPLY) |
 						      (1 << IPCT_ASSURED) |
@@ -2023,6 +2043,9 @@ ctnetlink_nfqueue_build_size(const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */
 #endif
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	       + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE */
+#endif
 	       + ctnetlink_proto_size(ct)
 	       ;
 }
@@ -2118,8 +2141,16 @@ ctnetlink_nfqueue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct)
 			return err;
 	}
 #if defined(CONFIG_NF_CONNTRACK_MARK)
-	if (cda[CTA_MARK])
-		ct->mark = ntohl(nla_get_be32(cda[CTA_MARK]));
+	if (cda[CTA_MARK]) {
+		u32 mask = 0, mark, newmark;
+		if (cda[CTA_MARK_MASK])
+			mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK]));
+
+		mark = ntohl(nla_get_be32(cda[CTA_MARK]));
+		newmark = (ct->mark & mask) ^ mark;
+		if (newmark != ct->mark)
+			ct->mark = newmark;
+	}
 #endif
 	return 0;
 }
@@ -2134,9 +2165,9 @@ ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct)
 	if (ret < 0)
 		return ret;
 
-	spin_lock_bh(&nf_conntrack_lock);
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	ret = ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct);
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 
 	return ret;
 }
@@ -2691,13 +2722,13 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
 		}
 
 		/* after list removal, usage count == 1 */
-		spin_lock_bh(&nf_conntrack_lock);
+		spin_lock_bh(&nf_conntrack_expect_lock);
 		if (del_timer(&exp->timeout)) {
 			nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid,
 						   nlmsg_report(nlh));
 			nf_ct_expect_put(exp);
 		}
-		spin_unlock_bh(&nf_conntrack_lock);
+		spin_unlock_bh(&nf_conntrack_expect_lock);
 		/* have to put what we 'get' above.
 		 * after this line usage count == 0 */
 		nf_ct_expect_put(exp);
@@ -2706,7 +2737,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
 		struct nf_conn_help *m_help;
 
 		/* delete all expectations for this helper */
-		spin_lock_bh(&nf_conntrack_lock);
+		spin_lock_bh(&nf_conntrack_expect_lock);
 		for (i = 0; i < nf_ct_expect_hsize; i++) {
 			hlist_for_each_entry_safe(exp, next,
 						  &net->ct.expect_hash[i],
@@ -2721,10 +2752,10 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
 				}
 			}
 		}
-		spin_unlock_bh(&nf_conntrack_lock);
+		spin_unlock_bh(&nf_conntrack_expect_lock);
 	} else {
 		/* This basically means we have to flush everything*/
-		spin_lock_bh(&nf_conntrack_lock);
+		spin_lock_bh(&nf_conntrack_expect_lock);
 		for (i = 0; i < nf_ct_expect_hsize; i++) {
 			hlist_for_each_entry_safe(exp, next,
 						  &net->ct.expect_hash[i],
@@ -2737,7 +2768,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
 				}
 			}
 		}
-		spin_unlock_bh(&nf_conntrack_lock);
+		spin_unlock_bh(&nf_conntrack_expect_lock);
 	}
 
 	return 0;
@@ -2963,11 +2994,11 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	spin_lock_bh(&nf_conntrack_lock);
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	exp = __nf_ct_expect_find(net, zone, &tuple);
 
 	if (!exp) {
-		spin_unlock_bh(&nf_conntrack_lock);
+		spin_unlock_bh(&nf_conntrack_expect_lock);
 		err = -ENOENT;
 		if (nlh->nlmsg_flags & NLM_F_CREATE) {
 			err = ctnetlink_create_expect(net, zone, cda,
@@ -2981,7 +3012,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
 	err = -EEXIST;
 	if (!(nlh->nlmsg_flags & NLM_F_EXCL))
 		err = ctnetlink_change_expect(exp, cda);
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 
 	return err;
 }
diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c
index 7bd03decd36..825c3e3f830 100644
--- a/net/netfilter/nf_conntrack_pptp.c
+++ b/net/netfilter/nf_conntrack_pptp.c
@@ -605,32 +605,14 @@ static struct nf_conntrack_helper pptp __read_mostly = {
 	.expect_policy		= &pptp_exp_policy,
 };
 
-static void nf_conntrack_pptp_net_exit(struct net *net)
-{
-	nf_ct_gre_keymap_flush(net);
-}
-
-static struct pernet_operations nf_conntrack_pptp_net_ops = {
-	.exit = nf_conntrack_pptp_net_exit,
-};
-
 static int __init nf_conntrack_pptp_init(void)
 {
-	int rv;
-
-	rv = nf_conntrack_helper_register(&pptp);
-	if (rv < 0)
-		return rv;
-	rv = register_pernet_subsys(&nf_conntrack_pptp_net_ops);
-	if (rv < 0)
-		nf_conntrack_helper_unregister(&pptp);
-	return rv;
+	return nf_conntrack_helper_register(&pptp);
 }
 
 static void __exit nf_conntrack_pptp_fini(void)
 {
 	nf_conntrack_helper_unregister(&pptp);
-	unregister_pernet_subsys(&nf_conntrack_pptp_net_ops);
 }
 
 module_init(nf_conntrack_pptp_init);
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index ce3004156ee..b65d5864b6d 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -92,12 +92,6 @@ nf_ct_l3proto_find_get(u_int16_t l3proto)
 }
 EXPORT_SYMBOL_GPL(nf_ct_l3proto_find_get);
 
-void nf_ct_l3proto_put(struct nf_conntrack_l3proto *p)
-{
-	module_put(p->me);
-}
-EXPORT_SYMBOL_GPL(nf_ct_l3proto_put);
-
 int
 nf_ct_l3proto_try_module_get(unsigned short l3proto)
 {
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index a99b6c3427b..cb372f96f10 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -428,7 +428,7 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	const char *msg;
 	u_int8_t state;
 
-	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
+	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
 	BUG_ON(dh == NULL);
 
 	state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE];
@@ -457,7 +457,7 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 out_invalid:
 	if (LOG_INVALID(net, IPPROTO_DCCP))
 		nf_log_packet(net, nf_ct_l3num(ct), 0, skb, NULL, NULL,
-			      NULL, msg);
+			      NULL, "%s", msg);
 	return false;
 }
 
@@ -486,7 +486,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
 	u_int8_t type, old_state, new_state;
 	enum ct_dccp_roles role;
 
-	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
+	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
 	BUG_ON(dh == NULL);
 	type = dh->dccph_type;
 
@@ -577,7 +577,7 @@ static int dccp_error(struct net *net, struct nf_conn *tmpl,
 	unsigned int cscov;
 	const char *msg;
 
-	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
+	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
 	if (dh == NULL) {
 		msg = "nf_ct_dccp: short packet ";
 		goto out_invalid;
@@ -614,7 +614,7 @@ static int dccp_error(struct net *net, struct nf_conn *tmpl,
 
 out_invalid:
 	if (LOG_INVALID(net, IPPROTO_DCCP))
-		nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, msg);
+		nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "%s", msg);
 	return -NF_ACCEPT;
 }
 
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 9d9c0dade60..d5665739e3b 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -66,7 +66,7 @@ static inline struct netns_proto_gre *gre_pernet(struct net *net)
 	return net_generic(net, proto_gre_net_id);
 }
 
-void nf_ct_gre_keymap_flush(struct net *net)
+static void nf_ct_gre_keymap_flush(struct net *net)
 {
 	struct netns_proto_gre *net_gre = gre_pernet(net);
 	struct nf_ct_gre_keymap *km, *tmp;
@@ -78,7 +78,6 @@ void nf_ct_gre_keymap_flush(struct net *net)
 	}
 	write_unlock_bh(&net_gre->keymap_lock);
 }
-EXPORT_SYMBOL(nf_ct_gre_keymap_flush);
 
 static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km,
 				const struct nf_conntrack_tuple *t)
diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c
index 17c1bcb182c..f6e2ae91a80 100644
--- a/net/netfilter/nf_conntrack_seqadj.c
+++ b/net/netfilter/nf_conntrack_seqadj.c
@@ -36,6 +36,11 @@ int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
 	if (off == 0)
 		return 0;
 
+	if (unlikely(!seqadj)) {
+		WARN_ONCE(1, "Missing nfct_seqadj_ext_add() setup call\n");
+		return 0;
+	}
+
 	set_bit(IPS_SEQ_ADJUST_BIT, &ct->status);
 
 	spin_lock_bh(&ct->lock);
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 466410eaa48..4c3ba1c8d68 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -800,7 +800,7 @@ static int refresh_signalling_expectation(struct nf_conn *ct,
 	struct hlist_node *next;
 	int found = 0;
 
-	spin_lock_bh(&nf_conntrack_lock);
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
 		if (exp->class != SIP_EXPECT_SIGNALLING ||
 		    !nf_inet_addr_cmp(&exp->tuple.dst.u3, addr) ||
@@ -815,7 +815,7 @@ static int refresh_signalling_expectation(struct nf_conn *ct,
 		found = 1;
 		break;
 	}
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 	return found;
 }
 
@@ -825,7 +825,7 @@ static void flush_expectations(struct nf_conn *ct, bool media)
 	struct nf_conntrack_expect *exp;
 	struct hlist_node *next;
 
-	spin_lock_bh(&nf_conntrack_lock);
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
 		if ((exp->class != SIP_EXPECT_SIGNALLING) ^ media)
 			continue;
@@ -836,7 +836,7 @@ static void flush_expectations(struct nf_conn *ct, bool media)
 		if (!media)
 			break;
 	}
-	spin_unlock_bh(&nf_conntrack_lock);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
 }
 
 static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c
index 902fb0a6b38..7a394df0deb 100644
--- a/net/netfilter/nf_conntrack_timestamp.c
+++ b/net/netfilter/nf_conntrack_timestamp.c
@@ -97,7 +97,6 @@ int nf_conntrack_tstamp_pernet_init(struct net *net)
 void nf_conntrack_tstamp_pernet_fini(struct net *net)
 {
 	nf_conntrack_tstamp_fini_sysctl(net);
-	nf_ct_extend_unregister(&tstamp_extend);
 }
 
 int nf_conntrack_tstamp_init(void)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 63a81540221..a49907b1dab 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -315,7 +315,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	 * manips not an issue.
 	 */
 	if (maniptype == NF_NAT_MANIP_SRC &&
-	    !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) {
+	    !(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
 		/* try the original tuple first */
 		if (in_range(l3proto, l4proto, orig_tuple, range)) {
 			if (!nf_nat_used_tuple(orig_tuple, ct)) {
@@ -339,7 +339,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
 	 */
 
 	/* Only bother mapping if it's not already in range and unique */
-	if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) {
+	if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
 		if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
 			if (l4proto->in_range(tuple, maniptype,
 					      &range->min_proto,
@@ -358,6 +358,19 @@ out:
 	rcu_read_unlock();
 }
 
+struct nf_conn_nat *nf_ct_nat_ext_add(struct nf_conn *ct)
+{
+	struct nf_conn_nat *nat = nfct_nat(ct);
+	if (nat)
+		return nat;
+
+	if (!nf_ct_is_confirmed(ct))
+		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
+
+	return nat;
+}
+EXPORT_SYMBOL_GPL(nf_ct_nat_ext_add);
+
 unsigned int
 nf_nat_setup_info(struct nf_conn *ct,
 		  const struct nf_nat_range *range,
@@ -368,14 +381,9 @@ nf_nat_setup_info(struct nf_conn *ct,
 	struct nf_conn_nat *nat;
 
 	/* nat helper or nfctnetlink also setup binding */
-	nat = nfct_nat(ct);
-	if (!nat) {
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL) {
-			pr_debug("failed to add NAT extension\n");
-			return NF_ACCEPT;
-		}
-	}
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
 
 	NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC ||
 		     maniptype == NF_NAT_MANIP_DST);
@@ -432,15 +440,15 @@ nf_nat_setup_info(struct nf_conn *ct,
 }
 EXPORT_SYMBOL(nf_nat_setup_info);
 
-unsigned int
-nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+static unsigned int
+__nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip)
 {
 	/* Force range to this IP; let proto decide mapping for
 	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
 	 * Use reply in case it's already been mangled (eg local packet).
 	 */
 	union nf_inet_addr ip =
-		(HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
+		(manip == NF_NAT_MANIP_SRC ?
 		ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 :
 		ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3);
 	struct nf_nat_range range = {
@@ -448,7 +456,13 @@ nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
 		.min_addr	= ip,
 		.max_addr	= ip,
 	};
-	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
+	return nf_nat_setup_info(ct, &range, manip);
+}
+
+unsigned int
+nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+{
+	return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum));
 }
 EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding);
 
@@ -511,6 +525,39 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data)
 	return i->status & IPS_NAT_MASK ? 1 : 0;
 }
 
+static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
+{
+	struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (nf_nat_proto_remove(ct, data))
+		return 1;
+
+	if (!nat || !nat->ct)
+		return 0;
+
+	/* This netns is being destroyed, and conntrack has nat null binding.
+	 * Remove it from bysource hash, as the table will be freed soon.
+	 *
+	 * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack()
+	 * will delete entry from already-freed table.
+	 */
+	if (!del_timer(&ct->timeout))
+		return 1;
+
+	spin_lock_bh(&nf_nat_lock);
+	hlist_del_rcu(&nat->bysource);
+	ct->status &= ~IPS_NAT_DONE_MASK;
+	nat->ct = NULL;
+	spin_unlock_bh(&nf_nat_lock);
+
+	add_timer(&ct->timeout);
+
+	/* don't delete conntrack.  Although that would make things a lot
+	 * simpler, we'd end up flushing all conntracks on nat rmmod.
+	 */
+	return 0;
+}
+
 static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
 {
 	struct nf_nat_proto_clean clean = {
@@ -702,9 +749,9 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = {
 
 static int
 nfnetlink_parse_nat(const struct nlattr *nat,
-		    const struct nf_conn *ct, struct nf_nat_range *range)
+		    const struct nf_conn *ct, struct nf_nat_range *range,
+		    const struct nf_nat_l3proto *l3proto)
 {
-	const struct nf_nat_l3proto *l3proto;
 	struct nlattr *tb[CTA_NAT_MAX+1];
 	int err;
 
@@ -714,38 +761,46 @@ nfnetlink_parse_nat(const struct nlattr *nat,
 	if (err < 0)
 		return err;
 
-	rcu_read_lock();
-	l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
-	if (l3proto == NULL) {
-		err = -EAGAIN;
-		goto out;
-	}
 	err = l3proto->nlattr_to_range(tb, range);
 	if (err < 0)
-		goto out;
+		return err;
 
 	if (!tb[CTA_NAT_PROTO])
-		goto out;
+		return 0;
 
-	err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
-out:
-	rcu_read_unlock();
-	return err;
+	return nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range);
 }
 
+/* This function is called under rcu_read_lock() */
 static int
 nfnetlink_parse_nat_setup(struct nf_conn *ct,
 			  enum nf_nat_manip_type manip,
 			  const struct nlattr *attr)
 {
 	struct nf_nat_range range;
+	const struct nf_nat_l3proto *l3proto;
 	int err;
 
-	err = nfnetlink_parse_nat(attr, ct, &range);
+	/* Should not happen, restricted to creating new conntracks
+	 * via ctnetlink.
+	 */
+	if (WARN_ON_ONCE(nf_nat_initialized(ct, manip)))
+		return -EEXIST;
+
+	/* Make sure that L3 NAT is there by when we call nf_nat_setup_info to
+	 * attach the null binding, otherwise this may oops.
+	 */
+	l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct));
+	if (l3proto == NULL)
+		return -EAGAIN;
+
+	/* No NAT information has been passed, allocate the null-binding */
+	if (attr == NULL)
+		return __nf_nat_alloc_null_binding(ct, manip);
+
+	err = nfnetlink_parse_nat(attr, ct, &range, l3proto);
 	if (err < 0)
 		return err;
-	if (nf_nat_initialized(ct, manip))
-		return -EEXIST;
 
 	return nf_nat_setup_info(ct, &range, manip);
 }
@@ -773,7 +828,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
 	struct nf_nat_proto_clean clean = {};
 
-	nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean, 0, 0);
+	nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean, 0, 0);
 	synchronize_rcu();
 	nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
 }
diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c
index f02b3605823..1fb2258c353 100644
--- a/net/netfilter/nf_nat_irc.c
+++ b/net/netfilter/nf_nat_irc.c
@@ -34,10 +34,14 @@ static unsigned int help(struct sk_buff *skb,
 			 struct nf_conntrack_expect *exp)
 {
 	char buffer[sizeof("4294967296 65635")];
+	struct nf_conn *ct = exp->master;
+	union nf_inet_addr newaddr;
 	u_int16_t port;
 	unsigned int ret;
 
 	/* Reply comes from server. */
+	newaddr = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3;
+
 	exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
 	exp->dir = IP_CT_DIR_REPLY;
 	exp->expectfn = nf_nat_follow_master;
@@ -57,17 +61,35 @@ static unsigned int help(struct sk_buff *skb,
 	}
 
 	if (port == 0) {
-		nf_ct_helper_log(skb, exp->master, "all ports in use");
+		nf_ct_helper_log(skb, ct, "all ports in use");
 		return NF_DROP;
 	}
 
-	ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo,
-				       protoff, matchoff, matchlen, buffer,
-				       strlen(buffer));
+	/* strlen("\1DCC CHAT chat AAAAAAAA P\1\n")=27
+	 * strlen("\1DCC SCHAT chat AAAAAAAA P\1\n")=28
+	 * strlen("\1DCC SEND F AAAAAAAA P S\1\n")=26
+	 * strlen("\1DCC MOVE F AAAAAAAA P S\1\n")=26
+	 * strlen("\1DCC TSEND F AAAAAAAA P S\1\n")=27
+	 *
+	 * AAAAAAAAA: bound addr (1.0.0.0==16777216, min 8 digits,
+	 *                        255.255.255.255==4294967296, 10 digits)
+	 * P:         bound port (min 1 d, max 5d (65635))
+	 * F:         filename   (min 1 d )
+	 * S:         size       (min 1 d )
+	 * 0x01, \n:  terminators
+	 */
+	/* AAA = "us", ie. where server normally talks to. */
+	snprintf(buffer, sizeof(buffer), "%u %u", ntohl(newaddr.ip), port);
+	pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n",
+		 buffer, &newaddr.ip, port);
+
+	ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff,
+				       matchlen, buffer, strlen(buffer));
 	if (ret != NF_ACCEPT) {
-		nf_ct_helper_log(skb, exp->master, "cannot mangle packet");
+		nf_ct_helper_log(skb, ct, "cannot mangle packet");
 		nf_ct_unexpect_related(exp);
 	}
+
 	return ret;
 }
 
diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c
index 9baaf734c14..83a72a235ca 100644
--- a/net/netfilter/nf_nat_proto_common.c
+++ b/net/netfilter/nf_nat_proto_common.c
@@ -74,22 +74,24 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
 		range_size = ntohs(range->max_proto.all) - min + 1;
 	}
 
-	if (range->flags & NF_NAT_RANGE_PROTO_RANDOM)
+	if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) {
 		off = l3proto->secure_port(tuple, maniptype == NF_NAT_MANIP_SRC
 						  ? tuple->dst.u.all
 						  : tuple->src.u.all);
-	else
+	} else if (range->flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY) {
+		off = prandom_u32();
+	} else {
 		off = *rover;
+	}
 
 	for (i = 0; ; ++off) {
 		*portptr = htons(min + off % range_size);
 		if (++i != range_size && nf_nat_used_tuple(tuple, ct))
 			continue;
-		if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM))
+		if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL))
 			*rover = off;
 		return;
 	}
-	return;
 }
 EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple);
 
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 9858e3e51a3..52e20c9a46a 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -363,9 +363,8 @@ static int __net_init synproxy_net_init(struct net *net)
 		goto err2;
 	if (!nfct_synproxy_ext_add(ct))
 		goto err2;
-	__set_bit(IPS_TEMPLATE_BIT, &ct->status);
-	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
 
+	nf_conntrack_tmpl_insert(net, ct);
 	snet->tmpl = ct;
 
 	snet->stats = alloc_percpu(struct synproxy_stats);
@@ -390,7 +389,7 @@ static void __net_exit synproxy_net_exit(struct net *net)
 {
 	struct synproxy_net *snet = synproxy_pernet(net);
 
-	nf_conntrack_free(snet->tmpl);
+	nf_ct_put(snet->tmpl);
 	synproxy_proc_exit(net);
 	free_percpu(snet->stats);
 }
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index dcddc49c0e0..8746ff9a835 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -35,7 +35,7 @@ int nft_register_afinfo(struct net *net, struct nft_af_info *afi)
 {
 	INIT_LIST_HEAD(&afi->tables);
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_add_tail(&afi->list, &net->nft.af_info);
+	list_add_tail_rcu(&afi->list, &net->nft.af_info);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 	return 0;
 }
@@ -51,7 +51,7 @@ EXPORT_SYMBOL_GPL(nft_register_afinfo);
 void nft_unregister_afinfo(struct nft_af_info *afi)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_del(&afi->list);
+	list_del_rcu(&afi->list);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 }
 EXPORT_SYMBOL_GPL(nft_unregister_afinfo);
@@ -88,6 +88,45 @@ nf_tables_afinfo_lookup(struct net *net, int family, bool autoload)
 	return ERR_PTR(-EAFNOSUPPORT);
 }
 
+static void nft_ctx_init(struct nft_ctx *ctx,
+			 const struct sk_buff *skb,
+			 const struct nlmsghdr *nlh,
+			 struct nft_af_info *afi,
+			 struct nft_table *table,
+			 struct nft_chain *chain,
+			 const struct nlattr * const *nla)
+{
+	ctx->net	= sock_net(skb->sk);
+	ctx->afi	= afi;
+	ctx->table	= table;
+	ctx->chain	= chain;
+	ctx->nla   	= nla;
+	ctx->portid	= NETLINK_CB(skb).portid;
+	ctx->report	= nlmsg_report(nlh);
+	ctx->seq	= nlh->nlmsg_seq;
+}
+
+static struct nft_trans *nft_trans_alloc(struct nft_ctx *ctx, int msg_type,
+					 u32 size)
+{
+	struct nft_trans *trans;
+
+	trans = kzalloc(sizeof(struct nft_trans) + size, GFP_KERNEL);
+	if (trans == NULL)
+		return NULL;
+
+	trans->msg_type = msg_type;
+	trans->ctx	= *ctx;
+
+	return trans;
+}
+
+static void nft_trans_destroy(struct nft_trans *trans)
+{
+	list_del(&trans->list);
+	kfree(trans);
+}
+
 /*
  * Tables
  */
@@ -124,37 +163,43 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table)
 	return ++table->hgenerator;
 }
 
-static struct nf_chain_type *chain_type[AF_MAX][NFT_CHAIN_T_MAX];
+static const struct nf_chain_type *chain_type[AF_MAX][NFT_CHAIN_T_MAX];
 
-static int __nf_tables_chain_type_lookup(int family, const struct nlattr *nla)
+static const struct nf_chain_type *
+__nf_tables_chain_type_lookup(int family, const struct nlattr *nla)
 {
 	int i;
 
-	for (i=0; i<NFT_CHAIN_T_MAX; i++) {
+	for (i = 0; i < NFT_CHAIN_T_MAX; i++) {
 		if (chain_type[family][i] != NULL &&
 		    !nla_strcmp(nla, chain_type[family][i]->name))
-			return i;
+			return chain_type[family][i];
 	}
-	return -1;
+	return NULL;
 }
 
-static int nf_tables_chain_type_lookup(const struct nft_af_info *afi,
-				       const struct nlattr *nla,
-				       bool autoload)
+static const struct nf_chain_type *
+nf_tables_chain_type_lookup(const struct nft_af_info *afi,
+			    const struct nlattr *nla,
+			    bool autoload)
 {
-	int type;
+	const struct nf_chain_type *type;
 
 	type = __nf_tables_chain_type_lookup(afi->family, nla);
+	if (type != NULL)
+		return type;
 #ifdef CONFIG_MODULES
-	if (type < 0 && autoload) {
+	if (autoload) {
 		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-		request_module("nft-chain-%u-%*.s", afi->family,
-			       nla_len(nla)-1, (const char *)nla_data(nla));
+		request_module("nft-chain-%u-%.*s", afi->family,
+			       nla_len(nla), (const char *)nla_data(nla));
 		nfnl_lock(NFNL_SUBSYS_NFTABLES);
 		type = __nf_tables_chain_type_lookup(afi->family, nla);
+		if (type != NULL)
+			return ERR_PTR(-EAGAIN);
 	}
 #endif
-	return type;
+	return ERR_PTR(-ENOENT);
 }
 
 static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
@@ -180,7 +225,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, u32 portid, u32 seq,
 	nfmsg->res_id		= 0;
 
 	if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) ||
-	    nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)))
+	    nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) ||
+	    nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)))
 		goto nla_put_failure;
 
 	return nlmsg_end(skb, nlh);
@@ -190,20 +236,13 @@ nla_put_failure:
 	return -1;
 }
 
-static int nf_tables_table_notify(const struct sk_buff *oskb,
-				  const struct nlmsghdr *nlh,
-				  const struct nft_table *table,
-				  int event, int family)
+static int nf_tables_table_notify(const struct nft_ctx *ctx, int event)
 {
 	struct sk_buff *skb;
-	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
-	u32 seq = nlh ? nlh->nlmsg_seq : 0;
-	struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
-	bool report;
 	int err;
 
-	report = nlh ? nlmsg_report(nlh) : false;
-	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+	if (!ctx->report &&
+	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return 0;
 
 	err = -ENOBUFS;
@@ -211,18 +250,20 @@ static int nf_tables_table_notify(const struct sk_buff *oskb,
 	if (skb == NULL)
 		goto err;
 
-	err = nf_tables_fill_table_info(skb, portid, seq, event, 0,
-					family, table);
+	err = nf_tables_fill_table_info(skb, ctx->portid, ctx->seq, event, 0,
+					ctx->afi->family, ctx->table);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
-			     GFP_KERNEL);
+	err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+			     ctx->report, GFP_KERNEL);
 err:
-	if (err < 0)
-		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	if (err < 0) {
+		nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+				  err);
+	}
 	return err;
 }
 
@@ -236,11 +277,14 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
-	list_for_each_entry(afi, &net->nft.af_info, list) {
+	rcu_read_lock();
+	cb->seq = net->nft.base_seq;
+
+	list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
 		if (family != NFPROTO_UNSPEC && family != afi->family)
 			continue;
 
-		list_for_each_entry(table, &afi->tables, list) {
+		list_for_each_entry_rcu(table, &afi->tables, list) {
 			if (idx < s_idx)
 				goto cont;
 			if (idx > s_idx)
@@ -253,15 +297,21 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
 						      NLM_F_MULTI,
 						      afi->family, table) < 0)
 				goto done;
+
+			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 			idx++;
 		}
 	}
 done:
+	rcu_read_unlock();
 	cb->args[0] = idx;
 	return skb->len;
 }
 
+/* Internal table flags */
+#define NFT_TABLE_INACTIVE	(1 << 15)
+
 static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
@@ -288,6 +338,8 @@ static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb2)
@@ -306,13 +358,17 @@ err:
 	return err;
 }
 
-static int nf_tables_table_enable(struct nft_table *table)
+static int nf_tables_table_enable(const struct nft_af_info *afi,
+				  struct nft_table *table)
 {
 	struct nft_chain *chain;
 	int err, i = 0;
 
 	list_for_each_entry(chain, &table->chains, list) {
-		err = nf_register_hook(&nft_base_chain(chain)->ops);
+		if (!(chain->flags & NFT_BASE_CHAIN))
+			continue;
+
+		err = nf_register_hooks(nft_base_chain(chain)->ops, afi->nops);
 		if (err < 0)
 			goto err;
 
@@ -321,59 +377,87 @@ static int nf_tables_table_enable(struct nft_table *table)
 	return 0;
 err:
 	list_for_each_entry(chain, &table->chains, list) {
+		if (!(chain->flags & NFT_BASE_CHAIN))
+			continue;
+
 		if (i-- <= 0)
 			break;
 
-		nf_unregister_hook(&nft_base_chain(chain)->ops);
+		nf_unregister_hooks(nft_base_chain(chain)->ops, afi->nops);
 	}
 	return err;
 }
 
-static int nf_tables_table_disable(struct nft_table *table)
+static void nf_tables_table_disable(const struct nft_af_info *afi,
+				   struct nft_table *table)
 {
 	struct nft_chain *chain;
 
-	list_for_each_entry(chain, &table->chains, list)
-		nf_unregister_hook(&nft_base_chain(chain)->ops);
-
-	return 0;
+	list_for_each_entry(chain, &table->chains, list) {
+		if (chain->flags & NFT_BASE_CHAIN)
+			nf_unregister_hooks(nft_base_chain(chain)->ops,
+					    afi->nops);
+	}
 }
 
-static int nf_tables_updtable(struct sock *nlsk, struct sk_buff *skb,
-			      const struct nlmsghdr *nlh,
-			      const struct nlattr * const nla[],
-			      struct nft_af_info *afi, struct nft_table *table)
+static int nf_tables_updtable(struct nft_ctx *ctx)
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	int family = nfmsg->nfgen_family, ret = 0;
+	struct nft_trans *trans;
+	u32 flags;
+	int ret = 0;
 
-	if (nla[NFTA_TABLE_FLAGS]) {
-		__be32 flags;
+	if (!ctx->nla[NFTA_TABLE_FLAGS])
+		return 0;
 
-		flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS]));
-		if (flags & ~NFT_TABLE_F_DORMANT)
-			return -EINVAL;
+	flags = ntohl(nla_get_be32(ctx->nla[NFTA_TABLE_FLAGS]));
+	if (flags & ~NFT_TABLE_F_DORMANT)
+		return -EINVAL;
+
+	if (flags == ctx->table->flags)
+		return 0;
+
+	trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE,
+				sizeof(struct nft_trans_table));
+	if (trans == NULL)
+		return -ENOMEM;
 
-		if ((flags & NFT_TABLE_F_DORMANT) &&
-		    !(table->flags & NFT_TABLE_F_DORMANT)) {
-			ret = nf_tables_table_disable(table);
-			if (ret >= 0)
-				table->flags |= NFT_TABLE_F_DORMANT;
-		} else if (!(flags & NFT_TABLE_F_DORMANT) &&
-			   table->flags & NFT_TABLE_F_DORMANT) {
-			ret = nf_tables_table_enable(table);
-			if (ret >= 0)
-				table->flags &= ~NFT_TABLE_F_DORMANT;
+	if ((flags & NFT_TABLE_F_DORMANT) &&
+	    !(ctx->table->flags & NFT_TABLE_F_DORMANT)) {
+		nft_trans_table_enable(trans) = false;
+	} else if (!(flags & NFT_TABLE_F_DORMANT) &&
+		   ctx->table->flags & NFT_TABLE_F_DORMANT) {
+		ret = nf_tables_table_enable(ctx->afi, ctx->table);
+		if (ret >= 0) {
+			ctx->table->flags &= ~NFT_TABLE_F_DORMANT;
+			nft_trans_table_enable(trans) = true;
 		}
-		if (ret < 0)
-			goto err;
 	}
+	if (ret < 0)
+		goto err;
 
-	nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family);
+	nft_trans_table_update(trans) = true;
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+	return 0;
 err:
+	nft_trans_destroy(trans);
 	return ret;
 }
 
+static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type)
+{
+	struct nft_trans *trans;
+
+	trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_table));
+	if (trans == NULL)
+		return -ENOMEM;
+
+	if (msg_type == NFT_MSG_NEWTABLE)
+		ctx->table->flags |= NFT_TABLE_INACTIVE;
+
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+	return 0;
+}
+
 static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
@@ -384,6 +468,9 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_table *table;
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
+	u32 flags = 0;
+	struct nft_ctx ctx;
+	int err;
 
 	afi = nf_tables_afinfo_lookup(net, family, true);
 	if (IS_ERR(afi))
@@ -398,35 +485,45 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	}
 
 	if (table != NULL) {
+		if (table->flags & NFT_TABLE_INACTIVE)
+			return -ENOENT;
 		if (nlh->nlmsg_flags & NLM_F_EXCL)
 			return -EEXIST;
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
-		return nf_tables_updtable(nlsk, skb, nlh, nla, afi, table);
+
+		nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+		return nf_tables_updtable(&ctx);
 	}
 
+	if (nla[NFTA_TABLE_FLAGS]) {
+		flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS]));
+		if (flags & ~NFT_TABLE_F_DORMANT)
+			return -EINVAL;
+	}
+
+	if (!try_module_get(afi->owner))
+		return -EAFNOSUPPORT;
+
 	table = kzalloc(sizeof(*table) + nla_len(name), GFP_KERNEL);
-	if (table == NULL)
+	if (table == NULL) {
+		module_put(afi->owner);
 		return -ENOMEM;
+	}
 
 	nla_strlcpy(table->name, name, nla_len(name));
 	INIT_LIST_HEAD(&table->chains);
 	INIT_LIST_HEAD(&table->sets);
+	table->flags = flags;
 
-	if (nla[NFTA_TABLE_FLAGS]) {
-		__be32 flags;
-
-		flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS]));
-		if (flags & ~NFT_TABLE_F_DORMANT) {
-			kfree(table);
-			return -EINVAL;
-		}
-
-		table->flags |= flags;
+	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+	err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE);
+	if (err < 0) {
+		kfree(table);
+		module_put(afi->owner);
+		return err;
 	}
-
-	list_add_tail(&table->list, &afi->tables);
-	nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family);
+	list_add_tail_rcu(&table->list, &afi->tables);
 	return 0;
 }
 
@@ -438,7 +535,8 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_af_info *afi;
 	struct nft_table *table;
 	struct net *net = sock_net(skb->sk);
-	int family = nfmsg->nfgen_family;
+	int family = nfmsg->nfgen_family, err;
+	struct nft_ctx ctx;
 
 	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
@@ -447,17 +545,29 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
-
-	if (table->use)
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
+	if (table->use > 0)
 		return -EBUSY;
 
-	list_del(&table->list);
-	nf_tables_table_notify(skb, nlh, table, NFT_MSG_DELTABLE, family);
-	kfree(table);
+	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+	err = nft_trans_table_add(&ctx, NFT_MSG_DELTABLE);
+	if (err < 0)
+		return err;
+
+	list_del_rcu(&table->list);
 	return 0;
 }
 
-int nft_register_chain_type(struct nf_chain_type *ctype)
+static void nf_tables_table_destroy(struct nft_ctx *ctx)
+{
+	BUG_ON(ctx->table->use > 0);
+
+	kfree(ctx->table);
+	module_put(ctx->afi->owner);
+}
+
+int nft_register_chain_type(const struct nf_chain_type *ctype)
 {
 	int err = 0;
 
@@ -466,10 +576,6 @@ int nft_register_chain_type(struct nf_chain_type *ctype)
 		err = -EBUSY;
 		goto out;
 	}
-
-	if (!try_module_get(ctype->me))
-		goto out;
-
 	chain_type[ctype->family][ctype->type] = ctype;
 out:
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
@@ -477,11 +583,10 @@ out:
 }
 EXPORT_SYMBOL_GPL(nft_register_chain_type);
 
-void nft_unregister_chain_type(struct nf_chain_type *ctype)
+void nft_unregister_chain_type(const struct nf_chain_type *ctype)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
 	chain_type[ctype->family][ctype->type] = NULL;
-	module_put(ctype->me);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 }
 EXPORT_SYMBOL_GPL(nft_unregister_chain_type);
@@ -526,7 +631,7 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
 				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
 	[NFTA_CHAIN_HOOK]	= { .type = NLA_NESTED },
 	[NFTA_CHAIN_POLICY]	= { .type = NLA_U32 },
-	[NFTA_CHAIN_TYPE]	= { .type = NLA_NUL_STRING },
+	[NFTA_CHAIN_TYPE]	= { .type = NLA_STRING },
 	[NFTA_CHAIN_COUNTERS]	= { .type = NLA_NESTED },
 };
 
@@ -539,13 +644,20 @@ static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats)
 {
 	struct nft_stats *cpu_stats, total;
 	struct nlattr *nest;
+	unsigned int seq;
+	u64 pkts, bytes;
 	int cpu;
 
 	memset(&total, 0, sizeof(total));
 	for_each_possible_cpu(cpu) {
 		cpu_stats = per_cpu_ptr(stats, cpu);
-		total.pkts += cpu_stats->pkts;
-		total.bytes += cpu_stats->bytes;
+		do {
+			seq = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
+			pkts = cpu_stats->pkts;
+			bytes = cpu_stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq));
+		total.pkts += pkts;
+		total.bytes += bytes;
 	}
 	nest = nla_nest_start(skb, NFTA_CHAIN_COUNTERS);
 	if (nest == NULL)
@@ -589,7 +701,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq,
 
 	if (chain->flags & NFT_BASE_CHAIN) {
 		const struct nft_base_chain *basechain = nft_base_chain(chain);
-		const struct nf_hook_ops *ops = &basechain->ops;
+		const struct nf_hook_ops *ops = &basechain->ops[0];
 		struct nlattr *nest;
 
 		nest = nla_nest_start(skb, NFTA_CHAIN_HOOK);
@@ -605,9 +717,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq,
 				 htonl(basechain->policy)))
 			goto nla_put_failure;
 
-		if (nla_put_string(skb, NFTA_CHAIN_TYPE,
-			chain_type[ops->pf][nft_base_chain(chain)->type]->name))
-				goto nla_put_failure;
+		if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name))
+			goto nla_put_failure;
 
 		if (nft_dump_stats(skb, nft_base_chain(chain)->stats))
 			goto nla_put_failure;
@@ -623,21 +734,13 @@ nla_put_failure:
 	return -1;
 }
 
-static int nf_tables_chain_notify(const struct sk_buff *oskb,
-				  const struct nlmsghdr *nlh,
-				  const struct nft_table *table,
-				  const struct nft_chain *chain,
-				  int event, int family)
+static int nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
 {
 	struct sk_buff *skb;
-	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
-	struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
-	u32 seq = nlh ? nlh->nlmsg_seq : 0;
-	bool report;
 	int err;
 
-	report = nlh ? nlmsg_report(nlh) : false;
-	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+	if (!ctx->report &&
+	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return 0;
 
 	err = -ENOBUFS;
@@ -645,18 +748,21 @@ static int nf_tables_chain_notify(const struct sk_buff *oskb,
 	if (skb == NULL)
 		goto err;
 
-	err = nf_tables_fill_chain_info(skb, portid, seq, event, 0, family,
-					table, chain);
+	err = nf_tables_fill_chain_info(skb, ctx->portid, ctx->seq, event, 0,
+					ctx->afi->family, ctx->table,
+					ctx->chain);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
-			     GFP_KERNEL);
+	err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+			     ctx->report, GFP_KERNEL);
 err:
-	if (err < 0)
-		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	if (err < 0) {
+		nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+				  err);
+	}
 	return err;
 }
 
@@ -671,12 +777,15 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
-	list_for_each_entry(afi, &net->nft.af_info, list) {
+	rcu_read_lock();
+	cb->seq = net->nft.base_seq;
+
+	list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
 		if (family != NFPROTO_UNSPEC && family != afi->family)
 			continue;
 
-		list_for_each_entry(table, &afi->tables, list) {
-			list_for_each_entry(chain, &table->chains, list) {
+		list_for_each_entry_rcu(table, &afi->tables, list) {
+			list_for_each_entry_rcu(chain, &table->chains, list) {
 				if (idx < s_idx)
 					goto cont;
 				if (idx > s_idx)
@@ -688,17 +797,19 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
 							      NLM_F_MULTI,
 							      afi->family, table, chain) < 0)
 					goto done;
+
+				nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 				idx++;
 			}
 		}
 	}
 done:
+	rcu_read_unlock();
 	cb->args[0] = idx;
 	return skb->len;
 }
 
-
 static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
@@ -726,10 +837,14 @@ static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
 
 	chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]);
 	if (IS_ERR(chain))
 		return PTR_ERR(chain);
+	if (chain->flags & NFT_CHAIN_INACTIVE)
+		return -ENOENT;
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb2)
@@ -748,29 +863,12 @@ err:
 	return err;
 }
 
-static int
-nf_tables_chain_policy(struct nft_base_chain *chain, const struct nlattr *attr)
-{
-	switch (ntohl(nla_get_be32(attr))) {
-	case NF_DROP:
-		chain->policy = NF_DROP;
-		break;
-	case NF_ACCEPT:
-		chain->policy = NF_ACCEPT;
-		break;
-	default:
-		return -EINVAL;
-	}
-	return 0;
-}
-
 static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = {
 	[NFTA_COUNTER_PACKETS]	= { .type = NLA_U64 },
 	[NFTA_COUNTER_BYTES]	= { .type = NLA_U64 },
 };
 
-static int
-nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr)
+static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr)
 {
 	struct nlattr *tb[NFTA_COUNTER_MAX+1];
 	struct nft_stats __percpu *newstats;
@@ -779,14 +877,14 @@ nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr)
 
 	err = nla_parse_nested(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy);
 	if (err < 0)
-		return err;
+		return ERR_PTR(err);
 
 	if (!tb[NFTA_COUNTER_BYTES] || !tb[NFTA_COUNTER_PACKETS])
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
-	newstats = alloc_percpu(struct nft_stats);
+	newstats = netdev_alloc_pcpu_stats(struct nft_stats);
 	if (newstats == NULL)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	/* Restore old counters on this cpu, no problem. Per-cpu statistics
 	 * are not exposed to userspace.
@@ -795,36 +893,71 @@ nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr)
 	stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
 	stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
 
+	return newstats;
+}
+
+static void nft_chain_stats_replace(struct nft_base_chain *chain,
+				    struct nft_stats __percpu *newstats)
+{
 	if (chain->stats) {
-		/* nfnl_lock is held, add some nfnl function for this, later */
 		struct nft_stats __percpu *oldstats =
-			rcu_dereference_protected(chain->stats, 1);
+				nft_dereference(chain->stats);
 
 		rcu_assign_pointer(chain->stats, newstats);
 		synchronize_rcu();
 		free_percpu(oldstats);
 	} else
 		rcu_assign_pointer(chain->stats, newstats);
+}
 
+static int nft_trans_chain_add(struct nft_ctx *ctx, int msg_type)
+{
+	struct nft_trans *trans;
+
+	trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_chain));
+	if (trans == NULL)
+		return -ENOMEM;
+
+	if (msg_type == NFT_MSG_NEWCHAIN)
+		ctx->chain->flags |= NFT_CHAIN_INACTIVE;
+
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
 }
 
+static void nf_tables_chain_destroy(struct nft_chain *chain)
+{
+	BUG_ON(chain->use > 0);
+
+	if (chain->flags & NFT_BASE_CHAIN) {
+		module_put(nft_base_chain(chain)->type->owner);
+		free_percpu(nft_base_chain(chain)->stats);
+		kfree(nft_base_chain(chain));
+	} else {
+		kfree(chain);
+	}
+}
+
 static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nlattr * uninitialized_var(name);
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_base_chain *basechain = NULL;
 	struct nlattr *ha[NFTA_HOOK_MAX + 1];
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
+	u8 policy = NF_ACCEPT;
 	u64 handle = 0;
+	unsigned int i;
+	struct nft_stats __percpu *stats;
 	int err;
 	bool create;
+	struct nft_ctx ctx;
 
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
@@ -836,9 +969,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
-	if (table->use == UINT_MAX)
-		return -EOVERFLOW;
-
 	chain = NULL;
 	name = nla[NFTA_CHAIN_NAME];
 
@@ -856,7 +986,28 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 		}
 	}
 
+	if (nla[NFTA_CHAIN_POLICY]) {
+		if ((chain != NULL &&
+		    !(chain->flags & NFT_BASE_CHAIN)) ||
+		    nla[NFTA_CHAIN_HOOK] == NULL)
+			return -EOPNOTSUPP;
+
+		policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY]));
+		switch (policy) {
+		case NF_DROP:
+		case NF_ACCEPT:
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
 	if (chain != NULL) {
+		struct nft_stats *stats = NULL;
+		struct nft_trans *trans;
+
+		if (chain->flags & NFT_CHAIN_INACTIVE)
+			return -ENOENT;
 		if (nlh->nlmsg_flags & NLM_F_EXCL)
 			return -EEXIST;
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
@@ -866,44 +1017,53 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 		    !IS_ERR(nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME])))
 			return -EEXIST;
 
-		if (nla[NFTA_CHAIN_POLICY]) {
+		if (nla[NFTA_CHAIN_COUNTERS]) {
 			if (!(chain->flags & NFT_BASE_CHAIN))
 				return -EOPNOTSUPP;
 
-			err = nf_tables_chain_policy(nft_base_chain(chain),
-						     nla[NFTA_CHAIN_POLICY]);
-			if (err < 0)
-				return err;
+			stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
+			if (IS_ERR(stats))
+				return PTR_ERR(stats);
 		}
 
-		if (nla[NFTA_CHAIN_COUNTERS]) {
-			if (!(chain->flags & NFT_BASE_CHAIN))
-				return -EOPNOTSUPP;
+		nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+		trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN,
+					sizeof(struct nft_trans_chain));
+		if (trans == NULL)
+			return -ENOMEM;
 
-			err = nf_tables_counters(nft_base_chain(chain),
-						 nla[NFTA_CHAIN_COUNTERS]);
-			if (err < 0)
-				return err;
-		}
+		nft_trans_chain_stats(trans) = stats;
+		nft_trans_chain_update(trans) = true;
 
-		if (nla[NFTA_CHAIN_HANDLE] && name)
-			nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
+		if (nla[NFTA_CHAIN_POLICY])
+			nft_trans_chain_policy(trans) = policy;
+		else
+			nft_trans_chain_policy(trans) = -1;
 
-		goto notify;
+		if (nla[NFTA_CHAIN_HANDLE] && name) {
+			nla_strlcpy(nft_trans_chain_name(trans), name,
+				    NFT_CHAIN_MAXNAMELEN);
+		}
+		list_add_tail(&trans->list, &net->nft.commit_list);
+		return 0;
 	}
 
+	if (table->use == UINT_MAX)
+		return -EOVERFLOW;
+
 	if (nla[NFTA_CHAIN_HOOK]) {
+		const struct nf_chain_type *type;
 		struct nf_hook_ops *ops;
 		nf_hookfn *hookfn;
-		u32 hooknum;
-		int type = NFT_CHAIN_T_DEFAULT;
+		u32 hooknum, priority;
 
+		type = chain_type[family][NFT_CHAIN_T_DEFAULT];
 		if (nla[NFTA_CHAIN_TYPE]) {
 			type = nf_tables_chain_type_lookup(afi,
 							   nla[NFTA_CHAIN_TYPE],
 							   create);
-			if (type < 0)
-				return -ENOENT;
+			if (IS_ERR(type))
+				return PTR_ERR(type);
 		}
 
 		err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK],
@@ -917,59 +1077,55 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 		hooknum = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
 		if (hooknum >= afi->nhooks)
 			return -EINVAL;
+		priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY]));
 
-		hookfn = chain_type[family][type]->fn[hooknum];
-		if (hookfn == NULL)
+		if (!(type->hook_mask & (1 << hooknum)))
 			return -EOPNOTSUPP;
+		if (!try_module_get(type->owner))
+			return -ENOENT;
+		hookfn = type->hooks[hooknum];
 
 		basechain = kzalloc(sizeof(*basechain), GFP_KERNEL);
 		if (basechain == NULL)
 			return -ENOMEM;
 
-		basechain->type = type;
-		chain = &basechain->chain;
-
-		ops = &basechain->ops;
-		ops->pf		= family;
-		ops->owner	= afi->owner;
-		ops->hooknum	= ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
-		ops->priority	= ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY]));
-		ops->priv	= chain;
-		ops->hook       = hookfn;
-		if (afi->hooks[ops->hooknum])
-			ops->hook = afi->hooks[ops->hooknum];
-
-		chain->flags |= NFT_BASE_CHAIN;
-
-		if (nla[NFTA_CHAIN_POLICY]) {
-			err = nf_tables_chain_policy(basechain,
-						     nla[NFTA_CHAIN_POLICY]);
-			if (err < 0) {
-				free_percpu(basechain->stats);
-				kfree(basechain);
-				return err;
-			}
-		} else
-			basechain->policy = NF_ACCEPT;
-
 		if (nla[NFTA_CHAIN_COUNTERS]) {
-			err = nf_tables_counters(basechain,
-						 nla[NFTA_CHAIN_COUNTERS]);
-			if (err < 0) {
-				free_percpu(basechain->stats);
+			stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
+			if (IS_ERR(stats)) {
+				module_put(type->owner);
 				kfree(basechain);
-				return err;
+				return PTR_ERR(stats);
 			}
+			basechain->stats = stats;
 		} else {
-			struct nft_stats __percpu *newstats;
+			stats = netdev_alloc_pcpu_stats(struct nft_stats);
+			if (IS_ERR(stats)) {
+				module_put(type->owner);
+				kfree(basechain);
+				return PTR_ERR(stats);
+			}
+			rcu_assign_pointer(basechain->stats, stats);
+		}
 
-			newstats = alloc_percpu(struct nft_stats);
-			if (newstats == NULL)
-				return -ENOMEM;
+		basechain->type = type;
+		chain = &basechain->chain;
 
-			rcu_assign_pointer(nft_base_chain(chain)->stats,
-					   newstats);
+		for (i = 0; i < afi->nops; i++) {
+			ops = &basechain->ops[i];
+			ops->pf		= family;
+			ops->owner	= afi->owner;
+			ops->hooknum	= hooknum;
+			ops->priority	= priority;
+			ops->priv	= chain;
+			ops->hook	= afi->hooks[ops->hooknum];
+			if (hookfn)
+				ops->hook = hookfn;
+			if (afi->hook_ops_init)
+				afi->hook_ops_init(ops, i);
 		}
+
+		chain->flags |= NFT_BASE_CHAIN;
+		basechain->policy = policy;
 	} else {
 		chain = kzalloc(sizeof(*chain), GFP_KERNEL);
 		if (chain == NULL)
@@ -984,32 +1140,28 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 
 	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
 	    chain->flags & NFT_BASE_CHAIN) {
-		err = nf_register_hook(&nft_base_chain(chain)->ops);
-		if (err < 0) {
-			free_percpu(basechain->stats);
-			kfree(basechain);
-			return err;
-		}
+		err = nf_register_hooks(nft_base_chain(chain)->ops, afi->nops);
+		if (err < 0)
+			goto err1;
 	}
-	list_add_tail(&chain->list, &table->chains);
-	table->use++;
-notify:
-	nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_NEWCHAIN,
-			       family);
-	return 0;
-}
-
-static void nf_tables_rcu_chain_destroy(struct rcu_head *head)
-{
-	struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head);
 
-	BUG_ON(chain->use > 0);
+	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+	err = nft_trans_chain_add(&ctx, NFT_MSG_NEWCHAIN);
+	if (err < 0)
+		goto err2;
 
-	if (chain->flags & NFT_BASE_CHAIN) {
-		free_percpu(nft_base_chain(chain)->stats);
-		kfree(nft_base_chain(chain));
-	} else
-		kfree(chain);
+	table->use++;
+	list_add_tail_rcu(&chain->list, &table->chains);
+	return 0;
+err2:
+	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
+	    chain->flags & NFT_BASE_CHAIN) {
+		nf_unregister_hooks(nft_base_chain(chain)->ops,
+				    afi->nops);
+	}
+err1:
+	nf_tables_chain_destroy(chain);
+	return err;
 }
 
 static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
@@ -1017,11 +1169,13 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
+	struct nft_ctx ctx;
+	int err;
 
 	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
@@ -1030,46 +1184,27 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
 
 	chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]);
 	if (IS_ERR(chain))
 		return PTR_ERR(chain);
-
-	if (!list_empty(&chain->rules))
+	if (chain->flags & NFT_CHAIN_INACTIVE)
+		return -ENOENT;
+	if (chain->use > 0)
 		return -EBUSY;
 
-	list_del(&chain->list);
-	table->use--;
-
-	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
-	    chain->flags & NFT_BASE_CHAIN)
-		nf_unregister_hook(&nft_base_chain(chain)->ops);
-
-	nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_DELCHAIN,
-			       family);
+	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+	err = nft_trans_chain_add(&ctx, NFT_MSG_DELCHAIN);
+	if (err < 0)
+		return err;
 
-	/* Make sure all rule references are gone before this is released */
-	call_rcu(&chain->rcu_head, nf_tables_rcu_chain_destroy);
+	table->use--;
+	list_del_rcu(&chain->list);
 	return 0;
 }
 
-static void nft_ctx_init(struct nft_ctx *ctx,
-			 const struct sk_buff *skb,
-			 const struct nlmsghdr *nlh,
-			 const struct nft_af_info *afi,
-			 const struct nft_table *table,
-			 const struct nft_chain *chain,
-			 const struct nlattr * const *nla)
-{
-	ctx->net   = sock_net(skb->sk);
-	ctx->skb   = skb;
-	ctx->nlh   = nlh;
-	ctx->afi   = afi;
-	ctx->table = table;
-	ctx->chain = chain;
-	ctx->nla   = nla;
-}
-
 /*
  * Expressions
  */
@@ -1084,7 +1219,10 @@ static void nft_ctx_init(struct nft_ctx *ctx,
 int nft_register_expr(struct nft_expr_type *type)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_add_tail(&type->list, &nf_tables_expressions);
+	if (type->family == NFPROTO_UNSPEC)
+		list_add_tail_rcu(&type->list, &nf_tables_expressions);
+	else
+		list_add_rcu(&type->list, &nf_tables_expressions);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 	return 0;
 }
@@ -1099,40 +1237,50 @@ EXPORT_SYMBOL_GPL(nft_register_expr);
 void nft_unregister_expr(struct nft_expr_type *type)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_del(&type->list);
+	list_del_rcu(&type->list);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 }
 EXPORT_SYMBOL_GPL(nft_unregister_expr);
 
-static const struct nft_expr_type *__nft_expr_type_get(struct nlattr *nla)
+static const struct nft_expr_type *__nft_expr_type_get(u8 family,
+						       struct nlattr *nla)
 {
 	const struct nft_expr_type *type;
 
 	list_for_each_entry(type, &nf_tables_expressions, list) {
-		if (!nla_strcmp(nla, type->name))
+		if (!nla_strcmp(nla, type->name) &&
+		    (!type->family || type->family == family))
 			return type;
 	}
 	return NULL;
 }
 
-static const struct nft_expr_type *nft_expr_type_get(struct nlattr *nla)
+static const struct nft_expr_type *nft_expr_type_get(u8 family,
+						     struct nlattr *nla)
 {
 	const struct nft_expr_type *type;
 
 	if (nla == NULL)
 		return ERR_PTR(-EINVAL);
 
-	type = __nft_expr_type_get(nla);
+	type = __nft_expr_type_get(family, nla);
 	if (type != NULL && try_module_get(type->owner))
 		return type;
 
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
 		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+		request_module("nft-expr-%u-%.*s", family,
+			       nla_len(nla), (char *)nla_data(nla));
+		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		if (__nft_expr_type_get(family, nla))
+			return ERR_PTR(-EAGAIN);
+
+		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 		request_module("nft-expr-%.*s",
 			       nla_len(nla), (char *)nla_data(nla));
 		nfnl_lock(NFNL_SUBSYS_NFTABLES);
-		if (__nft_expr_type_get(nla))
+		if (__nft_expr_type_get(family, nla))
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -1183,7 +1331,7 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
 	if (err < 0)
 		return err;
 
-	type = nft_expr_type_get(tb[NFTA_EXPR_NAME]);
+	type = nft_expr_type_get(ctx->afi->family, tb[NFTA_EXPR_NAME]);
 	if (IS_ERR(type))
 		return PTR_ERR(type);
 
@@ -1234,10 +1382,11 @@ err1:
 	return err;
 }
 
-static void nf_tables_expr_destroy(struct nft_expr *expr)
+static void nf_tables_expr_destroy(const struct nft_ctx *ctx,
+				   struct nft_expr *expr)
 {
 	if (expr->ops->destroy)
-		expr->ops->destroy(expr);
+		expr->ops->destroy(ctx, expr);
 	module_put(expr->ops->type->owner);
 }
 
@@ -1276,6 +1425,8 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
 	[NFTA_RULE_EXPRESSIONS]	= { .type = NLA_NESTED },
 	[NFTA_RULE_COMPAT]	= { .type = NLA_NESTED },
 	[NFTA_RULE_POSITION]	= { .type = NLA_U64 },
+	[NFTA_RULE_USERDATA]	= { .type = NLA_BINARY,
+				    .len = NFT_USERDATA_MAXLEN },
 };
 
 static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
@@ -1328,6 +1479,10 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
 	}
 	nla_nest_end(skb, list);
 
+	if (rule->ulen &&
+	    nla_put(skb, NFTA_RULE_USERDATA, rule->ulen, nft_userdata(rule)))
+		goto nla_put_failure;
+
 	return nlmsg_end(skb, nlh);
 
 nla_put_failure:
@@ -1335,22 +1490,15 @@ nla_put_failure:
 	return -1;
 }
 
-static int nf_tables_rule_notify(const struct sk_buff *oskb,
-				 const struct nlmsghdr *nlh,
-				 const struct nft_table *table,
-				 const struct nft_chain *chain,
+static int nf_tables_rule_notify(const struct nft_ctx *ctx,
 				 const struct nft_rule *rule,
-				 int event, u32 flags, int family)
+				 int event)
 {
 	struct sk_buff *skb;
-	u32 portid = NETLINK_CB(oskb).portid;
-	struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
-	u32 seq = nlh->nlmsg_seq;
-	bool report;
 	int err;
 
-	report = nlmsg_report(nlh);
-	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+	if (!ctx->report &&
+	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return 0;
 
 	err = -ENOBUFS;
@@ -1358,18 +1506,21 @@ static int nf_tables_rule_notify(const struct sk_buff *oskb,
 	if (skb == NULL)
 		goto err;
 
-	err = nf_tables_fill_rule_info(skb, portid, seq, event, flags,
-				       family, table, chain, rule);
+	err = nf_tables_fill_rule_info(skb, ctx->portid, ctx->seq, event, 0,
+				       ctx->afi->family, ctx->table,
+				       ctx->chain, rule);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
-			     GFP_KERNEL);
+	err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+			     ctx->report, GFP_KERNEL);
 err:
-	if (err < 0)
-		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	if (err < 0) {
+		nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+				  err);
+	}
 	return err;
 }
 
@@ -1419,16 +1570,17 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 	unsigned int idx = 0, s_idx = cb->args[0];
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
-	u8 genctr = ACCESS_ONCE(net->nft.genctr);
-	u8 gencursor = ACCESS_ONCE(net->nft.gencursor);
 
-	list_for_each_entry(afi, &net->nft.af_info, list) {
+	rcu_read_lock();
+	cb->seq = net->nft.base_seq;
+
+	list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
 		if (family != NFPROTO_UNSPEC && family != afi->family)
 			continue;
 
-		list_for_each_entry(table, &afi->tables, list) {
-			list_for_each_entry(chain, &table->chains, list) {
-				list_for_each_entry(rule, &chain->rules, list) {
+		list_for_each_entry_rcu(table, &afi->tables, list) {
+			list_for_each_entry_rcu(chain, &table->chains, list) {
+				list_for_each_entry_rcu(rule, &chain->rules, list) {
 					if (!nft_rule_is_active(net, rule))
 						goto cont;
 					if (idx < s_idx)
@@ -1442,6 +1594,8 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 								      NLM_F_MULTI | NLM_F_APPEND,
 								      afi->family, table, chain, rule) < 0)
 						goto done;
+
+					nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 					idx++;
 				}
@@ -1449,9 +1603,7 @@ cont:
 		}
 	}
 done:
-	/* Invalidate this dump, a transition to the new generation happened */
-	if (gencursor != net->nft.gencursor || genctr != net->nft.genctr)
-		return -EBUSY;
+	rcu_read_unlock();
 
 	cb->args[0] = idx;
 	return skb->len;
@@ -1485,10 +1637,14 @@ static int nf_tables_getrule(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
 
 	chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
 	if (IS_ERR(chain))
 		return PTR_ERR(chain);
+	if (chain->flags & NFT_CHAIN_INACTIVE)
+		return -ENOENT;
 
 	rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
 	if (IS_ERR(rule))
@@ -1511,9 +1667,9 @@ err:
 	return err;
 }
 
-static void nf_tables_rcu_rule_destroy(struct rcu_head *head)
+static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
+				   struct nft_rule *rule)
 {
-	struct nft_rule *rule = container_of(head, struct nft_rule, rcu_head);
 	struct nft_expr *expr;
 
 	/*
@@ -1522,55 +1678,46 @@ static void nf_tables_rcu_rule_destroy(struct rcu_head *head)
 	 */
 	expr = nft_expr_first(rule);
 	while (expr->ops && expr != nft_expr_last(rule)) {
-		nf_tables_expr_destroy(expr);
+		nf_tables_expr_destroy(ctx, expr);
 		expr = nft_expr_next(expr);
 	}
 	kfree(rule);
 }
 
-static void nf_tables_rule_destroy(struct nft_rule *rule)
+static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type,
+					    struct nft_rule *rule)
 {
-	call_rcu(&rule->rcu_head, nf_tables_rcu_rule_destroy);
-}
-
-#define NFT_RULE_MAXEXPRS	128
+	struct nft_trans *trans;
 
-static struct nft_expr_info *info;
+	trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_rule));
+	if (trans == NULL)
+		return NULL;
 
-static struct nft_rule_trans *
-nf_tables_trans_add(struct nft_rule *rule, const struct nft_ctx *ctx)
-{
-	struct nft_rule_trans *rupd;
+	nft_trans_rule(trans) = rule;
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 
-	rupd = kmalloc(sizeof(struct nft_rule_trans), GFP_KERNEL);
-	if (rupd == NULL)
-	       return NULL;
+	return trans;
+}
 
-	rupd->chain = ctx->chain;
-	rupd->table = ctx->table;
-	rupd->rule = rule;
-	rupd->family = ctx->afi->family;
-	rupd->nlh = ctx->nlh;
-	list_add_tail(&rupd->list, &ctx->net->nft.commit_list);
+#define NFT_RULE_MAXEXPRS	128
 
-	return rupd;
-}
+static struct nft_expr_info *info;
 
 static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 			     const struct nlmsghdr *nlh,
 			     const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct net *net = sock_net(skb->sk);
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_rule *rule, *old_rule = NULL;
-	struct nft_rule_trans *repl = NULL;
+	struct nft_trans *trans = NULL;
 	struct nft_expr *expr;
 	struct nft_ctx ctx;
 	struct nlattr *tmp;
-	unsigned int size, i, n;
+	unsigned int size, i, n, ulen = 0;
 	int err, rem;
 	bool create;
 	u64 handle, pos_handle;
@@ -1605,6 +1752,9 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 		if (!create || nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EINVAL;
 		handle = nf_tables_alloc_handle(table);
+
+		if (chain->use == UINT_MAX)
+			return -EOVERFLOW;
 	}
 
 	if (nla[NFTA_RULE_POSITION]) {
@@ -1636,8 +1786,11 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 		}
 	}
 
+	if (nla[NFTA_RULE_USERDATA])
+		ulen = nla_len(nla[NFTA_RULE_USERDATA]);
+
 	err = -ENOMEM;
-	rule = kzalloc(sizeof(*rule) + size, GFP_KERNEL);
+	rule = kzalloc(sizeof(*rule) + size + ulen, GFP_KERNEL);
 	if (rule == NULL)
 		goto err1;
 
@@ -1645,6 +1798,10 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 
 	rule->handle = handle;
 	rule->dlen   = size;
+	rule->ulen   = ulen;
+
+	if (ulen)
+		nla_memcpy(nft_userdata(rule), nla[NFTA_RULE_USERDATA], ulen);
 
 	expr = nft_expr_first(rule);
 	for (i = 0; i < n; i++) {
@@ -1657,13 +1814,15 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
 		if (nft_rule_is_active_next(net, old_rule)) {
-			repl = nf_tables_trans_add(old_rule, &ctx);
-			if (repl == NULL) {
+			trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
+						   old_rule);
+			if (trans == NULL) {
 				err = -ENOMEM;
 				goto err2;
 			}
 			nft_rule_disactivate_next(net, old_rule);
-			list_add_tail(&rule->list, &old_rule->list);
+			chain->use--;
+			list_add_tail_rcu(&rule->list, &old_rule->list);
 		} else {
 			err = -ENOENT;
 			goto err2;
@@ -1680,22 +1839,23 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 			list_add_rcu(&rule->list, &chain->rules);
 	}
 
-	if (nf_tables_trans_add(rule, &ctx) == NULL) {
+	if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
 		err = -ENOMEM;
 		goto err3;
 	}
+	chain->use++;
 	return 0;
 
 err3:
 	list_del_rcu(&rule->list);
-	if (repl) {
-		list_del_rcu(&repl->rule->list);
-		list_del(&repl->list);
-		nft_rule_clear(net, repl->rule);
-		kfree(repl);
+	if (trans) {
+		list_del_rcu(&nft_trans_rule(trans)->list);
+		nft_rule_clear(net, nft_trans_rule(trans));
+		nft_trans_destroy(trans);
+		chain->use++;
 	}
 err2:
-	nf_tables_rule_destroy(rule);
+	nf_tables_rule_destroy(&ctx, rule);
 err1:
 	for (i = 0; i < n; i++) {
 		if (info[i].ops != NULL)
@@ -1709,24 +1869,38 @@ nf_tables_delrule_one(struct nft_ctx *ctx, struct nft_rule *rule)
 {
 	/* You cannot delete the same rule twice */
 	if (nft_rule_is_active_next(ctx->net, rule)) {
-		if (nf_tables_trans_add(rule, ctx) == NULL)
+		if (nft_trans_rule_add(ctx, NFT_MSG_DELRULE, rule) == NULL)
 			return -ENOMEM;
 		nft_rule_disactivate_next(ctx->net, rule);
+		ctx->chain->use--;
 		return 0;
 	}
 	return -ENOENT;
 }
 
+static int nf_table_delrule_by_chain(struct nft_ctx *ctx)
+{
+	struct nft_rule *rule;
+	int err;
+
+	list_for_each_entry(rule, &ctx->chain->rules, list) {
+		err = nf_tables_delrule_one(ctx, rule);
+		if (err < 0)
+			return err;
+	}
+	return 0;
+}
+
 static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 			     const struct nlmsghdr *nlh,
 			     const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct net *net = sock_net(skb->sk);
-	const struct nft_table *table;
-	struct nft_chain *chain;
-	struct nft_rule *rule, *tmp;
+	struct nft_table *table;
+	struct nft_chain *chain = NULL;
+	struct nft_rule *rule;
 	int family = nfmsg->nfgen_family, err = 0;
 	struct nft_ctx ctx;
 
@@ -1737,23 +1911,32 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
 
-	chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
-	if (IS_ERR(chain))
-		return PTR_ERR(chain);
+	if (nla[NFTA_RULE_CHAIN]) {
+		chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
+		if (IS_ERR(chain))
+			return PTR_ERR(chain);
+	}
 
 	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
 
-	if (nla[NFTA_RULE_HANDLE]) {
-		rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
-		if (IS_ERR(rule))
-			return PTR_ERR(rule);
+	if (chain) {
+		if (nla[NFTA_RULE_HANDLE]) {
+			rule = nf_tables_rule_lookup(chain,
+						     nla[NFTA_RULE_HANDLE]);
+			if (IS_ERR(rule))
+				return PTR_ERR(rule);
 
-		err = nf_tables_delrule_one(&ctx, rule);
-	} else {
-		/* Remove all rules in this chain */
-		list_for_each_entry_safe(rule, tmp, &chain->rules, list) {
 			err = nf_tables_delrule_one(&ctx, rule);
+		} else {
+			err = nf_table_delrule_by_chain(&ctx);
+		}
+	} else {
+		list_for_each_entry(chain, &table->chains, list) {
+			ctx.chain = chain;
+			err = nf_table_delrule_by_chain(&ctx);
 			if (err < 0)
 				break;
 		}
@@ -1762,75 +1945,6 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 	return err;
 }
 
-static int nf_tables_commit(struct sk_buff *skb)
-{
-	struct net *net = sock_net(skb->sk);
-	struct nft_rule_trans *rupd, *tmp;
-
-	/* Bump generation counter, invalidate any dump in progress */
-	net->nft.genctr++;
-
-	/* A new generation has just started */
-	net->nft.gencursor = gencursor_next(net);
-
-	/* Make sure all packets have left the previous generation before
-	 * purging old rules.
-	 */
-	synchronize_rcu();
-
-	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
-		/* Delete this rule from the dirty list */
-		list_del(&rupd->list);
-
-		/* This rule was inactive in the past and just became active.
-		 * Clear the next bit of the genmask since its meaning has
-		 * changed, now it is the future.
-		 */
-		if (nft_rule_is_active(net, rupd->rule)) {
-			nft_rule_clear(net, rupd->rule);
-			nf_tables_rule_notify(skb, rupd->nlh, rupd->table,
-					      rupd->chain, rupd->rule,
-					      NFT_MSG_NEWRULE, 0,
-					      rupd->family);
-			kfree(rupd);
-			continue;
-		}
-
-		/* This rule is in the past, get rid of it */
-		list_del_rcu(&rupd->rule->list);
-		nf_tables_rule_notify(skb, rupd->nlh, rupd->table, rupd->chain,
-				      rupd->rule, NFT_MSG_DELRULE, 0,
-				      rupd->family);
-		nf_tables_rule_destroy(rupd->rule);
-		kfree(rupd);
-	}
-
-	return 0;
-}
-
-static int nf_tables_abort(struct sk_buff *skb)
-{
-	struct net *net = sock_net(skb->sk);
-	struct nft_rule_trans *rupd, *tmp;
-
-	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
-		/* Delete all rules from the dirty list */
-		list_del(&rupd->list);
-
-		if (!nft_rule_is_active_next(net, rupd->rule)) {
-			nft_rule_clear(net, rupd->rule);
-			kfree(rupd);
-			continue;
-		}
-
-		/* This rule is inactive, get rid of it */
-		list_del_rcu(&rupd->rule->list);
-		nf_tables_rule_destroy(rupd->rule);
-		kfree(rupd);
-	}
-	return 0;
-}
-
 /*
  * Sets
  */
@@ -1840,7 +1954,7 @@ static LIST_HEAD(nf_tables_set_ops);
 int nft_register_set(struct nft_set_ops *ops)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_add_tail(&ops->list, &nf_tables_set_ops);
+	list_add_tail_rcu(&ops->list, &nf_tables_set_ops);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 	return 0;
 }
@@ -1849,14 +1963,23 @@ EXPORT_SYMBOL_GPL(nft_register_set);
 void nft_unregister_set(struct nft_set_ops *ops)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_del(&ops->list);
+	list_del_rcu(&ops->list);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 }
 EXPORT_SYMBOL_GPL(nft_unregister_set);
 
-static const struct nft_set_ops *nft_select_set_ops(const struct nlattr * const nla[])
+/*
+ * Select a set implementation based on the data characteristics and the
+ * given policy. The total memory use might not be known if no size is
+ * given, in that case the amount of memory per element is used.
+ */
+static const struct nft_set_ops *
+nft_select_set_ops(const struct nlattr * const nla[],
+		   const struct nft_set_desc *desc,
+		   enum nft_set_policies policy)
 {
-	const struct nft_set_ops *ops;
+	const struct nft_set_ops *ops, *bops;
+	struct nft_set_estimate est, best;
 	u32 features;
 
 #ifdef CONFIG_MODULES
@@ -1874,26 +1997,64 @@ static const struct nft_set_ops *nft_select_set_ops(const struct nlattr * const
 		features &= NFT_SET_INTERVAL | NFT_SET_MAP;
 	}
 
-	// FIXME: implement selection properly
+	bops	   = NULL;
+	best.size  = ~0;
+	best.class = ~0;
+
 	list_for_each_entry(ops, &nf_tables_set_ops, list) {
 		if ((ops->features & features) != features)
 			continue;
+		if (!ops->estimate(desc, features, &est))
+			continue;
+
+		switch (policy) {
+		case NFT_SET_POL_PERFORMANCE:
+			if (est.class < best.class)
+				break;
+			if (est.class == best.class && est.size < best.size)
+				break;
+			continue;
+		case NFT_SET_POL_MEMORY:
+			if (est.size < best.size)
+				break;
+			if (est.size == best.size && est.class < best.class)
+				break;
+			continue;
+		default:
+			break;
+		}
+
 		if (!try_module_get(ops->owner))
 			continue;
-		return ops;
+		if (bops != NULL)
+			module_put(bops->owner);
+
+		bops = ops;
+		best = est;
 	}
 
+	if (bops != NULL)
+		return bops;
+
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
 static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
 	[NFTA_SET_TABLE]		= { .type = NLA_STRING },
-	[NFTA_SET_NAME]			= { .type = NLA_STRING },
+	[NFTA_SET_NAME]			= { .type = NLA_STRING,
+					    .len = IFNAMSIZ - 1 },
 	[NFTA_SET_FLAGS]		= { .type = NLA_U32 },
 	[NFTA_SET_KEY_TYPE]		= { .type = NLA_U32 },
 	[NFTA_SET_KEY_LEN]		= { .type = NLA_U32 },
 	[NFTA_SET_DATA_TYPE]		= { .type = NLA_U32 },
 	[NFTA_SET_DATA_LEN]		= { .type = NLA_U32 },
+	[NFTA_SET_POLICY]		= { .type = NLA_U32 },
+	[NFTA_SET_DESC]			= { .type = NLA_NESTED },
+	[NFTA_SET_ID]			= { .type = NLA_U32 },
+};
+
+static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = {
+	[NFTA_SET_DESC_SIZE]		= { .type = NLA_U32 },
 };
 
 static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
@@ -1903,17 +2064,24 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
 {
 	struct net *net = sock_net(skb->sk);
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nft_af_info *afi;
-	const struct nft_table *table = NULL;
+	struct nft_af_info *afi = NULL;
+	struct nft_table *table = NULL;
 
-	afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
-	if (IS_ERR(afi))
-		return PTR_ERR(afi);
+	if (nfmsg->nfgen_family != NFPROTO_UNSPEC) {
+		afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
+		if (IS_ERR(afi))
+			return PTR_ERR(afi);
+	}
 
 	if (nla[NFTA_SET_TABLE] != NULL) {
+		if (afi == NULL)
+			return -EAFNOSUPPORT;
+
 		table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]);
 		if (IS_ERR(table))
 			return PTR_ERR(table);
+		if (table->flags & NFT_TABLE_INACTIVE)
+			return -ENOENT;
 	}
 
 	nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla);
@@ -1935,13 +2103,27 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
 	return ERR_PTR(-ENOENT);
 }
 
+struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
+					  const struct nlattr *nla)
+{
+	struct nft_trans *trans;
+	u32 id = ntohl(nla_get_be32(nla));
+
+	list_for_each_entry(trans, &net->nft.commit_list, list) {
+		if (trans->msg_type == NFT_MSG_NEWSET &&
+		    id == nft_trans_set_id(trans))
+			return nft_trans_set(trans);
+	}
+	return ERR_PTR(-ENOENT);
+}
+
 static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 				    const char *name)
 {
 	const struct nft_set *i;
 	const char *p;
 	unsigned long *inuse;
-	unsigned int n = 0;
+	unsigned int n = 0, min = 0;
 
 	p = strnchr(name, IFNAMSIZ, '%');
 	if (p != NULL) {
@@ -1951,20 +2133,28 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 		inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL);
 		if (inuse == NULL)
 			return -ENOMEM;
-
+cont:
 		list_for_each_entry(i, &ctx->table->sets, list) {
-			if (!sscanf(i->name, name, &n))
+			int tmp;
+
+			if (!sscanf(i->name, name, &tmp))
 				continue;
-			if (n < 0 || n > BITS_PER_LONG * PAGE_SIZE)
+			if (tmp < min || tmp >= min + BITS_PER_BYTE * PAGE_SIZE)
 				continue;
-			set_bit(n, inuse);
+
+			set_bit(tmp - min, inuse);
 		}
 
-		n = find_first_zero_bit(inuse, BITS_PER_LONG * PAGE_SIZE);
+		n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE);
+		if (n >= BITS_PER_BYTE * PAGE_SIZE) {
+			min += BITS_PER_BYTE * PAGE_SIZE;
+			memset(inuse, 0, PAGE_SIZE);
+			goto cont;
+		}
 		free_page((unsigned long)inuse);
 	}
 
-	snprintf(set->name, sizeof(set->name), name, n);
+	snprintf(set->name, sizeof(set->name), name, min + n);
 	list_for_each_entry(i, &ctx->table->sets, list) {
 		if (!strcmp(set->name, i->name))
 			return -ENFILE;
@@ -1977,8 +2167,9 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 {
 	struct nfgenmsg *nfmsg;
 	struct nlmsghdr *nlh;
-	u32 portid = NETLINK_CB(ctx->skb).portid;
-	u32 seq = ctx->nlh->nlmsg_seq;
+	struct nlattr *desc;
+	u32 portid = ctx->portid;
+	u32 seq = ctx->seq;
 
 	event |= NFNL_SUBSYS_NFTABLES << 8;
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
@@ -2010,6 +2201,14 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			goto nla_put_failure;
 	}
 
+	desc = nla_nest_start(skb, NFTA_SET_DESC);
+	if (desc == NULL)
+		goto nla_put_failure;
+	if (set->size &&
+	    nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(set->size)))
+		goto nla_put_failure;
+	nla_nest_end(skb, desc);
+
 	return nlmsg_end(skb, nlh);
 
 nla_put_failure:
@@ -2019,19 +2218,18 @@ nla_put_failure:
 
 static int nf_tables_set_notify(const struct nft_ctx *ctx,
 				const struct nft_set *set,
-				int event)
+				int event, gfp_t gfp_flags)
 {
 	struct sk_buff *skb;
-	u32 portid = NETLINK_CB(ctx->skb).portid;
-	bool report;
+	u32 portid = ctx->portid;
 	int err;
 
-	report = nlmsg_report(ctx->nlh);
-	if (!report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
+	if (!ctx->report &&
+	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return 0;
 
 	err = -ENOBUFS;
-	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	skb = nlmsg_new(NLMSG_GOODSIZE, gfp_flags);
 	if (skb == NULL)
 		goto err;
 
@@ -2041,8 +2239,8 @@ static int nf_tables_set_notify(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, report,
-			     GFP_KERNEL);
+	err = nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES,
+			     ctx->report, gfp_flags);
 err:
 	if (err < 0)
 		nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, err);
@@ -2058,7 +2256,10 @@ static int nf_tables_dump_sets_table(struct nft_ctx *ctx, struct sk_buff *skb,
 	if (cb->args[1])
 		return skb->len;
 
-	list_for_each_entry(set, &ctx->table->sets, list) {
+	rcu_read_lock();
+	cb->seq = ctx->net->nft.base_seq;
+
+	list_for_each_entry_rcu(set, &ctx->table->sets, list) {
 		if (idx < s_idx)
 			goto cont;
 		if (nf_tables_fill_set(skb, ctx, set, NFT_MSG_NEWSET,
@@ -2066,30 +2267,39 @@ static int nf_tables_dump_sets_table(struct nft_ctx *ctx, struct sk_buff *skb,
 			cb->args[0] = idx;
 			goto done;
 		}
+		nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 		idx++;
 	}
 	cb->args[1] = 1;
 done:
+	rcu_read_unlock();
 	return skb->len;
 }
 
-static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb,
-				   struct netlink_callback *cb)
+static int nf_tables_dump_sets_family(struct nft_ctx *ctx, struct sk_buff *skb,
+				      struct netlink_callback *cb)
 {
 	const struct nft_set *set;
-	unsigned int idx = 0, s_idx = cb->args[0];
+	unsigned int idx, s_idx = cb->args[0];
 	struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2];
 
 	if (cb->args[1])
 		return skb->len;
 
-	list_for_each_entry(table, &ctx->afi->tables, list) {
-		if (cur_table && cur_table != table)
-			continue;
+	rcu_read_lock();
+	cb->seq = ctx->net->nft.base_seq;
+
+	list_for_each_entry_rcu(table, &ctx->afi->tables, list) {
+		if (cur_table) {
+			if (cur_table != table)
+				continue;
 
+			cur_table = NULL;
+		}
 		ctx->table = table;
-		list_for_each_entry(set, &ctx->table->sets, list) {
+		idx = 0;
+		list_for_each_entry_rcu(set, &ctx->table->sets, list) {
 			if (idx < s_idx)
 				goto cont;
 			if (nf_tables_fill_set(skb, ctx, set, NFT_MSG_NEWSET,
@@ -2098,12 +2308,74 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb,
 				cb->args[2] = (unsigned long) table;
 				goto done;
 			}
+			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 			idx++;
 		}
 	}
 	cb->args[1] = 1;
 done:
+	rcu_read_unlock();
+	return skb->len;
+}
+
+static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	const struct nft_set *set;
+	unsigned int idx, s_idx = cb->args[0];
+	struct nft_af_info *afi;
+	struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2];
+	struct net *net = sock_net(skb->sk);
+	int cur_family = cb->args[3];
+
+	if (cb->args[1])
+		return skb->len;
+
+	rcu_read_lock();
+	cb->seq = net->nft.base_seq;
+
+	list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
+		if (cur_family) {
+			if (afi->family != cur_family)
+				continue;
+
+			cur_family = 0;
+		}
+
+		list_for_each_entry_rcu(table, &afi->tables, list) {
+			if (cur_table) {
+				if (cur_table != table)
+					continue;
+
+				cur_table = NULL;
+			}
+
+			ctx->table = table;
+			ctx->afi = afi;
+			idx = 0;
+			list_for_each_entry_rcu(set, &ctx->table->sets, list) {
+				if (idx < s_idx)
+					goto cont;
+				if (nf_tables_fill_set(skb, ctx, set,
+						       NFT_MSG_NEWSET,
+						       NLM_F_MULTI) < 0) {
+					cb->args[0] = idx;
+					cb->args[2] = (unsigned long) table;
+					cb->args[3] = afi->family;
+					goto done;
+				}
+				nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+cont:
+				idx++;
+			}
+			if (s_idx)
+				s_idx = 0;
+		}
+	}
+	cb->args[1] = 1;
+done:
+	rcu_read_unlock();
 	return skb->len;
 }
 
@@ -2123,14 +2395,19 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
 	if (err < 0)
 		return err;
 
-	if (ctx.table == NULL)
-		ret = nf_tables_dump_sets_all(&ctx, skb, cb);
-	else
+	if (ctx.table == NULL) {
+		if (ctx.afi == NULL)
+			ret = nf_tables_dump_sets_all(&ctx, skb, cb);
+		else
+			ret = nf_tables_dump_sets_family(&ctx, skb, cb);
+	} else
 		ret = nf_tables_dump_sets_table(&ctx, skb, cb);
 
 	return ret;
 }
 
+#define NFT_SET_INACTIVE	(1 << 15)	/* Internal set flag */
+
 static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
 			    const struct nlmsghdr *nlh,
 			    const struct nlattr * const nla[])
@@ -2138,6 +2415,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
 	const struct nft_set *set;
 	struct nft_ctx ctx;
 	struct sk_buff *skb2;
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	int err;
 
 	/* Verify existance before starting dump */
@@ -2152,9 +2430,15 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
 		return netlink_dump_start(nlsk, skb, nlh, &c);
 	}
 
+	/* Only accept unspec with dump */
+	if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
+		return -EAFNOSUPPORT;
+
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
+	if (set->flags & NFT_SET_INACTIVE)
+		return -ENOENT;
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (skb2 == NULL)
@@ -2171,13 +2455,50 @@ err:
 	return err;
 }
 
+static int nf_tables_set_desc_parse(const struct nft_ctx *ctx,
+				    struct nft_set_desc *desc,
+				    const struct nlattr *nla)
+{
+	struct nlattr *da[NFTA_SET_DESC_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(da, NFTA_SET_DESC_MAX, nla, nft_set_desc_policy);
+	if (err < 0)
+		return err;
+
+	if (da[NFTA_SET_DESC_SIZE] != NULL)
+		desc->size = ntohl(nla_get_be32(da[NFTA_SET_DESC_SIZE]));
+
+	return 0;
+}
+
+static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type,
+			     struct nft_set *set)
+{
+	struct nft_trans *trans;
+
+	trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_set));
+	if (trans == NULL)
+		return -ENOMEM;
+
+	if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) {
+		nft_trans_set_id(trans) =
+			ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID]));
+		set->flags |= NFT_SET_INACTIVE;
+	}
+	nft_trans_set(trans) = set;
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+
+	return 0;
+}
+
 static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 			    const struct nlmsghdr *nlh,
 			    const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nft_set_ops *ops;
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct net *net = sock_net(skb->sk);
 	struct nft_table *table;
 	struct nft_set *set;
@@ -2185,14 +2506,18 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	char name[IFNAMSIZ];
 	unsigned int size;
 	bool create;
-	u32 ktype, klen, dlen, dtype, flags;
+	u32 ktype, dtype, flags, policy;
+	struct nft_set_desc desc;
 	int err;
 
 	if (nla[NFTA_SET_TABLE] == NULL ||
 	    nla[NFTA_SET_NAME] == NULL ||
-	    nla[NFTA_SET_KEY_LEN] == NULL)
+	    nla[NFTA_SET_KEY_LEN] == NULL ||
+	    nla[NFTA_SET_ID] == NULL)
 		return -EINVAL;
 
+	memset(&desc, 0, sizeof(desc));
+
 	ktype = NFT_DATA_VALUE;
 	if (nla[NFTA_SET_KEY_TYPE] != NULL) {
 		ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
@@ -2200,8 +2525,8 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 			return -EINVAL;
 	}
 
-	klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN]));
-	if (klen == 0 || klen > FIELD_SIZEOF(struct nft_data, data))
+	desc.klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN]));
+	if (desc.klen == 0 || desc.klen > FIELD_SIZEOF(struct nft_data, data))
 		return -EINVAL;
 
 	flags = 0;
@@ -2213,7 +2538,6 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	}
 
 	dtype = 0;
-	dlen  = 0;
 	if (nla[NFTA_SET_DATA_TYPE] != NULL) {
 		if (!(flags & NFT_SET_MAP))
 			return -EINVAL;
@@ -2226,15 +2550,25 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 		if (dtype != NFT_DATA_VERDICT) {
 			if (nla[NFTA_SET_DATA_LEN] == NULL)
 				return -EINVAL;
-			dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN]));
-			if (dlen == 0 ||
-			    dlen > FIELD_SIZEOF(struct nft_data, data))
+			desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN]));
+			if (desc.dlen == 0 ||
+			    desc.dlen > FIELD_SIZEOF(struct nft_data, data))
 				return -EINVAL;
 		} else
-			dlen = sizeof(struct nft_data);
+			desc.dlen = sizeof(struct nft_data);
 	} else if (flags & NFT_SET_MAP)
 		return -EINVAL;
 
+	policy = NFT_SET_POL_PERFORMANCE;
+	if (nla[NFTA_SET_POLICY] != NULL)
+		policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
+
+	if (nla[NFTA_SET_DESC] != NULL) {
+		err = nf_tables_set_desc_parse(&ctx, &desc, nla[NFTA_SET_DESC]);
+		if (err < 0)
+			return err;
+	}
+
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
 	afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, create);
@@ -2265,7 +2599,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	if (!(nlh->nlmsg_flags & NLM_F_CREATE))
 		return -ENOENT;
 
-	ops = nft_select_set_ops(nla);
+	ops = nft_select_set_ops(nla, &desc, policy);
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
 
@@ -2286,17 +2620,22 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	INIT_LIST_HEAD(&set->bindings);
 	set->ops   = ops;
 	set->ktype = ktype;
-	set->klen  = klen;
+	set->klen  = desc.klen;
 	set->dtype = dtype;
-	set->dlen  = dlen;
+	set->dlen  = desc.dlen;
 	set->flags = flags;
+	set->size  = desc.size;
 
-	err = ops->init(set, nla);
+	err = ops->init(set, &desc, nla);
 	if (err < 0)
 		goto err2;
 
-	list_add_tail(&set->list, &table->sets);
-	nf_tables_set_notify(&ctx, set, NFT_MSG_NEWSET);
+	err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
+	if (err < 0)
+		goto err2;
+
+	list_add_tail_rcu(&set->list, &table->sets);
+	table->use++;
 	return 0;
 
 err2:
@@ -2306,25 +2645,31 @@ err1:
 	return err;
 }
 
-static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
+static void nft_set_destroy(struct nft_set *set)
 {
-	list_del(&set->list);
-	if (!(set->flags & NFT_SET_ANONYMOUS))
-		nf_tables_set_notify(ctx, set, NFT_MSG_DELSET);
-
 	set->ops->destroy(set);
 	module_put(set->ops->owner);
 	kfree(set);
 }
 
+static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
+{
+	list_del_rcu(&set->list);
+	nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC);
+	nft_set_destroy(set);
+}
+
 static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
 			    const struct nlmsghdr *nlh,
 			    const struct nlattr * const nla[])
 {
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct nft_set *set;
 	struct nft_ctx ctx;
 	int err;
 
+	if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
+		return -EAFNOSUPPORT;
 	if (nla[NFTA_SET_TABLE] == NULL)
 		return -EINVAL;
 
@@ -2335,10 +2680,17 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
+	if (set->flags & NFT_SET_INACTIVE)
+		return -ENOENT;
 	if (!list_empty(&set->bindings))
 		return -EBUSY;
 
-	nf_tables_set_destroy(&ctx, set);
+	err = nft_trans_set_add(&ctx, NFT_MSG_DELSET, set);
+	if (err < 0)
+		return err;
+
+	list_del_rcu(&set->list);
+	ctx.table->use--;
 	return 0;
 }
 
@@ -2350,7 +2702,9 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx,
 	enum nft_registers dreg;
 
 	dreg = nft_type_to_reg(set->dtype);
-	return nft_validate_data_load(ctx, dreg, &elem->data, set->dtype);
+	return nft_validate_data_load(ctx, dreg, &elem->data,
+				      set->dtype == NFT_DATA_VERDICT ?
+				      NFT_DATA_VERDICT : NFT_DATA_VALUE);
 }
 
 int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
@@ -2387,16 +2741,17 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 	}
 bind:
 	binding->chain = ctx->chain;
-	list_add_tail(&binding->list, &set->bindings);
+	list_add_tail_rcu(&binding->list, &set->bindings);
 	return 0;
 }
 
 void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 			  struct nft_set_binding *binding)
 {
-	list_del(&binding->list);
+	list_del_rcu(&binding->list);
 
-	if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS)
+	if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS &&
+	    !(set->flags & NFT_SET_INACTIVE))
 		nf_tables_set_destroy(ctx, set);
 }
 
@@ -2414,16 +2769,18 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX +
 	[NFTA_SET_ELEM_LIST_TABLE]	= { .type = NLA_STRING },
 	[NFTA_SET_ELEM_LIST_SET]	= { .type = NLA_STRING },
 	[NFTA_SET_ELEM_LIST_ELEMENTS]	= { .type = NLA_NESTED },
+	[NFTA_SET_ELEM_LIST_SET_ID]	= { .type = NLA_U32 },
 };
 
 static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
 				      const struct sk_buff *skb,
 				      const struct nlmsghdr *nlh,
-				      const struct nlattr * const nla[])
+				      const struct nlattr * const nla[],
+				      bool trans)
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nft_af_info *afi;
-	const struct nft_table *table;
+	struct nft_af_info *afi;
+	struct nft_table *table;
 	struct net *net = sock_net(skb->sk);
 
 	afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
@@ -2433,6 +2790,8 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
 	table = nf_tables_table_lookup(afi, nla[NFTA_SET_ELEM_LIST_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (!trans && (table->flags & NFT_TABLE_INACTIVE))
+		return -ENOENT;
 
 	nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla);
 	return 0;
@@ -2501,19 +2860,21 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	u32 portid, seq;
 	int event, err;
 
-	nfmsg = nlmsg_data(cb->nlh);
-	err = nlmsg_parse(cb->nlh, sizeof(*nfmsg), nla, NFTA_SET_ELEM_LIST_MAX,
-			  nft_set_elem_list_policy);
+	err = nlmsg_parse(cb->nlh, sizeof(struct nfgenmsg), nla,
+			  NFTA_SET_ELEM_LIST_MAX, nft_set_elem_list_policy);
 	if (err < 0)
 		return err;
 
-	err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla);
+	err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla,
+					 false);
 	if (err < 0)
 		return err;
 
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
+	if (set->flags & NFT_SET_INACTIVE)
+		return -ENOENT;
 
 	event  = NFT_MSG_NEWSETELEM;
 	event |= NFNL_SUBSYS_NFTABLES << 8;
@@ -2526,7 +2887,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 		goto nla_put_failure;
 
 	nfmsg = nlmsg_data(nlh);
-	nfmsg->nfgen_family = NFPROTO_UNSPEC;
+	nfmsg->nfgen_family = ctx.afi->family;
 	nfmsg->version      = NFNETLINK_V0;
 	nfmsg->res_id       = 0;
 
@@ -2570,13 +2931,15 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_ctx ctx;
 	int err;
 
-	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla);
+	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false);
 	if (err < 0)
 		return err;
 
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
+	if (set->flags & NFT_SET_INACTIVE)
+		return -ENOENT;
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
@@ -2587,7 +2950,98 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb,
 	return -EOPNOTSUPP;
 }
 
-static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
+static int nf_tables_fill_setelem_info(struct sk_buff *skb,
+				       const struct nft_ctx *ctx, u32 seq,
+				       u32 portid, int event, u16 flags,
+				       const struct nft_set *set,
+				       const struct nft_set_elem *elem)
+{
+	struct nfgenmsg *nfmsg;
+	struct nlmsghdr *nlh;
+	struct nlattr *nest;
+	int err;
+
+	event |= NFNL_SUBSYS_NFTABLES << 8;
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
+			flags);
+	if (nlh == NULL)
+		goto nla_put_failure;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family	= ctx->afi->family;
+	nfmsg->version		= NFNETLINK_V0;
+	nfmsg->res_id		= 0;
+
+	if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name))
+		goto nla_put_failure;
+	if (nla_put_string(skb, NFTA_SET_NAME, set->name))
+		goto nla_put_failure;
+
+	nest = nla_nest_start(skb, NFTA_SET_ELEM_LIST_ELEMENTS);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	err = nf_tables_fill_setelem(skb, set, elem);
+	if (err < 0)
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_trim(skb, nlh);
+	return -1;
+}
+
+static int nf_tables_setelem_notify(const struct nft_ctx *ctx,
+				    const struct nft_set *set,
+				    const struct nft_set_elem *elem,
+				    int event, u16 flags)
+{
+	struct net *net = ctx->net;
+	u32 portid = ctx->portid;
+	struct sk_buff *skb;
+	int err;
+
+	if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+		return 0;
+
+	err = -ENOBUFS;
+	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (skb == NULL)
+		goto err;
+
+	err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags,
+					  set, elem);
+	if (err < 0) {
+		kfree_skb(skb);
+		goto err;
+	}
+
+	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, ctx->report,
+			     GFP_KERNEL);
+err:
+	if (err < 0)
+		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	return err;
+}
+
+static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx,
+					      int msg_type,
+					      struct nft_set *set)
+{
+	struct nft_trans *trans;
+
+	trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_elem));
+	if (trans == NULL)
+		return NULL;
+
+	nft_trans_elem_set(trans) = set;
+	return trans;
+}
+
+static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			    const struct nlattr *attr)
 {
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
@@ -2595,8 +3049,12 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
 	struct nft_set_elem elem;
 	struct nft_set_binding *binding;
 	enum nft_registers dreg;
+	struct nft_trans *trans;
 	int err;
 
+	if (set->size && set->nelems == set->size)
+		return -ENFILE;
+
 	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
 			       nft_set_elem_policy);
 	if (err < 0)
@@ -2616,6 +3074,9 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
 		if (nla[NFTA_SET_ELEM_DATA] == NULL &&
 		    !(elem.flags & NFT_SET_ELEM_INTERVAL_END))
 			return -EINVAL;
+		if (nla[NFTA_SET_ELEM_DATA] != NULL &&
+		    elem.flags & NFT_SET_ELEM_INTERVAL_END)
+			return -EINVAL;
 	} else {
 		if (nla[NFTA_SET_ELEM_DATA] != NULL)
 			return -EINVAL;
@@ -2646,7 +3107,7 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
 			struct nft_ctx bind_ctx = {
 				.afi	= ctx->afi,
 				.table	= ctx->table,
-				.chain	= binding->chain,
+				.chain	= (struct nft_chain *)binding->chain,
 			};
 
 			err = nft_validate_data_load(&bind_ctx, dreg,
@@ -2656,12 +3117,20 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
 		}
 	}
 
+	trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
+	if (trans == NULL)
+		goto err3;
+
 	err = set->ops->insert(set, &elem);
 	if (err < 0)
-		goto err3;
+		goto err4;
 
+	nft_trans_elem(trans) = elem;
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
 
+err4:
+	kfree(trans);
 err3:
 	if (nla[NFTA_SET_ELEM_DATA] != NULL)
 		nft_data_uninit(&elem.data, d2.type);
@@ -2675,35 +3144,46 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb,
 				const struct nlmsghdr *nlh,
 				const struct nlattr * const nla[])
 {
+	struct net *net = sock_net(skb->sk);
 	const struct nlattr *attr;
 	struct nft_set *set;
 	struct nft_ctx ctx;
-	int rem, err;
+	int rem, err = 0;
 
-	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla);
+	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, true);
 	if (err < 0)
 		return err;
 
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]);
-	if (IS_ERR(set))
-		return PTR_ERR(set);
+	if (IS_ERR(set)) {
+		if (nla[NFTA_SET_ELEM_LIST_SET_ID]) {
+			set = nf_tables_set_lookup_byid(net,
+					nla[NFTA_SET_ELEM_LIST_SET_ID]);
+		}
+		if (IS_ERR(set))
+			return PTR_ERR(set);
+	}
+
 	if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT)
 		return -EBUSY;
 
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
 		err = nft_add_set_elem(&ctx, set, attr);
 		if (err < 0)
-			return err;
+			break;
+
+		set->nelems++;
 	}
-	return 0;
+	return err;
 }
 
-static int nft_del_setelem(const struct nft_ctx *ctx, struct nft_set *set,
+static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 			   const struct nlattr *attr)
 {
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
 	struct nft_data_desc desc;
 	struct nft_set_elem elem;
+	struct nft_trans *trans;
 	int err;
 
 	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
@@ -2727,7 +3207,12 @@ static int nft_del_setelem(const struct nft_ctx *ctx, struct nft_set *set,
 	if (err < 0)
 		goto err2;
 
-	set->ops->remove(set, &elem);
+	trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set);
+	if (trans == NULL)
+		goto err2;
+
+	nft_trans_elem(trans) = elem;
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 
 	nft_data_uninit(&elem.key, NFT_DATA_VALUE);
 	if (set->flags & NFT_SET_MAP)
@@ -2746,9 +3231,9 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
 	const struct nlattr *attr;
 	struct nft_set *set;
 	struct nft_ctx ctx;
-	int rem, err;
+	int rem, err = 0;
 
-	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla);
+	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false);
 	if (err < 0)
 		return err;
 
@@ -2761,14 +3246,16 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
 		err = nft_del_setelem(&ctx, set, attr);
 		if (err < 0)
-			return err;
+			break;
+
+		set->nelems--;
 	}
-	return 0;
+	return err;
 }
 
 static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 	[NFT_MSG_NEWTABLE] = {
-		.call		= nf_tables_newtable,
+		.call_batch	= nf_tables_newtable,
 		.attr_count	= NFTA_TABLE_MAX,
 		.policy		= nft_table_policy,
 	},
@@ -2778,12 +3265,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_table_policy,
 	},
 	[NFT_MSG_DELTABLE] = {
-		.call		= nf_tables_deltable,
+		.call_batch	= nf_tables_deltable,
 		.attr_count	= NFTA_TABLE_MAX,
 		.policy		= nft_table_policy,
 	},
 	[NFT_MSG_NEWCHAIN] = {
-		.call		= nf_tables_newchain,
+		.call_batch	= nf_tables_newchain,
 		.attr_count	= NFTA_CHAIN_MAX,
 		.policy		= nft_chain_policy,
 	},
@@ -2793,7 +3280,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_chain_policy,
 	},
 	[NFT_MSG_DELCHAIN] = {
-		.call		= nf_tables_delchain,
+		.call_batch	= nf_tables_delchain,
 		.attr_count	= NFTA_CHAIN_MAX,
 		.policy		= nft_chain_policy,
 	},
@@ -2813,7 +3300,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_rule_policy,
 	},
 	[NFT_MSG_NEWSET] = {
-		.call		= nf_tables_newset,
+		.call_batch	= nf_tables_newset,
 		.attr_count	= NFTA_SET_MAX,
 		.policy		= nft_set_policy,
 	},
@@ -2823,12 +3310,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_set_policy,
 	},
 	[NFT_MSG_DELSET] = {
-		.call		= nf_tables_delset,
+		.call_batch	= nf_tables_delset,
 		.attr_count	= NFTA_SET_MAX,
 		.policy		= nft_set_policy,
 	},
 	[NFT_MSG_NEWSETELEM] = {
-		.call		= nf_tables_newsetelem,
+		.call_batch	= nf_tables_newsetelem,
 		.attr_count	= NFTA_SET_ELEM_LIST_MAX,
 		.policy		= nft_set_elem_list_policy,
 	},
@@ -2838,12 +3325,282 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_set_elem_list_policy,
 	},
 	[NFT_MSG_DELSETELEM] = {
-		.call		= nf_tables_delsetelem,
+		.call_batch	= nf_tables_delsetelem,
 		.attr_count	= NFTA_SET_ELEM_LIST_MAX,
 		.policy		= nft_set_elem_list_policy,
 	},
 };
 
+static void nft_chain_commit_update(struct nft_trans *trans)
+{
+	struct nft_base_chain *basechain;
+
+	if (nft_trans_chain_name(trans)[0])
+		strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans));
+
+	if (!(trans->ctx.chain->flags & NFT_BASE_CHAIN))
+		return;
+
+	basechain = nft_base_chain(trans->ctx.chain);
+	nft_chain_stats_replace(basechain, nft_trans_chain_stats(trans));
+
+	switch (nft_trans_chain_policy(trans)) {
+	case NF_DROP:
+	case NF_ACCEPT:
+		basechain->policy = nft_trans_chain_policy(trans);
+		break;
+	}
+}
+
+/* Schedule objects for release via rcu to make sure no packets are accesing
+ * removed rules.
+ */
+static void nf_tables_commit_release_rcu(struct rcu_head *rt)
+{
+	struct nft_trans *trans = container_of(rt, struct nft_trans, rcu_head);
+
+	switch (trans->msg_type) {
+	case NFT_MSG_DELTABLE:
+		nf_tables_table_destroy(&trans->ctx);
+		break;
+	case NFT_MSG_DELCHAIN:
+		nf_tables_chain_destroy(trans->ctx.chain);
+		break;
+	case NFT_MSG_DELRULE:
+		nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
+		break;
+	case NFT_MSG_DELSET:
+		nft_set_destroy(nft_trans_set(trans));
+		break;
+	}
+	kfree(trans);
+}
+
+static int nf_tables_commit(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nft_trans *trans, *next;
+	struct nft_set *set;
+
+	/* Bump generation counter, invalidate any dump in progress */
+	while (++net->nft.base_seq == 0);
+
+	/* A new generation has just started */
+	net->nft.gencursor = gencursor_next(net);
+
+	/* Make sure all packets have left the previous generation before
+	 * purging old rules.
+	 */
+	synchronize_rcu();
+
+	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+		switch (trans->msg_type) {
+		case NFT_MSG_NEWTABLE:
+			if (nft_trans_table_update(trans)) {
+				if (!nft_trans_table_enable(trans)) {
+					nf_tables_table_disable(trans->ctx.afi,
+								trans->ctx.table);
+					trans->ctx.table->flags |= NFT_TABLE_F_DORMANT;
+				}
+			} else {
+				trans->ctx.table->flags &= ~NFT_TABLE_INACTIVE;
+			}
+			nf_tables_table_notify(&trans->ctx, NFT_MSG_NEWTABLE);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELTABLE:
+			nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE);
+			break;
+		case NFT_MSG_NEWCHAIN:
+			if (nft_trans_chain_update(trans))
+				nft_chain_commit_update(trans);
+			else
+				trans->ctx.chain->flags &= ~NFT_CHAIN_INACTIVE;
+
+			nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELCHAIN:
+			nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN);
+			if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT) &&
+			    trans->ctx.chain->flags & NFT_BASE_CHAIN) {
+				nf_unregister_hooks(nft_base_chain(trans->ctx.chain)->ops,
+						    trans->ctx.afi->nops);
+			}
+			break;
+		case NFT_MSG_NEWRULE:
+			nft_rule_clear(trans->ctx.net, nft_trans_rule(trans));
+			nf_tables_rule_notify(&trans->ctx,
+					      nft_trans_rule(trans),
+					      NFT_MSG_NEWRULE);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELRULE:
+			list_del_rcu(&nft_trans_rule(trans)->list);
+			nf_tables_rule_notify(&trans->ctx,
+					      nft_trans_rule(trans),
+					      NFT_MSG_DELRULE);
+			break;
+		case NFT_MSG_NEWSET:
+			nft_trans_set(trans)->flags &= ~NFT_SET_INACTIVE;
+			/* This avoids hitting -EBUSY when deleting the table
+			 * from the transaction.
+			 */
+			if (nft_trans_set(trans)->flags & NFT_SET_ANONYMOUS &&
+			    !list_empty(&nft_trans_set(trans)->bindings))
+				trans->ctx.table->use--;
+
+			nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
+					     NFT_MSG_NEWSET, GFP_KERNEL);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELSET:
+			nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
+					     NFT_MSG_DELSET, GFP_KERNEL);
+			break;
+		case NFT_MSG_NEWSETELEM:
+			nf_tables_setelem_notify(&trans->ctx,
+						 nft_trans_elem_set(trans),
+						 &nft_trans_elem(trans),
+						 NFT_MSG_NEWSETELEM, 0);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELSETELEM:
+			nf_tables_setelem_notify(&trans->ctx,
+						 nft_trans_elem_set(trans),
+						 &nft_trans_elem(trans),
+						 NFT_MSG_DELSETELEM, 0);
+			set = nft_trans_elem_set(trans);
+			set->ops->get(set, &nft_trans_elem(trans));
+			set->ops->remove(set, &nft_trans_elem(trans));
+			nft_trans_destroy(trans);
+			break;
+		}
+	}
+
+	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+		list_del(&trans->list);
+		trans->ctx.nla = NULL;
+		call_rcu(&trans->rcu_head, nf_tables_commit_release_rcu);
+	}
+
+	return 0;
+}
+
+/* Schedule objects for release via rcu to make sure no packets are accesing
+ * aborted rules.
+ */
+static void nf_tables_abort_release_rcu(struct rcu_head *rt)
+{
+	struct nft_trans *trans = container_of(rt, struct nft_trans, rcu_head);
+
+	switch (trans->msg_type) {
+	case NFT_MSG_NEWTABLE:
+		nf_tables_table_destroy(&trans->ctx);
+		break;
+	case NFT_MSG_NEWCHAIN:
+		nf_tables_chain_destroy(trans->ctx.chain);
+		break;
+	case NFT_MSG_NEWRULE:
+		nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
+		break;
+	case NFT_MSG_NEWSET:
+		nft_set_destroy(nft_trans_set(trans));
+		break;
+	}
+	kfree(trans);
+}
+
+static int nf_tables_abort(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nft_trans *trans, *next;
+	struct nft_set *set;
+
+	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+		switch (trans->msg_type) {
+		case NFT_MSG_NEWTABLE:
+			if (nft_trans_table_update(trans)) {
+				if (nft_trans_table_enable(trans)) {
+					nf_tables_table_disable(trans->ctx.afi,
+								trans->ctx.table);
+					trans->ctx.table->flags |= NFT_TABLE_F_DORMANT;
+				}
+				nft_trans_destroy(trans);
+			} else {
+				list_del_rcu(&trans->ctx.table->list);
+			}
+			break;
+		case NFT_MSG_DELTABLE:
+			list_add_tail_rcu(&trans->ctx.table->list,
+					  &trans->ctx.afi->tables);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_NEWCHAIN:
+			if (nft_trans_chain_update(trans)) {
+				if (nft_trans_chain_stats(trans))
+					free_percpu(nft_trans_chain_stats(trans));
+
+				nft_trans_destroy(trans);
+			} else {
+				trans->ctx.table->use--;
+				list_del_rcu(&trans->ctx.chain->list);
+				if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT) &&
+				    trans->ctx.chain->flags & NFT_BASE_CHAIN) {
+					nf_unregister_hooks(nft_base_chain(trans->ctx.chain)->ops,
+							    trans->ctx.afi->nops);
+				}
+			}
+			break;
+		case NFT_MSG_DELCHAIN:
+			trans->ctx.table->use++;
+			list_add_tail_rcu(&trans->ctx.chain->list,
+					  &trans->ctx.table->chains);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_NEWRULE:
+			trans->ctx.chain->use--;
+			list_del_rcu(&nft_trans_rule(trans)->list);
+			break;
+		case NFT_MSG_DELRULE:
+			trans->ctx.chain->use++;
+			nft_rule_clear(trans->ctx.net, nft_trans_rule(trans));
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_NEWSET:
+			trans->ctx.table->use--;
+			list_del_rcu(&nft_trans_set(trans)->list);
+			break;
+		case NFT_MSG_DELSET:
+			trans->ctx.table->use++;
+			list_add_tail_rcu(&nft_trans_set(trans)->list,
+					  &trans->ctx.table->sets);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_NEWSETELEM:
+			nft_trans_elem_set(trans)->nelems--;
+			set = nft_trans_elem_set(trans);
+			set->ops->get(set, &nft_trans_elem(trans));
+			set->ops->remove(set, &nft_trans_elem(trans));
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELSETELEM:
+			nft_trans_elem_set(trans)->nelems++;
+			nft_trans_destroy(trans);
+			break;
+		}
+	}
+
+	list_for_each_entry_safe_reverse(trans, next,
+					 &net->nft.commit_list, list) {
+		list_del(&trans->list);
+		trans->ctx.nla = NULL;
+		call_rcu(&trans->rcu_head, nf_tables_abort_release_rcu);
+	}
+
+	return 0;
+}
+
 static const struct nfnetlink_subsystem nf_tables_subsys = {
 	.name		= "nf_tables",
 	.subsys_id	= NFNL_SUBSYS_NFTABLES,
@@ -2870,6 +3627,9 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx,
 					const struct nft_set_iter *iter,
 					const struct nft_set_elem *elem)
 {
+	if (elem->flags & NFT_SET_ELEM_INTERVAL_END)
+		return 0;
+
 	switch (elem->data.verdict) {
 	case NFT_JUMP:
 	case NFT_GOTO:
@@ -3044,9 +3804,16 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 	data->verdict = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE]));
 
 	switch (data->verdict) {
-	case NF_ACCEPT:
-	case NF_DROP:
-	case NF_QUEUE:
+	default:
+		switch (data->verdict & NF_VERDICT_MASK) {
+		case NF_ACCEPT:
+		case NF_DROP:
+		case NF_QUEUE:
+			break;
+		default:
+			return -EINVAL;
+		}
+		/* fall through */
 	case NFT_CONTINUE:
 	case NFT_BREAK:
 	case NFT_RETURN:
@@ -3067,8 +3834,6 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 		data->chain = chain;
 		desc->len = sizeof(data);
 		break;
-	default:
-		return -EINVAL;
 	}
 
 	desc->type = NFT_DATA_VERDICT;
@@ -3223,6 +3988,7 @@ static int nf_tables_init_net(struct net *net)
 {
 	INIT_LIST_HEAD(&net->nft.af_info);
 	INIT_LIST_HEAD(&net->nft.commit_list);
+	net->nft.base_seq = 1;
 	return 0;
 }
 
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index cb9e685caae..3b90eb2b2c5 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -25,9 +25,8 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr,
 			      struct nft_data data[NFT_REG_MAX + 1])
 {
 	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
-	u32 mask;
+	u32 mask = nft_cmp_fast_mask(priv->len);
 
-	mask = ~0U >> (sizeof(priv->data) * BITS_PER_BYTE - priv->len);
 	if ((data[priv->sreg].data[0] & mask) == priv->data)
 		return;
 	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
@@ -67,20 +66,6 @@ struct nft_jumpstack {
 	int			rulenum;
 };
 
-static inline void
-nft_chain_stats(const struct nft_chain *this, const struct nft_pktinfo *pkt,
-		struct nft_jumpstack *jumpstack, unsigned int stackptr)
-{
-	struct nft_stats __percpu *stats;
-	const struct nft_chain *chain = stackptr ? jumpstack[0].chain : this;
-
-	rcu_read_lock_bh();
-	stats = rcu_dereference(nft_base_chain(chain)->stats);
-	__this_cpu_inc(stats->pkts);
-	__this_cpu_add(stats->bytes, pkt->skb->len);
-	rcu_read_unlock_bh();
-}
-
 enum nft_trace {
 	NFT_TRACE_RULE,
 	NFT_TRACE_RETURN,
@@ -103,28 +88,29 @@ static struct nf_loginfo trace_loginfo = {
 	},
 };
 
-static inline void nft_trace_packet(const struct nft_pktinfo *pkt,
-				    const struct nft_chain *chain,
-				    int rulenum, enum nft_trace type)
+static void nft_trace_packet(const struct nft_pktinfo *pkt,
+			     const struct nft_chain *chain,
+			     int rulenum, enum nft_trace type)
 {
 	struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
 
-	nf_log_packet(net, pkt->xt.family, pkt->hooknum, pkt->skb, pkt->in,
+	nf_log_packet(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in,
 		      pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ",
 		      chain->table->name, chain->name, comments[type],
 		      rulenum);
 }
 
 unsigned int
-nft_do_chain_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
+nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 {
-	const struct nft_chain *chain = ops->priv;
+	const struct nft_chain *chain = ops->priv, *basechain = chain;
 	const struct nft_rule *rule;
 	const struct nft_expr *expr, *last;
 	struct nft_data data[NFT_REG_MAX + 1];
 	unsigned int stackptr = 0;
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
-	int rulenum = 0;
+	struct nft_stats *stats;
+	int rulenum;
 	/*
 	 * Cache cursor to avoid problems in case that the cursor is updated
 	 * while traversing the ruleset.
@@ -132,6 +118,7 @@ nft_do_chain_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 	unsigned int gencursor = ACCESS_ONCE(chain->net->nft.gencursor);
 
 do_chain:
+	rulenum = 0;
 	rule = list_entry(&chain->rules, struct nft_rule, list);
 next_rule:
 	data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
@@ -157,14 +144,16 @@ next_rule:
 		switch (data[NFT_REG_VERDICT].verdict) {
 		case NFT_BREAK:
 			data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
-			/* fall through */
+			continue;
 		case NFT_CONTINUE:
+			if (unlikely(pkt->skb->nf_trace))
+				nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
 			continue;
 		}
 		break;
 	}
 
-	switch (data[NFT_REG_VERDICT].verdict) {
+	switch (data[NFT_REG_VERDICT].verdict & NF_VERDICT_MASK) {
 	case NF_ACCEPT:
 	case NF_DROP:
 	case NF_QUEUE:
@@ -172,6 +161,9 @@ next_rule:
 			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
 
 		return data[NFT_REG_VERDICT].verdict;
+	}
+
+	switch (data[NFT_REG_VERDICT].verdict) {
 	case NFT_JUMP:
 		if (unlikely(pkt->skb->nf_trace))
 			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
@@ -181,39 +173,48 @@ next_rule:
 		jumpstack[stackptr].rule  = rule;
 		jumpstack[stackptr].rulenum = rulenum;
 		stackptr++;
-		/* fall through */
+		chain = data[NFT_REG_VERDICT].chain;
+		goto do_chain;
 	case NFT_GOTO:
+		if (unlikely(pkt->skb->nf_trace))
+			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+
 		chain = data[NFT_REG_VERDICT].chain;
 		goto do_chain;
 	case NFT_RETURN:
 		if (unlikely(pkt->skb->nf_trace))
 			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN);
-
-		/* fall through */
+		break;
 	case NFT_CONTINUE:
+		if (unlikely(pkt->skb->nf_trace && !(chain->flags & NFT_BASE_CHAIN)))
+			nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN);
 		break;
 	default:
 		WARN_ON(1);
 	}
 
 	if (stackptr > 0) {
-		if (unlikely(pkt->skb->nf_trace))
-			nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN);
-
 		stackptr--;
 		chain = jumpstack[stackptr].chain;
 		rule  = jumpstack[stackptr].rule;
 		rulenum = jumpstack[stackptr].rulenum;
 		goto next_rule;
 	}
-	nft_chain_stats(chain, pkt, jumpstack, stackptr);
 
 	if (unlikely(pkt->skb->nf_trace))
-		nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_POLICY);
+		nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY);
+
+	rcu_read_lock_bh();
+	stats = this_cpu_ptr(rcu_dereference(nft_base_chain(basechain)->stats));
+	u64_stats_update_begin(&stats->syncp);
+	stats->pkts++;
+	stats->bytes += pkt->skb->len;
+	u64_stats_update_end(&stats->syncp);
+	rcu_read_unlock_bh();
 
-	return nft_base_chain(chain)->policy;
+	return nft_base_chain(basechain)->policy;
 }
-EXPORT_SYMBOL_GPL(nft_do_chain_pktinfo);
+EXPORT_SYMBOL_GPL(nft_do_chain);
 
 int __init nf_tables_core_module_init(void)
 {
diff --git a/net/netfilter/nf_tables_inet.c b/net/netfilter/nf_tables_inet.c
new file mode 100644
index 00000000000..9dd2d216cfc
--- /dev/null
+++ b/net/netfilter/nf_tables_inet.c
@@ -0,0 +1,104 @@
+/*
+ * Copyright (c) 2012-2014 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv4.h>
+#include <net/netfilter/nf_tables_ipv6.h>
+#include <net/ip.h>
+
+static void nft_inet_hook_ops_init(struct nf_hook_ops *ops, unsigned int n)
+{
+	struct nft_af_info *afi;
+
+	if (n == 1)
+		afi = &nft_af_ipv4;
+	else
+		afi = &nft_af_ipv6;
+
+	ops->pf = afi->family;
+	if (afi->hooks[ops->hooknum])
+		ops->hook = afi->hooks[ops->hooknum];
+}
+
+static struct nft_af_info nft_af_inet __read_mostly = {
+	.family		= NFPROTO_INET,
+	.nhooks		= NF_INET_NUMHOOKS,
+	.owner		= THIS_MODULE,
+	.nops		= 2,
+	.hook_ops_init	= nft_inet_hook_ops_init,
+};
+
+static int __net_init nf_tables_inet_init_net(struct net *net)
+{
+	net->nft.inet = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL);
+	if (net->nft.inet == NULL)
+		return -ENOMEM;
+	memcpy(net->nft.inet, &nft_af_inet, sizeof(nft_af_inet));
+
+	if (nft_register_afinfo(net, net->nft.inet) < 0)
+		goto err;
+
+	return 0;
+
+err:
+	kfree(net->nft.inet);
+	return -ENOMEM;
+}
+
+static void __net_exit nf_tables_inet_exit_net(struct net *net)
+{
+	nft_unregister_afinfo(net->nft.inet);
+	kfree(net->nft.inet);
+}
+
+static struct pernet_operations nf_tables_inet_net_ops = {
+	.init	= nf_tables_inet_init_net,
+	.exit	= nf_tables_inet_exit_net,
+};
+
+static const struct nf_chain_type filter_inet = {
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_INET,
+	.owner		= THIS_MODULE,
+	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_FORWARD) |
+			  (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING),
+};
+
+static int __init nf_tables_inet_init(void)
+{
+	int ret;
+
+	nft_register_chain_type(&filter_inet);
+	ret = register_pernet_subsys(&nf_tables_inet_net_ops);
+	if (ret < 0)
+		nft_unregister_chain_type(&filter_inet);
+
+	return ret;
+}
+
+static void __exit nf_tables_inet_exit(void)
+{
+	unregister_pernet_subsys(&nf_tables_inet_net_ops);
+	nft_unregister_chain_type(&filter_inet);
+}
+
+module_init(nf_tables_inet_init);
+module_exit(nf_tables_inet_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_FAMILY(1);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 046aa13b4fe..c138b8fbe28 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -61,6 +61,14 @@ void nfnl_unlock(__u8 subsys_id)
 }
 EXPORT_SYMBOL_GPL(nfnl_unlock);
 
+#ifdef CONFIG_PROVE_LOCKING
+int lockdep_nfnl_is_held(u8 subsys_id)
+{
+	return lockdep_is_held(&table[subsys_id].mutex);
+}
+EXPORT_SYMBOL_GPL(lockdep_nfnl_is_held);
+#endif
+
 int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n)
 {
 	nfnl_lock(n->subsys_id);
@@ -248,15 +256,15 @@ replay:
 #endif
 		{
 			nfnl_unlock(subsys_id);
-			kfree_skb(nskb);
-			return netlink_ack(skb, nlh, -EOPNOTSUPP);
+			netlink_ack(skb, nlh, -EOPNOTSUPP);
+			return kfree_skb(nskb);
 		}
 	}
 
 	if (!ss->commit || !ss->abort) {
 		nfnl_unlock(subsys_id);
-		kfree_skb(nskb);
-		return netlink_ack(skb, nlh, -EOPNOTSUPP);
+		netlink_ack(skb, nlh, -EOPNOTSUPP);
+		return kfree_skb(skb);
 	}
 
 	while (skb->len >= nlmsg_total_size(0)) {
@@ -360,14 +368,13 @@ done:
 static void nfnetlink_rcv(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
-	struct net *net = sock_net(skb->sk);
 	int msglen;
 
 	if (nlh->nlmsg_len < NLMSG_HDRLEN ||
 	    skb->len < nlh->nlmsg_len)
 		return;
 
-	if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+	if (!netlink_net_capable(skb, CAP_NET_ADMIN)) {
 		netlink_ack(skb, nlh, -EPERM);
 		return;
 	}
@@ -392,19 +399,17 @@ static void nfnetlink_rcv(struct sk_buff *skb)
 }
 
 #ifdef CONFIG_MODULES
-static void nfnetlink_bind(int group)
+static int nfnetlink_bind(int group)
 {
 	const struct nfnetlink_subsystem *ss;
 	int type = nfnl_group2type[group];
 
 	rcu_read_lock();
 	ss = nfnetlink_get_subsys(type);
-	if (!ss) {
-		rcu_read_unlock();
-		request_module("nfnetlink-subsys-%d", type);
-		return;
-	}
 	rcu_read_unlock();
+	if (!ss)
+		request_module("nfnetlink-subsys-%d", type);
+	return 0;
 }
 #endif
 
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index c7b6d466a66..2baa125c2e8 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -32,18 +32,24 @@ static LIST_HEAD(nfnl_acct_list);
 struct nf_acct {
 	atomic64_t		pkts;
 	atomic64_t		bytes;
+	unsigned long		flags;
 	struct list_head	head;
 	atomic_t		refcnt;
 	char			name[NFACCT_NAME_MAX];
 	struct rcu_head		rcu_head;
+	char			data[0];
 };
 
+#define NFACCT_F_QUOTA (NFACCT_F_QUOTA_PKTS | NFACCT_F_QUOTA_BYTES)
+
 static int
 nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb,
 	     const struct nlmsghdr *nlh, const struct nlattr * const tb[])
 {
 	struct nf_acct *nfacct, *matching = NULL;
 	char *acct_name;
+	unsigned int size = 0;
+	u32 flags = 0;
 
 	if (!tb[NFACCT_NAME])
 		return -EINVAL;
@@ -68,15 +74,38 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb,
 			/* reset counters if you request a replacement. */
 			atomic64_set(&matching->pkts, 0);
 			atomic64_set(&matching->bytes, 0);
+			smp_mb__before_atomic();
+			/* reset overquota flag if quota is enabled. */
+			if ((matching->flags & NFACCT_F_QUOTA))
+				clear_bit(NFACCT_F_OVERQUOTA, &matching->flags);
 			return 0;
 		}
 		return -EBUSY;
 	}
 
-	nfacct = kzalloc(sizeof(struct nf_acct), GFP_KERNEL);
+	if (tb[NFACCT_FLAGS]) {
+		flags = ntohl(nla_get_be32(tb[NFACCT_FLAGS]));
+		if (flags & ~NFACCT_F_QUOTA)
+			return -EOPNOTSUPP;
+		if ((flags & NFACCT_F_QUOTA) == NFACCT_F_QUOTA)
+			return -EINVAL;
+		if (flags & NFACCT_F_OVERQUOTA)
+			return -EINVAL;
+
+		size += sizeof(u64);
+	}
+
+	nfacct = kzalloc(sizeof(struct nf_acct) + size, GFP_KERNEL);
 	if (nfacct == NULL)
 		return -ENOMEM;
 
+	if (flags & NFACCT_F_QUOTA) {
+		u64 *quota = (u64 *)nfacct->data;
+
+		*quota = be64_to_cpu(nla_get_be64(tb[NFACCT_QUOTA]));
+		nfacct->flags = flags;
+	}
+
 	strncpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX);
 
 	if (tb[NFACCT_BYTES]) {
@@ -117,6 +146,9 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	if (type == NFNL_MSG_ACCT_GET_CTRZERO) {
 		pkts = atomic64_xchg(&acct->pkts, 0);
 		bytes = atomic64_xchg(&acct->bytes, 0);
+		smp_mb__before_atomic();
+		if (acct->flags & NFACCT_F_QUOTA)
+			clear_bit(NFACCT_F_OVERQUOTA, &acct->flags);
 	} else {
 		pkts = atomic64_read(&acct->pkts);
 		bytes = atomic64_read(&acct->bytes);
@@ -125,7 +157,13 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	    nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes)) ||
 	    nla_put_be32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt))))
 		goto nla_put_failure;
+	if (acct->flags & NFACCT_F_QUOTA) {
+		u64 *quota = (u64 *)acct->data;
 
+		if (nla_put_be32(skb, NFACCT_FLAGS, htonl(acct->flags)) ||
+		    nla_put_be64(skb, NFACCT_QUOTA, cpu_to_be64(*quota)))
+			goto nla_put_failure;
+	}
 	nlmsg_end(skb, nlh);
 	return skb->len;
 
@@ -270,6 +308,8 @@ static const struct nla_policy nfnl_acct_policy[NFACCT_MAX+1] = {
 	[NFACCT_NAME] = { .type = NLA_NUL_STRING, .len = NFACCT_NAME_MAX-1 },
 	[NFACCT_BYTES] = { .type = NLA_U64 },
 	[NFACCT_PKTS] = { .type = NLA_U64 },
+	[NFACCT_FLAGS] = { .type = NLA_U32 },
+	[NFACCT_QUOTA] = { .type = NLA_U64 },
 };
 
 static const struct nfnl_callback nfnl_acct_cb[NFNL_MSG_ACCT_MAX] = {
@@ -336,6 +376,50 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct)
 }
 EXPORT_SYMBOL_GPL(nfnl_acct_update);
 
+static void nfnl_overquota_report(struct nf_acct *nfacct)
+{
+	int ret;
+	struct sk_buff *skb;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (skb == NULL)
+		return;
+
+	ret = nfnl_acct_fill_info(skb, 0, 0, NFNL_MSG_ACCT_OVERQUOTA, 0,
+				  nfacct);
+	if (ret <= 0) {
+		kfree_skb(skb);
+		return;
+	}
+	netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA,
+			  GFP_ATOMIC);
+}
+
+int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct)
+{
+	u64 now;
+	u64 *quota;
+	int ret = NFACCT_UNDERQUOTA;
+
+	/* no place here if we don't have a quota */
+	if (!(nfacct->flags & NFACCT_F_QUOTA))
+		return NFACCT_NO_QUOTA;
+
+	quota = (u64 *)nfacct->data;
+	now = (nfacct->flags & NFACCT_F_QUOTA_PKTS) ?
+	       atomic64_read(&nfacct->pkts) : atomic64_read(&nfacct->bytes);
+
+	ret = now > *quota;
+
+	if (now >= *quota &&
+	    !test_and_set_bit(NFACCT_F_OVERQUOTA, &nfacct->flags)) {
+		nfnl_overquota_report(nfacct);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nfnl_acct_overquota);
+
 static int __init nfnl_acct_init(void)
 {
 	int ret;
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 3c4b69e5fe1..d292c8d286e 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -28,8 +28,6 @@
 #include <linux/proc_fs.h>
 #include <linux/security.h>
 #include <linux/list.h>
-#include <linux/jhash.h>
-#include <linux/random.h>
 #include <linux/slab.h>
 #include <net/sock.h>
 #include <net/netfilter/nf_log.h>
@@ -75,7 +73,6 @@ struct nfulnl_instance {
 };
 
 #define INSTANCE_BUCKETS	16
-static unsigned int hash_init;
 
 static int nfnl_log_net_id __read_mostly;
 
@@ -1053,6 +1050,7 @@ static void __net_exit nfnl_log_net_exit(struct net *net)
 #ifdef CONFIG_PROC_FS
 	remove_proc_entry("nfnetlink_log", net->nf.proc_netfilter);
 #endif
+	nf_log_unset(net, &nfulnl_logger);
 }
 
 static struct pernet_operations nfnl_log_net_ops = {
@@ -1066,11 +1064,6 @@ static int __init nfnetlink_log_init(void)
 {
 	int status = -ENOMEM;
 
-	/* it's not really all that important to have a random value, so
-	 * we can do this from the init function, even if there hasn't
-	 * been that much entropy yet */
-	get_random_bytes(&hash_init, sizeof(hash_init));
-
 	netlink_register_notifier(&nfulnl_rtnl_notifier);
 	status = nfnetlink_subsys_register(&nfulnl_subsys);
 	if (status < 0) {
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 21258cf7009..108120f216b 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -29,6 +29,7 @@
 #include <linux/netfilter/nfnetlink_queue.h>
 #include <linux/list.h>
 #include <net/sock.h>
+#include <net/tcp_states.h>
 #include <net/netfilter/nf_queue.h>
 #include <net/netns/generic.h>
 #include <net/netfilter/nfnetlink_queue.h>
@@ -235,51 +236,6 @@ nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data)
 	spin_unlock_bh(&queue->lock);
 }
 
-static void
-nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
-{
-	int i, j = 0;
-	int plen = 0; /* length of skb->head fragment */
-	struct page *page;
-	unsigned int offset;
-
-	/* dont bother with small payloads */
-	if (len <= skb_tailroom(to)) {
-		skb_copy_bits(from, 0, skb_put(to, len), len);
-		return;
-	}
-
-	if (hlen) {
-		skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
-		len -= hlen;
-	} else {
-		plen = min_t(int, skb_headlen(from), len);
-		if (plen) {
-			page = virt_to_head_page(from->head);
-			offset = from->data - (unsigned char *)page_address(page);
-			__skb_fill_page_desc(to, 0, page, offset, plen);
-			get_page(page);
-			j = 1;
-			len -= plen;
-		}
-	}
-
-	to->truesize += len + plen;
-	to->len += len + plen;
-	to->data_len += len + plen;
-
-	for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
-		if (!len)
-			break;
-		skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i];
-		skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len);
-		len -= skb_shinfo(to)->frags[j].size;
-		skb_frag_ref(to, j);
-		j++;
-	}
-	skb_shinfo(to)->nr_frags = j;
-}
-
 static int
 nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet,
 		      bool csum_verify)
@@ -297,6 +253,31 @@ nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet,
 	return flags ? nla_put_be32(nlskb, NFQA_SKB_INFO, htonl(flags)) : 0;
 }
 
+static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk)
+{
+	const struct cred *cred;
+
+	if (sk->sk_state == TCP_TIME_WAIT)
+		return 0;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	if (sk->sk_socket && sk->sk_socket->file) {
+		cred = sk->sk_socket->file->f_cred;
+		if (nla_put_be32(skb, NFQA_UID,
+		    htonl(from_kuid_munged(&init_user_ns, cred->fsuid))))
+			goto nla_put_failure;
+		if (nla_put_be32(skb, NFQA_GID,
+		    htonl(from_kgid_munged(&init_user_ns, cred->fsgid))))
+			goto nla_put_failure;
+	}
+	read_unlock_bh(&sk->sk_callback_lock);
+	return 0;
+
+nla_put_failure:
+	read_unlock_bh(&sk->sk_callback_lock);
+	return -1;
+}
+
 static struct sk_buff *
 nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 			   struct nf_queue_entry *entry,
@@ -304,7 +285,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 {
 	size_t size;
 	size_t data_len = 0, cap_len = 0;
-	int hlen = 0;
+	unsigned int hlen = 0;
 	struct sk_buff *skb;
 	struct nlattr *nla;
 	struct nfqnl_msg_packet_hdr *pmsg;
@@ -356,14 +337,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 		if (data_len > entskb->len)
 			data_len = entskb->len;
 
-		if (!entskb->head_frag ||
-		    skb_headlen(entskb) < L1_CACHE_BYTES ||
-		    skb_shinfo(entskb)->nr_frags >= MAX_SKB_FRAGS)
-			hlen = skb_headlen(entskb);
-
-		if (skb_has_frag_list(entskb))
-			hlen = entskb->len;
-		hlen = min_t(int, data_len, hlen);
+		hlen = skb_zerocopy_headlen(entskb);
+		hlen = min_t(unsigned int, hlen, data_len);
 		size += sizeof(struct nlattr) + hlen;
 		cap_len = entskb->len;
 		break;
@@ -372,15 +347,23 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	if (queue->flags & NFQA_CFG_F_CONNTRACK)
 		ct = nfqnl_ct_get(entskb, &size, &ctinfo);
 
+	if (queue->flags & NFQA_CFG_F_UID_GID) {
+		size +=  (nla_total_size(sizeof(u_int32_t))	/* uid */
+			+ nla_total_size(sizeof(u_int32_t)));	/* gid */
+	}
+
 	skb = nfnetlink_alloc_skb(net, size, queue->peer_portid,
 				  GFP_ATOMIC);
-	if (!skb)
+	if (!skb) {
+		skb_tx_error(entskb);
 		return NULL;
+	}
 
 	nlh = nlmsg_put(skb, 0, 0,
 			NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
 			sizeof(struct nfgenmsg), 0);
 	if (!nlh) {
+		skb_tx_error(entskb);
 		kfree_skb(skb);
 		return NULL;
 	}
@@ -484,6 +467,10 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 			goto nla_put_failure;
 	}
 
+	if ((queue->flags & NFQA_CFG_F_UID_GID) && entskb->sk &&
+	    nfqnl_put_sk_uidgid(skb, entskb->sk) < 0)
+		goto nla_put_failure;
+
 	if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0)
 		goto nla_put_failure;
 
@@ -504,13 +491,15 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 		nla->nla_type = NFQA_PAYLOAD;
 		nla->nla_len = nla_attr_size(data_len);
 
-		nfqnl_zcopy(skb, entskb, data_len, hlen);
+		if (skb_zerocopy(skb, entskb, data_len, hlen))
+			goto nla_put_failure;
 	}
 
 	nlh->nlmsg_len = skb->len;
 	return skb;
 
 nla_put_failure:
+	skb_tx_error(entskb);
 	kfree_skb(skb);
 	net_err_ratelimited("nf_queue: error creating packet message\n");
 	return NULL;
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 954925db414..e2b3f51c81f 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -128,7 +128,7 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx,
 	BUG_ON(err < 0);
 	desc.len *= BITS_PER_BYTE;
 
-	mask = ~0U >> (sizeof(priv->data) * BITS_PER_BYTE - desc.len);
+	mask = nft_cmp_fast_mask(desc.len);
 	priv->data = data.data[0] & mask;
 	priv->len  = desc.len;
 	return 0;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index da0c1f4ada1..1840989092e 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -92,7 +92,7 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par,
 	if (ctx->chain->flags & NFT_BASE_CHAIN) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
-		const struct nf_hook_ops *ops = &basechain->ops;
+		const struct nf_hook_ops *ops = &basechain->ops[0];
 
 		par->hook_mask = 1 << ops->hooknum;
 	}
@@ -192,9 +192,18 @@ err:
 }
 
 static void
-nft_target_destroy(const struct nft_expr *expr)
+nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
 {
 	struct xt_target *target = expr->ops->data;
+	void *info = nft_expr_priv(expr);
+	struct xt_tgdtor_param par;
+
+	par.net = ctx->net;
+	par.target = target;
+	par.targinfo = info;
+	par.family = ctx->afi->family;
+	if (par.target->destroy != NULL)
+		par.target->destroy(&par);
 
 	module_put(target->me);
 }
@@ -253,7 +262,7 @@ static int nft_target_validate(const struct nft_ctx *ctx,
 	if (ctx->chain->flags & NFT_BASE_CHAIN) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
-		const struct nf_hook_ops *ops = &basechain->ops;
+		const struct nf_hook_ops *ops = &basechain->ops[0];
 
 		hook_mask = 1 << ops->hooknum;
 		if (hook_mask & target->hooks)
@@ -323,7 +332,7 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
 	if (ctx->chain->flags & NFT_BASE_CHAIN) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
-		const struct nf_hook_ops *ops = &basechain->ops;
+		const struct nf_hook_ops *ops = &basechain->ops[0];
 
 		par->hook_mask = 1 << ops->hooknum;
 	}
@@ -379,9 +388,18 @@ err:
 }
 
 static void
-nft_match_destroy(const struct nft_expr *expr)
+nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
 {
 	struct xt_match *match = expr->ops->data;
+	void *info = nft_expr_priv(expr);
+	struct xt_mtdtor_param par;
+
+	par.net = ctx->net;
+	par.match = match;
+	par.matchinfo = info;
+	par.family = ctx->afi->family;
+	if (par.match->destroy != NULL)
+		par.match->destroy(&par);
 
 	module_put(match->me);
 }
@@ -449,7 +467,7 @@ static int nft_match_validate(const struct nft_ctx *ctx,
 	if (ctx->chain->flags & NFT_BASE_CHAIN) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
-		const struct nf_hook_ops *ops = &basechain->ops;
+		const struct nf_hook_ops *ops = &basechain->ops[0];
 
 		hook_mask = 1 << ops->hooknum;
 		if (hook_mask & match->hooks)
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 955f4e6e708..cc560301624 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -18,17 +18,21 @@
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_labels.h>
 
 struct nft_ct {
 	enum nft_ct_keys	key:8;
 	enum ip_conntrack_dir	dir:8;
-	enum nft_registers	dreg:8;
-	uint8_t			family;
+	union {
+		enum nft_registers	dreg:8;
+		enum nft_registers	sreg:8;
+	};
 };
 
-static void nft_ct_eval(const struct nft_expr *expr,
-			struct nft_data data[NFT_REG_MAX + 1],
-			const struct nft_pktinfo *pkt)
+static void nft_ct_get_eval(const struct nft_expr *expr,
+			    struct nft_data data[NFT_REG_MAX + 1],
+			    const struct nft_pktinfo *pkt)
 {
 	const struct nft_ct *priv = nft_expr_priv(expr);
 	struct nft_data *dest = &data[priv->dreg];
@@ -93,6 +97,26 @@ static void nft_ct_eval(const struct nft_expr *expr,
 			goto err;
 		strncpy((char *)dest->data, helper->name, sizeof(dest->data));
 		return;
+#ifdef CONFIG_NF_CONNTRACK_LABELS
+	case NFT_CT_LABELS: {
+		struct nf_conn_labels *labels = nf_ct_labels_find(ct);
+		unsigned int size;
+
+		if (!labels) {
+			memset(dest->data, 0, sizeof(dest->data));
+			return;
+		}
+
+		BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE > sizeof(dest->data));
+		size = labels->words * sizeof(long);
+
+		memcpy(dest->data, labels->bits, size);
+		if (size < sizeof(dest->data))
+			memset(((char *) dest->data) + size, 0,
+			       sizeof(dest->data) - size);
+		return;
+	}
+#endif
 	}
 
 	tuple = &ct->tuplehash[priv->dir].tuple;
@@ -123,35 +147,82 @@ err:
 	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
 }
 
+static void nft_ct_set_eval(const struct nft_expr *expr,
+			    struct nft_data data[NFT_REG_MAX + 1],
+			    const struct nft_pktinfo *pkt)
+{
+	const struct nft_ct *priv = nft_expr_priv(expr);
+	struct sk_buff *skb = pkt->skb;
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	u32 value = data[priv->sreg].data[0];
+#endif
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (ct == NULL)
+		return;
+
+	switch (priv->key) {
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	case NFT_CT_MARK:
+		if (ct->mark != value) {
+			ct->mark = value;
+			nf_conntrack_event_cache(IPCT_MARK, ct);
+		}
+		break;
+#endif
+	}
+}
+
 static const struct nla_policy nft_ct_policy[NFTA_CT_MAX + 1] = {
 	[NFTA_CT_DREG]		= { .type = NLA_U32 },
 	[NFTA_CT_KEY]		= { .type = NLA_U32 },
 	[NFTA_CT_DIRECTION]	= { .type = NLA_U8 },
+	[NFTA_CT_SREG]		= { .type = NLA_U32 },
 };
 
-static int nft_ct_init(const struct nft_ctx *ctx,
-		       const struct nft_expr *expr,
-		       const struct nlattr * const tb[])
+static int nft_ct_l3proto_try_module_get(uint8_t family)
 {
-	struct nft_ct *priv = nft_expr_priv(expr);
 	int err;
 
-	if (tb[NFTA_CT_DREG] == NULL ||
-	    tb[NFTA_CT_KEY] == NULL)
-		return -EINVAL;
-
-	priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
-	if (tb[NFTA_CT_DIRECTION] != NULL) {
-		priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]);
-		switch (priv->dir) {
-		case IP_CT_DIR_ORIGINAL:
-		case IP_CT_DIR_REPLY:
-			break;
-		default:
-			return -EINVAL;
-		}
+	if (family == NFPROTO_INET) {
+		err = nf_ct_l3proto_try_module_get(NFPROTO_IPV4);
+		if (err < 0)
+			goto err1;
+		err = nf_ct_l3proto_try_module_get(NFPROTO_IPV6);
+		if (err < 0)
+			goto err2;
+	} else {
+		err = nf_ct_l3proto_try_module_get(family);
+		if (err < 0)
+			goto err1;
 	}
+	return 0;
+
+err2:
+	nf_ct_l3proto_module_put(NFPROTO_IPV4);
+err1:
+	return err;
+}
+
+static void nft_ct_l3proto_module_put(uint8_t family)
+{
+	if (family == NFPROTO_INET) {
+		nf_ct_l3proto_module_put(NFPROTO_IPV4);
+		nf_ct_l3proto_module_put(NFPROTO_IPV6);
+	} else
+		nf_ct_l3proto_module_put(family);
+}
+
+static int nft_ct_get_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
+{
+	struct nft_ct *priv = nft_expr_priv(expr);
+	int err;
 
+	priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
 	switch (priv->key) {
 	case NFT_CT_STATE:
 	case NFT_CT_DIRECTION:
@@ -162,11 +233,15 @@ static int nft_ct_init(const struct nft_ctx *ctx,
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
 	case NFT_CT_SECMARK:
 #endif
+#ifdef CONFIG_NF_CONNTRACK_LABELS
+	case NFT_CT_LABELS:
+#endif
 	case NFT_CT_EXPIRATION:
 	case NFT_CT_HELPER:
 		if (tb[NFTA_CT_DIRECTION] != NULL)
 			return -EINVAL;
 		break;
+	case NFT_CT_L3PROTOCOL:
 	case NFT_CT_PROTOCOL:
 	case NFT_CT_SRC:
 	case NFT_CT_DST:
@@ -179,34 +254,69 @@ static int nft_ct_init(const struct nft_ctx *ctx,
 		return -EOPNOTSUPP;
 	}
 
-	err = nf_ct_l3proto_try_module_get(ctx->afi->family);
-	if (err < 0)
-		return err;
-	priv->family = ctx->afi->family;
+	if (tb[NFTA_CT_DIRECTION] != NULL) {
+		priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]);
+		switch (priv->dir) {
+		case IP_CT_DIR_ORIGINAL:
+		case IP_CT_DIR_REPLY:
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
 
 	priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG]));
 	err = nft_validate_output_register(priv->dreg);
 	if (err < 0)
-		goto err1;
+		return err;
 
 	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
 	if (err < 0)
-		goto err1;
-	return 0;
+		return err;
 
-err1:
-	nf_ct_l3proto_module_put(ctx->afi->family);
-	return err;
+	err = nft_ct_l3proto_try_module_get(ctx->afi->family);
+	if (err < 0)
+		return err;
+
+	return 0;
 }
 
-static void nft_ct_destroy(const struct nft_expr *expr)
+static int nft_ct_set_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
 {
 	struct nft_ct *priv = nft_expr_priv(expr);
+	int err;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
+	switch (priv->key) {
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	case NFT_CT_MARK:
+		break;
+#endif
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_CT_SREG]));
+	err = nft_validate_input_register(priv->sreg);
+	if (err < 0)
+		return err;
+
+	err = nft_ct_l3proto_try_module_get(ctx->afi->family);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
 
-	nf_ct_l3proto_module_put(priv->family);
+static void nft_ct_destroy(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr)
+{
+	nft_ct_l3proto_module_put(ctx->afi->family);
 }
 
-static int nft_ct_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_ct *priv = nft_expr_priv(expr);
 
@@ -214,7 +324,32 @@ static int nft_ct_dump(struct sk_buff *skb, const struct nft_expr *expr)
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key)))
 		goto nla_put_failure;
-	if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir))
+
+	switch (priv->key) {
+	case NFT_CT_PROTOCOL:
+	case NFT_CT_SRC:
+	case NFT_CT_DST:
+	case NFT_CT_PROTO_SRC:
+	case NFT_CT_PROTO_DST:
+		if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir))
+			goto nla_put_failure;
+	default:
+		break;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static int nft_ct_set_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_ct *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_CT_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key)))
 		goto nla_put_failure;
 	return 0;
 
@@ -223,18 +358,46 @@ nla_put_failure:
 }
 
 static struct nft_expr_type nft_ct_type;
-static const struct nft_expr_ops nft_ct_ops = {
+static const struct nft_expr_ops nft_ct_get_ops = {
+	.type		= &nft_ct_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ct)),
+	.eval		= nft_ct_get_eval,
+	.init		= nft_ct_get_init,
+	.destroy	= nft_ct_destroy,
+	.dump		= nft_ct_get_dump,
+};
+
+static const struct nft_expr_ops nft_ct_set_ops = {
 	.type		= &nft_ct_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ct)),
-	.eval		= nft_ct_eval,
-	.init		= nft_ct_init,
+	.eval		= nft_ct_set_eval,
+	.init		= nft_ct_set_init,
 	.destroy	= nft_ct_destroy,
-	.dump		= nft_ct_dump,
+	.dump		= nft_ct_set_dump,
 };
 
+static const struct nft_expr_ops *
+nft_ct_select_ops(const struct nft_ctx *ctx,
+		    const struct nlattr * const tb[])
+{
+	if (tb[NFTA_CT_KEY] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_CT_DREG] && tb[NFTA_CT_SREG])
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_CT_DREG])
+		return &nft_ct_get_ops;
+
+	if (tb[NFTA_CT_SREG])
+		return &nft_ct_set_ops;
+
+	return ERR_PTR(-EINVAL);
+}
+
 static struct nft_expr_type nft_ct_type __read_mostly = {
 	.name		= "ct",
-	.ops		= &nft_ct_ops,
+	.select_ops	= &nft_ct_select_ops,
 	.policy		= nft_ct_policy,
 	.maxattr	= NFTA_CT_MAX,
 	.owner		= THIS_MODULE,
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index 8e0bb75e7c5..55c939f5371 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -31,7 +31,7 @@ static void nft_exthdr_eval(const struct nft_expr *expr,
 {
 	struct nft_exthdr *priv = nft_expr_priv(expr);
 	struct nft_data *dest = &data[priv->dreg];
-	unsigned int offset;
+	unsigned int offset = 0;
 	int err;
 
 	err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL);
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 3d3f8fce10a..4080ed6a072 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -12,23 +12,36 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/list.h>
+#include <linux/log2.h>
 #include <linux/jhash.h>
 #include <linux/netlink.h>
+#include <linux/vmalloc.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 
+#define NFT_HASH_MIN_SIZE	4UL
+
 struct nft_hash {
-	struct hlist_head	*hash;
-	unsigned int		hsize;
+	struct nft_hash_table __rcu	*tbl;
+};
+
+struct nft_hash_table {
+	unsigned int			size;
+	struct nft_hash_elem __rcu	*buckets[];
 };
 
 struct nft_hash_elem {
-	struct hlist_node	hnode;
-	struct nft_data		key;
-	struct nft_data		data[];
+	struct nft_hash_elem __rcu	*next;
+	struct nft_data			key;
+	struct nft_data			data[];
 };
 
+#define nft_hash_for_each_entry(i, head) \
+	for (i = nft_dereference(head); i != NULL; i = nft_dereference(i->next))
+#define nft_hash_for_each_entry_rcu(i, head) \
+	for (i = rcu_dereference(head); i != NULL; i = rcu_dereference(i->next))
+
 static u32 nft_hash_rnd __read_mostly;
 static bool nft_hash_rnd_initted __read_mostly;
 
@@ -38,7 +51,7 @@ static unsigned int nft_hash_data(const struct nft_data *data,
 	unsigned int h;
 
 	h = jhash(data->data, len, nft_hash_rnd);
-	return ((u64)h * hsize) >> 32;
+	return h & (hsize - 1);
 }
 
 static bool nft_hash_lookup(const struct nft_set *set,
@@ -46,11 +59,12 @@ static bool nft_hash_lookup(const struct nft_set *set,
 			    struct nft_data *data)
 {
 	const struct nft_hash *priv = nft_set_priv(set);
+	const struct nft_hash_table *tbl = rcu_dereference(priv->tbl);
 	const struct nft_hash_elem *he;
 	unsigned int h;
 
-	h = nft_hash_data(key, priv->hsize, set->klen);
-	hlist_for_each_entry(he, &priv->hash[h], hnode) {
+	h = nft_hash_data(key, tbl->size, set->klen);
+	nft_hash_for_each_entry_rcu(he, tbl->buckets[h]) {
 		if (nft_data_cmp(&he->key, key, set->klen))
 			continue;
 		if (set->flags & NFT_SET_MAP)
@@ -60,19 +74,148 @@ static bool nft_hash_lookup(const struct nft_set *set,
 	return false;
 }
 
-static void nft_hash_elem_destroy(const struct nft_set *set,
-				  struct nft_hash_elem *he)
+static void nft_hash_tbl_free(const struct nft_hash_table *tbl)
 {
-	nft_data_uninit(&he->key, NFT_DATA_VALUE);
-	if (set->flags & NFT_SET_MAP)
-		nft_data_uninit(he->data, set->dtype);
-	kfree(he);
+	kvfree(tbl);
+}
+
+static unsigned int nft_hash_tbl_size(unsigned int nelem)
+{
+	return max(roundup_pow_of_two(nelem * 4 / 3), NFT_HASH_MIN_SIZE);
+}
+
+static struct nft_hash_table *nft_hash_tbl_alloc(unsigned int nbuckets)
+{
+	struct nft_hash_table *tbl;
+	size_t size;
+
+	size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
+	tbl = kzalloc(size, GFP_KERNEL | __GFP_REPEAT | __GFP_NOWARN);
+	if (tbl == NULL)
+		tbl = vzalloc(size);
+	if (tbl == NULL)
+		return NULL;
+	tbl->size = nbuckets;
+
+	return tbl;
+}
+
+static void nft_hash_chain_unzip(const struct nft_set *set,
+				 const struct nft_hash_table *ntbl,
+				 struct nft_hash_table *tbl, unsigned int n)
+{
+	struct nft_hash_elem *he, *last, *next;
+	unsigned int h;
+
+	he = nft_dereference(tbl->buckets[n]);
+	if (he == NULL)
+		return;
+	h = nft_hash_data(&he->key, ntbl->size, set->klen);
+
+	/* Find last element of first chain hashing to bucket h */
+	last = he;
+	nft_hash_for_each_entry(he, he->next) {
+		if (nft_hash_data(&he->key, ntbl->size, set->klen) != h)
+			break;
+		last = he;
+	}
+
+	/* Unlink first chain from the old table */
+	RCU_INIT_POINTER(tbl->buckets[n], last->next);
+
+	/* If end of chain reached, done */
+	if (he == NULL)
+		return;
+
+	/* Find first element of second chain hashing to bucket h */
+	next = NULL;
+	nft_hash_for_each_entry(he, he->next) {
+		if (nft_hash_data(&he->key, ntbl->size, set->klen) != h)
+			continue;
+		next = he;
+		break;
+	}
+
+	/* Link the two chains */
+	RCU_INIT_POINTER(last->next, next);
+}
+
+static int nft_hash_tbl_expand(const struct nft_set *set, struct nft_hash *priv)
+{
+	struct nft_hash_table *tbl = nft_dereference(priv->tbl), *ntbl;
+	struct nft_hash_elem *he;
+	unsigned int i, h;
+	bool complete;
+
+	ntbl = nft_hash_tbl_alloc(tbl->size * 2);
+	if (ntbl == NULL)
+		return -ENOMEM;
+
+	/* Link new table's buckets to first element in the old table
+	 * hashing to the new bucket.
+	 */
+	for (i = 0; i < ntbl->size; i++) {
+		h = i < tbl->size ? i : i - tbl->size;
+		nft_hash_for_each_entry(he, tbl->buckets[h]) {
+			if (nft_hash_data(&he->key, ntbl->size, set->klen) != i)
+				continue;
+			RCU_INIT_POINTER(ntbl->buckets[i], he);
+			break;
+		}
+	}
+
+	/* Publish new table */
+	rcu_assign_pointer(priv->tbl, ntbl);
+
+	/* Unzip interleaved hash chains */
+	do {
+		/* Wait for readers to use new table/unzipped chains */
+		synchronize_rcu();
+
+		complete = true;
+		for (i = 0; i < tbl->size; i++) {
+			nft_hash_chain_unzip(set, ntbl, tbl, i);
+			if (tbl->buckets[i] != NULL)
+				complete = false;
+		}
+	} while (!complete);
+
+	nft_hash_tbl_free(tbl);
+	return 0;
+}
+
+static int nft_hash_tbl_shrink(const struct nft_set *set, struct nft_hash *priv)
+{
+	struct nft_hash_table *tbl = nft_dereference(priv->tbl), *ntbl;
+	struct nft_hash_elem __rcu **pprev;
+	unsigned int i;
+
+	ntbl = nft_hash_tbl_alloc(tbl->size / 2);
+	if (ntbl == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < ntbl->size; i++) {
+		ntbl->buckets[i] = tbl->buckets[i];
+
+		for (pprev = &ntbl->buckets[i]; *pprev != NULL;
+		     pprev = &nft_dereference(*pprev)->next)
+			;
+		RCU_INIT_POINTER(*pprev, tbl->buckets[i + ntbl->size]);
+	}
+
+	/* Publish new table */
+	rcu_assign_pointer(priv->tbl, ntbl);
+	synchronize_rcu();
+
+	nft_hash_tbl_free(tbl);
+	return 0;
 }
 
 static int nft_hash_insert(const struct nft_set *set,
 			   const struct nft_set_elem *elem)
 {
 	struct nft_hash *priv = nft_set_priv(set);
+	struct nft_hash_table *tbl = nft_dereference(priv->tbl);
 	struct nft_hash_elem *he;
 	unsigned int size, h;
 
@@ -91,33 +234,64 @@ static int nft_hash_insert(const struct nft_set *set,
 	if (set->flags & NFT_SET_MAP)
 		nft_data_copy(he->data, &elem->data);
 
-	h = nft_hash_data(&he->key, priv->hsize, set->klen);
-	hlist_add_head_rcu(&he->hnode, &priv->hash[h]);
+	h = nft_hash_data(&he->key, tbl->size, set->klen);
+	RCU_INIT_POINTER(he->next, tbl->buckets[h]);
+	rcu_assign_pointer(tbl->buckets[h], he);
+
+	/* Expand table when exceeding 75% load */
+	if (set->nelems + 1 > tbl->size / 4 * 3)
+		nft_hash_tbl_expand(set, priv);
+
 	return 0;
 }
 
+static void nft_hash_elem_destroy(const struct nft_set *set,
+				  struct nft_hash_elem *he)
+{
+	nft_data_uninit(&he->key, NFT_DATA_VALUE);
+	if (set->flags & NFT_SET_MAP)
+		nft_data_uninit(he->data, set->dtype);
+	kfree(he);
+}
+
 static void nft_hash_remove(const struct nft_set *set,
 			    const struct nft_set_elem *elem)
 {
-	struct nft_hash_elem *he = elem->cookie;
+	struct nft_hash *priv = nft_set_priv(set);
+	struct nft_hash_table *tbl = nft_dereference(priv->tbl);
+	struct nft_hash_elem *he, __rcu **pprev;
+
+	pprev = elem->cookie;
+	he = nft_dereference((*pprev));
 
-	hlist_del_rcu(&he->hnode);
+	RCU_INIT_POINTER(*pprev, he->next);
+	synchronize_rcu();
 	kfree(he);
+
+	/* Shrink table beneath 30% load */
+	if (set->nelems - 1 < tbl->size * 3 / 10 &&
+	    tbl->size > NFT_HASH_MIN_SIZE)
+		nft_hash_tbl_shrink(set, priv);
 }
 
 static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
 {
 	const struct nft_hash *priv = nft_set_priv(set);
+	const struct nft_hash_table *tbl = nft_dereference(priv->tbl);
+	struct nft_hash_elem __rcu * const *pprev;
 	struct nft_hash_elem *he;
 	unsigned int h;
 
-	h = nft_hash_data(&elem->key, priv->hsize, set->klen);
-	hlist_for_each_entry(he, &priv->hash[h], hnode) {
-		if (nft_data_cmp(&he->key, &elem->key, set->klen))
+	h = nft_hash_data(&elem->key, tbl->size, set->klen);
+	pprev = &tbl->buckets[h];
+	nft_hash_for_each_entry(he, tbl->buckets[h]) {
+		if (nft_data_cmp(&he->key, &elem->key, set->klen)) {
+			pprev = &he->next;
 			continue;
+		}
 
-		elem->cookie = he;
-		elem->flags  = 0;
+		elem->cookie = (void *)pprev;
+		elem->flags = 0;
 		if (set->flags & NFT_SET_MAP)
 			nft_data_copy(&elem->data, he->data);
 		return 0;
@@ -129,12 +303,13 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 			  struct nft_set_iter *iter)
 {
 	const struct nft_hash *priv = nft_set_priv(set);
+	const struct nft_hash_table *tbl = nft_dereference(priv->tbl);
 	const struct nft_hash_elem *he;
 	struct nft_set_elem elem;
 	unsigned int i;
 
-	for (i = 0; i < priv->hsize; i++) {
-		hlist_for_each_entry(he, &priv->hash[i], hnode) {
+	for (i = 0; i < tbl->size; i++) {
+		nft_hash_for_each_entry(he, tbl->buckets[i]) {
 			if (iter->count < iter->skip)
 				goto cont;
 
@@ -158,50 +333,77 @@ static unsigned int nft_hash_privsize(const struct nlattr * const nla[])
 }
 
 static int nft_hash_init(const struct nft_set *set,
+			 const struct nft_set_desc *desc,
 			 const struct nlattr * const tb[])
 {
 	struct nft_hash *priv = nft_set_priv(set);
-	unsigned int cnt, i;
+	struct nft_hash_table *tbl;
+	unsigned int size;
 
 	if (unlikely(!nft_hash_rnd_initted)) {
 		get_random_bytes(&nft_hash_rnd, 4);
 		nft_hash_rnd_initted = true;
 	}
 
-	/* Aim for a load factor of 0.75 */
-	// FIXME: temporarily broken until we have set descriptions
-	cnt = 100;
-	cnt = cnt * 4 / 3;
+	size = NFT_HASH_MIN_SIZE;
+	if (desc->size)
+		size = nft_hash_tbl_size(desc->size);
 
-	priv->hash = kcalloc(cnt, sizeof(struct hlist_head), GFP_KERNEL);
-	if (priv->hash == NULL)
+	tbl = nft_hash_tbl_alloc(size);
+	if (tbl == NULL)
 		return -ENOMEM;
-	priv->hsize = cnt;
-
-	for (i = 0; i < cnt; i++)
-		INIT_HLIST_HEAD(&priv->hash[i]);
-
+	RCU_INIT_POINTER(priv->tbl, tbl);
 	return 0;
 }
 
 static void nft_hash_destroy(const struct nft_set *set)
 {
 	const struct nft_hash *priv = nft_set_priv(set);
-	const struct hlist_node *next;
-	struct nft_hash_elem *elem;
+	const struct nft_hash_table *tbl = nft_dereference(priv->tbl);
+	struct nft_hash_elem *he, *next;
 	unsigned int i;
 
-	for (i = 0; i < priv->hsize; i++) {
-		hlist_for_each_entry_safe(elem, next, &priv->hash[i], hnode) {
-			hlist_del(&elem->hnode);
-			nft_hash_elem_destroy(set, elem);
+	for (i = 0; i < tbl->size; i++) {
+		for (he = nft_dereference(tbl->buckets[i]); he != NULL;
+		     he = next) {
+			next = nft_dereference(he->next);
+			nft_hash_elem_destroy(set, he);
 		}
 	}
-	kfree(priv->hash);
+	kfree(tbl);
+}
+
+static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
+			      struct nft_set_estimate *est)
+{
+	unsigned int esize;
+
+	esize = sizeof(struct nft_hash_elem);
+	if (features & NFT_SET_MAP)
+		esize += FIELD_SIZEOF(struct nft_hash_elem, data[0]);
+
+	if (desc->size) {
+		est->size = sizeof(struct nft_hash) +
+			    nft_hash_tbl_size(desc->size) *
+			    sizeof(struct nft_hash_elem *) +
+			    desc->size * esize;
+	} else {
+		/* Resizing happens when the load drops below 30% or goes
+		 * above 75%. The average of 52.5% load (approximated by 50%)
+		 * is used for the size estimation of the hash buckets,
+		 * meaning we calculate two buckets per element.
+		 */
+		est->size = esize + 2 * sizeof(struct nft_hash_elem *);
+	}
+
+	est->class = NFT_SET_CLASS_O_1;
+
+	return true;
 }
 
 static struct nft_set_ops nft_hash_ops __read_mostly = {
 	.privsize       = nft_hash_privsize,
+	.estimate	= nft_hash_estimate,
 	.init		= nft_hash_init,
 	.destroy	= nft_hash_destroy,
 	.get		= nft_hash_get,
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index f169501f1ad..810385eb724 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -70,7 +70,8 @@ err1:
 	return err;
 }
 
-static void nft_immediate_destroy(const struct nft_expr *expr)
+static void nft_immediate_destroy(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr)
 {
 	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
 	return nft_data_uninit(&priv->data, nft_dreg_to_type(priv->dreg));
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 57cad072a13..10cfb156cdf 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -23,7 +23,6 @@ static const char *nft_log_null_prefix = "";
 struct nft_log {
 	struct nf_loginfo	loginfo;
 	char			*prefix;
-	int			family;
 };
 
 static void nft_log_eval(const struct nft_expr *expr,
@@ -33,7 +32,7 @@ static void nft_log_eval(const struct nft_expr *expr,
 	const struct nft_log *priv = nft_expr_priv(expr);
 	struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
 
-	nf_log_packet(net, priv->family, pkt->hooknum, pkt->skb, pkt->in,
+	nf_log_packet(net, pkt->ops->pf, pkt->ops->hooknum, pkt->skb, pkt->in,
 		      pkt->out, &priv->loginfo, "%s", priv->prefix);
 }
 
@@ -52,8 +51,6 @@ static int nft_log_init(const struct nft_ctx *ctx,
 	struct nf_loginfo *li = &priv->loginfo;
 	const struct nlattr *nla;
 
-	priv->family = ctx->afi->family;
-
 	nla = tb[NFTA_LOG_PREFIX];
 	if (nla != NULL) {
 		priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
@@ -77,7 +74,8 @@ static int nft_log_init(const struct nft_ctx *ctx,
 	return 0;
 }
 
-static void nft_log_destroy(const struct nft_expr *expr)
+static void nft_log_destroy(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr)
 {
 	struct nft_log *priv = nft_expr_priv(expr);
 
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 8a6116b75b5..6404a726d17 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -16,6 +16,7 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
 
 struct nft_lookup {
 	struct nft_set			*set;
@@ -55,8 +56,14 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 		return -EINVAL;
 
 	set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET]);
-	if (IS_ERR(set))
-		return PTR_ERR(set);
+	if (IS_ERR(set)) {
+		if (tb[NFTA_LOOKUP_SET_ID]) {
+			set = nf_tables_set_lookup_byid(ctx->net,
+							tb[NFTA_LOOKUP_SET_ID]);
+		}
+		if (IS_ERR(set))
+			return PTR_ERR(set);
+	}
 
 	priv->sreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_SREG]));
 	err = nft_validate_input_register(priv->sreg);
@@ -88,11 +95,12 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 	return 0;
 }
 
-static void nft_lookup_destroy(const struct nft_expr *expr)
+static void nft_lookup_destroy(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr)
 {
 	struct nft_lookup *priv = nft_expr_priv(expr);
 
-	nf_tables_unbind_set(NULL, priv->set, &priv->binding);
+	nf_tables_unbind_set(ctx, priv->set, &priv->binding);
 }
 
 static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr)
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 8c28220a90b..852b178c6ae 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -18,15 +18,11 @@
 #include <net/sock.h>
 #include <net/tcp_states.h> /* for TCP_TIME_WAIT */
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_meta.h>
 
-struct nft_meta {
-	enum nft_meta_keys	key:8;
-	enum nft_registers	dreg:8;
-};
-
-static void nft_meta_eval(const struct nft_expr *expr,
-			  struct nft_data data[NFT_REG_MAX + 1],
-			  const struct nft_pktinfo *pkt)
+void nft_meta_get_eval(const struct nft_expr *expr,
+		       struct nft_data data[NFT_REG_MAX + 1],
+		       const struct nft_pktinfo *pkt)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 	const struct sk_buff *skb = pkt->skb;
@@ -40,6 +36,12 @@ static void nft_meta_eval(const struct nft_expr *expr,
 	case NFT_META_PROTOCOL:
 		*(__be16 *)dest->data = skb->protocol;
 		break;
+	case NFT_META_NFPROTO:
+		dest->data[0] = pkt->ops->pf;
+		break;
+	case NFT_META_L4PROTO:
+		dest->data[0] = pkt->tprot;
+		break;
 	case NFT_META_PRIORITY:
 		dest->data[0] = skb->priority;
 		break;
@@ -107,7 +109,7 @@ static void nft_meta_eval(const struct nft_expr *expr,
 				 skb->sk->sk_socket->file->f_cred->fsgid);
 		read_unlock_bh(&skb->sk->sk_callback_lock);
 		break;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	case NFT_META_RTCLASSID: {
 		const struct dst_entry *dst = skb_dst(skb);
 
@@ -131,26 +133,52 @@ static void nft_meta_eval(const struct nft_expr *expr,
 err:
 	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
 }
+EXPORT_SYMBOL_GPL(nft_meta_get_eval);
 
-static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
+void nft_meta_set_eval(const struct nft_expr *expr,
+		       struct nft_data data[NFT_REG_MAX + 1],
+		       const struct nft_pktinfo *pkt)
+{
+	const struct nft_meta *meta = nft_expr_priv(expr);
+	struct sk_buff *skb = pkt->skb;
+	u32 value = data[meta->sreg].data[0];
+
+	switch (meta->key) {
+	case NFT_META_MARK:
+		skb->mark = value;
+		break;
+	case NFT_META_PRIORITY:
+		skb->priority = value;
+		break;
+	case NFT_META_NFTRACE:
+		skb->nf_trace = 1;
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+EXPORT_SYMBOL_GPL(nft_meta_set_eval);
+
+const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
 	[NFTA_META_DREG]	= { .type = NLA_U32 },
 	[NFTA_META_KEY]		= { .type = NLA_U32 },
+	[NFTA_META_SREG]	= { .type = NLA_U32 },
 };
+EXPORT_SYMBOL_GPL(nft_meta_policy);
 
-static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
-			 const struct nlattr * const tb[])
+int nft_meta_get_init(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nlattr * const tb[])
 {
 	struct nft_meta *priv = nft_expr_priv(expr);
 	int err;
 
-	if (tb[NFTA_META_DREG] == NULL ||
-	    tb[NFTA_META_KEY] == NULL)
-		return -EINVAL;
-
 	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
 	switch (priv->key) {
 	case NFT_META_LEN:
 	case NFT_META_PROTOCOL:
+	case NFT_META_NFPROTO:
+	case NFT_META_L4PROTO:
 	case NFT_META_PRIORITY:
 	case NFT_META_MARK:
 	case NFT_META_IIF:
@@ -161,7 +189,7 @@ static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	case NFT_META_OIFTYPE:
 	case NFT_META_SKUID:
 	case NFT_META_SKGID:
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
 	case NFT_META_RTCLASSID:
 #endif
 #ifdef CONFIG_NETWORK_SECMARK
@@ -176,35 +204,113 @@ static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	err = nft_validate_output_register(priv->dreg);
 	if (err < 0)
 		return err;
-	return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+
+	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+	if (err < 0)
+		return err;
+
+	return 0;
 }
+EXPORT_SYMBOL_GPL(nft_meta_get_init);
 
-static int nft_meta_dump(struct sk_buff *skb, const struct nft_expr *expr)
+int nft_meta_set_init(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nlattr * const tb[])
+{
+	struct nft_meta *priv = nft_expr_priv(expr);
+	int err;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+	switch (priv->key) {
+	case NFT_META_MARK:
+	case NFT_META_PRIORITY:
+	case NFT_META_NFTRACE:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_META_SREG]));
+	err = nft_validate_input_register(priv->sreg);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_meta_set_init);
+
+int nft_meta_get_dump(struct sk_buff *skb,
+		      const struct nft_expr *expr)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 
+	if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key)))
+		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_META_DREG, htonl(priv->dreg)))
 		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+EXPORT_SYMBOL_GPL(nft_meta_get_dump);
+
+int nft_meta_set_dump(struct sk_buff *skb,
+		      const struct nft_expr *expr)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+
 	if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key)))
 		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_META_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
 	return -1;
 }
+EXPORT_SYMBOL_GPL(nft_meta_set_dump);
 
 static struct nft_expr_type nft_meta_type;
-static const struct nft_expr_ops nft_meta_ops = {
+static const struct nft_expr_ops nft_meta_get_ops = {
+	.type		= &nft_meta_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.eval		= nft_meta_get_eval,
+	.init		= nft_meta_get_init,
+	.dump		= nft_meta_get_dump,
+};
+
+static const struct nft_expr_ops nft_meta_set_ops = {
 	.type		= &nft_meta_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
-	.eval		= nft_meta_eval,
-	.init		= nft_meta_init,
-	.dump		= nft_meta_dump,
+	.eval		= nft_meta_set_eval,
+	.init		= nft_meta_set_init,
+	.dump		= nft_meta_set_dump,
 };
 
+static const struct nft_expr_ops *
+nft_meta_select_ops(const struct nft_ctx *ctx,
+		    const struct nlattr * const tb[])
+{
+	if (tb[NFTA_META_KEY] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG])
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_META_DREG])
+		return &nft_meta_get_ops;
+
+	if (tb[NFTA_META_SREG])
+		return &nft_meta_set_ops;
+
+	return ERR_PTR(-EINVAL);
+}
+
 static struct nft_expr_type nft_meta_type __read_mostly = {
 	.name		= "meta",
-	.ops		= &nft_meta_ops,
+	.select_ops	= &nft_meta_select_ops,
 	.policy		= nft_meta_policy,
 	.maxattr	= NFTA_META_MAX,
 	.owner		= THIS_MODULE,
diff --git a/net/netfilter/nft_meta_target.c b/net/netfilter/nft_meta_target.c
deleted file mode 100644
index 71177df75ff..00000000000
--- a/net/netfilter/nft_meta_target.c
+++ /dev/null
@@ -1,117 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/rbtree.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-
-struct nft_meta {
-	enum nft_meta_keys	key;
-};
-
-static void nft_meta_eval(const struct nft_expr *expr,
-			  struct nft_data *nfres,
-			  struct nft_data *data,
-			  const struct nft_pktinfo *pkt)
-{
-	const struct nft_meta *meta = nft_expr_priv(expr);
-	struct sk_buff *skb = pkt->skb;
-	u32 val = data->data[0];
-
-	switch (meta->key) {
-	case NFT_META_MARK:
-		skb->mark = val;
-		break;
-	case NFT_META_PRIORITY:
-		skb->priority = val;
-		break;
-	case NFT_META_NFTRACE:
-		skb->nf_trace = val;
-		break;
-#ifdef CONFIG_NETWORK_SECMARK
-	case NFT_META_SECMARK:
-		skb->secmark = val;
-		break;
-#endif
-	default:
-		WARN_ON(1);
-	}
-}
-
-static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
-	[NFTA_META_KEY]		= { .type = NLA_U32 },
-};
-
-static int nft_meta_init(const struct nft_expr *expr, struct nlattr *tb[])
-{
-	struct nft_meta *meta = nft_expr_priv(expr);
-
-	if (tb[NFTA_META_KEY] == NULL)
-		return -EINVAL;
-
-	meta->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
-	switch (meta->key) {
-	case NFT_META_MARK:
-	case NFT_META_PRIORITY:
-	case NFT_META_NFTRACE:
-#ifdef CONFIG_NETWORK_SECMARK
-	case NFT_META_SECMARK:
-#endif
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int nft_meta_dump(struct sk_buff *skb, const struct nft_expr *expr)
-{
-	struct nft_meta *meta = nft_expr_priv(expr);
-
-	NLA_PUT_BE32(skb, NFTA_META_KEY, htonl(meta->key));
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static struct nft_expr_ops meta_target __read_mostly = {
-	.name		= "meta",
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
-	.owner		= THIS_MODULE,
-	.eval		= nft_meta_eval,
-	.init		= nft_meta_init,
-	.dump		= nft_meta_dump,
-	.policy		= nft_meta_policy,
-	.maxattr	= NFTA_META_MAX,
-};
-
-static int __init nft_meta_target_init(void)
-{
-	return nft_register_expr(&meta_target);
-}
-
-static void __exit nft_meta_target_exit(void)
-{
-	nft_unregister_expr(&meta_target);
-}
-
-module_init(nft_meta_target_init);
-module_exit(nft_meta_target_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_EXPR("meta");
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index d3b1ffe2618..79ff58cd36d 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -31,8 +31,8 @@ struct nft_nat {
 	enum nft_registers      sreg_addr_max:8;
 	enum nft_registers      sreg_proto_min:8;
 	enum nft_registers      sreg_proto_max:8;
-	int                     family;
-	enum nf_nat_manip_type  type;
+	enum nf_nat_manip_type  type:8;
+	u8			family;
 };
 
 static void nft_nat_eval(const struct nft_expr *expr,
@@ -88,6 +88,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 			const struct nlattr * const tb[])
 {
 	struct nft_nat *priv = nft_expr_priv(expr);
+	u32 family;
 	int err;
 
 	if (tb[NFTA_NAT_TYPE] == NULL)
@@ -107,9 +108,12 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	if (tb[NFTA_NAT_FAMILY] == NULL)
 		return -EINVAL;
 
-	priv->family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY]));
-	if (priv->family != AF_INET && priv->family != AF_INET6)
-		return -EINVAL;
+	family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY]));
+	if (family != AF_INET && family != AF_INET6)
+		return -EAFNOSUPPORT;
+	if (family != ctx->afi->family)
+		return -EOPNOTSUPP;
+	priv->family = family;
 
 	if (tb[NFTA_NAT_REG_ADDR_MIN]) {
 		priv->sreg_addr_min = ntohl(nla_get_be32(
@@ -171,12 +175,14 @@ static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
 	if (nla_put_be32(skb,
 			 NFTA_NAT_REG_ADDR_MAX, htonl(priv->sreg_addr_max)))
 		goto nla_put_failure;
-	if (nla_put_be32(skb,
-			 NFTA_NAT_REG_PROTO_MIN, htonl(priv->sreg_proto_min)))
-		goto nla_put_failure;
-	if (nla_put_be32(skb,
-			 NFTA_NAT_REG_PROTO_MAX, htonl(priv->sreg_proto_max)))
-		goto nla_put_failure;
+	if (priv->sreg_proto_min) {
+		if (nla_put_be32(skb, NFTA_NAT_REG_PROTO_MIN,
+				 htonl(priv->sreg_proto_min)))
+			goto nla_put_failure;
+		if (nla_put_be32(skb, NFTA_NAT_REG_PROTO_MAX,
+				 htonl(priv->sreg_proto_max)))
+			goto nla_put_failure;
+	}
 	return 0;
 
 nla_put_failure:
@@ -202,13 +208,7 @@ static struct nft_expr_type nft_nat_type __read_mostly = {
 
 static int __init nft_nat_module_init(void)
 {
-	int err;
-
-	err = nft_register_expr(&nft_nat_type);
-	if (err < 0)
-		return err;
-
-	return 0;
+	return nft_register_expr(&nft_nat_type);
 }
 
 static void __exit nft_nat_module_exit(void)
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index a2aeb318678..85daa84bfdf 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -135,7 +135,8 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
 	if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data))
 		return ERR_PTR(-EINVAL);
 
-	if (len <= 4 && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER)
+	if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
+	    base != NFT_PAYLOAD_LL_HEADER)
 		return &nft_payload_fast_ops;
 	else
 		return &nft_payload_ops;
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
new file mode 100644
index 00000000000..e8ae2f6bf23
--- /dev/null
+++ b/net/netfilter/nft_queue.c
@@ -0,0 +1,132 @@
+/*
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code partly funded by OISF
+ * (http://www.openinfosecfoundation.org/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/jhash.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_queue.h>
+
+static u32 jhash_initval __read_mostly;
+
+struct nft_queue {
+	u16	queuenum;
+	u16	queues_total;
+	u16	flags;
+};
+
+static void nft_queue_eval(const struct nft_expr *expr,
+			   struct nft_data data[NFT_REG_MAX + 1],
+			   const struct nft_pktinfo *pkt)
+{
+	struct nft_queue *priv = nft_expr_priv(expr);
+	u32 queue = priv->queuenum;
+	u32 ret;
+
+	if (priv->queues_total > 1) {
+		if (priv->flags & NFT_QUEUE_FLAG_CPU_FANOUT) {
+			int cpu = smp_processor_id();
+
+			queue = priv->queuenum + cpu % priv->queues_total;
+		} else {
+			queue = nfqueue_hash(pkt->skb, queue,
+					     priv->queues_total, pkt->ops->pf,
+					     jhash_initval);
+		}
+	}
+
+	ret = NF_QUEUE_NR(queue);
+	if (priv->flags & NFT_QUEUE_FLAG_BYPASS)
+		ret |= NF_VERDICT_FLAG_QUEUE_BYPASS;
+
+	data[NFT_REG_VERDICT].verdict = ret;
+}
+
+static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = {
+	[NFTA_QUEUE_NUM]	= { .type = NLA_U16 },
+	[NFTA_QUEUE_TOTAL]	= { .type = NLA_U16 },
+	[NFTA_QUEUE_FLAGS]	= { .type = NLA_U16 },
+};
+
+static int nft_queue_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
+{
+	struct nft_queue *priv = nft_expr_priv(expr);
+
+	if (tb[NFTA_QUEUE_NUM] == NULL)
+		return -EINVAL;
+
+	init_hashrandom(&jhash_initval);
+	priv->queuenum = ntohs(nla_get_be16(tb[NFTA_QUEUE_NUM]));
+
+	if (tb[NFTA_QUEUE_TOTAL] != NULL)
+		priv->queues_total = ntohs(nla_get_be16(tb[NFTA_QUEUE_TOTAL]));
+	if (tb[NFTA_QUEUE_FLAGS] != NULL) {
+		priv->flags = ntohs(nla_get_be16(tb[NFTA_QUEUE_FLAGS]));
+		if (priv->flags & ~NFT_QUEUE_FLAG_MASK)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static int nft_queue_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_queue *priv = nft_expr_priv(expr);
+
+	if (nla_put_be16(skb, NFTA_QUEUE_NUM, htons(priv->queuenum)) ||
+	    nla_put_be16(skb, NFTA_QUEUE_TOTAL, htons(priv->queues_total)) ||
+	    nla_put_be16(skb, NFTA_QUEUE_FLAGS, htons(priv->flags)))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_type nft_queue_type;
+static const struct nft_expr_ops nft_queue_ops = {
+	.type		= &nft_queue_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_queue)),
+	.eval		= nft_queue_eval,
+	.init		= nft_queue_init,
+	.dump		= nft_queue_dump,
+};
+
+static struct nft_expr_type nft_queue_type __read_mostly = {
+	.name		= "queue",
+	.ops		= &nft_queue_ops,
+	.policy		= nft_queue_policy,
+	.maxattr	= NFTA_QUEUE_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_queue_module_init(void)
+{
+	return nft_register_expr(&nft_queue_type);
+}
+
+static void __exit nft_queue_module_exit(void)
+{
+	nft_unregister_expr(&nft_queue_type);
+}
+
+module_init(nft_queue_module_init);
+module_exit(nft_queue_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Leblond <eric@regit.org>");
+MODULE_ALIAS_NFT_EXPR("queue");
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index ca0c1b231bf..e1836ff8819 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -18,6 +18,8 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 
+static DEFINE_SPINLOCK(nft_rbtree_lock);
+
 struct nft_rbtree {
 	struct rb_root		root;
 };
@@ -38,6 +40,7 @@ static bool nft_rbtree_lookup(const struct nft_set *set,
 	const struct rb_node *parent = priv->root.rb_node;
 	int d;
 
+	spin_lock_bh(&nft_rbtree_lock);
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
@@ -53,6 +56,8 @@ found:
 				goto out;
 			if (set->flags & NFT_SET_MAP)
 				nft_data_copy(data, rbe->data);
+
+			spin_unlock_bh(&nft_rbtree_lock);
 			return true;
 		}
 	}
@@ -62,6 +67,7 @@ found:
 		goto found;
 	}
 out:
+	spin_unlock_bh(&nft_rbtree_lock);
 	return false;
 }
 
@@ -69,8 +75,10 @@ static void nft_rbtree_elem_destroy(const struct nft_set *set,
 				    struct nft_rbtree_elem *rbe)
 {
 	nft_data_uninit(&rbe->key, NFT_DATA_VALUE);
-	if (set->flags & NFT_SET_MAP)
+	if (set->flags & NFT_SET_MAP &&
+	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 		nft_data_uninit(rbe->data, set->dtype);
+
 	kfree(rbe);
 }
 
@@ -108,7 +116,8 @@ static int nft_rbtree_insert(const struct nft_set *set,
 	int err;
 
 	size = sizeof(*rbe);
-	if (set->flags & NFT_SET_MAP)
+	if (set->flags & NFT_SET_MAP &&
+	    !(elem->flags & NFT_SET_ELEM_INTERVAL_END))
 		size += sizeof(rbe->data[0]);
 
 	rbe = kzalloc(size, GFP_KERNEL);
@@ -117,12 +126,16 @@ static int nft_rbtree_insert(const struct nft_set *set,
 
 	rbe->flags = elem->flags;
 	nft_data_copy(&rbe->key, &elem->key);
-	if (set->flags & NFT_SET_MAP)
+	if (set->flags & NFT_SET_MAP &&
+	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 		nft_data_copy(rbe->data, &elem->data);
 
+	spin_lock_bh(&nft_rbtree_lock);
 	err = __nft_rbtree_insert(set, rbe);
 	if (err < 0)
 		kfree(rbe);
+
+	spin_unlock_bh(&nft_rbtree_lock);
 	return err;
 }
 
@@ -132,7 +145,9 @@ static void nft_rbtree_remove(const struct nft_set *set,
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe = elem->cookie;
 
+	spin_lock_bh(&nft_rbtree_lock);
 	rb_erase(&rbe->node, &priv->root);
+	spin_unlock_bh(&nft_rbtree_lock);
 	kfree(rbe);
 }
 
@@ -143,6 +158,7 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
 	struct nft_rbtree_elem *rbe;
 	int d;
 
+	spin_lock_bh(&nft_rbtree_lock);
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
@@ -153,12 +169,15 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
 			parent = parent->rb_right;
 		else {
 			elem->cookie = rbe;
-			if (set->flags & NFT_SET_MAP)
+			if (set->flags & NFT_SET_MAP &&
+			    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 				nft_data_copy(&elem->data, rbe->data);
 			elem->flags = rbe->flags;
+			spin_unlock_bh(&nft_rbtree_lock);
 			return 0;
 		}
 	}
+	spin_unlock_bh(&nft_rbtree_lock);
 	return -ENOENT;
 }
 
@@ -171,22 +190,27 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 	struct nft_set_elem elem;
 	struct rb_node *node;
 
+	spin_lock_bh(&nft_rbtree_lock);
 	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
 		if (iter->count < iter->skip)
 			goto cont;
 
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 		nft_data_copy(&elem.key, &rbe->key);
-		if (set->flags & NFT_SET_MAP)
+		if (set->flags & NFT_SET_MAP &&
+		    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 			nft_data_copy(&elem.data, rbe->data);
 		elem.flags = rbe->flags;
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
-		if (iter->err < 0)
+		if (iter->err < 0) {
+			spin_unlock_bh(&nft_rbtree_lock);
 			return;
+		}
 cont:
 		iter->count++;
 	}
+	spin_unlock_bh(&nft_rbtree_lock);
 }
 
 static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[])
@@ -195,6 +219,7 @@ static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[])
 }
 
 static int nft_rbtree_init(const struct nft_set *set,
+			   const struct nft_set_desc *desc,
 			   const struct nlattr * const nla[])
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
@@ -209,15 +234,37 @@ static void nft_rbtree_destroy(const struct nft_set *set)
 	struct nft_rbtree_elem *rbe;
 	struct rb_node *node;
 
+	spin_lock_bh(&nft_rbtree_lock);
 	while ((node = priv->root.rb_node) != NULL) {
 		rb_erase(node, &priv->root);
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 		nft_rbtree_elem_destroy(set, rbe);
 	}
+	spin_unlock_bh(&nft_rbtree_lock);
+}
+
+static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
+				struct nft_set_estimate *est)
+{
+	unsigned int nsize;
+
+	nsize = sizeof(struct nft_rbtree_elem);
+	if (features & NFT_SET_MAP)
+		nsize += FIELD_SIZEOF(struct nft_rbtree_elem, data[0]);
+
+	if (desc->size)
+		est->size = sizeof(struct nft_rbtree) + desc->size * nsize;
+	else
+		est->size = nsize;
+
+	est->class = NFT_SET_CLASS_O_LOG_N;
+
+	return true;
 }
 
 static struct nft_set_ops nft_rbtree_ops __read_mostly = {
 	.privsize	= nft_rbtree_privsize,
+	.estimate	= nft_rbtree_estimate,
 	.init		= nft_rbtree_init,
 	.destroy	= nft_rbtree_destroy,
 	.insert		= nft_rbtree_insert,
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
new file mode 100644
index 00000000000..f3448c29644
--- /dev/null
+++ b/net/netfilter/nft_reject.c
@@ -0,0 +1,74 @@
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+
+const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
+	[NFTA_REJECT_TYPE]		= { .type = NLA_U32 },
+	[NFTA_REJECT_ICMP_CODE]		= { .type = NLA_U8 },
+};
+EXPORT_SYMBOL_GPL(nft_reject_policy);
+
+int nft_reject_init(const struct nft_ctx *ctx,
+		    const struct nft_expr *expr,
+		    const struct nlattr * const tb[])
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+
+	if (tb[NFTA_REJECT_TYPE] == NULL)
+		return -EINVAL;
+
+	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+		if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
+			return -EINVAL;
+		priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+	case NFT_REJECT_TCP_RST:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_reject_init);
+
+int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_reject *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
+		goto nla_put_failure;
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
+			goto nla_put_failure;
+		break;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+EXPORT_SYMBOL_GPL(nft_reject_dump);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
new file mode 100644
index 00000000000..b718a52a465
--- /dev/null
+++ b/net/netfilter/nft_reject_inet.c
@@ -0,0 +1,63 @@
+/*
+ * Copyright (c) 2014 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+
+static void nft_reject_inet_eval(const struct nft_expr *expr,
+				 struct nft_data data[NFT_REG_MAX + 1],
+				 const struct nft_pktinfo *pkt)
+{
+	switch (pkt->ops->pf) {
+	case NFPROTO_IPV4:
+		return nft_reject_ipv4_eval(expr, data, pkt);
+	case NFPROTO_IPV6:
+		return nft_reject_ipv6_eval(expr, data, pkt);
+	}
+}
+
+static struct nft_expr_type nft_reject_inet_type;
+static const struct nft_expr_ops nft_reject_inet_ops = {
+	.type		= &nft_reject_inet_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+	.eval		= nft_reject_inet_eval,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_inet_type __read_mostly = {
+	.family		= NFPROTO_INET,
+	.name		= "reject",
+	.ops		= &nft_reject_inet_ops,
+	.policy		= nft_reject_policy,
+	.maxattr	= NFTA_REJECT_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_reject_inet_module_init(void)
+{
+	return nft_register_expr(&nft_reject_inet_type);
+}
+
+static void __exit nft_reject_inet_module_exit(void)
+{
+	nft_unregister_expr(&nft_reject_inet_type);
+}
+
+module_init(nft_reject_inet_module_init);
+module_exit(nft_reject_inet_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(1, "reject");
diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
index 3228d7f24eb..4973cbddc44 100644
--- a/net/netfilter/xt_AUDIT.c
+++ b/net/netfilter/xt_AUDIT.c
@@ -146,11 +146,11 @@ audit_tg(struct sk_buff *skb, const struct xt_action_param *par)
 
 		if (par->family == NFPROTO_BRIDGE) {
 			switch (eth_hdr(skb)->h_proto) {
-			case __constant_htons(ETH_P_IP):
+			case htons(ETH_P_IP):
 				audit_ip4(ab, skb);
 				break;
 
-			case __constant_htons(ETH_P_IPV6):
+			case htons(ETH_P_IPV6):
 				audit_ip6(ab, skb);
 				break;
 			}
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index da35ac06a97..75747aecdeb 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -211,8 +211,10 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 	ret = 0;
 	if ((info->ct_events || info->exp_events) &&
 	    !nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events,
-				  GFP_KERNEL))
+				  GFP_KERNEL)) {
+		ret = -EINVAL;
 		goto err3;
+	}
 
 	if (info->helper[0]) {
 		ret = xt_ct_set_helper(ct, info->helper, par);
@@ -226,12 +228,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 			goto err3;
 	}
 
-	__set_bit(IPS_TEMPLATE_BIT, &ct->status);
-	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
-
-	/* Overload tuple linked list to put us in template list. */
-	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
-				 &par->net->ct.tmpl);
+	nf_conntrack_tmpl_insert(par->net, ct);
 out:
 	info->ct = ct;
 	return 0;
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index ed00fef5899..8f1779ff7e3 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -11,15 +11,13 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/jhash.h>
-
 #include <linux/netfilter.h>
 #include <linux/netfilter_arp.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_NFQUEUE.h>
 
+#include <net/netfilter/nf_queue.h>
+
 MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
 MODULE_DESCRIPTION("Xtables: packet forwarding to netlink");
 MODULE_LICENSE("GPL");
@@ -28,7 +26,6 @@ MODULE_ALIAS("ip6t_NFQUEUE");
 MODULE_ALIAS("arpt_NFQUEUE");
 
 static u32 jhash_initval __read_mostly;
-static bool rnd_inited __read_mostly;
 
 static unsigned int
 nfqueue_tg(struct sk_buff *skb, const struct xt_action_param *par)
@@ -38,69 +35,16 @@ nfqueue_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	return NF_QUEUE_NR(tinfo->queuenum);
 }
 
-static u32 hash_v4(const struct sk_buff *skb)
-{
-	const struct iphdr *iph = ip_hdr(skb);
-
-	/* packets in either direction go into same queue */
-	if ((__force u32)iph->saddr < (__force u32)iph->daddr)
-		return jhash_3words((__force u32)iph->saddr,
-			(__force u32)iph->daddr, iph->protocol, jhash_initval);
-
-	return jhash_3words((__force u32)iph->daddr,
-			(__force u32)iph->saddr, iph->protocol, jhash_initval);
-}
-
-#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
-static u32 hash_v6(const struct sk_buff *skb)
-{
-	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-	u32 a, b, c;
-
-	if ((__force u32)ip6h->saddr.s6_addr32[3] <
-	    (__force u32)ip6h->daddr.s6_addr32[3]) {
-		a = (__force u32) ip6h->saddr.s6_addr32[3];
-		b = (__force u32) ip6h->daddr.s6_addr32[3];
-	} else {
-		b = (__force u32) ip6h->saddr.s6_addr32[3];
-		a = (__force u32) ip6h->daddr.s6_addr32[3];
-	}
-
-	if ((__force u32)ip6h->saddr.s6_addr32[1] <
-	    (__force u32)ip6h->daddr.s6_addr32[1])
-		c = (__force u32) ip6h->saddr.s6_addr32[1];
-	else
-		c = (__force u32) ip6h->daddr.s6_addr32[1];
-
-	return jhash_3words(a, b, c, jhash_initval);
-}
-#endif
-
-static u32
-nfqueue_hash(const struct sk_buff *skb, const struct xt_action_param *par)
-{
-	const struct xt_NFQ_info_v1 *info = par->targinfo;
-	u32 queue = info->queuenum;
-
-	if (par->family == NFPROTO_IPV4)
-		queue += ((u64) hash_v4(skb) * info->queues_total) >> 32;
-#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
-	else if (par->family == NFPROTO_IPV6)
-		queue += ((u64) hash_v6(skb) * info->queues_total) >> 32;
-#endif
-
-	return queue;
-}
-
 static unsigned int
 nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct xt_NFQ_info_v1 *info = par->targinfo;
 	u32 queue = info->queuenum;
 
-	if (info->queues_total > 1)
-		queue = nfqueue_hash(skb, par);
-
+	if (info->queues_total > 1) {
+		queue = nfqueue_hash(skb, queue, info->queues_total,
+				     par->family, jhash_initval);
+	}
 	return NF_QUEUE_NR(queue);
 }
 
@@ -120,10 +64,8 @@ static int nfqueue_tg_check(const struct xt_tgchk_param *par)
 	const struct xt_NFQ_info_v3 *info = par->targinfo;
 	u32 maxid;
 
-	if (unlikely(!rnd_inited)) {
-		get_random_bytes(&jhash_initval, sizeof(jhash_initval));
-		rnd_inited = true;
-	}
+	init_hashrandom(&jhash_initval);
+
 	if (info->queues_total == 0) {
 		pr_err("NFQUEUE: number of total queues is 0\n");
 		return -EINVAL;
@@ -154,8 +96,10 @@ nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par)
 			int cpu = smp_processor_id();
 
 			queue = info->queuenum + cpu % info->queues_total;
-		} else
-			queue = nfqueue_hash(skb, par);
+		} else {
+			queue = nfqueue_hash(skb, queue, info->queues_total,
+					     par->family, jhash_initval);
+		}
 	}
 
 	ret = NF_QUEUE_NR(queue);
diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c
index 12d4da8e6c7..bbffdbdaf60 100644
--- a/net/netfilter/xt_bpf.c
+++ b/net/netfilter/xt_bpf.c
@@ -23,10 +23,11 @@ MODULE_ALIAS("ip6t_bpf");
 static int bpf_mt_check(const struct xt_mtchk_param *par)
 {
 	struct xt_bpf_info *info = par->matchinfo;
-	struct sock_fprog program;
+	struct sock_fprog_kern program;
 
 	program.len = info->bpf_program_num_elem;
-	program.filter = (struct sock_filter __user *) info->bpf_program;
+	program.filter = info->bpf_program;
+
 	if (sk_unattached_filter_create(&info->filter, &program)) {
 		pr_info("bpf: check failed: parse error\n");
 		return -EINVAL;
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
new file mode 100644
index 00000000000..f4e83300532
--- /dev/null
+++ b/net/netfilter/xt_cgroup.c
@@ -0,0 +1,72 @@
+/*
+ * Xtables module to match the process control group.
+ *
+ * Might be used to implement individual "per-application" firewall
+ * policies in contrast to global policies based on control groups.
+ * Matching is based upon processes tagged to net_cls' classid marker.
+ *
+ * (C) 2013 Daniel Borkmann <dborkman@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/skbuff.h>
+#include <linux/module.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_cgroup.h>
+#include <net/sock.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
+MODULE_DESCRIPTION("Xtables: process control group matching");
+MODULE_ALIAS("ipt_cgroup");
+MODULE_ALIAS("ip6t_cgroup");
+
+static int cgroup_mt_check(const struct xt_mtchk_param *par)
+{
+	struct xt_cgroup_info *info = par->matchinfo;
+
+	if (info->invert & ~1)
+		return -EINVAL;
+
+	return info->id ? 0 : -EINVAL;
+}
+
+static bool
+cgroup_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_cgroup_info *info = par->matchinfo;
+
+	if (skb->sk == NULL)
+		return false;
+
+	return (info->id == skb->sk->sk_classid) ^ info->invert;
+}
+
+static struct xt_match cgroup_mt_reg __read_mostly = {
+	.name       = "cgroup",
+	.revision   = 0,
+	.family     = NFPROTO_UNSPEC,
+	.checkentry = cgroup_mt_check,
+	.match      = cgroup_mt,
+	.matchsize  = sizeof(struct xt_cgroup_info),
+	.me         = THIS_MODULE,
+	.hooks      = (1 << NF_INET_LOCAL_OUT) |
+		      (1 << NF_INET_POST_ROUTING) |
+		      (1 << NF_INET_LOCAL_IN),
+};
+
+static int __init cgroup_mt_init(void)
+{
+	return xt_register_match(&cgroup_mt_reg);
+}
+
+static void __exit cgroup_mt_exit(void)
+{
+	xt_unregister_match(&cgroup_mt_reg);
+}
+
+module_init(cgroup_mt_init);
+module_exit(cgroup_mt_exit);
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index c40b2695633..fbc66bb250d 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -19,6 +19,7 @@
 #include <linux/jhash.h>
 #include <linux/slab.h>
 #include <linux/list.h>
+#include <linux/rbtree.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/skbuff.h>
@@ -31,6 +32,16 @@
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 
+#define CONNLIMIT_SLOTS		256U
+
+#ifdef CONFIG_LOCKDEP
+#define CONNLIMIT_LOCK_SLOTS	8U
+#else
+#define CONNLIMIT_LOCK_SLOTS	256U
+#endif
+
+#define CONNLIMIT_GC_MAX_NODES	8
+
 /* we will save the tuples of all connections we care about */
 struct xt_connlimit_conn {
 	struct hlist_node		node;
@@ -38,16 +49,27 @@ struct xt_connlimit_conn {
 	union nf_inet_addr		addr;
 };
 
+struct xt_connlimit_rb {
+	struct rb_node node;
+	struct hlist_head hhead; /* connections/hosts in same subnet */
+	union nf_inet_addr addr; /* search key */
+};
+
+static spinlock_t xt_connlimit_locks[CONNLIMIT_LOCK_SLOTS] __cacheline_aligned_in_smp;
+
 struct xt_connlimit_data {
-	struct hlist_head	iphash[256];
-	spinlock_t		lock;
+	struct rb_root climit_root4[CONNLIMIT_SLOTS];
+	struct rb_root climit_root6[CONNLIMIT_SLOTS];
 };
 
 static u_int32_t connlimit_rnd __read_mostly;
+static struct kmem_cache *connlimit_rb_cachep __read_mostly;
+static struct kmem_cache *connlimit_conn_cachep __read_mostly;
 
 static inline unsigned int connlimit_iphash(__be32 addr)
 {
-	return jhash_1word((__force __u32)addr, connlimit_rnd) & 0xFF;
+	return jhash_1word((__force __u32)addr,
+			    connlimit_rnd) % CONNLIMIT_SLOTS;
 }
 
 static inline unsigned int
@@ -60,7 +82,8 @@ connlimit_iphash6(const union nf_inet_addr *addr,
 	for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i)
 		res.ip6[i] = addr->ip6[i] & mask->ip6[i];
 
-	return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6), connlimit_rnd) & 0xFF;
+	return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6),
+		       connlimit_rnd) % CONNLIMIT_SLOTS;
 }
 
 static inline bool already_closed(const struct nf_conn *conn)
@@ -72,13 +95,14 @@ static inline bool already_closed(const struct nf_conn *conn)
 		return 0;
 }
 
-static inline unsigned int
+static int
 same_source_net(const union nf_inet_addr *addr,
 		const union nf_inet_addr *mask,
 		const union nf_inet_addr *u3, u_int8_t family)
 {
 	if (family == NFPROTO_IPV4) {
-		return (addr->ip & mask->ip) == (u3->ip & mask->ip);
+		return ntohl(addr->ip & mask->ip) -
+		       ntohl(u3->ip & mask->ip);
 	} else {
 		union nf_inet_addr lh, rh;
 		unsigned int i;
@@ -88,89 +112,205 @@ same_source_net(const union nf_inet_addr *addr,
 			rh.ip6[i] = u3->ip6[i] & mask->ip6[i];
 		}
 
-		return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6)) == 0;
+		return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6));
 	}
 }
 
-static int count_them(struct net *net,
-		      struct xt_connlimit_data *data,
+static bool add_hlist(struct hlist_head *head,
 		      const struct nf_conntrack_tuple *tuple,
-		      const union nf_inet_addr *addr,
-		      const union nf_inet_addr *mask,
-		      u_int8_t family)
+		      const union nf_inet_addr *addr)
+{
+	struct xt_connlimit_conn *conn;
+
+	conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC);
+	if (conn == NULL)
+		return false;
+	conn->tuple = *tuple;
+	conn->addr = *addr;
+	hlist_add_head(&conn->node, head);
+	return true;
+}
+
+static unsigned int check_hlist(struct net *net,
+				struct hlist_head *head,
+				const struct nf_conntrack_tuple *tuple,
+				bool *addit)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct xt_connlimit_conn *conn;
 	struct hlist_node *n;
 	struct nf_conn *found_ct;
-	struct hlist_head *hash;
-	bool addit = true;
-	int matches = 0;
-
-	if (family == NFPROTO_IPV6)
-		hash = &data->iphash[connlimit_iphash6(addr, mask)];
-	else
-		hash = &data->iphash[connlimit_iphash(addr->ip & mask->ip)];
+	unsigned int length = 0;
 
+	*addit = true;
 	rcu_read_lock();
 
 	/* check the saved connections */
-	hlist_for_each_entry_safe(conn, n, hash, node) {
+	hlist_for_each_entry_safe(conn, n, head, node) {
 		found    = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE,
 						 &conn->tuple);
-		found_ct = NULL;
+		if (found == NULL) {
+			hlist_del(&conn->node);
+			kmem_cache_free(connlimit_conn_cachep, conn);
+			continue;
+		}
 
-		if (found != NULL)
-			found_ct = nf_ct_tuplehash_to_ctrack(found);
+		found_ct = nf_ct_tuplehash_to_ctrack(found);
 
-		if (found_ct != NULL &&
-		    nf_ct_tuple_equal(&conn->tuple, tuple) &&
-		    !already_closed(found_ct))
+		if (nf_ct_tuple_equal(&conn->tuple, tuple)) {
 			/*
 			 * Just to be sure we have it only once in the list.
 			 * We should not see tuples twice unless someone hooks
 			 * this into a table without "-p tcp --syn".
 			 */
-			addit = false;
-
-		if (found == NULL) {
-			/* this one is gone */
-			hlist_del(&conn->node);
-			kfree(conn);
-			continue;
-		}
-
-		if (already_closed(found_ct)) {
+			*addit = false;
+		} else if (already_closed(found_ct)) {
 			/*
 			 * we do not care about connections which are
 			 * closed already -> ditch it
 			 */
 			nf_ct_put(found_ct);
 			hlist_del(&conn->node);
-			kfree(conn);
+			kmem_cache_free(connlimit_conn_cachep, conn);
 			continue;
 		}
 
-		if (same_source_net(addr, mask, &conn->addr, family))
-			/* same source network -> be counted! */
-			++matches;
 		nf_ct_put(found_ct);
+		length++;
 	}
 
 	rcu_read_unlock();
 
-	if (addit) {
-		/* save the new connection in our list */
-		conn = kmalloc(sizeof(*conn), GFP_ATOMIC);
-		if (conn == NULL)
-			return -ENOMEM;
-		conn->tuple = *tuple;
-		conn->addr = *addr;
-		hlist_add_head(&conn->node, hash);
-		++matches;
+	return length;
+}
+
+static void tree_nodes_free(struct rb_root *root,
+			    struct xt_connlimit_rb *gc_nodes[],
+			    unsigned int gc_count)
+{
+	struct xt_connlimit_rb *rbconn;
+
+	while (gc_count) {
+		rbconn = gc_nodes[--gc_count];
+		rb_erase(&rbconn->node, root);
+		kmem_cache_free(connlimit_rb_cachep, rbconn);
+	}
+}
+
+static unsigned int
+count_tree(struct net *net, struct rb_root *root,
+	   const struct nf_conntrack_tuple *tuple,
+	   const union nf_inet_addr *addr, const union nf_inet_addr *mask,
+	   u8 family)
+{
+	struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES];
+	struct rb_node **rbnode, *parent;
+	struct xt_connlimit_rb *rbconn;
+	struct xt_connlimit_conn *conn;
+	unsigned int gc_count;
+	bool no_gc = false;
+
+ restart:
+	gc_count = 0;
+	parent = NULL;
+	rbnode = &(root->rb_node);
+	while (*rbnode) {
+		int diff;
+		bool addit;
+
+		rbconn = container_of(*rbnode, struct xt_connlimit_rb, node);
+
+		parent = *rbnode;
+		diff = same_source_net(addr, mask, &rbconn->addr, family);
+		if (diff < 0) {
+			rbnode = &((*rbnode)->rb_left);
+		} else if (diff > 0) {
+			rbnode = &((*rbnode)->rb_right);
+		} else {
+			/* same source network -> be counted! */
+			unsigned int count;
+			count = check_hlist(net, &rbconn->hhead, tuple, &addit);
+
+			tree_nodes_free(root, gc_nodes, gc_count);
+			if (!addit)
+				return count;
+
+			if (!add_hlist(&rbconn->hhead, tuple, addr))
+				return 0; /* hotdrop */
+
+			return count + 1;
+		}
+
+		if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
+			continue;
+
+		/* only used for GC on hhead, retval and 'addit' ignored */
+		check_hlist(net, &rbconn->hhead, tuple, &addit);
+		if (hlist_empty(&rbconn->hhead))
+			gc_nodes[gc_count++] = rbconn;
+	}
+
+	if (gc_count) {
+		no_gc = true;
+		tree_nodes_free(root, gc_nodes, gc_count);
+		/* tree_node_free before new allocation permits
+		 * allocator to re-use newly free'd object.
+		 *
+		 * This is a rare event; in most cases we will find
+		 * existing node to re-use. (or gc_count is 0).
+		 */
+		goto restart;
+	}
+
+	/* no match, need to insert new node */
+	rbconn = kmem_cache_alloc(connlimit_rb_cachep, GFP_ATOMIC);
+	if (rbconn == NULL)
+		return 0;
+
+	conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC);
+	if (conn == NULL) {
+		kmem_cache_free(connlimit_rb_cachep, rbconn);
+		return 0;
+	}
+
+	conn->tuple = *tuple;
+	conn->addr = *addr;
+	rbconn->addr = *addr;
+
+	INIT_HLIST_HEAD(&rbconn->hhead);
+	hlist_add_head(&conn->node, &rbconn->hhead);
+
+	rb_link_node(&rbconn->node, parent, rbnode);
+	rb_insert_color(&rbconn->node, root);
+	return 1;
+}
+
+static int count_them(struct net *net,
+		      struct xt_connlimit_data *data,
+		      const struct nf_conntrack_tuple *tuple,
+		      const union nf_inet_addr *addr,
+		      const union nf_inet_addr *mask,
+		      u_int8_t family)
+{
+	struct rb_root *root;
+	int count;
+	u32 hash;
+
+	if (family == NFPROTO_IPV6) {
+		hash = connlimit_iphash6(addr, mask);
+		root = &data->climit_root6[hash];
+	} else {
+		hash = connlimit_iphash(addr->ip & mask->ip);
+		root = &data->climit_root4[hash];
 	}
 
-	return matches;
+	spin_lock_bh(&xt_connlimit_locks[hash % CONNLIMIT_LOCK_SLOTS]);
+
+	count = count_tree(net, root, tuple, addr, mask, family);
+
+	spin_unlock_bh(&xt_connlimit_locks[hash % CONNLIMIT_LOCK_SLOTS]);
+
+	return count;
 }
 
 static bool
@@ -183,7 +323,7 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	const struct nf_conntrack_tuple *tuple_ptr = &tuple;
 	enum ip_conntrack_info ctinfo;
 	const struct nf_conn *ct;
-	int connections;
+	unsigned int connections;
 
 	ct = nf_ct_get(skb, &ctinfo);
 	if (ct != NULL)
@@ -202,12 +342,9 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
 			  iph->daddr : iph->saddr;
 	}
 
-	spin_lock_bh(&info->data->lock);
 	connections = count_them(net, info->data, tuple_ptr, &addr,
 	                         &info->mask, par->family);
-	spin_unlock_bh(&info->data->lock);
-
-	if (connections < 0)
+	if (connections == 0)
 		/* kmalloc failed, drop it entirely */
 		goto hotdrop;
 
@@ -247,29 +384,44 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par)
 		return -ENOMEM;
 	}
 
-	spin_lock_init(&info->data->lock);
-	for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i)
-		INIT_HLIST_HEAD(&info->data->iphash[i]);
+	for (i = 0; i < ARRAY_SIZE(info->data->climit_root4); ++i)
+		info->data->climit_root4[i] = RB_ROOT;
+	for (i = 0; i < ARRAY_SIZE(info->data->climit_root6); ++i)
+		info->data->climit_root6[i] = RB_ROOT;
 
 	return 0;
 }
 
-static void connlimit_mt_destroy(const struct xt_mtdtor_param *par)
+static void destroy_tree(struct rb_root *r)
 {
-	const struct xt_connlimit_info *info = par->matchinfo;
 	struct xt_connlimit_conn *conn;
+	struct xt_connlimit_rb *rbconn;
 	struct hlist_node *n;
-	struct hlist_head *hash = info->data->iphash;
+	struct rb_node *node;
+
+	while ((node = rb_first(r)) != NULL) {
+		rbconn = container_of(node, struct xt_connlimit_rb, node);
+
+		rb_erase(node, r);
+
+		hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node)
+			kmem_cache_free(connlimit_conn_cachep, conn);
+
+		kmem_cache_free(connlimit_rb_cachep, rbconn);
+	}
+}
+
+static void connlimit_mt_destroy(const struct xt_mtdtor_param *par)
+{
+	const struct xt_connlimit_info *info = par->matchinfo;
 	unsigned int i;
 
 	nf_ct_l3proto_module_put(par->family);
 
-	for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) {
-		hlist_for_each_entry_safe(conn, n, &hash[i], node) {
-			hlist_del(&conn->node);
-			kfree(conn);
-		}
-	}
+	for (i = 0; i < ARRAY_SIZE(info->data->climit_root4); ++i)
+		destroy_tree(&info->data->climit_root4[i]);
+	for (i = 0; i < ARRAY_SIZE(info->data->climit_root6); ++i)
+		destroy_tree(&info->data->climit_root6[i]);
 
 	kfree(info->data);
 }
@@ -287,12 +439,40 @@ static struct xt_match connlimit_mt_reg __read_mostly = {
 
 static int __init connlimit_mt_init(void)
 {
-	return xt_register_match(&connlimit_mt_reg);
+	int ret, i;
+
+	BUILD_BUG_ON(CONNLIMIT_LOCK_SLOTS > CONNLIMIT_SLOTS);
+	BUILD_BUG_ON((CONNLIMIT_SLOTS % CONNLIMIT_LOCK_SLOTS) != 0);
+
+	for (i = 0; i < CONNLIMIT_LOCK_SLOTS; ++i)
+		spin_lock_init(&xt_connlimit_locks[i]);
+
+	connlimit_conn_cachep = kmem_cache_create("xt_connlimit_conn",
+					   sizeof(struct xt_connlimit_conn),
+					   0, 0, NULL);
+	if (!connlimit_conn_cachep)
+		return -ENOMEM;
+
+	connlimit_rb_cachep = kmem_cache_create("xt_connlimit_rb",
+					   sizeof(struct xt_connlimit_rb),
+					   0, 0, NULL);
+	if (!connlimit_rb_cachep) {
+		kmem_cache_destroy(connlimit_conn_cachep);
+		return -ENOMEM;
+	}
+	ret = xt_register_match(&connlimit_mt_reg);
+	if (ret != 0) {
+		kmem_cache_destroy(connlimit_conn_cachep);
+		kmem_cache_destroy(connlimit_rb_cachep);
+	}
+	return ret;
 }
 
 static void __exit connlimit_mt_exit(void)
 {
 	xt_unregister_match(&connlimit_mt_reg);
+	kmem_cache_destroy(connlimit_conn_cachep);
+	kmem_cache_destroy(connlimit_rb_cachep);
 }
 
 module_init(connlimit_mt_init);
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 9ff035c7140..a3910fc2122 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -325,21 +325,24 @@ static void htable_gc(unsigned long htlong)
 	add_timer(&ht->timer);
 }
 
-static void htable_destroy(struct xt_hashlimit_htable *hinfo)
+static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo)
 {
 	struct hashlimit_net *hashlimit_net = hashlimit_pernet(hinfo->net);
 	struct proc_dir_entry *parent;
 
-	del_timer_sync(&hinfo->timer);
-
 	if (hinfo->family == NFPROTO_IPV4)
 		parent = hashlimit_net->ipt_hashlimit;
 	else
 		parent = hashlimit_net->ip6t_hashlimit;
 
-	if(parent != NULL)
+	if (parent != NULL)
 		remove_proc_entry(hinfo->name, parent);
+}
 
+static void htable_destroy(struct xt_hashlimit_htable *hinfo)
+{
+	del_timer_sync(&hinfo->timer);
+	htable_remove_proc_entry(hinfo);
 	htable_selective_cleanup(hinfo, select_all);
 	kfree(hinfo->name);
 	vfree(hinfo);
@@ -883,21 +886,15 @@ static int __net_init hashlimit_proc_net_init(struct net *net)
 static void __net_exit hashlimit_proc_net_exit(struct net *net)
 {
 	struct xt_hashlimit_htable *hinfo;
-	struct proc_dir_entry *pde;
 	struct hashlimit_net *hashlimit_net = hashlimit_pernet(net);
 
-	/* recent_net_exit() is called before recent_mt_destroy(). Make sure
-	 * that the parent xt_recent proc entry is is empty before trying to
-	 * remove it.
+	/* hashlimit_net_exit() is called before hashlimit_mt_destroy().
+	 * Make sure that the parent ipt_hashlimit and ip6t_hashlimit proc
+	 * entries is empty before trying to remove it.
 	 */
 	mutex_lock(&hashlimit_mutex);
-	pde = hashlimit_net->ipt_hashlimit;
-	if (pde == NULL)
-		pde = hashlimit_net->ip6t_hashlimit;
-
 	hlist_for_each_entry(hinfo, &hashlimit_net->htables, node)
-		remove_proc_entry(hinfo->name, pde);
-
+		htable_remove_proc_entry(hinfo);
 	hashlimit_net->ipt_hashlimit = NULL;
 	hashlimit_net->ip6t_hashlimit = NULL;
 	mutex_unlock(&hashlimit_mutex);
diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c
new file mode 100644
index 00000000000..89d53104c6b
--- /dev/null
+++ b/net/netfilter/xt_ipcomp.c
@@ -0,0 +1,111 @@
+/*  Kernel module to match IPComp parameters for IPv4 and IPv6
+ *
+ *  Copyright (C) 2013 WindRiver
+ *
+ *  Author:
+ *  Fan Du <fan.du@windriver.com>
+ *
+ *  Based on:
+ *  net/netfilter/xt_esp.c
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+
+#include <linux/netfilter/xt_ipcomp.h>
+#include <linux/netfilter/x_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Fan Du <fan.du@windriver.com>");
+MODULE_DESCRIPTION("Xtables: IPv4/6 IPsec-IPComp SPI match");
+
+/* Returns 1 if the spi is matched by the range, 0 otherwise */
+static inline bool
+spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert)
+{
+	bool r;
+	pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n",
+		 invert ? '!' : ' ', min, spi, max);
+	r = (spi >= min && spi <= max) ^ invert;
+	pr_debug(" result %s\n", r ? "PASS" : "FAILED");
+	return r;
+}
+
+static bool comp_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct ip_comp_hdr _comphdr;
+	const struct ip_comp_hdr *chdr;
+	const struct xt_ipcomp *compinfo = par->matchinfo;
+
+	/* Must not be a fragment. */
+	if (par->fragoff != 0)
+		return false;
+
+	chdr = skb_header_pointer(skb, par->thoff, sizeof(_comphdr), &_comphdr);
+	if (chdr == NULL) {
+		/* We've been asked to examine this packet, and we
+		 * can't.  Hence, no choice but to drop.
+		 */
+		pr_debug("Dropping evil IPComp tinygram.\n");
+		par->hotdrop = true;
+		return 0;
+	}
+
+	return spi_match(compinfo->spis[0], compinfo->spis[1],
+			 ntohs(chdr->cpi),
+			 !!(compinfo->invflags & XT_IPCOMP_INV_SPI));
+}
+
+static int comp_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct xt_ipcomp *compinfo = par->matchinfo;
+
+	/* Must specify no unknown invflags */
+	if (compinfo->invflags & ~XT_IPCOMP_INV_MASK) {
+		pr_err("unknown flags %X\n", compinfo->invflags);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct xt_match comp_mt_reg[] __read_mostly = {
+	{
+		.name		= "ipcomp",
+		.family		= NFPROTO_IPV4,
+		.match		= comp_mt,
+		.matchsize	= sizeof(struct xt_ipcomp),
+		.proto		= IPPROTO_COMP,
+		.checkentry	= comp_mt_check,
+		.me		= THIS_MODULE,
+	},
+	{
+		.name		= "ipcomp",
+		.family		= NFPROTO_IPV6,
+		.match		= comp_mt,
+		.matchsize	= sizeof(struct xt_ipcomp),
+		.proto		= IPPROTO_COMP,
+		.checkentry	= comp_mt_check,
+		.me		= THIS_MODULE,
+	},
+};
+
+static int __init comp_mt_init(void)
+{
+	return xt_register_matches(comp_mt_reg, ARRAY_SIZE(comp_mt_reg));
+}
+
+static void __exit comp_mt_exit(void)
+{
+	xt_unregister_matches(comp_mt_reg, ARRAY_SIZE(comp_mt_reg));
+}
+
+module_init(comp_mt_init);
+module_exit(comp_mt_exit);
diff --git a/net/netfilter/xt_l2tp.c b/net/netfilter/xt_l2tp.c
new file mode 100644
index 00000000000..8aee572771f
--- /dev/null
+++ b/net/netfilter/xt_l2tp.c
@@ -0,0 +1,354 @@
+/* Kernel module to match L2TP header parameters. */
+
+/* (C) 2013      James Chapman <jchapman@katalix.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/if_ether.h>
+#include <net/ip.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+#include <net/udp.h>
+#include <linux/l2tp.h>
+
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_tcpudp.h>
+#include <linux/netfilter/xt_l2tp.h>
+
+/* L2TP header masks */
+#define L2TP_HDR_T_BIT	0x8000
+#define L2TP_HDR_L_BIT	0x4000
+#define L2TP_HDR_VER	0x000f
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("James Chapman <jchapman@katalix.com>");
+MODULE_DESCRIPTION("Xtables: L2TP header match");
+MODULE_ALIAS("ipt_l2tp");
+MODULE_ALIAS("ip6t_l2tp");
+
+/* The L2TP fields that can be matched */
+struct l2tp_data {
+	u32 tid;
+	u32 sid;
+	u8 type;
+	u8 version;
+};
+
+union l2tp_val {
+	__be16 val16[2];
+	__be32 val32;
+};
+
+static bool l2tp_match(const struct xt_l2tp_info *info, struct l2tp_data *data)
+{
+	if ((info->flags & XT_L2TP_TYPE) && (info->type != data->type))
+		return false;
+
+	if ((info->flags & XT_L2TP_VERSION) && (info->version != data->version))
+		return false;
+
+	/* Check tid only for L2TPv3 control or any L2TPv2 packets */
+	if ((info->flags & XT_L2TP_TID) &&
+	    ((data->type == XT_L2TP_TYPE_CONTROL) || (data->version == 2)) &&
+	    (info->tid != data->tid))
+		return false;
+
+	/* Check sid only for L2TP data packets */
+	if ((info->flags & XT_L2TP_SID) && (data->type == XT_L2TP_TYPE_DATA) &&
+	    (info->sid != data->sid))
+		return false;
+
+	return true;
+}
+
+/* Parse L2TP header fields when UDP encapsulation is used. Handles
+ * L2TPv2 and L2TPv3. Note the L2TPv3 control and data packets have a
+ * different format. See
+ * RFC2661, Section 3.1, L2TPv2 Header Format
+ * RFC3931, Section 3.2.1, L2TPv3 Control Message Header
+ * RFC3931, Section 3.2.2, L2TPv3 Data Message Header
+ * RFC3931, Section 4.1.2.1, L2TPv3 Session Header over UDP
+ */
+static bool l2tp_udp_mt(const struct sk_buff *skb, struct xt_action_param *par, u16 thoff)
+{
+	const struct xt_l2tp_info *info = par->matchinfo;
+	int uhlen = sizeof(struct udphdr);
+	int offs = thoff + uhlen;
+	union l2tp_val *lh;
+	union l2tp_val lhbuf;
+	u16 flags;
+	struct l2tp_data data = { 0, };
+
+	if (par->fragoff != 0)
+		return false;
+
+	/* Extract L2TP header fields. The flags in the first 16 bits
+	 * tell us where the other fields are.
+	 */
+	lh = skb_header_pointer(skb, offs, 2, &lhbuf);
+	if (lh == NULL)
+		return false;
+
+	flags = ntohs(lh->val16[0]);
+	if (flags & L2TP_HDR_T_BIT)
+		data.type = XT_L2TP_TYPE_CONTROL;
+	else
+		data.type = XT_L2TP_TYPE_DATA;
+	data.version = (u8) flags & L2TP_HDR_VER;
+
+	/* Now extract the L2TP tid/sid. These are in different places
+	 * for L2TPv2 (rfc2661) and L2TPv3 (rfc3931). For L2TPv2, we
+	 * must also check to see if the length field is present,
+	 * since this affects the offsets into the packet of the
+	 * tid/sid fields.
+	 */
+	if (data.version == 3) {
+		lh = skb_header_pointer(skb, offs + 4, 4, &lhbuf);
+		if (lh == NULL)
+			return false;
+		if (data.type == XT_L2TP_TYPE_CONTROL)
+			data.tid = ntohl(lh->val32);
+		else
+			data.sid = ntohl(lh->val32);
+	} else if (data.version == 2) {
+		if (flags & L2TP_HDR_L_BIT)
+			offs += 2;
+		lh = skb_header_pointer(skb, offs + 2, 4, &lhbuf);
+		if (lh == NULL)
+			return false;
+		data.tid = (u32) ntohs(lh->val16[0]);
+		data.sid = (u32) ntohs(lh->val16[1]);
+	} else
+		return false;
+
+	return l2tp_match(info, &data);
+}
+
+/* Parse L2TP header fields for IP encapsulation (no UDP header).
+ * L2TPv3 data packets have a different form with IP encap. See
+ * RC3931, Section 4.1.1.1, L2TPv3 Session Header over IP.
+ * RC3931, Section 4.1.1.2, L2TPv3 Control and Data Traffic over IP.
+ */
+static bool l2tp_ip_mt(const struct sk_buff *skb, struct xt_action_param *par, u16 thoff)
+{
+	const struct xt_l2tp_info *info = par->matchinfo;
+	union l2tp_val *lh;
+	union l2tp_val lhbuf;
+	struct l2tp_data data = { 0, };
+
+	/* For IP encap, the L2TP sid is the first 32-bits. */
+	lh = skb_header_pointer(skb, thoff, sizeof(lhbuf), &lhbuf);
+	if (lh == NULL)
+		return false;
+	if (lh->val32 == 0) {
+		/* Must be a control packet. The L2TP tid is further
+		 * into the packet.
+		 */
+		data.type = XT_L2TP_TYPE_CONTROL;
+		lh = skb_header_pointer(skb, thoff + 8, sizeof(lhbuf),
+					&lhbuf);
+		if (lh == NULL)
+			return false;
+		data.tid = ntohl(lh->val32);
+	} else {
+		data.sid = ntohl(lh->val32);
+		data.type = XT_L2TP_TYPE_DATA;
+	}
+
+	data.version = 3;
+
+	return l2tp_match(info, &data);
+}
+
+static bool l2tp_mt4(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct iphdr *iph = ip_hdr(skb);
+	u8 ipproto = iph->protocol;
+
+	/* l2tp_mt_check4 already restricts the transport protocol */
+	switch (ipproto) {
+	case IPPROTO_UDP:
+		return l2tp_udp_mt(skb, par, par->thoff);
+	case IPPROTO_L2TP:
+		return l2tp_ip_mt(skb, par, par->thoff);
+	}
+
+	return false;
+}
+
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
+static bool l2tp_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	unsigned int thoff = 0;
+	unsigned short fragoff = 0;
+	int ipproto;
+
+	ipproto = ipv6_find_hdr(skb, &thoff, -1, &fragoff, NULL);
+	if (fragoff != 0)
+		return false;
+
+	/* l2tp_mt_check6 already restricts the transport protocol */
+	switch (ipproto) {
+	case IPPROTO_UDP:
+		return l2tp_udp_mt(skb, par, thoff);
+	case IPPROTO_L2TP:
+		return l2tp_ip_mt(skb, par, thoff);
+	}
+
+	return false;
+}
+#endif
+
+static int l2tp_mt_check(const struct xt_mtchk_param *par)
+{
+	const struct xt_l2tp_info *info = par->matchinfo;
+
+	/* Check for invalid flags */
+	if (info->flags & ~(XT_L2TP_TID | XT_L2TP_SID | XT_L2TP_VERSION |
+			    XT_L2TP_TYPE)) {
+		pr_info("unknown flags: %x\n", info->flags);
+		return -EINVAL;
+	}
+
+	/* At least one of tid, sid or type=control must be specified */
+	if ((!(info->flags & XT_L2TP_TID)) &&
+	    (!(info->flags & XT_L2TP_SID)) &&
+	    ((!(info->flags & XT_L2TP_TYPE)) ||
+	     (info->type != XT_L2TP_TYPE_CONTROL))) {
+		pr_info("invalid flags combination: %x\n", info->flags);
+		return -EINVAL;
+	}
+
+	/* If version 2 is specified, check that incompatible params
+	 * are not supplied
+	 */
+	if (info->flags & XT_L2TP_VERSION) {
+		if ((info->version < 2) || (info->version > 3)) {
+			pr_info("wrong L2TP version: %u\n", info->version);
+			return -EINVAL;
+		}
+
+		if (info->version == 2) {
+			if ((info->flags & XT_L2TP_TID) &&
+			    (info->tid > 0xffff)) {
+				pr_info("v2 tid > 0xffff: %u\n", info->tid);
+				return -EINVAL;
+			}
+			if ((info->flags & XT_L2TP_SID) &&
+			    (info->sid > 0xffff)) {
+				pr_info("v2 sid > 0xffff: %u\n", info->sid);
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int l2tp_mt_check4(const struct xt_mtchk_param *par)
+{
+	const struct xt_l2tp_info *info = par->matchinfo;
+	const struct ipt_entry *e = par->entryinfo;
+	const struct ipt_ip *ip = &e->ip;
+	int ret;
+
+	ret = l2tp_mt_check(par);
+	if (ret != 0)
+		return ret;
+
+	if ((ip->proto != IPPROTO_UDP) &&
+	    (ip->proto != IPPROTO_L2TP)) {
+		pr_info("missing protocol rule (udp|l2tpip)\n");
+		return -EINVAL;
+	}
+
+	if ((ip->proto == IPPROTO_L2TP) &&
+	    (info->version == 2)) {
+		pr_info("v2 doesn't support IP mode\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
+static int l2tp_mt_check6(const struct xt_mtchk_param *par)
+{
+	const struct xt_l2tp_info *info = par->matchinfo;
+	const struct ip6t_entry *e = par->entryinfo;
+	const struct ip6t_ip6 *ip = &e->ipv6;
+	int ret;
+
+	ret = l2tp_mt_check(par);
+	if (ret != 0)
+		return ret;
+
+	if ((ip->proto != IPPROTO_UDP) &&
+	    (ip->proto != IPPROTO_L2TP)) {
+		pr_info("missing protocol rule (udp|l2tpip)\n");
+		return -EINVAL;
+	}
+
+	if ((ip->proto == IPPROTO_L2TP) &&
+	    (info->version == 2)) {
+		pr_info("v2 doesn't support IP mode\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+#endif
+
+static struct xt_match l2tp_mt_reg[] __read_mostly = {
+	{
+		.name      = "l2tp",
+		.revision  = 0,
+		.family    = NFPROTO_IPV4,
+		.match     = l2tp_mt4,
+		.matchsize = XT_ALIGN(sizeof(struct xt_l2tp_info)),
+		.checkentry = l2tp_mt_check4,
+		.hooks     = ((1 << NF_INET_PRE_ROUTING) |
+			      (1 << NF_INET_LOCAL_IN) |
+			      (1 << NF_INET_LOCAL_OUT) |
+			      (1 << NF_INET_FORWARD)),
+		.me        = THIS_MODULE,
+	},
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
+	{
+		.name      = "l2tp",
+		.revision  = 0,
+		.family    = NFPROTO_IPV6,
+		.match     = l2tp_mt6,
+		.matchsize = XT_ALIGN(sizeof(struct xt_l2tp_info)),
+		.checkentry = l2tp_mt_check6,
+		.hooks     = ((1 << NF_INET_PRE_ROUTING) |
+			      (1 << NF_INET_LOCAL_IN) |
+			      (1 << NF_INET_LOCAL_OUT) |
+			      (1 << NF_INET_FORWARD)),
+		.me        = THIS_MODULE,
+	},
+#endif
+};
+
+static int __init l2tp_mt_init(void)
+{
+	return xt_register_matches(&l2tp_mt_reg[0], ARRAY_SIZE(l2tp_mt_reg));
+}
+
+static void __exit l2tp_mt_exit(void)
+{
+	xt_unregister_matches(&l2tp_mt_reg[0], ARRAY_SIZE(l2tp_mt_reg));
+}
+
+module_init(l2tp_mt_init);
+module_exit(l2tp_mt_exit);
diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c
index b3be0ef21f1..8c646ed9c92 100644
--- a/net/netfilter/xt_nfacct.c
+++ b/net/netfilter/xt_nfacct.c
@@ -21,11 +21,14 @@ MODULE_ALIAS("ip6t_nfacct");
 
 static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
+	int overquota;
 	const struct xt_nfacct_match_info *info = par->targinfo;
 
 	nfnl_acct_update(skb, info->nfacct);
 
-	return true;
+	overquota = nfnl_acct_overquota(skb, info->nfacct);
+
+	return overquota == NFACCT_UNDERQUOTA ? false : true;
 }
 
 static int
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index 7174611bd67..c529161cdbf 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -422,4 +422,6 @@ module_exit(xt_osf_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Evgeniy Polyakov <zbr@ioremap.net>");
 MODULE_DESCRIPTION("Passive OS fingerprint matching.");
+MODULE_ALIAS("ipt_osf");
+MODULE_ALIAS("ip6t_osf");
 MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF);
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 1e657cf715c..a9faae89f95 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -313,10 +313,7 @@ out:
 
 static void recent_table_free(void *addr)
 {
-	if (is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
+	kvfree(addr);
 }
 
 static int recent_mt_check(const struct xt_mtchk_param *par,
diff --git a/net/netfilter/xt_repldata.h b/net/netfilter/xt_repldata.h
index 6efe4e5a81c..8fd324116e6 100644
--- a/net/netfilter/xt_repldata.h
+++ b/net/netfilter/xt_repldata.h
@@ -5,23 +5,35 @@
  * they serve as the hanging-off data accessed through repl.data[].
  */
 
+/* tbl has the following structure equivalent, but is C99 compliant:
+ * struct {
+ *	struct type##_replace repl;
+ *	struct type##_standard entries[nhooks];
+ *	struct type##_error term;
+ * } *tbl;
+ */
+
 #define xt_alloc_initial_table(type, typ2) ({ \
 	unsigned int hook_mask = info->valid_hooks; \
 	unsigned int nhooks = hweight32(hook_mask); \
 	unsigned int bytes = 0, hooknum = 0, i = 0; \
 	struct { \
 		struct type##_replace repl; \
-		struct type##_standard entries[nhooks]; \
-		struct type##_error term; \
-	} *tbl = kzalloc(sizeof(*tbl), GFP_KERNEL); \
+		struct type##_standard entries[]; \
+	} *tbl; \
+	struct type##_error *term; \
+	size_t term_offset = (offsetof(typeof(*tbl), entries[nhooks]) + \
+		__alignof__(*term) - 1) & ~(__alignof__(*term) - 1); \
+	tbl = kzalloc(term_offset + sizeof(*term), GFP_KERNEL); \
 	if (tbl == NULL) \
 		return NULL; \
+	term = (struct type##_error *)&(((char *)tbl)[term_offset]); \
 	strncpy(tbl->repl.name, info->name, sizeof(tbl->repl.name)); \
-	tbl->term = (struct type##_error)typ2##_ERROR_INIT;  \
+	*term = (struct type##_error)typ2##_ERROR_INIT;  \
 	tbl->repl.valid_hooks = hook_mask; \
 	tbl->repl.num_entries = nhooks + 1; \
 	tbl->repl.size = nhooks * sizeof(struct type##_standard) + \
-	                 sizeof(struct type##_error); \
+			 sizeof(struct type##_error); \
 	for (; hook_mask != 0; hook_mask >>= 1, ++hooknum) { \
 		if (!(hook_mask & 1)) \
 			continue; \
diff --git a/net/netfilter/xt_statistic.c b/net/netfilter/xt_statistic.c
index 4fe4fb4276d..11de55e7a86 100644
--- a/net/netfilter/xt_statistic.c
+++ b/net/netfilter/xt_statistic.c
@@ -37,7 +37,7 @@ statistic_mt(const struct sk_buff *skb, struct xt_action_param *par)
 
 	switch (info->mode) {
 	case XT_STATISTIC_MODE_RANDOM:
-		if ((net_random() & 0x7FFFFFFF) < info->u.random.probability)
+		if ((prandom_u32() & 0x7FFFFFFF) < info->u.random.probability)
 			ret = !ret;
 		break;
 	case XT_STATISTIC_MODE_NTH:
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index bca50b95c18..e6fac7e3db5 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -131,7 +131,7 @@ int netlink_add_tap(struct netlink_tap *nt)
 }
 EXPORT_SYMBOL_GPL(netlink_add_tap);
 
-int __netlink_remove_tap(struct netlink_tap *nt)
+static int __netlink_remove_tap(struct netlink_tap *nt)
 {
 	bool found = false;
 	struct netlink_tap *tmp;
@@ -155,7 +155,6 @@ out:
 
 	return found ? 0 : -ENODEV;
 }
-EXPORT_SYMBOL_GPL(__netlink_remove_tap);
 
 int netlink_remove_tap(struct netlink_tap *nt)
 {
@@ -204,6 +203,8 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	if (nskb) {
 		nskb->dev = dev;
 		nskb->protocol = htons((u16) sk->sk_protocol);
+		nskb->pkt_type = netlink_is_kernel(sk) ?
+				 PACKET_KERNEL : PACKET_USER;
 
 		ret = dev_queue_xmit(nskb);
 		if (unlikely(ret > 0))
@@ -239,6 +240,13 @@ static void netlink_deliver_tap(struct sk_buff *skb)
 	rcu_read_unlock();
 }
 
+static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src,
+				       struct sk_buff *skb)
+{
+	if (!(netlink_is_kernel(dst) && netlink_is_kernel(src)))
+		netlink_deliver_tap(skb);
+}
+
 static void netlink_overrun(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -628,7 +636,7 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock,
 		while (nlk->cb_running && netlink_dump_space(nlk)) {
 			err = netlink_dump(sk);
 			if (err < 0) {
-				sk->sk_err = err;
+				sk->sk_err = -err;
 				sk->sk_error_report(sk);
 				break;
 			}
@@ -1198,7 +1206,8 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	struct module *module = NULL;
 	struct mutex *cb_mutex;
 	struct netlink_sock *nlk;
-	void (*bind)(int group);
+	int (*bind)(int group);
+	void (*unbind)(int group);
 	int err = 0;
 
 	sock->state = SS_UNCONNECTED;
@@ -1224,6 +1233,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 		err = -EPROTONOSUPPORT;
 	cb_mutex = nl_table[protocol].cb_mutex;
 	bind = nl_table[protocol].bind;
+	unbind = nl_table[protocol].unbind;
 	netlink_unlock_table();
 
 	if (err < 0)
@@ -1240,6 +1250,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	nlk = nlk_sk(sock->sk);
 	nlk->module = module;
 	nlk->netlink_bind = bind;
+	nlk->netlink_unbind = unbind;
 out:
 	return err;
 
@@ -1293,6 +1304,7 @@ static int netlink_release(struct socket *sock)
 			kfree_rcu(old, rcu);
 			nl_table[sk->sk_protocol].module = NULL;
 			nl_table[sk->sk_protocol].bind = NULL;
+			nl_table[sk->sk_protocol].unbind = NULL;
 			nl_table[sk->sk_protocol].flags = 0;
 			nl_table[sk->sk_protocol].registered = 0;
 		}
@@ -1352,7 +1364,74 @@ retry:
 	return err;
 }
 
-static inline int netlink_capable(const struct socket *sock, unsigned int flag)
+/**
+ * __netlink_ns_capable - General netlink message capability test
+ * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace.
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+			struct user_namespace *user_ns, int cap)
+{
+	return ((nsp->flags & NETLINK_SKB_DST) ||
+		file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
+		ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(__netlink_ns_capable);
+
+/**
+ * netlink_ns_capable - General netlink message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool netlink_ns_capable(const struct sk_buff *skb,
+			struct user_namespace *user_ns, int cap)
+{
+	return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_ns_capable);
+
+/**
+ * netlink_capable - Netlink global message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in all user namespaces.
+ */
+bool netlink_capable(const struct sk_buff *skb, int cap)
+{
+	return netlink_ns_capable(skb, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_capable);
+
+/**
+ * netlink_net_capable - Netlink network namespace message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap over the network namespace of
+ * the socket we received the message from.
+ */
+bool netlink_net_capable(const struct sk_buff *skb, int cap)
+{
+	return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_net_capable);
+
+static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
 {
 	return (nl_table[sock->sk->sk_protocol].flags & flag) ||
 		ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
@@ -1403,6 +1482,19 @@ static int netlink_realloc_groups(struct sock *sk)
 	return err;
 }
 
+static void netlink_unbind(int group, long unsigned int groups,
+			   struct netlink_sock *nlk)
+{
+	int undo;
+
+	if (!nlk->netlink_unbind)
+		return;
+
+	for (undo = 0; undo < group; undo++)
+		if (test_bit(group, &groups))
+			nlk->netlink_unbind(undo);
+}
+
 static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			int addr_len)
 {
@@ -1411,6 +1503,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err;
+	long unsigned int groups = nladdr->nl_groups;
 
 	if (addr_len < sizeof(struct sockaddr_nl))
 		return -EINVAL;
@@ -1419,45 +1512,53 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		return -EINVAL;
 
 	/* Only superuser is allowed to listen multicasts */
-	if (nladdr->nl_groups) {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+	if (groups) {
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)
 			return err;
 	}
 
-	if (nlk->portid) {
+	if (nlk->portid)
 		if (nladdr->nl_pid != nlk->portid)
 			return -EINVAL;
-	} else {
+
+	if (nlk->netlink_bind && groups) {
+		int group;
+
+		for (group = 0; group < nlk->ngroups; group++) {
+			if (!test_bit(group, &groups))
+				continue;
+			err = nlk->netlink_bind(group);
+			if (!err)
+				continue;
+			netlink_unbind(group, groups, nlk);
+			return err;
+		}
+	}
+
+	if (!nlk->portid) {
 		err = nladdr->nl_pid ?
 			netlink_insert(sk, net, nladdr->nl_pid) :
 			netlink_autobind(sock);
-		if (err)
+		if (err) {
+			netlink_unbind(nlk->ngroups - 1, groups, nlk);
 			return err;
+		}
 	}
 
-	if (!nladdr->nl_groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
+	if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
 		return 0;
 
 	netlink_table_grab();
 	netlink_update_subscriptions(sk, nlk->subscriptions +
-					 hweight32(nladdr->nl_groups) -
+					 hweight32(groups) -
 					 hweight32(nlk->groups[0]));
-	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups;
+	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups;
 	netlink_update_listeners(sk);
 	netlink_table_ungrab();
 
-	if (nlk->netlink_bind && nlk->groups[0]) {
-		int i;
-
-		for (i=0; i<nlk->ngroups; i++) {
-			if (test_bit(i, nlk->groups))
-				nlk->netlink_bind(i);
-		}
-	}
-
 	return 0;
 }
 
@@ -1481,8 +1582,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	if (addr->sa_family != AF_NETLINK)
 		return -EINVAL;
 
-	/* Only superuser is allowed to send multicasts */
-	if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+	if ((nladdr->nl_groups || nladdr->nl_pid) &&
+	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
 	if (!nlk->portid)
@@ -1645,7 +1746,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 	else
 #endif /* CONFIG_NETLINK_MMAP */
 		skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, len);
+	sk->sk_data_ready(sk);
 	return len;
 }
 
@@ -1697,14 +1798,10 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
 
 	ret = -ECONNREFUSED;
 	if (nlk->netlink_rcv != NULL) {
-		/* We could do a netlink_deliver_tap(skb) here as well
-		 * but since this is intended for the kernel only, we
-		 * should rather let it stay under the hood.
-		 */
-
 		ret = skb->len;
 		netlink_skb_set_owner_r(skb, sk);
 		NETLINK_CB(skb).sk = ssk;
+		netlink_deliver_tap_kernel(sk, ssk, skb);
 		nlk->netlink_rcv(skb);
 		consume_skb(skb);
 	} else {
@@ -1769,6 +1866,9 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
 	if (ring->pg_vec == NULL)
 		goto out_put;
 
+	if (ring->frame_size - NL_MMAP_HDRLEN < size)
+		goto out_put;
+
 	skb = alloc_skb_head(gfp_mask);
 	if (skb == NULL)
 		goto err1;
@@ -1778,6 +1878,7 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
 	if (ring->pg_vec == NULL)
 		goto out_free;
 
+	/* check again under lock */
 	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
 	if (maxlen < size)
 		goto out_free;
@@ -2088,20 +2189,24 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
 	case NETLINK_DROP_MEMBERSHIP: {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)
 			return err;
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
+		if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) {
+			err = nlk->netlink_bind(val);
+			if (err)
+				return err;
+		}
 		netlink_table_grab();
 		netlink_update_socket_mc(nlk, val,
 					 optname == NETLINK_ADD_MEMBERSHIP);
 		netlink_table_ungrab();
-
-		if (nlk->netlink_bind)
-			nlk->netlink_bind(val);
+		if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind)
+			nlk->netlink_unbind(val);
 
 		err = 0;
 		break;
@@ -2214,12 +2319,13 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
-	struct sockaddr_nl *addr = msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
 	u32 dst_portid;
 	u32 dst_group;
 	struct sk_buff *skb;
 	int err;
 	struct scm_cookie scm;
+	u32 netlink_skb_flags = 0;
 
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;
@@ -2239,8 +2345,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		dst_group = ffs(addr->nl_groups);
 		err =  -EPERM;
 		if ((dst_group || dst_portid) &&
-		    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+		    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 			goto out;
+		netlink_skb_flags |= NETLINK_SKB_DST;
 	} else {
 		dst_portid = nlk->dst_portid;
 		dst_group = nlk->dst_group;
@@ -2270,6 +2377,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	NETLINK_CB(skb).portid	= nlk->portid;
 	NETLINK_CB(skb).dst_group = dst_group;
 	NETLINK_CB(skb).creds	= siocb->scm->creds;
+	NETLINK_CB(skb).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
 	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
@@ -2335,6 +2443,11 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	}
 #endif
 
+	/* Record the max length of recvmsg() calls for future allocations */
+	nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len);
+	nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len,
+				     16384);
+
 	copied = data_skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;
@@ -2345,7 +2458,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	err = skb_copy_datagram_iovec(data_skb, 0, msg->msg_iov, copied);
 
 	if (msg->msg_name) {
-		struct sockaddr_nl *addr = (struct sockaddr_nl *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
 		addr->nl_family = AF_NETLINK;
 		addr->nl_pad    = 0;
 		addr->nl_pid	= NETLINK_CB(skb).portid;
@@ -2370,7 +2483,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	    atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
 		ret = netlink_dump(sk);
 		if (ret) {
-			sk->sk_err = ret;
+			sk->sk_err = -ret;
 			sk->sk_error_report(sk);
 		}
 	}
@@ -2381,7 +2494,7 @@ out:
 	return err ? : copied;
 }
 
-static void netlink_data_ready(struct sock *sk, int len)
+static void netlink_data_ready(struct sock *sk)
 {
 	BUG();
 }
@@ -2535,28 +2648,13 @@ void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group)
 		netlink_update_socket_mc(nlk_sk(sk), group, 0);
 }
 
-/**
- * netlink_clear_multicast_users - kick off multicast listeners
- *
- * This function removes all listeners from the given group.
- * @ksk: The kernel netlink socket, as returned by
- *	netlink_kernel_create().
- * @group: The multicast group to clear.
- */
-void netlink_clear_multicast_users(struct sock *ksk, unsigned int group)
-{
-	netlink_table_grab();
-	__netlink_clear_multicast_users(ksk, group);
-	netlink_table_ungrab();
-}
-
 struct nlmsghdr *
 __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags)
 {
 	struct nlmsghdr *nlh;
 	int size = nlmsg_msg_size(len);
 
-	nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size));
+	nlh = (struct nlmsghdr *)skb_put(skb, NLMSG_ALIGN(size));
 	nlh->nlmsg_type = type;
 	nlh->nlmsg_len = size;
 	nlh->nlmsg_flags = flags;
@@ -2594,7 +2692,27 @@ static int netlink_dump(struct sock *sk)
 	if (!netlink_rx_is_mmaped(sk) &&
 	    atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		goto errout_skb;
-	skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL);
+
+	/* NLMSG_GOODSIZE is small to avoid high order allocations being
+	 * required, but it makes sense to _attempt_ a 16K bytes allocation
+	 * to reduce number of system calls on dump operations, if user
+	 * ever provided a big enough buffer.
+	 */
+	if (alloc_size < nlk->max_recvmsg_len) {
+		skb = netlink_alloc_skb(sk,
+					nlk->max_recvmsg_len,
+					nlk->portid,
+					GFP_KERNEL |
+					__GFP_NOWARN |
+					__GFP_NORETRY);
+		/* available room should be exact amount to avoid MSG_TRUNC */
+		if (skb)
+			skb_reserve(skb, skb_tailroom(skb) -
+					 nlk->max_recvmsg_len);
+	}
+	if (!skb)
+		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
+					GFP_KERNEL);
 	if (!skb)
 		goto errout_skb;
 	netlink_skb_set_owner_r(skb, sk);
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index acbd774eeb7..0b59d441f5b 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -31,13 +31,15 @@ struct netlink_sock {
 	u32			ngroups;
 	unsigned long		*groups;
 	unsigned long		state;
+	size_t			max_recvmsg_len;
 	wait_queue_head_t	wait;
 	bool			cb_running;
 	struct netlink_callback	cb;
 	struct mutex		*cb_mutex;
 	struct mutex		cb_def_mutex;
 	void			(*netlink_rcv)(struct sk_buff *skb);
-	void			(*netlink_bind)(int group);
+	int			(*netlink_bind)(int group);
+	void			(*netlink_unbind)(int group);
 	struct module		*module;
 #ifdef CONFIG_NETLINK_MMAP
 	struct mutex		pg_vec_lock;
@@ -73,7 +75,8 @@ struct netlink_table {
 	unsigned int		groups;
 	struct mutex		*cb_mutex;
 	struct module		*module;
-	void			(*bind)(int group);
+	int			(*bind)(int group);
+	void			(*unbind)(int group);
 	bool			(*compare)(struct net *net, struct sock *sock);
 	int			registered;
 };
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 713671ae45a..76393f2f4b2 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -317,7 +317,7 @@ static void genl_unregister_mc_groups(struct genl_family *family)
 	}
 }
 
-static int genl_validate_ops(struct genl_family *family)
+static int genl_validate_ops(const struct genl_family *family)
 {
 	const struct genl_ops *ops = family->ops;
 	unsigned int n_ops = family->n_ops;
@@ -337,10 +337,6 @@ static int genl_validate_ops(struct genl_family *family)
 				return -EINVAL;
 	}
 
-	/* family is not registered yet, so no locking needed */
-	family->ops = ops;
-	family->n_ops = n_ops;
-
 	return 0;
 }
 
@@ -461,6 +457,26 @@ int genl_unregister_family(struct genl_family *family)
 EXPORT_SYMBOL(genl_unregister_family);
 
 /**
+ * genlmsg_new_unicast - Allocate generic netlink message for unicast
+ * @payload: size of the message payload
+ * @info: information on destination
+ * @flags: the type of memory to allocate
+ *
+ * Allocates a new sk_buff large enough to cover the specified payload
+ * plus required Netlink headers. Will check receiving socket for
+ * memory mapped i/o capability and use it if enabled. Will fall back
+ * to non-mapped skb if message size exceeds the frame size of the ring.
+ */
+struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info,
+				    gfp_t flags)
+{
+	size_t len = nlmsg_total_size(genlmsg_total_size(payload));
+
+	return netlink_alloc_skb(info->dst_sk, len, info->snd_portid, flags);
+}
+EXPORT_SYMBOL_GPL(genlmsg_new_unicast);
+
+/**
  * genlmsg_put - Add generic netlink header to netlink message
  * @skb: socket buffer holding the message
  * @portid: netlink portid the message is addressed to
@@ -541,7 +557,7 @@ static int genl_family_rcv_msg(struct genl_family *family,
 		return -EOPNOTSUPP;
 
 	if ((ops->flags & GENL_ADMIN_PERM) &&
-	    !capable(CAP_NET_ADMIN))
+	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) {
@@ -600,6 +616,7 @@ static int genl_family_rcv_msg(struct genl_family *family,
 	info.genlhdr = nlmsg_data(nlh);
 	info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN;
 	info.attrs = attrbuf;
+	info.dst_sk = skb->sk;
 	genl_info_net_set(&info, net);
 	memset(&info.user_ptr, 0, sizeof(info.user_ptr));
 
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 53c19a35fc6..ede50d197e1 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1011,7 +1011,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	skb_queue_head(&sk->sk_receive_queue, skb);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 
 	bh_unlock_sock(sk);
 
@@ -1028,7 +1028,7 @@ static int nr_sendmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct nr_sock *nr = nr_sk(sk);
-	struct sockaddr_ax25 *usax = (struct sockaddr_ax25 *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_ax25 *, usax, msg->msg_name);
 	int err;
 	struct sockaddr_ax25 sax;
 	struct sk_buff *skb;
@@ -1137,7 +1137,7 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock,
 		      struct msghdr *msg, size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_ax25 *, sax, msg->msg_name);
 	size_t copied;
 	struct sk_buff *skb;
 	int er;
diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c
index 9d68441e2a5..2277276f52b 100644
--- a/net/nfc/af_nfc.c
+++ b/net/nfc/af_nfc.c
@@ -16,9 +16,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/nfc.h>
diff --git a/net/nfc/core.c b/net/nfc/core.c
index 872529105ab..819b87702b7 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -16,9 +16,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__
@@ -135,11 +133,8 @@ int nfc_dev_up(struct nfc_dev *dev)
 		dev->dev_up = true;
 
 	/* We have to enable the device before discovering SEs */
-	if (dev->ops->discover_se) {
-		rc = dev->ops->discover_se(dev);
-		if (rc)
-			pr_warn("SE discovery failed\n");
-	}
+	if (dev->ops->discover_se && dev->ops->discover_se(dev))
+		pr_err("SE discovery failed\n");
 
 error:
 	device_unlock(&dev->dev);
@@ -285,9 +280,6 @@ static struct nfc_target *nfc_find_target(struct nfc_dev *dev, u32 target_idx)
 {
 	int i;
 
-	if (dev->n_targets == 0)
-		return NULL;
-
 	for (i = 0; i < dev->n_targets; i++) {
 		if (dev->targets[i].idx == target_idx)
 			return &dev->targets[i];
@@ -384,7 +376,7 @@ int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx,
 {
 	dev->dep_link_up = true;
 
-	if (!dev->active_target) {
+	if (!dev->active_target && rf_mode == NFC_RF_INITIATOR) {
 		struct nfc_target *target;
 
 		target = nfc_find_target(dev, target_idx);
@@ -551,9 +543,9 @@ error:
 
 struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx)
 {
-	struct nfc_se *se, *n;
+	struct nfc_se *se;
 
-	list_for_each_entry_safe(se, n, &dev->secure_elements, list)
+	list_for_each_entry(se, &dev->secure_elements, list)
 		if (se->idx == se_idx)
 			return se;
 
@@ -660,9 +652,6 @@ int nfc_set_remote_general_bytes(struct nfc_dev *dev, u8 *gb, u8 gb_len)
 {
 	pr_debug("dev_name=%s gb_len=%d\n", dev_name(&dev->dev), gb_len);
 
-	if (gb_len > NFC_MAX_GT_LEN)
-		return -EINVAL;
-
 	return nfc_llcp_set_remote_gb(dev, gb, gb_len);
 }
 EXPORT_SYMBOL(nfc_set_remote_general_bytes);
diff --git a/net/nfc/digital.h b/net/nfc/digital.h
index 08b29b55ea6..71ad7eefddd 100644
--- a/net/nfc/digital.h
+++ b/net/nfc/digital.h
@@ -71,7 +71,14 @@ static inline int digital_in_send_cmd(struct nfc_digital_dev *ddev,
 void digital_poll_next_tech(struct nfc_digital_dev *ddev);
 
 int digital_in_send_sens_req(struct nfc_digital_dev *ddev, u8 rf_tech);
+int digital_in_send_sensb_req(struct nfc_digital_dev *ddev, u8 rf_tech);
 int digital_in_send_sensf_req(struct nfc_digital_dev *ddev, u8 rf_tech);
+int digital_in_send_iso15693_inv_req(struct nfc_digital_dev *ddev, u8 rf_tech);
+
+int digital_in_iso_dep_pull_sod(struct nfc_digital_dev *ddev,
+				struct sk_buff *skb);
+int digital_in_iso_dep_push_sod(struct nfc_digital_dev *ddev,
+				struct sk_buff *skb);
 
 int digital_target_found(struct nfc_digital_dev *ddev,
 			 struct nfc_target *target, u8 protocol);
diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
index 09fc9543995..a6ce3c627e4 100644
--- a/net/nfc/digital_core.c
+++ b/net/nfc/digital_core.c
@@ -22,9 +22,13 @@
 #define DIGITAL_PROTO_NFCA_RF_TECH \
 	(NFC_PROTO_JEWEL_MASK | NFC_PROTO_MIFARE_MASK | NFC_PROTO_NFC_DEP_MASK)
 
+#define DIGITAL_PROTO_NFCB_RF_TECH	NFC_PROTO_ISO14443_B_MASK
+
 #define DIGITAL_PROTO_NFCF_RF_TECH \
 	(NFC_PROTO_FELICA_MASK | NFC_PROTO_NFC_DEP_MASK)
 
+#define DIGITAL_PROTO_ISO15693_RF_TECH	NFC_PROTO_ISO15693_MASK
+
 struct digital_cmd {
 	struct list_head queue;
 
@@ -331,6 +335,24 @@ int digital_target_found(struct nfc_digital_dev *ddev,
 		}
 		break;
 
+	case NFC_PROTO_ISO15693:
+		framing = NFC_DIGITAL_FRAMING_ISO15693_T5T;
+		check_crc = digital_skb_check_crc_b;
+		add_crc = digital_skb_add_crc_b;
+		break;
+
+	case NFC_PROTO_ISO14443:
+		framing = NFC_DIGITAL_FRAMING_NFCA_T4T;
+		check_crc = digital_skb_check_crc_a;
+		add_crc = digital_skb_add_crc_a;
+		break;
+
+	case NFC_PROTO_ISO14443_B:
+		framing = NFC_DIGITAL_FRAMING_NFCB_T4T;
+		check_crc = digital_skb_check_crc_b;
+		add_crc = digital_skb_add_crc_b;
+		break;
+
 	default:
 		pr_err("Invalid protocol %d\n", protocol);
 		return -EINVAL;
@@ -339,7 +361,6 @@ int digital_target_found(struct nfc_digital_dev *ddev,
 	pr_debug("rf_tech=%d, protocol=%d\n", rf_tech, protocol);
 
 	ddev->curr_rf_tech = rf_tech;
-	ddev->curr_protocol = protocol;
 
 	if (DIGITAL_DRV_CAPS_IN_CRC(ddev)) {
 		ddev->skb_add_crc = digital_skb_add_crc_none;
@@ -365,6 +386,8 @@ int digital_target_found(struct nfc_digital_dev *ddev,
 
 void digital_poll_next_tech(struct nfc_digital_dev *ddev)
 {
+	u8 rand_mod;
+
 	digital_switch_rf(ddev, 0);
 
 	mutex_lock(&ddev->poll_lock);
@@ -374,8 +397,8 @@ void digital_poll_next_tech(struct nfc_digital_dev *ddev)
 		return;
 	}
 
-	ddev->poll_tech_index = (ddev->poll_tech_index + 1) %
-				ddev->poll_tech_count;
+	get_random_bytes(&rand_mod, sizeof(rand_mod));
+	ddev->poll_tech_index = rand_mod % ddev->poll_tech_count;
 
 	mutex_unlock(&ddev->poll_lock);
 
@@ -462,7 +485,11 @@ static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols,
 		digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106A,
 				      digital_in_send_sens_req);
 
-	if (im_protocols & DIGITAL_PROTO_NFCF_RF_TECH) {
+	if (matching_im_protocols & DIGITAL_PROTO_NFCB_RF_TECH)
+		digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106B,
+				      digital_in_send_sensb_req);
+
+	if (matching_im_protocols & DIGITAL_PROTO_NFCF_RF_TECH) {
 		digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_212F,
 				      digital_in_send_sensf_req);
 
@@ -470,7 +497,11 @@ static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols,
 				      digital_in_send_sensf_req);
 	}
 
-	if (tm_protocols & NFC_PROTO_NFC_DEP_MASK) {
+	if (matching_im_protocols & DIGITAL_PROTO_ISO15693_RF_TECH)
+		digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_ISO15693,
+				      digital_in_send_iso15693_inv_req);
+
+	if (matching_tm_protocols & NFC_PROTO_NFC_DEP_MASK) {
 		if (ddev->ops->tg_listen_mdaa) {
 			digital_add_poll_tech(ddev, 0,
 					      digital_tg_listen_mdaa);
@@ -541,8 +572,14 @@ static int digital_dep_link_up(struct nfc_dev *nfc_dev,
 			       __u8 comm_mode, __u8 *gb, size_t gb_len)
 {
 	struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev);
+	int rc;
+
+	rc = digital_in_send_atr_req(ddev, target, comm_mode, gb, gb_len);
+
+	if (!rc)
+		ddev->curr_protocol = NFC_PROTO_NFC_DEP;
 
-	return digital_in_send_atr_req(ddev, target, comm_mode, gb, gb_len);
+	return rc;
 }
 
 static int digital_dep_link_down(struct nfc_dev *nfc_dev)
@@ -557,6 +594,20 @@ static int digital_dep_link_down(struct nfc_dev *nfc_dev)
 static int digital_activate_target(struct nfc_dev *nfc_dev,
 				   struct nfc_target *target, __u32 protocol)
 {
+	struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev);
+
+	if (ddev->poll_tech_count) {
+		pr_err("Can't activate a target while polling\n");
+		return -EBUSY;
+	}
+
+	if (ddev->curr_protocol) {
+		pr_err("A target is already active\n");
+		return -EBUSY;
+	}
+
+	ddev->curr_protocol = protocol;
+
 	return 0;
 }
 
@@ -565,6 +616,11 @@ static void digital_deactivate_target(struct nfc_dev *nfc_dev,
 {
 	struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev);
 
+	if (!ddev->curr_protocol) {
+		pr_err("No active target\n");
+		return;
+	}
+
 	ddev->curr_protocol = 0;
 }
 
@@ -583,20 +639,31 @@ static void digital_in_send_complete(struct nfc_digital_dev *ddev, void *arg,
 
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
+		resp = NULL;
 		goto done;
 	}
 
-	if (ddev->curr_protocol == NFC_PROTO_MIFARE)
+	if (ddev->curr_protocol == NFC_PROTO_MIFARE) {
 		rc = digital_in_recv_mifare_res(resp);
-	else
-		rc = ddev->skb_check_crc(resp);
+		/* crc check is done in digital_in_recv_mifare_res() */
+		goto done;
+	}
 
+	if ((ddev->curr_protocol == NFC_PROTO_ISO14443) ||
+	    (ddev->curr_protocol == NFC_PROTO_ISO14443_B)) {
+		rc = digital_in_iso_dep_pull_sod(ddev, resp);
+		if (rc)
+			goto done;
+	}
+
+	rc = ddev->skb_check_crc(resp);
+
+done:
 	if (rc) {
 		kfree_skb(resp);
 		resp = NULL;
 	}
 
-done:
 	data_exch->cb(data_exch->cb_context, resp, rc);
 
 	kfree(data_exch);
@@ -608,6 +675,7 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target,
 {
 	struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev);
 	struct digital_data_exch *data_exch;
+	int rc;
 
 	data_exch = kzalloc(sizeof(struct digital_data_exch), GFP_KERNEL);
 	if (!data_exch) {
@@ -618,13 +686,28 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	data_exch->cb = cb;
 	data_exch->cb_context = cb_context;
 
-	if (ddev->curr_protocol == NFC_PROTO_NFC_DEP)
-		return digital_in_send_dep_req(ddev, target, skb, data_exch);
+	if (ddev->curr_protocol == NFC_PROTO_NFC_DEP) {
+		rc = digital_in_send_dep_req(ddev, target, skb, data_exch);
+		goto exit;
+	}
+
+	if ((ddev->curr_protocol == NFC_PROTO_ISO14443) ||
+	    (ddev->curr_protocol == NFC_PROTO_ISO14443_B)) {
+		rc = digital_in_iso_dep_push_sod(ddev, skb);
+		if (rc)
+			goto exit;
+	}
 
 	ddev->skb_add_crc(skb);
 
-	return digital_in_send_cmd(ddev, skb, 500, digital_in_send_complete,
-				   data_exch);
+	rc = digital_in_send_cmd(ddev, skb, 500, digital_in_send_complete,
+				 data_exch);
+
+exit:
+	if (rc)
+		kfree(data_exch);
+
+	return rc;
 }
 
 static struct nfc_ops digital_nfc_ops = {
@@ -676,6 +759,12 @@ struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops,
 		ddev->protocols |= NFC_PROTO_FELICA_MASK;
 	if (supported_protocols & NFC_PROTO_NFC_DEP_MASK)
 		ddev->protocols |= NFC_PROTO_NFC_DEP_MASK;
+	if (supported_protocols & NFC_PROTO_ISO15693_MASK)
+		ddev->protocols |= NFC_PROTO_ISO15693_MASK;
+	if (supported_protocols & NFC_PROTO_ISO14443_MASK)
+		ddev->protocols |= NFC_PROTO_ISO14443_MASK;
+	if (supported_protocols & NFC_PROTO_ISO14443_B_MASK)
+		ddev->protocols |= NFC_PROTO_ISO14443_B_MASK;
 
 	ddev->tx_headroom = tx_headroom + DIGITAL_MAX_HEADER_LEN;
 	ddev->tx_tailroom = tx_tailroom + DIGITAL_CRC_LEN;
diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c
index 07bbc24fb4c..171cb9949ab 100644
--- a/net/nfc/digital_dep.c
+++ b/net/nfc/digital_dep.c
@@ -32,7 +32,6 @@
 #define DIGITAL_ATR_REQ_MIN_SIZE 16
 #define DIGITAL_ATR_REQ_MAX_SIZE 64
 
-#define DIGITAL_NFCID3_LEN ((u8)8)
 #define DIGITAL_LR_BITS_PAYLOAD_SIZE_254B 0x30
 #define DIGITAL_GB_BIT	0x02
 
@@ -206,10 +205,9 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev,
 	atr_req->dir = DIGITAL_NFC_DEP_FRAME_DIR_OUT;
 	atr_req->cmd = DIGITAL_CMD_ATR_REQ;
 	if (target->nfcid2_len)
-		memcpy(atr_req->nfcid3, target->nfcid2,
-		       max(target->nfcid2_len, DIGITAL_NFCID3_LEN));
+		memcpy(atr_req->nfcid3, target->nfcid2, NFC_NFCID2_MAXSIZE);
 	else
-		get_random_bytes(atr_req->nfcid3, DIGITAL_NFCID3_LEN);
+		get_random_bytes(atr_req->nfcid3, NFC_NFCID3_MAXSIZE);
 
 	atr_req->did = 0;
 	atr_req->bs = 0;
@@ -226,9 +224,8 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev,
 
 	ddev->skb_add_crc(skb);
 
-	digital_in_send_cmd(ddev, skb, 500, digital_in_recv_atr_res, target);
-
-	return 0;
+	return digital_in_send_cmd(ddev, skb, 500, digital_in_recv_atr_res,
+				   target);
 }
 
 static int digital_in_send_rtox(struct nfc_digital_dev *ddev,
@@ -382,6 +379,33 @@ int digital_in_send_dep_req(struct nfc_digital_dev *ddev,
 				   data_exch);
 }
 
+static void digital_tg_set_rf_tech(struct nfc_digital_dev *ddev, u8 rf_tech)
+{
+	ddev->curr_rf_tech = rf_tech;
+
+	ddev->skb_add_crc = digital_skb_add_crc_none;
+	ddev->skb_check_crc = digital_skb_check_crc_none;
+
+	if (DIGITAL_DRV_CAPS_TG_CRC(ddev))
+		return;
+
+	switch (ddev->curr_rf_tech) {
+	case NFC_DIGITAL_RF_TECH_106A:
+		ddev->skb_add_crc = digital_skb_add_crc_a;
+		ddev->skb_check_crc = digital_skb_check_crc_a;
+		break;
+
+	case NFC_DIGITAL_RF_TECH_212F:
+	case NFC_DIGITAL_RF_TECH_424F:
+		ddev->skb_add_crc = digital_skb_add_crc_f;
+		ddev->skb_check_crc = digital_skb_check_crc_f;
+		break;
+
+	default:
+		break;
+	}
+}
+
 static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg,
 				    struct sk_buff *resp)
 {
@@ -472,11 +496,13 @@ int digital_tg_send_dep_res(struct nfc_digital_dev *ddev, struct sk_buff *skb)
 static void digital_tg_send_psl_res_complete(struct nfc_digital_dev *ddev,
 					     void *arg, struct sk_buff *resp)
 {
-	u8 rf_tech = PTR_ERR(arg);
+	u8 rf_tech = (unsigned long)arg;
 
 	if (IS_ERR(resp))
 		return;
 
+	digital_tg_set_rf_tech(ddev, rf_tech);
+
 	digital_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH, rf_tech);
 
 	digital_tg_listen(ddev, 1500, digital_tg_recv_dep_req, NULL);
@@ -508,7 +534,7 @@ static int digital_tg_send_psl_res(struct nfc_digital_dev *ddev, u8 did,
 	ddev->skb_add_crc(skb);
 
 	rc = digital_tg_send_cmd(ddev, skb, 0, digital_tg_send_psl_res_complete,
-				 ERR_PTR(rf_tech));
+				 (void *)(unsigned long)rf_tech);
 
 	if (rc)
 		kfree_skb(skb);
@@ -563,7 +589,7 @@ static void digital_tg_recv_psl_req(struct nfc_digital_dev *ddev, void *arg,
 		rf_tech = NFC_DIGITAL_RF_TECH_424F;
 		break;
 	default:
-		pr_err("Unsuported dsi value %d\n", dsi);
+		pr_err("Unsupported dsi value %d\n", dsi);
 		goto exit;
 	}
 
@@ -661,16 +687,10 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg,
 
 	if (resp->data[0] == DIGITAL_NFC_DEP_NFCA_SOD_SB) {
 		min_size = DIGITAL_ATR_REQ_MIN_SIZE + 2;
-
-		ddev->curr_rf_tech = NFC_DIGITAL_RF_TECH_106A;
-		ddev->skb_add_crc = digital_skb_add_crc_a;
-		ddev->skb_check_crc = digital_skb_check_crc_a;
+		digital_tg_set_rf_tech(ddev, NFC_DIGITAL_RF_TECH_106A);
 	} else {
 		min_size = DIGITAL_ATR_REQ_MIN_SIZE + 1;
-
-		ddev->curr_rf_tech = NFC_DIGITAL_RF_TECH_212F;
-		ddev->skb_add_crc = digital_skb_add_crc_f;
-		ddev->skb_check_crc = digital_skb_check_crc_f;
+		digital_tg_set_rf_tech(ddev, NFC_DIGITAL_RF_TECH_212F);
 	}
 
 	if (resp->len < min_size) {
@@ -678,10 +698,7 @@ void digital_tg_recv_atr_req(struct nfc_digital_dev *ddev, void *arg,
 		goto exit;
 	}
 
-	if (DIGITAL_DRV_CAPS_TG_CRC(ddev)) {
-		ddev->skb_add_crc = digital_skb_add_crc_none;
-		ddev->skb_check_crc = digital_skb_check_crc_none;
-	}
+	ddev->curr_protocol = NFC_PROTO_NFC_DEP_MASK;
 
 	rc = ddev->skb_check_crc(resp);
 	if (rc) {
diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c
index 251c8c753eb..c2c1c0189b7 100644
--- a/net/nfc/digital_technology.c
+++ b/net/nfc/digital_technology.c
@@ -30,6 +30,7 @@
 
 #define DIGITAL_SEL_RES_NFCID1_COMPLETE(sel_res) (!((sel_res) & 0x04))
 #define DIGITAL_SEL_RES_IS_T2T(sel_res) (!((sel_res) & 0x60))
+#define DIGITAL_SEL_RES_IS_T4T(sel_res) ((sel_res) & 0x20)
 #define DIGITAL_SEL_RES_IS_NFC_DEP(sel_res) ((sel_res) & 0x40)
 
 #define DIGITAL_SENS_RES_IS_T1T(sens_res) (((sens_res) & 0x0C00) == 0x0C00)
@@ -40,6 +41,24 @@
 #define DIGITAL_MIFARE_READ_RES_LEN 16
 #define DIGITAL_MIFARE_ACK_RES	0x0A
 
+#define DIGITAL_CMD_SENSB_REQ			0x05
+#define DIGITAL_SENSB_ADVANCED			BIT(5)
+#define DIGITAL_SENSB_EXTENDED			BIT(4)
+#define DIGITAL_SENSB_ALLB_REQ			BIT(3)
+#define DIGITAL_SENSB_N(n)			((n) & 0x7)
+
+#define DIGITAL_CMD_SENSB_RES			0x50
+
+#define DIGITAL_CMD_ATTRIB_REQ			0x1D
+#define DIGITAL_ATTRIB_P1_TR0_DEFAULT		(0x0 << 6)
+#define DIGITAL_ATTRIB_P1_TR1_DEFAULT		(0x0 << 4)
+#define DIGITAL_ATTRIB_P1_SUPRESS_EOS		BIT(3)
+#define DIGITAL_ATTRIB_P1_SUPRESS_SOS		BIT(2)
+#define DIGITAL_ATTRIB_P2_LISTEN_POLL_1		(0x0 << 6)
+#define DIGITAL_ATTRIB_P2_POLL_LISTEN_1		(0x0 << 4)
+#define DIGITAL_ATTRIB_P2_MAX_FRAME_256		0x8
+#define DIGITAL_ATTRIB_P4_DID(n)		((n) & 0xf)
+
 #define DIGITAL_CMD_SENSF_REQ	0x00
 #define DIGITAL_CMD_SENSF_RES	0x01
 
@@ -51,6 +70,35 @@
 #define DIGITAL_SENSF_REQ_RC_SC   1
 #define DIGITAL_SENSF_REQ_RC_AP   2
 
+#define DIGITAL_CMD_ISO15693_INVENTORY_REQ	0x01
+
+#define DIGITAL_ISO15693_REQ_FLAG_DATA_RATE	BIT(1)
+#define DIGITAL_ISO15693_REQ_FLAG_INVENTORY	BIT(2)
+#define DIGITAL_ISO15693_REQ_FLAG_NB_SLOTS	BIT(5)
+#define DIGITAL_ISO15693_RES_FLAG_ERROR		BIT(0)
+#define DIGITAL_ISO15693_RES_IS_VALID(flags) \
+	(!((flags) & DIGITAL_ISO15693_RES_FLAG_ERROR))
+
+#define DIGITAL_ISO_DEP_I_PCB	 0x02
+#define DIGITAL_ISO_DEP_PNI(pni) ((pni) & 0x01)
+
+#define DIGITAL_ISO_DEP_PCB_TYPE(pcb) ((pcb) & 0xC0)
+
+#define DIGITAL_ISO_DEP_I_BLOCK 0x00
+
+#define DIGITAL_ISO_DEP_BLOCK_HAS_DID(pcb) ((pcb) & 0x08)
+
+static const u8 digital_ats_fsc[] = {
+	 16,  24,  32,  40,  48,  64,  96, 128,
+};
+
+#define DIGITAL_ATS_FSCI(t0) ((t0) & 0x0F)
+#define DIGITAL_SENSB_FSCI(pi2) (((pi2) & 0xF0) >> 4)
+#define DIGITAL_ATS_MAX_FSC  256
+
+#define DIGITAL_RATS_BYTE1 0xE0
+#define DIGITAL_RATS_PARAM 0x80
+
 struct digital_sdd_res {
 	u8 nfcid1[4];
 	u8 bcc;
@@ -63,6 +111,32 @@ struct digital_sel_req {
 	u8 bcc;
 } __packed;
 
+struct digital_sensb_req {
+	u8 cmd;
+	u8 afi;
+	u8 param;
+} __packed;
+
+struct digital_sensb_res {
+	u8 cmd;
+	u8 nfcid0[4];
+	u8 app_data[4];
+	u8 proto_info[3];
+} __packed;
+
+struct digital_attrib_req {
+	u8 cmd;
+	u8 nfcid0[4];
+	u8 param1;
+	u8 param2;
+	u8 param3;
+	u8 param4;
+} __packed;
+
+struct digital_attrib_res {
+	u8 mbli_did;
+} __packed;
+
 struct digital_sensf_req {
 	u8 cmd;
 	u8 sc1;
@@ -82,9 +156,127 @@ struct digital_sensf_res {
 	u8 rd[2];
 } __packed;
 
+struct digital_iso15693_inv_req {
+	u8 flags;
+	u8 cmd;
+	u8 mask_len;
+	u64 mask;
+} __packed;
+
+struct digital_iso15693_inv_res {
+	u8 flags;
+	u8 dsfid;
+	u64 uid;
+} __packed;
+
 static int digital_in_send_sdd_req(struct nfc_digital_dev *ddev,
 				   struct nfc_target *target);
 
+int digital_in_iso_dep_pull_sod(struct nfc_digital_dev *ddev,
+				struct sk_buff *skb)
+{
+	u8 pcb;
+	u8 block_type;
+
+	if (skb->len < 1)
+		return -EIO;
+
+	pcb = *skb->data;
+	block_type = DIGITAL_ISO_DEP_PCB_TYPE(pcb);
+
+	/* No support fo R-block nor S-block */
+	if (block_type != DIGITAL_ISO_DEP_I_BLOCK) {
+		pr_err("ISO_DEP R-block and S-block not supported\n");
+		return -EIO;
+	}
+
+	if (DIGITAL_ISO_DEP_BLOCK_HAS_DID(pcb)) {
+		pr_err("DID field in ISO_DEP PCB not supported\n");
+		return -EIO;
+	}
+
+	skb_pull(skb, 1);
+
+	return 0;
+}
+
+int digital_in_iso_dep_push_sod(struct nfc_digital_dev *ddev,
+				struct sk_buff *skb)
+{
+	/*
+	 * Chaining not supported so skb->len + 1 PCB byte + 2 CRC bytes must
+	 * not be greater than remote FSC
+	 */
+	if (skb->len + 3 > ddev->target_fsc)
+		return -EIO;
+
+	skb_push(skb, 1);
+
+	*skb->data = DIGITAL_ISO_DEP_I_PCB | ddev->curr_nfc_dep_pni;
+
+	ddev->curr_nfc_dep_pni =
+		DIGITAL_ISO_DEP_PNI(ddev->curr_nfc_dep_pni + 1);
+
+	return 0;
+}
+
+static void digital_in_recv_ats(struct nfc_digital_dev *ddev, void *arg,
+				struct sk_buff *resp)
+{
+	struct nfc_target *target = arg;
+	u8 fsdi;
+	int rc;
+
+	if (IS_ERR(resp)) {
+		rc = PTR_ERR(resp);
+		resp = NULL;
+		goto exit;
+	}
+
+	if (resp->len < 2) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	fsdi = DIGITAL_ATS_FSCI(resp->data[1]);
+	if (fsdi >= 8)
+		ddev->target_fsc = DIGITAL_ATS_MAX_FSC;
+	else
+		ddev->target_fsc = digital_ats_fsc[fsdi];
+
+	ddev->curr_nfc_dep_pni = 0;
+
+	rc = digital_target_found(ddev, target, NFC_PROTO_ISO14443);
+
+exit:
+	dev_kfree_skb(resp);
+	kfree(target);
+
+	if (rc)
+		digital_poll_next_tech(ddev);
+}
+
+static int digital_in_send_rats(struct nfc_digital_dev *ddev,
+				struct nfc_target *target)
+{
+	int rc;
+	struct sk_buff *skb;
+
+	skb = digital_skb_alloc(ddev, 2);
+	if (!skb)
+		return -ENOMEM;
+
+	*skb_put(skb, 1) = DIGITAL_RATS_BYTE1;
+	*skb_put(skb, 1) = DIGITAL_RATS_PARAM;
+
+	rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_ats,
+				 target);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
 static void digital_in_recv_sel_res(struct nfc_digital_dev *ddev, void *arg,
 				    struct sk_buff *resp)
 {
@@ -122,8 +314,19 @@ static void digital_in_recv_sel_res(struct nfc_digital_dev *ddev, void *arg,
 		goto exit_free_skb;
 	}
 
+	target->sel_res = sel_res;
+
 	if (DIGITAL_SEL_RES_IS_T2T(sel_res)) {
 		nfc_proto = NFC_PROTO_MIFARE;
+	} else if (DIGITAL_SEL_RES_IS_T4T(sel_res)) {
+		rc = digital_in_send_rats(ddev, target);
+		if (rc)
+			goto exit;
+		/*
+		 * Skip target_found and don't free it for now. This will be
+		 * done when receiving the ATS
+		 */
+		goto exit_free_skb;
 	} else if (DIGITAL_SEL_RES_IS_NFC_DEP(sel_res)) {
 		nfc_proto = NFC_PROTO_NFC_DEP;
 	} else {
@@ -131,8 +334,6 @@ static void digital_in_recv_sel_res(struct nfc_digital_dev *ddev, void *arg,
 		goto exit;
 	}
 
-	target->sel_res = sel_res;
-
 	rc = digital_target_found(ddev, target, nfc_proto);
 
 exit:
@@ -375,6 +576,175 @@ int digital_in_recv_mifare_res(struct sk_buff *resp)
 	return -EIO;
 }
 
+static void digital_in_recv_attrib_res(struct nfc_digital_dev *ddev, void *arg,
+				       struct sk_buff *resp)
+{
+	struct nfc_target *target = arg;
+	struct digital_attrib_res *attrib_res;
+	int rc;
+
+	if (IS_ERR(resp)) {
+		rc = PTR_ERR(resp);
+		resp = NULL;
+		goto exit;
+	}
+
+	if (resp->len < sizeof(*attrib_res)) {
+		PROTOCOL_ERR("12.6.2");
+		rc = -EIO;
+		goto exit;
+	}
+
+	attrib_res = (struct digital_attrib_res *)resp->data;
+
+	if (attrib_res->mbli_did & 0x0f) {
+		PROTOCOL_ERR("12.6.2.1");
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = digital_target_found(ddev, target, NFC_PROTO_ISO14443_B);
+
+exit:
+	dev_kfree_skb(resp);
+	kfree(target);
+
+	if (rc)
+		digital_poll_next_tech(ddev);
+}
+
+static int digital_in_send_attrib_req(struct nfc_digital_dev *ddev,
+			       struct nfc_target *target,
+			       struct digital_sensb_res *sensb_res)
+{
+	struct digital_attrib_req *attrib_req;
+	struct sk_buff *skb;
+	int rc;
+
+	skb = digital_skb_alloc(ddev, sizeof(*attrib_req));
+	if (!skb)
+		return -ENOMEM;
+
+	attrib_req = (struct digital_attrib_req *)skb_put(skb,
+							  sizeof(*attrib_req));
+
+	attrib_req->cmd = DIGITAL_CMD_ATTRIB_REQ;
+	memcpy(attrib_req->nfcid0, sensb_res->nfcid0,
+	       sizeof(attrib_req->nfcid0));
+	attrib_req->param1 = DIGITAL_ATTRIB_P1_TR0_DEFAULT |
+			     DIGITAL_ATTRIB_P1_TR1_DEFAULT;
+	attrib_req->param2 = DIGITAL_ATTRIB_P2_LISTEN_POLL_1 |
+			     DIGITAL_ATTRIB_P2_POLL_LISTEN_1 |
+			     DIGITAL_ATTRIB_P2_MAX_FRAME_256;
+	attrib_req->param3 = sensb_res->proto_info[1] & 0x07;
+	attrib_req->param4 = DIGITAL_ATTRIB_P4_DID(0);
+
+	rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_attrib_res,
+				 target);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
+static void digital_in_recv_sensb_res(struct nfc_digital_dev *ddev, void *arg,
+				      struct sk_buff *resp)
+{
+	struct nfc_target *target = NULL;
+	struct digital_sensb_res *sensb_res;
+	u8 fsci;
+	int rc;
+
+	if (IS_ERR(resp)) {
+		rc = PTR_ERR(resp);
+		resp = NULL;
+		goto exit;
+	}
+
+	if (resp->len != sizeof(*sensb_res)) {
+		PROTOCOL_ERR("5.6.2.1");
+		rc = -EIO;
+		goto exit;
+	}
+
+	sensb_res = (struct digital_sensb_res *)resp->data;
+
+	if (sensb_res->cmd != DIGITAL_CMD_SENSB_RES) {
+		PROTOCOL_ERR("5.6.2");
+		rc = -EIO;
+		goto exit;
+	}
+
+	if (!(sensb_res->proto_info[1] & BIT(0))) {
+		PROTOCOL_ERR("5.6.2.12");
+		rc = -EIO;
+		goto exit;
+	}
+
+	if (sensb_res->proto_info[1] & BIT(3)) {
+		PROTOCOL_ERR("5.6.2.16");
+		rc = -EIO;
+		goto exit;
+	}
+
+	fsci = DIGITAL_SENSB_FSCI(sensb_res->proto_info[1]);
+	if (fsci >= 8)
+		ddev->target_fsc = DIGITAL_ATS_MAX_FSC;
+	else
+		ddev->target_fsc = digital_ats_fsc[fsci];
+
+	target = kzalloc(sizeof(struct nfc_target), GFP_KERNEL);
+	if (!target) {
+		rc = -ENOMEM;
+		goto exit;
+	}
+
+	rc = digital_in_send_attrib_req(ddev, target, sensb_res);
+
+exit:
+	dev_kfree_skb(resp);
+
+	if (rc) {
+		kfree(target);
+		digital_poll_next_tech(ddev);
+	}
+}
+
+int digital_in_send_sensb_req(struct nfc_digital_dev *ddev, u8 rf_tech)
+{
+	struct digital_sensb_req *sensb_req;
+	struct sk_buff *skb;
+	int rc;
+
+	rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH,
+				     NFC_DIGITAL_RF_TECH_106B);
+	if (rc)
+		return rc;
+
+	rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING,
+				     NFC_DIGITAL_FRAMING_NFCB);
+	if (rc)
+		return rc;
+
+	skb = digital_skb_alloc(ddev, sizeof(*sensb_req));
+	if (!skb)
+		return -ENOMEM;
+
+	sensb_req = (struct digital_sensb_req *)skb_put(skb,
+							sizeof(*sensb_req));
+
+	sensb_req->cmd = DIGITAL_CMD_SENSB_REQ;
+	sensb_req->afi = 0x00; /* All families and sub-families */
+	sensb_req->param = DIGITAL_SENSB_N(0);
+
+	rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sensb_res,
+				 NULL);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
 static void digital_in_recv_sensf_res(struct nfc_digital_dev *ddev, void *arg,
 				   struct sk_buff *resp)
 {
@@ -473,6 +843,93 @@ int digital_in_send_sensf_req(struct nfc_digital_dev *ddev, u8 rf_tech)
 	return rc;
 }
 
+static void digital_in_recv_iso15693_inv_res(struct nfc_digital_dev *ddev,
+		void *arg, struct sk_buff *resp)
+{
+	struct digital_iso15693_inv_res *res;
+	struct nfc_target *target = NULL;
+	int rc;
+
+	if (IS_ERR(resp)) {
+		rc = PTR_ERR(resp);
+		resp = NULL;
+		goto out_free_skb;
+	}
+
+	if (resp->len != sizeof(*res)) {
+		rc = -EIO;
+		goto out_free_skb;
+	}
+
+	res = (struct digital_iso15693_inv_res *)resp->data;
+
+	if (!DIGITAL_ISO15693_RES_IS_VALID(res->flags)) {
+		PROTOCOL_ERR("ISO15693 - 10.3.1");
+		rc = -EINVAL;
+		goto out_free_skb;
+	}
+
+	target = kzalloc(sizeof(*target), GFP_KERNEL);
+	if (!target) {
+		rc = -ENOMEM;
+		goto out_free_skb;
+	}
+
+	target->is_iso15693 = 1;
+	target->iso15693_dsfid = res->dsfid;
+	memcpy(target->iso15693_uid, &res->uid, sizeof(target->iso15693_uid));
+
+	rc = digital_target_found(ddev, target, NFC_PROTO_ISO15693);
+
+	kfree(target);
+
+out_free_skb:
+	dev_kfree_skb(resp);
+
+	if (rc)
+		digital_poll_next_tech(ddev);
+}
+
+int digital_in_send_iso15693_inv_req(struct nfc_digital_dev *ddev, u8 rf_tech)
+{
+	struct digital_iso15693_inv_req *req;
+	struct sk_buff *skb;
+	int rc;
+
+	rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH,
+				     NFC_DIGITAL_RF_TECH_ISO15693);
+	if (rc)
+		return rc;
+
+	rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING,
+				     NFC_DIGITAL_FRAMING_ISO15693_INVENTORY);
+	if (rc)
+		return rc;
+
+	skb = digital_skb_alloc(ddev, sizeof(*req));
+	if (!skb)
+		return -ENOMEM;
+
+	skb_put(skb, sizeof(*req) - sizeof(req->mask)); /* No mask */
+	req = (struct digital_iso15693_inv_req *)skb->data;
+
+	/* Single sub-carrier, high data rate, no AFI, single slot
+	 * Inventory command
+	 */
+	req->flags = DIGITAL_ISO15693_REQ_FLAG_DATA_RATE |
+		     DIGITAL_ISO15693_REQ_FLAG_INVENTORY |
+		     DIGITAL_ISO15693_REQ_FLAG_NB_SLOTS;
+	req->cmd = DIGITAL_CMD_ISO15693_INVENTORY_REQ;
+	req->mask_len = 0;
+
+	rc = digital_in_send_cmd(ddev, skb, 30,
+				 digital_in_recv_iso15693_inv_res, NULL);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
 static int digital_tg_send_sel_res(struct nfc_digital_dev *ddev)
 {
 	struct sk_buff *skb;
@@ -634,6 +1091,18 @@ exit:
 	dev_kfree_skb(resp);
 }
 
+static void digital_tg_recv_atr_or_sensf_req(struct nfc_digital_dev *ddev,
+		void *arg, struct sk_buff *resp)
+{
+	if (!IS_ERR(resp) && (resp->len >= 2) &&
+			(resp->data[1] == DIGITAL_CMD_SENSF_REQ))
+		digital_tg_recv_sensf_req(ddev, arg, resp);
+	else
+		digital_tg_recv_atr_req(ddev, arg, resp);
+
+	return;
+}
+
 static int digital_tg_send_sensf_res(struct nfc_digital_dev *ddev,
 			      struct digital_sensf_req *sensf_req)
 {
@@ -644,7 +1113,7 @@ static int digital_tg_send_sensf_res(struct nfc_digital_dev *ddev,
 
 	size = sizeof(struct digital_sensf_res);
 
-	if (sensf_req->rc != DIGITAL_SENSF_REQ_RC_NONE)
+	if (sensf_req->rc == DIGITAL_SENSF_REQ_RC_NONE)
 		size -= sizeof(sensf_res->rd);
 
 	skb = digital_skb_alloc(ddev, size);
@@ -679,7 +1148,7 @@ static int digital_tg_send_sensf_res(struct nfc_digital_dev *ddev,
 		digital_skb_add_crc_f(skb);
 
 	rc = digital_tg_send_cmd(ddev, skb, 300,
-				 digital_tg_recv_atr_req, NULL);
+				 digital_tg_recv_atr_or_sensf_req, NULL);
 	if (rc)
 		kfree_skb(skb);
 
diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c
index 64f922be928..677d24bb70f 100644
--- a/net/nfc/hci/command.c
+++ b/net/nfc/hci/command.c
@@ -12,9 +12,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) "hci: %s: " fmt, __func__
@@ -28,6 +26,8 @@
 
 #include "hci.h"
 
+#define MAX_FWI 4949
+
 static int nfc_hci_execute_cmd_async(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 			       const u8 *param, size_t param_len,
 			       data_exchange_cb_t cb, void *cb_context)
@@ -39,7 +39,7 @@ static int nfc_hci_execute_cmd_async(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 	 * for all commands?
 	 */
 	return nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_COMMAND, cmd,
-				      param, param_len, cb, cb_context, 3000);
+				      param, param_len, cb, cb_context, MAX_FWI);
 }
 
 /*
@@ -84,7 +84,7 @@ static int nfc_hci_execute_cmd(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 						    NFC_HCI_HCP_COMMAND, cmd,
 						    param, param_len,
 						    nfc_hci_execute_cb, &hcp_ew,
-						    3000);
+						    MAX_FWI);
 	if (hcp_ew.exec_result < 0)
 		return hcp_ew.exec_result;
 
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index d07ca4c5cf8..47403705197 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -12,9 +12,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) "hci: %s: " fmt, __func__
@@ -227,7 +225,7 @@ int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate)
 			goto exit;
 		}
 
-		targets->sens_res = be16_to_cpu(*(u16 *)atqa_skb->data);
+		targets->sens_res = be16_to_cpu(*(__be16 *)atqa_skb->data);
 		targets->sel_res = sak_skb->data[0];
 
 		r = nfc_hci_get_param(hdev, NFC_HCI_RF_READER_A_GATE,
@@ -337,11 +335,8 @@ exit:
 	kfree_skb(skb);
 
 exit_noskb:
-	if (r) {
-		/* TODO: There was an error dispatching the event,
-		 * how to propagate up to nfc core?
-		 */
-	}
+	if (r)
+		nfc_hci_driver_failure(hdev, r);
 }
 
 static void nfc_hci_cmd_timeout(unsigned long data)
@@ -385,34 +380,31 @@ static int hci_dev_session_init(struct nfc_hci_dev *hdev)
 	if (r < 0)
 		goto disconnect_all;
 
-	if (skb->len && skb->len == strlen(hdev->init_data.session_id))
-		if (memcmp(hdev->init_data.session_id, skb->data,
-			   skb->len) == 0) {
-			/* TODO ELa: restore gate<->pipe table from
-			 * some TBD location.
-			 * note: it doesn't seem possible to get the chip
-			 * currently open gate/pipe table.
-			 * It is only possible to obtain the supported
-			 * gate list.
-			 */
+	if (skb->len && skb->len == strlen(hdev->init_data.session_id) &&
+		(memcmp(hdev->init_data.session_id, skb->data,
+			   skb->len) == 0) && hdev->ops->load_session) {
+		/* Restore gate<->pipe table from some proprietary location. */
 
-			/* goto exit
-			 * For now, always do a full initialization */
-		}
+		r = hdev->ops->load_session(hdev);
 
-	r = nfc_hci_disconnect_all_gates(hdev);
-	if (r < 0)
-		goto exit;
+		if (r < 0)
+			goto disconnect_all;
+	} else {
 
-	r = hci_dev_connect_gates(hdev, hdev->init_data.gate_count,
-				  hdev->init_data.gates);
-	if (r < 0)
-		goto disconnect_all;
+		r = nfc_hci_disconnect_all_gates(hdev);
+		if (r < 0)
+			goto exit;
+
+		r = hci_dev_connect_gates(hdev, hdev->init_data.gate_count,
+					  hdev->init_data.gates);
+		if (r < 0)
+			goto disconnect_all;
 
-	r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE,
-			      NFC_HCI_ADMIN_SESSION_IDENTITY,
-			      hdev->init_data.session_id,
-			      strlen(hdev->init_data.session_id));
+		r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE,
+				NFC_HCI_ADMIN_SESSION_IDENTITY,
+				hdev->init_data.session_id,
+				strlen(hdev->init_data.session_id));
+	}
 	if (r == 0)
 		goto exit;
 
diff --git a/net/nfc/hci/hci.h b/net/nfc/hci/hci.h
index b274d12c18a..c3d2e2c1394 100644
--- a/net/nfc/hci/hci.h
+++ b/net/nfc/hci/hci.h
@@ -12,9 +12,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __LOCAL_HCI_H
diff --git a/net/nfc/hci/hcp.c b/net/nfc/hci/hcp.c
index b6b4109f234..e9de1514656 100644
--- a/net/nfc/hci/hcp.c
+++ b/net/nfc/hci/hcp.c
@@ -12,9 +12,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) "hci: %s: " fmt, __func__
diff --git a/net/nfc/hci/llc.c b/net/nfc/hci/llc.c
index fe5e966e5b8..1b90c053185 100644
--- a/net/nfc/hci/llc.c
+++ b/net/nfc/hci/llc.c
@@ -13,23 +13,19 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <net/nfc/llc.h>
 
 #include "llc.h"
 
-static struct list_head llc_engines;
+static LIST_HEAD(llc_engines);
 
 int nfc_llc_init(void)
 {
 	int r;
 
-	INIT_LIST_HEAD(&llc_engines);
-
 	r = nfc_llc_nop_register();
 	if (r)
 		goto exit;
diff --git a/net/nfc/hci/llc.h b/net/nfc/hci/llc.h
index 7be0b7f3ceb..5dad4c57ffb 100644
--- a/net/nfc/hci/llc.h
+++ b/net/nfc/hci/llc.h
@@ -13,9 +13,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __LOCAL_LLC_H_
diff --git a/net/nfc/hci/llc_nop.c b/net/nfc/hci/llc_nop.c
index 87b10291b40..d0435d5a197 100644
--- a/net/nfc/hci/llc_nop.c
+++ b/net/nfc/hci/llc_nop.c
@@ -13,9 +13,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/types.h>
diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c
index 27b313befc3..401c7e25527 100644
--- a/net/nfc/hci/llc_shdlc.c
+++ b/net/nfc/hci/llc_shdlc.c
@@ -13,9 +13,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) "shdlc: %s: " fmt, __func__
@@ -300,7 +298,7 @@ static void llc_shdlc_rcv_rej(struct llc_shdlc *shdlc, int y_nr)
 {
 	struct sk_buff *skb;
 
-	pr_debug("remote asks retransmition from frame %d\n", y_nr);
+	pr_debug("remote asks retransmission from frame %d\n", y_nr);
 
 	if (llc_shdlc_x_lteq_y_lt_z(shdlc->dnr, y_nr, shdlc->ns)) {
 		if (shdlc->t2_active) {
diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h
index f4d48b57ea1..de1789e3cc8 100644
--- a/net/nfc/llcp.h
+++ b/net/nfc/llcp.h
@@ -12,9 +12,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 enum llcp_state {
diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c
index 1017894807c..a3ad69a4c64 100644
--- a/net/nfc/llcp_commands.c
+++ b/net/nfc/llcp_commands.c
@@ -12,9 +12,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) "llcp: %s: " fmt, __func__
@@ -389,7 +387,7 @@ int nfc_llcp_send_symm(struct nfc_dev *dev)
 
 	__net_timestamp(skb);
 
-	nfc_llcp_send_to_raw_sock(local, skb, NFC_LLCP_DIRECTION_TX);
+	nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX);
 
 	return nfc_data_exchange(dev, local->target_idx, skb,
 				 nfc_llcp_recv, local);
@@ -677,7 +675,7 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock,
 
 	do {
 		remote_miu = sock->remote_miu > LLCP_MAX_MIU ?
-				local->remote_miu : sock->remote_miu;
+				LLCP_DEFAULT_MIU : sock->remote_miu;
 
 		frag_len = min_t(size_t, remote_miu, remaining_len);
 
@@ -686,8 +684,10 @@ int nfc_llcp_send_i_frame(struct nfc_llcp_sock *sock,
 
 		pdu = llcp_allocate_pdu(sock, LLCP_PDU_I,
 					frag_len + LLCP_SEQUENCE_SIZE);
-		if (pdu == NULL)
+		if (pdu == NULL) {
+			kfree(msg_data);
 			return -ENOMEM;
+		}
 
 		skb_put(pdu, LLCP_SEQUENCE_SIZE);
 
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index 81cd3416c7d..51e78879731 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -12,9 +12,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) "llcp: %s: " fmt, __func__
@@ -29,7 +27,7 @@
 
 static u8 llcp_magic[3] = {0x46, 0x66, 0x6d};
 
-static struct list_head llcp_devices;
+static LIST_HEAD(llcp_devices);
 
 static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb);
 
@@ -295,9 +293,9 @@ static void nfc_llcp_sdreq_timer(unsigned long data)
 
 struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev)
 {
-	struct nfc_llcp_local *local, *n;
+	struct nfc_llcp_local *local;
 
-	list_for_each_entry_safe(local, n, &llcp_devices, list)
+	list_for_each_entry(local, &llcp_devices, list)
 		if (local->dev == dev)
 			return local;
 
@@ -611,14 +609,16 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len)
 
 int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len)
 {
-	struct nfc_llcp_local *local = nfc_llcp_find_local(dev);
+	struct nfc_llcp_local *local;
+
+	if (gb_len < 3 || gb_len > NFC_MAX_GT_LEN)
+		return -EINVAL;
 
+	local = nfc_llcp_find_local(dev);
 	if (local == NULL) {
 		pr_err("No LLCP device\n");
 		return -ENODEV;
 	}
-	if (gb_len < 3)
-		return -EINVAL;
 
 	memset(local->remote_gb, 0, NFC_MAX_GT_LEN);
 	memcpy(local->remote_gb, gb, gb_len);
@@ -680,16 +680,17 @@ void nfc_llcp_send_to_raw_sock(struct nfc_llcp_local *local,
 			continue;
 
 		if (skb_copy == NULL) {
-			skb_copy = __pskb_copy(skb, NFC_LLCP_RAW_HEADER_SIZE,
-					       GFP_ATOMIC);
+			skb_copy = __pskb_copy_fclone(skb, NFC_RAW_HEADER_SIZE,
+						      GFP_ATOMIC, true);
 
 			if (skb_copy == NULL)
 				continue;
 
-			data = skb_push(skb_copy, NFC_LLCP_RAW_HEADER_SIZE);
+			data = skb_push(skb_copy, NFC_RAW_HEADER_SIZE);
 
 			data[0] = local->dev ? local->dev->idx : 0xFF;
-			data[1] = direction;
+			data[1] = direction & 0x01;
+			data[1] |= (RAW_PAYLOAD_LLCP << 1);
 		}
 
 		nskb = skb_clone(skb_copy, GFP_ATOMIC);
@@ -747,7 +748,7 @@ static void nfc_llcp_tx_work(struct work_struct *work)
 			__net_timestamp(skb);
 
 			nfc_llcp_send_to_raw_sock(local, skb,
-						  NFC_LLCP_DIRECTION_TX);
+						  NFC_DIRECTION_TX);
 
 			ret = nfc_data_exchange(local->dev, local->target_idx,
 						skb, nfc_llcp_recv, local);
@@ -945,7 +946,6 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local,
 	new_sock->local = nfc_llcp_local_get(local);
 	new_sock->rw = sock->rw;
 	new_sock->miux = sock->miux;
-	new_sock->remote_miu = local->remote_miu;
 	new_sock->nfc_protocol = sock->nfc_protocol;
 	new_sock->dsap = ssap;
 	new_sock->target_idx = local->target_idx;
@@ -977,7 +977,7 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local,
 	new_sk->sk_state = LLCP_CONNECTED;
 
 	/* Wake the listening processes */
-	parent->sk_data_ready(parent, 0);
+	parent->sk_data_ready(parent);
 
 	/* Send CC */
 	nfc_llcp_send_cc(new_sock);
@@ -1477,7 +1477,7 @@ static void nfc_llcp_rx_work(struct work_struct *work)
 
 	__net_timestamp(skb);
 
-	nfc_llcp_send_to_raw_sock(local, skb, NFC_LLCP_DIRECTION_RX);
+	nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_RX);
 
 	nfc_llcp_rx_skb(local, skb);
 
@@ -1625,8 +1625,6 @@ void nfc_llcp_unregister_device(struct nfc_dev *dev)
 
 int __init nfc_llcp_init(void)
 {
-	INIT_LIST_HEAD(&llcp_devices);
-
 	return nfc_llcp_sock_init();
 }
 
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 824c6056bf8..51f077a92fa 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -12,9 +12,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) "llcp: %s: " fmt, __func__
@@ -702,7 +700,6 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr,
 
 	llcp_sock->dev = dev;
 	llcp_sock->local = nfc_llcp_local_get(local);
-	llcp_sock->remote_miu = llcp_sock->local->remote_miu;
 	llcp_sock->ssap = nfc_llcp_get_local_ssap(local);
 	if (llcp_sock->ssap == LLCP_SAP_MAX) {
 		ret = -ENOMEM;
@@ -772,8 +769,8 @@ static int llcp_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	lock_sock(sk);
 
 	if (sk->sk_type == SOCK_DGRAM) {
-		struct sockaddr_nfc_llcp *addr =
-			(struct sockaddr_nfc_llcp *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, addr,
+				 msg->msg_name);
 
 		if (msg->msg_namelen < sizeof(*addr)) {
 			release_sock(sk);
@@ -845,8 +842,8 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	if (sk->sk_type == SOCK_DGRAM && msg->msg_name) {
 		struct nfc_llcp_ui_cb *ui_cb = nfc_llcp_ui_skb_cb(skb);
-		struct sockaddr_nfc_llcp *sockaddr =
-			(struct sockaddr_nfc_llcp *) msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, sockaddr,
+				 msg->msg_name);
 
 		msg->msg_namelen = sizeof(struct sockaddr_nfc_llcp);
 
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index b943d46a164..2b400e1a869 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -20,8 +20,7 @@
  *  GNU General Public License for more details.
  *
  *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
  *
  */
 
@@ -75,7 +74,7 @@ static int __nci_request(struct nci_dev *ndev,
 
 	ndev->req_status = NCI_REQ_PEND;
 
-	init_completion(&ndev->req_completion);
+	reinit_completion(&ndev->req_completion);
 	req(ndev, opt);
 	completion_rc =
 		wait_for_completion_interruptible_timeout(&ndev->req_completion,
@@ -302,6 +301,9 @@ static int nci_open_device(struct nci_dev *ndev)
 	rc = __nci_request(ndev, nci_reset_req, 0,
 			   msecs_to_jiffies(NCI_RESET_TIMEOUT));
 
+	if (ndev->ops->setup)
+		ndev->ops->setup(ndev);
+
 	if (!rc) {
 		rc = __nci_request(ndev, nci_init_req, 0,
 				   msecs_to_jiffies(NCI_INIT_TIMEOUT));
@@ -362,6 +364,8 @@ static int nci_close_device(struct nci_dev *ndev)
 		      msecs_to_jiffies(NCI_RESET_TIMEOUT));
 	clear_bit(NCI_INIT, &ndev->flags);
 
+	del_timer_sync(&ndev->cmd_timer);
+
 	/* Flush cmd wq */
 	flush_workqueue(ndev->cmd_wq);
 
@@ -409,12 +413,26 @@ static int nci_dev_down(struct nfc_dev *nfc_dev)
 	return nci_close_device(ndev);
 }
 
+int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val)
+{
+	struct nci_set_config_param param;
+
+	if (!val || !len)
+		return 0;
+
+	param.id = id;
+	param.len = len;
+	param.val = val;
+
+	return __nci_request(ndev, nci_set_config_req, (unsigned long)&param,
+			     msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT));
+}
+EXPORT_SYMBOL(nci_set_config);
+
 static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev)
 {
 	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
 	struct nci_set_config_param param;
-	__u8 local_gb[NFC_MAX_GT_LEN];
-	int i;
 
 	param.val = nfc_get_local_general_bytes(nfc_dev, &param.len);
 	if ((param.val == NULL) || (param.len == 0))
@@ -423,11 +441,7 @@ static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev)
 	if (param.len > NFC_MAX_GT_LEN)
 		return -EINVAL;
 
-	for (i = 0; i < param.len; i++)
-		local_gb[param.len-1-i] = param.val[i];
-
 	param.id = NCI_PN_ATR_REQ_GEN_BYTES;
-	param.val = local_gb;
 
 	return nci_request(ndev, nci_set_config_req, (unsigned long)&param,
 			   msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT));
@@ -695,6 +709,7 @@ struct nci_dev *nci_allocate_device(struct nci_ops *ops,
 	ndev->ops = ops;
 	ndev->tx_headroom = tx_headroom;
 	ndev->tx_tailroom = tx_tailroom;
+	init_completion(&ndev->req_completion);
 
 	ndev->nfc_dev = nfc_allocate_device(&nci_nfc_ops,
 					    supported_protocols,
@@ -846,6 +861,10 @@ static int nci_send_frame(struct nci_dev *ndev, struct sk_buff *skb)
 	/* Get rid of skb owner, prior to sending to the driver. */
 	skb_orphan(skb);
 
+	/* Send copy to sniffer */
+	nfc_send_to_raw_sock(ndev->nfc_dev, skb,
+			     RAW_PAYLOAD_NCI, NFC_DIRECTION_TX);
+
 	return ndev->ops->send(ndev, skb);
 }
 
@@ -920,6 +939,11 @@ static void nci_rx_work(struct work_struct *work)
 	struct sk_buff *skb;
 
 	while ((skb = skb_dequeue(&ndev->rx_q))) {
+
+		/* Send copy to sniffer */
+		nfc_send_to_raw_sock(ndev->nfc_dev, skb,
+				     RAW_PAYLOAD_NCI, NFC_DIRECTION_RX);
+
 		/* Process frame */
 		switch (nci_mt(skb->data)) {
 		case NCI_MT_RSP_PKT:
diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c
index 2a9399dd6c6..6c3aef85287 100644
--- a/net/nfc/nci/data.c
+++ b/net/nfc/nci/data.c
@@ -16,8 +16,7 @@
  *  GNU General Public License for more details.
  *
  *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
  *
  */
 
diff --git a/net/nfc/nci/lib.c b/net/nfc/nci/lib.c
index 6b7fd26c68d..ed774a2e989 100644
--- a/net/nfc/nci/lib.c
+++ b/net/nfc/nci/lib.c
@@ -20,8 +20,7 @@
  *  GNU General Public License for more details.
  *
  *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
  *
  */
 
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index b2aa98ef092..f8f6af23138 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -20,8 +20,7 @@
  *  GNU General Public License for more details.
  *
  *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
  *
  */
 
@@ -367,7 +366,6 @@ static int nci_extract_activation_params_nfc_dep(struct nci_dev *ndev,
 			struct nci_rf_intf_activated_ntf *ntf, __u8 *data)
 {
 	struct activation_params_poll_nfc_dep *poll;
-	int i;
 
 	switch (ntf->activation_rf_tech_and_mode) {
 	case NCI_NFC_A_PASSIVE_POLL_MODE:
@@ -375,10 +373,8 @@ static int nci_extract_activation_params_nfc_dep(struct nci_dev *ndev,
 		poll = &ntf->activation_params.poll_nfc_dep;
 		poll->atr_res_len = min_t(__u8, *data++, 63);
 		pr_debug("atr_res_len %d\n", poll->atr_res_len);
-		if (poll->atr_res_len > 0) {
-			for (i = 0; i < poll->atr_res_len; i++)
-				poll->atr_res[poll->atr_res_len-1-i] = data[i];
-		}
+		if (poll->atr_res_len > 0)
+			memcpy(poll->atr_res, data, poll->atr_res_len);
 		break;
 
 	default:
diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c
index dd072f38ad0..041de51ccdb 100644
--- a/net/nfc/nci/rsp.c
+++ b/net/nfc/nci/rsp.c
@@ -20,8 +20,7 @@
  *  GNU General Public License for more details.
  *
  *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
  *
  */
 
diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c
index f1d426f10cc..ec250e77763 100644
--- a/net/nfc/nci/spi.c
+++ b/net/nfc/nci/spi.c
@@ -105,7 +105,7 @@ int nci_spi_send(struct nci_spi *nspi,
 	if (ret != 0 || nspi->acknowledge_mode == NCI_SPI_CRC_DISABLED)
 		goto done;
 
-	init_completion(&nspi->req_completion);
+	reinit_completion(&nspi->req_completion);
 	completion_rc =	wait_for_completion_interruptible_timeout(
 							&nspi->req_completion,
 							NCI_SPI_SEND_TIMEOUT);
@@ -145,6 +145,7 @@ struct nci_spi *nci_spi_allocate_spi(struct spi_device *spi,
 
 	nspi->spi = spi;
 	nspi->ndev = ndev;
+	init_completion(&nspi->req_completion);
 
 	return nspi;
 }
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index a9b2342d525..43cb1c17e26 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -16,9 +16,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__
@@ -96,6 +94,14 @@ static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target,
 		    target->sensf_res))
 		goto nla_put_failure;
 
+	if (target->is_iso15693) {
+		if (nla_put_u8(msg, NFC_ATTR_TARGET_ISO15693_DSFID,
+			       target->iso15693_dsfid) ||
+		    nla_put(msg, NFC_ATTR_TARGET_ISO15693_UID,
+			    sizeof(target->iso15693_uid), target->iso15693_uid))
+			goto nla_put_failure;
+	}
+
 	return genlmsg_end(msg, hdr);
 
 nla_put_failure:
diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h
index aaf606fc1fa..88d60064890 100644
--- a/net/nfc/nfc.h
+++ b/net/nfc/nfc.h
@@ -16,9 +16,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __LOCAL_NFC_H
@@ -42,6 +40,12 @@ struct nfc_rawsock {
 	struct work_struct tx_work;
 	bool tx_work_scheduled;
 };
+
+struct nfc_sock_list {
+	struct hlist_head head;
+	rwlock_t          lock;
+};
+
 #define nfc_rawsock(sk) ((struct nfc_rawsock *) sk)
 #define to_rawsock_sk(_tx_work) \
 	((struct sock *) container_of(_tx_work, struct nfc_rawsock, tx_work))
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 66bcd2eb577..11c3544ea54 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -16,9 +16,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__
@@ -29,6 +27,24 @@
 
 #include "nfc.h"
 
+static struct nfc_sock_list raw_sk_list = {
+	.lock = __RW_LOCK_UNLOCKED(raw_sk_list.lock)
+};
+
+static void nfc_sock_link(struct nfc_sock_list *l, struct sock *sk)
+{
+	write_lock(&l->lock);
+	sk_add_node(sk, &l->head);
+	write_unlock(&l->lock);
+}
+
+static void nfc_sock_unlink(struct nfc_sock_list *l, struct sock *sk)
+{
+	write_lock(&l->lock);
+	sk_del_node_init(sk);
+	write_unlock(&l->lock);
+}
+
 static void rawsock_write_queue_purge(struct sock *sk)
 {
 	pr_debug("sk=%p\n", sk);
@@ -59,6 +75,9 @@ static int rawsock_release(struct socket *sock)
 	if (!sk)
 		return 0;
 
+	if (sock->type == SOCK_RAW)
+		nfc_sock_unlink(&raw_sk_list, sk);
+
 	sock_orphan(sk);
 	sock_put(sk);
 
@@ -277,6 +296,26 @@ static const struct proto_ops rawsock_ops = {
 	.mmap           = sock_no_mmap,
 };
 
+static const struct proto_ops rawsock_raw_ops = {
+	.family         = PF_NFC,
+	.owner          = THIS_MODULE,
+	.release        = rawsock_release,
+	.bind           = sock_no_bind,
+	.connect        = sock_no_connect,
+	.socketpair     = sock_no_socketpair,
+	.accept         = sock_no_accept,
+	.getname        = sock_no_getname,
+	.poll           = datagram_poll,
+	.ioctl          = sock_no_ioctl,
+	.listen         = sock_no_listen,
+	.shutdown       = sock_no_shutdown,
+	.setsockopt     = sock_no_setsockopt,
+	.getsockopt     = sock_no_getsockopt,
+	.sendmsg        = sock_no_sendmsg,
+	.recvmsg        = rawsock_recvmsg,
+	.mmap           = sock_no_mmap,
+};
+
 static void rawsock_destruct(struct sock *sk)
 {
 	pr_debug("sk=%p\n", sk);
@@ -302,10 +341,13 @@ static int rawsock_create(struct net *net, struct socket *sock,
 
 	pr_debug("sock=%p\n", sock);
 
-	if (sock->type != SOCK_SEQPACKET)
+	if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW))
 		return -ESOCKTNOSUPPORT;
 
-	sock->ops = &rawsock_ops;
+	if (sock->type == SOCK_RAW)
+		sock->ops = &rawsock_raw_ops;
+	else
+		sock->ops = &rawsock_ops;
 
 	sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto);
 	if (!sk)
@@ -315,13 +357,53 @@ static int rawsock_create(struct net *net, struct socket *sock,
 	sk->sk_protocol = nfc_proto->id;
 	sk->sk_destruct = rawsock_destruct;
 	sock->state = SS_UNCONNECTED;
-
-	INIT_WORK(&nfc_rawsock(sk)->tx_work, rawsock_tx_work);
-	nfc_rawsock(sk)->tx_work_scheduled = false;
+	if (sock->type == SOCK_RAW)
+		nfc_sock_link(&raw_sk_list, sk);
+	else {
+		INIT_WORK(&nfc_rawsock(sk)->tx_work, rawsock_tx_work);
+		nfc_rawsock(sk)->tx_work_scheduled = false;
+	}
 
 	return 0;
 }
 
+void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb,
+			  u8 payload_type, u8 direction)
+{
+	struct sk_buff *skb_copy = NULL, *nskb;
+	struct sock *sk;
+	u8 *data;
+
+	read_lock(&raw_sk_list.lock);
+
+	sk_for_each(sk, &raw_sk_list.head) {
+		if (!skb_copy) {
+			skb_copy = __pskb_copy_fclone(skb, NFC_RAW_HEADER_SIZE,
+						      GFP_ATOMIC, true);
+			if (!skb_copy)
+				continue;
+
+			data = skb_push(skb_copy, NFC_RAW_HEADER_SIZE);
+
+			data[0] = dev ? dev->idx : 0xFF;
+			data[1] = direction & 0x01;
+			data[1] |= (payload_type << 1);
+		}
+
+		nskb = skb_clone(skb_copy, GFP_ATOMIC);
+		if (!nskb)
+			continue;
+
+		if (sock_queue_rcv_skb(sk, nskb))
+			kfree_skb(nskb);
+	}
+
+	read_unlock(&raw_sk_list.lock);
+
+	kfree_skb(skb_copy);
+}
+EXPORT_SYMBOL(nfc_send_to_raw_sock);
+
 static struct proto rawsock_proto = {
 	.name     = "NFC_RAW",
 	.owner    = THIS_MODULE,
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 65cfaa81607..e70d8b18e96 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -134,8 +134,8 @@ static int set_eth_addr(struct sk_buff *skb,
 
 	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
-	memcpy(eth_hdr(skb)->h_source, eth_key->eth_src, ETH_ALEN);
-	memcpy(eth_hdr(skb)->h_dest, eth_key->eth_dst, ETH_ALEN);
+	ether_addr_copy(eth_hdr(skb)->h_source, eth_key->eth_src);
+	ether_addr_copy(eth_hdr(skb)->h_dest, eth_key->eth_dst);
 
 	ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
@@ -165,7 +165,7 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
 	}
 
 	csum_replace4(&nh->check, *addr, new_addr);
-	skb->rxhash = 0;
+	skb_clear_hash(skb);
 	*addr = new_addr;
 }
 
@@ -199,7 +199,7 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
 	if (recalculate_csum)
 		update_ipv6_checksum(skb, l4_proto, addr, new_addr);
 
-	skb->rxhash = 0;
+	skb_clear_hash(skb);
 	memcpy(addr, new_addr, sizeof(__be32[4]));
 }
 
@@ -296,7 +296,7 @@ static void set_tp_port(struct sk_buff *skb, __be16 *port,
 {
 	inet_proto_csum_replace2(check, skb, *port, new_port, 0);
 	*port = new_port;
-	skb->rxhash = 0;
+	skb_clear_hash(skb);
 }
 
 static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
@@ -310,7 +310,7 @@ static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
 			uh->check = CSUM_MANGLED_0;
 	} else {
 		*port = new_port;
-		skb->rxhash = 0;
+		skb_clear_hash(skb);
 	}
 }
 
@@ -381,7 +381,7 @@ static int set_sctp(struct sk_buff *skb,
 		/* Carry any checksum errors through. */
 		sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
 
-		skb->rxhash = 0;
+		skb_clear_hash(skb);
 	}
 
 	return 0;
@@ -445,7 +445,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 		 a = nla_next(a, &rem)) {
 		switch (nla_type(a)) {
 		case OVS_SAMPLE_ATTR_PROBABILITY:
-			if (net_random() >= nla_get_u32(a))
+			if (prandom_u32() >= nla_get_u32(a))
 				return 0;
 			break;
 
@@ -551,6 +551,8 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 		case OVS_ACTION_ATTR_SAMPLE:
 			err = sample(dp, skb, a);
+			if (unlikely(err)) /* skb already freed. */
+				return err;
 			break;
 		}
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6f5e1dd3be2..9db4bf6740d 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -44,23 +44,49 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/inetdevice.h>
 #include <linux/list.h>
-#include <linux/lockdep.h>
 #include <linux/openvswitch.h>
 #include <linux/rculist.h>
 #include <linux/dmi.h>
-#include <linux/workqueue.h>
+#include <linux/genetlink.h>
+#include <net/genetlink.h>
 #include <net/genetlink.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
 #include "datapath.h"
 #include "flow.h"
+#include "flow_table.h"
 #include "flow_netlink.h"
 #include "vport-internal_dev.h"
 #include "vport-netdev.h"
 
 int ovs_net_id __read_mostly;
 
+static struct genl_family dp_packet_genl_family;
+static struct genl_family dp_flow_genl_family;
+static struct genl_family dp_datapath_genl_family;
+
+static struct genl_multicast_group ovs_dp_flow_multicast_group = {
+	.name = OVS_FLOW_MCGROUP
+};
+
+static struct genl_multicast_group ovs_dp_datapath_multicast_group = {
+	.name = OVS_DATAPATH_MCGROUP
+};
+
+struct genl_multicast_group ovs_dp_vport_multicast_group = {
+	.name = OVS_VPORT_MCGROUP
+};
+
+/* Check if need to build a reply message.
+ * OVS userspace sets the NLM_F_ECHO flag if it needs the reply. */
+static bool ovs_must_notify(struct genl_info *info,
+			    const struct genl_multicast_group *grp)
+{
+	return info->nlhdr->nlmsg_flags & NLM_F_ECHO ||
+		netlink_has_listeners(genl_info_net(info)->genl_sock, 0);
+}
+
 static void ovs_notify(struct genl_family *family,
 		       struct sk_buff *skb, struct genl_info *info)
 {
@@ -108,10 +134,9 @@ int lockdep_ovsl_is_held(void)
 #endif
 
 static struct vport *new_vport(const struct vport_parms *);
-static int queue_gso_packets(struct net *, int dp_ifindex, struct sk_buff *,
+static int queue_gso_packets(struct datapath *dp, struct sk_buff *,
 			     const struct dp_upcall_info *);
-static int queue_userspace_packet(struct net *, int dp_ifindex,
-				  struct sk_buff *,
+static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
 				  const struct dp_upcall_info *);
 
 /* Must be called with rcu_read_lock or ovs_mutex. */
@@ -133,7 +158,7 @@ static struct datapath *get_dp(struct net *net, int dp_ifindex)
 }
 
 /* Must be called with rcu_read_lock or ovs_mutex. */
-const char *ovs_dp_name(const struct datapath *dp)
+static const char *ovs_dp_name(const struct datapath *dp)
 {
 	struct vport *vport = ovs_vport_ovsl_rcu(dp, OVSP_LOCAL);
 	return vport->ops->get_name(vport);
@@ -161,7 +186,6 @@ static void destroy_dp_rcu(struct rcu_head *rcu)
 {
 	struct datapath *dp = container_of(rcu, struct datapath, rcu);
 
-	ovs_flow_tbl_destroy(&dp->table);
 	free_percpu(dp->stats_percpu);
 	release_net(ovs_dp_get_net(dp));
 	kfree(dp->ports);
@@ -174,6 +198,7 @@ static struct hlist_head *vport_hash_bucket(const struct datapath *dp,
 	return &dp->ports[port_no & (DP_VPORT_HASH_BUCKETS - 1)];
 }
 
+/* Called with ovs_mutex or RCU read lock. */
 struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no)
 {
 	struct vport *vport;
@@ -234,7 +259,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
 	}
 
 	/* Look up flow. */
-	flow = ovs_flow_tbl_lookup(&dp->table, &key, &n_mask_hit);
+	flow = ovs_flow_tbl_lookup_stats(&dp->table, &key, &n_mask_hit);
 	if (unlikely(!flow)) {
 		struct dp_upcall_info upcall;
 
@@ -251,33 +276,22 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
 	OVS_CB(skb)->flow = flow;
 	OVS_CB(skb)->pkt_key = &key;
 
-	stats_counter = &stats->n_hit;
-	ovs_flow_used(OVS_CB(skb)->flow, skb);
+	ovs_flow_stats_update(OVS_CB(skb)->flow, key.tp.flags, skb);
 	ovs_execute_actions(dp, skb);
+	stats_counter = &stats->n_hit;
 
 out:
 	/* Update datapath statistics. */
-	u64_stats_update_begin(&stats->sync);
+	u64_stats_update_begin(&stats->syncp);
 	(*stats_counter)++;
 	stats->n_mask_hit += n_mask_hit;
-	u64_stats_update_end(&stats->sync);
+	u64_stats_update_end(&stats->syncp);
 }
 
-static struct genl_family dp_packet_genl_family = {
-	.id = GENL_ID_GENERATE,
-	.hdrsize = sizeof(struct ovs_header),
-	.name = OVS_PACKET_FAMILY,
-	.version = OVS_PACKET_VERSION,
-	.maxattr = OVS_PACKET_ATTR_MAX,
-	.netnsok = true,
-	.parallel_ops = true,
-};
-
 int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 		  const struct dp_upcall_info *upcall_info)
 {
 	struct dp_stats_percpu *stats;
-	int dp_ifindex;
 	int err;
 
 	if (upcall_info->portid == 0) {
@@ -285,16 +299,10 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 		goto err;
 	}
 
-	dp_ifindex = get_dpifindex(dp);
-	if (!dp_ifindex) {
-		err = -ENODEV;
-		goto err;
-	}
-
 	if (!skb_is_gso(skb))
-		err = queue_userspace_packet(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info);
+		err = queue_userspace_packet(dp, skb, upcall_info);
 	else
-		err = queue_gso_packets(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info);
+		err = queue_gso_packets(dp, skb, upcall_info);
 	if (err)
 		goto err;
 
@@ -303,15 +311,14 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 err:
 	stats = this_cpu_ptr(dp->stats_percpu);
 
-	u64_stats_update_begin(&stats->sync);
+	u64_stats_update_begin(&stats->syncp);
 	stats->n_lost++;
-	u64_stats_update_end(&stats->sync);
+	u64_stats_update_end(&stats->syncp);
 
 	return err;
 }
 
-static int queue_gso_packets(struct net *net, int dp_ifindex,
-			     struct sk_buff *skb,
+static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     const struct dp_upcall_info *upcall_info)
 {
 	unsigned short gso_type = skb_shinfo(skb)->gso_type;
@@ -320,14 +327,14 @@ static int queue_gso_packets(struct net *net, int dp_ifindex,
 	struct sk_buff *segs, *nskb;
 	int err;
 
-	segs = __skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM, false);
+	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
 	if (IS_ERR(segs))
 		return PTR_ERR(segs);
 
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
-		err = queue_userspace_packet(net, dp_ifindex, skb, upcall_info);
+		err = queue_userspace_packet(dp, skb, upcall_info);
 		if (err)
 			break;
 
@@ -380,11 +387,11 @@ static size_t key_attr_size(void)
 		+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
 }
 
-static size_t upcall_msg_size(const struct sk_buff *skb,
-			      const struct nlattr *userdata)
+static size_t upcall_msg_size(const struct nlattr *userdata,
+			      unsigned int hdrlen)
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
-		+ nla_total_size(skb->len) /* OVS_PACKET_ATTR_PACKET */
+		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
 		+ nla_total_size(key_attr_size()); /* OVS_PACKET_ATTR_KEY */
 
 	/* OVS_PACKET_ATTR_USERDATA */
@@ -394,15 +401,24 @@ static size_t upcall_msg_size(const struct sk_buff *skb,
 	return size;
 }
 
-static int queue_userspace_packet(struct net *net, int dp_ifindex,
-				  struct sk_buff *skb,
+static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 				  const struct dp_upcall_info *upcall_info)
 {
 	struct ovs_header *upcall;
 	struct sk_buff *nskb = NULL;
 	struct sk_buff *user_skb; /* to be queued to userspace */
 	struct nlattr *nla;
-	int err;
+	struct genl_info info = {
+		.dst_sk = ovs_dp_get_net(dp)->genl_sock,
+		.snd_portid = upcall_info->portid,
+	};
+	size_t len;
+	unsigned int hlen;
+	int err, dp_ifindex;
+
+	dp_ifindex = get_dpifindex(dp);
+	if (!dp_ifindex)
+		return -ENODEV;
 
 	if (vlan_tx_tag_present(skb)) {
 		nskb = skb_clone(skb, GFP_ATOMIC);
@@ -422,7 +438,22 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex,
 		goto out;
 	}
 
-	user_skb = genlmsg_new(upcall_msg_size(skb, upcall_info->userdata), GFP_ATOMIC);
+	/* Complete checksum if needed */
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    (err = skb_checksum_help(skb)))
+		goto out;
+
+	/* Older versions of OVS user space enforce alignment of the last
+	 * Netlink attribute to NLA_ALIGNTO which would require extensive
+	 * padding logic. Only perform zerocopy if padding is not required.
+	 */
+	if (dp->user_features & OVS_DP_F_UNALIGNED)
+		hlen = skb_zerocopy_headlen(skb);
+	else
+		hlen = skb->len;
+
+	len = upcall_msg_size(upcall_info->userdata, hlen);
+	user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
 		goto out;
@@ -441,26 +472,36 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex,
 			  nla_len(upcall_info->userdata),
 			  nla_data(upcall_info->userdata));
 
-	nla = __nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, skb->len);
+	/* Only reserve room for attribute header, packet data is added
+	 * in skb_zerocopy() */
+	if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
+		err = -ENOBUFS;
+		goto out;
+	}
+	nla->nla_len = nla_attr_size(skb->len);
 
-	skb_copy_and_csum_dev(skb, nla_data(nla));
+	err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+	if (err)
+		goto out;
 
-	genlmsg_end(user_skb, upcall);
-	err = genlmsg_unicast(net, user_skb, upcall_info->portid);
+	/* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */
+	if (!(dp->user_features & OVS_DP_F_UNALIGNED)) {
+		size_t plen = NLA_ALIGN(user_skb->len) - user_skb->len;
 
+		if (plen > 0)
+			memset(skb_put(user_skb, plen), 0, plen);
+	}
+
+	((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len;
+
+	err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid);
 out:
+	if (err)
+		skb_tx_error(skb);
 	kfree_skb(nskb);
 	return err;
 }
 
-static void clear_stats(struct sw_flow *flow)
-{
-	flow->used = 0;
-	flow->tcp_flags = 0;
-	flow->packet_count = 0;
-	flow->byte_count = 0;
-}
-
 static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 {
 	struct ovs_header *ovs_header = info->userhdr;
@@ -565,6 +606,18 @@ static const struct genl_ops dp_packet_genl_ops[] = {
 	}
 };
 
+static struct genl_family dp_packet_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_PACKET_FAMILY,
+	.version = OVS_PACKET_VERSION,
+	.maxattr = OVS_PACKET_ATTR_MAX,
+	.netnsok = true,
+	.parallel_ops = true,
+	.ops = dp_packet_genl_ops,
+	.n_ops = ARRAY_SIZE(dp_packet_genl_ops),
+};
+
 static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
 			 struct ovs_dp_megaflow_stats *mega_stats)
 {
@@ -585,9 +638,9 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
 		percpu_stats = per_cpu_ptr(dp->stats_percpu, i);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&percpu_stats->sync);
+			start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
 			local_stats = *percpu_stats;
-		} while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start));
+		} while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
 
 		stats->n_hit += local_stats.n_hit;
 		stats->n_missed += local_stats.n_missed;
@@ -596,26 +649,6 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
 	}
 }
 
-static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
-	[OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
-	[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
-	[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
-};
-
-static struct genl_family dp_flow_genl_family = {
-	.id = GENL_ID_GENERATE,
-	.hdrsize = sizeof(struct ovs_header),
-	.name = OVS_FLOW_FAMILY,
-	.version = OVS_FLOW_VERSION,
-	.maxattr = OVS_FLOW_ATTR_MAX,
-	.netnsok = true,
-	.parallel_ops = true,
-};
-
-static struct genl_multicast_group ovs_dp_flow_multicast_group = {
-	.name = OVS_FLOW_MCGROUP
-};
-
 static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
 {
 	return NLMSG_ALIGN(sizeof(struct ovs_header))
@@ -627,25 +660,25 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
 		+ nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */
 }
 
-/* Called with ovs_mutex. */
-static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
+/* Called with ovs_mutex or RCU read lock. */
+static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
 				  struct sk_buff *skb, u32 portid,
 				  u32 seq, u32 flags, u8 cmd)
 {
 	const int skb_orig_len = skb->len;
 	struct nlattr *start;
 	struct ovs_flow_stats stats;
+	__be16 tcp_flags;
+	unsigned long used;
 	struct ovs_header *ovs_header;
 	struct nlattr *nla;
-	unsigned long used;
-	u8 tcp_flags;
 	int err;
 
 	ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd);
 	if (!ovs_header)
 		return -EMSGSIZE;
 
-	ovs_header->dp_ifindex = get_dpifindex(dp);
+	ovs_header->dp_ifindex = dp_ifindex;
 
 	/* Fill flow key. */
 	nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY);
@@ -667,24 +700,18 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
 
 	nla_nest_end(skb, nla);
 
-	spin_lock_bh(&flow->lock);
-	used = flow->used;
-	stats.n_packets = flow->packet_count;
-	stats.n_bytes = flow->byte_count;
-	tcp_flags = (u8)ntohs(flow->tcp_flags);
-	spin_unlock_bh(&flow->lock);
+	ovs_flow_stats_get(flow, &stats, &used, &tcp_flags);
 
 	if (used &&
 	    nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used)))
 		goto nla_put_failure;
 
 	if (stats.n_packets &&
-	    nla_put(skb, OVS_FLOW_ATTR_STATS,
-		    sizeof(struct ovs_flow_stats), &stats))
+	    nla_put(skb, OVS_FLOW_ATTR_STATS, sizeof(struct ovs_flow_stats), &stats))
 		goto nla_put_failure;
 
-	if (tcp_flags &&
-	    nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, tcp_flags))
+	if ((u8)ntohs(tcp_flags) &&
+	     nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, (u8)ntohs(tcp_flags)))
 		goto nla_put_failure;
 
 	/* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if
@@ -701,11 +728,10 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
 	if (start) {
 		const struct sw_flow_actions *sf_acts;
 
-		sf_acts = rcu_dereference_check(flow->sf_acts,
-						lockdep_ovsl_is_held());
-
+		sf_acts = rcu_dereference_ovsl(flow->sf_acts);
 		err = ovs_nla_put_actions(sf_acts->actions,
 					  sf_acts->actions_len, skb);
+
 		if (!err)
 			nla_nest_end(skb, start);
 		else {
@@ -726,49 +752,192 @@ error:
 	return err;
 }
 
-static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow)
+/* May not be called with RCU read lock. */
+static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *acts,
+					       struct genl_info *info,
+					       bool always)
 {
-	const struct sw_flow_actions *sf_acts;
+	struct sk_buff *skb;
 
-	sf_acts = ovsl_dereference(flow->sf_acts);
+	if (!always && !ovs_must_notify(info, &ovs_dp_flow_multicast_group))
+		return NULL;
+
+	skb = genlmsg_new_unicast(ovs_flow_cmd_msg_size(acts), info, GFP_KERNEL);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
 
-	return genlmsg_new(ovs_flow_cmd_msg_size(sf_acts), GFP_KERNEL);
+	return skb;
 }
 
-static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow,
-					       struct datapath *dp,
-					       u32 portid, u32 seq, u8 cmd)
+/* Called with ovs_mutex. */
+static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow,
+					       int dp_ifindex,
+					       struct genl_info *info, u8 cmd,
+					       bool always)
 {
 	struct sk_buff *skb;
 	int retval;
 
-	skb = ovs_flow_cmd_alloc_info(flow);
-	if (!skb)
-		return ERR_PTR(-ENOMEM);
+	skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), info,
+				      always);
+	if (!skb || IS_ERR(skb))
+		return skb;
 
-	retval = ovs_flow_cmd_fill_info(flow, dp, skb, portid, seq, 0, cmd);
+	retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb,
+					info->snd_portid, info->snd_seq, 0,
+					cmd);
 	BUG_ON(retval < 0);
 	return skb;
 }
 
-static struct sw_flow *__ovs_flow_tbl_lookup(struct flow_table *tbl,
-					      const struct sw_flow_key *key)
+static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 {
-	u32 __always_unused n_mask_hit;
+	struct nlattr **a = info->attrs;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct sw_flow *flow, *new_flow;
+	struct sw_flow_mask mask;
+	struct sk_buff *reply;
+	struct datapath *dp;
+	struct sw_flow_actions *acts;
+	struct sw_flow_match match;
+	int error;
+
+	/* Must have key and actions. */
+	error = -EINVAL;
+	if (!a[OVS_FLOW_ATTR_KEY])
+		goto error;
+	if (!a[OVS_FLOW_ATTR_ACTIONS])
+		goto error;
+
+	/* Most of the time we need to allocate a new flow, do it before
+	 * locking.
+	 */
+	new_flow = ovs_flow_alloc();
+	if (IS_ERR(new_flow)) {
+		error = PTR_ERR(new_flow);
+		goto error;
+	}
+
+	/* Extract key. */
+	ovs_match_init(&match, &new_flow->unmasked_key, &mask);
+	error = ovs_nla_get_match(&match,
+				  a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
+	if (error)
+		goto err_kfree_flow;
+
+	ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask);
+
+	/* Validate actions. */
+	acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
+	error = PTR_ERR(acts);
+	if (IS_ERR(acts))
+		goto err_kfree_flow;
+
+	error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
+				     0, &acts);
+	if (error) {
+		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
+		goto err_kfree_acts;
+	}
+
+	reply = ovs_flow_cmd_alloc_info(acts, info, false);
+	if (IS_ERR(reply)) {
+		error = PTR_ERR(reply);
+		goto err_kfree_acts;
+	}
+
+	ovs_lock();
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (unlikely(!dp)) {
+		error = -ENODEV;
+		goto err_unlock_ovs;
+	}
+	/* Check if this is a duplicate flow */
+	flow = ovs_flow_tbl_lookup(&dp->table, &new_flow->unmasked_key);
+	if (likely(!flow)) {
+		rcu_assign_pointer(new_flow->sf_acts, acts);
+
+		/* Put flow in bucket. */
+		error = ovs_flow_tbl_insert(&dp->table, new_flow, &mask);
+		if (unlikely(error)) {
+			acts = NULL;
+			goto err_unlock_ovs;
+		}
+
+		if (unlikely(reply)) {
+			error = ovs_flow_cmd_fill_info(new_flow,
+						       ovs_header->dp_ifindex,
+						       reply, info->snd_portid,
+						       info->snd_seq, 0,
+						       OVS_FLOW_CMD_NEW);
+			BUG_ON(error < 0);
+		}
+		ovs_unlock();
+	} else {
+		struct sw_flow_actions *old_acts;
+
+		/* Bail out if we're not allowed to modify an existing flow.
+		 * We accept NLM_F_CREATE in place of the intended NLM_F_EXCL
+		 * because Generic Netlink treats the latter as a dump
+		 * request.  We also accept NLM_F_EXCL in case that bug ever
+		 * gets fixed.
+		 */
+		if (unlikely(info->nlhdr->nlmsg_flags & (NLM_F_CREATE
+							 | NLM_F_EXCL))) {
+			error = -EEXIST;
+			goto err_unlock_ovs;
+		}
+		/* The unmasked key has to be the same for flow updates. */
+		if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
+			flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+			if (!flow) {
+				error = -ENOENT;
+				goto err_unlock_ovs;
+			}
+		}
+		/* Update actions. */
+		old_acts = ovsl_dereference(flow->sf_acts);
+		rcu_assign_pointer(flow->sf_acts, acts);
+
+		if (unlikely(reply)) {
+			error = ovs_flow_cmd_fill_info(flow,
+						       ovs_header->dp_ifindex,
+						       reply, info->snd_portid,
+						       info->snd_seq, 0,
+						       OVS_FLOW_CMD_NEW);
+			BUG_ON(error < 0);
+		}
+		ovs_unlock();
+
+		ovs_nla_free_flow_actions(old_acts);
+		ovs_flow_free(new_flow, false);
+	}
 
-	return ovs_flow_tbl_lookup(tbl, key, &n_mask_hit);
+	if (reply)
+		ovs_notify(&dp_flow_genl_family, reply, info);
+	return 0;
+
+err_unlock_ovs:
+	ovs_unlock();
+	kfree_skb(reply);
+err_kfree_acts:
+	kfree(acts);
+err_kfree_flow:
+	ovs_flow_free(new_flow, false);
+error:
+	return error;
 }
 
-static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
+static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
 	struct ovs_header *ovs_header = info->userhdr;
 	struct sw_flow_key key, masked_key;
-	struct sw_flow *flow = NULL;
+	struct sw_flow *flow;
 	struct sw_flow_mask mask;
-	struct sk_buff *reply;
+	struct sk_buff *reply = NULL;
 	struct datapath *dp;
-	struct sw_flow_actions *acts = NULL;
+	struct sw_flow_actions *old_acts = NULL, *acts = NULL;
 	struct sw_flow_match match;
 	int error;
 
@@ -795,99 +964,71 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
 					     &masked_key, 0, &acts);
 		if (error) {
 			OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
-			goto err_kfree;
+			goto err_kfree_acts;
+		}
+	}
+
+	/* Can allocate before locking if have acts. */
+	if (acts) {
+		reply = ovs_flow_cmd_alloc_info(acts, info, false);
+		if (IS_ERR(reply)) {
+			error = PTR_ERR(reply);
+			goto err_kfree_acts;
 		}
-	} else if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW) {
-		error = -EINVAL;
-		goto error;
 	}
 
 	ovs_lock();
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
-	error = -ENODEV;
-	if (!dp)
+	if (unlikely(!dp)) {
+		error = -ENODEV;
 		goto err_unlock_ovs;
-
-	/* Check if this is a duplicate flow */
-	flow = __ovs_flow_tbl_lookup(&dp->table, &key);
-	if (!flow) {
-		/* Bail out if we're not allowed to create a new flow. */
+	}
+	/* Check that the flow exists. */
+	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (unlikely(!flow)) {
 		error = -ENOENT;
-		if (info->genlhdr->cmd == OVS_FLOW_CMD_SET)
-			goto err_unlock_ovs;
-
-		/* Allocate flow. */
-		flow = ovs_flow_alloc();
-		if (IS_ERR(flow)) {
-			error = PTR_ERR(flow);
-			goto err_unlock_ovs;
-		}
-		clear_stats(flow);
+		goto err_unlock_ovs;
+	}
 
-		flow->key = masked_key;
-		flow->unmasked_key = key;
+	/* Update actions, if present. */
+	if (likely(acts)) {
+		old_acts = ovsl_dereference(flow->sf_acts);
 		rcu_assign_pointer(flow->sf_acts, acts);
 
-		/* Put flow in bucket. */
-		error = ovs_flow_tbl_insert(&dp->table, flow, &mask);
-		if (error) {
-			acts = NULL;
-			goto err_flow_free;
+		if (unlikely(reply)) {
+			error = ovs_flow_cmd_fill_info(flow,
+						       ovs_header->dp_ifindex,
+						       reply, info->snd_portid,
+						       info->snd_seq, 0,
+						       OVS_FLOW_CMD_NEW);
+			BUG_ON(error < 0);
 		}
-
-		reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
-						info->snd_seq, OVS_FLOW_CMD_NEW);
 	} else {
-		/* We found a matching flow. */
-		struct sw_flow_actions *old_acts;
-
-		/* Bail out if we're not allowed to modify an existing flow.
-		 * We accept NLM_F_CREATE in place of the intended NLM_F_EXCL
-		 * because Generic Netlink treats the latter as a dump
-		 * request.  We also accept NLM_F_EXCL in case that bug ever
-		 * gets fixed.
-		 */
-		error = -EEXIST;
-		if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW &&
-		    info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL))
-			goto err_unlock_ovs;
-
-		/* The unmasked key has to be the same for flow updates. */
-		error = -EINVAL;
-		if (!ovs_flow_cmp_unmasked_key(flow, &match)) {
-			OVS_NLERR("Flow modification message rejected, unmasked key does not match.\n");
+		/* Could not alloc without acts before locking. */
+		reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex,
+						info, OVS_FLOW_CMD_NEW, false);
+		if (unlikely(IS_ERR(reply))) {
+			error = PTR_ERR(reply);
 			goto err_unlock_ovs;
 		}
-
-		/* Update actions. */
-		old_acts = ovsl_dereference(flow->sf_acts);
-		rcu_assign_pointer(flow->sf_acts, acts);
-		ovs_nla_free_flow_actions(old_acts);
-
-		reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
-					       info->snd_seq, OVS_FLOW_CMD_NEW);
-
-		/* Clear stats. */
-		if (a[OVS_FLOW_ATTR_CLEAR]) {
-			spin_lock_bh(&flow->lock);
-			clear_stats(flow);
-			spin_unlock_bh(&flow->lock);
-		}
 	}
+
+	/* Clear stats. */
+	if (a[OVS_FLOW_ATTR_CLEAR])
+		ovs_flow_stats_clear(flow);
 	ovs_unlock();
 
-	if (!IS_ERR(reply))
+	if (reply)
 		ovs_notify(&dp_flow_genl_family, reply, info);
-	else
-		genl_set_err(&dp_flow_genl_family, sock_net(skb->sk), 0,
-			     0, PTR_ERR(reply));
+	if (old_acts)
+		ovs_nla_free_flow_actions(old_acts);
+
 	return 0;
 
-err_flow_free:
-	ovs_flow_free(flow, false);
 err_unlock_ovs:
 	ovs_unlock();
-err_kfree:
+	kfree_skb(reply);
+err_kfree_acts:
 	kfree(acts);
 error:
 	return error;
@@ -921,14 +1062,14 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 		goto unlock;
 	}
 
-	flow = __ovs_flow_tbl_lookup(&dp->table, &key);
-	if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
+	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (!flow) {
 		err = -ENOENT;
 		goto unlock;
 	}
 
-	reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
-					info->snd_seq, OVS_FLOW_CMD_NEW);
+	reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info,
+					OVS_FLOW_CMD_NEW, true);
 	if (IS_ERR(reply)) {
 		err = PTR_ERR(reply);
 		goto unlock;
@@ -952,45 +1093,53 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow_match match;
 	int err;
 
+	if (likely(a[OVS_FLOW_ATTR_KEY])) {
+		ovs_match_init(&match, &key, NULL);
+		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
+		if (unlikely(err))
+			return err;
+	}
+
 	ovs_lock();
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
-	if (!dp) {
+	if (unlikely(!dp)) {
 		err = -ENODEV;
 		goto unlock;
 	}
 
-	if (!a[OVS_FLOW_ATTR_KEY]) {
+	if (unlikely(!a[OVS_FLOW_ATTR_KEY])) {
 		err = ovs_flow_tbl_flush(&dp->table);
 		goto unlock;
 	}
 
-	ovs_match_init(&match, &key, NULL);
-	err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
-	if (err)
-		goto unlock;
-
-	flow = __ovs_flow_tbl_lookup(&dp->table, &key);
-	if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
+	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (unlikely(!flow)) {
 		err = -ENOENT;
 		goto unlock;
 	}
 
-	reply = ovs_flow_cmd_alloc_info(flow);
-	if (!reply) {
-		err = -ENOMEM;
-		goto unlock;
-	}
-
 	ovs_flow_tbl_remove(&dp->table, flow);
+	ovs_unlock();
 
-	err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_portid,
-				     info->snd_seq, 0, OVS_FLOW_CMD_DEL);
-	BUG_ON(err < 0);
+	reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts,
+					info, false);
+	if (likely(reply)) {
+		if (likely(!IS_ERR(reply))) {
+			rcu_read_lock();	/*To keep RCU checker happy. */
+			err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex,
+						     reply, info->snd_portid,
+						     info->snd_seq, 0,
+						     OVS_FLOW_CMD_DEL);
+			rcu_read_unlock();
+			BUG_ON(err < 0);
+
+			ovs_notify(&dp_flow_genl_family, reply, info);
+		} else {
+			netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, PTR_ERR(reply));
+		}
+	}
 
 	ovs_flow_free(flow, true);
-	ovs_unlock();
-
-	ovs_notify(&dp_flow_genl_family, reply, info);
 	return 0;
 unlock:
 	ovs_unlock();
@@ -1021,7 +1170,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (!flow)
 			break;
 
-		if (ovs_flow_cmd_fill_info(flow, dp, skb,
+		if (ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, skb,
 					   NETLINK_CB(cb->skb).portid,
 					   cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					   OVS_FLOW_CMD_NEW) < 0)
@@ -1034,11 +1183,17 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-static const struct genl_ops dp_flow_genl_ops[] = {
+static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
+	[OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
+	[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
+	[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
+};
+
+static struct genl_ops dp_flow_genl_ops[] = {
 	{ .cmd = OVS_FLOW_CMD_NEW,
 	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .policy = flow_policy,
-	  .doit = ovs_flow_cmd_new_or_set
+	  .doit = ovs_flow_cmd_new
 	},
 	{ .cmd = OVS_FLOW_CMD_DEL,
 	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -1054,27 +1209,22 @@ static const struct genl_ops dp_flow_genl_ops[] = {
 	{ .cmd = OVS_FLOW_CMD_SET,
 	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .policy = flow_policy,
-	  .doit = ovs_flow_cmd_new_or_set,
+	  .doit = ovs_flow_cmd_set,
 	},
 };
 
-static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
-	[OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
-	[OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 },
-};
-
-static struct genl_family dp_datapath_genl_family = {
+static struct genl_family dp_flow_genl_family = {
 	.id = GENL_ID_GENERATE,
 	.hdrsize = sizeof(struct ovs_header),
-	.name = OVS_DATAPATH_FAMILY,
-	.version = OVS_DATAPATH_VERSION,
-	.maxattr = OVS_DP_ATTR_MAX,
+	.name = OVS_FLOW_FAMILY,
+	.version = OVS_FLOW_VERSION,
+	.maxattr = OVS_FLOW_ATTR_MAX,
 	.netnsok = true,
 	.parallel_ops = true,
-};
-
-static struct genl_multicast_group ovs_dp_datapath_multicast_group = {
-	.name = OVS_DATAPATH_MCGROUP
+	.ops = dp_flow_genl_ops,
+	.n_ops = ARRAY_SIZE(dp_flow_genl_ops),
+	.mcgrps = &ovs_dp_flow_multicast_group,
+	.n_mcgrps = 1,
 };
 
 static size_t ovs_dp_cmd_msg_size(void)
@@ -1084,10 +1234,12 @@ static size_t ovs_dp_cmd_msg_size(void)
 	msgsize += nla_total_size(IFNAMSIZ);
 	msgsize += nla_total_size(sizeof(struct ovs_dp_stats));
 	msgsize += nla_total_size(sizeof(struct ovs_dp_megaflow_stats));
+	msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */
 
 	return msgsize;
 }
 
+/* Called with ovs_mutex or RCU read lock. */
 static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 				u32 portid, u32 seq, u32 flags, u8 cmd)
 {
@@ -1103,9 +1255,7 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 
 	ovs_header->dp_ifindex = get_dpifindex(dp);
 
-	rcu_read_lock();
 	err = nla_put_string(skb, OVS_DP_ATTR_NAME, ovs_dp_name(dp));
-	rcu_read_unlock();
 	if (err)
 		goto nla_put_failure;
 
@@ -1119,6 +1269,9 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 			&dp_megaflow_stats))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features))
+		goto nla_put_failure;
+
 	return genlmsg_end(skb, ovs_header);
 
 nla_put_failure:
@@ -1127,25 +1280,12 @@ error:
 	return -EMSGSIZE;
 }
 
-static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 portid,
-					     u32 seq, u8 cmd)
+static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info)
 {
-	struct sk_buff *skb;
-	int retval;
-
-	skb = genlmsg_new(ovs_dp_cmd_msg_size(), GFP_KERNEL);
-	if (!skb)
-		return ERR_PTR(-ENOMEM);
-
-	retval = ovs_dp_cmd_fill_info(dp, skb, portid, seq, 0, cmd);
-	if (retval < 0) {
-		kfree_skb(skb);
-		return ERR_PTR(retval);
-	}
-	return skb;
+	return genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL);
 }
 
-/* Called with ovs_mutex. */
+/* Called with rcu_read_lock or ovs_mutex. */
 static struct datapath *lookup_datapath(struct net *net,
 					struct ovs_header *ovs_header,
 					struct nlattr *a[OVS_DP_ATTR_MAX + 1])
@@ -1157,14 +1297,30 @@ static struct datapath *lookup_datapath(struct net *net,
 	else {
 		struct vport *vport;
 
-		rcu_read_lock();
 		vport = ovs_vport_locate(net, nla_data(a[OVS_DP_ATTR_NAME]));
 		dp = vport && vport->port_no == OVSP_LOCAL ? vport->dp : NULL;
-		rcu_read_unlock();
 	}
 	return dp ? dp : ERR_PTR(-ENODEV);
 }
 
+static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *info)
+{
+	struct datapath *dp;
+
+	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
+	if (IS_ERR(dp))
+		return;
+
+	WARN(dp->user_features, "Dropping previously announced user features\n");
+	dp->user_features = 0;
+}
+
+static void ovs_dp_change(struct datapath *dp, struct nlattr **a)
+{
+	if (a[OVS_DP_ATTR_USER_FEATURES])
+		dp->user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]);
+}
+
 static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
@@ -1179,12 +1335,14 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID])
 		goto err;
 
-	ovs_lock();
+	reply = ovs_dp_cmd_alloc_info(info);
+	if (!reply)
+		return -ENOMEM;
 
 	err = -ENOMEM;
 	dp = kzalloc(sizeof(*dp), GFP_KERNEL);
 	if (dp == NULL)
-		goto err_unlock_ovs;
+		goto err_free_reply;
 
 	ovs_dp_set_net(dp, hold_net(sock_net(skb->sk)));
 
@@ -1193,18 +1351,12 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		goto err_free_dp;
 
-	dp->stats_percpu = alloc_percpu(struct dp_stats_percpu);
+	dp->stats_percpu = netdev_alloc_pcpu_stats(struct dp_stats_percpu);
 	if (!dp->stats_percpu) {
 		err = -ENOMEM;
 		goto err_destroy_table;
 	}
 
-	for_each_possible_cpu(i) {
-		struct dp_stats_percpu *dpath_stats;
-		dpath_stats = per_cpu_ptr(dp->stats_percpu, i);
-		u64_stats_init(&dpath_stats->sync);
-	}
-
 	dp->ports = kmalloc(DP_VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
 			    GFP_KERNEL);
 	if (!dp->ports) {
@@ -1223,20 +1375,32 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	parms.port_no = OVSP_LOCAL;
 	parms.upcall_portid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]);
 
+	ovs_dp_change(dp, a);
+
+	/* So far only local changes have been made, now need the lock. */
+	ovs_lock();
+
 	vport = new_vport(&parms);
 	if (IS_ERR(vport)) {
 		err = PTR_ERR(vport);
 		if (err == -EBUSY)
 			err = -EEXIST;
 
+		if (err == -EEXIST) {
+			/* An outdated user space instance that does not understand
+			 * the concept of user_features has attempted to create a new
+			 * datapath and is likely to reuse it. Drop all user features.
+			 */
+			if (info->genlhdr->version < OVS_DP_VER_FEATURES)
+				ovs_dp_reset_user_features(skb, info);
+		}
+
 		goto err_destroy_ports_array;
 	}
 
-	reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
-				      info->snd_seq, OVS_DP_CMD_NEW);
-	err = PTR_ERR(reply);
-	if (IS_ERR(reply))
-		goto err_destroy_local_port;
+	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+				   info->snd_seq, 0, OVS_DP_CMD_NEW);
+	BUG_ON(err < 0);
 
 	ovs_net = net_generic(ovs_dp_get_net(dp), ovs_net_id);
 	list_add_tail_rcu(&dp->list_node, &ovs_net->dps);
@@ -1246,19 +1410,18 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
-err_destroy_local_port:
-	ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));
 err_destroy_ports_array:
+	ovs_unlock();
 	kfree(dp->ports);
 err_destroy_percpu:
 	free_percpu(dp->stats_percpu);
 err_destroy_table:
-	ovs_flow_tbl_destroy(&dp->table);
+	ovs_flow_tbl_destroy(&dp->table, false);
 err_free_dp:
 	release_net(ovs_dp_get_net(dp));
 	kfree(dp);
-err_unlock_ovs:
-	ovs_unlock();
+err_free_reply:
+	kfree_skb(reply);
 err:
 	return err;
 }
@@ -1280,10 +1443,13 @@ static void __dp_destroy(struct datapath *dp)
 	list_del_rcu(&dp->list_node);
 
 	/* OVSP_LOCAL is datapath internal port. We need to make sure that
-	 * all port in datapath are destroyed first before freeing datapath.
+	 * all ports in datapath are destroyed first before freeing datapath.
 	 */
 	ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));
 
+	/* RCU destroy the flow table */
+	ovs_flow_tbl_destroy(&dp->table, true);
+
 	call_rcu(&dp->rcu, destroy_dp_rcu);
 }
 
@@ -1293,17 +1459,19 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	int err;
 
+	reply = ovs_dp_cmd_alloc_info(info);
+	if (!reply)
+		return -ENOMEM;
+
 	ovs_lock();
 	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
 	err = PTR_ERR(dp);
 	if (IS_ERR(dp))
-		goto unlock;
+		goto err_unlock_free;
 
-	reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
-				      info->snd_seq, OVS_DP_CMD_DEL);
-	err = PTR_ERR(reply);
-	if (IS_ERR(reply))
-		goto unlock;
+	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+				   info->snd_seq, 0, OVS_DP_CMD_DEL);
+	BUG_ON(err < 0);
 
 	__dp_destroy(dp);
 	ovs_unlock();
@@ -1311,8 +1479,10 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 
 	return 0;
-unlock:
+
+err_unlock_free:
 	ovs_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1322,28 +1492,30 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	int err;
 
+	reply = ovs_dp_cmd_alloc_info(info);
+	if (!reply)
+		return -ENOMEM;
+
 	ovs_lock();
 	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
 	err = PTR_ERR(dp);
 	if (IS_ERR(dp))
-		goto unlock;
+		goto err_unlock_free;
 
-	reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
-				      info->snd_seq, OVS_DP_CMD_NEW);
-	if (IS_ERR(reply)) {
-		err = PTR_ERR(reply);
-		genl_set_err(&dp_datapath_genl_family, sock_net(skb->sk), 0,
-			     0, err);
-		err = 0;
-		goto unlock;
-	}
+	ovs_dp_change(dp, info->attrs);
+
+	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+				   info->snd_seq, 0, OVS_DP_CMD_NEW);
+	BUG_ON(err < 0);
 
 	ovs_unlock();
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 
 	return 0;
-unlock:
+
+err_unlock_free:
 	ovs_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1353,25 +1525,26 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	int err;
 
-	ovs_lock();
+	reply = ovs_dp_cmd_alloc_info(info);
+	if (!reply)
+		return -ENOMEM;
+
+	rcu_read_lock();
 	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
 	if (IS_ERR(dp)) {
 		err = PTR_ERR(dp);
-		goto unlock;
-	}
-
-	reply = ovs_dp_cmd_build_info(dp, info->snd_portid,
-				      info->snd_seq, OVS_DP_CMD_NEW);
-	if (IS_ERR(reply)) {
-		err = PTR_ERR(reply);
-		goto unlock;
+		goto err_unlock_free;
 	}
+	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+				   info->snd_seq, 0, OVS_DP_CMD_NEW);
+	BUG_ON(err < 0);
+	rcu_read_unlock();
 
-	ovs_unlock();
 	return genlmsg_reply(reply, info);
 
-unlock:
-	ovs_unlock();
+err_unlock_free:
+	rcu_read_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1398,7 +1571,13 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-static const struct genl_ops dp_datapath_genl_ops[] = {
+static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
+	[OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+	[OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+	[OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 },
+};
+
+static struct genl_ops dp_datapath_genl_ops[] = {
 	{ .cmd = OVS_DP_CMD_NEW,
 	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .policy = datapath_policy,
@@ -1422,27 +1601,18 @@ static const struct genl_ops dp_datapath_genl_ops[] = {
 	},
 };
 
-static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
-	[OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
-	[OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
-	[OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
-	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
-	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
-	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
-};
-
-struct genl_family dp_vport_genl_family = {
+static struct genl_family dp_datapath_genl_family = {
 	.id = GENL_ID_GENERATE,
 	.hdrsize = sizeof(struct ovs_header),
-	.name = OVS_VPORT_FAMILY,
-	.version = OVS_VPORT_VERSION,
-	.maxattr = OVS_VPORT_ATTR_MAX,
+	.name = OVS_DATAPATH_FAMILY,
+	.version = OVS_DATAPATH_VERSION,
+	.maxattr = OVS_DP_ATTR_MAX,
 	.netnsok = true,
 	.parallel_ops = true,
-};
-
-struct genl_multicast_group ovs_dp_vport_multicast_group = {
-	.name = OVS_VPORT_MCGROUP
+	.ops = dp_datapath_genl_ops,
+	.n_ops = ARRAY_SIZE(dp_datapath_genl_ops),
+	.mcgrps = &ovs_dp_datapath_multicast_group,
+	.n_mcgrps = 1,
 };
 
 /* Called with ovs_mutex or RCU read lock. */
@@ -1484,7 +1654,12 @@ error:
 	return err;
 }
 
-/* Called with ovs_mutex or RCU read lock. */
+static struct sk_buff *ovs_vport_cmd_alloc_info(void)
+{
+	return nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+}
+
+/* Called with ovs_mutex, only via ovs_dp_notify_wq(). */
 struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
 					 u32 seq, u8 cmd)
 {
@@ -1546,33 +1721,35 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	u32 port_no;
 	int err;
 
-	err = -EINVAL;
 	if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
 	    !a[OVS_VPORT_ATTR_UPCALL_PID])
-		goto exit;
+		return -EINVAL;
+
+	port_no = a[OVS_VPORT_ATTR_PORT_NO]
+		? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0;
+	if (port_no >= DP_MAX_PORTS)
+		return -EFBIG;
+
+	reply = ovs_vport_cmd_alloc_info();
+	if (!reply)
+		return -ENOMEM;
 
 	ovs_lock();
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
 	err = -ENODEV;
 	if (!dp)
-		goto exit_unlock;
-
-	if (a[OVS_VPORT_ATTR_PORT_NO]) {
-		port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);
-
-		err = -EFBIG;
-		if (port_no >= DP_MAX_PORTS)
-			goto exit_unlock;
+		goto exit_unlock_free;
 
+	if (port_no) {
 		vport = ovs_vport_ovsl(dp, port_no);
 		err = -EBUSY;
 		if (vport)
-			goto exit_unlock;
+			goto exit_unlock_free;
 	} else {
 		for (port_no = 1; ; port_no++) {
 			if (port_no >= DP_MAX_PORTS) {
 				err = -EFBIG;
-				goto exit_unlock;
+				goto exit_unlock_free;
 			}
 			vport = ovs_vport_ovsl(dp, port_no);
 			if (!vport)
@@ -1590,22 +1767,19 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	vport = new_vport(&parms);
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
-		goto exit_unlock;
+		goto exit_unlock_free;
 
-	err = 0;
-	reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq,
-					 OVS_VPORT_CMD_NEW);
-	if (IS_ERR(reply)) {
-		err = PTR_ERR(reply);
-		ovs_dp_detach_port(vport);
-		goto exit_unlock;
-	}
+	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+	BUG_ON(err < 0);
+	ovs_unlock();
 
 	ovs_notify(&dp_vport_genl_family, reply, info);
+	return 0;
 
-exit_unlock:
+exit_unlock_free:
 	ovs_unlock();
-exit:
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1616,28 +1790,26 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct vport *vport;
 	int err;
 
+	reply = ovs_vport_cmd_alloc_info();
+	if (!reply)
+		return -ENOMEM;
+
 	ovs_lock();
 	vport = lookup_vport(sock_net(skb->sk), info->userhdr, a);
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
-		goto exit_unlock;
+		goto exit_unlock_free;
 
 	if (a[OVS_VPORT_ATTR_TYPE] &&
 	    nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type) {
 		err = -EINVAL;
-		goto exit_unlock;
-	}
-
-	reply = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!reply) {
-		err = -ENOMEM;
-		goto exit_unlock;
+		goto exit_unlock_free;
 	}
 
 	if (a[OVS_VPORT_ATTR_OPTIONS]) {
 		err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]);
 		if (err)
-			goto exit_free;
+			goto exit_unlock_free;
 	}
 
 	if (a[OVS_VPORT_ATTR_UPCALL_PID])
@@ -1651,10 +1823,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_vport_genl_family, reply, info);
 	return 0;
 
-exit_free:
-	kfree_skb(reply);
-exit_unlock:
+exit_unlock_free:
 	ovs_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1665,30 +1836,33 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct vport *vport;
 	int err;
 
+	reply = ovs_vport_cmd_alloc_info();
+	if (!reply)
+		return -ENOMEM;
+
 	ovs_lock();
 	vport = lookup_vport(sock_net(skb->sk), info->userhdr, a);
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
-		goto exit_unlock;
+		goto exit_unlock_free;
 
 	if (vport->port_no == OVSP_LOCAL) {
 		err = -EINVAL;
-		goto exit_unlock;
+		goto exit_unlock_free;
 	}
 
-	reply = ovs_vport_cmd_build_info(vport, info->snd_portid,
-					 info->snd_seq, OVS_VPORT_CMD_DEL);
-	err = PTR_ERR(reply);
-	if (IS_ERR(reply))
-		goto exit_unlock;
-
-	err = 0;
+	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+				      info->snd_seq, 0, OVS_VPORT_CMD_DEL);
+	BUG_ON(err < 0);
 	ovs_dp_detach_port(vport);
+	ovs_unlock();
 
 	ovs_notify(&dp_vport_genl_family, reply, info);
+	return 0;
 
-exit_unlock:
+exit_unlock_free:
 	ovs_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1700,24 +1874,25 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	struct vport *vport;
 	int err;
 
+	reply = ovs_vport_cmd_alloc_info();
+	if (!reply)
+		return -ENOMEM;
+
 	rcu_read_lock();
 	vport = lookup_vport(sock_net(skb->sk), ovs_header, a);
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
-		goto exit_unlock;
-
-	reply = ovs_vport_cmd_build_info(vport, info->snd_portid,
-					 info->snd_seq, OVS_VPORT_CMD_NEW);
-	err = PTR_ERR(reply);
-	if (IS_ERR(reply))
-		goto exit_unlock;
-
+		goto exit_unlock_free;
+	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+	BUG_ON(err < 0);
 	rcu_read_unlock();
 
 	return genlmsg_reply(reply, info);
 
-exit_unlock:
+exit_unlock_free:
 	rcu_read_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1728,11 +1903,12 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int bucket = cb->args[0], skip = cb->args[1];
 	int i, j = 0;
 
+	rcu_read_lock();
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
-	if (!dp)
+	if (!dp) {
+		rcu_read_unlock();
 		return -ENODEV;
-
-	rcu_read_lock();
+	}
 	for (i = bucket; i < DP_VPORT_HASH_BUCKETS; i++) {
 		struct vport *vport;
 
@@ -1759,7 +1935,16 @@ out:
 	return skb->len;
 }
 
-static const struct genl_ops dp_vport_genl_ops[] = {
+static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
+	[OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+	[OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
+	[OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
+};
+
+static struct genl_ops dp_vport_genl_ops[] = {
 	{ .cmd = OVS_VPORT_CMD_NEW,
 	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .policy = vport_policy,
@@ -1783,26 +1968,25 @@ static const struct genl_ops dp_vport_genl_ops[] = {
 	},
 };
 
-struct genl_family_and_ops {
-	struct genl_family *family;
-	const struct genl_ops *ops;
-	int n_ops;
-	const struct genl_multicast_group *group;
+struct genl_family dp_vport_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_VPORT_FAMILY,
+	.version = OVS_VPORT_VERSION,
+	.maxattr = OVS_VPORT_ATTR_MAX,
+	.netnsok = true,
+	.parallel_ops = true,
+	.ops = dp_vport_genl_ops,
+	.n_ops = ARRAY_SIZE(dp_vport_genl_ops),
+	.mcgrps = &ovs_dp_vport_multicast_group,
+	.n_mcgrps = 1,
 };
 
-static const struct genl_family_and_ops dp_genl_families[] = {
-	{ &dp_datapath_genl_family,
-	  dp_datapath_genl_ops, ARRAY_SIZE(dp_datapath_genl_ops),
-	  &ovs_dp_datapath_multicast_group },
-	{ &dp_vport_genl_family,
-	  dp_vport_genl_ops, ARRAY_SIZE(dp_vport_genl_ops),
-	  &ovs_dp_vport_multicast_group },
-	{ &dp_flow_genl_family,
-	  dp_flow_genl_ops, ARRAY_SIZE(dp_flow_genl_ops),
-	  &ovs_dp_flow_multicast_group },
-	{ &dp_packet_genl_family,
-	  dp_packet_genl_ops, ARRAY_SIZE(dp_packet_genl_ops),
-	  NULL },
+static struct genl_family * const dp_genl_families[] = {
+	&dp_datapath_genl_family,
+	&dp_vport_genl_family,
+	&dp_flow_genl_family,
+	&dp_packet_genl_family,
 };
 
 static void dp_unregister_genl(int n_families)
@@ -1810,33 +1994,25 @@ static void dp_unregister_genl(int n_families)
 	int i;
 
 	for (i = 0; i < n_families; i++)
-		genl_unregister_family(dp_genl_families[i].family);
+		genl_unregister_family(dp_genl_families[i]);
 }
 
 static int dp_register_genl(void)
 {
-	int n_registered;
 	int err;
 	int i;
 
-	n_registered = 0;
 	for (i = 0; i < ARRAY_SIZE(dp_genl_families); i++) {
-		const struct genl_family_and_ops *f = &dp_genl_families[i];
 
-		f->family->ops = f->ops;
-		f->family->n_ops = f->n_ops;
-		f->family->mcgrps = f->group;
-		f->family->n_mcgrps = f->group ? 1 : 0;
-		err = genl_register_family(f->family);
+		err = genl_register_family(dp_genl_families[i]);
 		if (err)
 			goto error;
-		n_registered++;
 	}
 
 	return 0;
 
 error:
-	dp_unregister_genl(n_registered);
+	dp_unregister_genl(i);
 	return err;
 }
 
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 4067ea41be2..7ede507500d 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -55,7 +55,7 @@ struct dp_stats_percpu {
 	u64 n_missed;
 	u64 n_lost;
 	u64 n_mask_hit;
-	struct u64_stats_sync sync;
+	struct u64_stats_sync syncp;
 };
 
 /**
@@ -88,6 +88,8 @@ struct datapath {
 	/* Network namespace ref. */
 	struct net *net;
 #endif
+
+	u32 user_features;
 };
 
 /**
@@ -145,6 +147,8 @@ int lockdep_ovsl_is_held(void);
 #define ASSERT_OVSL()		WARN_ON(unlikely(!lockdep_ovsl_is_held()))
 #define ovsl_dereference(p)					\
 	rcu_dereference_protected(p, lockdep_ovsl_is_held())
+#define rcu_dereference_ovsl(p)					\
+	rcu_dereference_check(p, lockdep_ovsl_is_held())
 
 static inline struct net *ovs_dp_get_net(struct datapath *dp)
 {
@@ -178,21 +182,21 @@ static inline struct vport *ovs_vport_ovsl(const struct datapath *dp, int port_n
 
 extern struct notifier_block ovs_dp_device_notifier;
 extern struct genl_family dp_vport_genl_family;
-extern struct genl_multicast_group ovs_dp_vport_multicast_group;
 
 void ovs_dp_process_received_packet(struct vport *, struct sk_buff *);
 void ovs_dp_detach_port(struct vport *);
 int ovs_dp_upcall(struct datapath *, struct sk_buff *,
 		  const struct dp_upcall_info *);
 
-const char *ovs_dp_name(const struct datapath *dp);
 struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
 					 u8 cmd);
 
 int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb);
 void ovs_dp_notify_wq(struct work_struct *work);
 
-#define OVS_NLERR(fmt, ...) \
-	pr_info_once("netlink: " fmt, ##__VA_ARGS__)
-
+#define OVS_NLERR(fmt, ...)					\
+do {								\
+	if (net_ratelimit())					\
+		pr_info("netlink: " fmt, ##__VA_ARGS__);	\
+} while (0)
 #endif /* datapath.h */
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index b409f527960..d07ab538fc9 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -35,6 +35,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/sctp.h>
+#include <linux/smp.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/icmp.h>
@@ -60,23 +61,113 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies)
 
 #define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF))
 
-void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb)
+void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
+			   struct sk_buff *skb)
 {
-	__be16 tcp_flags = 0;
+	struct flow_stats *stats;
+	int node = numa_node_id();
+
+	stats = rcu_dereference(flow->stats[node]);
+
+	/* Check if already have node-specific stats. */
+	if (likely(stats)) {
+		spin_lock(&stats->lock);
+		/* Mark if we write on the pre-allocated stats. */
+		if (node == 0 && unlikely(flow->stats_last_writer != node))
+			flow->stats_last_writer = node;
+	} else {
+		stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */
+		spin_lock(&stats->lock);
+
+		/* If the current NUMA-node is the only writer on the
+		 * pre-allocated stats keep using them.
+		 */
+		if (unlikely(flow->stats_last_writer != node)) {
+			/* A previous locker may have already allocated the
+			 * stats, so we need to check again.  If node-specific
+			 * stats were already allocated, we update the pre-
+			 * allocated stats as we have already locked them.
+			 */
+			if (likely(flow->stats_last_writer != NUMA_NO_NODE)
+			    && likely(!rcu_dereference(flow->stats[node]))) {
+				/* Try to allocate node-specific stats. */
+				struct flow_stats *new_stats;
+
+				new_stats =
+					kmem_cache_alloc_node(flow_stats_cache,
+							      GFP_THISNODE |
+							      __GFP_NOMEMALLOC,
+							      node);
+				if (likely(new_stats)) {
+					new_stats->used = jiffies;
+					new_stats->packet_count = 1;
+					new_stats->byte_count = skb->len;
+					new_stats->tcp_flags = tcp_flags;
+					spin_lock_init(&new_stats->lock);
+
+					rcu_assign_pointer(flow->stats[node],
+							   new_stats);
+					goto unlock;
+				}
+			}
+			flow->stats_last_writer = node;
+		}
+	}
+
+	stats->used = jiffies;
+	stats->packet_count++;
+	stats->byte_count += skb->len;
+	stats->tcp_flags |= tcp_flags;
+unlock:
+	spin_unlock(&stats->lock);
+}
+
+/* Must be called with rcu_read_lock or ovs_mutex. */
+void ovs_flow_stats_get(const struct sw_flow *flow,
+			struct ovs_flow_stats *ovs_stats,
+			unsigned long *used, __be16 *tcp_flags)
+{
+	int node;
 
-	if ((flow->key.eth.type == htons(ETH_P_IP) ||
-	     flow->key.eth.type == htons(ETH_P_IPV6)) &&
-	    flow->key.ip.proto == IPPROTO_TCP &&
-	    likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) {
-		tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb));
+	*used = 0;
+	*tcp_flags = 0;
+	memset(ovs_stats, 0, sizeof(*ovs_stats));
+
+	for_each_node(node) {
+		struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]);
+
+		if (stats) {
+			/* Local CPU may write on non-local stats, so we must
+			 * block bottom-halves here.
+			 */
+			spin_lock_bh(&stats->lock);
+			if (!*used || time_after(stats->used, *used))
+				*used = stats->used;
+			*tcp_flags |= stats->tcp_flags;
+			ovs_stats->n_packets += stats->packet_count;
+			ovs_stats->n_bytes += stats->byte_count;
+			spin_unlock_bh(&stats->lock);
+		}
 	}
+}
 
-	spin_lock(&flow->lock);
-	flow->used = jiffies;
-	flow->packet_count++;
-	flow->byte_count += skb->len;
-	flow->tcp_flags |= tcp_flags;
-	spin_unlock(&flow->lock);
+/* Called with ovs_mutex. */
+void ovs_flow_stats_clear(struct sw_flow *flow)
+{
+	int node;
+
+	for_each_node(node) {
+		struct flow_stats *stats = ovsl_dereference(flow->stats[node]);
+
+		if (stats) {
+			spin_lock_bh(&stats->lock);
+			stats->used = 0;
+			stats->packet_count = 0;
+			stats->byte_count = 0;
+			stats->tcp_flags = 0;
+			spin_unlock_bh(&stats->lock);
+		}
+	}
 }
 
 static int check_header(struct sk_buff *skb, int len)
@@ -263,8 +354,8 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
 	/* The ICMPv6 type and code fields use the 16-bit transport port
 	 * fields, so we need to store them in 16-bit network byte order.
 	 */
-	key->ipv6.tp.src = htons(icmp->icmp6_type);
-	key->ipv6.tp.dst = htons(icmp->icmp6_code);
+	key->tp.src = htons(icmp->icmp6_type);
+	key->tp.dst = htons(icmp->icmp6_code);
 
 	if (icmp->icmp6_code == 0 &&
 	    (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
@@ -303,14 +394,14 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
 			    && opt_len == 8) {
 				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll)))
 					goto invalid;
-				memcpy(key->ipv6.nd.sll,
-				    &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+				ether_addr_copy(key->ipv6.nd.sll,
+						&nd->opt[offset+sizeof(*nd_opt)]);
 			} else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR
 				   && opt_len == 8) {
 				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll)))
 					goto invalid;
-				memcpy(key->ipv6.nd.tll,
-				    &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+				ether_addr_copy(key->ipv6.nd.tll,
+						&nd->opt[offset+sizeof(*nd_opt)]);
 			}
 
 			icmp_len -= opt_len;
@@ -370,8 +461,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 	 * header in the linear data area.
 	 */
 	eth = eth_hdr(skb);
-	memcpy(key->eth.src, eth->h_source, ETH_ALEN);
-	memcpy(key->eth.dst, eth->h_dest, ETH_ALEN);
+	ether_addr_copy(key->eth.src, eth->h_source);
+	ether_addr_copy(key->eth.dst, eth->h_dest);
 
 	__skb_pull(skb, 2 * ETH_ALEN);
 	/* We are going to push all headers that we pull, so no need to
@@ -426,21 +517,21 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 		if (key->ip.proto == IPPROTO_TCP) {
 			if (tcphdr_ok(skb)) {
 				struct tcphdr *tcp = tcp_hdr(skb);
-				key->ipv4.tp.src = tcp->source;
-				key->ipv4.tp.dst = tcp->dest;
-				key->ipv4.tp.flags = TCP_FLAGS_BE16(tcp);
+				key->tp.src = tcp->source;
+				key->tp.dst = tcp->dest;
+				key->tp.flags = TCP_FLAGS_BE16(tcp);
 			}
 		} else if (key->ip.proto == IPPROTO_UDP) {
 			if (udphdr_ok(skb)) {
 				struct udphdr *udp = udp_hdr(skb);
-				key->ipv4.tp.src = udp->source;
-				key->ipv4.tp.dst = udp->dest;
+				key->tp.src = udp->source;
+				key->tp.dst = udp->dest;
 			}
 		} else if (key->ip.proto == IPPROTO_SCTP) {
 			if (sctphdr_ok(skb)) {
 				struct sctphdr *sctp = sctp_hdr(skb);
-				key->ipv4.tp.src = sctp->source;
-				key->ipv4.tp.dst = sctp->dest;
+				key->tp.src = sctp->source;
+				key->tp.dst = sctp->dest;
 			}
 		} else if (key->ip.proto == IPPROTO_ICMP) {
 			if (icmphdr_ok(skb)) {
@@ -448,8 +539,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 				/* The ICMP type and code fields use the 16-bit
 				 * transport port fields, so we need to store
 				 * them in 16-bit network byte order. */
-				key->ipv4.tp.src = htons(icmp->type);
-				key->ipv4.tp.dst = htons(icmp->code);
+				key->tp.src = htons(icmp->type);
+				key->tp.dst = htons(icmp->code);
 			}
 		}
 
@@ -469,8 +560,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 				key->ip.proto = ntohs(arp->ar_op);
 			memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
 			memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
-			memcpy(key->ipv4.arp.sha, arp->ar_sha, ETH_ALEN);
-			memcpy(key->ipv4.arp.tha, arp->ar_tha, ETH_ALEN);
+			ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha);
+			ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha);
 		}
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		int nh_len;             /* IPv6 Header + Extensions */
@@ -495,21 +586,21 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 		if (key->ip.proto == NEXTHDR_TCP) {
 			if (tcphdr_ok(skb)) {
 				struct tcphdr *tcp = tcp_hdr(skb);
-				key->ipv6.tp.src = tcp->source;
-				key->ipv6.tp.dst = tcp->dest;
-				key->ipv6.tp.flags = TCP_FLAGS_BE16(tcp);
+				key->tp.src = tcp->source;
+				key->tp.dst = tcp->dest;
+				key->tp.flags = TCP_FLAGS_BE16(tcp);
 			}
 		} else if (key->ip.proto == NEXTHDR_UDP) {
 			if (udphdr_ok(skb)) {
 				struct udphdr *udp = udp_hdr(skb);
-				key->ipv6.tp.src = udp->source;
-				key->ipv6.tp.dst = udp->dest;
+				key->tp.src = udp->source;
+				key->tp.dst = udp->dest;
 			}
 		} else if (key->ip.proto == NEXTHDR_SCTP) {
 			if (sctphdr_ok(skb)) {
 				struct sctphdr *sctp = sctp_hdr(skb);
-				key->ipv6.tp.src = sctp->source;
-				key->ipv6.tp.dst = sctp->dest;
+				key->tp.src = sctp->source;
+				key->tp.dst = sctp->dest;
 			}
 		} else if (key->ip.proto == NEXTHDR_ICMP) {
 			if (icmp6hdr_ok(skb)) {
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 1510f51dbf7..5e5aaed3a85 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -19,6 +19,7 @@
 #ifndef FLOW_H
 #define FLOW_H 1
 
+#include <linux/cache.h>
 #include <linux/kernel.h>
 #include <linux/netlink.h>
 #include <linux/openvswitch.h>
@@ -46,7 +47,7 @@ struct ovs_key_ipv4_tunnel {
 	__be16 tun_flags;
 	u8   ipv4_tos;
 	u8   ipv4_ttl;
-};
+} __packed __aligned(4); /* Minimize padding. */
 
 static inline void ovs_flow_tun_key_init(struct ovs_key_ipv4_tunnel *tun_key,
 					 const struct iphdr *iph, __be64 tun_id,
@@ -70,7 +71,7 @@ struct sw_flow_key {
 		u32	priority;	/* Packet QoS priority. */
 		u32	skb_mark;	/* SKB mark. */
 		u16	in_port;	/* Input switch port (or DP_MAX_PORTS). */
-	} phy;
+	} __packed phy; /* Safe when right after 'tun_key'. */
 	struct {
 		u8     src[ETH_ALEN];	/* Ethernet source address. */
 		u8     dst[ETH_ALEN];	/* Ethernet destination address. */
@@ -83,23 +84,21 @@ struct sw_flow_key {
 		u8     ttl;		/* IP TTL/hop limit. */
 		u8     frag;		/* One of OVS_FRAG_TYPE_*. */
 	} ip;
+	struct {
+		__be16 src;		/* TCP/UDP/SCTP source port. */
+		__be16 dst;		/* TCP/UDP/SCTP destination port. */
+		__be16 flags;		/* TCP flags. */
+	} tp;
 	union {
 		struct {
 			struct {
 				__be32 src;	/* IP source address. */
 				__be32 dst;	/* IP destination address. */
 			} addr;
-			union {
-				struct {
-					__be16 src;		/* TCP/UDP/SCTP source port. */
-					__be16 dst;		/* TCP/UDP/SCTP destination port. */
-					__be16 flags;		/* TCP flags. */
-				} tp;
-				struct {
-					u8 sha[ETH_ALEN];	/* ARP source hardware address. */
-					u8 tha[ETH_ALEN];	/* ARP target hardware address. */
-				} arp;
-			};
+			struct {
+				u8 sha[ETH_ALEN];	/* ARP source hardware address. */
+				u8 tha[ETH_ALEN];	/* ARP target hardware address. */
+			} arp;
 		} ipv4;
 		struct {
 			struct {
@@ -108,11 +107,6 @@ struct sw_flow_key {
 			} addr;
 			__be32 label;			/* IPv6 flow label. */
 			struct {
-				__be16 src;		/* TCP/UDP/SCTP source port. */
-				__be16 dst;		/* TCP/UDP/SCTP destination port. */
-				__be16 flags;		/* TCP flags. */
-			} tp;
-			struct {
 				struct in6_addr target;	/* ND target address. */
 				u8 sll[ETH_ALEN];	/* ND source link layer address. */
 				u8 tll[ETH_ALEN];	/* ND target link layer address. */
@@ -122,8 +116,8 @@ struct sw_flow_key {
 } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
 
 struct sw_flow_key_range {
-	size_t start;
-	size_t end;
+	unsigned short int start;
+	unsigned short int end;
 };
 
 struct sw_flow_mask {
@@ -146,21 +140,30 @@ struct sw_flow_actions {
 	struct nlattr actions[];
 };
 
+struct flow_stats {
+	u64 packet_count;		/* Number of packets matched. */
+	u64 byte_count;			/* Number of bytes matched. */
+	unsigned long used;		/* Last used time (in jiffies). */
+	spinlock_t lock;		/* Lock for atomic stats update. */
+	__be16 tcp_flags;		/* Union of seen TCP flags. */
+};
+
 struct sw_flow {
 	struct rcu_head rcu;
 	struct hlist_node hash_node[2];
 	u32 hash;
-
+	int stats_last_writer;		/* NUMA-node id of the last writer on
+					 * 'stats[0]'.
+					 */
 	struct sw_flow_key key;
 	struct sw_flow_key unmasked_key;
 	struct sw_flow_mask *mask;
 	struct sw_flow_actions __rcu *sf_acts;
-
-	spinlock_t lock;	/* Lock for values below. */
-	unsigned long used;	/* Last used time (in jiffies). */
-	u64 packet_count;	/* Number of packets matched. */
-	u64 byte_count;		/* Number of bytes matched. */
-	__be16 tcp_flags;	/* Union of seen TCP flags. */
+	struct flow_stats __rcu *stats[]; /* One for each NUMA node.  First one
+					   * is allocated at flow creation time,
+					   * the rest are allocated on demand
+					   * while holding the 'stats[0].lock'.
+					   */
 };
 
 struct arp_eth_header {
@@ -177,7 +180,11 @@ struct arp_eth_header {
 	unsigned char       ar_tip[4];		/* target IP address        */
 } __packed;
 
-void ovs_flow_used(struct sw_flow *, struct sk_buff *);
+void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
+			   struct sk_buff *);
+void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *,
+			unsigned long *used, __be16 *tcp_flags);
+void ovs_flow_stats_clear(struct sw_flow *);
 u64 ovs_flow_used_time(unsigned long flow_jiffies);
 
 int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *);
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 2bc1bc1aca3..d757848da89 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -16,6 +16,8 @@
  * 02110-1301, USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include "flow.h"
 #include "datapath.h"
 #include <linux/uaccess.h>
@@ -202,11 +204,11 @@ static bool match_validate(const struct sw_flow_match *match,
 				if (match->mask && (match->mask->key.ip.proto == 0xff))
 					mask_allowed |= 1 << OVS_KEY_ATTR_ICMPV6;
 
-				if (match->key->ipv6.tp.src ==
+				if (match->key->tp.src ==
 						htons(NDISC_NEIGHBOUR_SOLICITATION) ||
-				    match->key->ipv6.tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
+				    match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
 					key_expected |= 1 << OVS_KEY_ATTR_ND;
-					if (match->mask && (match->mask->key.ipv6.tp.src == htons(0xffff)))
+					if (match->mask && (match->mask->key.tp.src == htons(0xffff)))
 						mask_allowed |= 1 << OVS_KEY_ATTR_ND;
 				}
 			}
@@ -216,14 +218,14 @@ static bool match_validate(const struct sw_flow_match *match,
 	if ((key_attrs & key_expected) != key_expected) {
 		/* Key attributes check failed. */
 		OVS_NLERR("Missing expected key attributes (key_attrs=%llx, expected=%llx).\n",
-				key_attrs, key_expected);
+				(unsigned long long)key_attrs, (unsigned long long)key_expected);
 		return false;
 	}
 
 	if ((mask_attrs & mask_allowed) != mask_attrs) {
 		/* Mask attributes check failed. */
 		OVS_NLERR("Contain more than allowed mask fields (mask_attrs=%llx, mask_allowed=%llx).\n",
-				mask_attrs, mask_allowed);
+				(unsigned long long)mask_attrs, (unsigned long long)mask_allowed);
 		return false;
 	}
 
@@ -487,7 +489,7 @@ static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 	return 0;
 }
 
-static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
+static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
 				const struct nlattr **a, bool is_mask)
 {
 	int err;
@@ -628,27 +630,18 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 		const struct ovs_key_tcp *tcp_key;
 
 		tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]);
-		if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
-			SW_FLOW_KEY_PUT(match, ipv4.tp.src,
-					tcp_key->tcp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
-					tcp_key->tcp_dst, is_mask);
-		} else {
-			SW_FLOW_KEY_PUT(match, ipv6.tp.src,
-					tcp_key->tcp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
-					tcp_key->tcp_dst, is_mask);
-		}
+		SW_FLOW_KEY_PUT(match, tp.src, tcp_key->tcp_src, is_mask);
+		SW_FLOW_KEY_PUT(match, tp.dst, tcp_key->tcp_dst, is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_TCP);
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) {
 		if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
-			SW_FLOW_KEY_PUT(match, ipv4.tp.flags,
+			SW_FLOW_KEY_PUT(match, tp.flags,
 					nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
 					is_mask);
 		} else {
-			SW_FLOW_KEY_PUT(match, ipv6.tp.flags,
+			SW_FLOW_KEY_PUT(match, tp.flags,
 					nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
 					is_mask);
 		}
@@ -659,17 +652,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 		const struct ovs_key_udp *udp_key;
 
 		udp_key = nla_data(a[OVS_KEY_ATTR_UDP]);
-		if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
-			SW_FLOW_KEY_PUT(match, ipv4.tp.src,
-					udp_key->udp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
-					udp_key->udp_dst, is_mask);
-		} else {
-			SW_FLOW_KEY_PUT(match, ipv6.tp.src,
-					udp_key->udp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
-					udp_key->udp_dst, is_mask);
-		}
+		SW_FLOW_KEY_PUT(match, tp.src, udp_key->udp_src, is_mask);
+		SW_FLOW_KEY_PUT(match, tp.dst, udp_key->udp_dst, is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_UDP);
 	}
 
@@ -677,17 +661,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 		const struct ovs_key_sctp *sctp_key;
 
 		sctp_key = nla_data(a[OVS_KEY_ATTR_SCTP]);
-		if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
-			SW_FLOW_KEY_PUT(match, ipv4.tp.src,
-					sctp_key->sctp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
-					sctp_key->sctp_dst, is_mask);
-		} else {
-			SW_FLOW_KEY_PUT(match, ipv6.tp.src,
-					sctp_key->sctp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
-					sctp_key->sctp_dst, is_mask);
-		}
+		SW_FLOW_KEY_PUT(match, tp.src, sctp_key->sctp_src, is_mask);
+		SW_FLOW_KEY_PUT(match, tp.dst, sctp_key->sctp_dst, is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_SCTP);
 	}
 
@@ -695,9 +670,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 		const struct ovs_key_icmp *icmp_key;
 
 		icmp_key = nla_data(a[OVS_KEY_ATTR_ICMP]);
-		SW_FLOW_KEY_PUT(match, ipv4.tp.src,
+		SW_FLOW_KEY_PUT(match, tp.src,
 				htons(icmp_key->icmp_type), is_mask);
-		SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
+		SW_FLOW_KEY_PUT(match, tp.dst,
 				htons(icmp_key->icmp_code), is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_ICMP);
 	}
@@ -706,9 +681,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 		const struct ovs_key_icmpv6 *icmpv6_key;
 
 		icmpv6_key = nla_data(a[OVS_KEY_ATTR_ICMPV6]);
-		SW_FLOW_KEY_PUT(match, ipv6.tp.src,
+		SW_FLOW_KEY_PUT(match, tp.src,
 				htons(icmpv6_key->icmpv6_type), is_mask);
-		SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
+		SW_FLOW_KEY_PUT(match, tp.dst,
 				htons(icmpv6_key->icmpv6_code), is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_ICMPV6);
 	}
@@ -934,8 +909,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 		goto nla_put_failure;
 
 	eth_key = nla_data(nla);
-	memcpy(eth_key->eth_src, output->eth.src, ETH_ALEN);
-	memcpy(eth_key->eth_dst, output->eth.dst, ETH_ALEN);
+	ether_addr_copy(eth_key->eth_src, output->eth.src);
+	ether_addr_copy(eth_key->eth_dst, output->eth.dst);
 
 	if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) {
 		__be16 eth_type;
@@ -1007,8 +982,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 		arp_key->arp_sip = output->ipv4.addr.src;
 		arp_key->arp_tip = output->ipv4.addr.dst;
 		arp_key->arp_op = htons(output->ip.proto);
-		memcpy(arp_key->arp_sha, output->ipv4.arp.sha, ETH_ALEN);
-		memcpy(arp_key->arp_tha, output->ipv4.arp.tha, ETH_ALEN);
+		ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha);
+		ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha);
 	}
 
 	if ((swkey->eth.type == htons(ETH_P_IP) ||
@@ -1022,19 +997,11 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (!nla)
 				goto nla_put_failure;
 			tcp_key = nla_data(nla);
-			if (swkey->eth.type == htons(ETH_P_IP)) {
-				tcp_key->tcp_src = output->ipv4.tp.src;
-				tcp_key->tcp_dst = output->ipv4.tp.dst;
-				if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
-						 output->ipv4.tp.flags))
-					goto nla_put_failure;
-			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
-				tcp_key->tcp_src = output->ipv6.tp.src;
-				tcp_key->tcp_dst = output->ipv6.tp.dst;
-				if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
-						 output->ipv6.tp.flags))
-					goto nla_put_failure;
-			}
+			tcp_key->tcp_src = output->tp.src;
+			tcp_key->tcp_dst = output->tp.dst;
+			if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
+					 output->tp.flags))
+				goto nla_put_failure;
 		} else if (swkey->ip.proto == IPPROTO_UDP) {
 			struct ovs_key_udp *udp_key;
 
@@ -1042,13 +1009,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (!nla)
 				goto nla_put_failure;
 			udp_key = nla_data(nla);
-			if (swkey->eth.type == htons(ETH_P_IP)) {
-				udp_key->udp_src = output->ipv4.tp.src;
-				udp_key->udp_dst = output->ipv4.tp.dst;
-			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
-				udp_key->udp_src = output->ipv6.tp.src;
-				udp_key->udp_dst = output->ipv6.tp.dst;
-			}
+			udp_key->udp_src = output->tp.src;
+			udp_key->udp_dst = output->tp.dst;
 		} else if (swkey->ip.proto == IPPROTO_SCTP) {
 			struct ovs_key_sctp *sctp_key;
 
@@ -1056,13 +1018,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (!nla)
 				goto nla_put_failure;
 			sctp_key = nla_data(nla);
-			if (swkey->eth.type == htons(ETH_P_IP)) {
-				sctp_key->sctp_src = swkey->ipv4.tp.src;
-				sctp_key->sctp_dst = swkey->ipv4.tp.dst;
-			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
-				sctp_key->sctp_src = swkey->ipv6.tp.src;
-				sctp_key->sctp_dst = swkey->ipv6.tp.dst;
-			}
+			sctp_key->sctp_src = output->tp.src;
+			sctp_key->sctp_dst = output->tp.dst;
 		} else if (swkey->eth.type == htons(ETH_P_IP) &&
 			   swkey->ip.proto == IPPROTO_ICMP) {
 			struct ovs_key_icmp *icmp_key;
@@ -1071,8 +1028,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (!nla)
 				goto nla_put_failure;
 			icmp_key = nla_data(nla);
-			icmp_key->icmp_type = ntohs(output->ipv4.tp.src);
-			icmp_key->icmp_code = ntohs(output->ipv4.tp.dst);
+			icmp_key->icmp_type = ntohs(output->tp.src);
+			icmp_key->icmp_code = ntohs(output->tp.dst);
 		} else if (swkey->eth.type == htons(ETH_P_IPV6) &&
 			   swkey->ip.proto == IPPROTO_ICMPV6) {
 			struct ovs_key_icmpv6 *icmpv6_key;
@@ -1082,8 +1039,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (!nla)
 				goto nla_put_failure;
 			icmpv6_key = nla_data(nla);
-			icmpv6_key->icmpv6_type = ntohs(output->ipv6.tp.src);
-			icmpv6_key->icmpv6_code = ntohs(output->ipv6.tp.dst);
+			icmpv6_key->icmpv6_type = ntohs(output->tp.src);
+			icmpv6_key->icmpv6_code = ntohs(output->tp.dst);
 
 			if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION ||
 			    icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) {
@@ -1095,8 +1052,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 				nd_key = nla_data(nla);
 				memcpy(nd_key->nd_target, &output->ipv6.nd.target,
 							sizeof(nd_key->nd_target));
-				memcpy(nd_key->nd_sll, output->ipv6.nd.sll, ETH_ALEN);
-				memcpy(nd_key->nd_tll, output->ipv6.nd.tll, ETH_ALEN);
+				ether_addr_copy(nd_key->nd_sll, output->ipv6.nd.sll);
+				ether_addr_copy(nd_key->nd_tll, output->ipv6.nd.tll);
 			}
 		}
 	}
@@ -1128,19 +1085,11 @@ struct sw_flow_actions *ovs_nla_alloc_flow_actions(int size)
 	return sfa;
 }
 
-/* RCU callback used by ovs_nla_free_flow_actions. */
-static void rcu_free_acts_callback(struct rcu_head *rcu)
-{
-	struct sw_flow_actions *sf_acts = container_of(rcu,
-			struct sw_flow_actions, rcu);
-	kfree(sf_acts);
-}
-
 /* Schedules 'sf_acts' to be freed after the next RCU grace period.
  * The caller must hold rcu_read_lock for this to be sensible. */
 void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
 {
-	call_rcu(&sf_acts->rcu, rcu_free_acts_callback);
+	kfree_rcu(sf_acts, rcu);
 }
 
 static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
@@ -1269,13 +1218,10 @@ static int validate_and_copy_sample(const struct nlattr *attr,
 
 static int validate_tp_port(const struct sw_flow_key *flow_key)
 {
-	if (flow_key->eth.type == htons(ETH_P_IP)) {
-		if (flow_key->ipv4.tp.src || flow_key->ipv4.tp.dst)
-			return 0;
-	} else if (flow_key->eth.type == htons(ETH_P_IPV6)) {
-		if (flow_key->ipv6.tp.src || flow_key->ipv6.tp.dst)
-			return 0;
-	}
+	if ((flow_key->eth.type == htons(ETH_P_IP) ||
+	     flow_key->eth.type == htons(ETH_P_IPV6)) &&
+	    (flow_key->tp.src || flow_key->tp.dst))
+		return 0;
 
 	return -EINVAL;
 }
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index e4254270608..cf2d853646f 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -25,7 +25,7 @@
 #include <linux/if_vlan.h>
 #include <net/llc_pdu.h>
 #include <linux/kernel.h>
-#include <linux/jhash.h>
+#include <linux/hash.h>
 #include <linux/jiffies.h>
 #include <linux/llc.h>
 #include <linux/module.h>
@@ -44,12 +44,11 @@
 #include <net/ipv6.h>
 #include <net/ndisc.h>
 
-#include "datapath.h"
-
 #define TBL_MIN_BUCKETS		1024
 #define REHASH_INTERVAL		(10 * 60 * HZ)
 
 static struct kmem_cache *flow_cache;
+struct kmem_cache *flow_stats_cache __read_mostly;
 
 static u16 range_n_bytes(const struct sw_flow_key_range *range)
 {
@@ -59,8 +58,10 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
 		       const struct sw_flow_mask *mask)
 {
-	const long *m = (long *)((u8 *)&mask->key + mask->range.start);
-	const long *s = (long *)((u8 *)src + mask->range.start);
+	const long *m = (const long *)((const u8 *)&mask->key +
+				mask->range.start);
+	const long *s = (const long *)((const u8 *)src +
+				mask->range.start);
 	long *d = (long *)((u8 *)dst + mask->range.start);
 	int i;
 
@@ -75,16 +76,35 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
 struct sw_flow *ovs_flow_alloc(void)
 {
 	struct sw_flow *flow;
+	struct flow_stats *stats;
+	int node;
 
 	flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
 	if (!flow)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock_init(&flow->lock);
 	flow->sf_acts = NULL;
 	flow->mask = NULL;
+	flow->stats_last_writer = NUMA_NO_NODE;
+
+	/* Initialize the default stat node. */
+	stats = kmem_cache_alloc_node(flow_stats_cache,
+				      GFP_KERNEL | __GFP_ZERO, 0);
+	if (!stats)
+		goto err;
+
+	spin_lock_init(&stats->lock);
+
+	RCU_INIT_POINTER(flow->stats[0], stats);
+
+	for_each_node(node)
+		if (node != 0)
+			RCU_INIT_POINTER(flow->stats[node], NULL);
 
 	return flow;
+err:
+	kmem_cache_free(flow_cache, flow);
+	return ERR_PTR(-ENOMEM);
 }
 
 int ovs_flow_tbl_count(struct flow_table *table)
@@ -117,7 +137,13 @@ static struct flex_array *alloc_buckets(unsigned int n_buckets)
 
 static void flow_free(struct sw_flow *flow)
 {
-	kfree((struct sf_flow_acts __force *)flow->sf_acts);
+	int node;
+
+	kfree((struct sw_flow_actions __force *)flow->sf_acts);
+	for_each_node(node)
+		if (flow->stats[node])
+			kmem_cache_free(flow_stats_cache,
+					(struct flow_stats __force *)flow->stats[node]);
 	kmem_cache_free(flow_cache, flow);
 }
 
@@ -128,37 +154,11 @@ static void rcu_free_flow_callback(struct rcu_head *rcu)
 	flow_free(flow);
 }
 
-static void rcu_free_sw_flow_mask_cb(struct rcu_head *rcu)
-{
-	struct sw_flow_mask *mask = container_of(rcu, struct sw_flow_mask, rcu);
-
-	kfree(mask);
-}
-
-static void flow_mask_del_ref(struct sw_flow_mask *mask, bool deferred)
-{
-	if (!mask)
-		return;
-
-	BUG_ON(!mask->ref_count);
-	mask->ref_count--;
-
-	if (!mask->ref_count) {
-		list_del_rcu(&mask->list);
-		if (deferred)
-			call_rcu(&mask->rcu, rcu_free_sw_flow_mask_cb);
-		else
-			kfree(mask);
-	}
-}
-
 void ovs_flow_free(struct sw_flow *flow, bool deferred)
 {
 	if (!flow)
 		return;
 
-	flow_mask_del_ref(flow->mask, deferred);
-
 	if (deferred)
 		call_rcu(&flow->rcu, rcu_free_flow_callback);
 	else
@@ -170,26 +170,9 @@ static void free_buckets(struct flex_array *buckets)
 	flex_array_free(buckets);
 }
 
+
 static void __table_instance_destroy(struct table_instance *ti)
 {
-	int i;
-
-	if (ti->keep_flows)
-		goto skip_flows;
-
-	for (i = 0; i < ti->n_buckets; i++) {
-		struct sw_flow *flow;
-		struct hlist_head *head = flex_array_get(ti->buckets, i);
-		struct hlist_node *n;
-		int ver = ti->node_ver;
-
-		hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
-			hlist_del(&flow->hash_node[ver]);
-			ovs_flow_free(flow, false);
-		}
-	}
-
-skip_flows:
 	free_buckets(ti->buckets);
 	kfree(ti);
 }
@@ -240,20 +223,38 @@ static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
 
 static void table_instance_destroy(struct table_instance *ti, bool deferred)
 {
+	int i;
+
 	if (!ti)
 		return;
 
+	if (ti->keep_flows)
+		goto skip_flows;
+
+	for (i = 0; i < ti->n_buckets; i++) {
+		struct sw_flow *flow;
+		struct hlist_head *head = flex_array_get(ti->buckets, i);
+		struct hlist_node *n;
+		int ver = ti->node_ver;
+
+		hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
+			hlist_del_rcu(&flow->hash_node[ver]);
+			ovs_flow_free(flow, deferred);
+		}
+	}
+
+skip_flows:
 	if (deferred)
 		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
 	else
 		__table_instance_destroy(ti);
 }
 
-void ovs_flow_tbl_destroy(struct flow_table *table)
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred)
 {
 	struct table_instance *ti = ovsl_dereference(table->ti);
 
-	table_instance_destroy(ti, false);
+	table_instance_destroy(ti, deferred);
 }
 
 struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
@@ -356,13 +357,13 @@ int ovs_flow_tbl_flush(struct flow_table *flow_table)
 static u32 flow_hash(const struct sw_flow_key *key, int key_start,
 		     int key_end)
 {
-	u32 *hash_key = (u32 *)((u8 *)key + key_start);
+	const u32 *hash_key = (const u32 *)((const u8 *)key + key_start);
 	int hash_u32s = (key_end - key_start) >> 2;
 
 	/* Make sure number of hash bytes are multiple of u32. */
 	BUILD_BUG_ON(sizeof(long) % sizeof(u32));
 
-	return jhash2(hash_key, hash_u32s, 0);
+	return arch_fast_hash2(hash_key, hash_u32s, 0);
 }
 
 static int flow_key_start(const struct sw_flow_key *key)
@@ -378,8 +379,8 @@ static bool cmp_key(const struct sw_flow_key *key1,
 		    const struct sw_flow_key *key2,
 		    int key_start, int key_end)
 {
-	const long *cp1 = (long *)((u8 *)key1 + key_start);
-	const long *cp2 = (long *)((u8 *)key2 + key_start);
+	const long *cp1 = (const long *)((const u8 *)key1 + key_start);
+	const long *cp2 = (const long *)((const u8 *)key2 + key_start);
 	long diffs = 0;
 	int i;
 
@@ -429,11 +430,11 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	return NULL;
 }
 
-struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
+struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
 				    const struct sw_flow_key *key,
 				    u32 *n_mask_hit)
 {
-	struct table_instance *ti = rcu_dereference(tbl->ti);
+	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
 	struct sw_flow_mask *mask;
 	struct sw_flow *flow;
 
@@ -447,6 +448,30 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
 	return NULL;
 }
 
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
+				    const struct sw_flow_key *key)
+{
+	u32 __always_unused n_mask_hit;
+
+	return ovs_flow_tbl_lookup_stats(tbl, key, &n_mask_hit);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+					  struct sw_flow_match *match)
+{
+	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
+	struct sw_flow_mask *mask;
+	struct sw_flow *flow;
+
+	/* Always called under ovs-mutex. */
+	list_for_each_entry(mask, &tbl->mask_list, list) {
+		flow = masked_flow_lookup(ti, match->key, mask);
+		if (flow && ovs_flow_cmp_unmasked_key(flow, match))  /* Found */
+			return flow;
+	}
+	return NULL;
+}
+
 int ovs_flow_tbl_num_masks(const struct flow_table *table)
 {
 	struct sw_flow_mask *mask;
@@ -463,6 +488,25 @@ static struct table_instance *table_instance_expand(struct table_instance *ti)
 	return table_instance_rehash(ti, ti->n_buckets * 2);
 }
 
+/* Remove 'mask' from the mask list, if it is not needed any more. */
+static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask)
+{
+	if (mask) {
+		/* ovs-lock is required to protect mask-refcount and
+		 * mask list.
+		 */
+		ASSERT_OVSL();
+		BUG_ON(!mask->ref_count);
+		mask->ref_count--;
+
+		if (!mask->ref_count) {
+			list_del_rcu(&mask->list);
+			kfree_rcu(mask, rcu);
+		}
+	}
+}
+
+/* Must be called with OVS mutex held. */
 void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
 {
 	struct table_instance *ti = ovsl_dereference(table->ti);
@@ -470,6 +514,11 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
 	BUG_ON(table->count == 0);
 	hlist_del_rcu(&flow->hash_node[ti->node_ver]);
 	table->count--;
+
+	/* RCU delete the mask. 'flow->mask' is not NULLed, as it should be
+	 * accessible as long as the RCU read lock is held.
+	 */
+	flow_mask_remove(table, flow->mask);
 }
 
 static struct sw_flow_mask *mask_alloc(void)
@@ -478,21 +527,16 @@ static struct sw_flow_mask *mask_alloc(void)
 
 	mask = kmalloc(sizeof(*mask), GFP_KERNEL);
 	if (mask)
-		mask->ref_count = 0;
+		mask->ref_count = 1;
 
 	return mask;
 }
 
-static void mask_add_ref(struct sw_flow_mask *mask)
-{
-	mask->ref_count++;
-}
-
 static bool mask_equal(const struct sw_flow_mask *a,
 		       const struct sw_flow_mask *b)
 {
-	u8 *a_ = (u8 *)&a->key + a->range.start;
-	u8 *b_ = (u8 *)&b->key + b->range.start;
+	const u8 *a_ = (const u8 *)&a->key + a->range.start;
+	const u8 *b_ = (const u8 *)&b->key + b->range.start;
 
 	return  (a->range.end == b->range.end)
 		&& (a->range.start == b->range.start)
@@ -514,11 +558,7 @@ static struct sw_flow_mask *flow_mask_find(const struct flow_table *tbl,
 	return NULL;
 }
 
-/**
- * add a new mask into the mask list.
- * The caller needs to make sure that 'mask' is not the same
- * as any masks that are already on the list.
- */
+/* Add 'mask' into the mask list, if it is not already there. */
 static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
 			    struct sw_flow_mask *new)
 {
@@ -532,13 +572,16 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
 		mask->key = new->key;
 		mask->range = new->range;
 		list_add_rcu(&mask->list, &tbl->mask_list);
+	} else {
+		BUG_ON(!mask->ref_count);
+		mask->ref_count++;
 	}
 
-	mask_add_ref(mask);
 	flow->mask = mask;
 	return 0;
 }
 
+/* Must be called with OVS mutex held. */
 int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
 			struct sw_flow_mask *mask)
 {
@@ -577,16 +620,28 @@ int ovs_flow_init(void)
 	BUILD_BUG_ON(__alignof__(struct sw_flow_key) % __alignof__(long));
 	BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long));
 
-	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow), 0,
-					0, NULL);
+	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
+				       + (num_possible_nodes()
+					  * sizeof(struct flow_stats *)),
+				       0, 0, NULL);
 	if (flow_cache == NULL)
 		return -ENOMEM;
 
+	flow_stats_cache
+		= kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats),
+				    0, SLAB_HWCACHE_ALIGN, NULL);
+	if (flow_stats_cache == NULL) {
+		kmem_cache_destroy(flow_cache);
+		flow_cache = NULL;
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
 /* Uninitializes the flow module. */
 void ovs_flow_exit(void)
 {
+	kmem_cache_destroy(flow_stats_cache);
 	kmem_cache_destroy(flow_cache);
 }
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index fbe45d5ad07..5918bff7f3f 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -52,6 +52,8 @@ struct flow_table {
 	unsigned int count;
 };
 
+extern struct kmem_cache *flow_stats_cache;
+
 int ovs_flow_init(void);
 void ovs_flow_exit(void);
 
@@ -60,7 +62,7 @@ void ovs_flow_free(struct sw_flow *, bool deferred);
 
 int ovs_flow_tbl_init(struct flow_table *);
 int ovs_flow_tbl_count(struct flow_table *table);
-void ovs_flow_tbl_destroy(struct flow_table *table);
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred);
 int ovs_flow_tbl_flush(struct flow_table *flow_table);
 
 int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
@@ -69,10 +71,13 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
 int  ovs_flow_tbl_num_masks(const struct flow_table *table);
 struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *table,
 				       u32 *bucket, u32 *idx);
-struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
+struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *,
 				    const struct sw_flow_key *,
 				    u32 *n_mask_hit);
-
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
+				    const struct sw_flow_key *);
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+					  struct sw_flow_match *match);
 bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
 			       struct sw_flow_match *match);
 
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index a3d6951602d..f49148a07da 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -110,6 +110,22 @@ static int gre_rcv(struct sk_buff *skb,
 	return PACKET_RCVD;
 }
 
+/* Called with rcu_read_lock and BH disabled. */
+static int gre_err(struct sk_buff *skb, u32 info,
+		   const struct tnl_ptk_info *tpi)
+{
+	struct ovs_net *ovs_net;
+	struct vport *vport;
+
+	ovs_net = net_generic(dev_net(skb->dev), ovs_net_id);
+	vport = rcu_dereference(ovs_net->vport_net.gre_vport);
+
+	if (unlikely(!vport))
+		return PACKET_REJECT;
+	else
+		return PACKET_RCVD;
+}
+
 static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 {
 	struct net *net = ovs_dp_get_net(vport->dp);
@@ -172,9 +188,9 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 	df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
 		htons(IP_DF) : 0;
 
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
-	return iptunnel_xmit(rt, skb, fl.saddr,
+	return iptunnel_xmit(skb->sk, rt, skb, fl.saddr,
 			     OVS_CB(skb)->tun_key->ipv4_dst, IPPROTO_GRE,
 			     OVS_CB(skb)->tun_key->ipv4_tos,
 			     OVS_CB(skb)->tun_key->ipv4_ttl, df, false);
@@ -186,6 +202,7 @@ error:
 
 static struct gre_cisco_protocol gre_protocol = {
 	.handler        = gre_rcv,
+	.err_handler    = gre_err,
 	.priority       = 1,
 };
 
@@ -256,7 +273,7 @@ static void gre_tnl_destroy(struct vport *vport)
 
 	ovs_net = net_generic(net, ovs_net_id);
 
-	rcu_assign_pointer(ovs_net->vport_net.gre_vport, NULL);
+	RCU_INIT_POINTER(ovs_net->vport_net.gre_vport, NULL);
 	ovs_vport_deferred_free(vport);
 	gre_exit();
 }
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 729c68763fe..789af9280e7 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -130,7 +130,7 @@ static void do_setup(struct net_device *netdev)
 	netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netdev->destructor = internal_dev_destructor;
-	SET_ETHTOOL_OPS(netdev, &internal_dev_ethtool_ops);
+	netdev->ethtool_ops = &internal_dev_ethtool_ops;
 	netdev->tx_queue_len = 0;
 
 	netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index e797a50ac2b..0edbd95c60e 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -122,7 +122,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 	vxlan_port = vxlan_vport(vport);
 	strncpy(vxlan_port->name, parms->name, IFNAMSIZ);
 
-	vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, false);
+	vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, 0);
 	if (IS_ERR(vs)) {
 		ovs_vport_free(vport);
 		return (void *)vs;
@@ -170,7 +170,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
 		htons(IP_DF) : 0;
 
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	inet_get_local_port_range(net, &port_min, &port_max);
 	src_port = vxlan_src_port(port_min, port_max, skb);
@@ -180,7 +180,8 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 			     OVS_CB(skb)->tun_key->ipv4_tos,
 			     OVS_CB(skb)->tun_key->ipv4_ttl, df,
 			     src_port, dst_port,
-			     htonl(be64_to_cpu(OVS_CB(skb)->tun_key->tun_id) << 8));
+			     htonl(be64_to_cpu(OVS_CB(skb)->tun_key->tun_id) << 8),
+			     false);
 	if (err < 0)
 		ip_rt_put(rt);
 error:
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index d830a95f03a..42c0f4a0b78 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -33,6 +33,9 @@
 #include "vport.h"
 #include "vport-internal_dev.h"
 
+static void ovs_vport_record_error(struct vport *,
+				   enum vport_err_type err_type);
+
 /* List of statically compiled vport implementations.  Don't forget to also
  * add yours to the list at the bottom of vport.h. */
 static const struct vport_ops *vport_ops_list[] = {
@@ -118,7 +121,6 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 {
 	struct vport *vport;
 	size_t alloc_size;
-	int i;
 
 	alloc_size = sizeof(struct vport);
 	if (priv_size) {
@@ -136,19 +138,12 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 	vport->ops = ops;
 	INIT_HLIST_NODE(&vport->dp_hash_node);
 
-	vport->percpu_stats = alloc_percpu(struct pcpu_tstats);
+	vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!vport->percpu_stats) {
 		kfree(vport);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	for_each_possible_cpu(i) {
-		struct pcpu_tstats *vport_stats;
-		vport_stats = per_cpu_ptr(vport->percpu_stats, i);
-		u64_stats_init(&vport_stats->syncp);
-	}
-
-
 	spin_lock_init(&vport->stats_lock);
 
 	return vport;
@@ -275,16 +270,16 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
 	spin_unlock_bh(&vport->stats_lock);
 
 	for_each_possible_cpu(i) {
-		const struct pcpu_tstats *percpu_stats;
-		struct pcpu_tstats local_stats;
+		const struct pcpu_sw_netstats *percpu_stats;
+		struct pcpu_sw_netstats local_stats;
 		unsigned int start;
 
 		percpu_stats = per_cpu_ptr(vport->percpu_stats, i);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&percpu_stats->syncp);
+			start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
 			local_stats = *percpu_stats;
-		} while (u64_stats_fetch_retry_bh(&percpu_stats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
 
 		stats->rx_bytes		+= local_stats.rx_bytes;
 		stats->rx_packets	+= local_stats.rx_packets;
@@ -344,7 +339,7 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
 void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
 		       struct ovs_key_ipv4_tunnel *tun_key)
 {
-	struct pcpu_tstats *stats;
+	struct pcpu_sw_netstats *stats;
 
 	stats = this_cpu_ptr(vport->percpu_stats);
 	u64_stats_update_begin(&stats->syncp);
@@ -370,7 +365,7 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
 	int sent = vport->ops->send(vport, skb);
 
 	if (likely(sent > 0)) {
-		struct pcpu_tstats *stats;
+		struct pcpu_sw_netstats *stats;
 
 		stats = this_cpu_ptr(vport->percpu_stats);
 
@@ -396,7 +391,8 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
  * If using the vport generic stats layer indicate that an error of the given
  * type has occurred.
  */
-void ovs_vport_record_error(struct vport *vport, enum vport_err_type err_type)
+static void ovs_vport_record_error(struct vport *vport,
+				   enum vport_err_type err_type)
 {
 	spin_lock(&vport->stats_lock);
 
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 1a9fbcec6e1..8d721e62f38 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -87,7 +87,7 @@ struct vport {
 	struct hlist_node dp_hash_node;
 	const struct vport_ops *ops;
 
-	struct pcpu_tstats __percpu *percpu_stats;
+	struct pcpu_sw_netstats __percpu *percpu_stats;
 
 	spinlock_t stats_lock;
 	struct vport_err_stats err_stats;
@@ -172,7 +172,7 @@ void ovs_vport_deferred_free(struct vport *vport);
  */
 static inline void *vport_priv(const struct vport *vport)
 {
-	return (u8 *)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN);
+	return (u8 *)(uintptr_t)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN);
 }
 
 /**
@@ -185,14 +185,13 @@ static inline void *vport_priv(const struct vport *vport)
  * the result of a hash table lookup.  @priv must point to the start of the
  * private data area.
  */
-static inline struct vport *vport_from_priv(const void *priv)
+static inline struct vport *vport_from_priv(void *priv)
 {
-	return (struct vport *)(priv - ALIGN(sizeof(struct vport), VPORT_ALIGN));
+	return (struct vport *)((u8 *)priv - ALIGN(sizeof(struct vport), VPORT_ALIGN));
 }
 
 void ovs_vport_receive(struct vport *, struct sk_buff *,
 		       struct ovs_key_ipv4_tunnel *);
-void ovs_vport_record_error(struct vport *, enum vport_err_type err_type);
 
 /* List of statically compiled vport implementations.  Don't forget to also
  * add yours to the list at the top of vport.c. */
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9d70f134992..b85c67ccb79 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -88,7 +88,7 @@
 #include <linux/virtio_net.h>
 #include <linux/errqueue.h>
 #include <linux/net_tstamp.h>
-#include <linux/reciprocal_div.h>
+#include <linux/percpu.h>
 #ifdef CONFIG_INET
 #include <net/inet_common.h>
 #endif
@@ -243,40 +243,41 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	const struct net_device_ops *ops = dev->netdev_ops;
 	netdev_features_t features;
 	struct netdev_queue *txq;
+	int ret = NETDEV_TX_BUSY;
 	u16 queue_map;
-	int ret;
 
 	if (unlikely(!netif_running(dev) ||
-		     !netif_carrier_ok(dev))) {
-		kfree_skb(skb);
-		return NET_XMIT_DROP;
-	}
+		     !netif_carrier_ok(dev)))
+		goto drop;
 
 	features = netif_skb_features(skb);
 	if (skb_needs_linearize(skb, features) &&
-	    __skb_linearize(skb)) {
-		kfree_skb(skb);
-		return NET_XMIT_DROP;
-	}
+	    __skb_linearize(skb))
+		goto drop;
 
 	queue_map = skb_get_queue_mapping(skb);
 	txq = netdev_get_tx_queue(dev, queue_map);
 
-	__netif_tx_lock_bh(txq);
-	if (unlikely(netif_xmit_frozen_or_stopped(txq))) {
-		ret = NETDEV_TX_BUSY;
-		kfree_skb(skb);
-		goto out;
+	local_bh_disable();
+
+	HARD_TX_LOCK(dev, txq, smp_processor_id());
+	if (!netif_xmit_frozen_or_drv_stopped(txq)) {
+		ret = ops->ndo_start_xmit(skb, dev);
+		if (ret == NETDEV_TX_OK)
+			txq_trans_update(txq);
 	}
+	HARD_TX_UNLOCK(dev, txq);
 
-	ret = ops->ndo_start_xmit(skb, dev);
-	if (likely(dev_xmit_complete(ret)))
-		txq_trans_update(txq);
-	else
+	local_bh_enable();
+
+	if (!dev_xmit_complete(ret))
 		kfree_skb(skb);
-out:
-	__netif_tx_unlock_bh(txq);
+
 	return ret;
+drop:
+	atomic_long_inc(&dev->tx_dropped);
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
 }
 
 static struct net_device *packet_cached_dev_get(struct packet_sock *po)
@@ -308,9 +309,25 @@ static bool packet_use_direct_xmit(const struct packet_sock *po)
 	return po->xmit == packet_direct_xmit;
 }
 
-static u16 packet_pick_tx_queue(struct net_device *dev)
+static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
 {
-	return (u16) smp_processor_id() % dev->real_num_tx_queues;
+	return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
+}
+
+static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	u16 queue_index;
+
+	if (ops->ndo_select_queue) {
+		queue_index = ops->ndo_select_queue(dev, skb, NULL,
+						    __packet_pick_tx_queue);
+		queue_index = netdev_cap_txqueue(dev, queue_index);
+	} else {
+		queue_index = __packet_pick_tx_queue(dev, skb);
+	}
+
+	skb_set_queue_mapping(skb, queue_index);
 }
 
 /* register_prot_hook must be invoked with the po->bind_lock held,
@@ -963,7 +980,7 @@ static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb)
 static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
-	ppd->hv1.tp_rxhash = skb_get_rxhash(pkc->skb);
+	ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb);
 }
 
 static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
@@ -977,9 +994,11 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
 {
 	if (vlan_tx_tag_present(pkc->skb)) {
 		ppd->hv1.tp_vlan_tci = vlan_tx_tag_get(pkc->skb);
-		ppd->tp_status = TP_STATUS_VLAN_VALID;
+		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
+		ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 	} else {
 		ppd->hv1.tp_vlan_tci = 0;
+		ppd->hv1.tp_vlan_tpid = 0;
 		ppd->tp_status = TP_STATUS_AVAILABLE;
 	}
 }
@@ -987,6 +1006,7 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
 static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
+	ppd->hv1.tp_padding = 0;
 	prb_fill_vlan_info(pkc, ppd);
 
 	if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH)
@@ -1165,6 +1185,47 @@ static void packet_increment_head(struct packet_ring_buffer *buff)
 	buff->head = buff->head != buff->frame_max ? buff->head+1 : 0;
 }
 
+static void packet_inc_pending(struct packet_ring_buffer *rb)
+{
+	this_cpu_inc(*rb->pending_refcnt);
+}
+
+static void packet_dec_pending(struct packet_ring_buffer *rb)
+{
+	this_cpu_dec(*rb->pending_refcnt);
+}
+
+static unsigned int packet_read_pending(const struct packet_ring_buffer *rb)
+{
+	unsigned int refcnt = 0;
+	int cpu;
+
+	/* We don't use pending refcount in rx_ring. */
+	if (rb->pending_refcnt == NULL)
+		return 0;
+
+	for_each_possible_cpu(cpu)
+		refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu);
+
+	return refcnt;
+}
+
+static int packet_alloc_pending(struct packet_sock *po)
+{
+	po->rx_ring.pending_refcnt = NULL;
+
+	po->tx_ring.pending_refcnt = alloc_percpu(unsigned int);
+	if (unlikely(po->tx_ring.pending_refcnt == NULL))
+		return -ENOBUFS;
+
+	return 0;
+}
+
+static void packet_free_pending(struct packet_sock *po)
+{
+	free_percpu(po->tx_ring.pending_refcnt);
+}
+
 static bool packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
 {
 	struct sock *sk = &po->sk;
@@ -1217,7 +1278,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
 {
-	return reciprocal_divide(skb->rxhash, num);
+	return reciprocal_scale(skb_get_hash(skb), num);
 }
 
 static unsigned int fanout_demux_lb(struct packet_fanout *f,
@@ -1244,7 +1305,7 @@ static unsigned int fanout_demux_rnd(struct packet_fanout *f,
 				     struct sk_buff *skb,
 				     unsigned int num)
 {
-	return reciprocal_divide(prandom_u32(), num);
+	return prandom_u32_max(num);
 }
 
 static unsigned int fanout_demux_rollover(struct packet_fanout *f,
@@ -1268,6 +1329,13 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f,
 	return idx;
 }
 
+static unsigned int fanout_demux_qm(struct packet_fanout *f,
+				    struct sk_buff *skb,
+				    unsigned int num)
+{
+	return skb_get_queue_mapping(skb) % num;
+}
+
 static bool fanout_has_flag(struct packet_fanout *f, u16 flag)
 {
 	return f->flags & (flag >> 8);
@@ -1295,7 +1363,6 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			if (!skb)
 				return 0;
 		}
-		skb_get_rxhash(skb);
 		idx = fanout_demux_hash(f, skb, num);
 		break;
 	case PACKET_FANOUT_LB:
@@ -1307,6 +1374,9 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 	case PACKET_FANOUT_RND:
 		idx = fanout_demux_rnd(f, skb, num);
 		break;
+	case PACKET_FANOUT_QM:
+		idx = fanout_demux_qm(f, skb, num);
+		break;
 	case PACKET_FANOUT_ROLLOVER:
 		idx = fanout_demux_rollover(f, skb, 0, (unsigned int) -1, num);
 		break;
@@ -1353,9 +1423,9 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
 	spin_unlock(&f->lock);
 }
 
-static bool match_fanout_group(struct packet_type *ptype, struct sock * sk)
+static bool match_fanout_group(struct packet_type *ptype, struct sock *sk)
 {
-	if (ptype->af_packet_priv == (void*)((struct packet_sock *)sk)->fanout)
+	if (ptype->af_packet_priv == (void *)((struct packet_sock *)sk)->fanout)
 		return true;
 
 	return false;
@@ -1377,6 +1447,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	case PACKET_FANOUT_LB:
 	case PACKET_FANOUT_CPU:
 	case PACKET_FANOUT_RND:
+	case PACKET_FANOUT_QM:
 		break;
 	default:
 		return -EINVAL;
@@ -1539,7 +1610,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock,
 			       struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_pkt *saddr = (struct sockaddr_pkt *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name);
 	struct sk_buff *skb = NULL;
 	struct net_device *dev;
 	__be16 proto = 0;
@@ -1777,7 +1848,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 	skb->dropcount = atomic_read(&sk->sk_drops);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
 	spin_unlock(&sk->sk_receive_queue.lock);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 	return 0;
 
 drop_n_acct:
@@ -1812,6 +1883,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct timespec ts;
 	__u32 ts_status;
 
+	/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
+	 * We may add members to them until current aligned size without forcing
+	 * userspace to call getsockopt(..., PACKET_HDRLEN, ...).
+	 */
+	BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32);
+	BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48);
+
 	if (skb->pkt_type == PACKET_LOOPBACK)
 		goto drop;
 
@@ -1918,11 +1996,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		h.h2->tp_nsec = ts.tv_nsec;
 		if (vlan_tx_tag_present(skb)) {
 			h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
-			status |= TP_STATUS_VLAN_VALID;
+			h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto);
+			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
 			h.h2->tp_vlan_tci = 0;
+			h.h2->tp_vlan_tpid = 0;
 		}
-		h.h2->tp_padding = 0;
+		memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding));
 		hdrlen = sizeof(*h.h2);
 		break;
 	case TPACKET_V3:
@@ -1936,6 +2016,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		h.h3->tp_net = netoff;
 		h.h3->tp_sec  = ts.tv_sec;
 		h.h3->tp_nsec = ts.tv_nsec;
+		memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding));
 		hdrlen = sizeof(*h.h3);
 		break;
 	default:
@@ -1954,25 +2035,26 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		sll->sll_ifindex = dev->ifindex;
 
 	smp_mb();
+
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
-	{
+	if (po->tp_version <= TPACKET_V2) {
 		u8 *start, *end;
 
-		if (po->tp_version <= TPACKET_V2) {
-			end = (u8 *)PAGE_ALIGN((unsigned long)h.raw
-				+ macoff + snaplen);
-			for (start = h.raw; start < end; start += PAGE_SIZE)
-				flush_dcache_page(pgv_to_page(start));
-		}
-		smp_wmb();
+		end = (u8 *) PAGE_ALIGN((unsigned long) h.raw +
+					macoff + snaplen);
+
+		for (start = h.raw; start < end; start += PAGE_SIZE)
+			flush_dcache_page(pgv_to_page(start));
 	}
+	smp_wmb();
 #endif
+
 	if (po->tp_version <= TPACKET_V2)
 		__packet_set_status(po, h.raw, status);
 	else
 		prb_clear_blk_fill_status(&po->rx_ring);
 
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 
 drop_n_restore:
 	if (skb_head != skb->data && skb_shared(skb)) {
@@ -1987,7 +2069,7 @@ ring_is_full:
 	po->stats.stats1.tp_drops++;
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 	kfree_skb(copy_skb);
 	goto drop_n_restore;
 }
@@ -1995,14 +2077,13 @@ ring_is_full:
 static void tpacket_destruct_skb(struct sk_buff *skb)
 {
 	struct packet_sock *po = pkt_sk(skb->sk);
-	void *ph;
 
 	if (likely(po->tx_ring.pg_vec)) {
+		void *ph;
 		__u32 ts;
 
 		ph = skb_shinfo(skb)->destructor_arg;
-		BUG_ON(atomic_read(&po->tx_ring.pending) == 0);
-		atomic_dec(&po->tx_ring.pending);
+		packet_dec_pending(&po->tx_ring);
 
 		ts = __packet_set_timestamp(po, ph, skb);
 		__packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts);
@@ -2142,7 +2223,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	__be16 proto;
 	int err, reserve = 0;
 	void *ph;
-	struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name);
+	bool need_wait = !(msg->msg_flags & MSG_DONTWAIT);
 	int tp_len, size_max;
 	unsigned char *addr;
 	int len_sum = 0;
@@ -2175,8 +2257,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
-	reserve = dev->hard_header_len;
-
+	reserve = dev->hard_header_len + VLAN_HLEN;
 	size_max = po->tx_ring.frame_size
 		- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
 
@@ -2185,10 +2266,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 
 	do {
 		ph = packet_current_frame(po, &po->tx_ring,
-				TP_STATUS_SEND_REQUEST);
-
+					  TP_STATUS_SEND_REQUEST);
 		if (unlikely(ph == NULL)) {
-			schedule();
+			if (need_wait && need_resched())
+				schedule();
 			continue;
 		}
 
@@ -2203,8 +2284,19 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 			goto out_status;
 
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
-				addr, hlen);
+					  addr, hlen);
+		if (tp_len > dev->mtu + dev->hard_header_len) {
+			struct ethhdr *ehdr;
+			/* Earlier code assumed this would be a VLAN pkt,
+			 * double-check this now that we have the actual
+			 * packet in hand.
+			 */
 
+			skb_reset_mac_header(skb);
+			ehdr = eth_hdr(skb);
+			if (ehdr->h_proto != htons(ETH_P_8021Q))
+				tp_len = -EMSGSIZE;
+		}
 		if (unlikely(tp_len < 0)) {
 			if (po->tp_loss) {
 				__packet_set_status(po, ph,
@@ -2219,10 +2311,11 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 			}
 		}
 
-		skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
+		packet_pick_tx_queue(dev, skb);
+
 		skb->destructor = tpacket_destruct_skb;
 		__packet_set_status(po, ph, TP_STATUS_SENDING);
-		atomic_inc(&po->tx_ring.pending);
+		packet_inc_pending(&po->tx_ring);
 
 		status = TP_STATUS_SEND_REQUEST;
 		err = po->xmit(skb);
@@ -2243,9 +2336,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		packet_increment_head(&po->tx_ring);
 		len_sum += tp_len;
 	} while (likely((ph != NULL) ||
-			((!(msg->msg_flags & MSG_DONTWAIT)) &&
-			 (atomic_read(&po->tx_ring.pending))))
-		);
+		/* Note: packet_read_pending() might be slow if we have
+		 * to call it as it's per_cpu variable, but in fast-path
+		 * we already short-circuit the loop with the first
+		 * condition, and luckily don't have to go that path
+		 * anyway.
+		 */
+		 (need_wait && packet_read_pending(&po->tx_ring))));
 
 	err = len_sum;
 	goto out_put;
@@ -2287,7 +2384,7 @@ static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad,
 static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name);
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
@@ -2429,7 +2526,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
-	skb_set_queue_mapping(skb, packet_pick_tx_queue(dev));
+
+	packet_pick_tx_queue(dev, skb);
 
 	if (po->has_vnet_hdr) {
 		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
@@ -2544,6 +2642,7 @@ static int packet_release(struct socket *sock)
 	/* Purge queues */
 
 	skb_queue_purge(&sk->sk_receive_queue);
+	packet_free_pending(po);
 	sk_refcnt_debug_release(sk);
 
 	sock_put(sk);
@@ -2554,9 +2653,12 @@ static int packet_release(struct socket *sock)
  *	Attach a packet hook.
  */
 
-static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protocol)
+static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
+	const struct net_device *dev_curr;
+	__be16 proto_curr;
+	bool need_rehook;
 
 	if (po->fanout) {
 		if (dev)
@@ -2566,21 +2668,29 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc
 	}
 
 	lock_sock(sk);
-
 	spin_lock(&po->bind_lock);
-	unregister_prot_hook(sk, true);
 
-	po->num = protocol;
-	po->prot_hook.type = protocol;
-	if (po->prot_hook.dev)
-		dev_put(po->prot_hook.dev);
+	proto_curr = po->prot_hook.type;
+	dev_curr = po->prot_hook.dev;
 
-	po->prot_hook.dev = dev;
-	po->ifindex = dev ? dev->ifindex : 0;
+	need_rehook = proto_curr != proto || dev_curr != dev;
+
+	if (need_rehook) {
+		unregister_prot_hook(sk, true);
+
+		po->num = proto;
+		po->prot_hook.type = proto;
 
-	packet_cached_dev_assign(po, dev);
+		if (po->prot_hook.dev)
+			dev_put(po->prot_hook.dev);
 
-	if (protocol == 0)
+		po->prot_hook.dev = dev;
+
+		po->ifindex = dev ? dev->ifindex : 0;
+		packet_cached_dev_assign(po, dev);
+	}
+
+	if (proto == 0 || !need_rehook)
 		goto out_unlock;
 
 	if (!dev || (dev->flags & IFF_UP)) {
@@ -2694,6 +2804,10 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	po->num = proto;
 	po->xmit = dev_queue_xmit;
 
+	err = packet_alloc_pending(po);
+	if (err)
+		goto out2;
+
 	packet_cached_dev_reset(po);
 
 	sk->sk_destruct = packet_sock_destruct;
@@ -2726,6 +2840,8 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	preempt_enable();
 
 	return 0;
+out2:
+	sk_free(sk);
 out:
 	return err;
 }
@@ -2845,6 +2961,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 		 * in, we fill it in now.
 		 */
 		if (sock->type == SOCK_PACKET) {
+			__sockaddr_check_size(sizeof(struct sockaddr_pkt));
 			msg->msg_namelen = sizeof(struct sockaddr_pkt);
 		} else {
 			struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
@@ -2867,11 +2984,12 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 		aux.tp_net = skb_network_offset(skb);
 		if (vlan_tx_tag_present(skb)) {
 			aux.tp_vlan_tci = vlan_tx_tag_get(skb);
-			aux.tp_status |= TP_STATUS_VLAN_VALID;
+			aux.tp_vlan_tpid = ntohs(skb->vlan_proto);
+			aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
 			aux.tp_vlan_tci = 0;
+			aux.tp_vlan_tpid = 0;
 		}
-		aux.tp_padding = 0;
 		put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
 	}
 
@@ -3570,34 +3688,26 @@ static void free_pg_vec(struct pgv *pg_vec, unsigned int order,
 
 static char *alloc_one_pg_vec_page(unsigned long order)
 {
-	char *buffer = NULL;
+	char *buffer;
 	gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP |
 			  __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY;
 
 	buffer = (char *) __get_free_pages(gfp_flags, order);
-
 	if (buffer)
 		return buffer;
 
-	/*
-	 * __get_free_pages failed, fall back to vmalloc
-	 */
+	/* __get_free_pages failed, fall back to vmalloc */
 	buffer = vzalloc((1 << order) * PAGE_SIZE);
-
 	if (buffer)
 		return buffer;
 
-	/*
-	 * vmalloc failed, lets dig into swap here
-	 */
+	/* vmalloc failed, lets dig into swap here */
 	gfp_flags &= ~__GFP_NORETRY;
-	buffer = (char *)__get_free_pages(gfp_flags, order);
+	buffer = (char *) __get_free_pages(gfp_flags, order);
 	if (buffer)
 		return buffer;
 
-	/*
-	 * complete and utter failure
-	 */
+	/* complete and utter failure */
 	return NULL;
 }
 
@@ -3652,7 +3762,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	if (!closing) {
 		if (atomic_read(&po->mapped))
 			goto out;
-		if (atomic_read(&rb->pending))
+		if (packet_read_pending(rb))
 			goto out;
 	}
 
@@ -3704,7 +3814,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		 */
 			if (!tx_ring)
 				init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring);
-				break;
+			break;
 		default:
 			break;
 		}
diff --git a/net/packet/diag.c b/net/packet/diag.c
index a9584a2f6d6..92f2c7107ee 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -3,6 +3,7 @@
 #include <linux/net.h>
 #include <linux/netdevice.h>
 #include <linux/packet_diag.h>
+#include <linux/percpu.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
@@ -127,6 +128,7 @@ static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb)
 
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 			struct packet_diag_req *req,
+			bool may_report_filterinfo,
 			struct user_namespace *user_ns,
 			u32 portid, u32 seq, u32 flags, int sk_ino)
 {
@@ -171,7 +173,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 		goto out_nlmsg_trim;
 
 	if ((req->pdiag_show & PACKET_SHOW_FILTER) &&
-	    sock_diag_put_filterinfo(user_ns, sk, skb, PACKET_DIAG_FILTER))
+	    sock_diag_put_filterinfo(may_report_filterinfo, sk, skb,
+				     PACKET_DIAG_FILTER))
 		goto out_nlmsg_trim;
 
 	return nlmsg_end(skb, nlh);
@@ -187,9 +190,11 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	struct packet_diag_req *req;
 	struct net *net;
 	struct sock *sk;
+	bool may_report_filterinfo;
 
 	net = sock_net(skb->sk);
 	req = nlmsg_data(cb->nlh);
+	may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
 
 	mutex_lock(&net->packet.sklist_lock);
 	sk_for_each(sk, &net->packet.sklist) {
@@ -199,6 +204,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 			goto next;
 
 		if (sk_diag_fill(sk, skb, req,
+				 may_report_filterinfo,
 				 sk_user_ns(NETLINK_CB(cb->skb).sk),
 				 NETLINK_CB(cb->skb).portid,
 				 cb->nlh->nlmsg_seq, NLM_F_MULTI,
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 0a87d7b36c9..eb9580a6b25 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -64,7 +64,7 @@ struct packet_ring_buffer {
 	unsigned int		pg_vec_pages;
 	unsigned int		pg_vec_len;
 
-	atomic_t		pending;
+	unsigned int __percpu	*pending_refcnt;
 
 	struct tpacket_kbdq_core	prb_bdqc;
 };
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 38946b26e47..290352c0e6b 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -86,7 +86,7 @@ static int pn_init(struct sock *sk)
 static int pn_sendmsg(struct kiocb *iocb, struct sock *sk,
 			struct msghdr *msg, size_t len)
 {
-	struct sockaddr_pn *target;
+	DECLARE_SOCKADDR(struct sockaddr_pn *, target, msg->msg_name);
 	struct sk_buff *skb;
 	int err;
 
@@ -94,13 +94,12 @@ static int pn_sendmsg(struct kiocb *iocb, struct sock *sk,
 				MSG_CMSG_COMPAT))
 		return -EOPNOTSUPP;
 
-	if (msg->msg_name == NULL)
+	if (target == NULL)
 		return -EDESTADDRREQ;
 
 	if (msg->msg_namelen < sizeof(struct sockaddr_pn))
 		return -EINVAL;
 
-	target = (struct sockaddr_pn *)msg->msg_name;
 	if (target->spn_family != AF_PHONET)
 		return -EAFNOSUPPORT;
 
@@ -160,6 +159,7 @@ static int pn_recvmsg(struct kiocb *iocb, struct sock *sk,
 	rval = (flags & MSG_TRUNC) ? skb->len : copylen;
 
 	if (msg->msg_name != NULL) {
+		__sockaddr_check_size(sizeof(sa));
 		memcpy(msg->msg_name, &sa, sizeof(sa));
 		*addr_len = sizeof(sa);
 	}
diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c
index a2fba7edfd1..66dc65e7c6a 100644
--- a/net/phonet/pep-gprs.c
+++ b/net/phonet/pep-gprs.c
@@ -37,7 +37,7 @@
 struct gprs_dev {
 	struct sock		*sk;
 	void			(*old_state_change)(struct sock *);
-	void			(*old_data_ready)(struct sock *, int);
+	void			(*old_data_ready)(struct sock *);
 	void			(*old_write_space)(struct sock *);
 
 	struct net_device	*dev;
@@ -146,7 +146,7 @@ drop:
 	return err;
 }
 
-static void gprs_data_ready(struct sock *sk, int len)
+static void gprs_data_ready(struct sock *sk)
 {
 	struct gprs_dev *gp = sk->sk_user_data;
 	struct sk_buff *skb;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index e77411735de..70a547ea517 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -462,10 +462,9 @@ out:
 queue:
 	skb->dev = NULL;
 	skb_set_owner_r(skb, sk);
-	err = skb->len;
 	skb_queue_tail(queue, skb);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, err);
+		sk->sk_data_ready(sk);
 	return NET_RX_SUCCESS;
 }
 
@@ -587,10 +586,9 @@ static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb)
 		pn->rx_credits--;
 		skb->dev = NULL;
 		skb_set_owner_r(skb, sk);
-		err = skb->len;
 		skb_queue_tail(&sk->sk_receive_queue, skb);
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk, err);
+			sk->sk_data_ready(sk);
 		return NET_RX_SUCCESS;
 
 	case PNS_PEP_CONNECT_RESP:
@@ -698,7 +696,7 @@ static int pep_do_rcv(struct sock *sk, struct sk_buff *skb)
 		skb_queue_head(&sk->sk_receive_queue, skb);
 		sk_acceptq_added(sk);
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk, 0);
+			sk->sk_data_ready(sk);
 		return NET_RX_SUCCESS;
 
 	case PNS_PEP_DISCONNECT_REQ:
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index dc15f430080..b64151ade6b 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -70,10 +70,10 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err;
 	u8 pnaddr;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	ASSERT_RTNL();
@@ -233,10 +233,10 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err;
 	u8 dst;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	ASSERT_RTNL();
diff --git a/net/rds/bind.c b/net/rds/bind.c
index b5ad65a0067..a2e6562da75 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -117,7 +117,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
 		rover = be16_to_cpu(*port);
 		last = rover;
 	} else {
-		rover = max_t(u16, net_random(), 2);
+		rover = max_t(u16, prandom_u32(), 2);
 		last = rover - 1;
 	}
 
diff --git a/net/rds/ib.c b/net/rds/ib.c
index b4c8b0022fe..ba2dffeff60 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -338,7 +338,8 @@ static int rds_ib_laddr_check(__be32 addr)
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
 	/* due to this, we will claim to support iWARP devices unless we
 	   check node_type. */
-	if (ret || cm_id->device->node_type != RDMA_NODE_IB_CA)
+	if (ret || !cm_id->device ||
+	    cm_id->device->node_type != RDMA_NODE_IB_CA)
 		ret = -EADDRNOTAVAIL;
 
 	rdsdebug("addr %pI4 ret %d node type %d\n",
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 8eb9501e3d6..d67de453c35 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -421,8 +421,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 				 struct rds_ib_refill_cache *cache)
 {
 	unsigned long flags;
-	struct list_head *old;
-	struct list_head __percpu *chpfirst;
+	struct list_head *old, *chpfirst;
 
 	local_irq_save(flags);
 
@@ -432,7 +431,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 	else /* put on front */
 		list_add_tail(new_item, chpfirst);
 
-	__this_cpu_write(chpfirst, new_item);
+	__this_cpu_write(cache->percpu->first, new_item);
 	__this_cpu_inc(cache->percpu->count);
 
 	if (__this_cpu_read(cache->percpu->count) < RDS_IB_RECYCLE_BATCH_COUNT)
@@ -452,7 +451,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 	} while (old);
 
 
-	__this_cpu_write(chpfirst, NULL);
+	__this_cpu_write(cache->percpu->first, NULL);
 	__this_cpu_write(cache->percpu->count, 0);
 end:
 	local_irq_restore(flags);
@@ -599,7 +598,7 @@ static void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq,
 {
 	atomic64_set(&ic->i_ack_next, seq);
 	if (ack_required) {
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
 	}
 }
@@ -607,7 +606,7 @@ static void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq,
 static u64 rds_ib_get_ack(struct rds_ib_connection *ic)
 {
 	clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	return atomic64_read(&ic->i_ack_next);
 }
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 37be6e226d1..1dde91e3dc7 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -298,7 +298,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context)
 		rds_ib_stats_inc(s_ib_tx_cq_event);
 
 		if (wc.wr_id == RDS_IB_ACK_WR_ID) {
-			if (ic->i_ack_queued + HZ/2 < jiffies)
+			if (time_after(jiffies, ic->i_ack_queued + HZ/2))
 				rds_ib_stats_inc(s_ib_tx_stalled);
 			rds_ib_ack_send_complete(ic);
 			continue;
@@ -315,7 +315,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context)
 
 			rm = rds_ib_send_unmap_op(ic, send, wc.status);
 
-			if (send->s_queued + HZ/2 < jiffies)
+			if (time_after(jiffies, send->s_queued + HZ/2))
 				rds_ib_stats_inc(s_ib_tx_stalled);
 
 			if (send->s_op) {
diff --git a/net/rds/iw.c b/net/rds/iw.c
index 7826d46baa7..589935661d6 100644
--- a/net/rds/iw.c
+++ b/net/rds/iw.c
@@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr)
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
 	/* due to this, we will claim to support IB devices unless we
 	   check node_type. */
-	if (ret || cm_id->device->node_type != RDMA_NODE_RNIC)
+	if (ret || !cm_id->device ||
+	    cm_id->device->node_type != RDMA_NODE_RNIC)
 		ret = -EADDRNOTAVAIL;
 
 	rdsdebug("addr %pI4 ret %d node type %d\n",
diff --git a/net/rds/iw_recv.c b/net/rds/iw_recv.c
index 45033358358..aa8bf678600 100644
--- a/net/rds/iw_recv.c
+++ b/net/rds/iw_recv.c
@@ -429,7 +429,7 @@ static void rds_iw_set_ack(struct rds_iw_connection *ic, u64 seq,
 {
 	atomic64_set(&ic->i_ack_next, seq);
 	if (ack_required) {
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
 	}
 }
@@ -437,7 +437,7 @@ static void rds_iw_set_ack(struct rds_iw_connection *ic, u64 seq,
 static u64 rds_iw_get_ack(struct rds_iw_connection *ic)
 {
 	clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	return atomic64_read(&ic->i_ack_next);
 }
diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c
index e40c3c5db2c..9105ea03aec 100644
--- a/net/rds/iw_send.c
+++ b/net/rds/iw_send.c
@@ -232,7 +232,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context)
 		}
 
 		if (wc.wr_id == RDS_IW_ACK_WR_ID) {
-			if (ic->i_ack_queued + HZ/2 < jiffies)
+			if (time_after(jiffies, ic->i_ack_queued + HZ/2))
 				rds_iw_stats_inc(s_iw_tx_stalled);
 			rds_iw_ack_send_complete(ic);
 			continue;
@@ -267,7 +267,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context)
 
 			send->s_wr.opcode = 0xdead;
 			send->s_wr.num_sge = 1;
-			if (send->s_queued + HZ/2 < jiffies)
+			if (time_after(jiffies, send->s_queued + HZ/2))
 				rds_iw_stats_inc(s_iw_tx_stalled);
 
 			/* If a RDMA operation produced an error, signal this right
diff --git a/net/rds/iw_sysctl.c b/net/rds/iw_sysctl.c
index 89c91515ed0..139239d2cb2 100644
--- a/net/rds/iw_sysctl.c
+++ b/net/rds/iw_sysctl.c
@@ -111,8 +111,7 @@ static struct ctl_table rds_iw_sysctl_table[] = {
 
 void rds_iw_sysctl_exit(void)
 {
-	if (rds_iw_sysctl_hdr)
-		unregister_net_sysctl_table(rds_iw_sysctl_hdr);
+	unregister_net_sysctl_table(rds_iw_sysctl_hdr);
 }
 
 int rds_iw_sysctl_init(void)
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index c2be901d19e..6cd9d1deafc 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -168,7 +168,7 @@ static int rds_rdma_listen_init(void)
 		return ret;
 	}
 
-	sin.sin_family = AF_INET,
+	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY);
 	sin.sin_port = (__force u16)htons(RDS_PORT);
 
diff --git a/net/rds/recv.c b/net/rds/recv.c
index de339b24ca1..bd82522534f 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -402,7 +402,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 	struct rds_sock *rs = rds_sk_to_rs(sk);
 	long timeo;
 	int ret = 0, nonblock = msg_flags & MSG_DONTWAIT;
-	struct sockaddr_in *sin;
+	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct rds_incoming *inc = NULL;
 
 	/* udp_recvmsg()->sock_recvtimeo() gets away without locking too.. */
@@ -479,7 +479,6 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 
 		rds_stats_inc(s_recv_delivered);
 
-		sin = (struct sockaddr_in *)msg->msg_name;
 		if (sin) {
 			sin->sin_family = AF_INET;
 			sin->sin_port = inc->i_hdr.h_sport;
diff --git a/net/rds/send.c b/net/rds/send.c
index 88eace57dd6..23718160d71 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -107,7 +107,7 @@ static int acquire_in_xmit(struct rds_connection *conn)
 static void release_in_xmit(struct rds_connection *conn)
 {
 	clear_bit(RDS_IN_XMIT, &conn->c_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	/*
 	 * We don't use wait_on_bit()/wake_up_bit() because our waking is in a
 	 * hot path and finding waiters is very rare.  We don't want to walk
@@ -661,7 +661,7 @@ void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
 
 	/* order flag updates with spin locks */
 	if (!list_empty(&list))
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 
 	spin_unlock_irqrestore(&conn->c_lock, flags);
 
@@ -691,7 +691,7 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
 	}
 
 	/* order flag updates with the rs lock */
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	spin_unlock_irqrestore(&rs->rs_lock, flags);
 
@@ -922,7 +922,7 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct rds_sock *rs = rds_sk_to_rs(sk);
-	struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
 	__be32 daddr;
 	__be16 dport;
 	struct rds_message *rm = NULL;
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index b5cb2aa08f3..c3b0cd43eb5 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -94,8 +94,7 @@ static struct ctl_table rds_sysctl_rds_table[] = {
 
 void rds_sysctl_exit(void)
 {
-	if (rds_sysctl_reg_table)
-		unregister_net_sysctl_table(rds_sysctl_reg_table);
+	unregister_net_sysctl_table(rds_sysctl_reg_table);
 }
 
 int rds_sysctl_init(void)
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 9cf2927d002..65637491f72 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -61,12 +61,12 @@ void rds_tcp_state_change(struct sock *sk);
 /* tcp_listen.c */
 int rds_tcp_listen_init(void);
 void rds_tcp_listen_stop(void);
-void rds_tcp_listen_data_ready(struct sock *sk, int bytes);
+void rds_tcp_listen_data_ready(struct sock *sk);
 
 /* tcp_recv.c */
 int rds_tcp_recv_init(void);
 void rds_tcp_recv_exit(void);
-void rds_tcp_data_ready(struct sock *sk, int bytes);
+void rds_tcp_data_ready(struct sock *sk);
 int rds_tcp_recv(struct rds_connection *conn);
 void rds_tcp_inc_free(struct rds_incoming *inc);
 int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iovec *iov,
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 7787537e9c2..23ab4dcd1d9 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -108,9 +108,9 @@ static void rds_tcp_accept_worker(struct work_struct *work)
 		cond_resched();
 }
 
-void rds_tcp_listen_data_ready(struct sock *sk, int bytes)
+void rds_tcp_listen_data_ready(struct sock *sk)
 {
-	void (*ready)(struct sock *sk, int bytes);
+	void (*ready)(struct sock *sk);
 
 	rdsdebug("listen data ready sk %p\n", sk);
 
@@ -132,7 +132,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes)
 
 out:
 	read_unlock(&sk->sk_callback_lock);
-	ready(sk, bytes);
+	ready(sk);
 }
 
 int rds_tcp_listen_init(void)
@@ -153,7 +153,7 @@ int rds_tcp_listen_init(void)
 	sock->sk->sk_data_ready = rds_tcp_listen_data_ready;
 	write_unlock_bh(&sock->sk->sk_callback_lock);
 
-	sin.sin_family = PF_INET,
+	sin.sin_family = PF_INET;
 	sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY);
 	sin.sin_port = (__force u16)htons(RDS_TCP_PORT);
 
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index 4fac4f2bb9d..9ae6e0a264e 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -314,13 +314,13 @@ int rds_tcp_recv(struct rds_connection *conn)
 	return ret;
 }
 
-void rds_tcp_data_ready(struct sock *sk, int bytes)
+void rds_tcp_data_ready(struct sock *sk)
 {
-	void (*ready)(struct sock *sk, int bytes);
+	void (*ready)(struct sock *sk);
 	struct rds_connection *conn;
 	struct rds_tcp_connection *tc;
 
-	rdsdebug("data ready sk %p bytes %d\n", sk, bytes);
+	rdsdebug("data ready sk %p\n", sk);
 
 	read_lock(&sk->sk_callback_lock);
 	conn = sk->sk_user_data;
@@ -337,7 +337,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes)
 		queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
 out:
 	read_unlock(&sk->sk_callback_lock);
-	ready(sk, bytes);
+	ready(sk);
 }
 
 int rds_tcp_recv_init(void)
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 81cf5a4c5e4..53b17ca0dff 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -93,7 +93,7 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
 		rm->m_ack_seq = tc->t_last_sent_nxt +
 				sizeof(struct rds_header) +
 				be32_to_cpu(rm->m_inc.i_hdr.h_len) - 1;
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		set_bit(RDS_MSG_HAS_ACK_SEQ, &rm->m_flags);
 		tc->t_last_expected_una = rm->m_ack_seq + 1;
 
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 1bacc107994..b3b16c070a7 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -14,9 +14,7 @@
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/kernel.h>
@@ -791,7 +789,8 @@ void rfkill_resume_polling(struct rfkill *rfkill)
 	if (!rfkill->ops->poll)
 		return;
 
-	schedule_work(&rfkill->poll_work.work);
+	queue_delayed_work(system_power_efficient_wq,
+			   &rfkill->poll_work, 0);
 }
 EXPORT_SYMBOL(rfkill_resume_polling);
 
@@ -896,7 +895,8 @@ static void rfkill_poll(struct work_struct *work)
 	 */
 	rfkill->ops->poll(rfkill, rfkill->data);
 
-	schedule_delayed_work(&rfkill->poll_work,
+	queue_delayed_work(system_power_efficient_wq,
+		&rfkill->poll_work,
 		round_jiffies_relative(POLL_INTERVAL));
 }
 
@@ -960,7 +960,8 @@ int __must_check rfkill_register(struct rfkill *rfkill)
 	INIT_WORK(&rfkill->sync_work, rfkill_sync_work);
 
 	if (rfkill->ops->poll)
-		schedule_delayed_work(&rfkill->poll_work,
+		queue_delayed_work(system_power_efficient_wq,
+			&rfkill->poll_work,
 			round_jiffies_relative(POLL_INTERVAL));
 
 	if (!rfkill->persistent || rfkill_epo_lock_active) {
diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index 5620d3c0747..14c98e48f26 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -25,19 +25,17 @@
 #include <linux/clk.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
-#include <linux/acpi_gpio.h>
+#include <linux/gpio/consumer.h>
 
 #include <linux/rfkill-gpio.h>
 
 struct rfkill_gpio_data {
 	const char		*name;
 	enum rfkill_type	type;
-	int			reset_gpio;
-	int			shutdown_gpio;
+	struct gpio_desc	*reset_gpio;
+	struct gpio_desc	*shutdown_gpio;
 
 	struct rfkill		*rfkill_dev;
-	char			*reset_name;
-	char			*shutdown_name;
 	struct clk		*clk;
 
 	bool			clk_enabled;
@@ -47,21 +45,14 @@ static int rfkill_gpio_set_power(void *data, bool blocked)
 {
 	struct rfkill_gpio_data *rfkill = data;
 
-	if (blocked) {
-		if (gpio_is_valid(rfkill->shutdown_gpio))
-			gpio_set_value(rfkill->shutdown_gpio, 0);
-		if (gpio_is_valid(rfkill->reset_gpio))
-			gpio_set_value(rfkill->reset_gpio, 0);
-		if (!IS_ERR(rfkill->clk) && rfkill->clk_enabled)
-			clk_disable(rfkill->clk);
-	} else {
-		if (!IS_ERR(rfkill->clk) && !rfkill->clk_enabled)
-			clk_enable(rfkill->clk);
-		if (gpio_is_valid(rfkill->reset_gpio))
-			gpio_set_value(rfkill->reset_gpio, 1);
-		if (gpio_is_valid(rfkill->shutdown_gpio))
-			gpio_set_value(rfkill->shutdown_gpio, 1);
-	}
+	if (!blocked && !IS_ERR(rfkill->clk) && !rfkill->clk_enabled)
+		clk_enable(rfkill->clk);
+
+	gpiod_set_value_cansleep(rfkill->shutdown_gpio, !blocked);
+	gpiod_set_value_cansleep(rfkill->reset_gpio, !blocked);
+
+	if (blocked && !IS_ERR(rfkill->clk) && rfkill->clk_enabled)
+		clk_disable(rfkill->clk);
 
 	rfkill->clk_enabled = blocked;
 
@@ -83,8 +74,6 @@ static int rfkill_gpio_acpi_probe(struct device *dev,
 
 	rfkill->name = dev_name(dev);
 	rfkill->type = (unsigned)id->driver_data;
-	rfkill->reset_gpio = acpi_get_gpio_by_index(dev, 0, NULL);
-	rfkill->shutdown_gpio = acpi_get_gpio_by_index(dev, 1, NULL);
 
 	return 0;
 }
@@ -93,9 +82,8 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 {
 	struct rfkill_gpio_platform_data *pdata = pdev->dev.platform_data;
 	struct rfkill_gpio_data *rfkill;
-	const char *clk_name = NULL;
-	int ret = 0;
-	int len = 0;
+	struct gpio_desc *gpio;
+	int ret;
 
 	rfkill = devm_kzalloc(&pdev->dev, sizeof(*rfkill), GFP_KERNEL);
 	if (!rfkill)
@@ -106,61 +94,36 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 	} else if (pdata) {
-		clk_name = pdata->power_clk_name;
 		rfkill->name = pdata->name;
 		rfkill->type = pdata->type;
-		rfkill->reset_gpio = pdata->reset_gpio;
-		rfkill->shutdown_gpio = pdata->shutdown_gpio;
 	} else {
 		return -ENODEV;
 	}
 
-	/* make sure at-least one of the GPIO is defined and that
-	 * a name is specified for this instance */
-	if ((!gpio_is_valid(rfkill->reset_gpio) &&
-	     !gpio_is_valid(rfkill->shutdown_gpio)) || !rfkill->name) {
-		pr_warn("%s: invalid platform data\n", __func__);
-		return -EINVAL;
-	}
+	rfkill->clk = devm_clk_get(&pdev->dev, NULL);
 
-	if (pdata && pdata->gpio_runtime_setup) {
-		ret = pdata->gpio_runtime_setup(pdev);
-		if (ret) {
-			pr_warn("%s: can't set up gpio\n", __func__);
+	gpio = devm_gpiod_get_index(&pdev->dev, "reset", 0);
+	if (!IS_ERR(gpio)) {
+		ret = gpiod_direction_output(gpio, 0);
+		if (ret)
 			return ret;
-		}
+		rfkill->reset_gpio = gpio;
 	}
 
-	len = strlen(rfkill->name);
-	rfkill->reset_name = devm_kzalloc(&pdev->dev, len + 7, GFP_KERNEL);
-	if (!rfkill->reset_name)
-		return -ENOMEM;
-
-	rfkill->shutdown_name = devm_kzalloc(&pdev->dev, len + 10, GFP_KERNEL);
-	if (!rfkill->shutdown_name)
-		return -ENOMEM;
-
-	snprintf(rfkill->reset_name, len + 6 , "%s_reset", rfkill->name);
-	snprintf(rfkill->shutdown_name, len + 9, "%s_shutdown", rfkill->name);
-
-	rfkill->clk = devm_clk_get(&pdev->dev, clk_name);
-
-	if (gpio_is_valid(rfkill->reset_gpio)) {
-		ret = devm_gpio_request_one(&pdev->dev, rfkill->reset_gpio,
-					    0, rfkill->reset_name);
-		if (ret) {
-			pr_warn("%s: failed to get reset gpio.\n", __func__);
+	gpio = devm_gpiod_get_index(&pdev->dev, "shutdown", 1);
+	if (!IS_ERR(gpio)) {
+		ret = gpiod_direction_output(gpio, 0);
+		if (ret)
 			return ret;
-		}
+		rfkill->shutdown_gpio = gpio;
 	}
 
-	if (gpio_is_valid(rfkill->shutdown_gpio)) {
-		ret = devm_gpio_request_one(&pdev->dev, rfkill->shutdown_gpio,
-					    0, rfkill->shutdown_name);
-		if (ret) {
-			pr_warn("%s: failed to get shutdown gpio.\n", __func__);
-			return ret;
-		}
+	/* Make sure at-least one of the GPIO is defined and that
+	 * a name is specified for this instance
+	 */
+	if ((!rfkill->reset_gpio && !rfkill->shutdown_gpio) || !rfkill->name) {
+		dev_err(&pdev->dev, "invalid platform data\n");
+		return -EINVAL;
 	}
 
 	rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev,
@@ -183,20 +146,23 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 static int rfkill_gpio_remove(struct platform_device *pdev)
 {
 	struct rfkill_gpio_data *rfkill = platform_get_drvdata(pdev);
-	struct rfkill_gpio_platform_data *pdata = pdev->dev.platform_data;
 
-	if (pdata && pdata->gpio_runtime_close)
-		pdata->gpio_runtime_close(pdev);
 	rfkill_unregister(rfkill->rfkill_dev);
 	rfkill_destroy(rfkill->rfkill_dev);
 
 	return 0;
 }
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id rfkill_acpi_match[] = {
+	{ "BCM2E1A", RFKILL_TYPE_BLUETOOTH },
+	{ "BCM2E39", RFKILL_TYPE_BLUETOOTH },
+	{ "BCM2E3D", RFKILL_TYPE_BLUETOOTH },
 	{ "BCM4752", RFKILL_TYPE_GPS },
+	{ "LNV4752", RFKILL_TYPE_GPS },
 	{ },
 };
+#endif
 
 static struct platform_driver rfkill_gpio_driver = {
 	.probe = rfkill_gpio_probe,
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 33af77246bf..8451c8cdc9d 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1012,7 +1012,7 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros
 	make_rose->source_call   = facilities.source_call;
 	make_rose->source_ndigis = facilities.source_ndigis;
 	for (n = 0 ; n < facilities.source_ndigis ; n++)
-		make_rose->source_digis[n]= facilities.source_digis[n];
+		make_rose->source_digis[n] = facilities.source_digis[n];
 	make_rose->neighbour     = neigh;
 	make_rose->device        = dev;
 	make_rose->facilities    = facilities;
@@ -1041,7 +1041,7 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros
 	rose_start_heartbeat(make);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 
 	return 1;
 }
@@ -1051,7 +1051,7 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct rose_sock *rose = rose_sk(sk);
-	struct sockaddr_rose *usrose = (struct sockaddr_rose *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_rose *, usrose, msg->msg_name);
 	int err;
 	struct full_sockaddr_rose srose;
 	struct sk_buff *skb;
@@ -1253,6 +1253,8 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	if (msg->msg_name) {
 		struct sockaddr_rose *srose;
+		DECLARE_SOCKADDR(struct full_sockaddr_rose *, full_srose,
+				 msg->msg_name);
 
 		memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose));
 		srose = msg->msg_name;
@@ -1260,18 +1262,9 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 		srose->srose_addr   = rose->dest_addr;
 		srose->srose_call   = rose->dest_call;
 		srose->srose_ndigis = rose->dest_ndigis;
-		if (msg->msg_namelen >= sizeof(struct full_sockaddr_rose)) {
-			struct full_sockaddr_rose *full_srose = (struct full_sockaddr_rose *)msg->msg_name;
-			for (n = 0 ; n < rose->dest_ndigis ; n++)
-				full_srose->srose_digis[n] = rose->dest_digis[n];
-			msg->msg_namelen = sizeof(struct full_sockaddr_rose);
-		} else {
-			if (rose->dest_ndigis >= 1) {
-				srose->srose_ndigis = 1;
-				srose->srose_digi = rose->dest_digis[0];
-			}
-			msg->msg_namelen = sizeof(struct sockaddr_rose);
-		}
+		for (n = 0 ; n < rose->dest_ndigis ; n++)
+			full_srose->srose_digis[n] = rose->dest_digis[n];
+		msg->msg_namelen = sizeof(struct full_sockaddr_rose);
 	}
 
 	skb_free_datagram(sk, skb);
diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c
index 28dbdb911b8..50005888be5 100644
--- a/net/rose/rose_dev.c
+++ b/net/rose/rose_dev.c
@@ -146,7 +146,7 @@ static netdev_tx_t rose_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static const struct header_ops rose_header_ops = {
 	.create	= rose_header,
-	.rebuild= rose_rebuild_header,
+	.rebuild = rose_rebuild_header,
 };
 
 static const struct net_device_ops rose_netdev_ops = {
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index d1c3429b69e..ec126f91276 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -20,9 +20,8 @@ af-rxrpc-y := \
 	ar-skbuff.o \
 	ar-transport.o
 
-ifeq ($(CONFIG_PROC_FS),y)
-af-rxrpc-y += ar-proc.o
-endif
+af-rxrpc-$(CONFIG_PROC_FS) += ar-proc.o
+af-rxrpc-$(CONFIG_SYSCTL) += sysctl.o
 
 obj-$(CONFIG_AF_RXRPC) += af-rxrpc.o
 
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index e61aa6001c6..7b167048963 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -838,6 +838,12 @@ static int __init af_rxrpc_init(void)
 		goto error_key_type_s;
 	}
 
+	ret = rxrpc_sysctl_init();
+	if (ret < 0) {
+		printk(KERN_CRIT "RxRPC: Cannot register sysctls\n");
+		goto error_sysctls;
+	}
+
 #ifdef CONFIG_PROC_FS
 	proc_create("rxrpc_calls", 0, init_net.proc_net, &rxrpc_call_seq_fops);
 	proc_create("rxrpc_conns", 0, init_net.proc_net,
@@ -845,6 +851,8 @@ static int __init af_rxrpc_init(void)
 #endif
 	return 0;
 
+error_sysctls:
+	unregister_key_type(&key_type_rxrpc_s);
 error_key_type_s:
 	unregister_key_type(&key_type_rxrpc);
 error_key_type:
@@ -865,6 +873,7 @@ error_call_jar:
 static void __exit af_rxrpc_exit(void)
 {
 	_enter("");
+	rxrpc_sysctl_exit();
 	unregister_key_type(&key_type_rxrpc_s);
 	unregister_key_type(&key_type_rxrpc);
 	sock_unregister(PF_RXRPC);
diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c
index e4d9cbcff40..c6be17a959a 100644
--- a/net/rxrpc/ar-ack.c
+++ b/net/rxrpc/ar-ack.c
@@ -19,12 +19,61 @@
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
 
-static unsigned int rxrpc_ack_defer = 1;
+/*
+ * How long to wait before scheduling ACK generation after seeing a
+ * packet with RXRPC_REQUEST_ACK set (in jiffies).
+ */
+unsigned rxrpc_requested_ack_delay = 1;
 
-static const char *const rxrpc_acks[] = {
-	"---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", "IDL",
-	"-?-"
-};
+/*
+ * How long to wait before scheduling an ACK with subtype DELAY (in jiffies).
+ *
+ * We use this when we've received new data packets.  If those packets aren't
+ * all consumed within this time we will send a DELAY ACK if an ACK was not
+ * requested to let the sender know it doesn't need to resend.
+ */
+unsigned rxrpc_soft_ack_delay = 1 * HZ;
+
+/*
+ * How long to wait before scheduling an ACK with subtype IDLE (in jiffies).
+ *
+ * We use this when we've consumed some previously soft-ACK'd packets when
+ * further packets aren't immediately received to decide when to send an IDLE
+ * ACK let the other end know that it can free up its Tx buffer space.
+ */
+unsigned rxrpc_idle_ack_delay = 0.5 * HZ;
+
+/*
+ * Receive window size in packets.  This indicates the maximum number of
+ * unconsumed received packets we're willing to retain in memory.  Once this
+ * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further
+ * packets.
+ */
+unsigned rxrpc_rx_window_size = 32;
+
+/*
+ * Maximum Rx MTU size.  This indicates to the sender the size of jumbo packet
+ * made by gluing normal packets together that we're willing to handle.
+ */
+unsigned rxrpc_rx_mtu = 5692;
+
+/*
+ * The maximum number of fragments in a received jumbo packet that we tell the
+ * sender that we're willing to handle.
+ */
+unsigned rxrpc_rx_jumbo_max = 4;
+
+static const char *rxrpc_acks(u8 reason)
+{
+	static const char *const str[] = {
+		"---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY",
+		"IDL", "-?-"
+	};
+
+	if (reason >= ARRAY_SIZE(str))
+		reason = ARRAY_SIZE(str) - 1;
+	return str[reason];
+}
 
 static const s8 rxrpc_ack_priority[] = {
 	[0]				= 0,
@@ -50,7 +99,7 @@ void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 	ASSERTCMP(prior, >, 0);
 
 	_enter("{%d},%s,%%%x,%u",
-	       call->debug_id, rxrpc_acks[ack_reason], ntohl(serial),
+	       call->debug_id, rxrpc_acks(ack_reason), ntohl(serial),
 	       immediate);
 
 	if (prior < rxrpc_ack_priority[call->ackr_reason]) {
@@ -75,24 +124,23 @@ void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 	switch (ack_reason) {
 	case RXRPC_ACK_DELAY:
 		_debug("run delay timer");
-		call->ack_timer.expires = jiffies + rxrpc_ack_timeout * HZ;
-		add_timer(&call->ack_timer);
-		return;
+		expiry = rxrpc_soft_ack_delay;
+		goto run_timer;
 
 	case RXRPC_ACK_IDLE:
 		if (!immediate) {
 			_debug("run defer timer");
-			expiry = 1;
+			expiry = rxrpc_idle_ack_delay;
 			goto run_timer;
 		}
 		goto cancel_timer;
 
 	case RXRPC_ACK_REQUESTED:
-		if (!rxrpc_ack_defer)
+		expiry = rxrpc_requested_ack_delay;
+		if (!expiry)
 			goto cancel_timer;
 		if (!immediate || serial == cpu_to_be32(1)) {
 			_debug("run defer timer");
-			expiry = rxrpc_ack_defer;
 			goto run_timer;
 		}
 
@@ -637,7 +685,7 @@ process_further:
 		       hard,
 		       ntohl(ack.previousPacket),
 		       ntohl(ack.serial),
-		       rxrpc_acks[ack.reason],
+		       rxrpc_acks(ack.reason),
 		       ack.nAcks);
 
 		rxrpc_extract_ackinfo(call, skb, latest, ack.nAcks);
@@ -1167,11 +1215,11 @@ send_ACK:
 	mtu = call->conn->trans->peer->if_mtu;
 	mtu -= call->conn->trans->peer->hdrsize;
 	ackinfo.maxMTU	= htonl(mtu);
-	ackinfo.rwind	= htonl(32);
+	ackinfo.rwind	= htonl(rxrpc_rx_window_size);
 
 	/* permit the peer to send us jumbo packets if it wants to */
-	ackinfo.rxMTU	= htonl(5692);
-	ackinfo.jumbo_max = htonl(4);
+	ackinfo.rxMTU	= htonl(rxrpc_rx_mtu);
+	ackinfo.jumbo_max = htonl(rxrpc_rx_jumbo_max);
 
 	hdr.serial = htonl(atomic_inc_return(&call->conn->serial));
 	_proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }",
@@ -1180,7 +1228,7 @@ send_ACK:
 	       ntohl(ack.firstPacket),
 	       ntohl(ack.previousPacket),
 	       ntohl(ack.serial),
-	       rxrpc_acks[ack.reason],
+	       rxrpc_acks(ack.reason),
 	       ack.nAcks);
 
 	del_timer_sync(&call->ack_timer);
diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/ar-call.c
index a3bbb360a3f..a9e05db0f5d 100644
--- a/net/rxrpc/ar-call.c
+++ b/net/rxrpc/ar-call.c
@@ -12,10 +12,22 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/circ_buf.h>
+#include <linux/hashtable.h>
+#include <linux/spinlock_types.h>
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
 
+/*
+ * Maximum lifetime of a call (in jiffies).
+ */
+unsigned rxrpc_max_call_lifetime = 60 * HZ;
+
+/*
+ * Time till dead call expires after last use (in jiffies).
+ */
+unsigned rxrpc_dead_call_expiry = 2 * HZ;
+
 const char *const rxrpc_call_states[] = {
 	[RXRPC_CALL_CLIENT_SEND_REQUEST]	= "ClSndReq",
 	[RXRPC_CALL_CLIENT_AWAIT_REPLY]		= "ClAwtRpl",
@@ -38,8 +50,6 @@ const char *const rxrpc_call_states[] = {
 struct kmem_cache *rxrpc_call_jar;
 LIST_HEAD(rxrpc_calls);
 DEFINE_RWLOCK(rxrpc_call_lock);
-static unsigned int rxrpc_call_max_lifetime = 60;
-static unsigned int rxrpc_dead_call_timeout = 2;
 
 static void rxrpc_destroy_call(struct work_struct *work);
 static void rxrpc_call_life_expired(unsigned long _call);
@@ -47,6 +57,145 @@ static void rxrpc_dead_call_expired(unsigned long _call);
 static void rxrpc_ack_time_expired(unsigned long _call);
 static void rxrpc_resend_time_expired(unsigned long _call);
 
+static DEFINE_SPINLOCK(rxrpc_call_hash_lock);
+static DEFINE_HASHTABLE(rxrpc_call_hash, 10);
+
+/*
+ * Hash function for rxrpc_call_hash
+ */
+static unsigned long rxrpc_call_hashfunc(
+	u8		clientflag,
+	__be32		cid,
+	__be32		call_id,
+	__be32		epoch,
+	__be16		service_id,
+	sa_family_t	proto,
+	void		*localptr,
+	unsigned int	addr_size,
+	const u8	*peer_addr)
+{
+	const u16 *p;
+	unsigned int i;
+	unsigned long key;
+	u32 hcid = ntohl(cid);
+
+	_enter("");
+
+	key = (unsigned long)localptr;
+	/* We just want to add up the __be32 values, so forcing the
+	 * cast should be okay.
+	 */
+	key += (__force u32)epoch;
+	key += (__force u16)service_id;
+	key += (__force u32)call_id;
+	key += (hcid & RXRPC_CIDMASK) >> RXRPC_CIDSHIFT;
+	key += hcid & RXRPC_CHANNELMASK;
+	key += clientflag;
+	key += proto;
+	/* Step through the peer address in 16-bit portions for speed */
+	for (i = 0, p = (const u16 *)peer_addr; i < addr_size >> 1; i++, p++)
+		key += *p;
+	_leave(" key = 0x%lx", key);
+	return key;
+}
+
+/*
+ * Add a call to the hashtable
+ */
+static void rxrpc_call_hash_add(struct rxrpc_call *call)
+{
+	unsigned long key;
+	unsigned int addr_size = 0;
+
+	_enter("");
+	switch (call->proto) {
+	case AF_INET:
+		addr_size = sizeof(call->peer_ip.ipv4_addr);
+		break;
+	case AF_INET6:
+		addr_size = sizeof(call->peer_ip.ipv6_addr);
+		break;
+	default:
+		break;
+	}
+	key = rxrpc_call_hashfunc(call->in_clientflag, call->cid,
+				  call->call_id, call->epoch,
+				  call->service_id, call->proto,
+				  call->conn->trans->local, addr_size,
+				  call->peer_ip.ipv6_addr);
+	/* Store the full key in the call */
+	call->hash_key = key;
+	spin_lock(&rxrpc_call_hash_lock);
+	hash_add_rcu(rxrpc_call_hash, &call->hash_node, key);
+	spin_unlock(&rxrpc_call_hash_lock);
+	_leave("");
+}
+
+/*
+ * Remove a call from the hashtable
+ */
+static void rxrpc_call_hash_del(struct rxrpc_call *call)
+{
+	_enter("");
+	spin_lock(&rxrpc_call_hash_lock);
+	hash_del_rcu(&call->hash_node);
+	spin_unlock(&rxrpc_call_hash_lock);
+	_leave("");
+}
+
+/*
+ * Find a call in the hashtable and return it, or NULL if it
+ * isn't there.
+ */
+struct rxrpc_call *rxrpc_find_call_hash(
+	u8		clientflag,
+	__be32		cid,
+	__be32		call_id,
+	__be32		epoch,
+	__be16		service_id,
+	void		*localptr,
+	sa_family_t	proto,
+	const u8	*peer_addr)
+{
+	unsigned long key;
+	unsigned int addr_size = 0;
+	struct rxrpc_call *call = NULL;
+	struct rxrpc_call *ret = NULL;
+
+	_enter("");
+	switch (proto) {
+	case AF_INET:
+		addr_size = sizeof(call->peer_ip.ipv4_addr);
+		break;
+	case AF_INET6:
+		addr_size = sizeof(call->peer_ip.ipv6_addr);
+		break;
+	default:
+		break;
+	}
+
+	key = rxrpc_call_hashfunc(clientflag, cid, call_id, epoch,
+				  service_id, proto, localptr, addr_size,
+				  peer_addr);
+	hash_for_each_possible_rcu(rxrpc_call_hash, call, hash_node, key) {
+		if (call->hash_key == key &&
+		    call->call_id == call_id &&
+		    call->cid == cid &&
+		    call->in_clientflag == clientflag &&
+		    call->service_id == service_id &&
+		    call->proto == proto &&
+		    call->local == localptr &&
+		    memcmp(call->peer_ip.ipv6_addr, peer_addr,
+			      addr_size) == 0 &&
+		    call->epoch == epoch) {
+			ret = call;
+			break;
+		}
+	}
+	_leave(" = %p", ret);
+	return ret;
+}
+
 /*
  * allocate a new call
  */
@@ -91,7 +240,7 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp)
 	call->rx_data_expect = 1;
 	call->rx_data_eaten = 0;
 	call->rx_first_oos = 0;
-	call->ackr_win_top = call->rx_data_eaten + 1 + RXRPC_MAXACKS;
+	call->ackr_win_top = call->rx_data_eaten + 1 + rxrpc_rx_window_size;
 	call->creation_jif = jiffies;
 	return call;
 }
@@ -128,11 +277,31 @@ static struct rxrpc_call *rxrpc_alloc_client_call(
 		return ERR_PTR(ret);
 	}
 
+	/* Record copies of information for hashtable lookup */
+	call->proto = rx->proto;
+	call->local = trans->local;
+	switch (call->proto) {
+	case AF_INET:
+		call->peer_ip.ipv4_addr =
+			trans->peer->srx.transport.sin.sin_addr.s_addr;
+		break;
+	case AF_INET6:
+		memcpy(call->peer_ip.ipv6_addr,
+		       trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8,
+		       sizeof(call->peer_ip.ipv6_addr));
+		break;
+	}
+	call->epoch = call->conn->epoch;
+	call->service_id = call->conn->service_id;
+	call->in_clientflag = call->conn->in_clientflag;
+	/* Add the new call to the hashtable */
+	rxrpc_call_hash_add(call);
+
 	spin_lock(&call->conn->trans->peer->lock);
 	list_add(&call->error_link, &call->conn->trans->peer->error_targets);
 	spin_unlock(&call->conn->trans->peer->lock);
 
-	call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ;
+	call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime;
 	add_timer(&call->lifetimer);
 
 	_leave(" = %p", call);
@@ -320,9 +489,12 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx,
 		parent = *p;
 		call = rb_entry(parent, struct rxrpc_call, conn_node);
 
-		if (call_id < call->call_id)
+		/* The tree is sorted in order of the __be32 value without
+		 * turning it into host order.
+		 */
+		if ((__force u32)call_id < (__force u32)call->call_id)
 			p = &(*p)->rb_left;
-		else if (call_id > call->call_id)
+		else if ((__force u32)call_id > (__force u32)call->call_id)
 			p = &(*p)->rb_right;
 		else
 			goto old_call;
@@ -347,9 +519,31 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx,
 	list_add_tail(&call->link, &rxrpc_calls);
 	write_unlock_bh(&rxrpc_call_lock);
 
+	/* Record copies of information for hashtable lookup */
+	call->proto = rx->proto;
+	call->local = conn->trans->local;
+	switch (call->proto) {
+	case AF_INET:
+		call->peer_ip.ipv4_addr =
+			conn->trans->peer->srx.transport.sin.sin_addr.s_addr;
+		break;
+	case AF_INET6:
+		memcpy(call->peer_ip.ipv6_addr,
+		       conn->trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8,
+		       sizeof(call->peer_ip.ipv6_addr));
+		break;
+	default:
+		break;
+	}
+	call->epoch = conn->epoch;
+	call->service_id = conn->service_id;
+	call->in_clientflag = conn->in_clientflag;
+	/* Add the new call to the hashtable */
+	rxrpc_call_hash_add(call);
+
 	_net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id);
 
-	call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ;
+	call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime;
 	add_timer(&call->lifetimer);
 	_leave(" = %p {%d} [new]", call, call->debug_id);
 	return call;
@@ -533,7 +727,7 @@ void rxrpc_release_call(struct rxrpc_call *call)
 	del_timer_sync(&call->resend_timer);
 	del_timer_sync(&call->ack_timer);
 	del_timer_sync(&call->lifetimer);
-	call->deadspan.expires = jiffies + rxrpc_dead_call_timeout * HZ;
+	call->deadspan.expires = jiffies + rxrpc_dead_call_expiry;
 	add_timer(&call->deadspan);
 
 	_leave("");
@@ -665,6 +859,9 @@ static void rxrpc_cleanup_call(struct rxrpc_call *call)
 		rxrpc_put_connection(call->conn);
 	}
 
+	/* Remove the call from the hash */
+	rxrpc_call_hash_del(call);
+
 	if (call->acks_window) {
 		_debug("kill Tx window %d",
 		       CIRC_CNT(call->acks_head, call->acks_tail,
diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c
index 4106ca95ec8..6631f4f1e39 100644
--- a/net/rxrpc/ar-connection.c
+++ b/net/rxrpc/ar-connection.c
@@ -18,11 +18,15 @@
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
 
+/*
+ * Time till a connection expires after last use (in seconds).
+ */
+unsigned rxrpc_connection_expiry = 10 * 60;
+
 static void rxrpc_connection_reaper(struct work_struct *work);
 
 LIST_HEAD(rxrpc_connections);
 DEFINE_RWLOCK(rxrpc_connection_lock);
-static unsigned long rxrpc_connection_timeout = 10 * 60;
 static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper);
 
 /*
@@ -381,6 +385,8 @@ static int rxrpc_connect_exclusive(struct rxrpc_sock *rx,
 
 		rxrpc_assign_connection_id(conn);
 		rx->conn = conn;
+	} else {
+		spin_lock(&trans->client_lock);
 	}
 
 	/* we've got a connection with a free channel and we can now attach the
@@ -860,7 +866,7 @@ static void rxrpc_connection_reaper(struct work_struct *work)
 
 		spin_lock(&conn->trans->client_lock);
 		write_lock(&conn->trans->conn_lock);
-		reap_time = conn->put_time + rxrpc_connection_timeout;
+		reap_time = conn->put_time + rxrpc_connection_expiry;
 
 		if (atomic_read(&conn->usage) > 0) {
 			;
@@ -914,7 +920,7 @@ void __exit rxrpc_destroy_all_connections(void)
 {
 	_enter("");
 
-	rxrpc_connection_timeout = 0;
+	rxrpc_connection_expiry = 0;
 	cancel_delayed_work(&rxrpc_connection_reap);
 	rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0);
 
diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c
index a9206087b4d..db57458c824 100644
--- a/net/rxrpc/ar-error.c
+++ b/net/rxrpc/ar-error.c
@@ -83,6 +83,7 @@ void rxrpc_UDP_error_report(struct sock *sk)
 
 		if (mtu == 0) {
 			/* they didn't give us a size, estimate one */
+			mtu = peer->if_mtu;
 			if (mtu > 1500) {
 				mtu >>= 1;
 				if (mtu < 1500)
diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c
index 529572f18d1..63b21e580de 100644
--- a/net/rxrpc/ar-input.c
+++ b/net/rxrpc/ar-input.c
@@ -25,8 +25,6 @@
 #include <net/net_namespace.h>
 #include "ar-internal.h"
 
-unsigned long rxrpc_ack_timeout = 1;
-
 const char *rxrpc_pkts[] = {
 	"?00",
 	"DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG",
@@ -115,7 +113,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
 			spin_unlock_bh(&sk->sk_receive_queue.lock);
 
 			if (!sock_flag(sk, SOCK_DEAD))
-				sk->sk_data_ready(sk, skb_len);
+				sk->sk_data_ready(sk);
 		}
 		skb = NULL;
 	} else {
@@ -349,8 +347,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb)
 	 * it */
 	if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
 		_proto("ACK Requested on %%%u", serial);
-		rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial,
-				  !(sp->hdr.flags & RXRPC_MORE_PACKETS));
+		rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, false);
 	}
 
 	switch (sp->hdr.type) {
@@ -526,36 +523,38 @@ protocol_error:
  * post an incoming packet to the appropriate call/socket to deal with
  * - must get rid of the sk_buff, either by freeing it or by queuing it
  */
-static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn,
+static void rxrpc_post_packet_to_call(struct rxrpc_call *call,
 				      struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp;
-	struct rxrpc_call *call;
-	struct rb_node *p;
-	__be32 call_id;
-
-	_enter("%p,%p", conn, skb);
 
-	read_lock_bh(&conn->lock);
+	_enter("%p,%p", call, skb);
 
 	sp = rxrpc_skb(skb);
 
-	/* look at extant calls by channel number first */
-	call = conn->channels[ntohl(sp->hdr.cid) & RXRPC_CHANNELMASK];
-	if (!call || call->call_id != sp->hdr.callNumber)
-		goto call_not_extant;
-
 	_debug("extant call [%d]", call->state);
-	ASSERTCMP(call->conn, ==, conn);
 
 	read_lock(&call->state_lock);
 	switch (call->state) {
 	case RXRPC_CALL_LOCALLY_ABORTED:
-		if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events))
+		if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events)) {
 			rxrpc_queue_call(call);
+			goto free_unlock;
+		}
 	case RXRPC_CALL_REMOTELY_ABORTED:
 	case RXRPC_CALL_NETWORK_ERROR:
 	case RXRPC_CALL_DEAD:
+		goto dead_call;
+	case RXRPC_CALL_COMPLETE:
+	case RXRPC_CALL_CLIENT_FINAL_ACK:
+		/* complete server call */
+		if (call->conn->in_clientflag)
+			goto dead_call;
+		/* resend last packet of a completed call */
+		_debug("final ack again");
+		rxrpc_get_call(call);
+		set_bit(RXRPC_CALL_ACK_FINAL, &call->events);
+		rxrpc_queue_call(call);
 		goto free_unlock;
 	default:
 		break;
@@ -563,7 +562,6 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn,
 
 	read_unlock(&call->state_lock);
 	rxrpc_get_call(call);
-	read_unlock_bh(&conn->lock);
 
 	if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
 	    sp->hdr.flags & RXRPC_JUMBO_PACKET)
@@ -574,78 +572,16 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn,
 	rxrpc_put_call(call);
 	goto done;
 
-call_not_extant:
-	/* search the completed calls in case what we're dealing with is
-	 * there */
-	_debug("call not extant");
-
-	call_id = sp->hdr.callNumber;
-	p = conn->calls.rb_node;
-	while (p) {
-		call = rb_entry(p, struct rxrpc_call, conn_node);
-
-		if (call_id < call->call_id)
-			p = p->rb_left;
-		else if (call_id > call->call_id)
-			p = p->rb_right;
-		else
-			goto found_completed_call;
-	}
-
 dead_call:
-	/* it's a either a really old call that we no longer remember or its a
-	 * new incoming call */
-	read_unlock_bh(&conn->lock);
-
-	if (sp->hdr.flags & RXRPC_CLIENT_INITIATED &&
-	    sp->hdr.seq == cpu_to_be32(1)) {
-		_debug("incoming call");
-		skb_queue_tail(&conn->trans->local->accept_queue, skb);
-		rxrpc_queue_work(&conn->trans->local->acceptor);
-		goto done;
-	}
-
-	_debug("dead call");
-	skb->priority = RX_CALL_DEAD;
-	rxrpc_reject_packet(conn->trans->local, skb);
-	goto done;
-
-	/* resend last packet of a completed call
-	 * - client calls may have been aborted or ACK'd
-	 * - server calls may have been aborted
-	 */
-found_completed_call:
-	_debug("completed call");
-
-	if (atomic_read(&call->usage) == 0)
-		goto dead_call;
-
-	/* synchronise any state changes */
-	read_lock(&call->state_lock);
-	ASSERTIFCMP(call->state != RXRPC_CALL_CLIENT_FINAL_ACK,
-		    call->state, >=, RXRPC_CALL_COMPLETE);
-
-	if (call->state == RXRPC_CALL_LOCALLY_ABORTED ||
-	    call->state == RXRPC_CALL_REMOTELY_ABORTED ||
-	    call->state == RXRPC_CALL_DEAD) {
-		read_unlock(&call->state_lock);
-		goto dead_call;
-	}
-
-	if (call->conn->in_clientflag) {
-		read_unlock(&call->state_lock);
-		goto dead_call; /* complete server call */
+	if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) {
+		skb->priority = RX_CALL_DEAD;
+		rxrpc_reject_packet(call->conn->trans->local, skb);
+		goto unlock;
 	}
-
-	_debug("final ack again");
-	rxrpc_get_call(call);
-	set_bit(RXRPC_CALL_ACK_FINAL, &call->events);
-	rxrpc_queue_call(call);
-
 free_unlock:
-	read_unlock(&call->state_lock);
-	read_unlock_bh(&conn->lock);
 	rxrpc_free_skb(skb);
+unlock:
+	read_unlock(&call->state_lock);
 done:
 	_leave("");
 }
@@ -664,21 +600,46 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn,
 	rxrpc_queue_conn(conn);
 }
 
+static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local,
+					       struct sk_buff *skb,
+					       struct rxrpc_skb_priv *sp)
+{
+	struct rxrpc_peer *peer;
+	struct rxrpc_transport *trans;
+	struct rxrpc_connection *conn;
+
+	peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr,
+				udp_hdr(skb)->source);
+	if (IS_ERR(peer))
+		goto cant_find_conn;
+
+	trans = rxrpc_find_transport(local, peer);
+	rxrpc_put_peer(peer);
+	if (!trans)
+		goto cant_find_conn;
+
+	conn = rxrpc_find_connection(trans, &sp->hdr);
+	rxrpc_put_transport(trans);
+	if (!conn)
+		goto cant_find_conn;
+
+	return conn;
+cant_find_conn:
+	return NULL;
+}
+
 /*
  * handle data received on the local endpoint
  * - may be called in interrupt context
  */
-void rxrpc_data_ready(struct sock *sk, int count)
+void rxrpc_data_ready(struct sock *sk)
 {
-	struct rxrpc_connection *conn;
-	struct rxrpc_transport *trans;
 	struct rxrpc_skb_priv *sp;
 	struct rxrpc_local *local;
-	struct rxrpc_peer *peer;
 	struct sk_buff *skb;
 	int ret;
 
-	_enter("%p, %d", sk, count);
+	_enter("%p", sk);
 
 	ASSERT(!irqs_disabled());
 
@@ -749,27 +710,34 @@ void rxrpc_data_ready(struct sock *sk, int count)
 	    (sp->hdr.callNumber == 0 || sp->hdr.seq == 0))
 		goto bad_message;
 
-	peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr, udp_hdr(skb)->source);
-	if (IS_ERR(peer))
-		goto cant_route_call;
+	if (sp->hdr.callNumber == 0) {
+		/* This is a connection-level packet. These should be
+		 * fairly rare, so the extra overhead of looking them up the
+		 * old-fashioned way doesn't really hurt */
+		struct rxrpc_connection *conn;
 
-	trans = rxrpc_find_transport(local, peer);
-	rxrpc_put_peer(peer);
-	if (!trans)
-		goto cant_route_call;
+		conn = rxrpc_conn_from_local(local, skb, sp);
+		if (!conn)
+			goto cant_route_call;
 
-	conn = rxrpc_find_connection(trans, &sp->hdr);
-	rxrpc_put_transport(trans);
-	if (!conn)
-		goto cant_route_call;
-
-	_debug("CONN %p {%d}", conn, conn->debug_id);
-
-	if (sp->hdr.callNumber == 0)
+		_debug("CONN %p {%d}", conn, conn->debug_id);
 		rxrpc_post_packet_to_conn(conn, skb);
-	else
-		rxrpc_post_packet_to_call(conn, skb);
-	rxrpc_put_connection(conn);
+		rxrpc_put_connection(conn);
+	} else {
+		struct rxrpc_call *call;
+		u8 in_clientflag = 0;
+
+		if (sp->hdr.flags & RXRPC_CLIENT_INITIATED)
+			in_clientflag = RXRPC_CLIENT_INITIATED;
+		call = rxrpc_find_call_hash(in_clientflag, sp->hdr.cid,
+					    sp->hdr.callNumber, sp->hdr.epoch,
+					    sp->hdr.serviceId, local, AF_INET,
+					    (u8 *)&ip_hdr(skb)->saddr);
+		if (call)
+			rxrpc_post_packet_to_call(call, skb);
+		else
+			goto cant_route_call;
+	}
 	rxrpc_put_local(local);
 	return;
 
@@ -790,8 +758,10 @@ cant_route_call:
 		skb->priority = RX_CALL_DEAD;
 	}
 
-	_debug("reject");
-	rxrpc_reject_packet(local, skb);
+	if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) {
+		_debug("reject type %d",sp->hdr.type);
+		rxrpc_reject_packet(local, skb);
+	}
 	rxrpc_put_local(local);
 	_leave(" [no call]");
 	return;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5f43675ee1d..ba9fd36d3f1 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -396,9 +396,20 @@ struct rxrpc_call {
 #define RXRPC_ACKR_WINDOW_ASZ DIV_ROUND_UP(RXRPC_MAXACKS, BITS_PER_LONG)
 	unsigned long		ackr_window[RXRPC_ACKR_WINDOW_ASZ + 1];
 
+	struct hlist_node	hash_node;
+	unsigned long		hash_key;	/* Full hash key */
+	u8			in_clientflag;	/* Copy of conn->in_clientflag for hashing */
+	struct rxrpc_local	*local;		/* Local endpoint. Used for hashing. */
+	sa_family_t		proto;		/* Frame protocol */
 	/* the following should all be in net order */
 	__be32			cid;		/* connection ID + channel index  */
 	__be32			call_id;	/* call ID on connection  */
+	__be32			epoch;		/* epoch of this connection */
+	__be16			service_id;	/* service ID */
+	union {					/* Peer IP address for hashing */
+		__be32	ipv4_addr;
+		__u8	ipv6_addr[16];		/* Anticipates eventual IPv6 support */
+	} peer_ip;
 };
 
 /*
@@ -433,6 +444,13 @@ int rxrpc_reject_call(struct rxrpc_sock *);
 /*
  * ar-ack.c
  */
+extern unsigned rxrpc_requested_ack_delay;
+extern unsigned rxrpc_soft_ack_delay;
+extern unsigned rxrpc_idle_ack_delay;
+extern unsigned rxrpc_rx_window_size;
+extern unsigned rxrpc_rx_mtu;
+extern unsigned rxrpc_rx_jumbo_max;
+
 void __rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool);
 void rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool);
 void rxrpc_process_call(struct work_struct *);
@@ -440,10 +458,14 @@ void rxrpc_process_call(struct work_struct *);
 /*
  * ar-call.c
  */
+extern unsigned rxrpc_max_call_lifetime;
+extern unsigned rxrpc_dead_call_expiry;
 extern struct kmem_cache *rxrpc_call_jar;
 extern struct list_head rxrpc_calls;
 extern rwlock_t rxrpc_call_lock;
 
+struct rxrpc_call *rxrpc_find_call_hash(u8,  __be32, __be32, __be32,
+					__be16, void *, sa_family_t, const u8 *);
 struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *,
 					 struct rxrpc_transport *,
 					 struct rxrpc_conn_bundle *,
@@ -460,6 +482,7 @@ void __exit rxrpc_destroy_all_calls(void);
 /*
  * ar-connection.c
  */
+extern unsigned rxrpc_connection_expiry;
 extern struct list_head rxrpc_connections;
 extern rwlock_t rxrpc_connection_lock;
 
@@ -493,10 +516,9 @@ void rxrpc_UDP_error_handler(struct work_struct *);
 /*
  * ar-input.c
  */
-extern unsigned long rxrpc_ack_timeout;
 extern const char *rxrpc_pkts[];
 
-void rxrpc_data_ready(struct sock *, int);
+void rxrpc_data_ready(struct sock *);
 int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, bool);
 void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *);
 
@@ -504,6 +526,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *);
  * ar-local.c
  */
 extern rwlock_t rxrpc_local_lock;
+
 struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *);
 void rxrpc_put_local(struct rxrpc_local *);
 void __exit rxrpc_destroy_all_locals(void);
@@ -522,7 +545,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t,
 /*
  * ar-output.c
  */
-extern int rxrpc_resend_timeout;
+extern unsigned rxrpc_resend_timeout;
 
 int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *);
 int rxrpc_client_sendmsg(struct kiocb *, struct rxrpc_sock *,
@@ -572,6 +595,8 @@ void rxrpc_packet_destructor(struct sk_buff *);
 /*
  * ar-transport.c
  */
+extern unsigned rxrpc_transport_expiry;
+
 struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *,
 					    struct rxrpc_peer *, gfp_t);
 void rxrpc_put_transport(struct rxrpc_transport *);
@@ -580,6 +605,17 @@ struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *,
 					     struct rxrpc_peer *);
 
 /*
+ * sysctl.c
+ */
+#ifdef CONFIG_SYSCTL
+extern int __init rxrpc_sysctl_init(void);
+extern void rxrpc_sysctl_exit(void);
+#else
+static inline int __init rxrpc_sysctl_init(void) { return 0; }
+static inline void rxrpc_sysctl_exit(void) {}
+#endif
+
+/*
  * debug tracing
  */
 extern unsigned int rxrpc_debug;
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index 7633a752c65..0ad080790a3 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -99,7 +99,7 @@ static int rxrpc_instantiate_xdr_rxkad(struct key *key, const __be32 *xdr,
 	_debug("tktlen: %x", tktlen);
 	if (tktlen > AFSTOKEN_RK_TIX_MAX)
 		return -EKEYREJECTED;
-	if (8 * 4 + tktlen != toklen)
+	if (toklen < 8 * 4 + tktlen)
 		return -EKEYREJECTED;
 
 	plen = sizeof(*token) + sizeof(*token->kad) + tktlen;
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index e1ac183d50b..0b4b9a79f5a 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -18,7 +18,10 @@
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
 
-int rxrpc_resend_timeout = 4;
+/*
+ * Time till packet resend (in jiffies).
+ */
+unsigned rxrpc_resend_timeout = 4 * HZ;
 
 static int rxrpc_send_data(struct kiocb *iocb,
 			   struct rxrpc_sock *rx,
@@ -152,8 +155,8 @@ int rxrpc_client_sendmsg(struct kiocb *iocb, struct rxrpc_sock *rx,
 	if (trans) {
 		service_id = rx->service_id;
 		if (msg->msg_name) {
-			struct sockaddr_rxrpc *srx =
-				(struct sockaddr_rxrpc *) msg->msg_name;
+			DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx,
+					 msg->msg_name);
 			service_id = htons(srx->srx_service);
 		}
 		key = rx->key;
@@ -487,7 +490,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	       ntohl(sp->hdr.serial), ntohl(sp->hdr.seq));
 
 	sp->need_resend = false;
-	sp->resend_at = jiffies + rxrpc_resend_timeout * HZ;
+	sp->resend_at = jiffies + rxrpc_resend_timeout;
 	if (!test_and_set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags)) {
 		_debug("run timer");
 		call->resend_timer.expires = sp->resend_at;
@@ -666,6 +669,7 @@ static int rxrpc_send_data(struct kiocb *iocb,
 		/* add the packet to the send queue if it's now full */
 		if (sp->remain <= 0 || (segment == 0 && !more)) {
 			struct rxrpc_connection *conn = call->conn;
+			uint32_t seq;
 			size_t pad;
 
 			/* pad out if we're using security */
@@ -678,11 +682,12 @@ static int rxrpc_send_data(struct kiocb *iocb,
 					memset(skb_put(skb, pad), 0, pad);
 			}
 
+			seq = atomic_inc_return(&call->sequence);
+
 			sp->hdr.epoch = conn->epoch;
 			sp->hdr.cid = call->cid;
 			sp->hdr.callNumber = call->call_id;
-			sp->hdr.seq =
-				htonl(atomic_inc_return(&call->sequence));
+			sp->hdr.seq = htonl(seq);
 			sp->hdr.serial =
 				htonl(atomic_inc_return(&conn->serial));
 			sp->hdr.type = RXRPC_PACKET_TYPE_DATA;
@@ -697,6 +702,8 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			else if (CIRC_SPACE(call->acks_head, call->acks_tail,
 					    call->acks_winsz) > 1)
 				sp->hdr.flags |= RXRPC_MORE_PACKETS;
+			if (more && seq & 1)
+				sp->hdr.flags |= RXRPC_REQUEST_ACK;
 
 			ret = rxrpc_secure_packet(
 				call, skb, skb->mark,
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 898492a8d61..e9aaa65c077 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -180,15 +180,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
 		if (copy > len - copied)
 			copy = len - copied;
 
-		if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-			ret = skb_copy_datagram_iovec(skb, offset,
-						      msg->msg_iov, copy);
-		} else {
-			ret = skb_copy_and_csum_datagram_iovec(skb, offset,
-							       msg->msg_iov);
-			if (ret == -EINVAL)
-				goto csum_copy_error;
-		}
+		ret = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copy);
 
 		if (ret < 0)
 			goto copy_error;
@@ -347,16 +339,6 @@ copy_error:
 	_leave(" = %d", ret);
 	return ret;
 
-csum_copy_error:
-	_debug("csum error");
-	release_sock(&rx->sk);
-	if (continue_call)
-		rxrpc_put_call(continue_call);
-	rxrpc_kill_skb(skb);
-	skb_kill_datagram(&rx->sk, skb, flags);
-	rxrpc_put_call(call);
-	return -EAGAIN;
-
 wait_interrupted:
 	ret = sock_intr_errno(timeo);
 wait_error:
diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/ar-skbuff.c
index de755e04d29..4cfab49e329 100644
--- a/net/rxrpc/ar-skbuff.c
+++ b/net/rxrpc/ar-skbuff.c
@@ -83,9 +83,14 @@ static void rxrpc_hard_ACK_data(struct rxrpc_call *call,
 		rxrpc_request_final_ACK(call);
 	} else if (atomic_dec_and_test(&call->ackr_not_idle) &&
 		   test_and_clear_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags)) {
+		/* We previously soft-ACK'd some received packets that have now
+		 * been consumed, so send a hard-ACK if no more packets are
+		 * immediately forthcoming to allow the transmitter to free up
+		 * its Tx bufferage.
+		 */
 		_debug("send Rx idle ACK");
 		__rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, sp->hdr.serial,
-				    true);
+				    false);
 	}
 
 	spin_unlock_bh(&call->lock);
diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c
index 92df566930b..1976dec84f2 100644
--- a/net/rxrpc/ar-transport.c
+++ b/net/rxrpc/ar-transport.c
@@ -17,11 +17,15 @@
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
 
+/*
+ * Time after last use at which transport record is cleaned up.
+ */
+unsigned rxrpc_transport_expiry = 3600 * 24;
+
 static void rxrpc_transport_reaper(struct work_struct *work);
 
 static LIST_HEAD(rxrpc_transports);
 static DEFINE_RWLOCK(rxrpc_transport_lock);
-static unsigned long rxrpc_transport_timeout = 3600 * 24;
 static DECLARE_DELAYED_WORK(rxrpc_transport_reap, rxrpc_transport_reaper);
 
 /*
@@ -235,7 +239,7 @@ static void rxrpc_transport_reaper(struct work_struct *work)
 		if (likely(atomic_read(&trans->usage) > 0))
 			continue;
 
-		reap_time = trans->put_time + rxrpc_transport_timeout;
+		reap_time = trans->put_time + rxrpc_transport_expiry;
 		if (reap_time <= now)
 			list_move_tail(&trans->link, &graveyard);
 		else if (reap_time < earliest)
@@ -271,7 +275,7 @@ void __exit rxrpc_destroy_all_transports(void)
 {
 	_enter("");
 
-	rxrpc_transport_timeout = 0;
+	rxrpc_transport_expiry = 0;
 	cancel_delayed_work(&rxrpc_transport_reap);
 	rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0);
 
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
new file mode 100644
index 00000000000..50a98a910eb
--- /dev/null
+++ b/net/rxrpc/sysctl.c
@@ -0,0 +1,146 @@
+/* sysctls for configuring RxRPC operating parameters
+ *
+ * Copyright (C) 2014 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/sysctl.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+static struct ctl_table_header *rxrpc_sysctl_reg_table;
+static const unsigned zero = 0;
+static const unsigned one = 1;
+static const unsigned four = 4;
+static const unsigned n_65535 = 65535;
+static const unsigned n_max_acks = RXRPC_MAXACKS;
+
+/*
+ * RxRPC operating parameters.
+ *
+ * See Documentation/networking/rxrpc.txt and the variable definitions for more
+ * information on the individual parameters.
+ */
+static struct ctl_table rxrpc_sysctl_table[] = {
+	/* Values measured in milliseconds */
+	{
+		.procname	= "req_ack_delay",
+		.data		= &rxrpc_requested_ack_delay,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+		.extra1		= (void *)&zero,
+	},
+	{
+		.procname	= "soft_ack_delay",
+		.data		= &rxrpc_soft_ack_delay,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+		.extra1		= (void *)&one,
+	},
+	{
+		.procname	= "idle_ack_delay",
+		.data		= &rxrpc_idle_ack_delay,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+		.extra1		= (void *)&one,
+	},
+	{
+		.procname	= "resend_timeout",
+		.data		= &rxrpc_resend_timeout,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+		.extra1		= (void *)&one,
+	},
+
+	/* Values measured in seconds but used in jiffies */
+	{
+		.procname	= "max_call_lifetime",
+		.data		= &rxrpc_max_call_lifetime,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+		.extra1		= (void *)&one,
+	},
+	{
+		.procname	= "dead_call_expiry",
+		.data		= &rxrpc_dead_call_expiry,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+		.extra1		= (void *)&one,
+	},
+
+	/* Values measured in seconds */
+	{
+		.procname	= "connection_expiry",
+		.data		= &rxrpc_connection_expiry,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&one,
+	},
+	{
+		.procname	= "transport_expiry",
+		.data		= &rxrpc_transport_expiry,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&one,
+	},
+
+	/* Non-time values */
+	{
+		.procname	= "rx_window_size",
+		.data		= &rxrpc_rx_window_size,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&one,
+		.extra2		= (void *)&n_max_acks,
+	},
+	{
+		.procname	= "rx_mtu",
+		.data		= &rxrpc_rx_mtu,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&one,
+		.extra1		= (void *)&n_65535,
+	},
+	{
+		.procname	= "rx_jumbo_max",
+		.data		= &rxrpc_rx_jumbo_max,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&one,
+		.extra2		= (void *)&four,
+	},
+
+	{ }
+};
+
+int __init rxrpc_sysctl_init(void)
+{
+	rxrpc_sysctl_reg_table = register_net_sysctl(&init_net, "net/rxrpc",
+						     rxrpc_sysctl_table);
+	if (!rxrpc_sysctl_reg_table)
+		return -ENOMEM;
+	return 0;
+}
+
+void rxrpc_sysctl_exit(void)
+{
+	if (rxrpc_sysctl_reg_table)
+		unregister_net_sysctl_table(rxrpc_sysctl_reg_table);
+}
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index ad1f1d81920..a1a8e29e5fc 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -286,6 +286,28 @@ config NET_SCH_FQ
 
 	  If unsure, say N.
 
+config NET_SCH_HHF
+	tristate "Heavy-Hitter Filter (HHF)"
+	help
+	  Say Y here if you want to use the Heavy-Hitter Filter (HHF)
+	  packet scheduling algorithm.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sch_hhf.
+
+config NET_SCH_PIE
+	tristate "Proportional Integral controller Enhanced (PIE) scheduler"
+	help
+	  Say Y here if you want to use the Proportional Integral controller
+	  Enhanced scheduler packet scheduling algorithm.
+	  For more information, please see
+	  http://tools.ietf.org/html/draft-pan-tsvwg-pie-00
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sch_pie.
+
+	  If unsure, say N.
+
 config NET_SCH_INGRESS
 	tristate "Ingress Qdisc"
 	depends on NET_CLS_ACT
@@ -435,6 +457,7 @@ config NET_CLS_FLOW
 config NET_CLS_CGROUP
 	tristate "Control Group Classifier"
 	select NET_CLS
+	select CGROUP_NET_CLASSID
 	depends on CGROUPS
 	---help---
 	  Say Y here if you want to classify packets based on the control
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 35fa47a494a..0a869a11f3e 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -40,6 +40,8 @@ obj-$(CONFIG_NET_SCH_QFQ)	+= sch_qfq.o
 obj-$(CONFIG_NET_SCH_CODEL)	+= sch_codel.o
 obj-$(CONFIG_NET_SCH_FQ_CODEL)	+= sch_fq_codel.o
 obj-$(CONFIG_NET_SCH_FQ)	+= sch_fq.o
+obj-$(CONFIG_NET_SCH_HHF)	+= sch_hhf.o
+obj-$(CONFIG_NET_SCH_PIE)	+= sch_pie.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 69cb848e834..648778aef1a 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -27,42 +27,40 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 
-void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo)
+void tcf_hash_destroy(struct tc_action *a)
 {
-	unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask);
-	struct tcf_common **p1p;
-
-	for (p1p = &hinfo->htab[h]; *p1p; p1p = &(*p1p)->tcfc_next) {
-		if (*p1p == p) {
-			write_lock_bh(hinfo->lock);
-			*p1p = p->tcfc_next;
-			write_unlock_bh(hinfo->lock);
-			gen_kill_estimator(&p->tcfc_bstats,
-					   &p->tcfc_rate_est);
-			/*
-			 * gen_estimator est_timer() might access p->tcfc_lock
-			 * or bstats, wait a RCU grace period before freeing p
-			 */
-			kfree_rcu(p, tcfc_rcu);
-			return;
-		}
-	}
-	WARN_ON(1);
+	struct tcf_common *p = a->priv;
+	struct tcf_hashinfo *hinfo = a->ops->hinfo;
+
+	spin_lock_bh(&hinfo->lock);
+	hlist_del(&p->tcfc_head);
+	spin_unlock_bh(&hinfo->lock);
+	gen_kill_estimator(&p->tcfc_bstats,
+			   &p->tcfc_rate_est);
+	/*
+	 * gen_estimator est_timer() might access p->tcfc_lock
+	 * or bstats, wait a RCU grace period before freeing p
+	 */
+	kfree_rcu(p, tcfc_rcu);
 }
 EXPORT_SYMBOL(tcf_hash_destroy);
 
-int tcf_hash_release(struct tcf_common *p, int bind,
-		     struct tcf_hashinfo *hinfo)
+int tcf_hash_release(struct tc_action *a, int bind)
 {
+	struct tcf_common *p = a->priv;
 	int ret = 0;
 
 	if (p) {
 		if (bind)
 			p->tcfc_bindcnt--;
+		else if (p->tcfc_bindcnt > 0)
+			return -EPERM;
 
 		p->tcfc_refcnt--;
 		if (p->tcfc_bindcnt <= 0 && p->tcfc_refcnt <= 0) {
-			tcf_hash_destroy(p, hinfo);
+			if (a->ops->cleanup)
+				a->ops->cleanup(a, bind);
+			tcf_hash_destroy(a);
 			ret = 1;
 		}
 	}
@@ -71,20 +69,22 @@ int tcf_hash_release(struct tcf_common *p, int bind,
 EXPORT_SYMBOL(tcf_hash_release);
 
 static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
-			   struct tc_action *a, struct tcf_hashinfo *hinfo)
+			   struct tc_action *a)
 {
+	struct tcf_hashinfo *hinfo = a->ops->hinfo;
+	struct hlist_head *head;
 	struct tcf_common *p;
 	int err = 0, index = -1, i = 0, s_i = 0, n_i = 0;
 	struct nlattr *nest;
 
-	read_lock_bh(hinfo->lock);
+	spin_lock_bh(&hinfo->lock);
 
 	s_i = cb->args[0];
 
 	for (i = 0; i < (hinfo->hmask + 1); i++) {
-		p = hinfo->htab[tcf_hash(i, hinfo->hmask)];
+		head = &hinfo->htab[tcf_hash(i, hinfo->hmask)];
 
-		for (; p; p = p->tcfc_next) {
+		hlist_for_each_entry_rcu(p, head, tcfc_head) {
 			index++;
 			if (index < s_i)
 				continue;
@@ -107,7 +107,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
 		}
 	}
 done:
-	read_unlock_bh(hinfo->lock);
+	spin_unlock_bh(&hinfo->lock);
 	if (n_i)
 		cb->args[0] += n_i;
 	return n_i;
@@ -117,12 +117,15 @@ nla_put_failure:
 	goto done;
 }
 
-static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a,
-			  struct tcf_hashinfo *hinfo)
+static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a)
 {
-	struct tcf_common *p, *s_p;
+	struct tcf_hashinfo *hinfo = a->ops->hinfo;
+	struct hlist_head *head;
+	struct hlist_node *n;
+	struct tcf_common *p;
 	struct nlattr *nest;
 	int i = 0, n_i = 0;
+	int ret = -EINVAL;
 
 	nest = nla_nest_start(skb, a->order);
 	if (nest == NULL)
@@ -130,14 +133,15 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a,
 	if (nla_put_string(skb, TCA_KIND, a->ops->kind))
 		goto nla_put_failure;
 	for (i = 0; i < (hinfo->hmask + 1); i++) {
-		p = hinfo->htab[tcf_hash(i, hinfo->hmask)];
-
-		while (p != NULL) {
-			s_p = p->tcfc_next;
-			if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo))
+		head = &hinfo->htab[tcf_hash(i, hinfo->hmask)];
+		hlist_for_each_entry_safe(p, n, head, tcfc_head) {
+			a->priv = p;
+			ret = tcf_hash_release(a, 0);
+			if (ret == ACT_P_DELETED) {
 				module_put(a->ops->owner);
-			n_i++;
-			p = s_p;
+				n_i++;
+			} else if (ret < 0)
+				goto nla_put_failure;
 		}
 	}
 	if (nla_put_u32(skb, TCA_FCNT, n_i))
@@ -147,51 +151,48 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a,
 	return n_i;
 nla_put_failure:
 	nla_nest_cancel(skb, nest);
-	return -EINVAL;
+	return ret;
 }
 
-int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb,
-		       int type, struct tc_action *a)
+static int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb,
+			      int type, struct tc_action *a)
 {
-	struct tcf_hashinfo *hinfo = a->ops->hinfo;
-
 	if (type == RTM_DELACTION) {
-		return tcf_del_walker(skb, a, hinfo);
+		return tcf_del_walker(skb, a);
 	} else if (type == RTM_GETACTION) {
-		return tcf_dump_walker(skb, cb, a, hinfo);
+		return tcf_dump_walker(skb, cb, a);
 	} else {
 		WARN(1, "tcf_generic_walker: unknown action %d\n", type);
 		return -EINVAL;
 	}
 }
-EXPORT_SYMBOL(tcf_generic_walker);
 
-struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo)
+static struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo)
 {
-	struct tcf_common *p;
+	struct tcf_common *p = NULL;
+	struct hlist_head *head;
 
-	read_lock_bh(hinfo->lock);
-	for (p = hinfo->htab[tcf_hash(index, hinfo->hmask)]; p;
-	     p = p->tcfc_next) {
+	spin_lock_bh(&hinfo->lock);
+	head = &hinfo->htab[tcf_hash(index, hinfo->hmask)];
+	hlist_for_each_entry_rcu(p, head, tcfc_head)
 		if (p->tcfc_index == index)
 			break;
-	}
-	read_unlock_bh(hinfo->lock);
+	spin_unlock_bh(&hinfo->lock);
 
 	return p;
 }
-EXPORT_SYMBOL(tcf_hash_lookup);
 
-u32 tcf_hash_new_index(u32 *idx_gen, struct tcf_hashinfo *hinfo)
+u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo)
 {
-	u32 val = *idx_gen;
+	u32 val = hinfo->index;
 
 	do {
 		if (++val == 0)
 			val = 1;
 	} while (tcf_hash_lookup(val, hinfo));
 
-	return (*idx_gen = val);
+	hinfo->index = val;
+	return val;
 }
 EXPORT_SYMBOL(tcf_hash_new_index);
 
@@ -208,34 +209,46 @@ int tcf_hash_search(struct tc_action *a, u32 index)
 }
 EXPORT_SYMBOL(tcf_hash_search);
 
-struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind,
-				  struct tcf_hashinfo *hinfo)
+int tcf_hash_check(u32 index, struct tc_action *a, int bind)
 {
+	struct tcf_hashinfo *hinfo = a->ops->hinfo;
 	struct tcf_common *p = NULL;
 	if (index && (p = tcf_hash_lookup(index, hinfo)) != NULL) {
 		if (bind)
 			p->tcfc_bindcnt++;
 		p->tcfc_refcnt++;
 		a->priv = p;
+		return 1;
 	}
-	return p;
+	return 0;
 }
 EXPORT_SYMBOL(tcf_hash_check);
 
-struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est,
-				   struct tc_action *a, int size, int bind,
-				   u32 *idx_gen, struct tcf_hashinfo *hinfo)
+void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est)
 {
+	struct tcf_common *pc = a->priv;
+	if (est)
+		gen_kill_estimator(&pc->tcfc_bstats,
+				   &pc->tcfc_rate_est);
+	kfree_rcu(pc, tcfc_rcu);
+}
+EXPORT_SYMBOL(tcf_hash_cleanup);
+
+int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
+		    int size, int bind)
+{
+	struct tcf_hashinfo *hinfo = a->ops->hinfo;
 	struct tcf_common *p = kzalloc(size, GFP_KERNEL);
 
 	if (unlikely(!p))
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 	p->tcfc_refcnt = 1;
 	if (bind)
 		p->tcfc_bindcnt = 1;
 
 	spin_lock_init(&p->tcfc_lock);
-	p->tcfc_index = index ? index : tcf_hash_new_index(idx_gen, hinfo);
+	INIT_HLIST_NODE(&p->tcfc_head);
+	p->tcfc_index = index ? index : tcf_hash_new_index(hinfo);
 	p->tcfc_tm.install = jiffies;
 	p->tcfc_tm.lastuse = jiffies;
 	if (est) {
@@ -243,35 +256,37 @@ struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est,
 					    &p->tcfc_lock, est);
 		if (err) {
 			kfree(p);
-			return ERR_PTR(err);
+			return err;
 		}
 	}
 
 	a->priv = (void *) p;
-	return p;
+	return 0;
 }
 EXPORT_SYMBOL(tcf_hash_create);
 
-void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo)
+void tcf_hash_insert(struct tc_action *a)
 {
+	struct tcf_common *p = a->priv;
+	struct tcf_hashinfo *hinfo = a->ops->hinfo;
 	unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask);
 
-	write_lock_bh(hinfo->lock);
-	p->tcfc_next = hinfo->htab[h];
-	hinfo->htab[h] = p;
-	write_unlock_bh(hinfo->lock);
+	spin_lock_bh(&hinfo->lock);
+	hlist_add_head(&p->tcfc_head, &hinfo->htab[h]);
+	spin_unlock_bh(&hinfo->lock);
 }
 EXPORT_SYMBOL(tcf_hash_insert);
 
-static struct tc_action_ops *act_base = NULL;
+static LIST_HEAD(act_base);
 static DEFINE_RWLOCK(act_mod_lock);
 
-int tcf_register_action(struct tc_action_ops *act)
+int tcf_register_action(struct tc_action_ops *act, unsigned int mask)
 {
-	struct tc_action_ops *a, **ap;
+	struct tc_action_ops *a;
+	int err;
 
-	/* Must supply act, dump, cleanup and init */
-	if (!act->act || !act->dump || !act->cleanup || !act->init)
+	/* Must supply act, dump and init */
+	if (!act->act || !act->dump || !act->init)
 		return -EINVAL;
 
 	/* Supply defaults */
@@ -280,15 +295,25 @@ int tcf_register_action(struct tc_action_ops *act)
 	if (!act->walk)
 		act->walk = tcf_generic_walker;
 
+	act->hinfo = kmalloc(sizeof(struct tcf_hashinfo), GFP_KERNEL);
+	if (!act->hinfo)
+		return -ENOMEM;
+	err = tcf_hashinfo_init(act->hinfo, mask);
+	if (err) {
+		kfree(act->hinfo);
+		return err;
+	}
+
 	write_lock(&act_mod_lock);
-	for (ap = &act_base; (a = *ap) != NULL; ap = &a->next) {
+	list_for_each_entry(a, &act_base, head) {
 		if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) {
 			write_unlock(&act_mod_lock);
+			tcf_hashinfo_destroy(act->hinfo);
+			kfree(act->hinfo);
 			return -EEXIST;
 		}
 	}
-	act->next = NULL;
-	*ap = act;
+	list_add_tail(&act->head, &act_base);
 	write_unlock(&act_mod_lock);
 	return 0;
 }
@@ -296,17 +321,18 @@ EXPORT_SYMBOL(tcf_register_action);
 
 int tcf_unregister_action(struct tc_action_ops *act)
 {
-	struct tc_action_ops *a, **ap;
+	struct tc_action_ops *a;
 	int err = -ENOENT;
 
 	write_lock(&act_mod_lock);
-	for (ap = &act_base; (a = *ap) != NULL; ap = &a->next)
-		if (a == act)
+	list_for_each_entry(a, &act_base, head) {
+		if (a == act) {
+			list_del(&act->head);
+			tcf_hashinfo_destroy(act->hinfo);
+			kfree(act->hinfo);
+			err = 0;
 			break;
-	if (a) {
-		*ap = a->next;
-		a->next = NULL;
-		err = 0;
+		}
 	}
 	write_unlock(&act_mod_lock);
 	return err;
@@ -316,69 +342,42 @@ EXPORT_SYMBOL(tcf_unregister_action);
 /* lookup by name */
 static struct tc_action_ops *tc_lookup_action_n(char *kind)
 {
-	struct tc_action_ops *a = NULL;
+	struct tc_action_ops *a, *res = NULL;
 
 	if (kind) {
 		read_lock(&act_mod_lock);
-		for (a = act_base; a; a = a->next) {
+		list_for_each_entry(a, &act_base, head) {
 			if (strcmp(kind, a->kind) == 0) {
-				if (!try_module_get(a->owner)) {
-					read_unlock(&act_mod_lock);
-					return NULL;
-				}
+				if (try_module_get(a->owner))
+					res = a;
 				break;
 			}
 		}
 		read_unlock(&act_mod_lock);
 	}
-	return a;
+	return res;
 }
 
 /* lookup by nlattr */
 static struct tc_action_ops *tc_lookup_action(struct nlattr *kind)
 {
-	struct tc_action_ops *a = NULL;
+	struct tc_action_ops *a, *res = NULL;
 
 	if (kind) {
 		read_lock(&act_mod_lock);
-		for (a = act_base; a; a = a->next) {
+		list_for_each_entry(a, &act_base, head) {
 			if (nla_strcmp(kind, a->kind) == 0) {
-				if (!try_module_get(a->owner)) {
-					read_unlock(&act_mod_lock);
-					return NULL;
-				}
-				break;
-			}
-		}
-		read_unlock(&act_mod_lock);
-	}
-	return a;
-}
-
-#if 0
-/* lookup by id */
-static struct tc_action_ops *tc_lookup_action_id(u32 type)
-{
-	struct tc_action_ops *a = NULL;
-
-	if (type) {
-		read_lock(&act_mod_lock);
-		for (a = act_base; a; a = a->next) {
-			if (a->type == type) {
-				if (!try_module_get(a->owner)) {
-					read_unlock(&act_mod_lock);
-					return NULL;
-				}
+				if (try_module_get(a->owner))
+					res = a;
 				break;
 			}
 		}
 		read_unlock(&act_mod_lock);
 	}
-	return a;
+	return res;
 }
-#endif
 
-int tcf_action_exec(struct sk_buff *skb, const struct tc_action *act,
+int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions,
 		    struct tcf_result *res)
 {
 	const struct tc_action *a;
@@ -389,53 +388,44 @@ int tcf_action_exec(struct sk_buff *skb, const struct tc_action *act,
 		ret = TC_ACT_OK;
 		goto exec_done;
 	}
-	while ((a = act) != NULL) {
+	list_for_each_entry(a, actions, list) {
 repeat:
-		if (a->ops) {
-			ret = a->ops->act(skb, a, res);
-			if (TC_MUNGED & skb->tc_verd) {
-				/* copied already, allow trampling */
-				skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
-				skb->tc_verd = CLR_TC_MUNGED(skb->tc_verd);
-			}
-			if (ret == TC_ACT_REPEAT)
-				goto repeat;	/* we need a ttl - JHS */
-			if (ret != TC_ACT_PIPE)
-				goto exec_done;
+		ret = a->ops->act(skb, a, res);
+		if (TC_MUNGED & skb->tc_verd) {
+			/* copied already, allow trampling */
+			skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
+			skb->tc_verd = CLR_TC_MUNGED(skb->tc_verd);
 		}
-		act = a->next;
+		if (ret == TC_ACT_REPEAT)
+			goto repeat;	/* we need a ttl - JHS */
+		if (ret != TC_ACT_PIPE)
+			goto exec_done;
 	}
 exec_done:
 	return ret;
 }
 EXPORT_SYMBOL(tcf_action_exec);
 
-void tcf_action_destroy(struct tc_action *act, int bind)
+int tcf_action_destroy(struct list_head *actions, int bind)
 {
-	struct tc_action *a;
+	struct tc_action *a, *tmp;
+	int ret = 0;
 
-	for (a = act; a; a = act) {
-		if (a->ops) {
-			if (a->ops->cleanup(a, bind) == ACT_P_DELETED)
-				module_put(a->ops->owner);
-			act = act->next;
-			kfree(a);
-		} else {
-			/*FIXME: Remove later - catch insertion bugs*/
-			WARN(1, "tcf_action_destroy: BUG? destroying NULL ops\n");
-			act = act->next;
-			kfree(a);
-		}
+	list_for_each_entry_safe(a, tmp, actions, list) {
+		ret = tcf_hash_release(a, bind);
+		if (ret == ACT_P_DELETED)
+			module_put(a->ops->owner);
+		else if (ret < 0)
+			return ret;
+		list_del(&a->list);
+		kfree(a);
 	}
+	return ret;
 }
 
 int
 tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 {
-	int err = -EINVAL;
-
-	if (a->ops == NULL)
-		return err;
 	return a->ops->dump(skb, a, bind, ref);
 }
 
@@ -446,9 +436,6 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 
-	if (a->ops == NULL)
-		return err;
-
 	if (nla_put_string(skb, TCA_KIND, a->ops->kind))
 		goto nla_put_failure;
 	if (tcf_action_copy_stats(skb, a, 0))
@@ -469,14 +456,13 @@ nla_put_failure:
 EXPORT_SYMBOL(tcf_action_dump_1);
 
 int
-tcf_action_dump(struct sk_buff *skb, struct tc_action *act, int bind, int ref)
+tcf_action_dump(struct sk_buff *skb, struct list_head *actions, int bind, int ref)
 {
 	struct tc_action *a;
 	int err = -EINVAL;
 	struct nlattr *nest;
 
-	while ((a = act) != NULL) {
-		act = a->next;
+	list_for_each_entry(a, actions, list) {
 		nest = nla_nest_start(skb, a->order);
 		if (nest == NULL)
 			goto nla_put_failure;
@@ -551,6 +537,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
 	if (a == NULL)
 		goto err_mod;
 
+	a->ops = a_o;
+	INIT_LIST_HEAD(&a->list);
 	/* backward compatibility for policer */
 	if (name == NULL)
 		err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, a, ovr, bind);
@@ -565,7 +553,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
 	 */
 	if (err != ACT_P_CREATED)
 		module_put(a_o->owner);
-	a->ops = a_o;
 
 	return a;
 
@@ -577,37 +564,33 @@ err_out:
 	return ERR_PTR(err);
 }
 
-struct tc_action *tcf_action_init(struct net *net, struct nlattr *nla,
+int tcf_action_init(struct net *net, struct nlattr *nla,
 				  struct nlattr *est, char *name, int ovr,
-				  int bind)
+				  int bind, struct list_head *actions)
 {
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
-	struct tc_action *head = NULL, *act, *act_prev = NULL;
+	struct tc_action *act;
 	int err;
 	int i;
 
 	err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL);
 	if (err < 0)
-		return ERR_PTR(err);
+		return err;
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
 		act = tcf_action_init_1(net, tb[i], est, name, ovr, bind);
-		if (IS_ERR(act))
+		if (IS_ERR(act)) {
+			err = PTR_ERR(act);
 			goto err;
+		}
 		act->order = i;
-
-		if (head == NULL)
-			head = act;
-		else
-			act_prev->next = act;
-		act_prev = act;
+		list_add_tail(&act->list, actions);
 	}
-	return head;
+	return 0;
 
 err:
-	if (head != NULL)
-		tcf_action_destroy(head, bind);
-	return act;
+	tcf_action_destroy(actions, bind);
+	return err;
 }
 
 int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
@@ -615,9 +598,9 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
 {
 	int err = 0;
 	struct gnet_dump d;
-	struct tcf_act_hdr *h = a->priv;
+	struct tcf_common *p = a->priv;
 
-	if (h == NULL)
+	if (p == NULL)
 		goto errout;
 
 	/* compat_mode being true specifies a call that is supposed
@@ -626,24 +609,20 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
 	if (compat_mode) {
 		if (a->type == TCA_OLD_COMPAT)
 			err = gnet_stats_start_copy_compat(skb, 0,
-				TCA_STATS, TCA_XSTATS, &h->tcf_lock, &d);
+				TCA_STATS, TCA_XSTATS, &p->tcfc_lock, &d);
 		else
 			return 0;
 	} else
 		err = gnet_stats_start_copy(skb, TCA_ACT_STATS,
-					    &h->tcf_lock, &d);
+					    &p->tcfc_lock, &d);
 
 	if (err < 0)
 		goto errout;
 
-	if (a->ops != NULL && a->ops->get_stats != NULL)
-		if (a->ops->get_stats(skb, a) < 0)
-			goto errout;
-
-	if (gnet_stats_copy_basic(&d, &h->tcf_bstats) < 0 ||
-	    gnet_stats_copy_rate_est(&d, &h->tcf_bstats,
-				     &h->tcf_rate_est) < 0 ||
-	    gnet_stats_copy_queue(&d, &h->tcf_qstats) < 0)
+	if (gnet_stats_copy_basic(&d, &p->tcfc_bstats) < 0 ||
+	    gnet_stats_copy_rate_est(&d, &p->tcfc_bstats,
+				     &p->tcfc_rate_est) < 0 ||
+	    gnet_stats_copy_queue(&d, &p->tcfc_qstats) < 0)
 		goto errout;
 
 	if (gnet_stats_finish_copy(&d) < 0)
@@ -656,7 +635,7 @@ errout:
 }
 
 static int
-tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 portid, u32 seq,
+tca_get_fill(struct sk_buff *skb, struct list_head *actions, u32 portid, u32 seq,
 	     u16 flags, int event, int bind, int ref)
 {
 	struct tcamsg *t;
@@ -676,7 +655,7 @@ tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 portid, u32 seq,
 	if (nest == NULL)
 		goto out_nlmsg_trim;
 
-	if (tcf_action_dump(skb, a, bind, ref) < 0)
+	if (tcf_action_dump(skb, actions, bind, ref) < 0)
 		goto out_nlmsg_trim;
 
 	nla_nest_end(skb, nest);
@@ -691,14 +670,14 @@ out_nlmsg_trim:
 
 static int
 act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
-	       struct tc_action *a, int event)
+	       struct list_head *actions, int event)
 {
 	struct sk_buff *skb;
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
-	if (tca_get_fill(skb, a, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) {
+	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
@@ -706,6 +685,20 @@ act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
 	return rtnl_unicast(skb, net, portid);
 }
 
+static struct tc_action *create_a(int i)
+{
+	struct tc_action *act;
+
+	act = kzalloc(sizeof(*act), GFP_KERNEL);
+	if (act == NULL) {
+		pr_debug("create_a: failed to alloc!\n");
+		return NULL;
+	}
+	act->order = i;
+	INIT_LIST_HEAD(&act->list);
+	return act;
+}
+
 static struct tc_action *
 tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid)
 {
@@ -725,13 +718,13 @@ tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid)
 	index = nla_get_u32(tb[TCA_ACT_INDEX]);
 
 	err = -ENOMEM;
-	a = kzalloc(sizeof(struct tc_action), GFP_KERNEL);
+	a = create_a(0);
 	if (a == NULL)
 		goto err_out;
 
 	err = -EINVAL;
 	a->ops = tc_lookup_action(tb[TCA_ACT_KIND]);
-	if (a->ops == NULL)
+	if (a->ops == NULL) /* could happen in batch of actions */
 		goto err_free;
 	err = -ENOENT;
 	if (a->ops->lookup(a, index) == 0)
@@ -748,29 +741,16 @@ err_out:
 	return ERR_PTR(err);
 }
 
-static void cleanup_a(struct tc_action *act)
+static void cleanup_a(struct list_head *actions)
 {
-	struct tc_action *a;
+	struct tc_action *a, *tmp;
 
-	for (a = act; a; a = act) {
-		act = a->next;
+	list_for_each_entry_safe(a, tmp, actions, list) {
+		list_del(&a->list);
 		kfree(a);
 	}
 }
 
-static struct tc_action *create_a(int i)
-{
-	struct tc_action *act;
-
-	act = kzalloc(sizeof(*act), GFP_KERNEL);
-	if (act == NULL) {
-		pr_debug("create_a: failed to alloc!\n");
-		return NULL;
-	}
-	act->order = i;
-	return act;
-}
-
 static int tca_action_flush(struct net *net, struct nlattr *nla,
 			    struct nlmsghdr *n, u32 portid)
 {
@@ -782,18 +762,12 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 	struct nlattr *nest;
 	struct nlattr *tb[TCA_ACT_MAX + 1];
 	struct nlattr *kind;
-	struct tc_action *a = create_a(0);
+	struct tc_action a;
 	int err = -ENOMEM;
 
-	if (a == NULL) {
-		pr_debug("tca_action_flush: couldnt create tc_action\n");
-		return err;
-	}
-
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb) {
 		pr_debug("tca_action_flush: failed skb alloc\n");
-		kfree(a);
 		return err;
 	}
 
@@ -805,8 +779,10 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 
 	err = -EINVAL;
 	kind = tb[TCA_ACT_KIND];
-	a->ops = tc_lookup_action(kind);
-	if (a->ops == NULL)
+	memset(&a, 0, sizeof(struct tc_action));
+	INIT_LIST_HEAD(&a.list);
+	a.ops = tc_lookup_action(kind);
+	if (a.ops == NULL) /*some idjot trying to flush unknown action */
 		goto err_out;
 
 	nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0);
@@ -821,7 +797,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 	if (nest == NULL)
 		goto out_module_put;
 
-	err = a->ops->walk(skb, &dcb, RTM_DELACTION, a);
+	err = a.ops->walk(skb, &dcb, RTM_DELACTION, &a);
 	if (err < 0)
 		goto out_module_put;
 	if (err == 0)
@@ -831,8 +807,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
 	nlh->nlmsg_flags |= NLM_F_ROOT;
-	module_put(a->ops->owner);
-	kfree(a);
+	module_put(a.ops->owner);
 	err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
 			     n->nlmsg_flags & NLM_F_ECHO);
 	if (err > 0)
@@ -841,21 +816,52 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 	return err;
 
 out_module_put:
-	module_put(a->ops->owner);
+	module_put(a.ops->owner);
 err_out:
 noflush_out:
 	kfree_skb(skb);
-	kfree(a);
 	return err;
 }
 
 static int
+tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
+	       u32 portid)
+{
+	int ret;
+	struct sk_buff *skb;
+
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION,
+			 0, 1) <= 0) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	/* now do the delete */
+	ret = tcf_action_destroy(actions, 0);
+	if (ret < 0) {
+		kfree_skb(skb);
+		return ret;
+	}
+
+	ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
+			     n->nlmsg_flags & NLM_F_ECHO);
+	if (ret > 0)
+		return 0;
+	return ret;
+}
+
+static int
 tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	      u32 portid, int event)
 {
 	int i, ret;
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
-	struct tc_action *head = NULL, *act, *act_prev = NULL;
+	struct tc_action *act;
+	LIST_HEAD(actions);
 
 	ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL);
 	if (ret < 0)
@@ -875,117 +881,62 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 			goto err;
 		}
 		act->order = i;
-
-		if (head == NULL)
-			head = act;
-		else
-			act_prev->next = act;
-		act_prev = act;
+		list_add_tail(&act->list, &actions);
 	}
 
 	if (event == RTM_GETACTION)
-		ret = act_get_notify(net, portid, n, head, event);
+		ret = act_get_notify(net, portid, n, &actions, event);
 	else { /* delete */
-		struct sk_buff *skb;
-
-		skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-		if (!skb) {
-			ret = -ENOBUFS;
-			goto err;
-		}
-
-		if (tca_get_fill(skb, head, portid, n->nlmsg_seq, 0, event,
-				 0, 1) <= 0) {
-			kfree_skb(skb);
-			ret = -EINVAL;
+		ret = tcf_del_notify(net, n, &actions, portid);
+		if (ret)
 			goto err;
-		}
-
-		/* now do the delete */
-		tcf_action_destroy(head, 0);
-		ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
-				     n->nlmsg_flags & NLM_F_ECHO);
-		if (ret > 0)
-			return 0;
 		return ret;
 	}
 err:
-	cleanup_a(head);
+	cleanup_a(&actions);
 	return ret;
 }
 
-static int tcf_add_notify(struct net *net, struct tc_action *a,
-			  u32 portid, u32 seq, int event, u16 flags)
+static int
+tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
+	       u32 portid)
 {
-	struct tcamsg *t;
-	struct nlmsghdr *nlh;
 	struct sk_buff *skb;
-	struct nlattr *nest;
-	unsigned char *b;
 	int err = 0;
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
 
-	b = skb_tail_pointer(skb);
-
-	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*t), flags);
-	if (!nlh)
-		goto out_kfree_skb;
-	t = nlmsg_data(nlh);
-	t->tca_family = AF_UNSPEC;
-	t->tca__pad1 = 0;
-	t->tca__pad2 = 0;
-
-	nest = nla_nest_start(skb, TCA_ACT_TAB);
-	if (nest == NULL)
-		goto out_kfree_skb;
-
-	if (tcf_action_dump(skb, a, 0, 0) < 0)
-		goto out_kfree_skb;
-
-	nla_nest_end(skb, nest);
-
-	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
-	NETLINK_CB(skb).dst_group = RTNLGRP_TC;
+	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags,
+			 RTM_NEWACTION, 0, 0) <= 0) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
 
-	err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO);
+	err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
+			     n->nlmsg_flags & NLM_F_ECHO);
 	if (err > 0)
 		err = 0;
 	return err;
-
-out_kfree_skb:
-	kfree_skb(skb);
-	return -1;
 }
 
-
 static int
 tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	       u32 portid, int ovr)
 {
 	int ret = 0;
-	struct tc_action *act;
-	struct tc_action *a;
-	u32 seq = n->nlmsg_seq;
+	LIST_HEAD(actions);
 
-	act = tcf_action_init(net, nla, NULL, NULL, ovr, 0);
-	if (act == NULL)
-		goto done;
-	if (IS_ERR(act)) {
-		ret = PTR_ERR(act);
+	ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions);
+	if (ret)
 		goto done;
-	}
 
 	/* dump then free all the actions after update; inserted policy
 	 * stays intact
 	 */
-	ret = tcf_add_notify(net, act, portid, seq, RTM_NEWACTION, n->nlmsg_flags);
-	for (a = act; a; a = act) {
-		act = a->next;
-		kfree(a);
-	}
+	ret = tcf_add_notify(net, n, &actions, portid);
+	cleanup_a(&actions);
 done:
 	return ret;
 }
@@ -997,7 +948,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n)
 	u32 portid = skb ? NETLINK_CB(skb).portid : 0;
 	int ret = 0, ovr = 0;
 
-	if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 5c5edf56adb..edbf40dac70 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -37,15 +37,6 @@
 #include <net/tc_act/tc_csum.h>
 
 #define CSUM_TAB_MASK 15
-static struct tcf_common *tcf_csum_ht[CSUM_TAB_MASK + 1];
-static u32 csum_idx_gen;
-static DEFINE_RWLOCK(csum_lock);
-
-static struct tcf_hashinfo csum_hash_info = {
-	.htab	= tcf_csum_ht,
-	.hmask	= CSUM_TAB_MASK,
-	.lock	= &csum_lock,
-};
 
 static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = {
 	[TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), },
@@ -56,7 +47,6 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est,
 {
 	struct nlattr *tb[TCA_CSUM_MAX + 1];
 	struct tc_csum *parm;
-	struct tcf_common *pc;
 	struct tcf_csum *p;
 	int ret = 0, err;
 
@@ -71,39 +61,31 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est,
 		return -EINVAL;
 	parm = nla_data(tb[TCA_CSUM_PARMS]);
 
-	pc = tcf_hash_check(parm->index, a, bind, &csum_hash_info);
-	if (!pc) {
-		pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind,
-				     &csum_idx_gen, &csum_hash_info);
-		if (IS_ERR(pc))
-			return PTR_ERR(pc);
-		p = to_tcf_csum(pc);
+	if (!tcf_hash_check(parm->index, a, bind)) {
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+		if (ret)
+			return ret;
 		ret = ACT_P_CREATED;
 	} else {
-		p = to_tcf_csum(pc);
-		if (!ovr) {
-			tcf_hash_release(pc, bind, &csum_hash_info);
+		if (bind)/* dont override defaults */
+			return 0;
+		tcf_hash_release(a, bind);
+		if (!ovr)
 			return -EEXIST;
-		}
 	}
 
+	p = to_tcf_csum(a);
 	spin_lock_bh(&p->tcf_lock);
 	p->tcf_action = parm->action;
 	p->update_flags = parm->update_flags;
 	spin_unlock_bh(&p->tcf_lock);
 
 	if (ret == ACT_P_CREATED)
-		tcf_hash_insert(pc, &csum_hash_info);
+		tcf_hash_insert(a);
 
 	return ret;
 }
 
-static int tcf_csum_cleanup(struct tc_action *a, int bind)
-{
-	struct tcf_csum *p = a->priv;
-	return tcf_hash_release(&p->common, bind, &csum_hash_info);
-}
-
 /**
  * tcf_csum_skb_nextlayer - Get next layer pointer
  * @skb: sk_buff to use
@@ -578,13 +560,10 @@ nla_put_failure:
 
 static struct tc_action_ops act_csum_ops = {
 	.kind		= "csum",
-	.hinfo		= &csum_hash_info,
 	.type		= TCA_ACT_CSUM,
-	.capab		= TCA_CAP_NONE,
 	.owner		= THIS_MODULE,
 	.act		= tcf_csum,
 	.dump		= tcf_csum_dump,
-	.cleanup	= tcf_csum_cleanup,
 	.init		= tcf_csum_init,
 };
 
@@ -593,7 +572,7 @@ MODULE_LICENSE("GPL");
 
 static int __init csum_init_module(void)
 {
-	return tcf_register_action(&act_csum_ops);
+	return tcf_register_action(&act_csum_ops, CSUM_TAB_MASK);
 }
 
 static void __exit csum_cleanup_module(void)
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 5645a4d32ab..d6bcbd9f779 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -24,20 +24,11 @@
 #include <net/tc_act/tc_gact.h>
 
 #define GACT_TAB_MASK	15
-static struct tcf_common *tcf_gact_ht[GACT_TAB_MASK + 1];
-static u32 gact_idx_gen;
-static DEFINE_RWLOCK(gact_lock);
-
-static struct tcf_hashinfo gact_hash_info = {
-	.htab	=	tcf_gact_ht,
-	.hmask	=	GACT_TAB_MASK,
-	.lock	=	&gact_lock,
-};
 
 #ifdef CONFIG_GACT_PROB
 static int gact_net_rand(struct tcf_gact *gact)
 {
-	if (!gact->tcfg_pval || net_random() % gact->tcfg_pval)
+	if (!gact->tcfg_pval || prandom_u32() % gact->tcfg_pval)
 		return gact->tcf_action;
 	return gact->tcfg_paction;
 }
@@ -65,7 +56,6 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	struct nlattr *tb[TCA_GACT_MAX + 1];
 	struct tc_gact *parm;
 	struct tcf_gact *gact;
-	struct tcf_common *pc;
 	int ret = 0;
 	int err;
 #ifdef CONFIG_GACT_PROB
@@ -94,21 +84,20 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	}
 #endif
 
-	pc = tcf_hash_check(parm->index, a, bind, &gact_hash_info);
-	if (!pc) {
-		pc = tcf_hash_create(parm->index, est, a, sizeof(*gact),
-				     bind, &gact_idx_gen, &gact_hash_info);
-		if (IS_ERR(pc))
-			return PTR_ERR(pc);
+	if (!tcf_hash_check(parm->index, a, bind)) {
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind);
+		if (ret)
+			return ret;
 		ret = ACT_P_CREATED;
 	} else {
-		if (!ovr) {
-			tcf_hash_release(pc, bind, &gact_hash_info);
+		if (bind)/* dont override defaults */
+			return 0;
+		tcf_hash_release(a, bind);
+		if (!ovr)
 			return -EEXIST;
-		}
 	}
 
-	gact = to_gact(pc);
+	gact = to_gact(a);
 
 	spin_lock_bh(&gact->tcf_lock);
 	gact->tcf_action = parm->action;
@@ -121,19 +110,10 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 #endif
 	spin_unlock_bh(&gact->tcf_lock);
 	if (ret == ACT_P_CREATED)
-		tcf_hash_insert(pc, &gact_hash_info);
+		tcf_hash_insert(a);
 	return ret;
 }
 
-static int tcf_gact_cleanup(struct tc_action *a, int bind)
-{
-	struct tcf_gact *gact = a->priv;
-
-	if (gact)
-		return tcf_hash_release(&gact->common, bind, &gact_hash_info);
-	return 0;
-}
-
 static int tcf_gact(struct sk_buff *skb, const struct tc_action *a,
 		    struct tcf_result *res)
 {
@@ -199,13 +179,10 @@ nla_put_failure:
 
 static struct tc_action_ops act_gact_ops = {
 	.kind		=	"gact",
-	.hinfo		=	&gact_hash_info,
 	.type		=	TCA_ACT_GACT,
-	.capab		=	TCA_CAP_NONE,
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_gact,
 	.dump		=	tcf_gact_dump,
-	.cleanup	=	tcf_gact_cleanup,
 	.init		=	tcf_gact_init,
 };
 
@@ -220,7 +197,7 @@ static int __init gact_init_module(void)
 #else
 	pr_info("GACT probability NOT on\n");
 #endif
-	return tcf_register_action(&act_gact_ops);
+	return tcf_register_action(&act_gact_ops, GACT_TAB_MASK);
 }
 
 static void __exit gact_cleanup_module(void)
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 882a89762f7..8a64a0734ae 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -29,15 +29,6 @@
 
 
 #define IPT_TAB_MASK     15
-static struct tcf_common *tcf_ipt_ht[IPT_TAB_MASK + 1];
-static u32 ipt_idx_gen;
-static DEFINE_RWLOCK(ipt_lock);
-
-static struct tcf_hashinfo ipt_hash_info = {
-	.htab	=	tcf_ipt_ht,
-	.hmask	=	IPT_TAB_MASK,
-	.lock	=	&ipt_lock,
-};
 
 static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook)
 {
@@ -77,22 +68,12 @@ static void ipt_destroy_target(struct xt_entry_target *t)
 	module_put(par.target->me);
 }
 
-static int tcf_ipt_release(struct tcf_ipt *ipt, int bind)
+static void tcf_ipt_release(struct tc_action *a, int bind)
 {
-	int ret = 0;
-	if (ipt) {
-		if (bind)
-			ipt->tcf_bindcnt--;
-		ipt->tcf_refcnt--;
-		if (ipt->tcf_bindcnt <= 0 && ipt->tcf_refcnt <= 0) {
-			ipt_destroy_target(ipt->tcfi_t);
-			kfree(ipt->tcfi_tname);
-			kfree(ipt->tcfi_t);
-			tcf_hash_destroy(&ipt->common, &ipt_hash_info);
-			ret = ACT_P_DELETED;
-		}
-	}
-	return ret;
+	struct tcf_ipt *ipt = to_ipt(a);
+	ipt_destroy_target(ipt->tcfi_t);
+	kfree(ipt->tcfi_tname);
+	kfree(ipt->tcfi_t);
 }
 
 static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = {
@@ -107,7 +88,6 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 {
 	struct nlattr *tb[TCA_IPT_MAX + 1];
 	struct tcf_ipt *ipt;
-	struct tcf_common *pc;
 	struct xt_entry_target *td, *t;
 	char *tname;
 	int ret = 0, err;
@@ -133,20 +113,20 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	if (tb[TCA_IPT_INDEX] != NULL)
 		index = nla_get_u32(tb[TCA_IPT_INDEX]);
 
-	pc = tcf_hash_check(index, a, bind, &ipt_hash_info);
-	if (!pc) {
-		pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind,
-				     &ipt_idx_gen, &ipt_hash_info);
-		if (IS_ERR(pc))
-			return PTR_ERR(pc);
+	if (!tcf_hash_check(index, a, bind) ) {
+		ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind);
+		if (ret)
+			return ret;
 		ret = ACT_P_CREATED;
 	} else {
-		if (!ovr) {
-			tcf_ipt_release(to_ipt(pc), bind);
+		if (bind)/* dont override defaults */
+			return 0;
+		tcf_hash_release(a, bind);
+
+		if (!ovr)
 			return -EEXIST;
-		}
 	}
-	ipt = to_ipt(pc);
+	ipt = to_ipt(a);
 
 	hook = nla_get_u32(tb[TCA_IPT_HOOK]);
 
@@ -177,7 +157,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	ipt->tcfi_hook  = hook;
 	spin_unlock_bh(&ipt->tcf_lock);
 	if (ret == ACT_P_CREATED)
-		tcf_hash_insert(pc, &ipt_hash_info);
+		tcf_hash_insert(a);
 	return ret;
 
 err3:
@@ -185,21 +165,11 @@ err3:
 err2:
 	kfree(tname);
 err1:
-	if (ret == ACT_P_CREATED) {
-		if (est)
-			gen_kill_estimator(&pc->tcfc_bstats,
-					   &pc->tcfc_rate_est);
-		kfree_rcu(pc, tcfc_rcu);
-	}
+	if (ret == ACT_P_CREATED)
+		tcf_hash_cleanup(a, est);
 	return err;
 }
 
-static int tcf_ipt_cleanup(struct tc_action *a, int bind)
-{
-	struct tcf_ipt *ipt = a->priv;
-	return tcf_ipt_release(ipt, bind);
-}
-
 static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
 		   struct tcf_result *res)
 {
@@ -291,25 +261,21 @@ nla_put_failure:
 
 static struct tc_action_ops act_ipt_ops = {
 	.kind		=	"ipt",
-	.hinfo		=	&ipt_hash_info,
 	.type		=	TCA_ACT_IPT,
-	.capab		=	TCA_CAP_NONE,
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_ipt,
 	.dump		=	tcf_ipt_dump,
-	.cleanup	=	tcf_ipt_cleanup,
+	.cleanup	=	tcf_ipt_release,
 	.init		=	tcf_ipt_init,
 };
 
 static struct tc_action_ops act_xt_ops = {
 	.kind		=	"xt",
-	.hinfo		=	&ipt_hash_info,
-	.type		=	TCA_ACT_IPT,
-	.capab		=	TCA_CAP_NONE,
+	.type		=	TCA_ACT_XT,
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_ipt,
 	.dump		=	tcf_ipt_dump,
-	.cleanup	=	tcf_ipt_cleanup,
+	.cleanup	=	tcf_ipt_release,
 	.init		=	tcf_ipt_init,
 };
 
@@ -321,16 +287,17 @@ MODULE_ALIAS("act_xt");
 static int __init ipt_init_module(void)
 {
 	int ret1, ret2;
-	ret1 = tcf_register_action(&act_xt_ops);
+
+	ret1 = tcf_register_action(&act_xt_ops, IPT_TAB_MASK);
 	if (ret1 < 0)
 		printk("Failed to load xt action\n");
-	ret2 = tcf_register_action(&act_ipt_ops);
+	ret2 = tcf_register_action(&act_ipt_ops, IPT_TAB_MASK);
 	if (ret2 < 0)
 		printk("Failed to load ipt action\n");
 
-	if (ret1 < 0 && ret2 < 0)
+	if (ret1 < 0 && ret2 < 0) {
 		return ret1;
-	else
+	} else
 		return 0;
 }
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 252378121ce..4f912c0e225 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -30,32 +30,14 @@
 #include <linux/if_arp.h>
 
 #define MIRRED_TAB_MASK     7
-static struct tcf_common *tcf_mirred_ht[MIRRED_TAB_MASK + 1];
-static u32 mirred_idx_gen;
-static DEFINE_RWLOCK(mirred_lock);
 static LIST_HEAD(mirred_list);
 
-static struct tcf_hashinfo mirred_hash_info = {
-	.htab	=	tcf_mirred_ht,
-	.hmask	=	MIRRED_TAB_MASK,
-	.lock	=	&mirred_lock,
-};
-
-static int tcf_mirred_release(struct tcf_mirred *m, int bind)
+static void tcf_mirred_release(struct tc_action *a, int bind)
 {
-	if (m) {
-		if (bind)
-			m->tcf_bindcnt--;
-		m->tcf_refcnt--;
-		if (!m->tcf_bindcnt && m->tcf_refcnt <= 0) {
-			list_del(&m->tcfm_list);
-			if (m->tcfm_dev)
-				dev_put(m->tcfm_dev);
-			tcf_hash_destroy(&m->common, &mirred_hash_info);
-			return 1;
-		}
-	}
-	return 0;
+	struct tcf_mirred *m = to_mirred(a);
+	list_del(&m->tcfm_list);
+	if (m->tcfm_dev)
+		dev_put(m->tcfm_dev);
 }
 
 static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
@@ -69,7 +51,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	struct nlattr *tb[TCA_MIRRED_MAX + 1];
 	struct tc_mirred *parm;
 	struct tcf_mirred *m;
-	struct tcf_common *pc;
 	struct net_device *dev;
 	int ret, ok_push = 0;
 
@@ -109,22 +90,20 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		dev = NULL;
 	}
 
-	pc = tcf_hash_check(parm->index, a, bind, &mirred_hash_info);
-	if (!pc) {
+	if (!tcf_hash_check(parm->index, a, bind)) {
 		if (dev == NULL)
 			return -EINVAL;
-		pc = tcf_hash_create(parm->index, est, a, sizeof(*m), bind,
-				     &mirred_idx_gen, &mirred_hash_info);
-		if (IS_ERR(pc))
-			return PTR_ERR(pc);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*m), bind);
+		if (ret)
+			return ret;
 		ret = ACT_P_CREATED;
 	} else {
 		if (!ovr) {
-			tcf_mirred_release(to_mirred(pc), bind);
+			tcf_hash_release(a, bind);
 			return -EEXIST;
 		}
 	}
-	m = to_mirred(pc);
+	m = to_mirred(a);
 
 	spin_lock_bh(&m->tcf_lock);
 	m->tcf_action = parm->action;
@@ -140,21 +119,12 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	spin_unlock_bh(&m->tcf_lock);
 	if (ret == ACT_P_CREATED) {
 		list_add(&m->tcfm_list, &mirred_list);
-		tcf_hash_insert(pc, &mirred_hash_info);
+		tcf_hash_insert(a);
 	}
 
 	return ret;
 }
 
-static int tcf_mirred_cleanup(struct tc_action *a, int bind)
-{
-	struct tcf_mirred *m = a->priv;
-
-	if (m)
-		return tcf_mirred_release(m, bind);
-	return 0;
-}
-
 static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 		      struct tcf_result *res)
 {
@@ -261,16 +231,13 @@ static struct notifier_block mirred_device_notifier = {
 	.notifier_call = mirred_device_event,
 };
 
-
 static struct tc_action_ops act_mirred_ops = {
 	.kind		=	"mirred",
-	.hinfo		=	&mirred_hash_info,
 	.type		=	TCA_ACT_MIRRED,
-	.capab		=	TCA_CAP_NONE,
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_mirred,
 	.dump		=	tcf_mirred_dump,
-	.cleanup	=	tcf_mirred_cleanup,
+	.cleanup	=	tcf_mirred_release,
 	.init		=	tcf_mirred_init,
 };
 
@@ -285,13 +252,13 @@ static int __init mirred_init_module(void)
 		return err;
 
 	pr_info("Mirror/redirect action on\n");
-	return tcf_register_action(&act_mirred_ops);
+	return tcf_register_action(&act_mirred_ops, MIRRED_TAB_MASK);
 }
 
 static void __exit mirred_cleanup_module(void)
 {
-	unregister_netdevice_notifier(&mirred_device_notifier);
 	tcf_unregister_action(&act_mirred_ops);
+	unregister_netdevice_notifier(&mirred_device_notifier);
 }
 
 module_init(mirred_init_module);
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 6a15ace0024..270a030d5fd 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -30,15 +30,6 @@
 
 
 #define NAT_TAB_MASK	15
-static struct tcf_common *tcf_nat_ht[NAT_TAB_MASK + 1];
-static u32 nat_idx_gen;
-static DEFINE_RWLOCK(nat_lock);
-
-static struct tcf_hashinfo nat_hash_info = {
-	.htab	=	tcf_nat_ht,
-	.hmask	=	NAT_TAB_MASK,
-	.lock	=	&nat_lock,
-};
 
 static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
 	[TCA_NAT_PARMS]	= { .len = sizeof(struct tc_nat) },
@@ -51,7 +42,6 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	struct tc_nat *parm;
 	int ret = 0, err;
 	struct tcf_nat *p;
-	struct tcf_common *pc;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -64,21 +54,19 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 		return -EINVAL;
 	parm = nla_data(tb[TCA_NAT_PARMS]);
 
-	pc = tcf_hash_check(parm->index, a, bind, &nat_hash_info);
-	if (!pc) {
-		pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind,
-				     &nat_idx_gen, &nat_hash_info);
-		if (IS_ERR(pc))
-			return PTR_ERR(pc);
-		p = to_tcf_nat(pc);
+	if (!tcf_hash_check(parm->index, a, bind)) {
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+		if (ret)
+			return ret;
 		ret = ACT_P_CREATED;
 	} else {
-		p = to_tcf_nat(pc);
-		if (!ovr) {
-			tcf_hash_release(pc, bind, &nat_hash_info);
+		if (bind)
+			return 0;
+		tcf_hash_release(a, bind);
+		if (!ovr)
 			return -EEXIST;
-		}
 	}
+	p = to_tcf_nat(a);
 
 	spin_lock_bh(&p->tcf_lock);
 	p->old_addr = parm->old_addr;
@@ -90,18 +78,11 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	spin_unlock_bh(&p->tcf_lock);
 
 	if (ret == ACT_P_CREATED)
-		tcf_hash_insert(pc, &nat_hash_info);
+		tcf_hash_insert(a);
 
 	return ret;
 }
 
-static int tcf_nat_cleanup(struct tc_action *a, int bind)
-{
-	struct tcf_nat *p = a->priv;
-
-	return tcf_hash_release(&p->common, bind, &nat_hash_info);
-}
-
 static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
 		   struct tcf_result *res)
 {
@@ -301,13 +282,10 @@ nla_put_failure:
 
 static struct tc_action_ops act_nat_ops = {
 	.kind		=	"nat",
-	.hinfo		=	&nat_hash_info,
 	.type		=	TCA_ACT_NAT,
-	.capab		=	TCA_CAP_NONE,
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_nat,
 	.dump		=	tcf_nat_dump,
-	.cleanup	=	tcf_nat_cleanup,
 	.init		=	tcf_nat_init,
 };
 
@@ -316,7 +294,7 @@ MODULE_LICENSE("GPL");
 
 static int __init nat_init_module(void)
 {
-	return tcf_register_action(&act_nat_ops);
+	return tcf_register_action(&act_nat_ops, NAT_TAB_MASK);
 }
 
 static void __exit nat_cleanup_module(void)
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 03b67674169..5f9bcb2e080 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -24,15 +24,6 @@
 #include <net/tc_act/tc_pedit.h>
 
 #define PEDIT_TAB_MASK	15
-static struct tcf_common *tcf_pedit_ht[PEDIT_TAB_MASK + 1];
-static u32 pedit_idx_gen;
-static DEFINE_RWLOCK(pedit_lock);
-
-static struct tcf_hashinfo pedit_hash_info = {
-	.htab	=	tcf_pedit_ht,
-	.hmask	=	PEDIT_TAB_MASK,
-	.lock	=	&pedit_lock,
-};
 
 static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = {
 	[TCA_PEDIT_PARMS]	= { .len = sizeof(struct tc_pedit) },
@@ -46,7 +37,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	struct tc_pedit *parm;
 	int ret = 0, err;
 	struct tcf_pedit *p;
-	struct tcf_common *pc;
 	struct tc_pedit_key *keys = NULL;
 	int ksize;
 
@@ -64,30 +54,27 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	if (nla_len(tb[TCA_PEDIT_PARMS]) < sizeof(*parm) + ksize)
 		return -EINVAL;
 
-	pc = tcf_hash_check(parm->index, a, bind, &pedit_hash_info);
-	if (!pc) {
+	if (!tcf_hash_check(parm->index, a, bind)) {
 		if (!parm->nkeys)
 			return -EINVAL;
-		pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind,
-				     &pedit_idx_gen, &pedit_hash_info);
-		if (IS_ERR(pc))
-			return PTR_ERR(pc);
-		p = to_pedit(pc);
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind);
+		if (ret)
+			return ret;
+		p = to_pedit(a);
 		keys = kmalloc(ksize, GFP_KERNEL);
 		if (keys == NULL) {
-			if (est)
-				gen_kill_estimator(&pc->tcfc_bstats,
-						   &pc->tcfc_rate_est);
-			kfree_rcu(pc, tcfc_rcu);
+			tcf_hash_cleanup(a, est);
 			return -ENOMEM;
 		}
 		ret = ACT_P_CREATED;
 	} else {
-		p = to_pedit(pc);
-		if (!ovr) {
-			tcf_hash_release(pc, bind, &pedit_hash_info);
+		p = to_pedit(a);
+		tcf_hash_release(a, bind);
+		if (bind)
+			return 0;
+		if (!ovr)
 			return -EEXIST;
-		}
+
 		if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) {
 			keys = kmalloc(ksize, GFP_KERNEL);
 			if (keys == NULL)
@@ -106,22 +93,15 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	memcpy(p->tcfp_keys, parm->keys, ksize);
 	spin_unlock_bh(&p->tcf_lock);
 	if (ret == ACT_P_CREATED)
-		tcf_hash_insert(pc, &pedit_hash_info);
+		tcf_hash_insert(a);
 	return ret;
 }
 
-static int tcf_pedit_cleanup(struct tc_action *a, int bind)
+static void tcf_pedit_cleanup(struct tc_action *a, int bind)
 {
 	struct tcf_pedit *p = a->priv;
-
-	if (p) {
-		struct tc_pedit_key *keys = p->tcfp_keys;
-		if (tcf_hash_release(&p->common, bind, &pedit_hash_info)) {
-			kfree(keys);
-			return 1;
-		}
-	}
-	return 0;
+	struct tc_pedit_key *keys = p->tcfp_keys;
+	kfree(keys);
 }
 
 static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
@@ -236,9 +216,7 @@ nla_put_failure:
 
 static struct tc_action_ops act_pedit_ops = {
 	.kind		=	"pedit",
-	.hinfo		=	&pedit_hash_info,
 	.type		=	TCA_ACT_PEDIT,
-	.capab		=	TCA_CAP_NONE,
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_pedit,
 	.dump		=	tcf_pedit_dump,
@@ -252,7 +230,7 @@ MODULE_LICENSE("GPL");
 
 static int __init pedit_init_module(void)
 {
-	return tcf_register_action(&act_pedit_ops);
+	return tcf_register_action(&act_pedit_ops, PEDIT_TAB_MASK);
 }
 
 static void __exit pedit_cleanup_module(void)
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 16a62c36928..0566e4606a4 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -41,15 +41,6 @@ struct tcf_police {
 	container_of(pc, struct tcf_police, common)
 
 #define POL_TAB_MASK     15
-static struct tcf_common *tcf_police_ht[POL_TAB_MASK + 1];
-static u32 police_idx_gen;
-static DEFINE_RWLOCK(police_lock);
-
-static struct tcf_hashinfo police_hash_info = {
-	.htab	=	tcf_police_ht,
-	.hmask	=	POL_TAB_MASK,
-	.lock	=	&police_lock,
-};
 
 /* old policer structure from before tc actions */
 struct tc_police_compat {
@@ -67,18 +58,20 @@ struct tc_police_compat {
 static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *cb,
 			      int type, struct tc_action *a)
 {
+	struct tcf_hashinfo *hinfo = a->ops->hinfo;
+	struct hlist_head *head;
 	struct tcf_common *p;
 	int err = 0, index = -1, i = 0, s_i = 0, n_i = 0;
 	struct nlattr *nest;
 
-	read_lock_bh(&police_lock);
+	spin_lock_bh(&hinfo->lock);
 
 	s_i = cb->args[0];
 
 	for (i = 0; i < (POL_TAB_MASK + 1); i++) {
-		p = tcf_police_ht[tcf_hash(i, POL_TAB_MASK)];
+		head = &hinfo->htab[tcf_hash(i, POL_TAB_MASK)];
 
-		for (; p; p = p->tcfc_next) {
+		hlist_for_each_entry_rcu(p, head, tcfc_head) {
 			index++;
 			if (index < s_i)
 				continue;
@@ -101,7 +94,7 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c
 		}
 	}
 done:
-	read_unlock_bh(&police_lock);
+	spin_unlock_bh(&hinfo->lock);
 	if (n_i)
 		cb->args[0] += n_i;
 	return n_i;
@@ -111,29 +104,6 @@ nla_put_failure:
 	goto done;
 }
 
-static void tcf_police_destroy(struct tcf_police *p)
-{
-	unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK);
-	struct tcf_common **p1p;
-
-	for (p1p = &tcf_police_ht[h]; *p1p; p1p = &(*p1p)->tcfc_next) {
-		if (*p1p == &p->common) {
-			write_lock_bh(&police_lock);
-			*p1p = p->tcf_next;
-			write_unlock_bh(&police_lock);
-			gen_kill_estimator(&p->tcf_bstats,
-					   &p->tcf_rate_est);
-			/*
-			 * gen_estimator est_timer() might access p->tcf_lock
-			 * or bstats, wait a RCU grace period before freeing p
-			 */
-			kfree_rcu(p, tcf_rcu);
-			return;
-		}
-	}
-	WARN_ON(1);
-}
-
 static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
 	[TCA_POLICE_RATE]	= { .len = TC_RTAB_SIZE },
 	[TCA_POLICE_PEAKRATE]	= { .len = TC_RTAB_SIZE },
@@ -151,6 +121,7 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
 	struct tc_police *parm;
 	struct tcf_police *police;
 	struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL;
+	struct tcf_hashinfo *hinfo = a->ops->hinfo;
 	int size;
 
 	if (nla == NULL)
@@ -168,19 +139,17 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
 	parm = nla_data(tb[TCA_POLICE_TBF]);
 
 	if (parm->index) {
-		struct tcf_common *pc;
-
-		pc = tcf_hash_lookup(parm->index, &police_hash_info);
-		if (pc != NULL) {
-			a->priv = pc;
-			police = to_police(pc);
+		if (tcf_hash_search(a, parm->index)) {
+			police = to_police(a->priv);
 			if (bind) {
 				police->tcf_bindcnt += 1;
 				police->tcf_refcnt += 1;
+				return 0;
 			}
 			if (ovr)
 				goto override;
-			return ret;
+			/* not replacing */
+			return -EEXIST;
 		}
 	}
 
@@ -264,12 +233,11 @@ override:
 
 	police->tcfp_t_c = ktime_to_ns(ktime_get());
 	police->tcf_index = parm->index ? parm->index :
-		tcf_hash_new_index(&police_idx_gen, &police_hash_info);
+		tcf_hash_new_index(hinfo);
 	h = tcf_hash(police->tcf_index, POL_TAB_MASK);
-	write_lock_bh(&police_lock);
-	police->tcf_next = tcf_police_ht[h];
-	tcf_police_ht[h] = &police->common;
-	write_unlock_bh(&police_lock);
+	spin_lock_bh(&hinfo->lock);
+	hlist_add_head(&police->tcf_head, &hinfo->htab[h]);
+	spin_unlock_bh(&hinfo->lock);
 
 	a->priv = police;
 	return ret;
@@ -277,33 +245,13 @@ override:
 failure_unlock:
 	spin_unlock_bh(&police->tcf_lock);
 failure:
-	if (P_tab)
-		qdisc_put_rtab(P_tab);
-	if (R_tab)
-		qdisc_put_rtab(R_tab);
+	qdisc_put_rtab(P_tab);
+	qdisc_put_rtab(R_tab);
 	if (ret == ACT_P_CREATED)
 		kfree(police);
 	return err;
 }
 
-static int tcf_act_police_cleanup(struct tc_action *a, int bind)
-{
-	struct tcf_police *p = a->priv;
-	int ret = 0;
-
-	if (p != NULL) {
-		if (bind)
-			p->tcf_bindcnt--;
-
-		p->tcf_refcnt--;
-		if (p->tcf_refcnt <= 0 && !p->tcf_bindcnt) {
-			tcf_police_destroy(p);
-			ret = 1;
-		}
-	}
-	return ret;
-}
-
 static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
 			  struct tcf_result *res)
 {
@@ -400,13 +348,10 @@ MODULE_LICENSE("GPL");
 
 static struct tc_action_ops act_police_ops = {
 	.kind		=	"police",
-	.hinfo		=	&police_hash_info,
 	.type		=	TCA_ID_POLICE,
-	.capab		=	TCA_CAP_NONE,
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_act_police,
 	.dump		=	tcf_act_police_dump,
-	.cleanup	=	tcf_act_police_cleanup,
 	.init		=	tcf_act_police_locate,
 	.walk		=	tcf_act_police_walker
 };
@@ -414,7 +359,7 @@ static struct tc_action_ops act_police_ops = {
 static int __init
 police_init_module(void)
 {
-	return tcf_register_action(&act_police_ops);
+	return tcf_register_action(&act_police_ops, POL_TAB_MASK);
 }
 
 static void __exit
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 31157d3e729..992c2317ce8 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -25,15 +25,6 @@
 #include <net/tc_act/tc_defact.h>
 
 #define SIMP_TAB_MASK     7
-static struct tcf_common *tcf_simp_ht[SIMP_TAB_MASK + 1];
-static u32 simp_idx_gen;
-static DEFINE_RWLOCK(simp_lock);
-
-static struct tcf_hashinfo simp_hash_info = {
-	.htab	=	tcf_simp_ht,
-	.hmask	=	SIMP_TAB_MASK,
-	.lock	=	&simp_lock,
-};
 
 #define SIMP_MAX_DATA	32
 static int tcf_simp(struct sk_buff *skb, const struct tc_action *a,
@@ -55,20 +46,10 @@ static int tcf_simp(struct sk_buff *skb, const struct tc_action *a,
 	return d->tcf_action;
 }
 
-static int tcf_simp_release(struct tcf_defact *d, int bind)
+static void tcf_simp_release(struct tc_action *a, int bind)
 {
-	int ret = 0;
-	if (d) {
-		if (bind)
-			d->tcf_bindcnt--;
-		d->tcf_refcnt--;
-		if (d->tcf_bindcnt <= 0 && d->tcf_refcnt <= 0) {
-			kfree(d->tcfd_defdata);
-			tcf_hash_destroy(&d->common, &simp_hash_info);
-			ret = 1;
-		}
-	}
-	return ret;
+	struct tcf_defact *d = to_defact(a);
+	kfree(d->tcfd_defdata);
 }
 
 static int alloc_defdata(struct tcf_defact *d, char *defdata)
@@ -102,7 +83,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	struct nlattr *tb[TCA_DEF_MAX + 1];
 	struct tc_defact *parm;
 	struct tcf_defact *d;
-	struct tcf_common *pc;
 	char *defdata;
 	int ret = 0, err;
 
@@ -122,47 +102,36 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	parm = nla_data(tb[TCA_DEF_PARMS]);
 	defdata = nla_data(tb[TCA_DEF_DATA]);
 
-	pc = tcf_hash_check(parm->index, a, bind, &simp_hash_info);
-	if (!pc) {
-		pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind,
-				     &simp_idx_gen, &simp_hash_info);
-		if (IS_ERR(pc))
-			return PTR_ERR(pc);
+	if (!tcf_hash_check(parm->index, a, bind)) {
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind);
+		if (ret)
+			return ret;
 
-		d = to_defact(pc);
+		d = to_defact(a);
 		ret = alloc_defdata(d, defdata);
 		if (ret < 0) {
-			if (est)
-				gen_kill_estimator(&pc->tcfc_bstats,
-						   &pc->tcfc_rate_est);
-			kfree_rcu(pc, tcfc_rcu);
+			tcf_hash_cleanup(a, est);
 			return ret;
 		}
 		d->tcf_action = parm->action;
 		ret = ACT_P_CREATED;
 	} else {
-		d = to_defact(pc);
-		if (!ovr) {
-			tcf_simp_release(d, bind);
+		d = to_defact(a);
+
+		if (bind)
+			return 0;
+		tcf_hash_release(a, bind);
+		if (!ovr)
 			return -EEXIST;
-		}
+
 		reset_policy(d, defdata, parm);
 	}
 
 	if (ret == ACT_P_CREATED)
-		tcf_hash_insert(pc, &simp_hash_info);
+		tcf_hash_insert(a);
 	return ret;
 }
 
-static int tcf_simp_cleanup(struct tc_action *a, int bind)
-{
-	struct tcf_defact *d = a->priv;
-
-	if (d)
-		return tcf_simp_release(d, bind);
-	return 0;
-}
-
 static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
 			 int bind, int ref)
 {
@@ -193,13 +162,11 @@ nla_put_failure:
 
 static struct tc_action_ops act_simp_ops = {
 	.kind		=	"simple",
-	.hinfo		=	&simp_hash_info,
 	.type		=	TCA_ACT_SIMP,
-	.capab		=	TCA_CAP_NONE,
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_simp,
 	.dump		=	tcf_simp_dump,
-	.cleanup	=	tcf_simp_cleanup,
+	.cleanup	=	tcf_simp_release,
 	.init		=	tcf_simp_init,
 };
 
@@ -209,7 +176,8 @@ MODULE_LICENSE("GPL");
 
 static int __init simp_init_module(void)
 {
-	int ret = tcf_register_action(&act_simp_ops);
+	int ret;
+	ret = tcf_register_action(&act_simp_ops, SIMP_TAB_MASK);
 	if (!ret)
 		pr_info("Simple TC action Loaded\n");
 	return ret;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index cf20add1c3f..fcfeeaf838b 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -28,15 +28,6 @@
 #include <net/tc_act/tc_skbedit.h>
 
 #define SKBEDIT_TAB_MASK     15
-static struct tcf_common *tcf_skbedit_ht[SKBEDIT_TAB_MASK + 1];
-static u32 skbedit_idx_gen;
-static DEFINE_RWLOCK(skbedit_lock);
-
-static struct tcf_hashinfo skbedit_hash_info = {
-	.htab	=	tcf_skbedit_ht,
-	.hmask	=	SKBEDIT_TAB_MASK,
-	.lock	=	&skbedit_lock,
-};
 
 static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 		       struct tcf_result *res)
@@ -73,7 +64,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
 	struct tc_skbedit *parm;
 	struct tcf_skbedit *d;
-	struct tcf_common *pc;
 	u32 flags = 0, *priority = NULL, *mark = NULL;
 	u16 *queue_mapping = NULL;
 	int ret = 0, err;
@@ -108,21 +98,20 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 
 	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
 
-	pc = tcf_hash_check(parm->index, a, bind, &skbedit_hash_info);
-	if (!pc) {
-		pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind,
-				     &skbedit_idx_gen, &skbedit_hash_info);
-		if (IS_ERR(pc))
-			return PTR_ERR(pc);
+	if (!tcf_hash_check(parm->index, a, bind)) {
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind);
+		if (ret)
+			return ret;
 
-		d = to_skbedit(pc);
+		d = to_skbedit(a);
 		ret = ACT_P_CREATED;
 	} else {
-		d = to_skbedit(pc);
-		if (!ovr) {
-			tcf_hash_release(pc, bind, &skbedit_hash_info);
+		d = to_skbedit(a);
+		if (bind)
+			return 0;
+		tcf_hash_release(a, bind);
+		if (!ovr)
 			return -EEXIST;
-		}
 	}
 
 	spin_lock_bh(&d->tcf_lock);
@@ -140,19 +129,10 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	spin_unlock_bh(&d->tcf_lock);
 
 	if (ret == ACT_P_CREATED)
-		tcf_hash_insert(pc, &skbedit_hash_info);
+		tcf_hash_insert(a);
 	return ret;
 }
 
-static int tcf_skbedit_cleanup(struct tc_action *a, int bind)
-{
-	struct tcf_skbedit *d = a->priv;
-
-	if (d)
-		return tcf_hash_release(&d->common, bind, &skbedit_hash_info);
-	return 0;
-}
-
 static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
 			    int bind, int ref)
 {
@@ -194,13 +174,10 @@ nla_put_failure:
 
 static struct tc_action_ops act_skbedit_ops = {
 	.kind		=	"skbedit",
-	.hinfo		=	&skbedit_hash_info,
 	.type		=	TCA_ACT_SKBEDIT,
-	.capab		=	TCA_CAP_NONE,
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_skbedit,
 	.dump		=	tcf_skbedit_dump,
-	.cleanup	=	tcf_skbedit_cleanup,
 	.init		=	tcf_skbedit_init,
 };
 
@@ -210,7 +187,7 @@ MODULE_LICENSE("GPL");
 
 static int __init skbedit_init_module(void)
 {
-	return tcf_register_action(&act_skbedit_ops);
+	return tcf_register_action(&act_skbedit_ops, SKBEDIT_TAB_MASK);
 }
 
 static void __exit skbedit_cleanup_module(void)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 8e118af9097..45527e6b52d 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -31,8 +31,7 @@
 #include <net/pkt_cls.h>
 
 /* The list of all installed classifier types */
-
-static struct tcf_proto_ops *tcf_proto_base __read_mostly;
+static LIST_HEAD(tcf_proto_base);
 
 /* Protects list of registered TC modules. It is pure SMP lock. */
 static DEFINE_RWLOCK(cls_mod_lock);
@@ -41,36 +40,35 @@ static DEFINE_RWLOCK(cls_mod_lock);
 
 static const struct tcf_proto_ops *tcf_proto_lookup_ops(struct nlattr *kind)
 {
-	const struct tcf_proto_ops *t = NULL;
+	const struct tcf_proto_ops *t, *res = NULL;
 
 	if (kind) {
 		read_lock(&cls_mod_lock);
-		for (t = tcf_proto_base; t; t = t->next) {
+		list_for_each_entry(t, &tcf_proto_base, head) {
 			if (nla_strcmp(kind, t->kind) == 0) {
-				if (!try_module_get(t->owner))
-					t = NULL;
+				if (try_module_get(t->owner))
+					res = t;
 				break;
 			}
 		}
 		read_unlock(&cls_mod_lock);
 	}
-	return t;
+	return res;
 }
 
 /* Register(unregister) new classifier type */
 
 int register_tcf_proto_ops(struct tcf_proto_ops *ops)
 {
-	struct tcf_proto_ops *t, **tp;
+	struct tcf_proto_ops *t;
 	int rc = -EEXIST;
 
 	write_lock(&cls_mod_lock);
-	for (tp = &tcf_proto_base; (t = *tp) != NULL; tp = &t->next)
+	list_for_each_entry(t, &tcf_proto_base, head)
 		if (!strcmp(ops->kind, t->kind))
 			goto out;
 
-	ops->next = NULL;
-	*tp = ops;
+	list_add_tail(&ops->head, &tcf_proto_base);
 	rc = 0;
 out:
 	write_unlock(&cls_mod_lock);
@@ -80,19 +78,17 @@ EXPORT_SYMBOL(register_tcf_proto_ops);
 
 int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
 {
-	struct tcf_proto_ops *t, **tp;
+	struct tcf_proto_ops *t;
 	int rc = -ENOENT;
 
 	write_lock(&cls_mod_lock);
-	for (tp = &tcf_proto_base; (t = *tp) != NULL; tp = &t->next)
-		if (t == ops)
+	list_for_each_entry(t, &tcf_proto_base, head) {
+		if (t == ops) {
+			list_del(&t->head);
+			rc = 0;
 			break;
-
-	if (!t)
-		goto out;
-	*tp = t->next;
-	rc = 0;
-out:
+		}
+	}
 	write_unlock(&cls_mod_lock);
 	return rc;
 }
@@ -138,7 +134,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	int err;
 	int tp_created = 0;
 
-	if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTFILTER) &&
+	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
@@ -321,7 +318,8 @@ replay:
 		}
 	}
 
-	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh);
+	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
+			      n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE);
 	if (err == 0) {
 		if (tp_created) {
 			spin_lock_bh(root_lock);
@@ -344,7 +342,7 @@ errout:
 	return err;
 }
 
-static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp,
+static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp,
 			 unsigned long fh, u32 portid, u32 seq, u16 flags, int event)
 {
 	struct tcmsg *tcm;
@@ -366,7 +364,7 @@ static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp,
 	tcm->tcm_handle = fh;
 	if (RTM_DELTFILTER != event) {
 		tcm->tcm_handle = 0;
-		if (tp->ops->dump && tp->ops->dump(tp, fh, skb, tcm) < 0)
+		if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0)
 			goto nla_put_failure;
 	}
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
@@ -389,7 +387,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 	if (!skb)
 		return -ENOBUFS;
 
-	if (tcf_fill_node(skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) {
+	if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
@@ -408,8 +406,9 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n,
 			 struct tcf_walker *arg)
 {
 	struct tcf_dump_args *a = (void *)arg;
+	struct net *net = sock_net(a->skb->sk);
 
-	return tcf_fill_node(a->skb, tp, n, NETLINK_CB(a->cb->skb).portid,
+	return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid,
 			     a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER);
 }
 
@@ -467,7 +466,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		if (t > s_t)
 			memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0]));
 		if (cb->args[1] == 0) {
-			if (tcf_fill_node(skb, tp, 0, NETLINK_CB(cb->skb).portid,
+			if (tcf_fill_node(net, skb, tp, 0, NETLINK_CB(cb->skb).portid,
 					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					  RTM_NEWTFILTER) <= 0)
 				break;
@@ -500,46 +499,41 @@ out:
 void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	if (exts->action) {
-		tcf_action_destroy(exts->action, TCA_ACT_UNBIND);
-		exts->action = NULL;
-	}
+	tcf_action_destroy(&exts->actions, TCA_ACT_UNBIND);
+	INIT_LIST_HEAD(&exts->actions);
 #endif
 }
 EXPORT_SYMBOL(tcf_exts_destroy);
 
 int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
-		  struct nlattr *rate_tlv, struct tcf_exts *exts,
-		  const struct tcf_ext_map *map)
+		  struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr)
 {
-	memset(exts, 0, sizeof(*exts));
-
 #ifdef CONFIG_NET_CLS_ACT
 	{
 		struct tc_action *act;
 
-		if (map->police && tb[map->police]) {
-			act = tcf_action_init_1(net, tb[map->police], rate_tlv,
-						"police", TCA_ACT_NOREPLACE,
+		INIT_LIST_HEAD(&exts->actions);
+		if (exts->police && tb[exts->police]) {
+			act = tcf_action_init_1(net, tb[exts->police], rate_tlv,
+						"police", ovr,
 						TCA_ACT_BIND);
 			if (IS_ERR(act))
 				return PTR_ERR(act);
 
-			act->type = TCA_OLD_COMPAT;
-			exts->action = act;
-		} else if (map->action && tb[map->action]) {
-			act = tcf_action_init(net, tb[map->action], rate_tlv,
-					      NULL, TCA_ACT_NOREPLACE,
-					      TCA_ACT_BIND);
-			if (IS_ERR(act))
-				return PTR_ERR(act);
-
-			exts->action = act;
+			act->type = exts->type = TCA_OLD_COMPAT;
+			list_add(&act->list, &exts->actions);
+		} else if (exts->action && tb[exts->action]) {
+			int err;
+			err = tcf_action_init(net, tb[exts->action], rate_tlv,
+					      NULL, ovr,
+					      TCA_ACT_BIND, &exts->actions);
+			if (err)
+				return err;
 		}
 	}
 #else
-	if ((map->action && tb[map->action]) ||
-	    (map->police && tb[map->police]))
+	if ((exts->action && tb[exts->action]) ||
+	    (exts->police && tb[exts->police]))
 		return -EOPNOTSUPP;
 #endif
 
@@ -551,43 +545,42 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst,
 		     struct tcf_exts *src)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	if (src->action) {
-		struct tc_action *act;
-		tcf_tree_lock(tp);
-		act = dst->action;
-		dst->action = src->action;
-		tcf_tree_unlock(tp);
-		if (act)
-			tcf_action_destroy(act, TCA_ACT_UNBIND);
-	}
+	LIST_HEAD(tmp);
+	tcf_tree_lock(tp);
+	list_splice_init(&dst->actions, &tmp);
+	list_splice(&src->actions, &dst->actions);
+	tcf_tree_unlock(tp);
+	tcf_action_destroy(&tmp, TCA_ACT_UNBIND);
 #endif
 }
 EXPORT_SYMBOL(tcf_exts_change);
 
-int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts,
-		  const struct tcf_ext_map *map)
+#define tcf_exts_first_act(ext) \
+		list_first_entry(&(exts)->actions, struct tc_action, list)
+
+int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	if (map->action && exts->action) {
+	if (exts->action && !list_empty(&exts->actions)) {
 		/*
 		 * again for backward compatible mode - we want
 		 * to work with both old and new modes of entering
 		 * tc data even if iproute2  was newer - jhs
 		 */
 		struct nlattr *nest;
-
-		if (exts->action->type != TCA_OLD_COMPAT) {
-			nest = nla_nest_start(skb, map->action);
+		if (exts->type != TCA_OLD_COMPAT) {
+			nest = nla_nest_start(skb, exts->action);
 			if (nest == NULL)
 				goto nla_put_failure;
-			if (tcf_action_dump(skb, exts->action, 0, 0) < 0)
+			if (tcf_action_dump(skb, &exts->actions, 0, 0) < 0)
 				goto nla_put_failure;
 			nla_nest_end(skb, nest);
-		} else if (map->police) {
-			nest = nla_nest_start(skb, map->police);
-			if (nest == NULL)
+		} else if (exts->police) {
+			struct tc_action *act = tcf_exts_first_act(exts);
+			nest = nla_nest_start(skb, exts->police);
+			if (nest == NULL || !act)
 				goto nla_put_failure;
-			if (tcf_action_dump_old(skb, exts->action, 0, 0) < 0)
+			if (tcf_action_dump_old(skb, act, 0, 0) < 0)
 				goto nla_put_failure;
 			nla_nest_end(skb, nest);
 		}
@@ -600,17 +593,14 @@ nla_put_failure: __attribute__ ((unused))
 EXPORT_SYMBOL(tcf_exts_dump);
 
 
-int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts,
-			const struct tcf_ext_map *map)
+int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	if (exts->action)
-		if (tcf_action_copy_stats(skb, exts->action, 1) < 0)
-			goto nla_put_failure;
+	struct tc_action *a = tcf_exts_first_act(exts);
+	if (tcf_action_copy_stats(skb, a, 1) < 0)
+		return -1;
 #endif
 	return 0;
-nla_put_failure: __attribute__ ((unused))
-	return -1;
 }
 EXPORT_SYMBOL(tcf_exts_dump_stats);
 
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 636d9131d87..0ae1813e3e9 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -34,16 +34,11 @@ struct basic_filter {
 	struct list_head	link;
 };
 
-static const struct tcf_ext_map basic_ext_map = {
-	.action = TCA_BASIC_ACT,
-	.police = TCA_BASIC_POLICE
-};
-
 static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			  struct tcf_result *res)
 {
 	int r;
-	struct basic_head *head = (struct basic_head *) tp->root;
+	struct basic_head *head = tp->root;
 	struct basic_filter *f;
 
 	list_for_each_entry(f, &head->flist, link) {
@@ -61,7 +56,7 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 static unsigned long basic_get(struct tcf_proto *tp, u32 handle)
 {
 	unsigned long l = 0UL;
-	struct basic_head *head = (struct basic_head *) tp->root;
+	struct basic_head *head = tp->root;
 	struct basic_filter *f;
 
 	if (head == NULL)
@@ -112,7 +107,7 @@ static void basic_destroy(struct tcf_proto *tp)
 
 static int basic_delete(struct tcf_proto *tp, unsigned long arg)
 {
-	struct basic_head *head = (struct basic_head *) tp->root;
+	struct basic_head *head = tp->root;
 	struct basic_filter *t, *f = (struct basic_filter *) arg;
 
 	list_for_each_entry(t, &head->flist, link)
@@ -135,13 +130,14 @@ static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = {
 static int basic_set_parms(struct net *net, struct tcf_proto *tp,
 			   struct basic_filter *f, unsigned long base,
 			   struct nlattr **tb,
-			   struct nlattr *est)
+			   struct nlattr *est, bool ovr)
 {
 	int err;
 	struct tcf_exts e;
 	struct tcf_ematch_tree t;
 
-	err = tcf_exts_validate(net, tp, tb, est, &e, &basic_ext_map);
+	tcf_exts_init(&e, TCA_BASIC_ACT, TCA_BASIC_POLICE);
+	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -165,10 +161,10 @@ errout:
 
 static int basic_change(struct net *net, struct sk_buff *in_skb,
 			struct tcf_proto *tp, unsigned long base, u32 handle,
-			struct nlattr **tca, unsigned long *arg)
+			struct nlattr **tca, unsigned long *arg, bool ovr)
 {
 	int err;
-	struct basic_head *head = (struct basic_head *) tp->root;
+	struct basic_head *head = tp->root;
 	struct nlattr *tb[TCA_BASIC_MAX + 1];
 	struct basic_filter *f = (struct basic_filter *) *arg;
 
@@ -183,7 +179,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 	if (f != NULL) {
 		if (handle && f->handle != handle)
 			return -EINVAL;
-		return basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE]);
+		return basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr);
 	}
 
 	err = -ENOBUFS;
@@ -191,6 +187,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 	if (f == NULL)
 		goto errout;
 
+	tcf_exts_init(&f->exts, TCA_BASIC_ACT, TCA_BASIC_POLICE);
 	err = -EINVAL;
 	if (handle)
 		f->handle = handle;
@@ -209,7 +206,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 		f->handle = head->hgenerator;
 	}
 
-	err = basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE]);
+	err = basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr);
 	if (err < 0)
 		goto errout;
 
@@ -228,7 +225,7 @@ errout:
 
 static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 {
-	struct basic_head *head = (struct basic_head *) tp->root;
+	struct basic_head *head = tp->root;
 	struct basic_filter *f;
 
 	list_for_each_entry(f, &head->flist, link) {
@@ -244,7 +241,7 @@ skip:
 	}
 }
 
-static int basic_dump(struct tcf_proto *tp, unsigned long fh,
+static int basic_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		      struct sk_buff *skb, struct tcmsg *t)
 {
 	struct basic_filter *f = (struct basic_filter *) fh;
@@ -263,13 +260,13 @@ static int basic_dump(struct tcf_proto *tp, unsigned long fh,
 	    nla_put_u32(skb, TCA_BASIC_CLASSID, f->res.classid))
 		goto nla_put_failure;
 
-	if (tcf_exts_dump(skb, &f->exts, &basic_ext_map) < 0 ||
+	if (tcf_exts_dump(skb, &f->exts) < 0 ||
 	    tcf_em_tree_dump(skb, &f->ematches, TCA_BASIC_EMATCHES) < 0)
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 
-	if (tcf_exts_dump_stats(skb, &f->exts, &basic_ext_map) < 0)
+	if (tcf_exts_dump_stats(skb, &f->exts) < 0)
 		goto nla_put_failure;
 
 	return skb->len;
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 1002a822628..13f64df2c71 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -46,11 +46,6 @@ static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
 				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
 };
 
-static const struct tcf_ext_map bpf_ext_map = {
-	.action = TCA_BPF_ACT,
-	.police = TCA_BPF_POLICE,
-};
-
 static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			    struct tcf_result *res)
 {
@@ -161,11 +156,11 @@ static void cls_bpf_put(struct tcf_proto *tp, unsigned long f)
 static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 				   struct cls_bpf_prog *prog,
 				   unsigned long base, struct nlattr **tb,
-				   struct nlattr *est)
+				   struct nlattr *est, bool ovr)
 {
 	struct sock_filter *bpf_ops, *bpf_old;
 	struct tcf_exts exts;
-	struct sock_fprog tmp;
+	struct sock_fprog_kern tmp;
 	struct sk_filter *fp, *fp_old;
 	u16 bpf_size, bpf_len;
 	u32 classid;
@@ -174,7 +169,8 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 	if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID])
 		return -EINVAL;
 
-	ret = tcf_exts_validate(net, tp, tb, est, &exts, &bpf_ext_map);
+	tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE);
+	ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr);
 	if (ret < 0)
 		return ret;
 
@@ -195,7 +191,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 	memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);
 
 	tmp.len = bpf_len;
-	tmp.filter = (struct sock_filter __user *) bpf_ops;
+	tmp.filter = bpf_ops;
 
 	ret = sk_unattached_filter_create(&fp, &tmp);
 	if (ret)
@@ -246,7 +242,7 @@ static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp,
 static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 			  struct tcf_proto *tp, unsigned long base,
 			  u32 handle, struct nlattr **tca,
-			  unsigned long *arg)
+			  unsigned long *arg, bool ovr)
 {
 	struct cls_bpf_head *head = tp->root;
 	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) *arg;
@@ -264,13 +260,14 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 		if (handle && prog->handle != handle)
 			return -EINVAL;
 		return cls_bpf_modify_existing(net, tp, prog, base, tb,
-					       tca[TCA_RATE]);
+					       tca[TCA_RATE], ovr);
 	}
 
 	prog = kzalloc(sizeof(*prog), GFP_KERNEL);
 	if (prog == NULL)
 		return -ENOBUFS;
 
+	tcf_exts_init(&prog->exts, TCA_BPF_ACT, TCA_BPF_POLICE);
 	if (handle == 0)
 		prog->handle = cls_bpf_grab_new_handle(tp, head);
 	else
@@ -280,7 +277,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 		goto errout;
 	}
 
-	ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE]);
+	ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE], ovr);
 	if (ret < 0)
 		goto errout;
 
@@ -298,7 +295,7 @@ errout:
 	return ret;
 }
 
-static int cls_bpf_dump(struct tcf_proto *tp, unsigned long fh,
+static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 			struct sk_buff *skb, struct tcmsg *tm)
 {
 	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh;
@@ -323,14 +320,14 @@ static int cls_bpf_dump(struct tcf_proto *tp, unsigned long fh,
 	if (nla == NULL)
 		goto nla_put_failure;
 
-        memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
+	memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
 
-	if (tcf_exts_dump(skb, &prog->exts, &bpf_ext_map) < 0)
+	if (tcf_exts_dump(skb, &prog->exts) < 0)
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 
-	if (tcf_exts_dump_stats(skb, &prog->exts, &bpf_ext_map) < 0)
+	if (tcf_exts_dump_stats(skb, &prog->exts) < 0)
 		goto nla_put_failure;
 
 	return skb->len;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 16006c92c3f..cacf01bd04f 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -11,109 +11,13 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <linux/errno.h>
 #include <linux/skbuff.h>
-#include <linux/cgroup.h>
 #include <linux/rcupdate.h>
-#include <linux/fdtable.h>
 #include <net/rtnetlink.h>
 #include <net/pkt_cls.h>
 #include <net/sock.h>
 #include <net/cls_cgroup.h>
 
-static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css)
-{
-	return css ? container_of(css, struct cgroup_cls_state, css) : NULL;
-}
-
-static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p)
-{
-	return css_cls_state(task_css(p, net_cls_subsys_id));
-}
-
-static struct cgroup_subsys_state *
-cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
-{
-	struct cgroup_cls_state *cs;
-
-	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
-	if (!cs)
-		return ERR_PTR(-ENOMEM);
-	return &cs->css;
-}
-
-static int cgrp_css_online(struct cgroup_subsys_state *css)
-{
-	struct cgroup_cls_state *cs = css_cls_state(css);
-	struct cgroup_cls_state *parent = css_cls_state(css_parent(css));
-
-	if (parent)
-		cs->classid = parent->classid;
-	return 0;
-}
-
-static void cgrp_css_free(struct cgroup_subsys_state *css)
-{
-	kfree(css_cls_state(css));
-}
-
-static int update_classid(const void *v, struct file *file, unsigned n)
-{
-	int err;
-	struct socket *sock = sock_from_file(file, &err);
-	if (sock)
-		sock->sk->sk_classid = (u32)(unsigned long)v;
-	return 0;
-}
-
-static void cgrp_attach(struct cgroup_subsys_state *css,
-			struct cgroup_taskset *tset)
-{
-	struct task_struct *p;
-	struct cgroup_cls_state *cs = css_cls_state(css);
-	void *v = (void *)(unsigned long)cs->classid;
-
-	cgroup_taskset_for_each(p, css, tset) {
-		task_lock(p);
-		iterate_fd(p->files, 0, update_classid, v);
-		task_unlock(p);
-	}
-}
-
-static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
-{
-	return css_cls_state(css)->classid;
-}
-
-static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
-			 u64 value)
-{
-	css_cls_state(css)->classid = (u32) value;
-	return 0;
-}
-
-static struct cftype ss_files[] = {
-	{
-		.name = "classid",
-		.read_u64 = read_classid,
-		.write_u64 = write_classid,
-	},
-	{ }	/* terminate */
-};
-
-struct cgroup_subsys net_cls_subsys = {
-	.name		= "net_cls",
-	.css_alloc	= cgrp_css_alloc,
-	.css_online	= cgrp_css_online,
-	.css_free	= cgrp_css_free,
-	.attach		= cgrp_attach,
-	.subsys_id	= net_cls_subsys_id,
-	.base_cftypes	= ss_files,
-	.module		= THIS_MODULE,
-};
-
 struct cls_cgroup_head {
 	u32			handle;
 	struct tcf_exts		exts;
@@ -172,11 +76,6 @@ static int cls_cgroup_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static const struct tcf_ext_map cgroup_ext_map = {
-	.action = TCA_CGROUP_ACT,
-	.police = TCA_CGROUP_POLICE,
-};
-
 static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
 	[TCA_CGROUP_EMATCHES]	= { .type = NLA_NESTED },
 };
@@ -184,7 +83,7 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
 static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 			     struct tcf_proto *tp, unsigned long base,
 			     u32 handle, struct nlattr **tca,
-			     unsigned long *arg)
+			     unsigned long *arg, bool ovr)
 {
 	struct nlattr *tb[TCA_CGROUP_MAX + 1];
 	struct cls_cgroup_head *head = tp->root;
@@ -203,6 +102,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 		if (head == NULL)
 			return -ENOBUFS;
 
+		tcf_exts_init(&head->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
 		head->handle = handle;
 
 		tcf_tree_lock(tp);
@@ -218,8 +118,8 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 	if (err < 0)
 		return err;
 
-	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e,
-				&cgroup_ext_map);
+	tcf_exts_init(&e, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
+	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -264,7 +164,7 @@ skip:
 	arg->count++;
 }
 
-static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh,
+static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 			   struct sk_buff *skb, struct tcmsg *t)
 {
 	struct cls_cgroup_head *head = tp->root;
@@ -277,13 +177,13 @@ static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh,
 	if (nest == NULL)
 		goto nla_put_failure;
 
-	if (tcf_exts_dump(skb, &head->exts, &cgroup_ext_map) < 0 ||
+	if (tcf_exts_dump(skb, &head->exts) < 0 ||
 	    tcf_em_tree_dump(skb, &head->ematches, TCA_CGROUP_EMATCHES) < 0)
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 
-	if (tcf_exts_dump_stats(skb, &head->exts, &cgroup_ext_map) < 0)
+	if (tcf_exts_dump_stats(skb, &head->exts) < 0)
 		goto nla_put_failure;
 
 	return skb->len;
@@ -309,25 +209,12 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = {
 
 static int __init init_cgroup_cls(void)
 {
-	int ret;
-
-	ret = cgroup_load_subsys(&net_cls_subsys);
-	if (ret)
-		goto out;
-
-	ret = register_tcf_proto_ops(&cls_cgroup_ops);
-	if (ret)
-		cgroup_unload_subsys(&net_cls_subsys);
-
-out:
-	return ret;
+	return register_tcf_proto_ops(&cls_cgroup_ops);
 }
 
 static void __exit exit_cgroup_cls(void)
 {
 	unregister_tcf_proto_ops(&cls_cgroup_ops);
-
-	cgroup_unload_subsys(&net_cls_subsys);
 }
 
 module_init(init_cgroup_cls);
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 7881e2fccbc..35be16f7c19 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -56,11 +56,6 @@ struct flow_filter {
 	u32			hashrnd;
 };
 
-static const struct tcf_ext_map flow_ext_map = {
-	.action	= TCA_FLOW_ACT,
-	.police	= TCA_FLOW_POLICE,
-};
-
 static inline u32 addr_fold(void *addr)
 {
 	unsigned long a = (unsigned long)addr;
@@ -220,7 +215,7 @@ static u32 flow_get_vlan_tag(const struct sk_buff *skb)
 
 static u32 flow_get_rxhash(struct sk_buff *skb)
 {
-	return skb_get_rxhash(skb);
+	return skb_get_hash(skb);
 }
 
 static u32 flow_key_get(struct sk_buff *skb, int key, struct flow_keys *flow)
@@ -354,7 +349,7 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = {
 static int flow_change(struct net *net, struct sk_buff *in_skb,
 		       struct tcf_proto *tp, unsigned long base,
 		       u32 handle, struct nlattr **tca,
-		       unsigned long *arg)
+		       unsigned long *arg, bool ovr)
 {
 	struct flow_head *head = tp->root;
 	struct flow_filter *f;
@@ -397,7 +392,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 			return -EOPNOTSUPP;
 	}
 
-	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &flow_ext_map);
+	tcf_exts_init(&e, TCA_FLOW_ACT, TCA_FLOW_POLICE);
+	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -455,6 +451,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 
 		f->handle = handle;
 		f->mask	  = ~0U;
+		tcf_exts_init(&f->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
 
 		get_random_bytes(&f->hashrnd, 4);
 		f->perturb_timer.function = flow_perturbation;
@@ -566,7 +563,7 @@ static void flow_put(struct tcf_proto *tp, unsigned long f)
 {
 }
 
-static int flow_dump(struct tcf_proto *tp, unsigned long fh,
+static int flow_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		     struct sk_buff *skb, struct tcmsg *t)
 {
 	struct flow_filter *f = (struct flow_filter *)fh;
@@ -608,7 +605,7 @@ static int flow_dump(struct tcf_proto *tp, unsigned long fh,
 	    nla_put_u32(skb, TCA_FLOW_PERTURB, f->perturb_period / HZ))
 		goto nla_put_failure;
 
-	if (tcf_exts_dump(skb, &f->exts, &flow_ext_map) < 0)
+	if (tcf_exts_dump(skb, &f->exts) < 0)
 		goto nla_put_failure;
 #ifdef CONFIG_NET_EMATCH
 	if (f->ematches.hdr.nmatches &&
@@ -617,7 +614,7 @@ static int flow_dump(struct tcf_proto *tp, unsigned long fh,
 #endif
 	nla_nest_end(skb, nest);
 
-	if (tcf_exts_dump_stats(skb, &f->exts, &flow_ext_map) < 0)
+	if (tcf_exts_dump_stats(skb, &f->exts) < 0)
 		goto nla_put_failure;
 
 	return skb->len;
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 9b97172db84..861b03ccfed 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -29,11 +29,11 @@
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
 
-#define HTSIZE (PAGE_SIZE/sizeof(struct fw_filter *))
+#define HTSIZE 256
 
 struct fw_head {
-	struct fw_filter *ht[HTSIZE];
-	u32 mask;
+	u32			mask;
+	struct fw_filter	*ht[HTSIZE];
 };
 
 struct fw_filter {
@@ -41,46 +41,22 @@ struct fw_filter {
 	u32			id;
 	struct tcf_result	res;
 #ifdef CONFIG_NET_CLS_IND
-	char			indev[IFNAMSIZ];
+	int			ifindex;
 #endif /* CONFIG_NET_CLS_IND */
 	struct tcf_exts		exts;
 };
 
-static const struct tcf_ext_map fw_ext_map = {
-	.action = TCA_FW_ACT,
-	.police = TCA_FW_POLICE
-};
-
-static inline int fw_hash(u32 handle)
+static u32 fw_hash(u32 handle)
 {
-	if (HTSIZE == 4096)
-		return ((handle >> 24) & 0xFFF) ^
-		       ((handle >> 12) & 0xFFF) ^
-		       (handle & 0xFFF);
-	else if (HTSIZE == 2048)
-		return ((handle >> 22) & 0x7FF) ^
-		       ((handle >> 11) & 0x7FF) ^
-		       (handle & 0x7FF);
-	else if (HTSIZE == 1024)
-		return ((handle >> 20) & 0x3FF) ^
-		       ((handle >> 10) & 0x3FF) ^
-		       (handle & 0x3FF);
-	else if (HTSIZE == 512)
-		return (handle >> 27) ^
-		       ((handle >> 18) & 0x1FF) ^
-		       ((handle >> 9) & 0x1FF) ^
-		       (handle & 0x1FF);
-	else if (HTSIZE == 256) {
-		u8 *t = (u8 *) &handle;
-		return t[0] ^ t[1] ^ t[2] ^ t[3];
-	} else
-		return handle & (HTSIZE - 1);
+	handle ^= (handle >> 16);
+	handle ^= (handle >> 8);
+	return handle % HTSIZE;
 }
 
 static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			  struct tcf_result *res)
 {
-	struct fw_head *head = (struct fw_head *)tp->root;
+	struct fw_head *head = tp->root;
 	struct fw_filter *f;
 	int r;
 	u32 id = skb->mark;
@@ -91,7 +67,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			if (f->id == id) {
 				*res = f->res;
 #ifdef CONFIG_NET_CLS_IND
-				if (!tcf_match_indev(skb, f->indev))
+				if (!tcf_match_indev(skb, f->ifindex))
 					continue;
 #endif /* CONFIG_NET_CLS_IND */
 				r = tcf_exts_exec(skb, &f->exts, res);
@@ -116,7 +92,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 
 static unsigned long fw_get(struct tcf_proto *tp, u32 handle)
 {
-	struct fw_head *head = (struct fw_head *)tp->root;
+	struct fw_head *head = tp->root;
 	struct fw_filter *f;
 
 	if (head == NULL)
@@ -165,7 +141,7 @@ static void fw_destroy(struct tcf_proto *tp)
 
 static int fw_delete(struct tcf_proto *tp, unsigned long arg)
 {
-	struct fw_head *head = (struct fw_head *)tp->root;
+	struct fw_head *head = tp->root;
 	struct fw_filter *f = (struct fw_filter *)arg;
 	struct fw_filter **fp;
 
@@ -193,14 +169,15 @@ static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = {
 
 static int
 fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f,
-	struct nlattr **tb, struct nlattr **tca, unsigned long base)
+	struct nlattr **tb, struct nlattr **tca, unsigned long base, bool ovr)
 {
-	struct fw_head *head = (struct fw_head *)tp->root;
+	struct fw_head *head = tp->root;
 	struct tcf_exts e;
 	u32 mask;
 	int err;
 
-	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &fw_ext_map);
+	tcf_exts_init(&e, TCA_FW_ACT, TCA_FW_POLICE);
+	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -211,9 +188,13 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f,
 
 #ifdef CONFIG_NET_CLS_IND
 	if (tb[TCA_FW_INDEV]) {
-		err = tcf_change_indev(tp, f->indev, tb[TCA_FW_INDEV]);
-		if (err < 0)
+		int ret;
+		ret = tcf_change_indev(net, tb[TCA_FW_INDEV]);
+		if (ret < 0) {
+			err = ret;
 			goto errout;
+		}
+		f->ifindex = ret;
 	}
 #endif /* CONFIG_NET_CLS_IND */
 
@@ -237,9 +218,9 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 		     struct tcf_proto *tp, unsigned long base,
 		     u32 handle,
 		     struct nlattr **tca,
-		     unsigned long *arg)
+		     unsigned long *arg, bool ovr)
 {
-	struct fw_head *head = (struct fw_head *)tp->root;
+	struct fw_head *head = tp->root;
 	struct fw_filter *f = (struct fw_filter *) *arg;
 	struct nlattr *opt = tca[TCA_OPTIONS];
 	struct nlattr *tb[TCA_FW_MAX + 1];
@@ -255,7 +236,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	if (f != NULL) {
 		if (f->id != handle && handle)
 			return -EINVAL;
-		return fw_change_attrs(net, tp, f, tb, tca, base);
+		return fw_change_attrs(net, tp, f, tb, tca, base, ovr);
 	}
 
 	if (!handle)
@@ -280,9 +261,10 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	if (f == NULL)
 		return -ENOBUFS;
 
+	tcf_exts_init(&f->exts, TCA_FW_ACT, TCA_FW_POLICE);
 	f->id = handle;
 
-	err = fw_change_attrs(net, tp, f, tb, tca, base);
+	err = fw_change_attrs(net, tp, f, tb, tca, base, ovr);
 	if (err < 0)
 		goto errout;
 
@@ -301,7 +283,7 @@ errout:
 
 static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 {
-	struct fw_head *head = (struct fw_head *)tp->root;
+	struct fw_head *head = tp->root;
 	int h;
 
 	if (head == NULL)
@@ -327,10 +309,10 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 	}
 }
 
-static int fw_dump(struct tcf_proto *tp, unsigned long fh,
+static int fw_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		   struct sk_buff *skb, struct tcmsg *t)
 {
-	struct fw_head *head = (struct fw_head *)tp->root;
+	struct fw_head *head = tp->root;
 	struct fw_filter *f = (struct fw_filter *)fh;
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
@@ -351,20 +333,23 @@ static int fw_dump(struct tcf_proto *tp, unsigned long fh,
 	    nla_put_u32(skb, TCA_FW_CLASSID, f->res.classid))
 		goto nla_put_failure;
 #ifdef CONFIG_NET_CLS_IND
-	if (strlen(f->indev) &&
-	    nla_put_string(skb, TCA_FW_INDEV, f->indev))
-		goto nla_put_failure;
+	if (f->ifindex) {
+		struct net_device *dev;
+		dev = __dev_get_by_index(net, f->ifindex);
+		if (dev && nla_put_string(skb, TCA_FW_INDEV, dev->name))
+			goto nla_put_failure;
+	}
 #endif /* CONFIG_NET_CLS_IND */
 	if (head->mask != 0xFFFFFFFF &&
 	    nla_put_u32(skb, TCA_FW_MASK, head->mask))
 		goto nla_put_failure;
 
-	if (tcf_exts_dump(skb, &f->exts, &fw_ext_map) < 0)
+	if (tcf_exts_dump(skb, &f->exts) < 0)
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 
-	if (tcf_exts_dump_stats(skb, &f->exts, &fw_ext_map) < 0)
+	if (tcf_exts_dump_stats(skb, &f->exts) < 0)
 		goto nla_put_failure;
 
 	return skb->len;
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 37da567d833..dd9fc2523c7 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -59,11 +59,6 @@ struct route4_filter {
 
 #define ROUTE4_FAILURE ((struct route4_filter *)(-1L))
 
-static const struct tcf_ext_map route_ext_map = {
-	.police = TCA_ROUTE4_POLICE,
-	.action = TCA_ROUTE4_ACT
-};
-
 static inline int route4_fastmap_hash(u32 id, int iif)
 {
 	return id & 0xF;
@@ -128,7 +123,7 @@ static inline int route4_hash_wild(void)
 static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			   struct tcf_result *res)
 {
-	struct route4_head *head = (struct route4_head *)tp->root;
+	struct route4_head *head = tp->root;
 	struct dst_entry *dst;
 	struct route4_bucket *b;
 	struct route4_filter *f;
@@ -218,7 +213,7 @@ static inline u32 from_hash(u32 id)
 
 static unsigned long route4_get(struct tcf_proto *tp, u32 handle)
 {
-	struct route4_head *head = (struct route4_head *)tp->root;
+	struct route4_head *head = tp->root;
 	struct route4_bucket *b;
 	struct route4_filter *f;
 	unsigned int h1, h2;
@@ -289,7 +284,7 @@ static void route4_destroy(struct tcf_proto *tp)
 
 static int route4_delete(struct tcf_proto *tp, unsigned long arg)
 {
-	struct route4_head *head = (struct route4_head *)tp->root;
+	struct route4_head *head = tp->root;
 	struct route4_filter **fp, *f = (struct route4_filter *)arg;
 	unsigned int h = 0;
 	struct route4_bucket *b;
@@ -338,7 +333,8 @@ static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = {
 static int route4_set_parms(struct net *net, struct tcf_proto *tp,
 			    unsigned long base, struct route4_filter *f,
 			    u32 handle, struct route4_head *head,
-			    struct nlattr **tb, struct nlattr *est, int new)
+			    struct nlattr **tb, struct nlattr *est, int new,
+			    bool ovr)
 {
 	int err;
 	u32 id = 0, to = 0, nhandle = 0x8000;
@@ -347,7 +343,8 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
 	struct route4_bucket *b;
 	struct tcf_exts e;
 
-	err = tcf_exts_validate(net, tp, tb, est, &e, &route_ext_map);
+	tcf_exts_init(&e, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE);
+	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -432,7 +429,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 		       struct tcf_proto *tp, unsigned long base,
 		       u32 handle,
 		       struct nlattr **tca,
-		       unsigned long *arg)
+		       unsigned long *arg, bool ovr)
 {
 	struct route4_head *head = tp->root;
 	struct route4_filter *f, *f1, **fp;
@@ -459,7 +456,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 			old_handle = f->handle;
 
 		err = route4_set_parms(net, tp, base, f, handle, head, tb,
-			tca[TCA_RATE], 0);
+			tca[TCA_RATE], 0, ovr);
 		if (err < 0)
 			return err;
 
@@ -481,8 +478,9 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 	if (f == NULL)
 		goto errout;
 
+	tcf_exts_init(&f->exts, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE);
 	err = route4_set_parms(net, tp, base, f, handle, head, tb,
-		tca[TCA_RATE], 1);
+		tca[TCA_RATE], 1, ovr);
 	if (err < 0)
 		goto errout;
 
@@ -554,7 +552,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 	}
 }
 
-static int route4_dump(struct tcf_proto *tp, unsigned long fh,
+static int route4_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		       struct sk_buff *skb, struct tcmsg *t)
 {
 	struct route4_filter *f = (struct route4_filter *)fh;
@@ -589,12 +587,12 @@ static int route4_dump(struct tcf_proto *tp, unsigned long fh,
 	    nla_put_u32(skb, TCA_ROUTE4_CLASSID, f->res.classid))
 		goto nla_put_failure;
 
-	if (tcf_exts_dump(skb, &f->exts, &route_ext_map) < 0)
+	if (tcf_exts_dump(skb, &f->exts) < 0)
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 
-	if (tcf_exts_dump_stats(skb, &f->exts, &route_ext_map) < 0)
+	if (tcf_exts_dump_stats(skb, &f->exts) < 0)
 		goto nla_put_failure;
 
 	return skb->len;
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 252d8b05872..1020e233a5d 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -116,11 +116,6 @@ static inline unsigned int hash_src(__be32 *src)
 	return h & 0xF;
 }
 
-static struct tcf_ext_map rsvp_ext_map = {
-	.police = TCA_RSVP_POLICE,
-	.action = TCA_RSVP_ACT
-};
-
 #define RSVP_APPLY_RESULT()				\
 {							\
 	int r = tcf_exts_exec(skb, &f->exts, res);	\
@@ -420,7 +415,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
 		       struct tcf_proto *tp, unsigned long base,
 		       u32 handle,
 		       struct nlattr **tca,
-		       unsigned long *arg)
+		       unsigned long *arg, bool ovr)
 {
 	struct rsvp_head *data = tp->root;
 	struct rsvp_filter *f, **fp;
@@ -440,7 +435,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
 	if (err < 0)
 		return err;
 
-	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &rsvp_ext_map);
+	tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE);
+	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -471,6 +467,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
 	if (f == NULL)
 		goto errout2;
 
+	tcf_exts_init(&f->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE);
 	h2 = 16;
 	if (tb[TCA_RSVP_SRC]) {
 		memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src));
@@ -597,7 +594,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 	}
 }
 
-static int rsvp_dump(struct tcf_proto *tp, unsigned long fh,
+static int rsvp_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		     struct sk_buff *skb, struct tcmsg *t)
 {
 	struct rsvp_filter *f = (struct rsvp_filter *)fh;
@@ -633,12 +630,12 @@ static int rsvp_dump(struct tcf_proto *tp, unsigned long fh,
 	    nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src))
 		goto nla_put_failure;
 
-	if (tcf_exts_dump(skb, &f->exts, &rsvp_ext_map) < 0)
+	if (tcf_exts_dump(skb, &f->exts) < 0)
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 
-	if (tcf_exts_dump_stats(skb, &f->exts, &rsvp_ext_map) < 0)
+	if (tcf_exts_dump_stats(skb, &f->exts) < 0)
 		goto nla_put_failure;
 	return skb->len;
 
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index b86535a4016..c721cd4a469 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -24,9 +24,6 @@
 #define DEFAULT_HASH_SIZE	64	/* optimized for diffserv */
 
 
-#define	PRIV(tp)	((struct tcindex_data *) (tp)->root)
-
-
 struct tcindex_filter_result {
 	struct tcf_exts		exts;
 	struct tcf_result	res;
@@ -50,11 +47,6 @@ struct tcindex_data {
 	int fall_through;	/* 0: only classify if explicit match */
 };
 
-static const struct tcf_ext_map tcindex_ext_map = {
-	.police = TCA_TCINDEX_POLICE,
-	.action = TCA_TCINDEX_ACT
-};
-
 static inline int
 tcindex_filter_is_set(struct tcindex_filter_result *r)
 {
@@ -82,7 +74,7 @@ tcindex_lookup(struct tcindex_data *p, u16 key)
 static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			    struct tcf_result *res)
 {
-	struct tcindex_data *p = PRIV(tp);
+	struct tcindex_data *p = tp->root;
 	struct tcindex_filter_result *f;
 	int key = (skb->tc_index & p->mask) >> p->shift;
 
@@ -107,7 +99,7 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 
 static unsigned long tcindex_get(struct tcf_proto *tp, u32 handle)
 {
-	struct tcindex_data *p = PRIV(tp);
+	struct tcindex_data *p = tp->root;
 	struct tcindex_filter_result *r;
 
 	pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle);
@@ -145,7 +137,7 @@ static int tcindex_init(struct tcf_proto *tp)
 static int
 __tcindex_delete(struct tcf_proto *tp, unsigned long arg, int lock)
 {
-	struct tcindex_data *p = PRIV(tp);
+	struct tcindex_data *p = tp->root;
 	struct tcindex_filter_result *r = (struct tcindex_filter_result *) arg;
 	struct tcindex_filter *f = NULL;
 
@@ -196,11 +188,17 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
 	[TCA_TCINDEX_CLASSID]		= { .type = NLA_U32 },
 };
 
+static void tcindex_filter_result_init(struct tcindex_filter_result *r)
+{
+	memset(r, 0, sizeof(*r));
+	tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+}
+
 static int
 tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		  u32 handle, struct tcindex_data *p,
 		  struct tcindex_filter_result *r, struct nlattr **tb,
-		 struct nlattr *est)
+		  struct nlattr *est, bool ovr)
 {
 	int err, balloc = 0;
 	struct tcindex_filter_result new_filter_result, *old_r = r;
@@ -209,17 +207,17 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	struct tcindex_filter *f = NULL; /* make gcc behave */
 	struct tcf_exts e;
 
-	err = tcf_exts_validate(net, tp, tb, est, &e, &tcindex_ext_map);
+	tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
 	if (err < 0)
 		return err;
 
 	memcpy(&cp, p, sizeof(cp));
-	memset(&new_filter_result, 0, sizeof(new_filter_result));
+	tcindex_filter_result_init(&new_filter_result);
 
+	tcindex_filter_result_init(&cr);
 	if (old_r)
-		memcpy(&cr, r, sizeof(cr));
-	else
-		memset(&cr, 0, sizeof(cr));
+		cr.res = r->res;
 
 	if (tb[TCA_TCINDEX_HASH])
 		cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -271,9 +269,14 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	err = -ENOMEM;
 	if (!cp.perfect && !cp.h) {
 		if (valid_perfect_hash(&cp)) {
+			int i;
+
 			cp.perfect = kcalloc(cp.hash, sizeof(*r), GFP_KERNEL);
 			if (!cp.perfect)
 				goto errout;
+			for (i = 0; i < cp.hash; i++)
+				tcf_exts_init(&cp.perfect[i].exts, TCA_TCINDEX_ACT,
+					      TCA_TCINDEX_POLICE);
 			balloc = 1;
 		} else {
 			cp.h = kcalloc(cp.hash, sizeof(f), GFP_KERNEL);
@@ -299,14 +302,17 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		tcf_bind_filter(tp, &cr.res, base);
 	}
 
-	tcf_exts_change(tp, &cr.exts, &e);
+	if (old_r)
+		tcf_exts_change(tp, &r->exts, &e);
+	else
+		tcf_exts_change(tp, &cr.exts, &e);
 
 	tcf_tree_lock(tp);
 	if (old_r && old_r != r)
-		memset(old_r, 0, sizeof(*old_r));
+		tcindex_filter_result_init(old_r);
 
 	memcpy(p, &cp, sizeof(cp));
-	memcpy(r, &cr, sizeof(cr));
+	r->res = cr.res;
 
 	if (r == &new_filter_result) {
 		struct tcindex_filter **fp;
@@ -335,11 +341,11 @@ errout:
 static int
 tcindex_change(struct net *net, struct sk_buff *in_skb,
 	       struct tcf_proto *tp, unsigned long base, u32 handle,
-	       struct nlattr **tca, unsigned long *arg)
+	       struct nlattr **tca, unsigned long *arg, bool ovr)
 {
 	struct nlattr *opt = tca[TCA_OPTIONS];
 	struct nlattr *tb[TCA_TCINDEX_MAX + 1];
-	struct tcindex_data *p = PRIV(tp);
+	struct tcindex_data *p = tp->root;
 	struct tcindex_filter_result *r = (struct tcindex_filter_result *) *arg;
 	int err;
 
@@ -355,13 +361,13 @@ tcindex_change(struct net *net, struct sk_buff *in_skb,
 		return err;
 
 	return tcindex_set_parms(net, tp, base, handle, p, r, tb,
-				 tca[TCA_RATE]);
+				 tca[TCA_RATE], ovr);
 }
 
 
 static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker)
 {
-	struct tcindex_data *p = PRIV(tp);
+	struct tcindex_data *p = tp->root;
 	struct tcindex_filter *f, *next;
 	int i;
 
@@ -408,7 +414,7 @@ static int tcindex_destroy_element(struct tcf_proto *tp,
 
 static void tcindex_destroy(struct tcf_proto *tp)
 {
-	struct tcindex_data *p = PRIV(tp);
+	struct tcindex_data *p = tp->root;
 	struct tcf_walker walker;
 
 	pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
@@ -423,10 +429,10 @@ static void tcindex_destroy(struct tcf_proto *tp)
 }
 
 
-static int tcindex_dump(struct tcf_proto *tp, unsigned long fh,
+static int tcindex_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
     struct sk_buff *skb, struct tcmsg *t)
 {
-	struct tcindex_data *p = PRIV(tp);
+	struct tcindex_data *p = tp->root;
 	struct tcindex_filter_result *r = (struct tcindex_filter_result *) fh;
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
@@ -468,11 +474,11 @@ static int tcindex_dump(struct tcf_proto *tp, unsigned long fh,
 		    nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid))
 			goto nla_put_failure;
 
-		if (tcf_exts_dump(skb, &r->exts, &tcindex_ext_map) < 0)
+		if (tcf_exts_dump(skb, &r->exts) < 0)
 			goto nla_put_failure;
 		nla_nest_end(skb, nest);
 
-		if (tcf_exts_dump_stats(skb, &r->exts, &tcindex_ext_map) < 0)
+		if (tcf_exts_dump_stats(skb, &r->exts) < 0)
 			goto nla_put_failure;
 	}
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index eb07a1e536e..70c0be8d012 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -38,6 +38,7 @@
 #include <linux/errno.h>
 #include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
+#include <linux/bitmap.h>
 #include <net/netlink.h>
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
@@ -48,7 +49,7 @@ struct tc_u_knode {
 	struct tc_u_hnode	*ht_up;
 	struct tcf_exts		exts;
 #ifdef CONFIG_NET_CLS_IND
-	char                     indev[IFNAMSIZ];
+	int			ifindex;
 #endif
 	u8			fshift;
 	struct tcf_result	res;
@@ -79,11 +80,6 @@ struct tc_u_common {
 	u32			hgenerator;
 };
 
-static const struct tcf_ext_map u32_ext_map = {
-	.action = TCA_U32_ACT,
-	.police = TCA_U32_POLICE
-};
-
 static inline unsigned int u32_hash_fold(__be32 key,
 					 const struct tc_u32_sel *sel,
 					 u8 fshift)
@@ -100,7 +96,7 @@ static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct
 		unsigned int	  off;
 	} stack[TC_U32_MAXDEPTH];
 
-	struct tc_u_hnode *ht = (struct tc_u_hnode *)tp->root;
+	struct tc_u_hnode *ht = tp->root;
 	unsigned int off = skb_network_offset(skb);
 	struct tc_u_knode *n;
 	int sdepth = 0;
@@ -157,7 +153,7 @@ check_terminal:
 
 				*res = n->res;
 #ifdef CONFIG_NET_CLS_IND
-				if (!tcf_match_indev(skb, n->indev)) {
+				if (!tcf_match_indev(skb, n->ifindex)) {
 					n = n->next;
 					goto next_knode;
 				}
@@ -352,7 +348,7 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n)
 	return 0;
 }
 
-static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode* key)
+static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 {
 	struct tc_u_knode **kp;
 	struct tc_u_hnode *ht = key->ht_up;
@@ -465,17 +461,25 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg)
 	return 0;
 }
 
+#define NR_U32_NODE (1<<12)
 static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle)
 {
 	struct tc_u_knode *n;
-	unsigned int i = 0x7FF;
+	unsigned long i;
+	unsigned long *bitmap = kzalloc(BITS_TO_LONGS(NR_U32_NODE) * sizeof(unsigned long),
+					GFP_KERNEL);
+	if (!bitmap)
+		return handle | 0xFFF;
 
 	for (n = ht->ht[TC_U32_HASH(handle)]; n; n = n->next)
-		if (i < TC_U32_NODE(n->handle))
-			i = TC_U32_NODE(n->handle);
-	i++;
+		set_bit(TC_U32_NODE(n->handle), bitmap);
+
+	i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800);
+	if (i >= NR_U32_NODE)
+		i = find_next_zero_bit(bitmap, NR_U32_NODE, 1);
 
-	return handle | (i > 0xFFF ? 0xFFF : i);
+	kfree(bitmap);
+	return handle | (i >= NR_U32_NODE ? 0xFFF : i);
 }
 
 static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
@@ -491,12 +495,13 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
 static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 			 unsigned long base, struct tc_u_hnode *ht,
 			 struct tc_u_knode *n, struct nlattr **tb,
-			 struct nlattr *est)
+			 struct nlattr *est, bool ovr)
 {
 	int err;
 	struct tcf_exts e;
 
-	err = tcf_exts_validate(net, tp, tb, est, &e, &u32_ext_map);
+	tcf_exts_init(&e, TCA_U32_ACT, TCA_U32_POLICE);
+	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -531,9 +536,11 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 
 #ifdef CONFIG_NET_CLS_IND
 	if (tb[TCA_U32_INDEV]) {
-		err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV]);
-		if (err < 0)
+		int ret;
+		ret = tcf_change_indev(net, tb[TCA_U32_INDEV]);
+		if (ret < 0)
 			goto errout;
+		n->ifindex = ret;
 	}
 #endif
 	tcf_exts_change(tp, &n->exts, &e);
@@ -547,7 +554,7 @@ errout:
 static int u32_change(struct net *net, struct sk_buff *in_skb,
 		      struct tcf_proto *tp, unsigned long base, u32 handle,
 		      struct nlattr **tca,
-		      unsigned long *arg)
+		      unsigned long *arg, bool ovr)
 {
 	struct tc_u_common *tp_c = tp->data;
 	struct tc_u_hnode *ht;
@@ -571,7 +578,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 
 		return u32_set_parms(net, tp, base, n->ht_up, n, tb,
-				     tca[TCA_RATE]);
+				     tca[TCA_RATE], ovr);
 	}
 
 	if (tb[TCA_U32_DIVISOR]) {
@@ -646,6 +653,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	n->ht_up = ht;
 	n->handle = handle;
 	n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0;
+	tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE);
 
 #ifdef CONFIG_CLS_U32_MARK
 	if (tb[TCA_U32_MARK]) {
@@ -657,7 +665,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	}
 #endif
 
-	err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE]);
+	err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr);
 	if (err == 0) {
 		struct tc_u_knode **ins;
 		for (ins = &ht->ht[TC_U32_HASH(handle)]; *ins; ins = &(*ins)->next)
@@ -715,7 +723,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 	}
 }
 
-static int u32_dump(struct tcf_proto *tp, unsigned long fh,
+static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		     struct sk_buff *skb, struct tcmsg *t)
 {
 	struct tc_u_knode *n = (struct tc_u_knode *)fh;
@@ -759,13 +767,16 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh,
 			goto nla_put_failure;
 #endif
 
-		if (tcf_exts_dump(skb, &n->exts, &u32_ext_map) < 0)
+		if (tcf_exts_dump(skb, &n->exts) < 0)
 			goto nla_put_failure;
 
 #ifdef CONFIG_NET_CLS_IND
-		if (strlen(n->indev) &&
-		    nla_put_string(skb, TCA_U32_INDEV, n->indev))
-			goto nla_put_failure;
+		if (n->ifindex) {
+			struct net_device *dev;
+			dev = __dev_get_by_index(net, n->ifindex);
+			if (dev && nla_put_string(skb, TCA_U32_INDEV, dev->name))
+				goto nla_put_failure;
+		}
 #endif
 #ifdef CONFIG_CLS_U32_PERF
 		if (nla_put(skb, TCA_U32_PCNT,
@@ -778,7 +789,7 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh,
 	nla_nest_end(skb, nest);
 
 	if (TC_U32_KEY(n->handle))
-		if (tcf_exts_dump_stats(skb, &n->exts, &u32_ext_map) < 0)
+		if (tcf_exts_dump_stats(skb, &n->exts) < 0)
 			goto nla_put_failure;
 	return skb->len;
 
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index e5cef956722..9b8c0b0e60d 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -222,7 +222,7 @@ META_COLLECTOR(int_maclen)
 
 META_COLLECTOR(int_rxhash)
 {
-	dst->value = skb_get_rxhash(skb);
+	dst->value = skb_get_hash(skb);
 }
 
 /**************************************************************************
@@ -271,40 +271,52 @@ META_COLLECTOR(int_rtiif)
  * Socket Attributes
  **************************************************************************/
 
-#define SKIP_NONLOCAL(skb)			\
-	if (unlikely(skb->sk == NULL)) {	\
-		*err = -1;			\
-		return;				\
-	}
+#define skip_nonlocal(skb) \
+	(unlikely(skb->sk == NULL))
 
 META_COLLECTOR(int_sk_family)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_family;
 }
 
 META_COLLECTOR(int_sk_state)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_state;
 }
 
 META_COLLECTOR(int_sk_reuse)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_reuse;
 }
 
 META_COLLECTOR(int_sk_bound_if)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	/* No error if bound_dev_if is 0, legal userspace check */
 	dst->value = skb->sk->sk_bound_dev_if;
 }
 
 META_COLLECTOR(var_sk_bound_if)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 
 	if (skb->sk->sk_bound_dev_if == 0) {
 		dst->value = (unsigned long) "any";
@@ -322,151 +334,226 @@ META_COLLECTOR(var_sk_bound_if)
 
 META_COLLECTOR(int_sk_refcnt)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = atomic_read(&skb->sk->sk_refcnt);
 }
 
 META_COLLECTOR(int_sk_rcvbuf)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_rcvbuf;
 }
 
 META_COLLECTOR(int_sk_shutdown)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_shutdown;
 }
 
 META_COLLECTOR(int_sk_proto)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_protocol;
 }
 
 META_COLLECTOR(int_sk_type)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_type;
 }
 
 META_COLLECTOR(int_sk_rmem_alloc)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = sk_rmem_alloc_get(skb->sk);
 }
 
 META_COLLECTOR(int_sk_wmem_alloc)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = sk_wmem_alloc_get(skb->sk);
 }
 
 META_COLLECTOR(int_sk_omem_alloc)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = atomic_read(&skb->sk->sk_omem_alloc);
 }
 
 META_COLLECTOR(int_sk_rcv_qlen)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_receive_queue.qlen;
 }
 
 META_COLLECTOR(int_sk_snd_qlen)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_write_queue.qlen;
 }
 
 META_COLLECTOR(int_sk_wmem_queued)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_wmem_queued;
 }
 
 META_COLLECTOR(int_sk_fwd_alloc)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_forward_alloc;
 }
 
 META_COLLECTOR(int_sk_sndbuf)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_sndbuf;
 }
 
 META_COLLECTOR(int_sk_alloc)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = (__force int) skb->sk->sk_allocation;
 }
 
 META_COLLECTOR(int_sk_hash)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_hash;
 }
 
 META_COLLECTOR(int_sk_lingertime)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_lingertime / HZ;
 }
 
 META_COLLECTOR(int_sk_err_qlen)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_error_queue.qlen;
 }
 
 META_COLLECTOR(int_sk_ack_bl)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_ack_backlog;
 }
 
 META_COLLECTOR(int_sk_max_ack_bl)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_max_ack_backlog;
 }
 
 META_COLLECTOR(int_sk_prio)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_priority;
 }
 
 META_COLLECTOR(int_sk_rcvlowat)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_rcvlowat;
 }
 
 META_COLLECTOR(int_sk_rcvtimeo)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_rcvtimeo / HZ;
 }
 
 META_COLLECTOR(int_sk_sndtimeo)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_sndtimeo / HZ;
 }
 
 META_COLLECTOR(int_sk_sendmsg_off)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_frag.offset;
 }
 
 META_COLLECTOR(int_sk_write_pend)
 {
-	SKIP_NONLOCAL(skb);
+	if (skip_nonlocal(skb)) {
+		*err = -1;
+		return;
+	}
 	dst->value = skb->sk->sk_write_pending;
 }
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 547b4a88ae2..58bed7599db 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -135,7 +135,7 @@ static DEFINE_RWLOCK(qdisc_mod_lock);
 
 static struct Qdisc_ops *qdisc_base;
 
-/* Register/uregister queueing discipline */
+/* Register/unregister queueing discipline */
 
 int register_qdisc(struct Qdisc_ops *qops)
 {
@@ -273,8 +273,12 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
 
 void qdisc_list_add(struct Qdisc *q)
 {
-	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
-		list_add_tail(&q->list, &qdisc_dev(q)->qdisc->list);
+	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+		struct Qdisc *root = qdisc_dev(q)->qdisc;
+
+		WARN_ON_ONCE(root == &noop_qdisc);
+		list_add_tail(&q->list, &root->list);
+	}
 }
 EXPORT_SYMBOL(qdisc_list_add);
 
@@ -559,7 +563,7 @@ out:
 }
 EXPORT_SYMBOL(__qdisc_calculate_pkt_len);
 
-void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc)
+void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc)
 {
 	if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
 		pr_warn("%s: %s qdisc %X: is non-work-conserving?\n",
@@ -1080,7 +1084,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 	struct Qdisc *p = NULL;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETQDISC) &&
+	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
@@ -1147,7 +1152,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 	struct Qdisc *q, *p;
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
@@ -1300,6 +1305,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 	struct gnet_dump d;
 	struct qdisc_size_table *stab;
 
+	cond_resched();
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
 	if (!nlh)
 		goto out_nlmsg_trim;
@@ -1431,9 +1437,9 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
 	s_idx = cb->args[0];
 	s_q_idx = q_idx = cb->args[1];
 
-	rcu_read_lock();
 	idx = 0;
-	for_each_netdev_rcu(net, dev) {
+	ASSERT_RTNL();
+	for_each_netdev(net, dev) {
 		struct netdev_queue *dev_queue;
 
 		if (idx < s_idx)
@@ -1456,8 +1462,6 @@ cont:
 	}
 
 done:
-	rcu_read_unlock();
-
 	cb->args[0] = idx;
 	cb->args[1] = q_idx;
 
@@ -1487,7 +1491,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n)
 	u32 qid;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTCLASS) &&
+	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
@@ -1614,6 +1619,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q,
 	struct gnet_dump d;
 	const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops;
 
+	cond_resched();
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
 	if (!nlh)
 		goto out_nlmsg_trim;
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 1f9c31411f1..8449b337f9e 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -623,8 +623,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl,
 		if (nla_put_u32(skb, TCA_ATM_EXCESS, 0))
 			goto nla_put_failure;
 	}
-	nla_nest_end(skb, nest);
-	return skb->len;
+	return nla_nest_end(skb, nest);
 
 nla_put_failure:
 	nla_nest_cancel(skb, nest);
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 7a42c81a19e..ead526467cc 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1058,9 +1058,10 @@ static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio)
 				cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/
 					q->quanta[prio];
 			}
-			if (cl->quantum <= 0 || cl->quantum>32*qdisc_dev(cl->qdisc)->mtu) {
-				pr_warning("CBQ: class %08x has bad quantum==%ld, repaired.\n",
-					   cl->common.classid, cl->quantum);
+			if (cl->quantum <= 0 ||
+			    cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) {
+				pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n",
+					cl->common.classid, cl->quantum);
 				cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1;
 			}
 		}
@@ -1562,8 +1563,7 @@ static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb)
 		goto nla_put_failure;
 	if (cbq_dump_attr(skb, &q->link) < 0)
 		goto nla_put_failure;
-	nla_nest_end(skb, nest);
-	return skb->len;
+	return nla_nest_end(skb, nest);
 
 nla_put_failure:
 	nla_nest_cancel(skb, nest);
@@ -1598,8 +1598,7 @@ cbq_dump_class(struct Qdisc *sch, unsigned long arg,
 		goto nla_put_failure;
 	if (cbq_dump_attr(skb, cl) < 0)
 		goto nla_put_failure;
-	nla_nest_end(skb, nest);
-	return skb->len;
+	return nla_nest_end(skb, nest);
 
 nla_put_failure:
 	nla_nest_cancel(skb, nest);
@@ -1782,8 +1781,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 						    qdisc_root_sleeping_lock(sch),
 						    tca[TCA_RATE]);
 			if (err) {
-				if (rtab)
-					qdisc_put_rtab(rtab);
+				qdisc_put_rtab(rtab);
 				return err;
 			}
 		}
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index ddd73cb2d7b..ed30e436128 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -14,7 +14,6 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
-#include <linux/reciprocal_div.h>
 #include <linux/vmalloc.h>
 #include <net/pkt_sched.h>
 #include <net/inet_ecn.h>
@@ -77,12 +76,6 @@ struct choke_sched_data {
 	struct sk_buff **tab;
 };
 
-/* deliver a random number between 0 and N - 1 */
-static u32 random_N(unsigned int N)
-{
-	return reciprocal_divide(prandom_u32(), N);
-}
-
 /* number of elements in queue including holes */
 static unsigned int choke_len(const struct choke_sched_data *q)
 {
@@ -233,7 +226,7 @@ static struct sk_buff *choke_peek_random(const struct choke_sched_data *q,
 	int retrys = 3;
 
 	do {
-		*pidx = (q->head + random_N(choke_len(q))) & q->tab_mask;
+		*pidx = (q->head + prandom_u32_max(choke_len(q))) & q->tab_mask;
 		skb = q->tab[*pidx];
 		if (skb)
 			return skb;
@@ -398,12 +391,7 @@ static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = {
 
 static void choke_free(void *addr)
 {
-	if (addr) {
-		if (is_vmalloc_addr(addr))
-			vfree(addr);
-		else
-			kfree(addr);
-	}
+	kvfree(addr);
 }
 
 static int choke_change(struct Qdisc *sch, struct nlattr *opt)
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 8302717ea30..7bbbfe11219 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -391,8 +391,10 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)
 	while (1) {
 		cl = list_first_entry(&q->active, struct drr_class, alist);
 		skb = cl->qdisc->ops->peek(cl->qdisc);
-		if (skb == NULL)
+		if (skb == NULL) {
+			qdisc_warn_nonwc(__func__, cl->qdisc);
 			goto out;
+		}
 
 		len = qdisc_pkt_len(skb);
 		if (len <= cl->deficit) {
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 3886365cc20..49d6ef338b5 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -47,7 +47,7 @@ struct dsmark_qdisc_data {
 
 static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index)
 {
-	return (index <= p->indices && index > 0);
+	return index <= p->indices && index > 0;
 }
 
 /* ------------------------- Class/flow operations ------------------------- */
@@ -57,8 +57,8 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg,
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 
-	pr_debug("dsmark_graft(sch %p,[qdisc %p],new %p,old %p)\n",
-		sch, p, new, old);
+	pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n",
+		 __func__, sch, p, new, old);
 
 	if (new == NULL) {
 		new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
@@ -85,8 +85,8 @@ static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg)
 
 static unsigned long dsmark_get(struct Qdisc *sch, u32 classid)
 {
-	pr_debug("dsmark_get(sch %p,[qdisc %p],classid %x)\n",
-		sch, qdisc_priv(sch), classid);
+	pr_debug("%s(sch %p,[qdisc %p],classid %x)\n",
+		 __func__, sch, qdisc_priv(sch), classid);
 
 	return TC_H_MIN(classid) + 1;
 }
@@ -118,8 +118,8 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent,
 	int err = -EINVAL;
 	u8 mask = 0;
 
-	pr_debug("dsmark_change(sch %p,[qdisc %p],classid %x,parent %x),"
-		"arg 0x%lx\n", sch, p, classid, parent, *arg);
+	pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n",
+		 __func__, sch, p, classid, parent, *arg);
 
 	if (!dsmark_valid_index(p, *arg)) {
 		err = -ENOENT;
@@ -166,7 +166,8 @@ static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 	int i;
 
-	pr_debug("dsmark_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker);
+	pr_debug("%s(sch %p,[qdisc %p],walker %p)\n",
+		 __func__, sch, p, walker);
 
 	if (walker->stop)
 		return;
@@ -199,7 +200,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 	int err;
 
-	pr_debug("dsmark_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p);
+	pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p);
 
 	if (p->set_tc_index) {
 		switch (skb->protocol) {
@@ -275,7 +276,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 	struct sk_buff *skb;
 	u32 index;
 
-	pr_debug("dsmark_dequeue(sch %p,[qdisc %p])\n", sch, p);
+	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 
 	skb = p->q->ops->dequeue(p->q);
 	if (skb == NULL)
@@ -303,8 +304,8 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		 * and don't need yet another qdisc as a bypass.
 		 */
 		if (p->mask[index] != 0xff || p->value[index])
-			pr_warning("dsmark_dequeue: unsupported protocol %d\n",
-				   ntohs(skb->protocol));
+			pr_warn("%s: unsupported protocol %d\n",
+				__func__, ntohs(skb->protocol));
 		break;
 	}
 
@@ -315,7 +316,7 @@ static struct sk_buff *dsmark_peek(struct Qdisc *sch)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 
-	pr_debug("dsmark_peek(sch %p,[qdisc %p])\n", sch, p);
+	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 
 	return p->q->ops->peek(p->q);
 }
@@ -325,7 +326,7 @@ static unsigned int dsmark_drop(struct Qdisc *sch)
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 	unsigned int len;
 
-	pr_debug("dsmark_reset(sch %p,[qdisc %p])\n", sch, p);
+	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 
 	if (p->q->ops->drop == NULL)
 		return 0;
@@ -346,7 +347,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 	u16 indices;
 	u8 *mask;
 
-	pr_debug("dsmark_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt);
+	pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt);
 
 	if (!opt)
 		goto errout;
@@ -384,7 +385,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 	if (p->q == NULL)
 		p->q = &noop_qdisc;
 
-	pr_debug("dsmark_init: qdisc %p\n", p->q);
+	pr_debug("%s: qdisc %p\n", __func__, p->q);
 
 	err = 0;
 errout:
@@ -395,7 +396,7 @@ static void dsmark_reset(struct Qdisc *sch)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 
-	pr_debug("dsmark_reset(sch %p,[qdisc %p])\n", sch, p);
+	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 	qdisc_reset(p->q);
 	sch->q.qlen = 0;
 }
@@ -404,7 +405,7 @@ static void dsmark_destroy(struct Qdisc *sch)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 
-	pr_debug("dsmark_destroy(sch %p,[qdisc %p])\n", sch, p);
+	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 
 	tcf_destroy_chain(&p->filter_list);
 	qdisc_destroy(p->q);
@@ -417,7 +418,7 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl,
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 	struct nlattr *opts = NULL;
 
-	pr_debug("dsmark_dump_class(sch %p,[qdisc %p],class %ld\n", sch, p, cl);
+	pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl);
 
 	if (!dsmark_valid_index(p, cl))
 		return -EINVAL;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 95d84396190..ba32c2b005d 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -47,6 +47,7 @@
 #include <linux/rbtree.h>
 #include <linux/hash.h>
 #include <linux/prefetch.h>
+#include <linux/vmalloc.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/sock.h>
@@ -225,7 +226,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 		/* By forcing low order bit to 1, we make sure to not
 		 * collide with a local flow (socket pointers are word aligned)
 		 */
-		sk = (struct sock *)(skb_get_rxhash(skb) | 1L);
+		sk = (struct sock *)(skb_get_hash(skb) | 1L);
 	}
 
 	root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)];
@@ -578,28 +579,53 @@ static void fq_rehash(struct fq_sched_data *q,
 	q->stat_gc_flows += fcnt;
 }
 
-static int fq_resize(struct fq_sched_data *q, u32 log)
+static void *fq_alloc_node(size_t sz, int node)
 {
+	void *ptr;
+
+	ptr = kmalloc_node(sz, GFP_KERNEL | __GFP_REPEAT | __GFP_NOWARN, node);
+	if (!ptr)
+		ptr = vmalloc_node(sz, node);
+	return ptr;
+}
+
+static void fq_free(void *addr)
+{
+	kvfree(addr);
+}
+
+static int fq_resize(struct Qdisc *sch, u32 log)
+{
+	struct fq_sched_data *q = qdisc_priv(sch);
 	struct rb_root *array;
+	void *old_fq_root;
 	u32 idx;
 
 	if (q->fq_root && log == q->fq_trees_log)
 		return 0;
 
-	array = kmalloc(sizeof(struct rb_root) << log, GFP_KERNEL);
+	/* If XPS was setup, we can allocate memory on right NUMA node */
+	array = fq_alloc_node(sizeof(struct rb_root) << log,
+			      netdev_queue_numa_node_read(sch->dev_queue));
 	if (!array)
 		return -ENOMEM;
 
 	for (idx = 0; idx < (1U << log); idx++)
 		array[idx] = RB_ROOT;
 
-	if (q->fq_root) {
-		fq_rehash(q, q->fq_root, q->fq_trees_log, array, log);
-		kfree(q->fq_root);
-	}
+	sch_tree_lock(sch);
+
+	old_fq_root = q->fq_root;
+	if (old_fq_root)
+		fq_rehash(q, old_fq_root, q->fq_trees_log, array, log);
+
 	q->fq_root = array;
 	q->fq_trees_log = log;
 
+	sch_tree_unlock(sch);
+
+	fq_free(old_fq_root);
+
 	return 0;
 }
 
@@ -675,9 +701,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 		q->flow_refill_delay = usecs_to_jiffies(usecs_delay);
 	}
 
-	if (!err)
-		err = fq_resize(q, fq_log);
-
+	if (!err) {
+		sch_tree_unlock(sch);
+		err = fq_resize(sch, fq_log);
+		sch_tree_lock(sch);
+	}
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = fq_dequeue(sch);
 
@@ -697,7 +725,7 @@ static void fq_destroy(struct Qdisc *sch)
 	struct fq_sched_data *q = qdisc_priv(sch);
 
 	fq_reset(sch);
-	kfree(q->fq_root);
+	fq_free(q->fq_root);
 	qdisc_watchdog_cancel(&q->watchdog);
 }
 
@@ -723,7 +751,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt)
 	if (opt)
 		err = fq_change(sch, opt);
 	else
-		err = fq_resize(q, q->fq_trees_log);
+		err = fq_resize(sch, q->fq_trees_log);
 
 	return err;
 }
@@ -750,8 +778,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	    nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log))
 		goto nla_put_failure;
 
-	nla_nest_end(skb, opts);
-	return skb->len;
+	return nla_nest_end(skb, opts);
 
 nla_put_failure:
 	return -1;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 55786283a3d..063b726bf1f 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -365,12 +365,7 @@ static void *fq_codel_zalloc(size_t sz)
 
 static void fq_codel_free(void *addr)
 {
-	if (addr) {
-		if (is_vmalloc_addr(addr))
-			vfree(addr);
-		else
-			kfree(addr);
-	}
+	kvfree(addr);
 }
 
 static void fq_codel_destroy(struct Qdisc *sch)
@@ -390,7 +385,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt)
 	sch->limit = 10*1024;
 	q->flows_cnt = 1024;
 	q->quantum = psched_mtu(qdisc_dev(sch));
-	q->perturbation = net_random();
+	q->perturbation = prandom_u32();
 	INIT_LIST_HEAD(&q->new_flows);
 	INIT_LIST_HEAD(&q->old_flows);
 	codel_params_init(&q->cparams);
@@ -450,8 +445,7 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
 			q->flows_cnt))
 		goto nla_put_failure;
 
-	nla_nest_end(skb, opts);
-	return skb->len;
+	return nla_nest_end(skb, opts);
 
 nla_put_failure:
 	return -1;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 922a09406ba..e1543b03e39 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -126,7 +126,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_stopped(txq))
-		ret = dev_hard_start_xmit(skb, dev, txq, NULL);
+		ret = dev_hard_start_xmit(skb, dev, txq);
 
 	HARD_TX_UNLOCK(dev, txq);
 
@@ -310,6 +310,7 @@ void netif_carrier_on(struct net_device *dev)
 	if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
 		if (dev->reg_state == NETREG_UNINITIALIZED)
 			return;
+		atomic_inc(&dev->carrier_changes);
 		linkwatch_fire_event(dev);
 		if (netif_running(dev))
 			__netdev_watchdog_up(dev);
@@ -328,6 +329,7 @@ void netif_carrier_off(struct net_device *dev)
 	if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
 		if (dev->reg_state == NETREG_UNINITIALIZED)
 			return;
+		atomic_inc(&dev->carrier_changes);
 		linkwatch_fire_event(dev);
 	}
 }
@@ -338,13 +340,13 @@ EXPORT_SYMBOL(netif_carrier_off);
    cheaper.
  */
 
-static int noop_enqueue(struct sk_buff *skb, struct Qdisc * qdisc)
+static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
 {
 	kfree_skb(skb);
 	return NET_XMIT_CN;
 }
 
-static struct sk_buff *noop_dequeue(struct Qdisc * qdisc)
+static struct sk_buff *noop_dequeue(struct Qdisc *qdisc)
 {
 	return NULL;
 }
@@ -718,8 +720,8 @@ static void attach_default_qdiscs(struct net_device *dev)
 	} else {
 		qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT);
 		if (qdisc) {
-			qdisc->ops->attach(qdisc);
 			dev->qdisc = qdisc;
+			qdisc->ops->attach(qdisc);
 		}
 	}
 }
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index d42234c0f13..12cbc09157f 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -370,8 +370,8 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps)
 
 	for (i = table->DPs; i < MAX_DPs; i++) {
 		if (table->tab[i]) {
-			pr_warning("GRED: Warning: Destroying "
-				   "shadowed VQ 0x%x\n", i);
+			pr_warn("GRED: Warning: Destroying shadowed VQ 0x%x\n",
+				i);
 			gred_destroy_vq(table->tab[i]);
 			table->tab[i] = NULL;
 		}
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index c4075610502..ec8aeaac1dd 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1353,8 +1353,7 @@ hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb,
 		goto nla_put_failure;
 	if (hfsc_dump_curves(skb, cl) < 0)
 		goto nla_put_failure;
-	nla_nest_end(skb, nest);
-	return skb->len;
+	return nla_nest_end(skb, nest);
 
  nla_put_failure:
 	nla_nest_cancel(skb, nest);
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
new file mode 100644
index 00000000000..d85b6812a7d
--- /dev/null
+++ b/net/sched/sch_hhf.c
@@ -0,0 +1,740 @@
+/* net/sched/sch_hhf.c		Heavy-Hitter Filter (HHF)
+ *
+ * Copyright (C) 2013 Terry Lam <vtlam@google.com>
+ * Copyright (C) 2013 Nandita Dukkipati <nanditad@google.com>
+ */
+
+#include <linux/jhash.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/vmalloc.h>
+#include <net/flow_keys.h>
+#include <net/pkt_sched.h>
+#include <net/sock.h>
+
+/*	Heavy-Hitter Filter (HHF)
+ *
+ * Principles :
+ * Flows are classified into two buckets: non-heavy-hitter and heavy-hitter
+ * buckets. Initially, a new flow starts as non-heavy-hitter. Once classified
+ * as heavy-hitter, it is immediately switched to the heavy-hitter bucket.
+ * The buckets are dequeued by a Weighted Deficit Round Robin (WDRR) scheduler,
+ * in which the heavy-hitter bucket is served with less weight.
+ * In other words, non-heavy-hitters (e.g., short bursts of critical traffic)
+ * are isolated from heavy-hitters (e.g., persistent bulk traffic) and also have
+ * higher share of bandwidth.
+ *
+ * To capture heavy-hitters, we use the "multi-stage filter" algorithm in the
+ * following paper:
+ * [EV02] C. Estan and G. Varghese, "New Directions in Traffic Measurement and
+ * Accounting", in ACM SIGCOMM, 2002.
+ *
+ * Conceptually, a multi-stage filter comprises k independent hash functions
+ * and k counter arrays. Packets are indexed into k counter arrays by k hash
+ * functions, respectively. The counters are then increased by the packet sizes.
+ * Therefore,
+ *    - For a heavy-hitter flow: *all* of its k array counters must be large.
+ *    - For a non-heavy-hitter flow: some of its k array counters can be large
+ *      due to hash collision with other small flows; however, with high
+ *      probability, not *all* k counters are large.
+ *
+ * By the design of the multi-stage filter algorithm, the false negative rate
+ * (heavy-hitters getting away uncaptured) is zero. However, the algorithm is
+ * susceptible to false positives (non-heavy-hitters mistakenly classified as
+ * heavy-hitters).
+ * Therefore, we also implement the following optimizations to reduce false
+ * positives by avoiding unnecessary increment of the counter values:
+ *    - Optimization O1: once a heavy-hitter is identified, its bytes are not
+ *        accounted in the array counters. This technique is called "shielding"
+ *        in Section 3.3.1 of [EV02].
+ *    - Optimization O2: conservative update of counters
+ *                       (Section 3.3.2 of [EV02]),
+ *        New counter value = max {old counter value,
+ *                                 smallest counter value + packet bytes}
+ *
+ * Finally, we refresh the counters periodically since otherwise the counter
+ * values will keep accumulating.
+ *
+ * Once a flow is classified as heavy-hitter, we also save its per-flow state
+ * in an exact-matching flow table so that its subsequent packets can be
+ * dispatched to the heavy-hitter bucket accordingly.
+ *
+ *
+ * At a high level, this qdisc works as follows:
+ * Given a packet p:
+ *   - If the flow-id of p (e.g., TCP 5-tuple) is already in the exact-matching
+ *     heavy-hitter flow table, denoted table T, then send p to the heavy-hitter
+ *     bucket.
+ *   - Otherwise, forward p to the multi-stage filter, denoted filter F
+ *        + If F decides that p belongs to a non-heavy-hitter flow, then send p
+ *          to the non-heavy-hitter bucket.
+ *        + Otherwise, if F decides that p belongs to a new heavy-hitter flow,
+ *          then set up a new flow entry for the flow-id of p in the table T and
+ *          send p to the heavy-hitter bucket.
+ *
+ * In this implementation:
+ *   - T is a fixed-size hash-table with 1024 entries. Hash collision is
+ *     resolved by linked-list chaining.
+ *   - F has four counter arrays, each array containing 1024 32-bit counters.
+ *     That means 4 * 1024 * 32 bits = 16KB of memory.
+ *   - Since each array in F contains 1024 counters, 10 bits are sufficient to
+ *     index into each array.
+ *     Hence, instead of having four hash functions, we chop the 32-bit
+ *     skb-hash into three 10-bit chunks, and the remaining 10-bit chunk is
+ *     computed as XOR sum of those three chunks.
+ *   - We need to clear the counter arrays periodically; however, directly
+ *     memsetting 16KB of memory can lead to cache eviction and unwanted delay.
+ *     So by representing each counter by a valid bit, we only need to reset
+ *     4K of 1 bit (i.e. 512 bytes) instead of 16KB of memory.
+ *   - The Deficit Round Robin engine is taken from fq_codel implementation
+ *     (net/sched/sch_fq_codel.c). Note that wdrr_bucket corresponds to
+ *     fq_codel_flow in fq_codel implementation.
+ *
+ */
+
+/* Non-configurable parameters */
+#define HH_FLOWS_CNT	 1024  /* number of entries in exact-matching table T */
+#define HHF_ARRAYS_CNT	 4     /* number of arrays in multi-stage filter F */
+#define HHF_ARRAYS_LEN	 1024  /* number of counters in each array of F */
+#define HHF_BIT_MASK_LEN 10    /* masking 10 bits */
+#define HHF_BIT_MASK	 0x3FF /* bitmask of 10 bits */
+
+#define WDRR_BUCKET_CNT  2     /* two buckets for Weighted DRR */
+enum wdrr_bucket_idx {
+	WDRR_BUCKET_FOR_HH	= 0, /* bucket id for heavy-hitters */
+	WDRR_BUCKET_FOR_NON_HH	= 1  /* bucket id for non-heavy-hitters */
+};
+
+#define hhf_time_before(a, b)	\
+	(typecheck(u32, a) && typecheck(u32, b) && ((s32)((a) - (b)) < 0))
+
+/* Heavy-hitter per-flow state */
+struct hh_flow_state {
+	u32		 hash_id;	/* hash of flow-id (e.g. TCP 5-tuple) */
+	u32		 hit_timestamp;	/* last time heavy-hitter was seen */
+	struct list_head flowchain;	/* chaining under hash collision */
+};
+
+/* Weighted Deficit Round Robin (WDRR) scheduler */
+struct wdrr_bucket {
+	struct sk_buff	  *head;
+	struct sk_buff	  *tail;
+	struct list_head  bucketchain;
+	int		  deficit;
+};
+
+struct hhf_sched_data {
+	struct wdrr_bucket buckets[WDRR_BUCKET_CNT];
+	u32		   perturbation;   /* hash perturbation */
+	u32		   quantum;        /* psched_mtu(qdisc_dev(sch)); */
+	u32		   drop_overlimit; /* number of times max qdisc packet
+					    * limit was hit
+					    */
+	struct list_head   *hh_flows;       /* table T (currently active HHs) */
+	u32		   hh_flows_limit;            /* max active HH allocs */
+	u32		   hh_flows_overlimit; /* num of disallowed HH allocs */
+	u32		   hh_flows_total_cnt;          /* total admitted HHs */
+	u32		   hh_flows_current_cnt;        /* total current HHs  */
+	u32		   *hhf_arrays[HHF_ARRAYS_CNT]; /* HH filter F */
+	u32		   hhf_arrays_reset_timestamp;  /* last time hhf_arrays
+							 * was reset
+							 */
+	unsigned long	   *hhf_valid_bits[HHF_ARRAYS_CNT]; /* shadow valid bits
+							     * of hhf_arrays
+							     */
+	/* Similar to the "new_flows" vs. "old_flows" concept in fq_codel DRR */
+	struct list_head   new_buckets; /* list of new buckets */
+	struct list_head   old_buckets; /* list of old buckets */
+
+	/* Configurable HHF parameters */
+	u32		   hhf_reset_timeout; /* interval to reset counter
+					       * arrays in filter F
+					       * (default 40ms)
+					       */
+	u32		   hhf_admit_bytes;   /* counter thresh to classify as
+					       * HH (default 128KB).
+					       * With these default values,
+					       * 128KB / 40ms = 25 Mbps
+					       * i.e., we expect to capture HHs
+					       * sending > 25 Mbps.
+					       */
+	u32		   hhf_evict_timeout; /* aging threshold to evict idle
+					       * HHs out of table T. This should
+					       * be large enough to avoid
+					       * reordering during HH eviction.
+					       * (default 1s)
+					       */
+	u32		   hhf_non_hh_weight; /* WDRR weight for non-HHs
+					       * (default 2,
+					       *  i.e., non-HH : HH = 2 : 1)
+					       */
+};
+
+static u32 hhf_time_stamp(void)
+{
+	return jiffies;
+}
+
+static unsigned int skb_hash(const struct hhf_sched_data *q,
+			     const struct sk_buff *skb)
+{
+	struct flow_keys keys;
+	unsigned int hash;
+
+	if (skb->sk && skb->sk->sk_hash)
+		return skb->sk->sk_hash;
+
+	skb_flow_dissect(skb, &keys);
+	hash = jhash_3words((__force u32)keys.dst,
+			    (__force u32)keys.src ^ keys.ip_proto,
+			    (__force u32)keys.ports, q->perturbation);
+	return hash;
+}
+
+/* Looks up a heavy-hitter flow in a chaining list of table T. */
+static struct hh_flow_state *seek_list(const u32 hash,
+				       struct list_head *head,
+				       struct hhf_sched_data *q)
+{
+	struct hh_flow_state *flow, *next;
+	u32 now = hhf_time_stamp();
+
+	if (list_empty(head))
+		return NULL;
+
+	list_for_each_entry_safe(flow, next, head, flowchain) {
+		u32 prev = flow->hit_timestamp + q->hhf_evict_timeout;
+
+		if (hhf_time_before(prev, now)) {
+			/* Delete expired heavy-hitters, but preserve one entry
+			 * to avoid kzalloc() when next time this slot is hit.
+			 */
+			if (list_is_last(&flow->flowchain, head))
+				return NULL;
+			list_del(&flow->flowchain);
+			kfree(flow);
+			q->hh_flows_current_cnt--;
+		} else if (flow->hash_id == hash) {
+			return flow;
+		}
+	}
+	return NULL;
+}
+
+/* Returns a flow state entry for a new heavy-hitter.  Either reuses an expired
+ * entry or dynamically alloc a new entry.
+ */
+static struct hh_flow_state *alloc_new_hh(struct list_head *head,
+					  struct hhf_sched_data *q)
+{
+	struct hh_flow_state *flow;
+	u32 now = hhf_time_stamp();
+
+	if (!list_empty(head)) {
+		/* Find an expired heavy-hitter flow entry. */
+		list_for_each_entry(flow, head, flowchain) {
+			u32 prev = flow->hit_timestamp + q->hhf_evict_timeout;
+
+			if (hhf_time_before(prev, now))
+				return flow;
+		}
+	}
+
+	if (q->hh_flows_current_cnt >= q->hh_flows_limit) {
+		q->hh_flows_overlimit++;
+		return NULL;
+	}
+	/* Create new entry. */
+	flow = kzalloc(sizeof(struct hh_flow_state), GFP_ATOMIC);
+	if (!flow)
+		return NULL;
+
+	q->hh_flows_current_cnt++;
+	INIT_LIST_HEAD(&flow->flowchain);
+	list_add_tail(&flow->flowchain, head);
+
+	return flow;
+}
+
+/* Assigns packets to WDRR buckets.  Implements a multi-stage filter to
+ * classify heavy-hitters.
+ */
+static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	u32 tmp_hash, hash;
+	u32 xorsum, filter_pos[HHF_ARRAYS_CNT], flow_pos;
+	struct hh_flow_state *flow;
+	u32 pkt_len, min_hhf_val;
+	int i;
+	u32 prev;
+	u32 now = hhf_time_stamp();
+
+	/* Reset the HHF counter arrays if this is the right time. */
+	prev = q->hhf_arrays_reset_timestamp + q->hhf_reset_timeout;
+	if (hhf_time_before(prev, now)) {
+		for (i = 0; i < HHF_ARRAYS_CNT; i++)
+			bitmap_zero(q->hhf_valid_bits[i], HHF_ARRAYS_LEN);
+		q->hhf_arrays_reset_timestamp = now;
+	}
+
+	/* Get hashed flow-id of the skb. */
+	hash = skb_hash(q, skb);
+
+	/* Check if this packet belongs to an already established HH flow. */
+	flow_pos = hash & HHF_BIT_MASK;
+	flow = seek_list(hash, &q->hh_flows[flow_pos], q);
+	if (flow) { /* found its HH flow */
+		flow->hit_timestamp = now;
+		return WDRR_BUCKET_FOR_HH;
+	}
+
+	/* Now pass the packet through the multi-stage filter. */
+	tmp_hash = hash;
+	xorsum = 0;
+	for (i = 0; i < HHF_ARRAYS_CNT - 1; i++) {
+		/* Split the skb_hash into three 10-bit chunks. */
+		filter_pos[i] = tmp_hash & HHF_BIT_MASK;
+		xorsum ^= filter_pos[i];
+		tmp_hash >>= HHF_BIT_MASK_LEN;
+	}
+	/* The last chunk is computed as XOR sum of other chunks. */
+	filter_pos[HHF_ARRAYS_CNT - 1] = xorsum ^ tmp_hash;
+
+	pkt_len = qdisc_pkt_len(skb);
+	min_hhf_val = ~0U;
+	for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+		u32 val;
+
+		if (!test_bit(filter_pos[i], q->hhf_valid_bits[i])) {
+			q->hhf_arrays[i][filter_pos[i]] = 0;
+			__set_bit(filter_pos[i], q->hhf_valid_bits[i]);
+		}
+
+		val = q->hhf_arrays[i][filter_pos[i]] + pkt_len;
+		if (min_hhf_val > val)
+			min_hhf_val = val;
+	}
+
+	/* Found a new HH iff all counter values > HH admit threshold. */
+	if (min_hhf_val > q->hhf_admit_bytes) {
+		/* Just captured a new heavy-hitter. */
+		flow = alloc_new_hh(&q->hh_flows[flow_pos], q);
+		if (!flow) /* memory alloc problem */
+			return WDRR_BUCKET_FOR_NON_HH;
+		flow->hash_id = hash;
+		flow->hit_timestamp = now;
+		q->hh_flows_total_cnt++;
+
+		/* By returning without updating counters in q->hhf_arrays,
+		 * we implicitly implement "shielding" (see Optimization O1).
+		 */
+		return WDRR_BUCKET_FOR_HH;
+	}
+
+	/* Conservative update of HHF arrays (see Optimization O2). */
+	for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+		if (q->hhf_arrays[i][filter_pos[i]] < min_hhf_val)
+			q->hhf_arrays[i][filter_pos[i]] = min_hhf_val;
+	}
+	return WDRR_BUCKET_FOR_NON_HH;
+}
+
+/* Removes one skb from head of bucket. */
+static struct sk_buff *dequeue_head(struct wdrr_bucket *bucket)
+{
+	struct sk_buff *skb = bucket->head;
+
+	bucket->head = skb->next;
+	skb->next = NULL;
+	return skb;
+}
+
+/* Tail-adds skb to bucket. */
+static void bucket_add(struct wdrr_bucket *bucket, struct sk_buff *skb)
+{
+	if (bucket->head == NULL)
+		bucket->head = skb;
+	else
+		bucket->tail->next = skb;
+	bucket->tail = skb;
+	skb->next = NULL;
+}
+
+static unsigned int hhf_drop(struct Qdisc *sch)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	struct wdrr_bucket *bucket;
+
+	/* Always try to drop from heavy-hitters first. */
+	bucket = &q->buckets[WDRR_BUCKET_FOR_HH];
+	if (!bucket->head)
+		bucket = &q->buckets[WDRR_BUCKET_FOR_NON_HH];
+
+	if (bucket->head) {
+		struct sk_buff *skb = dequeue_head(bucket);
+
+		sch->q.qlen--;
+		sch->qstats.drops++;
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		kfree_skb(skb);
+	}
+
+	/* Return id of the bucket from which the packet was dropped. */
+	return bucket - q->buckets;
+}
+
+static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	enum wdrr_bucket_idx idx;
+	struct wdrr_bucket *bucket;
+
+	idx = hhf_classify(skb, sch);
+
+	bucket = &q->buckets[idx];
+	bucket_add(bucket, skb);
+	sch->qstats.backlog += qdisc_pkt_len(skb);
+
+	if (list_empty(&bucket->bucketchain)) {
+		unsigned int weight;
+
+		/* The logic of new_buckets vs. old_buckets is the same as
+		 * new_flows vs. old_flows in the implementation of fq_codel,
+		 * i.e., short bursts of non-HHs should have strict priority.
+		 */
+		if (idx == WDRR_BUCKET_FOR_HH) {
+			/* Always move heavy-hitters to old bucket. */
+			weight = 1;
+			list_add_tail(&bucket->bucketchain, &q->old_buckets);
+		} else {
+			weight = q->hhf_non_hh_weight;
+			list_add_tail(&bucket->bucketchain, &q->new_buckets);
+		}
+		bucket->deficit = weight * q->quantum;
+	}
+	if (++sch->q.qlen <= sch->limit)
+		return NET_XMIT_SUCCESS;
+
+	q->drop_overlimit++;
+	/* Return Congestion Notification only if we dropped a packet from this
+	 * bucket.
+	 */
+	if (hhf_drop(sch) == idx)
+		return NET_XMIT_CN;
+
+	/* As we dropped a packet, better let upper stack know this. */
+	qdisc_tree_decrease_qlen(sch, 1);
+	return NET_XMIT_SUCCESS;
+}
+
+static struct sk_buff *hhf_dequeue(struct Qdisc *sch)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb = NULL;
+	struct wdrr_bucket *bucket;
+	struct list_head *head;
+
+begin:
+	head = &q->new_buckets;
+	if (list_empty(head)) {
+		head = &q->old_buckets;
+		if (list_empty(head))
+			return NULL;
+	}
+	bucket = list_first_entry(head, struct wdrr_bucket, bucketchain);
+
+	if (bucket->deficit <= 0) {
+		int weight = (bucket - q->buckets == WDRR_BUCKET_FOR_HH) ?
+			      1 : q->hhf_non_hh_weight;
+
+		bucket->deficit += weight * q->quantum;
+		list_move_tail(&bucket->bucketchain, &q->old_buckets);
+		goto begin;
+	}
+
+	if (bucket->head) {
+		skb = dequeue_head(bucket);
+		sch->q.qlen--;
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
+	}
+
+	if (!skb) {
+		/* Force a pass through old_buckets to prevent starvation. */
+		if ((head == &q->new_buckets) && !list_empty(&q->old_buckets))
+			list_move_tail(&bucket->bucketchain, &q->old_buckets);
+		else
+			list_del_init(&bucket->bucketchain);
+		goto begin;
+	}
+	qdisc_bstats_update(sch, skb);
+	bucket->deficit -= qdisc_pkt_len(skb);
+
+	return skb;
+}
+
+static void hhf_reset(struct Qdisc *sch)
+{
+	struct sk_buff *skb;
+
+	while ((skb = hhf_dequeue(sch)) != NULL)
+		kfree_skb(skb);
+}
+
+static void *hhf_zalloc(size_t sz)
+{
+	void *ptr = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN);
+
+	if (!ptr)
+		ptr = vzalloc(sz);
+
+	return ptr;
+}
+
+static void hhf_free(void *addr)
+{
+	kvfree(addr);
+}
+
+static void hhf_destroy(struct Qdisc *sch)
+{
+	int i;
+	struct hhf_sched_data *q = qdisc_priv(sch);
+
+	for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+		hhf_free(q->hhf_arrays[i]);
+		hhf_free(q->hhf_valid_bits[i]);
+	}
+
+	for (i = 0; i < HH_FLOWS_CNT; i++) {
+		struct hh_flow_state *flow, *next;
+		struct list_head *head = &q->hh_flows[i];
+
+		if (list_empty(head))
+			continue;
+		list_for_each_entry_safe(flow, next, head, flowchain) {
+			list_del(&flow->flowchain);
+			kfree(flow);
+		}
+	}
+	hhf_free(q->hh_flows);
+}
+
+static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = {
+	[TCA_HHF_BACKLOG_LIMIT]	 = { .type = NLA_U32 },
+	[TCA_HHF_QUANTUM]	 = { .type = NLA_U32 },
+	[TCA_HHF_HH_FLOWS_LIMIT] = { .type = NLA_U32 },
+	[TCA_HHF_RESET_TIMEOUT]	 = { .type = NLA_U32 },
+	[TCA_HHF_ADMIT_BYTES]	 = { .type = NLA_U32 },
+	[TCA_HHF_EVICT_TIMEOUT]	 = { .type = NLA_U32 },
+	[TCA_HHF_NON_HH_WEIGHT]	 = { .type = NLA_U32 },
+};
+
+static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tb[TCA_HHF_MAX + 1];
+	unsigned int qlen;
+	int err;
+	u64 non_hh_quantum;
+	u32 new_quantum = q->quantum;
+	u32 new_hhf_non_hh_weight = q->hhf_non_hh_weight;
+
+	if (!opt)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_HHF_MAX, opt, hhf_policy);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_HHF_QUANTUM])
+		new_quantum = nla_get_u32(tb[TCA_HHF_QUANTUM]);
+
+	if (tb[TCA_HHF_NON_HH_WEIGHT])
+		new_hhf_non_hh_weight = nla_get_u32(tb[TCA_HHF_NON_HH_WEIGHT]);
+
+	non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight;
+	if (non_hh_quantum > INT_MAX)
+		return -EINVAL;
+
+	sch_tree_lock(sch);
+
+	if (tb[TCA_HHF_BACKLOG_LIMIT])
+		sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]);
+
+	q->quantum = new_quantum;
+	q->hhf_non_hh_weight = new_hhf_non_hh_weight;
+
+	if (tb[TCA_HHF_HH_FLOWS_LIMIT])
+		q->hh_flows_limit = nla_get_u32(tb[TCA_HHF_HH_FLOWS_LIMIT]);
+
+	if (tb[TCA_HHF_RESET_TIMEOUT]) {
+		u32 us = nla_get_u32(tb[TCA_HHF_RESET_TIMEOUT]);
+
+		q->hhf_reset_timeout = usecs_to_jiffies(us);
+	}
+
+	if (tb[TCA_HHF_ADMIT_BYTES])
+		q->hhf_admit_bytes = nla_get_u32(tb[TCA_HHF_ADMIT_BYTES]);
+
+	if (tb[TCA_HHF_EVICT_TIMEOUT]) {
+		u32 us = nla_get_u32(tb[TCA_HHF_EVICT_TIMEOUT]);
+
+		q->hhf_evict_timeout = usecs_to_jiffies(us);
+	}
+
+	qlen = sch->q.qlen;
+	while (sch->q.qlen > sch->limit) {
+		struct sk_buff *skb = hhf_dequeue(sch);
+
+		kfree_skb(skb);
+	}
+	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+
+	sch_tree_unlock(sch);
+	return 0;
+}
+
+static int hhf_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	int i;
+
+	sch->limit = 1000;
+	q->quantum = psched_mtu(qdisc_dev(sch));
+	q->perturbation = prandom_u32();
+	INIT_LIST_HEAD(&q->new_buckets);
+	INIT_LIST_HEAD(&q->old_buckets);
+
+	/* Configurable HHF parameters */
+	q->hhf_reset_timeout = HZ / 25; /* 40  ms */
+	q->hhf_admit_bytes = 131072;    /* 128 KB */
+	q->hhf_evict_timeout = HZ;      /* 1  sec */
+	q->hhf_non_hh_weight = 2;
+
+	if (opt) {
+		int err = hhf_change(sch, opt);
+
+		if (err)
+			return err;
+	}
+
+	if (!q->hh_flows) {
+		/* Initialize heavy-hitter flow table. */
+		q->hh_flows = hhf_zalloc(HH_FLOWS_CNT *
+					 sizeof(struct list_head));
+		if (!q->hh_flows)
+			return -ENOMEM;
+		for (i = 0; i < HH_FLOWS_CNT; i++)
+			INIT_LIST_HEAD(&q->hh_flows[i]);
+
+		/* Cap max active HHs at twice len of hh_flows table. */
+		q->hh_flows_limit = 2 * HH_FLOWS_CNT;
+		q->hh_flows_overlimit = 0;
+		q->hh_flows_total_cnt = 0;
+		q->hh_flows_current_cnt = 0;
+
+		/* Initialize heavy-hitter filter arrays. */
+		for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+			q->hhf_arrays[i] = hhf_zalloc(HHF_ARRAYS_LEN *
+						      sizeof(u32));
+			if (!q->hhf_arrays[i]) {
+				hhf_destroy(sch);
+				return -ENOMEM;
+			}
+		}
+		q->hhf_arrays_reset_timestamp = hhf_time_stamp();
+
+		/* Initialize valid bits of heavy-hitter filter arrays. */
+		for (i = 0; i < HHF_ARRAYS_CNT; i++) {
+			q->hhf_valid_bits[i] = hhf_zalloc(HHF_ARRAYS_LEN /
+							  BITS_PER_BYTE);
+			if (!q->hhf_valid_bits[i]) {
+				hhf_destroy(sch);
+				return -ENOMEM;
+			}
+		}
+
+		/* Initialize Weighted DRR buckets. */
+		for (i = 0; i < WDRR_BUCKET_CNT; i++) {
+			struct wdrr_bucket *bucket = q->buckets + i;
+
+			INIT_LIST_HEAD(&bucket->bucketchain);
+		}
+	}
+
+	return 0;
+}
+
+static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts;
+
+	opts = nla_nest_start(skb, TCA_OPTIONS);
+	if (opts == NULL)
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_HHF_BACKLOG_LIMIT, sch->limit) ||
+	    nla_put_u32(skb, TCA_HHF_QUANTUM, q->quantum) ||
+	    nla_put_u32(skb, TCA_HHF_HH_FLOWS_LIMIT, q->hh_flows_limit) ||
+	    nla_put_u32(skb, TCA_HHF_RESET_TIMEOUT,
+			jiffies_to_usecs(q->hhf_reset_timeout)) ||
+	    nla_put_u32(skb, TCA_HHF_ADMIT_BYTES, q->hhf_admit_bytes) ||
+	    nla_put_u32(skb, TCA_HHF_EVICT_TIMEOUT,
+			jiffies_to_usecs(q->hhf_evict_timeout)) ||
+	    nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, q->hhf_non_hh_weight))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, opts);
+
+nla_put_failure:
+	return -1;
+}
+
+static int hhf_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct hhf_sched_data *q = qdisc_priv(sch);
+	struct tc_hhf_xstats st = {
+		.drop_overlimit = q->drop_overlimit,
+		.hh_overlimit	= q->hh_flows_overlimit,
+		.hh_tot_count	= q->hh_flows_total_cnt,
+		.hh_cur_count	= q->hh_flows_current_cnt,
+	};
+
+	return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+static struct Qdisc_ops hhf_qdisc_ops __read_mostly = {
+	.id		=	"hhf",
+	.priv_size	=	sizeof(struct hhf_sched_data),
+
+	.enqueue	=	hhf_enqueue,
+	.dequeue	=	hhf_dequeue,
+	.peek		=	qdisc_peek_dequeued,
+	.drop		=	hhf_drop,
+	.init		=	hhf_init,
+	.reset		=	hhf_reset,
+	.destroy	=	hhf_destroy,
+	.change		=	hhf_change,
+	.dump		=	hhf_dump,
+	.dump_stats	=	hhf_dump_stats,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init hhf_module_init(void)
+{
+	return register_qdisc(&hhf_qdisc_ops);
+}
+
+static void __exit hhf_module_exit(void)
+{
+	unregister_qdisc(&hhf_qdisc_ops);
+}
+
+module_init(hhf_module_init)
+module_exit(hhf_module_exit)
+MODULE_AUTHOR("Terry Lam");
+MODULE_AUTHOR("Nandita Dukkipati");
+MODULE_LICENSE("GPL");
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 0e1e38b4002..9f949abcace 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -219,11 +219,16 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
 	if (skb->priority == sch->handle)
 		return HTB_DIRECT;	/* X:0 (direct flow) selected */
 	cl = htb_find(skb->priority, sch);
-	if (cl && cl->level == 0)
-		return cl;
+	if (cl) {
+		if (cl->level == 0)
+			return cl;
+		/* Start with inner filter chain if a non-leaf class is selected */
+		tcf = cl->filter_list;
+	} else {
+		tcf = q->filter_list;
+	}
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	tcf = q->filter_list;
 	while (tcf && (result = tc_classify(skb, tcf, &res)) >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -712,7 +717,7 @@ static s64 htb_do_events(struct htb_sched *q, const int level,
 
 	/* too much load - let's continue after a break for scheduling */
 	if (!(q->warned & HTB_WARN_TOOMANYEVENTS)) {
-		pr_warning("htb: too many events!\n");
+		pr_warn("htb: too many events!\n");
 		q->warned |= HTB_WARN_TOOMANYEVENTS;
 	}
 
@@ -1057,12 +1062,13 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt)
 
 static int htb_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
-	spinlock_t *root_lock = qdisc_root_sleeping_lock(sch);
 	struct htb_sched *q = qdisc_priv(sch);
 	struct nlattr *nest;
 	struct tc_htb_glob gopt;
 
-	spin_lock_bh(root_lock);
+	/* Its safe to not acquire qdisc lock. As we hold RTNL,
+	 * no change can happen on the qdisc parameters.
+	 */
 
 	gopt.direct_pkts = q->direct_pkts;
 	gopt.version = HTB_VER;
@@ -1076,13 +1082,10 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) ||
 	    nla_put_u32(skb, TCA_HTB_DIRECT_QLEN, q->direct_qlen))
 		goto nla_put_failure;
-	nla_nest_end(skb, nest);
 
-	spin_unlock_bh(root_lock);
-	return skb->len;
+	return nla_nest_end(skb, nest);
 
 nla_put_failure:
-	spin_unlock_bh(root_lock);
 	nla_nest_cancel(skb, nest);
 	return -1;
 }
@@ -1091,11 +1094,12 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg,
 			  struct sk_buff *skb, struct tcmsg *tcm)
 {
 	struct htb_class *cl = (struct htb_class *)arg;
-	spinlock_t *root_lock = qdisc_root_sleeping_lock(sch);
 	struct nlattr *nest;
 	struct tc_htb_opt opt;
 
-	spin_lock_bh(root_lock);
+	/* Its safe to not acquire qdisc lock. As we hold RTNL,
+	 * no change can happen on the class parameters.
+	 */
 	tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT;
 	tcm->tcm_handle = cl->common.classid;
 	if (!cl->level && cl->un.leaf.q)
@@ -1123,12 +1127,9 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg,
 	    nla_put_u64(skb, TCA_HTB_CEIL64, cl->ceil.rate_bytes_ps))
 		goto nla_put_failure;
 
-	nla_nest_end(skb, nest);
-	spin_unlock_bh(root_lock);
-	return skb->len;
+	return nla_nest_end(skb, nest);
 
 nla_put_failure:
-	spin_unlock_bh(root_lock);
 	nla_nest_cancel(skb, nest);
 	return -1;
 }
@@ -1276,9 +1277,10 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 	struct Qdisc *new_q = NULL;
 	int last_child = 0;
 
-	// TODO: why don't allow to delete subtree ? references ? does
-	// tc subsys quarantee us that in htb_destroy it holds no class
-	// refs so that we can remove children safely there ?
+	/* TODO: why don't allow to delete subtree ? references ? does
+	 * tc subsys guarantee us that in htb_destroy it holds no class
+	 * refs so that we can remove children safely there ?
+	 */
 	if (cl->children || cl->filter_cnt)
 		return -EBUSY;
 
@@ -1337,7 +1339,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	struct htb_sched *q = qdisc_priv(sch);
 	struct htb_class *cl = (struct htb_class *)*arg, *parent;
 	struct nlattr *opt = tca[TCA_OPTIONS];
-	struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
 	struct nlattr *tb[TCA_HTB_MAX + 1];
 	struct tc_htb_opt *hopt;
 	u64 rate64, ceil64;
@@ -1361,16 +1362,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		goto failure;
 
 	/* Keeping backward compatible with rate_table based iproute2 tc */
-	if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) {
-		rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]);
-		if (rtab)
-			qdisc_put_rtab(rtab);
-	}
-	if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) {
-		ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]);
-		if (ctab)
-			qdisc_put_rtab(ctab);
-	}
+	if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE)
+		qdisc_put_rtab(qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]));
+
+	if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE)
+		qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]));
 
 	if (!cl) {		/* new class */
 		struct Qdisc *new_q;
@@ -1477,21 +1473,30 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		sch_tree_lock(sch);
 	}
 
+	rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0;
+
+	ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0;
+
+	psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64);
+	psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64);
+
 	/* it used to be a nasty bug here, we have to check that node
 	 * is really leaf before changing cl->un.leaf !
 	 */
 	if (!cl->level) {
-		cl->quantum = hopt->rate.rate / q->rate2quantum;
+		u64 quantum = cl->rate.rate_bytes_ps;
+
+		do_div(quantum, q->rate2quantum);
+		cl->quantum = min_t(u64, quantum, INT_MAX);
+
 		if (!hopt->quantum && cl->quantum < 1000) {
-			pr_warning(
-			       "HTB: quantum of class %X is small. Consider r2q change.\n",
-			       cl->common.classid);
+			pr_warn("HTB: quantum of class %X is small. Consider r2q change.\n",
+				cl->common.classid);
 			cl->quantum = 1000;
 		}
 		if (!hopt->quantum && cl->quantum > 200000) {
-			pr_warning(
-			       "HTB: quantum of class %X is big. Consider r2q change.\n",
-			       cl->common.classid);
+			pr_warn("HTB: quantum of class %X is big. Consider r2q change.\n",
+				cl->common.classid);
 			cl->quantum = 200000;
 		}
 		if (hopt->quantum)
@@ -1500,13 +1505,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			cl->prio = TC_HTB_NUMPRIO - 1;
 	}
 
-	rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0;
-
-	ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0;
-
-	psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64);
-	psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64);
-
 	cl->buffer = PSCHED_TICKS2NS(hopt->buffer);
 	cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);
 
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index bce1665239b..62871c14e1f 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -100,8 +100,7 @@ static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb)
 	nest = nla_nest_start(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
-	nla_nest_end(skb, nest);
-	return skb->len;
+	return nla_nest_end(skb, nest);
 
 nla_put_failure:
 	nla_nest_cancel(skb, nest);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index bccd52b36e9..111d70fddae 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -88,10 +88,10 @@ struct netem_sched_data {
 	u32 duplicate;
 	u32 reorder;
 	u32 corrupt;
-	u32 rate;
+	u64 rate;
 	s32 packet_overhead;
 	u32 cell_size;
-	u32 cell_size_reciprocal;
+	struct reciprocal_value cell_size_reciprocal;
 	s32 cell_overhead;
 
 	struct crndstate {
@@ -110,6 +110,18 @@ struct netem_sched_data {
 		CLG_GILB_ELL,
 	} loss_model;
 
+	enum {
+		TX_IN_GAP_PERIOD = 1,
+		TX_IN_BURST_PERIOD,
+		LOST_IN_GAP_PERIOD,
+		LOST_IN_BURST_PERIOD,
+	} _4_state_model;
+
+	enum {
+		GOOD_STATE = 1,
+		BAD_STATE,
+	} GE_state_model;
+
 	/* Correlated Loss Generation models */
 	struct clgstate {
 		/* state of the Markov chain */
@@ -169,7 +181,7 @@ static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb)
 static void init_crandom(struct crndstate *state, unsigned long rho)
 {
 	state->rho = rho;
-	state->last = net_random();
+	state->last = prandom_u32();
 }
 
 /* get_crandom - correlated random number generator
@@ -182,9 +194,9 @@ static u32 get_crandom(struct crndstate *state)
 	unsigned long answer;
 
 	if (state->rho == 0)	/* no correlation */
-		return net_random();
+		return prandom_u32();
 
-	value = net_random();
+	value = prandom_u32();
 	rho = (u64)state->rho + 1;
 	answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32;
 	state->last = answer;
@@ -198,50 +210,52 @@ static u32 get_crandom(struct crndstate *state)
 static bool loss_4state(struct netem_sched_data *q)
 {
 	struct clgstate *clg = &q->clg;
-	u32 rnd = net_random();
+	u32 rnd = prandom_u32();
 
 	/*
 	 * Makes a comparison between rnd and the transition
 	 * probabilities outgoing from the current state, then decides the
 	 * next state and if the next packet has to be transmitted or lost.
 	 * The four states correspond to:
-	 *   1 => successfully transmitted packets within a gap period
-	 *   4 => isolated losses within a gap period
-	 *   3 => lost packets within a burst period
-	 *   2 => successfully transmitted packets within a burst period
+	 *   TX_IN_GAP_PERIOD => successfully transmitted packets within a gap period
+	 *   LOST_IN_BURST_PERIOD => isolated losses within a gap period
+	 *   LOST_IN_GAP_PERIOD => lost packets within a burst period
+	 *   TX_IN_GAP_PERIOD => successfully transmitted packets within a burst period
 	 */
 	switch (clg->state) {
-	case 1:
+	case TX_IN_GAP_PERIOD:
 		if (rnd < clg->a4) {
-			clg->state = 4;
+			clg->state = LOST_IN_BURST_PERIOD;
 			return true;
 		} else if (clg->a4 < rnd && rnd < clg->a1 + clg->a4) {
-			clg->state = 3;
+			clg->state = LOST_IN_GAP_PERIOD;
 			return true;
-		} else if (clg->a1 + clg->a4 < rnd)
-			clg->state = 1;
+		} else if (clg->a1 + clg->a4 < rnd) {
+			clg->state = TX_IN_GAP_PERIOD;
+		}
 
 		break;
-	case 2:
+	case TX_IN_BURST_PERIOD:
 		if (rnd < clg->a5) {
-			clg->state = 3;
+			clg->state = LOST_IN_GAP_PERIOD;
 			return true;
-		} else
-			clg->state = 2;
+		} else {
+			clg->state = TX_IN_BURST_PERIOD;
+		}
 
 		break;
-	case 3:
+	case LOST_IN_GAP_PERIOD:
 		if (rnd < clg->a3)
-			clg->state = 2;
+			clg->state = TX_IN_BURST_PERIOD;
 		else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) {
-			clg->state = 1;
+			clg->state = TX_IN_GAP_PERIOD;
 		} else if (clg->a2 + clg->a3 < rnd) {
-			clg->state = 3;
+			clg->state = LOST_IN_GAP_PERIOD;
 			return true;
 		}
 		break;
-	case 4:
-		clg->state = 1;
+	case LOST_IN_BURST_PERIOD:
+		clg->state = TX_IN_GAP_PERIOD;
 		break;
 	}
 
@@ -263,16 +277,16 @@ static bool loss_gilb_ell(struct netem_sched_data *q)
 	struct clgstate *clg = &q->clg;
 
 	switch (clg->state) {
-	case 1:
-		if (net_random() < clg->a1)
-			clg->state = 2;
-		if (net_random() < clg->a4)
+	case GOOD_STATE:
+		if (prandom_u32() < clg->a1)
+			clg->state = BAD_STATE;
+		if (prandom_u32() < clg->a4)
 			return true;
 		break;
-	case 2:
-		if (net_random() < clg->a2)
-			clg->state = 1;
-		if (net_random() > clg->a3)
+	case BAD_STATE:
+		if (prandom_u32() < clg->a2)
+			clg->state = GOOD_STATE;
+		if (prandom_u32() > clg->a3)
 			return true;
 	}
 
@@ -457,7 +471,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		     skb_checksum_help(skb)))
 			return qdisc_drop(skb, sch);
 
-		skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8);
+		skb->data[prandom_u32() % skb_headlen(skb)] ^=
+			1<<(prandom_u32() % 8);
 	}
 
 	if (unlikely(skb_queue_len(&sch->q) >= sch->limit))
@@ -495,7 +510,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 				now = netem_skb_cb(last)->time_to_send;
 			}
 
-			delay += packet_len_2_sched_time(skb->len, q);
+			delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q);
 		}
 
 		cb->time_to_send = now + delay;
@@ -633,12 +648,7 @@ static void netem_reset(struct Qdisc *sch)
 
 static void dist_free(struct disttable *d)
 {
-	if (d) {
-		if (is_vmalloc_addr(d))
-			vfree(d);
-		else
-			kfree(d);
-	}
+	kvfree(d);
 }
 
 /*
@@ -679,9 +689,8 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
 	return 0;
 }
 
-static void get_correlation(struct Qdisc *sch, const struct nlattr *attr)
+static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	const struct tc_netem_corr *c = nla_data(attr);
 
 	init_crandom(&q->delay_cor, c->delay_corr);
@@ -689,47 +698,45 @@ static void get_correlation(struct Qdisc *sch, const struct nlattr *attr)
 	init_crandom(&q->dup_cor, c->dup_corr);
 }
 
-static void get_reorder(struct Qdisc *sch, const struct nlattr *attr)
+static void get_reorder(struct netem_sched_data *q, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	const struct tc_netem_reorder *r = nla_data(attr);
 
 	q->reorder = r->probability;
 	init_crandom(&q->reorder_cor, r->correlation);
 }
 
-static void get_corrupt(struct Qdisc *sch, const struct nlattr *attr)
+static void get_corrupt(struct netem_sched_data *q, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	const struct tc_netem_corrupt *r = nla_data(attr);
 
 	q->corrupt = r->probability;
 	init_crandom(&q->corrupt_cor, r->correlation);
 }
 
-static void get_rate(struct Qdisc *sch, const struct nlattr *attr)
+static void get_rate(struct netem_sched_data *q, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	const struct tc_netem_rate *r = nla_data(attr);
 
 	q->rate = r->rate;
 	q->packet_overhead = r->packet_overhead;
 	q->cell_size = r->cell_size;
+	q->cell_overhead = r->cell_overhead;
 	if (q->cell_size)
 		q->cell_size_reciprocal = reciprocal_value(q->cell_size);
-	q->cell_overhead = r->cell_overhead;
+	else
+		q->cell_size_reciprocal = (struct reciprocal_value) { 0 };
 }
 
-static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
+static int get_loss_clg(struct netem_sched_data *q, const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	const struct nlattr *la;
 	int rem;
 
 	nla_for_each_nested(la, attr, rem) {
 		u16 type = nla_type(la);
 
-		switch(type) {
+		switch (type) {
 		case NETEM_LOSS_GI: {
 			const struct tc_netem_gimodel *gi = nla_data(la);
 
@@ -740,7 +747,7 @@ static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
 
 			q->loss_model = CLG_4_STATES;
 
-			q->clg.state = 1;
+			q->clg.state = TX_IN_GAP_PERIOD;
 			q->clg.a1 = gi->p13;
 			q->clg.a2 = gi->p31;
 			q->clg.a3 = gi->p32;
@@ -758,7 +765,7 @@ static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
 			}
 
 			q->loss_model = CLG_GILB_ELL;
-			q->clg.state = 1;
+			q->clg.state = GOOD_STATE;
 			q->clg.a1 = ge->p;
 			q->clg.a2 = ge->r;
 			q->clg.a3 = ge->h;
@@ -782,6 +789,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
 	[TCA_NETEM_RATE]	= { .len = sizeof(struct tc_netem_rate) },
 	[TCA_NETEM_LOSS]	= { .type = NLA_NESTED },
 	[TCA_NETEM_ECN]		= { .type = NLA_U32 },
+	[TCA_NETEM_RATE64]	= { .type = NLA_U64 },
 };
 
 static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
@@ -808,6 +816,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
 	struct netem_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_NETEM_MAX + 1];
 	struct tc_netem_qopt *qopt;
+	struct clgstate old_clg;
+	int old_loss_model = CLG_RANDOM;
 	int ret;
 
 	if (opt == NULL)
@@ -818,6 +828,33 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
 	if (ret < 0)
 		return ret;
 
+	/* backup q->clg and q->loss_model */
+	old_clg = q->clg;
+	old_loss_model = q->loss_model;
+
+	if (tb[TCA_NETEM_LOSS]) {
+		ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]);
+		if (ret) {
+			q->loss_model = old_loss_model;
+			return ret;
+		}
+	} else {
+		q->loss_model = CLG_RANDOM;
+	}
+
+	if (tb[TCA_NETEM_DELAY_DIST]) {
+		ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]);
+		if (ret) {
+			/* recover clg and loss_model, in case of
+			 * q->clg and q->loss_model were modified
+			 * in get_loss_clg()
+			 */
+			q->clg = old_clg;
+			q->loss_model = old_loss_model;
+			return ret;
+		}
+	}
+
 	sch->limit = qopt->limit;
 
 	q->latency = qopt->latency;
@@ -835,30 +872,24 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
 		q->reorder = ~0;
 
 	if (tb[TCA_NETEM_CORR])
-		get_correlation(sch, tb[TCA_NETEM_CORR]);
-
-	if (tb[TCA_NETEM_DELAY_DIST]) {
-		ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]);
-		if (ret)
-			return ret;
-	}
+		get_correlation(q, tb[TCA_NETEM_CORR]);
 
 	if (tb[TCA_NETEM_REORDER])
-		get_reorder(sch, tb[TCA_NETEM_REORDER]);
+		get_reorder(q, tb[TCA_NETEM_REORDER]);
 
 	if (tb[TCA_NETEM_CORRUPT])
-		get_corrupt(sch, tb[TCA_NETEM_CORRUPT]);
+		get_corrupt(q, tb[TCA_NETEM_CORRUPT]);
 
 	if (tb[TCA_NETEM_RATE])
-		get_rate(sch, tb[TCA_NETEM_RATE]);
+		get_rate(q, tb[TCA_NETEM_RATE]);
+
+	if (tb[TCA_NETEM_RATE64])
+		q->rate = max_t(u64, q->rate,
+				nla_get_u64(tb[TCA_NETEM_RATE64]));
 
 	if (tb[TCA_NETEM_ECN])
 		q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]);
 
-	q->loss_model = CLG_RANDOM;
-	if (tb[TCA_NETEM_LOSS])
-		ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]);
-
 	return ret;
 }
 
@@ -974,7 +1005,13 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt))
 		goto nla_put_failure;
 
-	rate.rate = q->rate;
+	if (q->rate >= (1ULL << 32)) {
+		if (nla_put_u64(skb, TCA_NETEM_RATE64, q->rate))
+			goto nla_put_failure;
+		rate.rate = ~0U;
+	} else {
+		rate.rate = q->rate;
+	}
 	rate.packet_overhead = q->packet_overhead;
 	rate.cell_size = q->cell_size;
 	rate.cell_overhead = q->cell_overhead;
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
new file mode 100644
index 00000000000..fefeeb73f15
--- /dev/null
+++ b/net/sched/sch_pie.c
@@ -0,0 +1,566 @@
+/* Copyright (C) 2013 Cisco Systems, Inc, 2013.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Author: Vijay Subramanian <vijaynsu@cisco.com>
+ * Author: Mythili Prabhu <mysuryan@cisco.com>
+ *
+ * ECN support is added by Naeem Khademi <naeemk@ifi.uio.no>
+ * University of Oslo, Norway.
+ *
+ * References:
+ * IETF draft submission: http://tools.ietf.org/html/draft-pan-aqm-pie-00
+ * IEEE  Conference on High Performance Switching and Routing 2013 :
+ * "PIE: A * Lightweight Control Scheme to Address the Bufferbloat Problem"
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/pkt_sched.h>
+#include <net/inet_ecn.h>
+
+#define QUEUE_THRESHOLD 10000
+#define DQCOUNT_INVALID -1
+#define MAX_PROB  0xffffffff
+#define PIE_SCALE 8
+
+/* parameters used */
+struct pie_params {
+	psched_time_t target;	/* user specified target delay in pschedtime */
+	u32 tupdate;		/* timer frequency (in jiffies) */
+	u32 limit;		/* number of packets that can be enqueued */
+	u32 alpha;		/* alpha and beta are between 0 and 32 */
+	u32 beta;		/* and are used for shift relative to 1 */
+	bool ecn;		/* true if ecn is enabled */
+	bool bytemode;		/* to scale drop early prob based on pkt size */
+};
+
+/* variables used */
+struct pie_vars {
+	u32 prob;		/* probability but scaled by u32 limit. */
+	psched_time_t burst_time;
+	psched_time_t qdelay;
+	psched_time_t qdelay_old;
+	u64 dq_count;		/* measured in bytes */
+	psched_time_t dq_tstamp;	/* drain rate */
+	u32 avg_dq_rate;	/* bytes per pschedtime tick,scaled */
+	u32 qlen_old;		/* in bytes */
+};
+
+/* statistics gathering */
+struct pie_stats {
+	u32 packets_in;		/* total number of packets enqueued */
+	u32 dropped;		/* packets dropped due to pie_action */
+	u32 overlimit;		/* dropped due to lack of space in queue */
+	u32 maxq;		/* maximum queue size */
+	u32 ecn_mark;		/* packets marked with ECN */
+};
+
+/* private data for the Qdisc */
+struct pie_sched_data {
+	struct pie_params params;
+	struct pie_vars vars;
+	struct pie_stats stats;
+	struct timer_list adapt_timer;
+};
+
+static void pie_params_init(struct pie_params *params)
+{
+	params->alpha = 2;
+	params->beta = 20;
+	params->tupdate = usecs_to_jiffies(30 * USEC_PER_MSEC);	/* 30 ms */
+	params->limit = 1000;	/* default of 1000 packets */
+	params->target = PSCHED_NS2TICKS(20 * NSEC_PER_MSEC);	/* 20 ms */
+	params->ecn = false;
+	params->bytemode = false;
+}
+
+static void pie_vars_init(struct pie_vars *vars)
+{
+	vars->dq_count = DQCOUNT_INVALID;
+	vars->avg_dq_rate = 0;
+	/* default of 100 ms in pschedtime */
+	vars->burst_time = PSCHED_NS2TICKS(100 * NSEC_PER_MSEC);
+}
+
+static bool drop_early(struct Qdisc *sch, u32 packet_size)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	u32 rnd;
+	u32 local_prob = q->vars.prob;
+	u32 mtu = psched_mtu(qdisc_dev(sch));
+
+	/* If there is still burst allowance left skip random early drop */
+	if (q->vars.burst_time > 0)
+		return false;
+
+	/* If current delay is less than half of target, and
+	 * if drop prob is low already, disable early_drop
+	 */
+	if ((q->vars.qdelay < q->params.target / 2)
+	    && (q->vars.prob < MAX_PROB / 5))
+		return false;
+
+	/* If we have fewer than 2 mtu-sized packets, disable drop_early,
+	 * similar to min_th in RED
+	 */
+	if (sch->qstats.backlog < 2 * mtu)
+		return false;
+
+	/* If bytemode is turned on, use packet size to compute new
+	 * probablity. Smaller packets will have lower drop prob in this case
+	 */
+	if (q->params.bytemode && packet_size <= mtu)
+		local_prob = (local_prob / mtu) * packet_size;
+	else
+		local_prob = q->vars.prob;
+
+	rnd = prandom_u32();
+	if (rnd < local_prob)
+		return true;
+
+	return false;
+}
+
+static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	bool enqueue = false;
+
+	if (unlikely(qdisc_qlen(sch) >= sch->limit)) {
+		q->stats.overlimit++;
+		goto out;
+	}
+
+	if (!drop_early(sch, skb->len)) {
+		enqueue = true;
+	} else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) &&
+		   INET_ECN_set_ce(skb)) {
+		/* If packet is ecn capable, mark it if drop probability
+		 * is lower than 10%, else drop it.
+		 */
+		q->stats.ecn_mark++;
+		enqueue = true;
+	}
+
+	/* we can enqueue the packet */
+	if (enqueue) {
+		q->stats.packets_in++;
+		if (qdisc_qlen(sch) > q->stats.maxq)
+			q->stats.maxq = qdisc_qlen(sch);
+
+		return qdisc_enqueue_tail(skb, sch);
+	}
+
+out:
+	q->stats.dropped++;
+	return qdisc_drop(skb, sch);
+}
+
+static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = {
+	[TCA_PIE_TARGET] = {.type = NLA_U32},
+	[TCA_PIE_LIMIT] = {.type = NLA_U32},
+	[TCA_PIE_TUPDATE] = {.type = NLA_U32},
+	[TCA_PIE_ALPHA] = {.type = NLA_U32},
+	[TCA_PIE_BETA] = {.type = NLA_U32},
+	[TCA_PIE_ECN] = {.type = NLA_U32},
+	[TCA_PIE_BYTEMODE] = {.type = NLA_U32},
+};
+
+static int pie_change(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tb[TCA_PIE_MAX + 1];
+	unsigned int qlen;
+	int err;
+
+	if (!opt)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_PIE_MAX, opt, pie_policy);
+	if (err < 0)
+		return err;
+
+	sch_tree_lock(sch);
+
+	/* convert from microseconds to pschedtime */
+	if (tb[TCA_PIE_TARGET]) {
+		/* target is in us */
+		u32 target = nla_get_u32(tb[TCA_PIE_TARGET]);
+
+		/* convert to pschedtime */
+		q->params.target = PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC);
+	}
+
+	/* tupdate is in jiffies */
+	if (tb[TCA_PIE_TUPDATE])
+		q->params.tupdate = usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE]));
+
+	if (tb[TCA_PIE_LIMIT]) {
+		u32 limit = nla_get_u32(tb[TCA_PIE_LIMIT]);
+
+		q->params.limit = limit;
+		sch->limit = limit;
+	}
+
+	if (tb[TCA_PIE_ALPHA])
+		q->params.alpha = nla_get_u32(tb[TCA_PIE_ALPHA]);
+
+	if (tb[TCA_PIE_BETA])
+		q->params.beta = nla_get_u32(tb[TCA_PIE_BETA]);
+
+	if (tb[TCA_PIE_ECN])
+		q->params.ecn = nla_get_u32(tb[TCA_PIE_ECN]);
+
+	if (tb[TCA_PIE_BYTEMODE])
+		q->params.bytemode = nla_get_u32(tb[TCA_PIE_BYTEMODE]);
+
+	/* Drop excess packets if new limit is lower */
+	qlen = sch->q.qlen;
+	while (sch->q.qlen > sch->limit) {
+		struct sk_buff *skb = __skb_dequeue(&sch->q);
+
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		qdisc_drop(skb, sch);
+	}
+	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+
+	sch_tree_unlock(sch);
+	return 0;
+}
+
+static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb)
+{
+
+	struct pie_sched_data *q = qdisc_priv(sch);
+	int qlen = sch->qstats.backlog;	/* current queue size in bytes */
+
+	/* If current queue is about 10 packets or more and dq_count is unset
+	 * we have enough packets to calculate the drain rate. Save
+	 * current time as dq_tstamp and start measurement cycle.
+	 */
+	if (qlen >= QUEUE_THRESHOLD && q->vars.dq_count == DQCOUNT_INVALID) {
+		q->vars.dq_tstamp = psched_get_time();
+		q->vars.dq_count = 0;
+	}
+
+	/* Calculate the average drain rate from this value.  If queue length
+	 * has receded to a small value viz., <= QUEUE_THRESHOLD bytes,reset
+	 * the dq_count to -1 as we don't have enough packets to calculate the
+	 * drain rate anymore The following if block is entered only when we
+	 * have a substantial queue built up (QUEUE_THRESHOLD bytes or more)
+	 * and we calculate the drain rate for the threshold here.  dq_count is
+	 * in bytes, time difference in psched_time, hence rate is in
+	 * bytes/psched_time.
+	 */
+	if (q->vars.dq_count != DQCOUNT_INVALID) {
+		q->vars.dq_count += skb->len;
+
+		if (q->vars.dq_count >= QUEUE_THRESHOLD) {
+			psched_time_t now = psched_get_time();
+			u32 dtime = now - q->vars.dq_tstamp;
+			u32 count = q->vars.dq_count << PIE_SCALE;
+
+			if (dtime == 0)
+				return;
+
+			count = count / dtime;
+
+			if (q->vars.avg_dq_rate == 0)
+				q->vars.avg_dq_rate = count;
+			else
+				q->vars.avg_dq_rate =
+				    (q->vars.avg_dq_rate -
+				     (q->vars.avg_dq_rate >> 3)) + (count >> 3);
+
+			/* If the queue has receded below the threshold, we hold
+			 * on to the last drain rate calculated, else we reset
+			 * dq_count to 0 to re-enter the if block when the next
+			 * packet is dequeued
+			 */
+			if (qlen < QUEUE_THRESHOLD)
+				q->vars.dq_count = DQCOUNT_INVALID;
+			else {
+				q->vars.dq_count = 0;
+				q->vars.dq_tstamp = psched_get_time();
+			}
+
+			if (q->vars.burst_time > 0) {
+				if (q->vars.burst_time > dtime)
+					q->vars.burst_time -= dtime;
+				else
+					q->vars.burst_time = 0;
+			}
+		}
+	}
+}
+
+static void calculate_probability(struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	u32 qlen = sch->qstats.backlog;	/* queue size in bytes */
+	psched_time_t qdelay = 0;	/* in pschedtime */
+	psched_time_t qdelay_old = q->vars.qdelay;	/* in pschedtime */
+	s32 delta = 0;		/* determines the change in probability */
+	u32 oldprob;
+	u32 alpha, beta;
+	bool update_prob = true;
+
+	q->vars.qdelay_old = q->vars.qdelay;
+
+	if (q->vars.avg_dq_rate > 0)
+		qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate;
+	else
+		qdelay = 0;
+
+	/* If qdelay is zero and qlen is not, it means qlen is very small, less
+	 * than dequeue_rate, so we do not update probabilty in this round
+	 */
+	if (qdelay == 0 && qlen != 0)
+		update_prob = false;
+
+	/* In the algorithm, alpha and beta are between 0 and 2 with typical
+	 * value for alpha as 0.125. In this implementation, we use values 0-32
+	 * passed from user space to represent this. Also, alpha and beta have
+	 * unit of HZ and need to be scaled before they can used to update
+	 * probability. alpha/beta are updated locally below by 1) scaling them
+	 * appropriately 2) scaling down by 16 to come to 0-2 range.
+	 * Please see paper for details.
+	 *
+	 * We scale alpha and beta differently depending on whether we are in
+	 * light, medium or high dropping mode.
+	 */
+	if (q->vars.prob < MAX_PROB / 100) {
+		alpha =
+		    (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7;
+		beta =
+		    (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 7;
+	} else if (q->vars.prob < MAX_PROB / 10) {
+		alpha =
+		    (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5;
+		beta =
+		    (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 5;
+	} else {
+		alpha =
+		    (q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
+		beta =
+		    (q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4;
+	}
+
+	/* alpha and beta should be between 0 and 32, in multiples of 1/16 */
+	delta += alpha * ((qdelay - q->params.target));
+	delta += beta * ((qdelay - qdelay_old));
+
+	oldprob = q->vars.prob;
+
+	/* to ensure we increase probability in steps of no more than 2% */
+	if (delta > (s32) (MAX_PROB / (100 / 2)) &&
+	    q->vars.prob >= MAX_PROB / 10)
+		delta = (MAX_PROB / 100) * 2;
+
+	/* Non-linear drop:
+	 * Tune drop probability to increase quickly for high delays(>= 250ms)
+	 * 250ms is derived through experiments and provides error protection
+	 */
+
+	if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC)))
+		delta += MAX_PROB / (100 / 2);
+
+	q->vars.prob += delta;
+
+	if (delta > 0) {
+		/* prevent overflow */
+		if (q->vars.prob < oldprob) {
+			q->vars.prob = MAX_PROB;
+			/* Prevent normalization error. If probability is at
+			 * maximum value already, we normalize it here, and
+			 * skip the check to do a non-linear drop in the next
+			 * section.
+			 */
+			update_prob = false;
+		}
+	} else {
+		/* prevent underflow */
+		if (q->vars.prob > oldprob)
+			q->vars.prob = 0;
+	}
+
+	/* Non-linear drop in probability: Reduce drop probability quickly if
+	 * delay is 0 for 2 consecutive Tupdate periods.
+	 */
+
+	if ((qdelay == 0) && (qdelay_old == 0) && update_prob)
+		q->vars.prob = (q->vars.prob * 98) / 100;
+
+	q->vars.qdelay = qdelay;
+	q->vars.qlen_old = qlen;
+
+	/* We restart the measurement cycle if the following conditions are met
+	 * 1. If the delay has been low for 2 consecutive Tupdate periods
+	 * 2. Calculated drop probability is zero
+	 * 3. We have atleast one estimate for the avg_dq_rate ie.,
+	 *    is a non-zero value
+	 */
+	if ((q->vars.qdelay < q->params.target / 2) &&
+	    (q->vars.qdelay_old < q->params.target / 2) &&
+	    (q->vars.prob == 0) &&
+	    (q->vars.avg_dq_rate > 0))
+		pie_vars_init(&q->vars);
+}
+
+static void pie_timer(unsigned long arg)
+{
+	struct Qdisc *sch = (struct Qdisc *)arg;
+	struct pie_sched_data *q = qdisc_priv(sch);
+	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
+
+	spin_lock(root_lock);
+	calculate_probability(sch);
+
+	/* reset the timer to fire after 'tupdate'. tupdate is in jiffies. */
+	if (q->params.tupdate)
+		mod_timer(&q->adapt_timer, jiffies + q->params.tupdate);
+	spin_unlock(root_lock);
+
+}
+
+static int pie_init(struct Qdisc *sch, struct nlattr *opt)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+
+	pie_params_init(&q->params);
+	pie_vars_init(&q->vars);
+	sch->limit = q->params.limit;
+
+	setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch);
+	mod_timer(&q->adapt_timer, jiffies + HZ / 2);
+
+	if (opt) {
+		int err = pie_change(sch, opt);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int pie_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts;
+
+	opts = nla_nest_start(skb, TCA_OPTIONS);
+	if (opts == NULL)
+		goto nla_put_failure;
+
+	/* convert target from pschedtime to us */
+	if (nla_put_u32(skb, TCA_PIE_TARGET,
+			((u32) PSCHED_TICKS2NS(q->params.target)) /
+			NSEC_PER_USEC) ||
+	    nla_put_u32(skb, TCA_PIE_LIMIT, sch->limit) ||
+	    nla_put_u32(skb, TCA_PIE_TUPDATE, jiffies_to_usecs(q->params.tupdate)) ||
+	    nla_put_u32(skb, TCA_PIE_ALPHA, q->params.alpha) ||
+	    nla_put_u32(skb, TCA_PIE_BETA, q->params.beta) ||
+	    nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) ||
+	    nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, opts);
+
+nla_put_failure:
+	nla_nest_cancel(skb, opts);
+	return -1;
+
+}
+
+static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	struct tc_pie_xstats st = {
+		.prob		= q->vars.prob,
+		.delay		= ((u32) PSCHED_TICKS2NS(q->vars.qdelay)) /
+				   NSEC_PER_USEC,
+		/* unscale and return dq_rate in bytes per sec */
+		.avg_dq_rate	= q->vars.avg_dq_rate *
+				  (PSCHED_TICKS_PER_SEC) >> PIE_SCALE,
+		.packets_in	= q->stats.packets_in,
+		.overlimit	= q->stats.overlimit,
+		.maxq		= q->stats.maxq,
+		.dropped	= q->stats.dropped,
+		.ecn_mark	= q->stats.ecn_mark,
+	};
+
+	return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch)
+{
+	struct sk_buff *skb;
+	skb = __qdisc_dequeue_head(sch, &sch->q);
+
+	if (!skb)
+		return NULL;
+
+	pie_process_dequeue(sch, skb);
+	return skb;
+}
+
+static void pie_reset(struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	qdisc_reset_queue(sch);
+	pie_vars_init(&q->vars);
+}
+
+static void pie_destroy(struct Qdisc *sch)
+{
+	struct pie_sched_data *q = qdisc_priv(sch);
+	q->params.tupdate = 0;
+	del_timer_sync(&q->adapt_timer);
+}
+
+static struct Qdisc_ops pie_qdisc_ops __read_mostly = {
+	.id = "pie",
+	.priv_size	= sizeof(struct pie_sched_data),
+	.enqueue	= pie_qdisc_enqueue,
+	.dequeue	= pie_qdisc_dequeue,
+	.peek		= qdisc_peek_dequeued,
+	.init		= pie_init,
+	.destroy	= pie_destroy,
+	.reset		= pie_reset,
+	.change		= pie_change,
+	.dump		= pie_dump,
+	.dump_stats	= pie_dump_stats,
+	.owner		= THIS_MODULE,
+};
+
+static int __init pie_module_init(void)
+{
+	return register_qdisc(&pie_qdisc_ops);
+}
+
+static void __exit pie_module_exit(void)
+{
+	unregister_qdisc(&pie_qdisc_ops);
+}
+
+module_init(pie_module_init);
+module_exit(pie_module_exit);
+
+MODULE_DESCRIPTION("Proportional Integral controller Enhanced (PIE) scheduler");
+MODULE_AUTHOR("Vijay Subramanian");
+MODULE_AUTHOR("Mythili Prabhu");
+MODULE_LICENSE("GPL");
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 30ea4674cab..9b0f7093d97 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -220,7 +220,7 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da
 
 static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q)
 {
-	q->bins[slot].perturbation = net_random();
+	q->bins[slot].perturbation = prandom_u32();
 }
 
 static void sfb_swap_slot(struct sfb_sched_data *q)
@@ -381,7 +381,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		goto enqueue;
 	}
 
-	r = net_random() & SFB_MAX_PROB;
+	r = prandom_u32() & SFB_MAX_PROB;
 
 	if (unlikely(r < p_min)) {
 		if (unlikely(p_min > SFB_MAX_PROB / 2)) {
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index d3a1bc26dbf..1af2f73906d 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -237,10 +237,12 @@ static inline void sfq_link(struct sfq_sched_data *q, sfq_index x)
 }
 
 #define sfq_unlink(q, x, n, p)			\
-	n = q->slots[x].dep.next;		\
-	p = q->slots[x].dep.prev;		\
-	sfq_dep_head(q, p)->next = n;		\
-	sfq_dep_head(q, n)->prev = p
+	do {					\
+		n = q->slots[x].dep.next;	\
+		p = q->slots[x].dep.prev;	\
+		sfq_dep_head(q, p)->next = n;	\
+		sfq_dep_head(q, n)->prev = p;	\
+	} while (0)
 
 
 static inline void sfq_dec(struct sfq_sched_data *q, sfq_index x)
@@ -627,7 +629,7 @@ static void sfq_perturbation(unsigned long arg)
 	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
 
 	spin_lock(root_lock);
-	q->perturbation = net_random();
+	q->perturbation = prandom_u32();
 	if (!q->filter_list && q->tail)
 		sfq_rehash(sch);
 	spin_unlock(root_lock);
@@ -696,7 +698,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	del_timer(&q->perturb_timer);
 	if (q->perturb_period) {
 		mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
-		q->perturbation = net_random();
+		q->perturbation = prandom_u32();
 	}
 	sch_tree_unlock(sch);
 	kfree(p);
@@ -714,12 +716,7 @@ static void *sfq_alloc(size_t sz)
 
 static void sfq_free(void *addr)
 {
-	if (addr) {
-		if (is_vmalloc_addr(addr))
-			vfree(addr);
-		else
-			kfree(addr);
-	}
+	kvfree(addr);
 }
 
 static void sfq_destroy(struct Qdisc *sch)
@@ -757,7 +754,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 	q->quantum = psched_mtu(qdisc_dev(sch));
 	q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
 	q->perturb_period = 0;
-	q->perturbation = net_random();
+	q->perturbation = prandom_u32();
 
 	if (opt) {
 		int err = sfq_change(sch, opt);
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index a6090051c5d..18ff6343370 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -21,7 +21,6 @@
 #include <net/netlink.h>
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
-#include <net/tcp.h>
 
 
 /*	Simple Token Bucket Filter.
@@ -102,12 +101,11 @@
 struct tbf_sched_data {
 /* Parameters */
 	u32		limit;		/* Maximal length of backlog: bytes */
+	u32		max_size;
 	s64		buffer;		/* Token bucket depth/rate: MUST BE >= MTU/B */
 	s64		mtu;
-	u32		max_size;
 	struct psched_ratecfg rate;
 	struct psched_ratecfg peak;
-	bool peak_present;
 
 /* Variables */
 	s64	tokens;			/* Current number of B tokens */
@@ -118,20 +116,40 @@ struct tbf_sched_data {
 };
 
 
+/* Time to Length, convert time in ns to length in bytes
+ * to determinate how many bytes can be sent in given time.
+ */
+static u64 psched_ns_t2l(const struct psched_ratecfg *r,
+			 u64 time_in_ns)
+{
+	/* The formula is :
+	 * len = (time_in_ns * r->rate_bytes_ps) / NSEC_PER_SEC
+	 */
+	u64 len = time_in_ns * r->rate_bytes_ps;
+
+	do_div(len, NSEC_PER_SEC);
+
+	if (unlikely(r->linklayer == TC_LINKLAYER_ATM)) {
+		do_div(len, 53);
+		len = len * 48;
+	}
+
+	if (len > r->overhead)
+		len -= r->overhead;
+	else
+		len = 0;
+
+	return len;
+}
+
 /*
  * Return length of individual segments of a gso packet,
  * including all headers (MAC, IP, TCP/UDP)
  */
-static unsigned int skb_gso_seglen(const struct sk_buff *skb)
+static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
 {
 	unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
-	const struct skb_shared_info *shinfo = skb_shinfo(skb);
-
-	if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
-		hdr_len += tcp_hdrlen(skb);
-	else
-		hdr_len += sizeof(struct udphdr);
-	return hdr_len + shinfo->gso_size;
+	return hdr_len + skb_gso_transport_seglen(skb);
 }
 
 /* GSO packet is too big, segment it so that tbf can transmit
@@ -176,7 +194,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	int ret;
 
 	if (qdisc_pkt_len(skb) > q->max_size) {
-		if (skb_is_gso(skb) && skb_gso_seglen(skb) <= q->max_size)
+		if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size)
 			return tbf_segment(skb, sch);
 		return qdisc_reshape_fail(skb, sch);
 	}
@@ -203,6 +221,11 @@ static unsigned int tbf_drop(struct Qdisc *sch)
 	return len;
 }
 
+static bool tbf_peak_present(const struct tbf_sched_data *q)
+{
+	return q->peak.rate_bytes_ps;
+}
+
 static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
@@ -219,7 +242,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
 		now = ktime_to_ns(ktime_get());
 		toks = min_t(s64, now - q->t_c, q->buffer);
 
-		if (q->peak_present) {
+		if (tbf_peak_present(q)) {
 			ptoks = toks + q->ptokens;
 			if (ptoks > q->mtu)
 				ptoks = q->mtu;
@@ -281,6 +304,8 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = {
 	[TCA_TBF_PTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
 	[TCA_TBF_RATE64]	= { .type = NLA_U64 },
 	[TCA_TBF_PRATE64]	= { .type = NLA_U64 },
+	[TCA_TBF_BURST] = { .type = NLA_U32 },
+	[TCA_TBF_PBURST] = { .type = NLA_U32 },
 };
 
 static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
@@ -289,10 +314,11 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_TBF_MAX + 1];
 	struct tc_tbf_qopt *qopt;
-	struct qdisc_rate_table *rtab = NULL;
-	struct qdisc_rate_table *ptab = NULL;
 	struct Qdisc *child = NULL;
-	int max_size, n;
+	struct psched_ratecfg rate;
+	struct psched_ratecfg peak;
+	u64 max_size;
+	s64 buffer, mtu;
 	u64 rate64 = 0, prate64 = 0;
 
 	err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy);
@@ -304,39 +330,60 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 		goto done;
 
 	qopt = nla_data(tb[TCA_TBF_PARMS]);
-	rtab = qdisc_get_rtab(&qopt->rate, tb[TCA_TBF_RTAB]);
-	if (rtab == NULL)
-		goto done;
+	if (qopt->rate.linklayer == TC_LINKLAYER_UNAWARE)
+		qdisc_put_rtab(qdisc_get_rtab(&qopt->rate,
+					      tb[TCA_TBF_RTAB]));
+
+	if (qopt->peakrate.linklayer == TC_LINKLAYER_UNAWARE)
+			qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
+						      tb[TCA_TBF_PTAB]));
+
+	buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U);
+	mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U);
+
+	if (tb[TCA_TBF_RATE64])
+		rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
+	psched_ratecfg_precompute(&rate, &qopt->rate, rate64);
+
+	if (tb[TCA_TBF_BURST]) {
+		max_size = nla_get_u32(tb[TCA_TBF_BURST]);
+		buffer = psched_l2t_ns(&rate, max_size);
+	} else {
+		max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U);
+	}
 
 	if (qopt->peakrate.rate) {
-		if (qopt->peakrate.rate > qopt->rate.rate)
-			ptab = qdisc_get_rtab(&qopt->peakrate, tb[TCA_TBF_PTAB]);
-		if (ptab == NULL)
+		if (tb[TCA_TBF_PRATE64])
+			prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
+		psched_ratecfg_precompute(&peak, &qopt->peakrate, prate64);
+		if (peak.rate_bytes_ps <= rate.rate_bytes_ps) {
+			pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n",
+					peak.rate_bytes_ps, rate.rate_bytes_ps);
+			err = -EINVAL;
 			goto done;
-	}
+		}
 
-	for (n = 0; n < 256; n++)
-		if (rtab->data[n] > qopt->buffer)
-			break;
-	max_size = (n << qopt->rate.cell_log) - 1;
-	if (ptab) {
-		int size;
-
-		for (n = 0; n < 256; n++)
-			if (ptab->data[n] > qopt->mtu)
-				break;
-		size = (n << qopt->peakrate.cell_log) - 1;
-		if (size < max_size)
-			max_size = size;
+		if (tb[TCA_TBF_PBURST]) {
+			u32 pburst = nla_get_u32(tb[TCA_TBF_PBURST]);
+			max_size = min_t(u32, max_size, pburst);
+			mtu = psched_l2t_ns(&peak, pburst);
+		} else {
+			max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu));
+		}
+	} else {
+		memset(&peak, 0, sizeof(peak));
 	}
-	if (max_size < 0)
-		goto done;
 
 	if (max_size < psched_mtu(qdisc_dev(sch)))
-		pr_warn_ratelimited("sch_tbf: burst %u is lower than device %s mtu (%u) !\n",
+		pr_warn_ratelimited("sch_tbf: burst %llu is lower than device %s mtu (%u) !\n",
 				    max_size, qdisc_dev(sch)->name,
 				    psched_mtu(qdisc_dev(sch)));
 
+	if (!max_size) {
+		err = -EINVAL;
+		goto done;
+	}
+
 	if (q->qdisc != &noop_qdisc) {
 		err = fifo_set_limit(q->qdisc, qopt->limit);
 		if (err)
@@ -356,31 +403,24 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 		q->qdisc = child;
 	}
 	q->limit = qopt->limit;
-	q->mtu = PSCHED_TICKS2NS(qopt->mtu);
+	if (tb[TCA_TBF_PBURST])
+		q->mtu = mtu;
+	else
+		q->mtu = PSCHED_TICKS2NS(qopt->mtu);
 	q->max_size = max_size;
-	q->buffer = PSCHED_TICKS2NS(qopt->buffer);
+	if (tb[TCA_TBF_BURST])
+		q->buffer = buffer;
+	else
+		q->buffer = PSCHED_TICKS2NS(qopt->buffer);
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
 
-	if (tb[TCA_TBF_RATE64])
-		rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
-	psched_ratecfg_precompute(&q->rate, &rtab->rate, rate64);
-	if (ptab) {
-		if (tb[TCA_TBF_PRATE64])
-			prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
-		psched_ratecfg_precompute(&q->peak, &ptab->rate, prate64);
-		q->peak_present = true;
-	} else {
-		q->peak_present = false;
-	}
+	memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg));
+	memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
 
 	sch_tree_unlock(sch);
 	err = 0;
 done:
-	if (rtab)
-		qdisc_put_rtab(rtab);
-	if (ptab)
-		qdisc_put_rtab(ptab);
 	return err;
 }
 
@@ -419,7 +459,7 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
 
 	opt.limit = q->limit;
 	psched_ratecfg_getrate(&opt.rate, &q->rate);
-	if (q->peak_present)
+	if (tbf_peak_present(q))
 		psched_ratecfg_getrate(&opt.peakrate, &q->peak);
 	else
 		memset(&opt.peakrate, 0, sizeof(opt.peakrate));
@@ -430,13 +470,12 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (q->rate.rate_bytes_ps >= (1ULL << 32) &&
 	    nla_put_u64(skb, TCA_TBF_RATE64, q->rate.rate_bytes_ps))
 		goto nla_put_failure;
-	if (q->peak_present &&
+	if (tbf_peak_present(q) &&
 	    q->peak.rate_bytes_ps >= (1ULL << 32) &&
 	    nla_put_u64(skb, TCA_TBF_PRATE64, q->peak.rate_bytes_ps))
 		goto nla_put_failure;
 
-	nla_nest_end(skb, nest);
-	return skb->len;
+	return nla_nest_end(skb, nest);
 
 nla_put_failure:
 	nla_nest_cancel(skb, nest);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 3d7c6bd4631..06a9ee6b2d3 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -55,6 +55,7 @@
 #include <net/sctp/sm.h>
 
 /* Forward declarations for internal functions. */
+static void sctp_select_active_and_retran_path(struct sctp_association *asoc);
 static void sctp_assoc_bh_rcv(struct work_struct *work);
 static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc);
 static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc);
@@ -145,8 +146,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 		= 5 * asoc->rto_max;
 
 	asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay;
-	asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] =
-		min_t(unsigned long, sp->autoclose, net->sctp.max_autoclose) * HZ;
+	asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ;
 
 	/* Initializes the timers */
 	for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i)
@@ -254,8 +254,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 		asoc->peer.ipv6_address = 1;
 	INIT_LIST_HEAD(&asoc->asocs);
 
-	asoc->autoclose = sp->autoclose;
-
 	asoc->default_stream = sp->default_stream;
 	asoc->default_ppid = sp->default_ppid;
 	asoc->default_flags = sp->default_flags;
@@ -333,7 +331,7 @@ void sctp_association_free(struct sctp_association *asoc)
 	/* Only real associations count against the endpoint, so
 	 * don't bother for if this is a temporary association.
 	 */
-	if (!asoc->temp) {
+	if (!list_empty(&asoc->asocs)) {
 		list_del(&asoc->asocs);
 
 		/* Decrement the backlog value for a TCP-style listening
@@ -777,9 +775,6 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 				  sctp_transport_cmd_t command,
 				  sctp_sn_error_t error)
 {
-	struct sctp_transport *t = NULL;
-	struct sctp_transport *first;
-	struct sctp_transport *second;
 	struct sctp_ulpevent *event;
 	struct sockaddr_storage addr;
 	int spc_state = 0;
@@ -832,13 +827,14 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 		return;
 	}
 
-	/* Generate and send a SCTP_PEER_ADDR_CHANGE notification to the
-	 * user.
+	/* Generate and send a SCTP_PEER_ADDR_CHANGE notification
+	 * to the user.
 	 */
 	if (ulp_notify) {
 		memset(&addr, 0, sizeof(struct sockaddr_storage));
 		memcpy(&addr, &transport->ipaddr,
 		       transport->af_specific->sockaddr_len);
+
 		event = sctp_ulpevent_make_peer_addr_change(asoc, &addr,
 					0, spc_state, error, GFP_ATOMIC);
 		if (event)
@@ -846,60 +842,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 	}
 
 	/* Select new active and retran paths. */
-
-	/* Look for the two most recently used active transports.
-	 *
-	 * This code produces the wrong ordering whenever jiffies
-	 * rolls over, but we still get usable transports, so we don't
-	 * worry about it.
-	 */
-	first = NULL; second = NULL;
-
-	list_for_each_entry(t, &asoc->peer.transport_addr_list,
-			transports) {
-
-		if ((t->state == SCTP_INACTIVE) ||
-		    (t->state == SCTP_UNCONFIRMED) ||
-		    (t->state == SCTP_PF))
-			continue;
-		if (!first || t->last_time_heard > first->last_time_heard) {
-			second = first;
-			first = t;
-		} else if (!second ||
-			   t->last_time_heard > second->last_time_heard)
-			second = t;
-	}
-
-	/* RFC 2960 6.4 Multi-Homed SCTP Endpoints
-	 *
-	 * By default, an endpoint should always transmit to the
-	 * primary path, unless the SCTP user explicitly specifies the
-	 * destination transport address (and possibly source
-	 * transport address) to use.
-	 *
-	 * [If the primary is active but not most recent, bump the most
-	 * recently used transport.]
-	 */
-	if (((asoc->peer.primary_path->state == SCTP_ACTIVE) ||
-	     (asoc->peer.primary_path->state == SCTP_UNKNOWN)) &&
-	    first != asoc->peer.primary_path) {
-		second = first;
-		first = asoc->peer.primary_path;
-	}
-
-	if (!second)
-		second = first;
-	/* If we failed to find a usable transport, just camp on the
-	 * primary, even if it is inactive.
-	 */
-	if (!first) {
-		first = asoc->peer.primary_path;
-		second = asoc->peer.primary_path;
-	}
-
-	/* Set the active and retran transports.  */
-	asoc->peer.active_path = first;
-	asoc->peer.retran_path = second;
+	sctp_select_active_and_retran_path(asoc);
 }
 
 /* Hold a reference to an association. */
@@ -1093,7 +1036,7 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 		}
 
 		if (chunk->transport)
-			chunk->transport->last_time_heard = jiffies;
+			chunk->transport->last_time_heard = ktime_get();
 
 		/* Run through the state machine. */
 		error = sctp_do_sm(net, SCTP_EVENT_T_CHUNK, subtype,
@@ -1154,6 +1097,7 @@ void sctp_assoc_update(struct sctp_association *asoc,
 	asoc->c = new->c;
 	asoc->peer.rwnd = new->peer.rwnd;
 	asoc->peer.sack_needed = new->peer.sack_needed;
+	asoc->peer.auth_capable = new->peer.auth_capable;
 	asoc->peer.i = new->peer.i;
 	sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
 			 asoc->peer.i.initial_tsn, GFP_ATOMIC);
@@ -1242,78 +1186,204 @@ void sctp_assoc_update(struct sctp_association *asoc,
 }
 
 /* Update the retran path for sending a retransmitted packet.
- * Round-robin through the active transports, else round-robin
- * through the inactive transports as this is the next best thing
- * we can try.
+ * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints:
+ *
+ *   When there is outbound data to send and the primary path
+ *   becomes inactive (e.g., due to failures), or where the
+ *   SCTP user explicitly requests to send data to an
+ *   inactive destination transport address, before reporting
+ *   an error to its ULP, the SCTP endpoint should try to send
+ *   the data to an alternate active destination transport
+ *   address if one exists.
+ *
+ *   When retransmitting data that timed out, if the endpoint
+ *   is multihomed, it should consider each source-destination
+ *   address pair in its retransmission selection policy.
+ *   When retransmitting timed-out data, the endpoint should
+ *   attempt to pick the most divergent source-destination
+ *   pair from the original source-destination pair to which
+ *   the packet was transmitted.
+ *
+ *   Note: Rules for picking the most divergent source-destination
+ *   pair are an implementation decision and are not specified
+ *   within this document.
+ *
+ * Our basic strategy is to round-robin transports in priorities
+ * according to sctp_state_prio_map[] e.g., if no such
+ * transport with state SCTP_ACTIVE exists, round-robin through
+ * SCTP_UNKNOWN, etc. You get the picture.
  */
+static const u8 sctp_trans_state_to_prio_map[] = {
+	[SCTP_ACTIVE]	= 3,	/* best case */
+	[SCTP_UNKNOWN]	= 2,
+	[SCTP_PF]	= 1,
+	[SCTP_INACTIVE] = 0,	/* worst case */
+};
+
+static u8 sctp_trans_score(const struct sctp_transport *trans)
+{
+	return sctp_trans_state_to_prio_map[trans->state];
+}
+
+static struct sctp_transport *sctp_trans_elect_tie(struct sctp_transport *trans1,
+						   struct sctp_transport *trans2)
+{
+	if (trans1->error_count > trans2->error_count) {
+		return trans2;
+	} else if (trans1->error_count == trans2->error_count &&
+		   ktime_after(trans2->last_time_heard,
+			       trans1->last_time_heard)) {
+		return trans2;
+	} else {
+		return trans1;
+	}
+}
+
+static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr,
+						    struct sctp_transport *best)
+{
+	u8 score_curr, score_best;
+
+	if (best == NULL)
+		return curr;
+
+	score_curr = sctp_trans_score(curr);
+	score_best = sctp_trans_score(best);
+
+	/* First, try a score-based selection if both transport states
+	 * differ. If we're in a tie, lets try to make a more clever
+	 * decision here based on error counts and last time heard.
+	 */
+	if (score_curr > score_best)
+		return curr;
+	else if (score_curr == score_best)
+		return sctp_trans_elect_tie(curr, best);
+	else
+		return best;
+}
+
 void sctp_assoc_update_retran_path(struct sctp_association *asoc)
 {
-	struct sctp_transport *t, *next;
-	struct list_head *head = &asoc->peer.transport_addr_list;
-	struct list_head *pos;
+	struct sctp_transport *trans = asoc->peer.retran_path;
+	struct sctp_transport *trans_next = NULL;
 
+	/* We're done as we only have the one and only path. */
 	if (asoc->peer.transport_count == 1)
 		return;
+	/* If active_path and retran_path are the same and active,
+	 * then this is the only active path. Use it.
+	 */
+	if (asoc->peer.active_path == asoc->peer.retran_path &&
+	    asoc->peer.active_path->state == SCTP_ACTIVE)
+		return;
 
-	/* Find the next transport in a round-robin fashion. */
-	t = asoc->peer.retran_path;
-	pos = &t->transports;
-	next = NULL;
+	/* Iterate from retran_path's successor back to retran_path. */
+	for (trans = list_next_entry(trans, transports); 1;
+	     trans = list_next_entry(trans, transports)) {
+		/* Manually skip the head element. */
+		if (&trans->transports == &asoc->peer.transport_addr_list)
+			continue;
+		if (trans->state == SCTP_UNCONFIRMED)
+			continue;
+		trans_next = sctp_trans_elect_best(trans, trans_next);
+		/* Active is good enough for immediate return. */
+		if (trans_next->state == SCTP_ACTIVE)
+			break;
+		/* We've reached the end, time to update path. */
+		if (trans == asoc->peer.retran_path)
+			break;
+	}
 
-	while (1) {
-		/* Skip the head. */
-		if (pos->next == head)
-			pos = head->next;
-		else
-			pos = pos->next;
+	asoc->peer.retran_path = trans_next;
 
-		t = list_entry(pos, struct sctp_transport, transports);
+	pr_debug("%s: association:%p updated new path to addr:%pISpc\n",
+		 __func__, asoc, &asoc->peer.retran_path->ipaddr.sa);
+}
 
-		/* We have exhausted the list, but didn't find any
-		 * other active transports.  If so, use the next
-		 * transport.
+static void sctp_select_active_and_retran_path(struct sctp_association *asoc)
+{
+	struct sctp_transport *trans, *trans_pri = NULL, *trans_sec = NULL;
+	struct sctp_transport *trans_pf = NULL;
+
+	/* Look for the two most recently used active transports. */
+	list_for_each_entry(trans, &asoc->peer.transport_addr_list,
+			    transports) {
+		/* Skip uninteresting transports. */
+		if (trans->state == SCTP_INACTIVE ||
+		    trans->state == SCTP_UNCONFIRMED)
+			continue;
+		/* Keep track of the best PF transport from our
+		 * list in case we don't find an active one.
 		 */
-		if (t == asoc->peer.retran_path) {
-			t = next;
-			break;
+		if (trans->state == SCTP_PF) {
+			trans_pf = sctp_trans_elect_best(trans, trans_pf);
+			continue;
 		}
-
-		/* Try to find an active transport. */
-
-		if ((t->state == SCTP_ACTIVE) ||
-		    (t->state == SCTP_UNKNOWN)) {
-			break;
-		} else {
-			/* Keep track of the next transport in case
-			 * we don't find any active transport.
-			 */
-			if (t->state != SCTP_UNCONFIRMED && !next)
-				next = t;
+		/* For active transports, pick the most recent ones. */
+		if (trans_pri == NULL ||
+		    ktime_after(trans->last_time_heard,
+				trans_pri->last_time_heard)) {
+			trans_sec = trans_pri;
+			trans_pri = trans;
+		} else if (trans_sec == NULL ||
+			   ktime_after(trans->last_time_heard,
+				       trans_sec->last_time_heard)) {
+			trans_sec = trans;
 		}
 	}
 
-	if (t)
-		asoc->peer.retran_path = t;
-	else
-		t = asoc->peer.retran_path;
+	/* RFC 2960 6.4 Multi-Homed SCTP Endpoints
+	 *
+	 * By default, an endpoint should always transmit to the primary
+	 * path, unless the SCTP user explicitly specifies the
+	 * destination transport address (and possibly source transport
+	 * address) to use. [If the primary is active but not most recent,
+	 * bump the most recently used transport.]
+	 */
+	if ((asoc->peer.primary_path->state == SCTP_ACTIVE ||
+	     asoc->peer.primary_path->state == SCTP_UNKNOWN) &&
+	     asoc->peer.primary_path != trans_pri) {
+		trans_sec = trans_pri;
+		trans_pri = asoc->peer.primary_path;
+	}
+
+	/* We did not find anything useful for a possible retransmission
+	 * path; either primary path that we found is the the same as
+	 * the current one, or we didn't generally find an active one.
+	 */
+	if (trans_sec == NULL)
+		trans_sec = trans_pri;
 
-	pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc,
-		 &t->ipaddr.sa);
+	/* If we failed to find a usable transport, just camp on the
+	 * primary or retran, even if they are inactive, if possible
+	 * pick a PF iff it's the better choice.
+	 */
+	if (trans_pri == NULL) {
+		trans_pri = sctp_trans_elect_best(asoc->peer.primary_path,
+						  asoc->peer.retran_path);
+		trans_pri = sctp_trans_elect_best(trans_pri, trans_pf);
+		trans_sec = asoc->peer.primary_path;
+	}
+
+	/* Set the active and retran transports. */
+	asoc->peer.active_path = trans_pri;
+	asoc->peer.retran_path = trans_sec;
 }
 
-/* Choose the transport for sending retransmit packet.  */
-struct sctp_transport *sctp_assoc_choose_alter_transport(
-	struct sctp_association *asoc, struct sctp_transport *last_sent_to)
+struct sctp_transport *
+sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
+				  struct sctp_transport *last_sent_to)
 {
 	/* If this is the first time packet is sent, use the active path,
 	 * else use the retran path. If the last packet was sent over the
 	 * retran path, update the retran path and use it.
 	 */
-	if (!last_sent_to)
+	if (last_sent_to == NULL) {
 		return asoc->peer.active_path;
-	else {
+	} else {
 		if (last_sent_to == asoc->peer.retran_path)
 			sctp_assoc_update_retran_path(asoc);
+
 		return asoc->peer.retran_path;
 	}
 }
@@ -1522,7 +1592,7 @@ int sctp_assoc_lookup_laddr(struct sctp_association *asoc,
 /* Set an association id for a given association */
 int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp)
 {
-	bool preload = gfp & __GFP_WAIT;
+	bool preload = !!(gfp & __GFP_WAIT);
 	int ret;
 
 	/* If the id is already assigned, keep it. */
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 5c9f64c1c90..0e8529113dc 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -41,7 +41,7 @@ static struct sctp_hmac sctp_hmac_list[SCTP_AUTH_NUM_HMACS] = {
 	},
 	{
 		.hmac_id = SCTP_AUTH_HMAC_ID_SHA1,
-		.hmac_name="hmac(sha1)",
+		.hmac_name = "hmac(sha1)",
 		.hmac_len = SCTP_SHA1_SIG_SIZE,
 	},
 	{
@@ -51,7 +51,7 @@ static struct sctp_hmac sctp_hmac_list[SCTP_AUTH_NUM_HMACS] = {
 #if defined (CONFIG_CRYPTO_SHA256) || defined (CONFIG_CRYPTO_SHA256_MODULE)
 	{
 		.hmac_id = SCTP_AUTH_HMAC_ID_SHA256,
-		.hmac_name="hmac(sha256)",
+		.hmac_name = "hmac(sha256)",
 		.hmac_len = SCTP_SHA256_SIG_SIZE,
 	}
 #endif
@@ -163,7 +163,7 @@ static int sctp_auth_compare_vectors(struct sctp_auth_bytes *vector1,
 		 * lead-zero padded.  If it is not, it
 		 * is automatically larger numerically.
 		 */
-		for (i = 0; i < abs(diff); i++ ) {
+		for (i = 0; i < abs(diff); i++) {
 			if (longer[i] != 0)
 				return diff;
 		}
@@ -226,9 +226,9 @@ static struct sctp_auth_bytes *sctp_auth_make_local_vector(
 				    gfp_t gfp)
 {
 	return sctp_auth_make_key_vector(
-				    (sctp_random_param_t*)asoc->c.auth_random,
-				    (sctp_chunks_param_t*)asoc->c.auth_chunks,
-				    (sctp_hmac_algo_param_t*)asoc->c.auth_hmacs,
+				    (sctp_random_param_t *)asoc->c.auth_random,
+				    (sctp_chunks_param_t *)asoc->c.auth_chunks,
+				    (sctp_hmac_algo_param_t *)asoc->c.auth_hmacs,
 				    gfp);
 }
 
@@ -386,14 +386,13 @@ nomem:
  */
 int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp)
 {
-	struct net *net = sock_net(asoc->base.sk);
 	struct sctp_auth_bytes	*secret;
 	struct sctp_shared_key *ep_key;
 
 	/* If we don't support AUTH, or peer is not capable
 	 * we don't need to do anything.
 	 */
-	if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+	if (!asoc->ep->auth_enable || !asoc->peer.auth_capable)
 		return 0;
 
 	/* If the key_id is non-zero and we couldn't find an
@@ -440,16 +439,16 @@ struct sctp_shared_key *sctp_auth_get_shkey(
  */
 int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp)
 {
-	struct net *net = sock_net(ep->base.sk);
 	struct crypto_hash *tfm = NULL;
 	__u16   id;
 
-	/* if the transforms are already allocted, we are done */
-	if (!net->sctp.auth_enable) {
+	/* If AUTH extension is disabled, we are done */
+	if (!ep->auth_enable) {
 		ep->auth_hmacs = NULL;
 		return 0;
 	}
 
+	/* If the transforms are already allocated, we are done */
 	if (ep->auth_hmacs)
 		return 0;
 
@@ -499,8 +498,7 @@ void sctp_auth_destroy_hmacs(struct crypto_hash *auth_hmacs[])
 	if (!auth_hmacs)
 		return;
 
-	for (i = 0; i < SCTP_AUTH_NUM_HMACS; i++)
-	{
+	for (i = 0; i < SCTP_AUTH_NUM_HMACS; i++) {
 		if (auth_hmacs[i])
 			crypto_free_hash(auth_hmacs[i]);
 	}
@@ -647,15 +645,15 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param)
 	 */
 	for (i = 0; !found && i < len; i++) {
 		switch (param->chunks[i]) {
-		    case SCTP_CID_INIT:
-		    case SCTP_CID_INIT_ACK:
-		    case SCTP_CID_SHUTDOWN_COMPLETE:
-		    case SCTP_CID_AUTH:
+		case SCTP_CID_INIT:
+		case SCTP_CID_INIT_ACK:
+		case SCTP_CID_SHUTDOWN_COMPLETE:
+		case SCTP_CID_AUTH:
 			break;
 
-		    default:
+		default:
 			if (param->chunks[i] == chunk)
-			    found = 1;
+				found = 1;
 			break;
 		}
 	}
@@ -666,12 +664,10 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param)
 /* Check if peer requested that this chunk is authenticated */
 int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
 {
-	struct net  *net;
 	if (!asoc)
 		return 0;
 
-	net = sock_net(asoc->base.sk);
-	if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+	if (!asoc->ep->auth_enable || !asoc->peer.auth_capable)
 		return 0;
 
 	return __sctp_auth_cid(chunk, asoc->peer.peer_chunks);
@@ -680,12 +676,10 @@ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
 /* Check if we requested that peer authenticate this chunk. */
 int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
 {
-	struct net *net;
 	if (!asoc)
 		return 0;
 
-	net = sock_net(asoc->base.sk);
-	if (!net->sctp.auth_enable)
+	if (!asoc->ep->auth_enable)
 		return 0;
 
 	return __sctp_auth_cid(chunk,
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 5573e425b0c..158701da2d3 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -254,7 +254,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 		SCTP_INC_STATS_USER(sock_net(asoc->base.sk), SCTP_MIB_FRAGUSRMSGS);
 
 	/* Create chunks for all the full sized DATA chunks. */
-	for (i=0, len=first_len; i < whole; i++) {
+	for (i = 0, len = first_len; i < whole; i++) {
 		frag = SCTP_DATA_MIDDLE_FRAG;
 
 		if (0 == i)
@@ -317,7 +317,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 			goto errout;
 		}
 
-		err = sctp_user_addto_chunk(chunk, offset, over,msgh->msg_iov);
+		err = sctp_user_addto_chunk(chunk, offset, over, msgh->msg_iov);
 
 		/* Put the chunk->skb back into the form expected by send.  */
 		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 6ffb6c1b13b..9da76ba4d10 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -68,7 +68,8 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 	if (!ep->digest)
 		return NULL;
 
-	if (net->sctp.auth_enable) {
+	ep->auth_enable = net->sctp.auth_enable;
+	if (ep->auth_enable) {
 		/* Allocate space for HMACS and CHUNKS authentication
 		 * variables.  There are arrays that we encode directly
 		 * into parameters to make the rest of the operations easier.
@@ -368,9 +369,9 @@ struct sctp_association *sctp_endpoint_lookup_assoc(
 {
 	struct sctp_association *asoc;
 
-	sctp_local_bh_disable();
+	local_bh_disable();
 	asoc = __sctp_endpoint_lookup_assoc(ep, paddr, transport);
-	sctp_local_bh_enable();
+	local_bh_enable();
 
 	return asoc;
 }
@@ -480,7 +481,7 @@ normal:
 		}
 
 		if (chunk->transport)
-			chunk->transport->last_time_heard = jiffies;
+			chunk->transport->last_time_heard = ktime_get();
 
 		error = sctp_do_sm(net, SCTP_EVENT_T_CHUNK, subtype, state,
 				   ep, asoc, chunk, GFP_ATOMIC);
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 66038533ca5..f2e2cbd2d75 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -119,7 +119,7 @@ int sctp_rcv(struct sk_buff *skb)
 	struct sctp_af *af;
 	struct net *net = dev_net(skb->dev);
 
-	if (skb->pkt_type!=PACKET_HOST)
+	if (skb->pkt_type != PACKET_HOST)
 		goto discard_it;
 
 	SCTP_INC_STATS_BH(net, SCTP_MIB_INSCTPPACKS);
@@ -180,8 +180,7 @@ int sctp_rcv(struct sk_buff *skb)
 	 * If a frame arrives on an interface and the receiving socket is
 	 * bound to another interface, via SO_BINDTODEVICE, treat it as OOTB
 	 */
-	if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb)))
-	{
+	if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb))) {
 		if (asoc) {
 			sctp_association_put(asoc);
 			asoc = NULL;
@@ -239,7 +238,7 @@ int sctp_rcv(struct sk_buff *skb)
 	 * bottom halves on this lock, but a user may be in the lock too,
 	 * so check if it is busy.
 	 */
-	sctp_bh_lock_sock(sk);
+	bh_lock_sock(sk);
 
 	if (sk != rcvr->sk) {
 		/* Our cached sk is different from the rcvr->sk.  This is
@@ -249,14 +248,14 @@ int sctp_rcv(struct sk_buff *skb)
 		 * be doing something with the new socket.  Switch our veiw
 		 * of the current sk.
 		 */
-		sctp_bh_unlock_sock(sk);
+		bh_unlock_sock(sk);
 		sk = rcvr->sk;
-		sctp_bh_lock_sock(sk);
+		bh_lock_sock(sk);
 	}
 
 	if (sock_owned_by_user(sk)) {
 		if (sctp_add_backlog(sk, skb)) {
-			sctp_bh_unlock_sock(sk);
+			bh_unlock_sock(sk);
 			sctp_chunk_free(chunk);
 			skb = NULL; /* sctp_chunk_free already freed the skb */
 			goto discard_release;
@@ -267,7 +266,7 @@ int sctp_rcv(struct sk_buff *skb)
 		sctp_inq_push(&chunk->rcvr->inqueue, chunk);
 	}
 
-	sctp_bh_unlock_sock(sk);
+	bh_unlock_sock(sk);
 
 	/* Release the asoc/ep ref we took in the lookup calls. */
 	if (asoc)
@@ -328,7 +327,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 		 */
 
 		sk = rcvr->sk;
-		sctp_bh_lock_sock(sk);
+		bh_lock_sock(sk);
 
 		if (sock_owned_by_user(sk)) {
 			if (sk_add_backlog(sk, skb, sk->sk_rcvbuf))
@@ -338,7 +337,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 		} else
 			sctp_inq_push(inqueue, chunk);
 
-		sctp_bh_unlock_sock(sk);
+		bh_unlock_sock(sk);
 
 		/* If the chunk was backloged again, don't drop refs */
 		if (backloged)
@@ -523,7 +522,7 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
 		goto out;
 	}
 
-	sctp_bh_lock_sock(sk);
+	bh_lock_sock(sk);
 
 	/* If too many ICMPs get dropped on busy
 	 * servers this needs to be solved differently.
@@ -536,17 +535,15 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
 	return sk;
 
 out:
-	if (asoc)
-		sctp_association_put(asoc);
+	sctp_association_put(asoc);
 	return NULL;
 }
 
 /* Common cleanup code for icmp/icmpv6 error handler. */
 void sctp_err_finish(struct sock *sk, struct sctp_association *asoc)
 {
-	sctp_bh_unlock_sock(sk);
-	if (asoc)
-		sctp_association_put(asoc);
+	bh_unlock_sock(sk);
+	sctp_association_put(asoc);
 }
 
 /*
@@ -612,8 +609,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
 		if (ICMP_FRAG_NEEDED == code) {
 			sctp_icmp_frag_needed(sk, asoc, transport, info);
 			goto out_unlock;
-		}
-		else {
+		} else {
 			if (ICMP_PROT_UNREACH == code) {
 				sctp_icmp_proto_unreachable(sk, asoc,
 							    transport);
@@ -722,17 +718,17 @@ static void __sctp_hash_endpoint(struct sctp_endpoint *ep)
 	epb->hashent = sctp_ep_hashfn(net, epb->bind_addr.port);
 	head = &sctp_ep_hashtable[epb->hashent];
 
-	sctp_write_lock(&head->lock);
+	write_lock(&head->lock);
 	hlist_add_head(&epb->node, &head->chain);
-	sctp_write_unlock(&head->lock);
+	write_unlock(&head->lock);
 }
 
 /* Add an endpoint to the hash. Local BH-safe. */
 void sctp_hash_endpoint(struct sctp_endpoint *ep)
 {
-	sctp_local_bh_disable();
+	local_bh_disable();
 	__sctp_hash_endpoint(ep);
-	sctp_local_bh_enable();
+	local_bh_enable();
 }
 
 /* Remove endpoint from the hash table.  */
@@ -748,17 +744,17 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep)
 
 	head = &sctp_ep_hashtable[epb->hashent];
 
-	sctp_write_lock(&head->lock);
+	write_lock(&head->lock);
 	hlist_del_init(&epb->node);
-	sctp_write_unlock(&head->lock);
+	write_unlock(&head->lock);
 }
 
 /* Remove endpoint from the hash.  Local BH-safe. */
 void sctp_unhash_endpoint(struct sctp_endpoint *ep)
 {
-	sctp_local_bh_disable();
+	local_bh_disable();
 	__sctp_unhash_endpoint(ep);
-	sctp_local_bh_enable();
+	local_bh_enable();
 }
 
 /* Look up an endpoint. */
@@ -802,9 +798,9 @@ static void __sctp_hash_established(struct sctp_association *asoc)
 
 	head = &sctp_assoc_hashtable[epb->hashent];
 
-	sctp_write_lock(&head->lock);
+	write_lock(&head->lock);
 	hlist_add_head(&epb->node, &head->chain);
-	sctp_write_unlock(&head->lock);
+	write_unlock(&head->lock);
 }
 
 /* Add an association to the hash. Local BH-safe. */
@@ -813,9 +809,9 @@ void sctp_hash_established(struct sctp_association *asoc)
 	if (asoc->temp)
 		return;
 
-	sctp_local_bh_disable();
+	local_bh_disable();
 	__sctp_hash_established(asoc);
-	sctp_local_bh_enable();
+	local_bh_enable();
 }
 
 /* Remove association from the hash table.  */
@@ -832,9 +828,9 @@ static void __sctp_unhash_established(struct sctp_association *asoc)
 
 	head = &sctp_assoc_hashtable[epb->hashent];
 
-	sctp_write_lock(&head->lock);
+	write_lock(&head->lock);
 	hlist_del_init(&epb->node);
-	sctp_write_unlock(&head->lock);
+	write_unlock(&head->lock);
 }
 
 /* Remove association from the hash table.  Local BH-safe. */
@@ -843,9 +839,9 @@ void sctp_unhash_established(struct sctp_association *asoc)
 	if (asoc->temp)
 		return;
 
-	sctp_local_bh_disable();
+	local_bh_disable();
 	__sctp_unhash_established(asoc);
-	sctp_local_bh_enable();
+	local_bh_enable();
 }
 
 /* Look up an association. */
@@ -895,9 +891,9 @@ struct sctp_association *sctp_lookup_association(struct net *net,
 {
 	struct sctp_association *asoc;
 
-	sctp_local_bh_disable();
+	local_bh_disable();
 	asoc = __sctp_lookup_association(net, laddr, paddr, transportp);
-	sctp_local_bh_enable();
+	local_bh_enable();
 
 	return asoc;
 }
@@ -1057,31 +1053,31 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net,
 		if (ch_end > skb_tail_pointer(skb))
 			break;
 
-		switch(ch->type) {
-		    case SCTP_CID_AUTH:
-			    have_auth = chunk_num;
-			    break;
-
-		    case SCTP_CID_COOKIE_ECHO:
-			    /* If a packet arrives containing an AUTH chunk as
-			     * a first chunk, a COOKIE-ECHO chunk as the second
-			     * chunk, and possibly more chunks after them, and
-			     * the receiver does not have an STCB for that
-			     * packet, then authentication is based on
-			     * the contents of the COOKIE- ECHO chunk.
-			     */
-			    if (have_auth == 1 && chunk_num == 2)
-				    return NULL;
-			    break;
-
-		    case SCTP_CID_ASCONF:
-			    if (have_auth || net->sctp.addip_noauth)
-				    asoc = __sctp_rcv_asconf_lookup(
-							net, ch, laddr,
-							sctp_hdr(skb)->source,
-							transportp);
-		    default:
-			    break;
+		switch (ch->type) {
+		case SCTP_CID_AUTH:
+			have_auth = chunk_num;
+			break;
+
+		case SCTP_CID_COOKIE_ECHO:
+			/* If a packet arrives containing an AUTH chunk as
+			 * a first chunk, a COOKIE-ECHO chunk as the second
+			 * chunk, and possibly more chunks after them, and
+			 * the receiver does not have an STCB for that
+			 * packet, then authentication is based on
+			 * the contents of the COOKIE- ECHO chunk.
+			 */
+			if (have_auth == 1 && chunk_num == 2)
+				return NULL;
+			break;
+
+		case SCTP_CID_ASCONF:
+			if (have_auth || net->sctp.addip_noauth)
+				asoc = __sctp_rcv_asconf_lookup(
+						net, ch, laddr,
+						sctp_hdr(skb)->source,
+						transportp);
+		default:
+			break;
 		}
 
 		if (asoc)
@@ -1118,19 +1114,10 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net,
 		return NULL;
 
 	/* If this is INIT/INIT-ACK look inside the chunk too. */
-	switch (ch->type) {
-	case SCTP_CID_INIT:
-	case SCTP_CID_INIT_ACK:
+	if (ch->type == SCTP_CID_INIT || ch->type == SCTP_CID_INIT_ACK)
 		return __sctp_rcv_init_lookup(net, skb, laddr, transportp);
-		break;
 
-	default:
-		return __sctp_rcv_walk_lookup(net, skb, laddr, transportp);
-		break;
-	}
-
-
-	return NULL;
+	return __sctp_rcv_walk_lookup(net, skb, laddr, transportp);
 }
 
 /* Lookup an association for an inbound skb. */
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 32db816ffba..1999592ba88 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -172,7 +172,8 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	switch (type) {
 	case ICMPV6_PKT_TOOBIG:
-		sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info));
+		if (ip6_sk_accept_pmtu(sk))
+			sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info));
 		goto out_unlock;
 	case ICMPV6_PARAMPROB:
 		if (ICMPV6_UNK_NEXTHDR == code) {
@@ -215,7 +216,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 	IP6_ECN_flow_xmit(sk, fl6->flowlabel);
 
 	if (!(transport->param_flags & SPP_PMTUD_ENABLE))
-		skb->local_df = 1;
+		skb->ignore_df = 1;
 
 	SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
 
@@ -262,7 +263,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	}
 
 	final_p = fl6_update_dst(fl6, np->opt, &final);
-	dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
+	dst = ip6_dst_lookup_flow(sk, fl6, final_p);
 	if (!asoc || saddr)
 		goto out;
 
@@ -321,7 +322,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		fl6->saddr = baddr->v6.sin6_addr;
 		fl6->fl6_sport = baddr->v6.sin6_port;
 		final_p = fl6_update_dst(fl6, np->opt, &final);
-		dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
+		dst = ip6_dst_lookup_flow(sk, fl6, final_p);
 	}
 
 out:
@@ -401,7 +402,7 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist,
 }
 
 /* Initialize a sockaddr_storage from in incoming skb. */
-static void sctp_v6_from_skb(union sctp_addr *addr,struct sk_buff *skb,
+static void sctp_v6_from_skb(union sctp_addr *addr, struct sk_buff *skb,
 			     int is_saddr)
 {
 	__be16 *port;
@@ -661,6 +662,8 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 	 */
 	sctp_v6_to_sk_daddr(&asoc->peer.primary_addr, newsk);
 
+	newsk->sk_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+
 	sk_refcnt_debug_inc(newsk);
 
 	if (newsk->sk_prot->init(newsk)) {
@@ -940,7 +943,6 @@ static struct inet_protosw sctpv6_seqpacket_protosw = {
 	.protocol      = IPPROTO_SCTP,
 	.prot 	       = &sctpv6_prot,
 	.ops           = &inet6_seqpacket_ops,
-	.no_check      = 0,
 	.flags         = SCTP_PROTOSW_FLAG
 };
 static struct inet_protosw sctpv6_stream_protosw = {
@@ -948,7 +950,6 @@ static struct inet_protosw sctpv6_stream_protosw = {
 	.protocol      = IPPROTO_SCTP,
 	.prot 	       = &sctpv6_prot,
 	.ops           = &inet6_seqpacket_ops,
-	.no_check      = 0,
 	.flags         = SCTP_PROTOSW_FLAG,
 };
 
diff --git a/net/sctp/objcnt.c b/net/sctp/objcnt.c
index 0c28e8a5532..40e7fac96c4 100644
--- a/net/sctp/objcnt.c
+++ b/net/sctp/objcnt.c
@@ -97,7 +97,7 @@ static void sctp_objcnt_seq_stop(struct seq_file *seq, void *v)
 {
 }
 
-static void * sctp_objcnt_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+static void *sctp_objcnt_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	++*pos;
 	return (*pos >= ARRAY_SIZE(sctp_dbg_objcnt)) ? NULL : (void *)pos;
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 6371337e1fe..01ab8e0723f 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -280,7 +280,7 @@ static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet,
 
 	/* We believe that this chunk is OK to add to the packet */
 	switch (chunk->chunk_hdr->type) {
-	    case SCTP_CID_DATA:
+	case SCTP_CID_DATA:
 		/* Account for the data being in the packet */
 		sctp_packet_append_data(packet, chunk);
 		/* Disallow SACK bundling after DATA. */
@@ -292,17 +292,17 @@ static sctp_xmit_t __sctp_packet_append_chunk(struct sctp_packet *packet,
 		/* timestamp the chunk for rtx purposes */
 		chunk->sent_at = jiffies;
 		break;
-	    case SCTP_CID_COOKIE_ECHO:
+	case SCTP_CID_COOKIE_ECHO:
 		packet->has_cookie_echo = 1;
 		break;
 
-	    case SCTP_CID_SACK:
+	case SCTP_CID_SACK:
 		packet->has_sack = 1;
 		if (chunk->asoc)
 			chunk->asoc->stats.osacks++;
 		break;
 
-	    case SCTP_CID_AUTH:
+	case SCTP_CID_AUTH:
 		packet->has_auth = 1;
 		packet->auth = chunk;
 		break;
@@ -387,7 +387,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	int err = 0;
 	int padding;		/* How much padding do we need?  */
 	__u8 has_data = 0;
-	struct dst_entry *dst = tp->dst;
+	struct dst_entry *dst;
 	unsigned char *auth = NULL;	/* pointer to auth in skb data */
 
 	pr_debug("%s: packet:%p\n", __func__, packet);
@@ -420,9 +420,9 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 		}
 	}
 	dst = dst_clone(tp->dst);
-	skb_dst_set(nskb, dst);
 	if (!dst)
 		goto no_route;
+	skb_dst_set(nskb, dst);
 
 	/* Build the SCTP header.  */
 	sh = (struct sctphdr *)skb_push(nskb, sizeof(struct sctphdr));
@@ -540,8 +540,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 		} else {
 			/* no need to seed pseudo checksum for SCTP */
 			nskb->ip_summed = CHECKSUM_PARTIAL;
-			nskb->csum_start = (skb_transport_header(nskb) -
-			                    nskb->head);
+			nskb->csum_start = skb_transport_header(nskb) - nskb->head;
 			nskb->csum_offset = offsetof(struct sctphdr, checksum);
 		}
 	}
@@ -558,7 +557,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	 * Note: The works for IPv6 layer checks this bit too later
 	 * in transmission.  See IP6_ECN_flow_xmit().
 	 */
-	(*tp->af_specific->ecn_capable)(nskb->sk);
+	tp->af_specific->ecn_capable(nskb->sk);
 
 	/* Set up the IP options.  */
 	/* BUG: not implemented
@@ -580,7 +579,8 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 		unsigned long timeout;
 
 		/* Restart the AUTOCLOSE timer when sending data. */
-		if (sctp_state(asoc, ESTABLISHED) && asoc->autoclose) {
+		if (sctp_state(asoc, ESTABLISHED) &&
+		    asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) {
 			timer = &asoc->timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
 			timeout = asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
 
@@ -591,8 +591,8 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 
 	pr_debug("***sctp_transmit_packet*** skb->len:%d\n", nskb->len);
 
-	nskb->local_df = packet->ipfragok;
-	(*tp->af_specific->sctp_xmit)(nskb, tp);
+	nskb->ignore_df = packet->ipfragok;
+	tp->af_specific->sctp_xmit(nskb, tp);
 
 out:
 	sctp_packet_reset(packet);
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index b6b09f3f1a8..9c77947c059 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -110,7 +110,7 @@ static inline int sctp_cacc_skip_3_1_d(struct sctp_transport *primary,
 				       struct sctp_transport *transport,
 				       int count_of_newacks)
 {
-	if (count_of_newacks >=2 && transport != primary)
+	if (count_of_newacks >= 2 && transport != primary)
 		return 1;
 	return 0;
 }
@@ -207,8 +207,6 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
 	INIT_LIST_HEAD(&q->retransmit);
 	INIT_LIST_HEAD(&q->sacked);
 	INIT_LIST_HEAD(&q->abandoned);
-
-	q->empty = 1;
 }
 
 /* Free the outqueue structure and any related pending chunks.
@@ -331,7 +329,6 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk)
 				SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS);
 			else
 				SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS);
-			q->empty = 0;
 			break;
 		}
 	} else {
@@ -470,7 +467,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport,
 	struct net *net = sock_net(q->asoc->base.sk);
 	int error = 0;
 
-	switch(reason) {
+	switch (reason) {
 	case SCTP_RTXR_T3_RTX:
 		SCTP_INC_STATS(net, SCTP_MIB_T3_RETRANSMITS);
 		sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_T3_RTX);
@@ -653,7 +650,6 @@ redo:
 			if (chunk->fast_retransmit == SCTP_NEED_FRTX)
 				chunk->fast_retransmit = SCTP_DONT_FRTX;
 
-			q->empty = 0;
 			q->asoc->stats.rtxchunks++;
 			break;
 		}
@@ -1064,8 +1060,6 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
 
 			sctp_transport_reset_timers(transport);
 
-			q->empty = 0;
-
 			/* Only let one DATA chunk get bundled with a
 			 * COOKIE-ECHO chunk.
 			 */
@@ -1088,7 +1082,7 @@ sctp_flush_out:
 	 *
 	 * --xguo
 	 */
-	while ((ltransport = sctp_list_dequeue(&transport_list)) != NULL ) {
+	while ((ltransport = sctp_list_dequeue(&transport_list)) != NULL) {
 		struct sctp_transport *t = list_entry(ltransport,
 						      struct sctp_transport,
 						      send_ready);
@@ -1217,7 +1211,7 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk)
 		 * destinations for which cacc_saw_newack is set.
 		 */
 		if (transport->cacc.cacc_saw_newack)
-			count_of_newacks ++;
+			count_of_newacks++;
 	}
 
 	/* Move the Cumulative TSN Ack Point if appropriate.  */
@@ -1274,29 +1268,17 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk)
 		 "advertised peer ack point:0x%x\n", __func__, asoc, ctsn,
 		 asoc->adv_peer_ack_point);
 
-	/* See if all chunks are acked.
-	 * Make sure the empty queue handler will get run later.
-	 */
-	q->empty = (list_empty(&q->out_chunk_list) &&
-		    list_empty(&q->retransmit));
-	if (!q->empty)
-		goto finish;
-
-	list_for_each_entry(transport, transport_list, transports) {
-		q->empty = q->empty && list_empty(&transport->transmitted);
-		if (!q->empty)
-			goto finish;
-	}
-
-	pr_debug("%s: sack queue is empty\n", __func__);
-finish:
-	return q->empty;
+	return sctp_outq_is_empty(q);
 }
 
-/* Is the outqueue empty?  */
+/* Is the outqueue empty?
+ * The queue is empty when we have not pending data, no in-flight data
+ * and nothing pending retransmissions.
+ */
 int sctp_outq_is_empty(const struct sctp_outq *q)
 {
-	return q->empty;
+	return q->out_qlen == 0 && q->outstanding_bytes == 0 &&
+	       list_empty(&q->retransmit);
 }
 
 /********************************************************************
diff --git a/net/sctp/probe.c b/net/sctp/probe.c
index 53c452efb40..5e68b94ee64 100644
--- a/net/sctp/probe.c
+++ b/net/sctp/probe.c
@@ -38,6 +38,7 @@
 #include <net/sctp/sctp.h>
 #include <net/sctp/sm.h>
 
+MODULE_SOFTDEP("pre: sctp");
 MODULE_AUTHOR("Wei Yongjun <yjwei@cn.fujitsu.com>");
 MODULE_DESCRIPTION("SCTP snooper");
 MODULE_LICENSE("GPL");
@@ -182,6 +183,20 @@ static struct jprobe sctp_recv_probe = {
 	.entry	= jsctp_sf_eat_sack,
 };
 
+static __init int sctp_setup_jprobe(void)
+{
+	int ret = register_jprobe(&sctp_recv_probe);
+
+	if (ret) {
+		if (request_module("sctp"))
+			goto out;
+		ret = register_jprobe(&sctp_recv_probe);
+	}
+
+out:
+	return ret;
+}
+
 static __init int sctpprobe_init(void)
 {
 	int ret = -ENOMEM;
@@ -202,7 +217,7 @@ static __init int sctpprobe_init(void)
 			 &sctpprobe_fops))
 		goto free_kfifo;
 
-	ret = register_jprobe(&sctp_recv_probe);
+	ret = sctp_setup_jprobe();
 	if (ret)
 		goto remove_proc;
 
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index de32e14f739..34229ee7f37 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -78,7 +78,7 @@ static int sctp_snmp_seq_show(struct seq_file *seq, void *v)
 
 	for (i = 0; sctp_snmp_list[i].name != NULL; i++)
 		seq_printf(seq, "%-32s\t%ld\n", sctp_snmp_list[i].name,
-			   snmp_fold_field((void __percpu **)net->sctp.sctp_statistics,
+			   snmp_fold_field(net->sctp.sctp_statistics,
 				      sctp_snmp_list[i].entry));
 
 	return 0;
@@ -177,7 +177,7 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa
 	rcu_read_unlock();
 }
 
-static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos)
+static void *sctp_eps_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	if (*pos >= sctp_ep_hashsize)
 		return NULL;
@@ -196,7 +196,7 @@ static void sctp_eps_seq_stop(struct seq_file *seq, void *v)
 }
 
 
-static void * sctp_eps_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+static void *sctp_eps_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	if (++*pos >= sctp_ep_hashsize)
 		return NULL;
@@ -218,7 +218,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v)
 		return -ENOMEM;
 
 	head = &sctp_ep_hashtable[hash];
-	sctp_local_bh_disable();
+	local_bh_disable();
 	read_lock(&head->lock);
 	sctp_for_each_hentry(epb, &head->chain) {
 		ep = sctp_ep(epb);
@@ -235,7 +235,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 	}
 	read_unlock(&head->lock);
-	sctp_local_bh_enable();
+	local_bh_enable();
 
 	return 0;
 }
@@ -282,7 +282,7 @@ void sctp_eps_proc_exit(struct net *net)
 }
 
 
-static void * sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos)
+static void *sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	if (*pos >= sctp_assoc_hashsize)
 		return NULL;
@@ -305,7 +305,7 @@ static void sctp_assocs_seq_stop(struct seq_file *seq, void *v)
 }
 
 
-static void * sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+static void *sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	if (++*pos >= sctp_assoc_hashsize)
 		return NULL;
@@ -326,7 +326,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
 		return -ENOMEM;
 
 	head = &sctp_assoc_hashtable[hash];
-	sctp_local_bh_disable();
+	local_bh_disable();
 	read_lock(&head->lock);
 	sctp_for_each_hentry(epb, &head->chain) {
 		assoc = sctp_assoc(epb);
@@ -362,7 +362,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 	}
 	read_unlock(&head->lock);
-	sctp_local_bh_enable();
+	local_bh_enable();
 
 	return 0;
 }
@@ -446,7 +446,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 		return -ENOMEM;
 
 	head = &sctp_assoc_hashtable[hash];
-	sctp_local_bh_disable();
+	local_bh_disable();
 	read_lock(&head->lock);
 	rcu_read_lock();
 	sctp_for_each_hentry(epb, &head->chain) {
@@ -505,7 +505,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 
 	rcu_read_unlock();
 	read_unlock(&head->lock);
-	sctp_local_bh_enable();
+	local_bh_enable();
 
 	return 0;
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 19bd4c5bdae..6789d785e69 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -491,8 +491,13 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			continue;
 		if ((laddr->state == SCTP_ADDR_SRC) &&
 		    (AF_INET == laddr->a.sa.sa_family)) {
-			fl4->saddr = laddr->a.v4.sin_addr.s_addr;
 			fl4->fl4_sport = laddr->a.v4.sin_port;
+			flowi4_update_output(fl4,
+					     asoc->base.sk->sk_bound_dev_if,
+					     RT_CONN_FLAGS(asoc->base.sk),
+					     daddr->v4.sin_addr.s_addr,
+					     laddr->a.v4.sin_addr.s_addr);
+
 			rt = ip_route_output_key(sock_net(sk), fl4);
 			if (!IS_ERR(rt)) {
 				dst = &rt->dst;
@@ -634,10 +639,10 @@ static void sctp_addr_wq_timeout_handler(unsigned long arg)
 			/* ignore bound-specific endpoints */
 			if (!sctp_is_ep_boundall(sk))
 				continue;
-			sctp_bh_lock_sock(sk);
+			bh_lock_sock(sk);
 			if (sctp_asconf_mgmt(sp, addrw) < 0)
 				pr_debug("%s: sctp_asconf_mgmt failed\n", __func__);
-			sctp_bh_unlock_sock(sk);
+			bh_unlock_sock(sk);
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 free_next:
@@ -957,7 +962,7 @@ static inline int sctp_v4_xmit(struct sk_buff *skb,
 
 	SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS);
 
-	return ip_queue_xmit(skb, &transport->fl);
+	return ip_queue_xmit(&inet->sk, skb, &transport->fl);
 }
 
 static struct sctp_af sctp_af_inet;
@@ -1012,7 +1017,6 @@ static struct inet_protosw sctp_seqpacket_protosw = {
 	.protocol   = IPPROTO_SCTP,
 	.prot       = &sctp_prot,
 	.ops        = &inet_seqpacket_ops,
-	.no_check   = 0,
 	.flags      = SCTP_PROTOSW_FLAG
 };
 static struct inet_protosw sctp_stream_protosw = {
@@ -1020,7 +1024,6 @@ static struct inet_protosw sctp_stream_protosw = {
 	.protocol   = IPPROTO_SCTP,
 	.prot       = &sctp_prot,
 	.ops        = &inet_seqpacket_ops,
-	.no_check   = 0,
 	.flags      = SCTP_PROTOSW_FLAG
 };
 
@@ -1030,6 +1033,7 @@ static const struct net_protocol sctp_protocol = {
 	.err_handler = sctp_v4_err,
 	.no_policy   = 1,
 	.netns_ok    = 1,
+	.icmp_strict_tag_validation = 1,
 };
 
 /* IPv4 address related functions.  */
@@ -1065,8 +1069,8 @@ static struct sctp_af sctp_af_inet = {
 #endif
 };
 
-struct sctp_pf *sctp_get_pf_specific(sa_family_t family) {
-
+struct sctp_pf *sctp_get_pf_specific(sa_family_t family)
+{
 	switch (family) {
 	case PF_INET:
 		return sctp_pf_inet_specific;
@@ -1099,14 +1103,15 @@ int sctp_register_pf(struct sctp_pf *pf, sa_family_t family)
 
 static inline int init_sctp_mibs(struct net *net)
 {
-	return snmp_mib_init((void __percpu **)net->sctp.sctp_statistics,
-			     sizeof(struct sctp_mib),
-			     __alignof__(struct sctp_mib));
+	net->sctp.sctp_statistics = alloc_percpu(struct sctp_mib);
+	if (!net->sctp.sctp_statistics)
+		return -ENOMEM;
+	return 0;
 }
 
 static inline void cleanup_sctp_mibs(struct net *net)
 {
-	snmp_mib_free((void __percpu **)net->sctp.sctp_statistics);
+	free_percpu(net->sctp.sctp_statistics);
 }
 
 static void sctp_v4_pf_init(void)
@@ -1460,7 +1465,6 @@ static __init int sctp_init(void)
 	if (status)
 		goto err_v6_add_protocol;
 
-	status = 0;
 out:
 	return status;
 err_v6_add_protocol:
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index d9aaf9641aa..ae0e616a7ca 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -78,6 +78,8 @@ static int sctp_process_param(struct sctp_association *asoc,
 			      gfp_t gfp);
 static void *sctp_addto_param(struct sctp_chunk *chunk, int len,
 			      const void *data);
+static void  *sctp_addto_chunk_fixed(struct sctp_chunk *, int len,
+				     const void *data);
 
 /* Control chunk destructor */
 static void sctp_control_release_owner(struct sk_buff *skb)
@@ -217,6 +219,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 			     gfp_t gfp, int vparam_len)
 {
 	struct net *net = sock_net(asoc->base.sk);
+	struct sctp_endpoint *ep = asoc->ep;
 	sctp_inithdr_t init;
 	union sctp_params addrs;
 	size_t chunksize;
@@ -276,7 +279,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 	chunksize += vparam_len;
 
 	/* Account for AUTH related parameters */
-	if (net->sctp.auth_enable) {
+	if (ep->auth_enable) {
 		/* Add random parameter length*/
 		chunksize += sizeof(asoc->c.auth_random);
 
@@ -361,7 +364,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 	}
 
 	/* Add SCTP-AUTH chunks to the parameter list */
-	if (net->sctp.auth_enable) {
+	if (ep->auth_enable) {
 		sctp_addto_chunk(retval, sizeof(asoc->c.auth_random),
 				 asoc->c.auth_random);
 		if (auth_hmacs)
@@ -1419,8 +1422,8 @@ static void sctp_chunk_destroy(struct sctp_chunk *chunk)
 	BUG_ON(!list_empty(&chunk->list));
 	list_del_init(&chunk->transmitted_list);
 
-	/* Free the chunk skb data and the SCTP_chunk stub itself. */
-	dev_kfree_skb(chunk->skb);
+	consume_skb(chunk->skb);
+	consume_skb(chunk->auth_chunk);
 
 	SCTP_DBG_OBJCNT_DEC(chunk);
 	kmem_cache_free(sctp_chunk_cachep, chunk);
@@ -1475,8 +1478,8 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data)
 /* Append bytes to the end of a chunk. Returns NULL if there isn't sufficient
  * space in the chunk
  */
-void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk,
-			     int len, const void *data)
+static void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk,
+				    int len, const void *data)
 {
 	if (skb_tailroom(chunk->skb) >= len)
 		return sctp_addto_chunk(chunk, len, data);
@@ -1779,7 +1782,7 @@ no_hmac:
 	else
 		kt = ktime_get();
 
-	if (!asoc && ktime_compare(bear_cookie->expiration, kt) < 0) {
+	if (!asoc && ktime_before(bear_cookie->expiration, kt)) {
 		/*
 		 * Section 3.3.10.3 Stale Cookie Error (3)
 		 *
@@ -1967,13 +1970,13 @@ static int sctp_verify_ext_param(struct net *net, union sctp_params param)
 
 	for (i = 0; i < num_ext; i++) {
 		switch (param.ext->chunks[i]) {
-		    case SCTP_CID_AUTH:
-			    have_auth = 1;
-			    break;
-		    case SCTP_CID_ASCONF:
-		    case SCTP_CID_ASCONF_ACK:
-			    have_asconf = 1;
-			    break;
+		case SCTP_CID_AUTH:
+			have_auth = 1;
+			break;
+		case SCTP_CID_ASCONF:
+		case SCTP_CID_ASCONF_ACK:
+			have_asconf = 1;
+			break;
 		}
 	}
 
@@ -2000,25 +2003,24 @@ static void sctp_process_ext_param(struct sctp_association *asoc,
 
 	for (i = 0; i < num_ext; i++) {
 		switch (param.ext->chunks[i]) {
-		    case SCTP_CID_FWD_TSN:
-			    if (net->sctp.prsctp_enable &&
-				!asoc->peer.prsctp_capable)
+		case SCTP_CID_FWD_TSN:
+			if (net->sctp.prsctp_enable && !asoc->peer.prsctp_capable)
 				    asoc->peer.prsctp_capable = 1;
-			    break;
-		    case SCTP_CID_AUTH:
-			    /* if the peer reports AUTH, assume that he
-			     * supports AUTH.
-			     */
-			    if (net->sctp.auth_enable)
-				    asoc->peer.auth_capable = 1;
-			    break;
-		    case SCTP_CID_ASCONF:
-		    case SCTP_CID_ASCONF_ACK:
-			    if (net->sctp.addip_enable)
-				    asoc->peer.asconf_capable = 1;
-			    break;
-		    default:
-			    break;
+			break;
+		case SCTP_CID_AUTH:
+			/* if the peer reports AUTH, assume that he
+			 * supports AUTH.
+			 */
+			if (asoc->ep->auth_enable)
+				asoc->peer.auth_capable = 1;
+			break;
+		case SCTP_CID_ASCONF:
+		case SCTP_CID_ASCONF_ACK:
+			if (net->sctp.addip_enable)
+				asoc->peer.asconf_capable = 1;
+			break;
+		default:
+			break;
 		}
 	}
 }
@@ -2101,6 +2103,7 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc,
  * 	SCTP_IERROR_NO_ERROR - continue with the chunk
  */
 static sctp_ierror_t sctp_verify_param(struct net *net,
+					const struct sctp_endpoint *ep,
 					const struct sctp_association *asoc,
 					union sctp_params param,
 					sctp_cid_t cid,
@@ -2151,7 +2154,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net,
 		goto fallthrough;
 
 	case SCTP_PARAM_RANDOM:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fallthrough;
 
 		/* SCTP-AUTH: Secion 6.1
@@ -2168,7 +2171,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net,
 		break;
 
 	case SCTP_PARAM_CHUNKS:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fallthrough;
 
 		/* SCTP-AUTH: Section 3.2
@@ -2184,7 +2187,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net,
 		break;
 
 	case SCTP_PARAM_HMAC_ALGO:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fallthrough;
 
 		hmacs = (struct sctp_hmac_algo_param *)param.p;
@@ -2219,10 +2222,9 @@ fallthrough:
 }
 
 /* Verify the INIT packet before we process it.  */
-int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
-		     sctp_cid_t cid,
-		     sctp_init_chunk_t *peer_init,
-		     struct sctp_chunk *chunk,
+int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep,
+		     const struct sctp_association *asoc, sctp_cid_t cid,
+		     sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk,
 		     struct sctp_chunk **errp)
 {
 	union sctp_params param;
@@ -2251,7 +2253,7 @@ int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
 	 * VIOLATION error.  We build the ERROR chunk here and let the normal
 	 * error handling code build and send the packet.
 	 */
-	if (param.v != (void*)chunk->chunk_end)
+	if (param.v != (void *)chunk->chunk_end)
 		return sctp_process_inv_paramlength(asoc, param.p, chunk, errp);
 
 	/* The only missing mandatory param possible today is
@@ -2263,17 +2265,17 @@ int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
 
 	/* Verify all the variable length parameters */
 	sctp_walk_params(param, peer_init, init_hdr.params) {
-
-		result = sctp_verify_param(net, asoc, param, cid, chunk, errp);
+		result = sctp_verify_param(net, ep, asoc, param, cid,
+					   chunk, errp);
 		switch (result) {
-		    case SCTP_IERROR_ABORT:
-		    case SCTP_IERROR_NOMEM:
-				return 0;
-		    case SCTP_IERROR_ERROR:
-				return 1;
-		    case SCTP_IERROR_NO_ERROR:
-		    default:
-				break;
+		case SCTP_IERROR_ABORT:
+		case SCTP_IERROR_NOMEM:
+			return 0;
+		case SCTP_IERROR_ERROR:
+			return 1;
+		case SCTP_IERROR_NO_ERROR:
+		default:
+			break;
 		}
 
 	} /* for (loop through all parameters) */
@@ -2308,7 +2310,7 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
 	 * added as the primary transport.  The source address seems to
 	 * be a a better choice than any of the embedded addresses.
 	 */
-	if(!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE))
+	if (!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE))
 		goto nomem;
 
 	if (sctp_cmp_addr_exact(sctp_source(chunk), peer_addr))
@@ -2496,6 +2498,7 @@ static int sctp_process_param(struct sctp_association *asoc,
 	struct sctp_af *af;
 	union sctp_addr_param *addr_param;
 	struct sctp_transport *t;
+	struct sctp_endpoint *ep = asoc->ep;
 
 	/* We maintain all INIT parameters in network byte order all the
 	 * time.  This allows us to not worry about whether the parameters
@@ -2635,7 +2638,7 @@ do_addr_param:
 		goto fall_through;
 
 	case SCTP_PARAM_RANDOM:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fall_through;
 
 		/* Save peer's random parameter */
@@ -2648,7 +2651,7 @@ do_addr_param:
 		break;
 
 	case SCTP_PARAM_HMAC_ALGO:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fall_through;
 
 		/* Save peer's HMAC list */
@@ -2664,7 +2667,7 @@ do_addr_param:
 		break;
 
 	case SCTP_PARAM_CHUNKS:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fall_through;
 
 		asoc->peer.peer_chunks = kmemdup(param.p,
@@ -3334,7 +3337,7 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack,
 
 	while (asconf_ack_len > 0) {
 		if (asconf_ack_param->crr_id == asconf_param->crr_id) {
-			switch(asconf_ack_param->param_hdr.type) {
+			switch (asconf_ack_param->param_hdr.type) {
 			case SCTP_PARAM_SUCCESS_REPORT:
 				return SCTP_ERROR_NO_ERROR;
 			case SCTP_PARAM_ERR_CAUSE:
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 02b7ad1ff46..fef2acdf4a2 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -248,7 +248,7 @@ void sctp_generate_t3_rtx_event(unsigned long peer)
 
 	/* Check whether a task is in the sock.  */
 
-	sctp_bh_lock_sock(asoc->base.sk);
+	bh_lock_sock(asoc->base.sk);
 	if (sock_owned_by_user(asoc->base.sk)) {
 		pr_debug("%s: sock is busy\n", __func__);
 
@@ -275,7 +275,7 @@ void sctp_generate_t3_rtx_event(unsigned long peer)
 		asoc->base.sk->sk_err = -error;
 
 out_unlock:
-	sctp_bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(asoc->base.sk);
 	sctp_transport_put(transport);
 }
 
@@ -288,7 +288,7 @@ static void sctp_generate_timeout_event(struct sctp_association *asoc,
 	struct net *net = sock_net(asoc->base.sk);
 	int error = 0;
 
-	sctp_bh_lock_sock(asoc->base.sk);
+	bh_lock_sock(asoc->base.sk);
 	if (sock_owned_by_user(asoc->base.sk)) {
 		pr_debug("%s: sock is busy: timer %d\n", __func__,
 			 timeout_type);
@@ -315,7 +315,7 @@ static void sctp_generate_timeout_event(struct sctp_association *asoc,
 		asoc->base.sk->sk_err = -error;
 
 out_unlock:
-	sctp_bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(asoc->base.sk);
 	sctp_association_put(asoc);
 }
 
@@ -367,7 +367,7 @@ void sctp_generate_heartbeat_event(unsigned long data)
 	struct sctp_association *asoc = transport->asoc;
 	struct net *net = sock_net(asoc->base.sk);
 
-	sctp_bh_lock_sock(asoc->base.sk);
+	bh_lock_sock(asoc->base.sk);
 	if (sock_owned_by_user(asoc->base.sk)) {
 		pr_debug("%s: sock is busy\n", __func__);
 
@@ -392,7 +392,7 @@ void sctp_generate_heartbeat_event(unsigned long data)
 		 asoc->base.sk->sk_err = -error;
 
 out_unlock:
-	sctp_bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(asoc->base.sk);
 	sctp_transport_put(transport);
 }
 
@@ -404,8 +404,8 @@ void sctp_generate_proto_unreach_event(unsigned long data)
 	struct sctp_transport *transport = (struct sctp_transport *) data;
 	struct sctp_association *asoc = transport->asoc;
 	struct net *net = sock_net(asoc->base.sk);
-	
-	sctp_bh_lock_sock(asoc->base.sk);
+
+	bh_lock_sock(asoc->base.sk);
 	if (sock_owned_by_user(asoc->base.sk)) {
 		pr_debug("%s: sock is busy\n", __func__);
 
@@ -427,7 +427,7 @@ void sctp_generate_proto_unreach_event(unsigned long data)
 		   asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC);
 
 out_unlock:
-	sctp_bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(asoc->base.sk);
 	sctp_association_put(asoc);
 }
 
@@ -495,11 +495,11 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands,
 	}
 
 	/* If the transport error count is greater than the pf_retrans
-	 * threshold, and less than pathmaxrtx, then mark this transport
-	 * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1,
-	 * point 1
+	 * threshold, and less than pathmaxrtx, and if the current state
+	 * is SCTP_ACTIVE, then mark this transport as Partially Failed,
+	 * see SCTP Quick Failover Draft, section 5.1
 	 */
-	if ((transport->state != SCTP_PF) &&
+	if ((transport->state == SCTP_ACTIVE) &&
 	   (asoc->pf_retrans < transport->pathmaxrxt) &&
 	   (transport->error_count > asoc->pf_retrans)) {
 
@@ -543,7 +543,7 @@ static void sctp_cmd_init_failed(sctp_cmd_seq_t *commands,
 {
 	struct sctp_ulpevent *event;
 
-	event = sctp_ulpevent_make_assoc_change(asoc,0, SCTP_CANT_STR_ASSOC,
+	event = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_CANT_STR_ASSOC,
 						(__u16)error, 0, 0, NULL,
 						GFP_ATOMIC);
 
@@ -1115,7 +1115,7 @@ int sctp_do_sm(struct net *net, sctp_event_t event_type, sctp_subtype_t subtype,
 	sctp_init_cmd_seq(&commands);
 
 	debug_pre_sfn();
-	status = (*state_fn->fn)(net, ep, asoc, subtype, event_arg, &commands);
+	status = state_fn->fn(net, ep, asoc, subtype, event_arg, &commands);
 	debug_post_sfn();
 
 	error = sctp_side_effects(event_type, subtype, state,
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index dd0eba919a8..5170a1ff95a 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -357,7 +357,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net,
 
 	/* Verify the INIT chunk before processing it. */
 	err_chunk = NULL;
-	if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+	if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
 			      (sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
 			      &err_chunk)) {
 		/* This chunk contains fatal error. It is to be discarded.
@@ -524,7 +524,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net,
 
 	/* Verify the INIT chunk before processing it. */
 	err_chunk = NULL;
-	if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+	if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
 			      (sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
 			      &err_chunk)) {
 
@@ -758,6 +758,12 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net,
 		struct sctp_chunk auth;
 		sctp_ierror_t ret;
 
+		/* Make sure that we and the peer are AUTH capable */
+		if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
+			sctp_association_free(new_asoc);
+			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+		}
+
 		/* set-up our fake chunk so that we can process it */
 		auth.skb = chunk->auth_chunk;
 		auth.asoc = chunk->asoc;
@@ -768,10 +774,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net,
 		auth.transport = chunk->transport;
 
 		ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
-
-		/* We can now safely free the auth_chunk clone */
-		kfree_skb(chunk->auth_chunk);
-
 		if (ret != SCTP_IERROR_NO_ERROR) {
 			sctp_association_free(new_asoc);
 			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -819,7 +821,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net,
 	SCTP_INC_STATS(net, SCTP_MIB_PASSIVEESTABS);
 	sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL());
 
-	if (new_asoc->autoclose)
+	if (new_asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE])
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE));
 
@@ -907,7 +909,7 @@ sctp_disposition_t sctp_sf_do_5_1E_ca(struct net *net,
 	SCTP_INC_STATS(net, SCTP_MIB_CURRESTAB);
 	SCTP_INC_STATS(net, SCTP_MIB_ACTIVEESTABS);
 	sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL());
-	if (asoc->autoclose)
+	if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE])
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE));
 
@@ -1428,7 +1430,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init(
 
 	/* Verify the INIT chunk before processing it. */
 	err_chunk = NULL;
-	if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+	if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
 			      (sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
 			      &err_chunk)) {
 		/* This chunk contains fatal error. It is to be discarded.
@@ -2945,7 +2947,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(struct net *net,
 		return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
 						  commands);
 
-	error = sctp_eat_data(asoc, chunk, commands );
+	error = sctp_eat_data(asoc, chunk, commands);
 	switch (error) {
 	case SCTP_IERROR_NO_ERROR:
 		break;
@@ -2969,7 +2971,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(struct net *net,
 	if (chunk->chunk_hdr->flags & SCTP_DATA_SACK_IMM)
 		force = SCTP_FORCE();
 
-	if (asoc->autoclose) {
+	if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) {
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE));
 	}
@@ -3066,7 +3068,7 @@ sctp_disposition_t sctp_sf_eat_data_fast_4_4(struct net *net,
 		return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
 						  commands);
 
-	error = sctp_eat_data(asoc, chunk, commands );
+	error = sctp_eat_data(asoc, chunk, commands);
 	switch (error) {
 	case SCTP_IERROR_NO_ERROR:
 	case SCTP_IERROR_HIGH_TSN:
@@ -3681,8 +3683,7 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net,
 	asconf_ack->dest = chunk->source;
 	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(asconf_ack));
 	if (asoc->new_transport) {
-	        sctp_sf_heartbeat(ep, asoc, type, asoc->new_transport,
-                    commands);
+		sctp_sf_heartbeat(ep, asoc, type, asoc->new_transport, commands);
 		((struct sctp_association *)asoc)->new_transport = NULL;
 	}
 
@@ -3765,7 +3766,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net,
 		 */
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
-		sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET,SCTP_NULL());
+		sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL());
 		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
 				SCTP_ERROR(ECONNABORTED));
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
@@ -3799,7 +3800,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net,
 		/* We are going to ABORT, so we might as well stop
 		 * processing the rest of the chunks in the packet.
 		 */
-		sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET,SCTP_NULL());
+		sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL());
 		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
 				SCTP_ERROR(ECONNABORTED));
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
@@ -3877,7 +3878,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn(struct net *net,
 				SCTP_CHUNK(chunk));
 
 	/* Count this as receiving DATA. */
-	if (asoc->autoclose) {
+	if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) {
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE));
 	}
@@ -4451,7 +4452,7 @@ static sctp_disposition_t sctp_sf_violation_chunklen(
 				     void *arg,
 				     sctp_cmd_seq_t *commands)
 {
-	static const char err_str[]="The following chunk had invalid length:";
+	static const char err_str[] = "The following chunk had invalid length:";
 
 	return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str,
 					sizeof(err_str));
@@ -4514,7 +4515,7 @@ static sctp_disposition_t sctp_sf_violation_ctsn(
 				     void *arg,
 				     sctp_cmd_seq_t *commands)
 {
-	static const char err_str[]="The cumulative tsn ack beyond the max tsn currently sent:";
+	static const char err_str[] = "The cumulative tsn ack beyond the max tsn currently sent:";
 
 	return sctp_sf_abort_violation(net, ep, asoc, arg, commands, err_str,
 					sizeof(err_str));
@@ -4534,7 +4535,7 @@ static sctp_disposition_t sctp_sf_violation_chunk(
 				     void *arg,
 				     sctp_cmd_seq_t *commands)
 {
-	static const char err_str[]="The following chunk violates protocol:";
+	static const char err_str[] = "The following chunk violates protocol:";
 
 	if (!asoc)
 		return sctp_sf_violation(net, ep, asoc, type, arg, commands);
@@ -4610,7 +4611,7 @@ sctp_disposition_t sctp_sf_do_prm_asoc(struct net *net,
 				       sctp_cmd_seq_t *commands)
 {
 	struct sctp_chunk *repl;
-	struct sctp_association* my_asoc;
+	struct sctp_association *my_asoc;
 
 	/* The comment below says that we enter COOKIE-WAIT AFTER
 	 * sending the INIT, but that doesn't actually work in our
@@ -5266,7 +5267,7 @@ sctp_disposition_t sctp_sf_do_9_2_start_shutdown(
 	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART,
 			SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD));
 
-	if (asoc->autoclose)
+	if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE])
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE));
 
@@ -5345,7 +5346,7 @@ sctp_disposition_t sctp_sf_do_9_2_shutdown_ack(
 	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART,
 			SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN));
 
-	if (asoc->autoclose)
+	if (asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE])
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE));
 
@@ -6000,7 +6001,7 @@ static struct sctp_packet *sctp_ootb_pkt_new(struct net *net,
 		/* Special case the INIT-ACK as there is no peer's vtag
 		 * yet.
 		 */
-		switch(chunk->chunk_hdr->type) {
+		switch (chunk->chunk_hdr->type) {
 		case SCTP_CID_INIT_ACK:
 		{
 			sctp_initack_chunk_t *initack;
@@ -6017,7 +6018,7 @@ static struct sctp_packet *sctp_ootb_pkt_new(struct net *net,
 		/* Special case the INIT and stale COOKIE_ECHO as there is no
 		 * vtag yet.
 		 */
-		switch(chunk->chunk_hdr->type) {
+		switch (chunk->chunk_hdr->type) {
 		case SCTP_CID_INIT:
 		{
 			sctp_init_chunk_t *init;
@@ -6207,7 +6208,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	 */
 	if (*sk->sk_prot_creator->memory_pressure) {
 		if (sctp_tsnmap_has_gap(map) &&
-	           (sctp_tsnmap_get_ctsn(map) + 1) == tsn) {
+		    (sctp_tsnmap_get_ctsn(map) + 1) == tsn) {
 			pr_debug("%s: under pressure, reneging for tsn:%u\n",
 				 __func__, tsn);
 			deliver = SCTP_CMD_RENEGE;
@@ -6231,7 +6232,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 		/* We are going to ABORT, so we might as well stop
 		 * processing the rest of the chunks in the packet.
 		 */
-		sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET,SCTP_NULL());
+		sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL());
 		sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
 				SCTP_ERROR(ECONNABORTED));
 		sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c
index a4f17437fb2..a987d54b379 100644
--- a/net/sctp/sm_statetable.c
+++ b/net/sctp/sm_statetable.c
@@ -69,7 +69,7 @@ static const sctp_sm_table_entry_t bug = {
 	if ((event_subtype._type > (_max))) {				\
 		pr_warn("table %p possible attack: event %d exceeds max %d\n", \
 			_table, event_subtype._type, _max);		\
-	        rtn = &bug;						\
+		rtn = &bug;						\
 	} else								\
 		rtn = &_table[event_subtype._type][(int)state];		\
 									\
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 191cd925780..42989968940 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -64,12 +64,14 @@
 #include <linux/crypto.h>
 #include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/compat.h>
 
 #include <net/ip.h>
 #include <net/icmp.h>
 #include <net/route.h>
 #include <net/ipv6.h>
 #include <net/inet_common.h>
+#include <net/busy_poll.h>
 
 #include <linux/socket.h> /* for sa_family_t */
 #include <linux/export.h>
@@ -82,7 +84,7 @@ static int sctp_writeable(struct sock *sk);
 static void sctp_wfree(struct sk_buff *skb);
 static int sctp_wait_for_sndbuf(struct sctp_association *, long *timeo_p,
 				size_t msg_len);
-static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p);
+static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p);
 static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p);
 static int sctp_wait_for_accept(struct sock *sk, long timeo);
 static void sctp_wait_for_close(struct sock *sk, long timeo);
@@ -272,7 +274,7 @@ static int sctp_bind(struct sock *sk, struct sockaddr *addr, int addr_len)
 {
 	int retval = 0;
 
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 
 	pr_debug("%s: sk:%p, addr:%p, addr_len:%d\n", __func__, sk,
 		 addr, addr_len);
@@ -284,7 +286,7 @@ static int sctp_bind(struct sock *sk, struct sockaddr *addr, int addr_len)
 	else
 		retval = -EINVAL;
 
-	sctp_release_sock(sk);
+	release_sock(sk);
 
 	return retval;
 }
@@ -952,7 +954,7 @@ int sctp_asconf_mgmt(struct sctp_sock *sp, struct sctp_sockaddr_entry *addrw)
  *
  * Returns 0 if ok, <0 errno code on error.
  */
-static int sctp_setsockopt_bindx(struct sock* sk,
+static int sctp_setsockopt_bindx(struct sock *sk,
 				 struct sockaddr __user *addrs,
 				 int addrs_size, int op)
 {
@@ -1039,7 +1041,7 @@ out:
  * Common routine for handling connect() and sctp_connectx().
  * Connect will come in with just a single address.
  */
-static int __sctp_connect(struct sock* sk,
+static int __sctp_connect(struct sock *sk,
 			  struct sockaddr *kaddrs,
 			  int addrs_size,
 			  sctp_assoc_t *assoc_id)
@@ -1299,7 +1301,7 @@ out_free:
  *
  * Returns >=0 if ok, <0 errno code on error.
  */
-static int __sctp_setsockopt_connectx(struct sock* sk,
+static int __sctp_setsockopt_connectx(struct sock *sk,
 				      struct sockaddr __user *addrs,
 				      int addrs_size,
 				      sctp_assoc_t *assoc_id)
@@ -1337,7 +1339,7 @@ static int __sctp_setsockopt_connectx(struct sock* sk,
  * This is an older interface.  It's kept for backward compatibility
  * to the option that doesn't provide association id.
  */
-static int sctp_setsockopt_connectx_old(struct sock* sk,
+static int sctp_setsockopt_connectx_old(struct sock *sk,
 					struct sockaddr __user *addrs,
 					int addrs_size)
 {
@@ -1350,7 +1352,7 @@ static int sctp_setsockopt_connectx_old(struct sock* sk,
  * indication to the call.  Error is always negative and association id is
  * always positive.
  */
-static int sctp_setsockopt_connectx(struct sock* sk,
+static int sctp_setsockopt_connectx(struct sock *sk,
 				    struct sockaddr __user *addrs,
 				    int addrs_size)
 {
@@ -1368,12 +1370,20 @@ static int sctp_setsockopt_connectx(struct sock* sk,
 /*
  * New (hopefully final) interface for the API.
  * We use the sctp_getaddrs_old structure so that use-space library
- * can avoid any unnecessary allocations.   The only defferent part
+ * can avoid any unnecessary allocations. The only different part
  * is that we store the actual length of the address buffer into the
- * addrs_num structure member.  That way we can re-use the existing
+ * addrs_num structure member. That way we can re-use the existing
  * code.
  */
-static int sctp_getsockopt_connectx3(struct sock* sk, int len,
+#ifdef CONFIG_COMPAT
+struct compat_sctp_getaddrs_old {
+	sctp_assoc_t	assoc_id;
+	s32		addr_num;
+	compat_uptr_t	addrs;		/* struct sockaddr * */
+};
+#endif
+
+static int sctp_getsockopt_connectx3(struct sock *sk, int len,
 				     char __user *optval,
 				     int __user *optlen)
 {
@@ -1381,16 +1391,30 @@ static int sctp_getsockopt_connectx3(struct sock* sk, int len,
 	sctp_assoc_t assoc_id = 0;
 	int err = 0;
 
-	if (len < sizeof(param))
-		return -EINVAL;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task()) {
+		struct compat_sctp_getaddrs_old param32;
 
-	if (copy_from_user(&param, optval, sizeof(param)))
-		return -EFAULT;
+		if (len < sizeof(param32))
+			return -EINVAL;
+		if (copy_from_user(&param32, optval, sizeof(param32)))
+			return -EFAULT;
 
-	err = __sctp_setsockopt_connectx(sk,
-			(struct sockaddr __user *)param.addrs,
-			param.addr_num, &assoc_id);
+		param.assoc_id = param32.assoc_id;
+		param.addr_num = param32.addr_num;
+		param.addrs = compat_ptr(param32.addrs);
+	} else
+#endif
+	{
+		if (len < sizeof(param))
+			return -EINVAL;
+		if (copy_from_user(&param, optval, sizeof(param)))
+			return -EFAULT;
+	}
 
+	err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *)
+					 param.addrs, param.addr_num,
+					 &assoc_id);
 	if (err == 0 || err == -EINPROGRESS) {
 		if (copy_to_user(optval, &assoc_id, sizeof(assoc_id)))
 			return -EFAULT;
@@ -1461,7 +1485,7 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	pr_debug("%s: sk:%p, timeout:%ld\n", __func__, sk, timeout);
 
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 	sk->sk_state = SCTP_SS_CLOSING;
 
@@ -1505,13 +1529,13 @@ static void sctp_close(struct sock *sk, long timeout)
 		sctp_wait_for_close(sk, timeout);
 
 	/* This will run the backlog queue.  */
-	sctp_release_sock(sk);
+	release_sock(sk);
 
 	/* Supposedly, no process has access to the socket, but
 	 * the net layers still may.
 	 */
-	sctp_local_bh_disable();
-	sctp_bh_lock_sock(sk);
+	local_bh_disable();
+	bh_lock_sock(sk);
 
 	/* Hold the sock, since sk_common_release() will put sock_put()
 	 * and we have just a little more cleanup.
@@ -1519,8 +1543,8 @@ static void sctp_close(struct sock *sk, long timeout)
 	sock_hold(sk);
 	sk_common_release(sk);
 
-	sctp_bh_unlock_sock(sk);
-	sctp_local_bh_enable();
+	bh_unlock_sock(sk);
+	local_bh_enable();
 
 	sock_put(sk);
 
@@ -1568,7 +1592,7 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 	struct net *net = sock_net(sk);
 	struct sctp_sock *sp;
 	struct sctp_endpoint *ep;
-	struct sctp_association *new_asoc=NULL, *asoc=NULL;
+	struct sctp_association *new_asoc = NULL, *asoc = NULL;
 	struct sctp_transport *transport, *chunk_tp;
 	struct sctp_chunk *chunk;
 	union sctp_addr to;
@@ -1665,7 +1689,7 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 	pr_debug("%s: about to look up association\n", __func__);
 
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 
 	/* If a msg_name has been specified, assume this is to be used.  */
 	if (msg_name) {
@@ -1743,7 +1767,7 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
 		 * either the default or the user specified stream counts.
 		 */
 		if (sinfo) {
-			if (!sinit || (sinit && !sinit->sinit_num_ostreams)) {
+			if (!sinit || !sinit->sinit_num_ostreams) {
 				/* Check against the defaults. */
 				if (sinfo->sinfo_stream >=
 				    sp->initmsg.sinit_num_ostreams) {
@@ -1949,7 +1973,7 @@ out_free:
 		sctp_association_free(asoc);
 	}
 out_unlock:
-	sctp_release_sock(sk);
+	release_sock(sk);
 
 out_nounlock:
 	return sctp_error(sk, msg_flags, err);
@@ -2035,7 +2059,7 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk,
 		 "addr_len:%p)\n", __func__, sk, msg, len, noblock, flags,
 		 addr_len);
 
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 
 	if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED)) {
 		err = -ENOTCONN;
@@ -2119,7 +2143,7 @@ out_free:
 		sctp_ulpevent_free(event);
 	}
 out:
-	sctp_release_sock(sk);
+	release_sock(sk);
 	return err;
 }
 
@@ -2195,6 +2219,7 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval,
 				     unsigned int optlen)
 {
 	struct sctp_sock *sp = sctp_sk(sk);
+	struct net *net = sock_net(sk);
 
 	/* Applicable to UDP-style socket only */
 	if (sctp_style(sk, TCP))
@@ -2204,6 +2229,9 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval,
 	if (copy_from_user(&sp->autoclose, optval, optlen))
 		return -EFAULT;
 
+	if (sp->autoclose > net->sctp.max_autoclose)
+		sp->autoclose = net->sctp.max_autoclose;
+
 	return 0;
 }
 
@@ -2458,7 +2486,7 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk,
 	int hb_change, pmtud_change, sackdelay_change;
 
 	if (optlen != sizeof(struct sctp_paddrparams))
-		return - EINVAL;
+		return -EINVAL;
 
 	if (copy_from_user(&params, optval, optlen))
 		return -EFAULT;
@@ -2479,7 +2507,7 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk,
 	/* If an address other than INADDR_ANY is specified, and
 	 * no transport is found, then the request is invalid.
 	 */
-	if (!sctp_is_any(sk, ( union sctp_addr *)&params.spp_address)) {
+	if (!sctp_is_any(sk, (union sctp_addr *)&params.spp_address)) {
 		trans = sctp_addr_id2transport(sk, &params.spp_address,
 					       params.spp_assoc_id);
 		if (!trans)
@@ -2523,6 +2551,16 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk,
 	return 0;
 }
 
+static inline __u32 sctp_spp_sackdelay_enable(__u32 param_flags)
+{
+	return (param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_ENABLE;
+}
+
+static inline __u32 sctp_spp_sackdelay_disable(__u32 param_flags)
+{
+	return (param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_DISABLE;
+}
+
 /*
  * 7.1.23.  Get or set delayed ack timer (SCTP_DELAYED_SACK)
  *
@@ -2574,8 +2612,11 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk,
 		if (params.sack_delay == 0 && params.sack_freq == 0)
 			return 0;
 	} else if (optlen == sizeof(struct sctp_assoc_value)) {
-		pr_warn("Use of struct sctp_assoc_value in delayed_ack socket option deprecated\n");
-		pr_warn("Use struct sctp_sack_info instead\n");
+		pr_warn_ratelimited(DEPRECATED
+				    "%s (pid %d) "
+				    "Use of struct sctp_assoc_value in delayed_ack socket option.\n"
+				    "Use struct sctp_sack_info instead\n",
+				    current->comm, task_pid_nr(current));
 		if (copy_from_user(&params, optval, optlen))
 			return -EFAULT;
 
@@ -2584,7 +2625,7 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk,
 		else
 			params.sack_freq = 0;
 	} else
-		return - EINVAL;
+		return -EINVAL;
 
 	/* Validate value parameter. */
 	if (params.sack_delay > 500)
@@ -2603,37 +2644,31 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk,
 			asoc->sackdelay =
 				msecs_to_jiffies(params.sack_delay);
 			asoc->param_flags =
-				(asoc->param_flags & ~SPP_SACKDELAY) |
-				SPP_SACKDELAY_ENABLE;
+				sctp_spp_sackdelay_enable(asoc->param_flags);
 		} else {
 			sp->sackdelay = params.sack_delay;
 			sp->param_flags =
-				(sp->param_flags & ~SPP_SACKDELAY) |
-				SPP_SACKDELAY_ENABLE;
+				sctp_spp_sackdelay_enable(sp->param_flags);
 		}
 	}
 
 	if (params.sack_freq == 1) {
 		if (asoc) {
 			asoc->param_flags =
-				(asoc->param_flags & ~SPP_SACKDELAY) |
-				SPP_SACKDELAY_DISABLE;
+				sctp_spp_sackdelay_disable(asoc->param_flags);
 		} else {
 			sp->param_flags =
-				(sp->param_flags & ~SPP_SACKDELAY) |
-				SPP_SACKDELAY_DISABLE;
+				sctp_spp_sackdelay_disable(sp->param_flags);
 		}
 	} else if (params.sack_freq > 1) {
 		if (asoc) {
 			asoc->sackfreq = params.sack_freq;
 			asoc->param_flags =
-				(asoc->param_flags & ~SPP_SACKDELAY) |
-				SPP_SACKDELAY_ENABLE;
+				sctp_spp_sackdelay_enable(asoc->param_flags);
 		} else {
 			sp->sackfreq = params.sack_freq;
 			sp->param_flags =
-				(sp->param_flags & ~SPP_SACKDELAY) |
-				SPP_SACKDELAY_ENABLE;
+				sctp_spp_sackdelay_enable(sp->param_flags);
 		}
 	}
 
@@ -2645,18 +2680,15 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk,
 				trans->sackdelay =
 					msecs_to_jiffies(params.sack_delay);
 				trans->param_flags =
-					(trans->param_flags & ~SPP_SACKDELAY) |
-					SPP_SACKDELAY_ENABLE;
+					sctp_spp_sackdelay_enable(trans->param_flags);
 			}
 			if (params.sack_freq == 1) {
 				trans->param_flags =
-					(trans->param_flags & ~SPP_SACKDELAY) |
-					SPP_SACKDELAY_DISABLE;
+					sctp_spp_sackdelay_disable(trans->param_flags);
 			} else if (params.sack_freq > 1) {
 				trans->sackfreq = params.sack_freq;
 				trans->param_flags =
-					(trans->param_flags & ~SPP_SACKDELAY) |
-					SPP_SACKDELAY_ENABLE;
+					sctp_spp_sackdelay_enable(trans->param_flags);
 			}
 		}
 	}
@@ -2810,6 +2842,8 @@ static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, unsigne
 {
 	struct sctp_rtoinfo rtoinfo;
 	struct sctp_association *asoc;
+	unsigned long rto_min, rto_max;
+	struct sctp_sock *sp = sctp_sk(sk);
 
 	if (optlen != sizeof (struct sctp_rtoinfo))
 		return -EINVAL;
@@ -2823,26 +2857,36 @@ static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, unsigne
 	if (!asoc && rtoinfo.srto_assoc_id && sctp_style(sk, UDP))
 		return -EINVAL;
 
+	rto_max = rtoinfo.srto_max;
+	rto_min = rtoinfo.srto_min;
+
+	if (rto_max)
+		rto_max = asoc ? msecs_to_jiffies(rto_max) : rto_max;
+	else
+		rto_max = asoc ? asoc->rto_max : sp->rtoinfo.srto_max;
+
+	if (rto_min)
+		rto_min = asoc ? msecs_to_jiffies(rto_min) : rto_min;
+	else
+		rto_min = asoc ? asoc->rto_min : sp->rtoinfo.srto_min;
+
+	if (rto_min > rto_max)
+		return -EINVAL;
+
 	if (asoc) {
 		if (rtoinfo.srto_initial != 0)
 			asoc->rto_initial =
 				msecs_to_jiffies(rtoinfo.srto_initial);
-		if (rtoinfo.srto_max != 0)
-			asoc->rto_max = msecs_to_jiffies(rtoinfo.srto_max);
-		if (rtoinfo.srto_min != 0)
-			asoc->rto_min = msecs_to_jiffies(rtoinfo.srto_min);
+		asoc->rto_max = rto_max;
+		asoc->rto_min = rto_min;
 	} else {
 		/* If there is no association or the association-id = 0
 		 * set the values to the endpoint.
 		 */
-		struct sctp_sock *sp = sctp_sk(sk);
-
 		if (rtoinfo.srto_initial != 0)
 			sp->rtoinfo.srto_initial = rtoinfo.srto_initial;
-		if (rtoinfo.srto_max != 0)
-			sp->rtoinfo.srto_max = rtoinfo.srto_max;
-		if (rtoinfo.srto_min != 0)
-			sp->rtoinfo.srto_min = rtoinfo.srto_min;
+		sp->rtoinfo.srto_max = rto_max;
+		sp->rtoinfo.srto_min = rto_min;
 	}
 
 	return 0;
@@ -2978,8 +3022,11 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned
 	int val;
 
 	if (optlen == sizeof(int)) {
-		pr_warn("Use of int in maxseg socket option deprecated\n");
-		pr_warn("Use struct sctp_assoc_value instead\n");
+		pr_warn_ratelimited(DEPRECATED
+				    "%s (pid %d) "
+				    "Use of int in maxseg socket option.\n"
+				    "Use struct sctp_assoc_value instead\n",
+				    current->comm, task_pid_nr(current));
 		if (copy_from_user(&val, optval, optlen))
 			return -EFAULT;
 		params.assoc_id = 0;
@@ -3236,8 +3283,11 @@ static int sctp_setsockopt_maxburst(struct sock *sk,
 	int assoc_id = 0;
 
 	if (optlen == sizeof(int)) {
-		pr_warn("Use of int in max_burst socket option deprecated\n");
-		pr_warn("Use struct sctp_assoc_value instead\n");
+		pr_warn_ratelimited(DEPRECATED
+				    "%s (pid %d) "
+				    "Use of int in max_burst socket option deprecated.\n"
+				    "Use struct sctp_assoc_value instead\n",
+				    current->comm, task_pid_nr(current));
 		if (copy_from_user(&val, optval, optlen))
 			return -EFAULT;
 	} else if (optlen == sizeof(struct sctp_assoc_value)) {
@@ -3272,10 +3322,10 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk,
 				      char __user *optval,
 				      unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authchunk val;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen != sizeof(struct sctp_authchunk))
@@ -3292,7 +3342,7 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk,
 	}
 
 	/* add this chunk id to the endpoint */
-	return sctp_auth_ep_add_chunkid(sctp_sk(sk)->ep, val.sauth_chunk);
+	return sctp_auth_ep_add_chunkid(ep, val.sauth_chunk);
 }
 
 /*
@@ -3305,18 +3355,18 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk,
 				      char __user *optval,
 				      unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_hmacalgo *hmacs;
 	u32 idents;
 	int err;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen < sizeof(struct sctp_hmacalgo))
 		return -EINVAL;
 
-	hmacs= memdup_user(optval, optlen);
+	hmacs = memdup_user(optval, optlen);
 	if (IS_ERR(hmacs))
 		return PTR_ERR(hmacs);
 
@@ -3327,7 +3377,7 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk,
 		goto out;
 	}
 
-	err = sctp_auth_ep_set_hmacs(sctp_sk(sk)->ep, hmacs);
+	err = sctp_auth_ep_set_hmacs(ep, hmacs);
 out:
 	kfree(hmacs);
 	return err;
@@ -3343,18 +3393,18 @@ static int sctp_setsockopt_auth_key(struct sock *sk,
 				    char __user *optval,
 				    unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkey *authkey;
 	struct sctp_association *asoc;
 	int ret;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen <= sizeof(struct sctp_authkey))
 		return -EINVAL;
 
-	authkey= memdup_user(optval, optlen);
+	authkey = memdup_user(optval, optlen);
 	if (IS_ERR(authkey))
 		return PTR_ERR(authkey);
 
@@ -3369,7 +3419,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk,
 		goto out;
 	}
 
-	ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey);
+	ret = sctp_auth_set_key(ep, asoc, authkey);
 out:
 	kzfree(authkey);
 	return ret;
@@ -3385,11 +3435,11 @@ static int sctp_setsockopt_active_key(struct sock *sk,
 				      char __user *optval,
 				      unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkeyid val;
 	struct sctp_association *asoc;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen != sizeof(struct sctp_authkeyid))
@@ -3401,8 +3451,7 @@ static int sctp_setsockopt_active_key(struct sock *sk,
 	if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP))
 		return -EINVAL;
 
-	return sctp_auth_set_active_key(sctp_sk(sk)->ep, asoc,
-					val.scact_keynumber);
+	return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber);
 }
 
 /*
@@ -3414,11 +3463,11 @@ static int sctp_setsockopt_del_key(struct sock *sk,
 				   char __user *optval,
 				   unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkeyid val;
 	struct sctp_association *asoc;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen != sizeof(struct sctp_authkeyid))
@@ -3430,8 +3479,7 @@ static int sctp_setsockopt_del_key(struct sock *sk,
 	if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP))
 		return -EINVAL;
 
-	return sctp_auth_del_key_id(sctp_sk(sk)->ep, asoc,
-				    val.scact_keynumber);
+	return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber);
 
 }
 
@@ -3564,7 +3612,7 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 		goto out_nounlock;
 	}
 
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 
 	switch (optname) {
 	case SCTP_SOCKOPT_BINDX_ADD:
@@ -3682,7 +3730,7 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 	}
 
-	sctp_release_sock(sk);
+	release_sock(sk);
 
 out_nounlock:
 	return retval;
@@ -3710,7 +3758,7 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr,
 	int err = 0;
 	struct sctp_af *af;
 
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 
 	pr_debug("%s: sk:%p, sockaddr:%p, addr_len:%d\n", __func__, sk,
 		 addr, addr_len);
@@ -3726,7 +3774,7 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr,
 		err = __sctp_connect(sk, addr, af->sockaddr_len, NULL);
 	}
 
-	sctp_release_sock(sk);
+	release_sock(sk);
 	return err;
 }
 
@@ -3752,7 +3800,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
 	long timeo;
 	int error = 0;
 
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 
 	sp = sctp_sk(sk);
 	ep = sp->ep;
@@ -3790,7 +3838,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
 	sctp_sock_migrate(sk, newsk, asoc, SCTP_SOCKET_TCP);
 
 out:
-	sctp_release_sock(sk);
+	release_sock(sk);
 	*err = error;
 	return newsk;
 }
@@ -3800,7 +3848,7 @@ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {
 	int rc = -ENOTCONN;
 
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 
 	/*
 	 * SEQPACKET-style sockets in LISTENING state are valid, for
@@ -3830,7 +3878,7 @@ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		break;
 	}
 out:
-	sctp_release_sock(sk);
+	release_sock(sk);
 	return rc;
 }
 
@@ -3908,7 +3956,7 @@ static int sctp_init_sock(struct sock *sk)
 	 */
 	sp->hbinterval  = net->sctp.hb_interval;
 	sp->pathmaxrxt  = net->sctp.max_retrans_path;
-	sp->pathmtu     = 0; // allow default discovery
+	sp->pathmtu     = 0; /* allow default discovery */
 	sp->sackdelay   = net->sctp.sack_timeout;
 	sp->sackfreq	= 2;
 	sp->param_flags = SPP_HB_ENABLE |
@@ -4451,7 +4499,7 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 	/* If an address other than INADDR_ANY is specified, and
 	 * no transport is found, then the request is invalid.
 	 */
-	if (!sctp_is_any(sk, ( union sctp_addr *)&params.spp_address)) {
+	if (!sctp_is_any(sk, (union sctp_addr *)&params.spp_address)) {
 		trans = sctp_addr_id2transport(sk, &params.spp_address,
 					       params.spp_assoc_id);
 		if (!trans) {
@@ -4557,12 +4605,15 @@ static int sctp_getsockopt_delayed_ack(struct sock *sk, int len,
 		if (copy_from_user(&params, optval, len))
 			return -EFAULT;
 	} else if (len == sizeof(struct sctp_assoc_value)) {
-		pr_warn("Use of struct sctp_assoc_value in delayed_ack socket option deprecated\n");
-		pr_warn("Use struct sctp_sack_info instead\n");
+		pr_warn_ratelimited(DEPRECATED
+				    "%s (pid %d) "
+				    "Use of struct sctp_assoc_value in delayed_ack socket option.\n"
+				    "Use struct sctp_sack_info instead\n",
+				    current->comm, task_pid_nr(current));
 		if (copy_from_user(&params, optval, len))
 			return -EFAULT;
 	} else
-		return - EINVAL;
+		return -EINVAL;
 
 	/* Get association, if sack_assoc_id != 0 and the socket is a one
 	 * to many style socket, and an association was not found, then
@@ -4652,8 +4703,8 @@ static int sctp_getsockopt_peer_addrs(struct sock *sk, int len,
 	if (!asoc)
 		return -EINVAL;
 
-	to = optval + offsetof(struct sctp_getaddrs,addrs);
-	space_left = len - offsetof(struct sctp_getaddrs,addrs);
+	to = optval + offsetof(struct sctp_getaddrs, addrs);
+	space_left = len - offsetof(struct sctp_getaddrs, addrs);
 
 	list_for_each_entry(from, &asoc->peer.transport_addr_list,
 				transports) {
@@ -4713,7 +4764,7 @@ static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to,
 		memcpy(to, &temp, addrlen);
 
 		to += addrlen;
-		cnt ++;
+		cnt++;
 		space_left -= addrlen;
 		*bytes_copied += addrlen;
 	}
@@ -4762,8 +4813,8 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
 		bp = &asoc->base.bind_addr;
 	}
 
-	to = optval + offsetof(struct sctp_getaddrs,addrs);
-	space_left = len - offsetof(struct sctp_getaddrs,addrs);
+	to = optval + offsetof(struct sctp_getaddrs, addrs);
+	space_left = len - offsetof(struct sctp_getaddrs, addrs);
 
 	addrs = kmalloc(space_left, GFP_KERNEL);
 	if (!addrs)
@@ -4802,7 +4853,7 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
 		memcpy(buf, &temp, addrlen);
 		buf += addrlen;
 		bytes_copied += addrlen;
-		cnt ++;
+		cnt++;
 		space_left -= addrlen;
 	}
 
@@ -5074,7 +5125,7 @@ static int sctp_getsockopt_associnfo(struct sock *sk, int len,
 		assocparams.sasoc_cookie_life = ktime_to_ms(asoc->cookie_life);
 
 		list_for_each(pos, &asoc->peer.transport_addr_list) {
-			cnt ++;
+			cnt++;
 		}
 
 		assocparams.sasoc_number_peer_destinations = cnt;
@@ -5202,8 +5253,11 @@ static int sctp_getsockopt_maxseg(struct sock *sk, int len,
 	struct sctp_association *asoc;
 
 	if (len == sizeof(int)) {
-		pr_warn("Use of int in maxseg socket option deprecated\n");
-		pr_warn("Use struct sctp_assoc_value instead\n");
+		pr_warn_ratelimited(DEPRECATED
+				    "%s (pid %d) "
+				    "Use of int in maxseg socket option.\n"
+				    "Use struct sctp_assoc_value instead\n",
+				    current->comm, task_pid_nr(current));
 		params.assoc_id = 0;
 	} else if (len >= sizeof(struct sctp_assoc_value)) {
 		len = sizeof(struct sctp_assoc_value);
@@ -5294,8 +5348,11 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len,
 	struct sctp_association *asoc;
 
 	if (len == sizeof(int)) {
-		pr_warn("Use of int in max_burst socket option deprecated\n");
-		pr_warn("Use struct sctp_assoc_value instead\n");
+		pr_warn_ratelimited(DEPRECATED
+				    "%s (pid %d) "
+				    "Use of int in max_burst socket option.\n"
+				    "Use struct sctp_assoc_value instead\n",
+				    current->comm, task_pid_nr(current));
 		params.assoc_id = 0;
 	} else if (len >= sizeof(struct sctp_assoc_value)) {
 		len = sizeof(struct sctp_assoc_value);
@@ -5329,16 +5386,16 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len,
 static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_hmacalgo  __user *p = (void __user *)optval;
 	struct sctp_hmac_algo_param *hmacs;
 	__u16 data_len = 0;
 	u32 num_idents;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
-	hmacs = sctp_sk(sk)->ep->auth_hmacs_list;
+	hmacs = ep->auth_hmacs_list;
 	data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t);
 
 	if (len < sizeof(struct sctp_hmacalgo) + data_len)
@@ -5359,11 +5416,11 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 static int sctp_getsockopt_active_key(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkeyid val;
 	struct sctp_association *asoc;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (len < sizeof(struct sctp_authkeyid))
@@ -5378,7 +5435,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len,
 	if (asoc)
 		val.scact_keynumber = asoc->active_key_id;
 	else
-		val.scact_keynumber = sctp_sk(sk)->ep->active_key_id;
+		val.scact_keynumber = ep->active_key_id;
 
 	len = sizeof(struct sctp_authkeyid);
 	if (put_user(len, optlen))
@@ -5392,7 +5449,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len,
 static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authchunks __user *p = (void __user *)optval;
 	struct sctp_authchunks val;
 	struct sctp_association *asoc;
@@ -5400,7 +5457,7 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len,
 	u32    num_chunks = 0;
 	char __user *to;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (len < sizeof(struct sctp_authchunks))
@@ -5427,7 +5484,8 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len,
 		return -EFAULT;
 num:
 	len = sizeof(struct sctp_authchunks) + num_chunks;
-	if (put_user(len, optlen)) return -EFAULT;
+	if (put_user(len, optlen))
+		return -EFAULT;
 	if (put_user(num_chunks, &p->gauth_number_of_chunks))
 		return -EFAULT;
 	return 0;
@@ -5436,7 +5494,7 @@ num:
 static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authchunks __user *p = (void __user *)optval;
 	struct sctp_authchunks val;
 	struct sctp_association *asoc;
@@ -5444,7 +5502,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
 	u32    num_chunks = 0;
 	char __user *to;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (len < sizeof(struct sctp_authchunks))
@@ -5459,9 +5517,9 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
 		return -EINVAL;
 
 	if (asoc)
-		ch = (struct sctp_chunks_param*)asoc->c.auth_chunks;
+		ch = (struct sctp_chunks_param *)asoc->c.auth_chunks;
 	else
-		ch = sctp_sk(sk)->ep->auth_chunk_list;
+		ch = ep->auth_chunk_list;
 
 	if (!ch)
 		goto num;
@@ -5718,7 +5776,7 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	if (get_user(len, optlen))
 		return -EFAULT;
 
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 
 	switch (optname) {
 	case SCTP_STATUS:
@@ -5842,7 +5900,7 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 		break;
 	}
 
-	sctp_release_sock(sk);
+	release_sock(sk);
 	return retval;
 }
 
@@ -5882,33 +5940,34 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 
 	pr_debug("%s: begins, snum:%d\n", __func__, snum);
 
-	sctp_local_bh_disable();
+	local_bh_disable();
 
 	if (snum == 0) {
 		/* Search for an available port. */
 		int low, high, remaining, index;
 		unsigned int rover;
+		struct net *net = sock_net(sk);
 
-		inet_get_local_port_range(sock_net(sk), &low, &high);
+		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
-		rover = net_random() % remaining + low;
+		rover = prandom_u32() % remaining + low;
 
 		do {
 			rover++;
 			if ((rover < low) || (rover > high))
 				rover = low;
-			if (inet_is_reserved_local_port(rover))
+			if (inet_is_local_reserved_port(net, rover))
 				continue;
 			index = sctp_phashfn(sock_net(sk), rover);
 			head = &sctp_port_hashtable[index];
-			sctp_spin_lock(&head->lock);
+			spin_lock(&head->lock);
 			sctp_for_each_hentry(pp, &head->chain)
 				if ((pp->port == rover) &&
 				    net_eq(sock_net(sk), pp->net))
 					goto next;
 			break;
 		next:
-			sctp_spin_unlock(&head->lock);
+			spin_unlock(&head->lock);
 		} while (--remaining > 0);
 
 		/* Exhausted local port range during search? */
@@ -5929,7 +5988,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 		 * port iterator, pp being NULL.
 		 */
 		head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), snum)];
-		sctp_spin_lock(&head->lock);
+		spin_lock(&head->lock);
 		sctp_for_each_hentry(pp, &head->chain) {
 			if ((pp->port == snum) && net_eq(pp->net, sock_net(sk)))
 				goto pp_found;
@@ -6013,10 +6072,10 @@ success:
 	ret = 0;
 
 fail_unlock:
-	sctp_spin_unlock(&head->lock);
+	spin_unlock(&head->lock);
 
 fail:
-	sctp_local_bh_enable();
+	local_bh_enable();
 	return ret;
 }
 
@@ -6108,7 +6167,7 @@ int sctp_inet_listen(struct socket *sock, int backlog)
 	if (unlikely(backlog < 0))
 		return err;
 
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 
 	/* Peeled-off sockets are not allowed to listen().  */
 	if (sctp_style(sk, UDP_HIGH_BANDWIDTH))
@@ -6141,7 +6200,7 @@ int sctp_inet_listen(struct socket *sock, int backlog)
 
 	err = 0;
 out:
-	sctp_release_sock(sk);
+	release_sock(sk);
 	return err;
 }
 
@@ -6250,20 +6309,20 @@ static inline void __sctp_put_port(struct sock *sk)
 						  inet_sk(sk)->inet_num)];
 	struct sctp_bind_bucket *pp;
 
-	sctp_spin_lock(&head->lock);
+	spin_lock(&head->lock);
 	pp = sctp_sk(sk)->bind_hash;
 	__sk_del_bind_node(sk);
 	sctp_sk(sk)->bind_hash = NULL;
 	inet_sk(sk)->inet_num = 0;
 	sctp_bucket_destroy(pp);
-	sctp_spin_unlock(&head->lock);
+	spin_unlock(&head->lock);
 }
 
 void sctp_put_port(struct sock *sk)
 {
-	sctp_local_bh_disable();
+	local_bh_disable();
 	__sctp_put_port(sk);
-	sctp_local_bh_enable();
+	local_bh_enable();
 }
 
 /*
@@ -6401,7 +6460,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs)
  * Note: This function is the same function as in core/datagram.c
  * with a few modifications to make lksctp work.
  */
-static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p)
+static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p)
 {
 	int error;
 	DEFINE_WAIT(wait);
@@ -6438,9 +6497,9 @@ static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p)
 	 * does not fit in the user's buffer, but this seems to be the
 	 * only way to honor MSG_DONTWAIT realistically.
 	 */
-	sctp_release_sock(sk);
+	release_sock(sk);
 	*timeo_p = schedule_timeout(*timeo_p);
-	sctp_lock_sock(sk);
+	lock_sock(sk);
 
 ready:
 	finish_wait(sk_sleep(sk), &wait);
@@ -6500,6 +6559,10 @@ static struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
 			break;
 
+		if (sk_can_busy_loop(sk) &&
+		    sk_busy_loop(sk, noblock))
+			continue;
+
 		/* User doesn't want to wait.  */
 		error = -EAGAIN;
 		if (!timeo)
@@ -6540,6 +6603,46 @@ static void __sctp_write_space(struct sctp_association *asoc)
 	}
 }
 
+static void sctp_wake_up_waiters(struct sock *sk,
+				 struct sctp_association *asoc)
+{
+	struct sctp_association *tmp = asoc;
+
+	/* We do accounting for the sndbuf space per association,
+	 * so we only need to wake our own association.
+	 */
+	if (asoc->ep->sndbuf_policy)
+		return __sctp_write_space(asoc);
+
+	/* If association goes down and is just flushing its
+	 * outq, then just normally notify others.
+	 */
+	if (asoc->base.dead)
+		return sctp_write_space(sk);
+
+	/* Accounting for the sndbuf space is per socket, so we
+	 * need to wake up others, try to be fair and in case of
+	 * other associations, let them have a go first instead
+	 * of just doing a sctp_write_space() call.
+	 *
+	 * Note that we reach sctp_wake_up_waiters() only when
+	 * associations free up queued chunks, thus we are under
+	 * lock and the list of associations on a socket is
+	 * guaranteed not to change.
+	 */
+	for (tmp = list_next_entry(tmp, asocs); 1;
+	     tmp = list_next_entry(tmp, asocs)) {
+		/* Manually skip the head element. */
+		if (&tmp->asocs == &((sctp_sk(sk))->ep->asocs))
+			continue;
+		/* Wake up association. */
+		__sctp_write_space(tmp);
+		/* We've reached the end. */
+		if (tmp == asoc)
+			break;
+	}
+}
+
 /* Do accounting for the sndbuf space.
  * Decrement the used sndbuf space of the corresponding association by the
  * data size which was just transmitted(freed).
@@ -6567,7 +6670,7 @@ static void sctp_wfree(struct sk_buff *skb)
 	sk_mem_uncharge(sk, skb->truesize);
 
 	sock_wfree(skb);
-	__sctp_write_space(asoc);
+	sctp_wake_up_waiters(sk, asoc);
 
 	sctp_association_put(asoc);
 }
@@ -6623,10 +6726,10 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 		/* Let another process have a go.  Since we are going
 		 * to sleep anyway.
 		 */
-		sctp_release_sock(sk);
+		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
 		BUG_ON(sk != asoc->base.sk);
-		sctp_lock_sock(sk);
+		lock_sock(sk);
 
 		*timeo_p = current_timeo;
 	}
@@ -6652,7 +6755,7 @@ do_nonblock:
 	goto out;
 }
 
-void sctp_data_ready(struct sock *sk, int len)
+void sctp_data_ready(struct sock *sk)
 {
 	struct socket_wq *wq;
 
@@ -6731,9 +6834,9 @@ static int sctp_wait_for_connect(struct sctp_association *asoc, long *timeo_p)
 		/* Let another process have a go.  Since we are going
 		 * to sleep anyway.
 		 */
-		sctp_release_sock(sk);
+		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
-		sctp_lock_sock(sk);
+		lock_sock(sk);
 
 		*timeo_p = current_timeo;
 	}
@@ -6776,9 +6879,9 @@ static int sctp_wait_for_accept(struct sock *sk, long timeo)
 					  TASK_INTERRUPTIBLE);
 
 		if (list_empty(&ep->asocs)) {
-			sctp_release_sock(sk);
+			release_sock(sk);
 			timeo = schedule_timeout(timeo);
-			sctp_lock_sock(sk);
+			lock_sock(sk);
 		}
 
 		err = -EINVAL;
@@ -6811,9 +6914,9 @@ static void sctp_wait_for_close(struct sock *sk, long timeout)
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 		if (list_empty(&sctp_sk(sk)->ep->asocs))
 			break;
-		sctp_release_sock(sk);
+		release_sock(sk);
 		timeout = schedule_timeout(timeout);
-		sctp_lock_sock(sk);
+		lock_sock(sk);
 	} while (!signal_pending(current) && timeout);
 
 	finish_wait(sk_sleep(sk), &wait);
@@ -6843,7 +6946,8 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newsk->sk_type = sk->sk_type;
 	newsk->sk_bound_dev_if = sk->sk_bound_dev_if;
 	newsk->sk_flags = sk->sk_flags;
-	newsk->sk_no_check = sk->sk_no_check;
+	newsk->sk_no_check_tx = sk->sk_no_check_tx;
+	newsk->sk_no_check_rx = sk->sk_no_check_rx;
 	newsk->sk_reuse = sk->sk_reuse;
 
 	newsk->sk_shutdown = sk->sk_shutdown;
@@ -6914,14 +7018,14 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	/* Hook this new socket in to the bind_hash list. */
 	head = &sctp_port_hashtable[sctp_phashfn(sock_net(oldsk),
 						 inet_sk(oldsk)->inet_num)];
-	sctp_local_bh_disable();
-	sctp_spin_lock(&head->lock);
+	local_bh_disable();
+	spin_lock(&head->lock);
 	pp = sctp_sk(oldsk)->bind_hash;
 	sk_add_bind_node(newsk, &pp->owner);
 	sctp_sk(newsk)->bind_hash = pp;
 	inet_sk(newsk)->inet_num = inet_sk(oldsk)->inet_num;
-	sctp_spin_unlock(&head->lock);
-	sctp_local_bh_enable();
+	spin_unlock(&head->lock);
+	local_bh_enable();
 
 	/* Copy the bind_addr list from the original endpoint to the new
 	 * endpoint so that we can handle restarts properly
@@ -7010,7 +7114,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 		newsk->sk_shutdown |= RCV_SHUTDOWN;
 
 	newsk->sk_state = SCTP_SS_ESTABLISHED;
-	sctp_release_sock(newsk);
+	release_sock(newsk);
 }
 
 
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 80b17b5df6b..12c7e01c267 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -34,6 +34,8 @@
  *    Sridhar Samudrala     <sri@us.ibm.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <net/sctp/structs.h>
 #include <net/sctp/sctp.h>
 #include <linux/sysctl.h>
@@ -46,6 +48,11 @@ static int sack_timer_min = 1;
 static int sack_timer_max = 500;
 static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */
 static int rwnd_scale_max = 16;
+static int rto_alpha_min = 0;
+static int rto_beta_min = 0;
+static int rto_alpha_max = 1000;
+static int rto_beta_max = 1000;
+
 static unsigned long max_autoclose_min = 0;
 static unsigned long max_autoclose_max =
 	(MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
@@ -55,11 +62,22 @@ extern long sysctl_sctp_mem[3];
 extern int sysctl_sctp_rmem[3];
 extern int sysctl_sctp_wmem[3];
 
-static int proc_sctp_do_hmac_alg(struct ctl_table *ctl,
-				int write,
+static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
+				void __user *buffer, size_t *lenp,
+				loff_t *ppos);
+static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
 				void __user *buffer, size_t *lenp,
-
 				loff_t *ppos);
+static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
+				void __user *buffer, size_t *lenp,
+				loff_t *ppos);
+static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos);
+static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos);
+
 static struct ctl_table sctp_table[] = {
 	{
 		.procname	= "sctp_mem",
@@ -101,32 +119,36 @@ static struct ctl_table sctp_net_table[] = {
 		.data		= &init_net.sctp.rto_min,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_sctp_do_rto_min,
 		.extra1         = &one,
-		.extra2         = &timer_max
+		.extra2         = &init_net.sctp.rto_max
 	},
 	{
 		.procname	= "rto_max",
 		.data		= &init_net.sctp.rto_max,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1         = &one,
+		.proc_handler	= proc_sctp_do_rto_max,
+		.extra1         = &init_net.sctp.rto_min,
 		.extra2         = &timer_max
 	},
 	{
 		.procname	= "rto_alpha_exp_divisor",
 		.data		= &init_net.sctp.rto_alpha,
 		.maxlen		= sizeof(int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_alpha_beta,
+		.extra1		= &rto_alpha_min,
+		.extra2		= &rto_alpha_max,
 	},
 	{
 		.procname	= "rto_beta_exp_divisor",
 		.data		= &init_net.sctp.rto_beta,
 		.maxlen		= sizeof(int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_alpha_beta,
+		.extra1		= &rto_beta_min,
+		.extra2		= &rto_beta_max,
 	},
 	{
 		.procname	= "max_burst",
@@ -146,6 +168,7 @@ static struct ctl_table sctp_net_table[] = {
 	},
 	{
 		.procname	= "cookie_hmac_alg",
+		.data		= &init_net.sctp.sctp_hmac_alg,
 		.maxlen		= 8,
 		.mode		= 0644,
 		.proc_handler	= proc_sctp_do_hmac_alg,
@@ -260,7 +283,7 @@ static struct ctl_table sctp_net_table[] = {
 		.data		= &init_net.sctp.auth_enable,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_sctp_do_auth,
 	},
 	{
 		.procname	= "addr_scope_policy",
@@ -293,47 +316,45 @@ static struct ctl_table sctp_net_table[] = {
 	{ /* sentinel */ }
 };
 
-static int proc_sctp_do_hmac_alg(struct ctl_table *ctl,
-				int write,
+static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
 				void __user *buffer, size_t *lenp,
 				loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
-	char tmp[8];
 	struct ctl_table tbl;
-	int ret;
-	int changed = 0;
+	bool changed = false;
 	char *none = "none";
+	char tmp[8];
+	int ret;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
 
 	if (write) {
 		tbl.data = tmp;
-		tbl.maxlen = 8;
+		tbl.maxlen = sizeof(tmp);
 	} else {
 		tbl.data = net->sctp.sctp_hmac_alg ? : none;
 		tbl.maxlen = strlen(tbl.data);
 	}
-		ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
 
-	if (write) {
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
 #ifdef CONFIG_CRYPTO_MD5
 		if (!strncmp(tmp, "md5", 3)) {
 			net->sctp.sctp_hmac_alg = "md5";
-			changed = 1;
+			changed = true;
 		}
 #endif
 #ifdef CONFIG_CRYPTO_SHA1
 		if (!strncmp(tmp, "sha1", 4)) {
 			net->sctp.sctp_hmac_alg = "sha1";
-			changed = 1;
+			changed = true;
 		}
 #endif
 		if (!strncmp(tmp, "none", 4)) {
 			net->sctp.sctp_hmac_alg = NULL;
-			changed = 1;
+			changed = true;
 		}
-
 		if (!changed)
 			ret = -EINVAL;
 	}
@@ -341,6 +362,104 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl,
 	return ret;
 }
 
+static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
+				void __user *buffer, size_t *lenp,
+				loff_t *ppos)
+{
+	struct net *net = current->nsproxy->net_ns;
+	unsigned int min = *(unsigned int *) ctl->extra1;
+	unsigned int max = *(unsigned int *) ctl->extra2;
+	struct ctl_table tbl;
+	int ret, new_value;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.rto_min;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		if (new_value > max || new_value < min)
+			return -EINVAL;
+
+		net->sctp.rto_min = new_value;
+	}
+
+	return ret;
+}
+
+static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
+				void __user *buffer, size_t *lenp,
+				loff_t *ppos)
+{
+	struct net *net = current->nsproxy->net_ns;
+	unsigned int min = *(unsigned int *) ctl->extra1;
+	unsigned int max = *(unsigned int *) ctl->extra2;
+	struct ctl_table tbl;
+	int ret, new_value;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.rto_max;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		if (new_value > max || new_value < min)
+			return -EINVAL;
+
+		net->sctp.rto_max = new_value;
+	}
+
+	return ret;
+}
+
+static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos)
+{
+	pr_warn_once("Changing rto_alpha or rto_beta may lead to "
+		     "suboptimal rtt/srtt estimations!\n");
+
+	return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
+}
+
+static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct ctl_table tbl;
+	int new_value, ret;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.auth_enable;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		struct sock *sk = net->sctp.ctl_sock;
+
+		net->sctp.auth_enable = new_value;
+		/* Update the value in the control socket */
+		lock_sock(sk);
+		sctp_sk(sk)->ep->auth_enable = new_value;
+		release_sock(sk);
+	}
+
+	return ret;
+}
+
 int sctp_sysctl_net_register(struct net *net)
 {
 	struct ctl_table *table;
@@ -354,6 +473,10 @@ int sctp_sysctl_net_register(struct net *net)
 		table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
 
 	net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table);
+	if (net->sctp.sysctl_header == NULL) {
+		kfree(table);
+		return -ENOMEM;
+	}
 	return 0;
 }
 
@@ -366,7 +489,7 @@ void sctp_sysctl_net_unregister(struct net *net)
 	kfree(table);
 }
 
-static struct ctl_table_header * sctp_sysctl_header;
+static struct ctl_table_header *sctp_sysctl_header;
 
 /* Sysctl registration.  */
 void sctp_sysctl_register(void)
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index d0810dc5f07..7dd672fa651 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -72,7 +72,7 @@ static struct sctp_transport *sctp_transport_init(struct net *net,
 	 */
 	peer->rto = msecs_to_jiffies(net->sctp.rto_initial);
 
-	peer->last_time_heard = jiffies;
+	peer->last_time_heard = ktime_get();
 	peer->last_time_ecne_reduced = jiffies;
 
 	peer->param_flags = SPP_HB_DISABLE |
@@ -652,5 +652,4 @@ void sctp_transport_immediate_rtx(struct sctp_transport *t)
 		if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto))
 			sctp_transport_hold(t);
 	}
-	return;
 }
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 85c64658bd0..b6842fdb53d 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -366,9 +366,10 @@ fail:
  * specification [SCTP] and any extensions for a list of possible
  * error formats.
  */
-struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
-	const struct sctp_association *asoc, struct sctp_chunk *chunk,
-	__u16 flags, gfp_t gfp)
+struct sctp_ulpevent *
+sctp_ulpevent_make_remote_error(const struct sctp_association *asoc,
+				struct sctp_chunk *chunk, __u16 flags,
+				gfp_t gfp)
 {
 	struct sctp_ulpevent *event;
 	struct sctp_remote_error *sre;
@@ -387,8 +388,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
 	/* Copy the skb to a new skb with room for us to prepend
 	 * notification with.
 	 */
-	skb = skb_copy_expand(chunk->skb, sizeof(struct sctp_remote_error),
-			      0, gfp);
+	skb = skb_copy_expand(chunk->skb, sizeof(*sre), 0, gfp);
 
 	/* Pull off the rest of the cause TLV from the chunk.  */
 	skb_pull(chunk->skb, elen);
@@ -399,62 +399,21 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
 	event = sctp_skb2event(skb);
 	sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize);
 
-	sre = (struct sctp_remote_error *)
-		skb_push(skb, sizeof(struct sctp_remote_error));
+	sre = (struct sctp_remote_error *) skb_push(skb, sizeof(*sre));
 
 	/* Trim the buffer to the right length.  */
-	skb_trim(skb, sizeof(struct sctp_remote_error) + elen);
+	skb_trim(skb, sizeof(*sre) + elen);
 
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_type:
-	 *   It should be SCTP_REMOTE_ERROR.
-	 */
+	/* RFC6458, Section 6.1.3. SCTP_REMOTE_ERROR */
+	memset(sre, 0, sizeof(*sre));
 	sre->sre_type = SCTP_REMOTE_ERROR;
-
-	/*
-	 * Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_flags: 16 bits (unsigned integer)
-	 *   Currently unused.
-	 */
 	sre->sre_flags = 0;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_length: sizeof (__u32)
-	 *
-	 * This field is the total length of the notification data,
-	 * including the notification header.
-	 */
 	sre->sre_length = skb->len;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_error: 16 bits (unsigned integer)
-	 * This value represents one of the Operational Error causes defined in
-	 * the SCTP specification, in network byte order.
-	 */
 	sre->sre_error = cause;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_assoc_id: sizeof (sctp_assoc_t)
-	 *
-	 * The association id field, holds the identifier for the association.
-	 * All notifications for a given association have the same association
-	 * identifier.  For TCP style socket, this field is ignored.
-	 */
 	sctp_ulpevent_set_owner(event, asoc);
 	sre->sre_assoc_id = sctp_assoc2id(asoc);
 
 	return event;
-
 fail:
 	return NULL;
 }
@@ -899,7 +858,9 @@ __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event)
 	return notification->sn_header.sn_type;
 }
 
-/* Copy out the sndrcvinfo into a msghdr.  */
+/* RFC6458, Section 5.3.2. SCTP Header Information Structure
+ * (SCTP_SNDRCV, DEPRECATED)
+ */
 void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
 				   struct msghdr *msghdr)
 {
@@ -908,74 +869,21 @@ void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
 	if (sctp_ulpevent_is_notification(event))
 		return;
 
-	/* Sockets API Extensions for SCTP
-	 * Section 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV)
-	 *
-	 * sinfo_stream: 16 bits (unsigned integer)
-	 *
-	 * For recvmsg() the SCTP stack places the message's stream number in
-	 * this value.
-	*/
+	memset(&sinfo, 0, sizeof(sinfo));
 	sinfo.sinfo_stream = event->stream;
-	/* sinfo_ssn: 16 bits (unsigned integer)
-	 *
-	 * For recvmsg() this value contains the stream sequence number that
-	 * the remote endpoint placed in the DATA chunk.  For fragmented
-	 * messages this is the same number for all deliveries of the message
-	 * (if more than one recvmsg() is needed to read the message).
-	 */
 	sinfo.sinfo_ssn = event->ssn;
-	/* sinfo_ppid: 32 bits (unsigned integer)
-	 *
-	 * In recvmsg() this value is
-	 * the same information that was passed by the upper layer in the peer
-	 * application.  Please note that byte order issues are NOT accounted
-	 * for and this information is passed opaquely by the SCTP stack from
-	 * one end to the other.
-	 */
 	sinfo.sinfo_ppid = event->ppid;
-	/* sinfo_flags: 16 bits (unsigned integer)
-	 *
-	 * This field may contain any of the following flags and is composed of
-	 * a bitwise OR of these values.
-	 *
-	 * recvmsg() flags:
-	 *
-	 * SCTP_UNORDERED - This flag is present when the message was sent
-	 *                 non-ordered.
-	 */
 	sinfo.sinfo_flags = event->flags;
-	/* sinfo_tsn: 32 bit (unsigned integer)
-	 *
-	 * For the receiving side, this field holds a TSN that was
-	 * assigned to one of the SCTP Data Chunks.
-	 */
 	sinfo.sinfo_tsn = event->tsn;
-	/* sinfo_cumtsn: 32 bit (unsigned integer)
-	 *
-	 * This field will hold the current cumulative TSN as
-	 * known by the underlying SCTP layer.  Note this field is
-	 * ignored when sending and only valid for a receive
-	 * operation when sinfo_flags are set to SCTP_UNORDERED.
-	 */
 	sinfo.sinfo_cumtsn = event->cumtsn;
-	/* sinfo_assoc_id: sizeof (sctp_assoc_t)
-	 *
-	 * The association handle field, sinfo_assoc_id, holds the identifier
-	 * for the association announced in the COMMUNICATION_UP notification.
-	 * All notifications for a given association have the same identifier.
-	 * Ignored for one-to-one style sockets.
-	 */
 	sinfo.sinfo_assoc_id = sctp_assoc2id(event->asoc);
-
-	/* context value that is set via SCTP_CONTEXT socket option. */
+	/* Context value that is set via SCTP_CONTEXT socket option. */
 	sinfo.sinfo_context = event->asoc->default_rcv_context;
-
 	/* These fields are not used while receiving. */
 	sinfo.sinfo_timetolive = 0;
 
 	put_cmsg(msghdr, IPPROTO_SCTP, SCTP_SNDRCV,
-		 sizeof(struct sctp_sndrcvinfo), (void *)&sinfo);
+		 sizeof(sinfo), &sinfo);
 }
 
 /* Do accounting for bytes received and hold a reference to the association
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index a67470083be..d49dc2ed30a 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -38,14 +38,15 @@
 #include <linux/types.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
+#include <net/busy_poll.h>
 #include <net/sctp/structs.h>
 #include <net/sctp/sctp.h>
 #include <net/sctp/sm.h>
 
 /* Forward declarations for internal helpers.  */
-static struct sctp_ulpevent * sctp_ulpq_reasm(struct sctp_ulpq *ulpq,
+static struct sctp_ulpevent *sctp_ulpq_reasm(struct sctp_ulpq *ulpq,
 					      struct sctp_ulpevent *);
-static struct sctp_ulpevent * sctp_ulpq_order(struct sctp_ulpq *,
+static struct sctp_ulpevent *sctp_ulpq_order(struct sctp_ulpq *,
 					      struct sctp_ulpevent *);
 static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq);
 
@@ -107,7 +108,7 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 	event = sctp_ulpq_reasm(ulpq, event);
 
 	/* Do ordering if needed.  */
-	if ((event) && (event->msg_flags & MSG_EOR)){
+	if ((event) && (event->msg_flags & MSG_EOR)) {
 		/* Create a temporary list to collect chunks on.  */
 		skb_queue_head_init(&temp);
 		__skb_queue_tail(&temp, sctp_event2skb(event));
@@ -204,6 +205,9 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 	if (sock_flag(sk, SOCK_DEAD) || (sk->sk_shutdown & RCV_SHUTDOWN))
 		goto out_free;
 
+	if (!sctp_ulpevent_is_notification(event))
+		sk_mark_napi_id(sk, skb);
+
 	/* Check if the user wishes to receive this event.  */
 	if (!sctp_ulpevent_is_enabled(event, &sctp_sk(sk)->subscribe))
 		goto out_free;
@@ -259,7 +263,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		sctp_ulpq_clear_pd(ulpq);
 
 	if (queue == &sk->sk_receive_queue)
-		sk->sk_data_ready(sk, 0);
+		sk->sk_data_ready(sk);
 	return 1;
 
 out_free:
@@ -336,7 +340,8 @@ static struct sctp_ulpevent *sctp_make_reassembled_event(struct net *net,
 		pos = f_frag->next;
 
 	/* Get the last skb in the f_frag's frag_list if present. */
-	for (last = list; list; last = list, list = list->next);
+	for (last = list; list; last = list, list = list->next)
+		;
 
 	/* Add the list of remaining fragments to the first fragments
 	 * frag_list.
@@ -726,7 +731,7 @@ static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq)
 
 	while ((event = sctp_ulpq_retrieve_reassembled(ulpq)) != NULL) {
 		/* Do ordering if needed.  */
-		if ((event) && (event->msg_flags & MSG_EOR)){
+		if ((event) && (event->msg_flags & MSG_EOR)) {
 			skb_queue_head_init(&temp);
 			__skb_queue_tail(&temp, sctp_event2skb(event));
 
@@ -1134,5 +1139,5 @@ void sctp_ulpq_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp)
 
 	/* If there is data waiting, send it up the socket now. */
 	if (sctp_ulpq_clear_pd(ulpq) || ev)
-		sk->sk_data_ready(sk, 0);
+		sk->sk_data_ready(sk);
 }
diff --git a/net/socket.c b/net/socket.c
index cd38a785f7d..abf56b2a14f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -72,6 +72,7 @@
 #include <linux/if_bridge.h>
 #include <linux/if_frad.h>
 #include <linux/if_vlan.h>
+#include <linux/ptp_classify.h>
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/cache.h>
@@ -450,16 +451,17 @@ EXPORT_SYMBOL(sockfd_lookup);
 
 static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	struct socket *sock;
 
 	*err = -EBADF;
-	file = fget_light(fd, fput_needed);
-	if (file) {
-		sock = sock_from_file(file, err);
-		if (sock)
+	if (f.file) {
+		sock = sock_from_file(f.file, err);
+		if (likely(sock)) {
+			*fput_needed = f.flags;
 			return sock;
-		fput_light(file, *fput_needed);
+		}
+		fdput(f);
 	}
 	return NULL;
 }
@@ -593,7 +595,7 @@ void sock_release(struct socket *sock)
 	}
 
 	if (rcu_dereference_protected(sock->wq, 1)->fasync_list)
-		printk(KERN_ERR "sock_release: fasync list not empty!\n");
+		pr_err("%s: fasync list not empty!\n", __func__);
 
 	if (test_bit(SOCK_EXTERNALLY_ALLOCATED, &sock->flags))
 		return;
@@ -1265,8 +1267,8 @@ int __sock_create(struct net *net, int family, int type, int protocol,
 		static int warned;
 		if (!warned) {
 			warned = 1;
-			printk(KERN_INFO "%s uses obsolete (PF_INET,SOCK_PACKET)\n",
-			       current->comm);
+			pr_info("%s uses obsolete (PF_INET,SOCK_PACKET)\n",
+				current->comm);
 		}
 		family = PF_PACKET;
 	}
@@ -1445,48 +1447,61 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
 		err = fd1;
 		goto out_release_both;
 	}
+
 	fd2 = get_unused_fd_flags(flags);
 	if (unlikely(fd2 < 0)) {
 		err = fd2;
-		put_unused_fd(fd1);
-		goto out_release_both;
+		goto out_put_unused_1;
 	}
 
 	newfile1 = sock_alloc_file(sock1, flags, NULL);
 	if (unlikely(IS_ERR(newfile1))) {
 		err = PTR_ERR(newfile1);
-		put_unused_fd(fd1);
-		put_unused_fd(fd2);
-		goto out_release_both;
+		goto out_put_unused_both;
 	}
 
 	newfile2 = sock_alloc_file(sock2, flags, NULL);
 	if (IS_ERR(newfile2)) {
 		err = PTR_ERR(newfile2);
-		fput(newfile1);
-		put_unused_fd(fd1);
-		put_unused_fd(fd2);
-		sock_release(sock2);
-		goto out;
+		goto out_fput_1;
 	}
 
+	err = put_user(fd1, &usockvec[0]);
+	if (err)
+		goto out_fput_both;
+
+	err = put_user(fd2, &usockvec[1]);
+	if (err)
+		goto out_fput_both;
+
 	audit_fd_pair(fd1, fd2);
+
 	fd_install(fd1, newfile1);
 	fd_install(fd2, newfile2);
 	/* fd1 and fd2 may be already another descriptors.
 	 * Not kernel problem.
 	 */
 
-	err = put_user(fd1, &usockvec[0]);
-	if (!err)
-		err = put_user(fd2, &usockvec[1]);
-	if (!err)
-		return 0;
+	return 0;
 
-	sys_close(fd2);
-	sys_close(fd1);
-	return err;
+out_fput_both:
+	fput(newfile2);
+	fput(newfile1);
+	put_unused_fd(fd2);
+	put_unused_fd(fd1);
+	goto out;
 
+out_fput_1:
+	fput(newfile1);
+	put_unused_fd(fd2);
+	put_unused_fd(fd1);
+	sock_release(sock2);
+	goto out;
+
+out_put_unused_both:
+	put_unused_fd(fd2);
+out_put_unused_1:
+	put_unused_fd(fd1);
 out_release_both:
 	sock_release(sock2);
 out_release_1:
@@ -1865,8 +1880,8 @@ out:
  *	Receive a datagram from a socket.
  */
 
-asmlinkage long sys_recv(int fd, void __user *ubuf, size_t size,
-			 unsigned int flags)
+SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size,
+		unsigned int, flags)
 {
 	return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL);
 }
@@ -1972,6 +1987,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 {
 	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
 		return -EFAULT;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	return 0;
@@ -2582,8 +2601,7 @@ int sock_register(const struct net_proto_family *ops)
 	int err;
 
 	if (ops->family >= NPROTO) {
-		printk(KERN_CRIT "protocol %d >= NPROTO(%d)\n", ops->family,
-		       NPROTO);
+		pr_crit("protocol %d >= NPROTO(%d)\n", ops->family, NPROTO);
 		return -ENOBUFS;
 	}
 
@@ -2597,7 +2615,7 @@ int sock_register(const struct net_proto_family *ops)
 	}
 	spin_unlock(&net_family_lock);
 
-	printk(KERN_INFO "NET: Registered protocol family %d\n", ops->family);
+	pr_info("NET: Registered protocol family %d\n", ops->family);
 	return err;
 }
 EXPORT_SYMBOL(sock_register);
@@ -2625,7 +2643,7 @@ void sock_unregister(int family)
 
 	synchronize_rcu();
 
-	printk(KERN_INFO "NET: Unregistered protocol family %d\n", family);
+	pr_info("NET: Unregistered protocol family %d\n", family);
 }
 EXPORT_SYMBOL(sock_unregister);
 
@@ -2668,9 +2686,7 @@ static int __init sock_init(void)
 		goto out;
 #endif
 
-#ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
-	skb_timestamping_init();
-#endif
+	ptp_classifier_init();
 
 out:
 	return err;
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 241b54f3020..0754d0f466d 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -9,19 +9,6 @@ config SUNRPC_BACKCHANNEL
 	bool
 	depends on SUNRPC
 
-config SUNRPC_XPRT_RDMA
-	tristate
-	depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS
-	default SUNRPC && INFINIBAND
-	help
-	  This option allows the NFS client and server to support
-	  an RDMA-enabled transport.
-
-	  To compile RPC client RDMA transport support as a module,
-	  choose M here: the module will be called xprtrdma.
-
-	  If unsure, say N.
-
 config SUNRPC_SWAP
 	bool
 	depends on SUNRPC
@@ -57,3 +44,29 @@ config SUNRPC_DEBUG
 	  but makes troubleshooting NFS issues significantly harder.
 
 	  If unsure, say Y.
+
+config SUNRPC_XPRT_RDMA_CLIENT
+	tristate "RPC over RDMA Client Support"
+	depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS
+	default SUNRPC && INFINIBAND
+	help
+	  This option allows the NFS client to support an RDMA-enabled
+	  transport.
+
+	  To compile RPC client RDMA transport support as a module,
+	  choose M here: the module will be called xprtrdma.
+
+	  If unsure, say N.
+
+config SUNRPC_XPRT_RDMA_SERVER
+	tristate "RPC over RDMA Server Support"
+	depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS
+	default SUNRPC && INFINIBAND
+	help
+	  This option allows the NFS server to support an RDMA-enabled
+	  transport.
+
+	  To compile RPC server RDMA transport support as a module,
+	  choose M here: the module will be called svcrdma.
+
+	  If unsure, say N.
diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile
index 8209a0411bc..e5a7a1cac8f 100644
--- a/net/sunrpc/Makefile
+++ b/net/sunrpc/Makefile
@@ -5,7 +5,8 @@
 
 obj-$(CONFIG_SUNRPC) += sunrpc.o
 obj-$(CONFIG_SUNRPC_GSS) += auth_gss/
-obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/
+
+obj-y += xprtrdma/
 
 sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \
 	    auth.o auth_null.o auth_unix.o auth_generic.o \
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 5285ead196c..f7736671742 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -296,7 +296,7 @@ static void
 rpcauth_unhash_cred_locked(struct rpc_cred *cred)
 {
 	hlist_del_rcu(&cred->cr_hash);
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags);
 }
 
@@ -592,6 +592,7 @@ rpcauth_lookupcred(struct rpc_auth *auth, int flags)
 	put_group_info(acred.group_info);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(rpcauth_lookupcred);
 
 void
 rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred,
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 97912b40c25..b6e440baccc 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -108,6 +108,7 @@ struct gss_auth {
 static DEFINE_SPINLOCK(pipe_version_lock);
 static struct rpc_wait_queue pipe_version_rpc_waitqueue;
 static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue);
+static void gss_put_auth(struct gss_auth *gss_auth);
 
 static void gss_free_ctx(struct gss_cl_ctx *);
 static const struct rpc_pipe_ops gss_upcall_ops_v0;
@@ -142,7 +143,7 @@ gss_cred_set_ctx(struct rpc_cred *cred, struct gss_cl_ctx *ctx)
 	gss_get_ctx(ctx);
 	rcu_assign_pointer(gss_cred->gc_ctx, ctx);
 	set_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(RPCAUTH_CRED_NEW, &cred->cr_flags);
 }
 
@@ -320,6 +321,7 @@ gss_release_msg(struct gss_upcall_msg *gss_msg)
 	if (gss_msg->ctx != NULL)
 		gss_put_ctx(gss_msg->ctx);
 	rpc_destroy_wait_queue(&gss_msg->rpc_waitqueue);
+	gss_put_auth(gss_msg->auth);
 	kfree(gss_msg);
 }
 
@@ -498,9 +500,12 @@ gss_alloc_msg(struct gss_auth *gss_auth,
 	default:
 		err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name);
 		if (err)
-			goto err_free_msg;
+			goto err_put_pipe_version;
 	};
+	kref_get(&gss_auth->kref);
 	return gss_msg;
+err_put_pipe_version:
+	put_pipe_version(gss_auth->net);
 err_free_msg:
 	kfree(gss_msg);
 err:
@@ -532,14 +537,7 @@ gss_setup_upcall(struct gss_auth *gss_auth, struct rpc_cred *cred)
 
 static void warn_gssd(void)
 {
-	static unsigned long ratelimit;
-	unsigned long now = jiffies;
-
-	if (time_after(now, ratelimit)) {
-		printk(KERN_WARNING "RPC: AUTH_GSS upcall timed out.\n"
-				"Please check user daemon is running.\n");
-		ratelimit = now + 15*HZ;
-	}
+	dprintk("AUTH_GSS upcall failed. Please check user daemon is running.\n");
 }
 
 static inline int
@@ -600,7 +598,6 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
 	struct rpc_pipe *pipe;
 	struct rpc_cred *cred = &gss_cred->gc_base;
 	struct gss_upcall_msg *gss_msg;
-	unsigned long timeout;
 	DEFINE_WAIT(wait);
 	int err;
 
@@ -608,17 +605,16 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
 		__func__, from_kuid(&init_user_ns, cred->cr_uid));
 retry:
 	err = 0;
-	/* Default timeout is 15s unless we know that gssd is not running */
-	timeout = 15 * HZ;
-	if (!sn->gssd_running)
-		timeout = HZ >> 2;
+	/* if gssd is down, just skip upcalling altogether */
+	if (!gssd_running(net)) {
+		warn_gssd();
+		return -EACCES;
+	}
 	gss_msg = gss_setup_upcall(gss_auth, cred);
 	if (PTR_ERR(gss_msg) == -EAGAIN) {
 		err = wait_event_interruptible_timeout(pipe_version_waitqueue,
-				sn->pipe_version >= 0, timeout);
+				sn->pipe_version >= 0, 15 * HZ);
 		if (sn->pipe_version < 0) {
-			if (err == 0)
-				sn->gssd_running = 0;
 			warn_gssd();
 			err = -EACCES;
 		}
@@ -1000,6 +996,8 @@ gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt)
 	gss_auth->service = gss_pseudoflavor_to_service(gss_auth->mech, flavor);
 	if (gss_auth->service == 0)
 		goto err_put_mech;
+	if (!gssd_running(gss_auth->net))
+		goto err_put_mech;
 	auth = &gss_auth->rpc_auth;
 	auth->au_cslack = GSS_CRED_SLACK >> 2;
 	auth->au_rslack = GSS_VERF_SLACK >> 2;
@@ -1071,6 +1069,12 @@ gss_free_callback(struct kref *kref)
 }
 
 static void
+gss_put_auth(struct gss_auth *gss_auth)
+{
+	kref_put(&gss_auth->kref, gss_free_callback);
+}
+
+static void
 gss_destroy(struct rpc_auth *auth)
 {
 	struct gss_auth *gss_auth = container_of(auth,
@@ -1091,7 +1095,7 @@ gss_destroy(struct rpc_auth *auth)
 	gss_auth->gss_pipe[1] = NULL;
 	rpcauth_destroy_credcache(auth);
 
-	kref_put(&gss_auth->kref, gss_free_callback);
+	gss_put_auth(gss_auth);
 }
 
 /*
@@ -1262,7 +1266,7 @@ gss_destroy_nullcred(struct rpc_cred *cred)
 	call_rcu(&cred->cr_rcu, gss_free_cred_callback);
 	if (ctx)
 		gss_put_ctx(ctx);
-	kref_put(&gss_auth->kref, gss_free_callback);
+	gss_put_auth(gss_auth);
 }
 
 static void
@@ -1517,7 +1521,7 @@ out:
 static int
 gss_refresh_null(struct rpc_task *task)
 {
-	return -EACCES;
+	return 0;
 }
 
 static __be32 *
diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c
index 76e42e6be75..24589bd2a4b 100644
--- a/net/sunrpc/auth_gss/gss_krb5_keys.c
+++ b/net/sunrpc/auth_gss/gss_krb5_keys.c
@@ -59,6 +59,7 @@
 #include <linux/crypto.h>
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/sunrpc/xdr.h>
+#include <linux/lcm.h>
 
 #ifdef RPC_DEBUG
 # define RPCDBG_FACILITY        RPCDBG_AUTH
@@ -72,7 +73,7 @@
 static void krb5_nfold(u32 inbits, const u8 *in,
 		       u32 outbits, u8 *out)
 {
-	int a, b, c, lcm;
+	unsigned long ulcm;
 	int byte, i, msbit;
 
 	/* the code below is more readable if I make these bytes
@@ -82,17 +83,7 @@ static void krb5_nfold(u32 inbits, const u8 *in,
 	outbits >>= 3;
 
 	/* first compute lcm(n,k) */
-
-	a = outbits;
-	b = inbits;
-
-	while (b != 0) {
-		c = b;
-		b = a%b;
-		a = c;
-	}
-
-	lcm = outbits*inbits/a;
+	ulcm = lcm(inbits, outbits);
 
 	/* now do the real work */
 
@@ -101,7 +92,7 @@ static void krb5_nfold(u32 inbits, const u8 *in,
 
 	/* this will end up cycling through k lcm(k,n)/k times, which
 	   is correct */
-	for (i = lcm-1; i >= 0; i--) {
+	for (i = ulcm-1; i >= 0; i--) {
 		/* compute the msbit in k which gets added into this byte */
 		msbit = (
 			/* first, start with the msbit in the first,
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index 27ce2624093..92d5ab99fbf 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -218,10 +218,8 @@ static struct gss_api_mech *_gss_mech_get_by_pseudoflavor(u32 pseudoflavor)
 
 	spin_lock(&registered_mechs_lock);
 	list_for_each_entry(pos, &registered_mechs, gm_list) {
-		if (!mech_supports_pseudoflavor(pos, pseudoflavor)) {
-			module_put(pos->gm_owner);
+		if (!mech_supports_pseudoflavor(pos, pseudoflavor))
 			continue;
-		}
 		if (try_module_get(pos->gm_owner))
 			gm = pos;
 		break;
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index 458f85e9b0b..abbb7dcd168 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -137,7 +137,6 @@ void init_gssp_clnt(struct sunrpc_net *sn)
 {
 	mutex_init(&sn->gssp_lock);
 	sn->gssp_clnt = NULL;
-	init_waitqueue_head(&sn->gssp_wq);
 }
 
 int set_gssp_clnt(struct net *net)
@@ -154,7 +153,6 @@ int set_gssp_clnt(struct net *net)
 		sn->gssp_clnt = clnt;
 	}
 	mutex_unlock(&sn->gssp_lock);
-	wake_up(&sn->gssp_wq);
 	return ret;
 }
 
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 008cdade5aa..4ce5eccec1f 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1263,65 +1263,34 @@ out:
 	return ret;
 }
 
-DEFINE_SPINLOCK(use_gssp_lock);
-
-static bool use_gss_proxy(struct net *net)
-{
-	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
-
-	if (sn->use_gss_proxy != -1)
-		return sn->use_gss_proxy;
-	spin_lock(&use_gssp_lock);
-	/*
-	 * If you wanted gss-proxy, you should have said so before
-	 * starting to accept requests:
-	 */
-	sn->use_gss_proxy = 0;
-	spin_unlock(&use_gssp_lock);
-	return 0;
-}
-
-#ifdef CONFIG_PROC_FS
-
+/*
+ * Try to set the sn->use_gss_proxy variable to a new value. We only allow
+ * it to be changed if it's currently undefined (-1). If it's any other value
+ * then return -EBUSY unless the type wouldn't have changed anyway.
+ */
 static int set_gss_proxy(struct net *net, int type)
 {
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
-	int ret = 0;
+	int ret;
 
 	WARN_ON_ONCE(type != 0 && type != 1);
-	spin_lock(&use_gssp_lock);
-	if (sn->use_gss_proxy == -1 || sn->use_gss_proxy == type)
-		sn->use_gss_proxy = type;
-	else
-		ret = -EBUSY;
-	spin_unlock(&use_gssp_lock);
-	wake_up(&sn->gssp_wq);
-	return ret;
-}
-
-static inline bool gssp_ready(struct sunrpc_net *sn)
-{
-	switch (sn->use_gss_proxy) {
-		case -1:
-			return false;
-		case 0:
-			return true;
-		case 1:
-			return sn->gssp_clnt;
-	}
-	WARN_ON_ONCE(1);
-	return false;
+	ret = cmpxchg(&sn->use_gss_proxy, -1, type);
+	if (ret != -1 && ret != type)
+		return -EBUSY;
+	return 0;
 }
 
-static int wait_for_gss_proxy(struct net *net, struct file *file)
+static bool use_gss_proxy(struct net *net)
 {
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 
-	if (file->f_flags & O_NONBLOCK && !gssp_ready(sn))
-		return -EAGAIN;
-	return wait_event_interruptible(sn->gssp_wq, gssp_ready(sn));
+	/* If use_gss_proxy is still undefined, then try to disable it */
+	if (sn->use_gss_proxy == -1)
+		set_gss_proxy(net, 0);
+	return sn->use_gss_proxy;
 }
 
+#ifdef CONFIG_PROC_FS
 
 static ssize_t write_gssp(struct file *file, const char __user *buf,
 			 size_t count, loff_t *ppos)
@@ -1342,10 +1311,10 @@ static ssize_t write_gssp(struct file *file, const char __user *buf,
 		return res;
 	if (i != 1)
 		return -EINVAL;
-	res = set_gss_proxy(net, 1);
+	res = set_gssp_clnt(net);
 	if (res)
 		return res;
-	res = set_gssp_clnt(net);
+	res = set_gss_proxy(net, 1);
 	if (res)
 		return res;
 	return count;
@@ -1355,16 +1324,12 @@ static ssize_t read_gssp(struct file *file, char __user *buf,
 			 size_t count, loff_t *ppos)
 {
 	struct net *net = PDE_DATA(file_inode(file));
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	unsigned long p = *ppos;
 	char tbuf[10];
 	size_t len;
-	int ret;
 
-	ret = wait_for_gss_proxy(net, file);
-	if (ret)
-		return ret;
-
-	snprintf(tbuf, sizeof(tbuf), "%d\n", use_gss_proxy(net));
+	snprintf(tbuf, sizeof(tbuf), "%d\n", sn->use_gss_proxy);
 	len = strlen(tbuf);
 	if (p >= len)
 		return 0;
@@ -1538,6 +1503,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp)
 			if (unwrap_integ_data(rqstp, &rqstp->rq_arg,
 					gc->gc_seq, rsci->mechctx))
 				goto garbage_args;
+			rqstp->rq_auth_slack = RPC_MAX_AUTH_SIZE;
 			break;
 		case RPC_GSS_SVC_PRIVACY:
 			/* placeholders for length and seq. number: */
@@ -1546,6 +1512,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp)
 			if (unwrap_priv_data(rqstp, &rqstp->rq_arg,
 					gc->gc_seq, rsci->mechctx))
 				goto garbage_args;
+			rqstp->rq_auth_slack = RPC_MAX_AUTH_SIZE * 2;
 			break;
 		default:
 			goto auth_err;
@@ -1626,8 +1593,7 @@ svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp)
 	BUG_ON(integ_len % 4);
 	*p++ = htonl(integ_len);
 	*p++ = htonl(gc->gc_seq);
-	if (xdr_buf_subsegment(resbuf, &integ_buf, integ_offset,
-				integ_len))
+	if (xdr_buf_subsegment(resbuf, &integ_buf, integ_offset, integ_len))
 		BUG();
 	if (resbuf->tail[0].iov_base == NULL) {
 		if (resbuf->head[0].iov_len + RPC_MAX_AUTH_SIZE > PAGE_SIZE)
@@ -1635,10 +1601,8 @@ svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp)
 		resbuf->tail[0].iov_base = resbuf->head[0].iov_base
 						+ resbuf->head[0].iov_len;
 		resbuf->tail[0].iov_len = 0;
-		resv = &resbuf->tail[0];
-	} else {
-		resv = &resbuf->tail[0];
 	}
+	resv = &resbuf->tail[0];
 	mic.data = (u8 *)resv->iov_base + resv->iov_len + 4;
 	if (gss_get_mic(gsd->rsci->mechctx, &integ_buf, &mic))
 		goto out_err;
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 890a29912d5..9761a0da964 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -64,7 +64,6 @@ static void xprt_free_allocation(struct rpc_rqst *req)
 	free_page((unsigned long)xbufp->head[0].iov_base);
 	xbufp = &req->rq_snd_buf;
 	free_page((unsigned long)xbufp->head[0].iov_base);
-	list_del(&req->rq_bc_pa_list);
 	kfree(req);
 }
 
@@ -168,8 +167,10 @@ out_free:
 	/*
 	 * Memory allocation failed, free the temporary list
 	 */
-	list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list)
+	list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) {
+		list_del(&req->rq_bc_pa_list);
 		xprt_free_allocation(req);
+	}
 
 	dprintk("RPC:       setup backchannel transport failed\n");
 	return -ENOMEM;
@@ -198,6 +199,7 @@ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs)
 	xprt_dec_alloc_count(xprt, max_reqs);
 	list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) {
 		dprintk("RPC:        req=%p\n", req);
+		list_del(&req->rq_bc_pa_list);
 		xprt_free_allocation(req);
 		if (--max_reqs == 0)
 			break;
@@ -210,39 +212,23 @@ out:
 }
 EXPORT_SYMBOL_GPL(xprt_destroy_backchannel);
 
-/*
- * One or more rpc_rqst structure have been preallocated during the
- * backchannel setup.  Buffer space for the send and private XDR buffers
- * has been preallocated as well.  Use xprt_alloc_bc_request to allocate
- * to this request.  Use xprt_free_bc_request to return it.
- *
- * We know that we're called in soft interrupt context, grab the spin_lock
- * since there is no need to grab the bottom half spin_lock.
- *
- * Return an available rpc_rqst, otherwise NULL if non are available.
- */
-struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt)
+static struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt, __be32 xid)
 {
-	struct rpc_rqst *req;
+	struct rpc_rqst *req = NULL;
 
 	dprintk("RPC:       allocate a backchannel request\n");
-	spin_lock(&xprt->bc_pa_lock);
-	if (!list_empty(&xprt->bc_pa_list)) {
-		req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
-				rq_bc_pa_list);
-		list_del(&req->rq_bc_pa_list);
-	} else {
-		req = NULL;
-	}
-	spin_unlock(&xprt->bc_pa_lock);
+	if (list_empty(&xprt->bc_pa_list))
+		goto not_found;
 
-	if (req != NULL) {
-		set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
-		req->rq_reply_bytes_recvd = 0;
-		req->rq_bytes_sent = 0;
-		memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
+	req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
+				rq_bc_pa_list);
+	req->rq_reply_bytes_recvd = 0;
+	req->rq_bytes_sent = 0;
+	memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
 			sizeof(req->rq_private_buf));
-	}
+	req->rq_xid = xid;
+	req->rq_connect_cookie = xprt->connect_cookie;
+not_found:
 	dprintk("RPC:       backchannel req=%p\n", req);
 	return req;
 }
@@ -257,10 +243,11 @@ void xprt_free_bc_request(struct rpc_rqst *req)
 
 	dprintk("RPC:       free backchannel req=%p\n", req);
 
-	smp_mb__before_clear_bit();
+	req->rq_connect_cookie = xprt->connect_cookie - 1;
+	smp_mb__before_atomic();
 	WARN_ON_ONCE(!test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state));
 	clear_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	if (!xprt_need_to_requeue(xprt)) {
 		/*
@@ -279,7 +266,57 @@ void xprt_free_bc_request(struct rpc_rqst *req)
 	 * may be reused by a new callback request.
 	 */
 	spin_lock_bh(&xprt->bc_pa_lock);
-	list_add(&req->rq_bc_pa_list, &xprt->bc_pa_list);
+	list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list);
 	spin_unlock_bh(&xprt->bc_pa_lock);
 }
 
+/*
+ * One or more rpc_rqst structure have been preallocated during the
+ * backchannel setup.  Buffer space for the send and private XDR buffers
+ * has been preallocated as well.  Use xprt_alloc_bc_request to allocate
+ * to this request.  Use xprt_free_bc_request to return it.
+ *
+ * We know that we're called in soft interrupt context, grab the spin_lock
+ * since there is no need to grab the bottom half spin_lock.
+ *
+ * Return an available rpc_rqst, otherwise NULL if non are available.
+ */
+struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid)
+{
+	struct rpc_rqst *req;
+
+	spin_lock(&xprt->bc_pa_lock);
+	list_for_each_entry(req, &xprt->bc_pa_list, rq_bc_pa_list) {
+		if (req->rq_connect_cookie != xprt->connect_cookie)
+			continue;
+		if (req->rq_xid == xid)
+			goto found;
+	}
+	req = xprt_alloc_bc_request(xprt, xid);
+found:
+	spin_unlock(&xprt->bc_pa_lock);
+	return req;
+}
+
+/*
+ * Add callback request to callback list.  The callback
+ * service sleeps on the sv_cb_waitq waiting for new
+ * requests.  Wake it up after adding enqueing the
+ * request.
+ */
+void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied)
+{
+	struct rpc_xprt *xprt = req->rq_xprt;
+	struct svc_serv *bc_serv = xprt->bc_serv;
+
+	req->rq_private_buf.len = copied;
+	set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
+
+	dprintk("RPC:       add callback request to list\n");
+	spin_lock(&bc_serv->sv_cb_lock);
+	list_del(&req->rq_bc_pa_list);
+	list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
+	wake_up(&bc_serv->sv_cb_waitq);
+	spin_unlock(&bc_serv->sv_cb_lock);
+}
+
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index a72de074172..06636214113 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -374,7 +374,7 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd)
 	}
 	return;
 out:
-	printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name);
+	printk(KERN_ERR "RPC: failed to unregister %s cache\n", cd->name);
 }
 EXPORT_SYMBOL_GPL(sunrpc_destroy_cache_detail);
 
@@ -619,7 +619,7 @@ static void cache_limit_defers(void)
 
 	/* Consider removing either the first or the last */
 	if (cache_defer_cnt > DFR_MAX) {
-		if (net_random() & 1)
+		if (prandom_u32() & 1)
 			discard = list_entry(cache_defer_list.next,
 					     struct cache_deferred_req, recent);
 		else
@@ -1111,9 +1111,7 @@ void qword_addhex(char **bpp, int *lp, char *buf, int blen)
 		*bp++ = 'x';
 		len -= 2;
 		while (blen && len >= 2) {
-			unsigned char c = *buf++;
-			*bp++ = '0' + ((c&0xf0)>>4) + (c>=0xa0)*('a'-'9'-1);
-			*bp++ = '0' + (c&0x0f) + ((c&0x0f)>=0x0a)*('a'-'9'-1);
+			bp = hex_byte_pack(bp, *buf++);
 			len -= 2;
 			blen--;
 		}
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index f09b7db2c49..2e6ab10734f 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -438,6 +438,38 @@ out_no_rpciod:
 	return ERR_PTR(err);
 }
 
+struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
+					struct rpc_xprt *xprt)
+{
+	struct rpc_clnt *clnt = NULL;
+
+	clnt = rpc_new_client(args, xprt, NULL);
+	if (IS_ERR(clnt))
+		return clnt;
+
+	if (!(args->flags & RPC_CLNT_CREATE_NOPING)) {
+		int err = rpc_ping(clnt);
+		if (err != 0) {
+			rpc_shutdown_client(clnt);
+			return ERR_PTR(err);
+		}
+	}
+
+	clnt->cl_softrtry = 1;
+	if (args->flags & RPC_CLNT_CREATE_HARDRTRY)
+		clnt->cl_softrtry = 0;
+
+	if (args->flags & RPC_CLNT_CREATE_AUTOBIND)
+		clnt->cl_autobind = 1;
+	if (args->flags & RPC_CLNT_CREATE_DISCRTRY)
+		clnt->cl_discrtry = 1;
+	if (!(args->flags & RPC_CLNT_CREATE_QUIET))
+		clnt->cl_chatty = 1;
+
+	return clnt;
+}
+EXPORT_SYMBOL_GPL(rpc_create_xprt);
+
 /**
  * rpc_create - create an RPC client and transport with one call
  * @args: rpc_clnt create argument structure
@@ -451,7 +483,6 @@ out_no_rpciod:
 struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 {
 	struct rpc_xprt *xprt;
-	struct rpc_clnt *clnt;
 	struct xprt_create xprtargs = {
 		.net = args->net,
 		.ident = args->protocol,
@@ -515,30 +546,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT)
 		xprt->resvport = 0;
 
-	clnt = rpc_new_client(args, xprt, NULL);
-	if (IS_ERR(clnt))
-		return clnt;
-
-	if (!(args->flags & RPC_CLNT_CREATE_NOPING)) {
-		int err = rpc_ping(clnt);
-		if (err != 0) {
-			rpc_shutdown_client(clnt);
-			return ERR_PTR(err);
-		}
-	}
-
-	clnt->cl_softrtry = 1;
-	if (args->flags & RPC_CLNT_CREATE_HARDRTRY)
-		clnt->cl_softrtry = 0;
-
-	if (args->flags & RPC_CLNT_CREATE_AUTOBIND)
-		clnt->cl_autobind = 1;
-	if (args->flags & RPC_CLNT_CREATE_DISCRTRY)
-		clnt->cl_discrtry = 1;
-	if (!(args->flags & RPC_CLNT_CREATE_QUIET))
-		clnt->cl_chatty = 1;
-
-	return clnt;
+	return rpc_create_xprt(args, xprt);
 }
 EXPORT_SYMBOL_GPL(rpc_create);
 
@@ -1363,6 +1371,7 @@ rpc_restart_call_prepare(struct rpc_task *task)
 	if (RPC_ASSASSINATED(task))
 		return 0;
 	task->tk_action = call_start;
+	task->tk_status = 0;
 	if (task->tk_ops->rpc_call_prepare != NULL)
 		task->tk_action = rpc_prepare_task;
 	return 1;
@@ -1379,6 +1388,7 @@ rpc_restart_call(struct rpc_task *task)
 	if (RPC_ASSASSINATED(task))
 		return 0;
 	task->tk_action = call_start;
+	task->tk_status = 0;
 	return 1;
 }
 EXPORT_SYMBOL_GPL(rpc_restart_call);
@@ -1529,9 +1539,13 @@ call_refreshresult(struct rpc_task *task)
 	task->tk_action = call_refresh;
 	switch (status) {
 	case 0:
-		if (rpcauth_uptodatecred(task))
+		if (rpcauth_uptodatecred(task)) {
 			task->tk_action = call_allocate;
-		return;
+			return;
+		}
+		/* Use rate-limiting and a max number of retries if refresh
+		 * had status 0 but failed to update the cred.
+		 */
 	case -ETIMEDOUT:
 		rpc_delay(task, 3*HZ);
 	case -EAGAIN:
@@ -1724,11 +1738,10 @@ call_bind_status(struct rpc_task *task)
 	case -EPROTONOSUPPORT:
 		dprintk("RPC: %5u remote rpcbind version unavailable, retrying\n",
 				task->tk_pid);
-		task->tk_status = 0;
-		task->tk_action = call_bind;
-		return;
+		goto retry_timeout;
 	case -ECONNREFUSED:		/* connection problems */
 	case -ECONNRESET:
+	case -ECONNABORTED:
 	case -ENOTCONN:
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
@@ -1751,6 +1764,7 @@ call_bind_status(struct rpc_task *task)
 	return;
 
 retry_timeout:
+	task->tk_status = 0;
 	task->tk_action = call_timeout;
 }
 
@@ -1793,19 +1807,19 @@ call_connect_status(struct rpc_task *task)
 	trace_rpc_connect_status(task, status);
 	task->tk_status = 0;
 	switch (status) {
-		/* if soft mounted, test if we've timed out */
-	case -ETIMEDOUT:
-		task->tk_action = call_timeout;
-		return;
 	case -ECONNREFUSED:
 	case -ECONNRESET:
+	case -ECONNABORTED:
 	case -ENETUNREACH:
-		/* retry with existing socket, after a delay */
-		rpc_delay(task, 3*HZ);
+	case -EHOSTUNREACH:
 		if (RPC_IS_SOFTCONN(task))
 			break;
+		/* retry with existing socket, after a delay */
+		rpc_delay(task, 3*HZ);
 	case -EAGAIN:
-		task->tk_action = call_bind;
+		/* Check for timeouts before looping back to call_bind */
+	case -ETIMEDOUT:
+		task->tk_action = call_timeout;
 		return;
 	case 0:
 		clnt->cl_stats->netreconn++;
@@ -1902,6 +1916,7 @@ call_transmit_status(struct rpc_task *task)
 			break;
 		}
 	case -ECONNRESET:
+	case -ECONNABORTED:
 	case -ENOTCONN:
 	case -EPIPE:
 		rpc_task_force_reencode(task);
@@ -1999,6 +2014,10 @@ call_status(struct rpc_task *task)
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
 	case -ENETUNREACH:
+		if (RPC_IS_SOFTCONN(task)) {
+			rpc_exit(task, status);
+			break;
+		}
 		/*
 		 * Delay any retries for 3 seconds, then handle as if it
 		 * were a timeout.
@@ -2011,8 +2030,9 @@ call_status(struct rpc_task *task)
 			xprt_conditional_disconnect(req->rq_xprt,
 					req->rq_connect_cookie);
 		break;
-	case -ECONNRESET:
 	case -ECONNREFUSED:
+	case -ECONNRESET:
+	case -ECONNABORTED:
 		rpc_force_rebind(clnt);
 		rpc_delay(task, 3*HZ);
 	case -EPIPE:
diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h
index 779742cfc1f..df582687653 100644
--- a/net/sunrpc/netns.h
+++ b/net/sunrpc/netns.h
@@ -14,6 +14,7 @@ struct sunrpc_net {
 	struct cache_detail *rsi_cache;
 
 	struct super_block *pipefs_sb;
+	struct rpc_pipe *gssd_dummy;
 	struct mutex pipefs_sb_lock;
 
 	struct list_head all_clients;
@@ -26,14 +27,11 @@ struct sunrpc_net {
 	unsigned int rpcb_is_af_local : 1;
 
 	struct mutex gssp_lock;
-	wait_queue_head_t gssp_wq;
 	struct rpc_clnt *gssp_clnt;
 	int use_gss_proxy;
 	int pipe_version;
 	atomic_t pipe_users;
 	struct proc_dir_entry *use_gssp_proc;
-
-	unsigned int gssd_running;
 };
 
 extern int sunrpc_net_id;
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index bf04b30a788..b1855489856 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -17,6 +17,7 @@
 #include <linux/fsnotify.h>
 #include <linux/kernel.h>
 #include <linux/rcupdate.h>
+#include <linux/utsname.h>
 
 #include <asm/ioctls.h>
 #include <linux/poll.h>
@@ -38,7 +39,7 @@
 #define NET_NAME(net)	((net == &init_net) ? " (init_net)" : "")
 
 static struct file_system_type rpc_pipe_fs_type;
-
+static const struct rpc_pipe_ops gssd_dummy_pipe_ops;
 
 static struct kmem_cache *rpc_inode_cachep __read_mostly;
 
@@ -216,14 +217,11 @@ rpc_destroy_inode(struct inode *inode)
 static int
 rpc_pipe_open(struct inode *inode, struct file *filp)
 {
-	struct net *net = inode->i_sb->s_fs_info;
-	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	struct rpc_pipe *pipe;
 	int first_open;
 	int res = -ENXIO;
 
 	mutex_lock(&inode->i_mutex);
-	sn->gssd_running = 1;
 	pipe = RPC_I(inode)->pipe;
 	if (pipe == NULL)
 		goto out;
@@ -1159,6 +1157,7 @@ enum {
 	RPCAUTH_nfsd4_cb,
 	RPCAUTH_cache,
 	RPCAUTH_nfsd,
+	RPCAUTH_gssd,
 	RPCAUTH_RootEOF
 };
 
@@ -1195,6 +1194,10 @@ static const struct rpc_filelist files[] = {
 		.name = "nfsd",
 		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
 	},
+	[RPCAUTH_gssd] = {
+		.name = "gssd",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
 };
 
 /*
@@ -1208,13 +1211,24 @@ struct dentry *rpc_d_lookup_sb(const struct super_block *sb,
 }
 EXPORT_SYMBOL_GPL(rpc_d_lookup_sb);
 
-void rpc_pipefs_init_net(struct net *net)
+int rpc_pipefs_init_net(struct net *net)
 {
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 
+	sn->gssd_dummy = rpc_mkpipe_data(&gssd_dummy_pipe_ops, 0);
+	if (IS_ERR(sn->gssd_dummy))
+		return PTR_ERR(sn->gssd_dummy);
+
 	mutex_init(&sn->pipefs_sb_lock);
-	sn->gssd_running = 1;
 	sn->pipe_version = -1;
+	return 0;
+}
+
+void rpc_pipefs_exit_net(struct net *net)
+{
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
+
+	rpc_destroy_pipe_data(sn->gssd_dummy);
 }
 
 /*
@@ -1244,11 +1258,134 @@ void rpc_put_sb_net(const struct net *net)
 }
 EXPORT_SYMBOL_GPL(rpc_put_sb_net);
 
+static const struct rpc_filelist gssd_dummy_clnt_dir[] = {
+	[0] = {
+		.name = "clntXX",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
+};
+
+static ssize_t
+dummy_downcall(struct file *filp, const char __user *src, size_t len)
+{
+	return -EINVAL;
+}
+
+static const struct rpc_pipe_ops gssd_dummy_pipe_ops = {
+	.upcall		= rpc_pipe_generic_upcall,
+	.downcall	= dummy_downcall,
+};
+
+/*
+ * Here we present a bogus "info" file to keep rpc.gssd happy. We don't expect
+ * that it will ever use this info to handle an upcall, but rpc.gssd expects
+ * that this file will be there and have a certain format.
+ */
+static int
+rpc_show_dummy_info(struct seq_file *m, void *v)
+{
+	seq_printf(m, "RPC server: %s\n", utsname()->nodename);
+	seq_printf(m, "service: foo (1) version 0\n");
+	seq_printf(m, "address: 127.0.0.1\n");
+	seq_printf(m, "protocol: tcp\n");
+	seq_printf(m, "port: 0\n");
+	return 0;
+}
+
+static int
+rpc_dummy_info_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, rpc_show_dummy_info, NULL);
+}
+
+static const struct file_operations rpc_dummy_info_operations = {
+	.owner		= THIS_MODULE,
+	.open		= rpc_dummy_info_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static const struct rpc_filelist gssd_dummy_info_file[] = {
+	[0] = {
+		.name = "info",
+		.i_fop = &rpc_dummy_info_operations,
+		.mode = S_IFREG | S_IRUSR,
+	},
+};
+
+/**
+ * rpc_gssd_dummy_populate - create a dummy gssd pipe
+ * @root:	root of the rpc_pipefs filesystem
+ * @pipe_data:	pipe data created when netns is initialized
+ *
+ * Create a dummy set of directories and a pipe that gssd can hold open to
+ * indicate that it is up and running.
+ */
+static struct dentry *
+rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data)
+{
+	int ret = 0;
+	struct dentry *gssd_dentry;
+	struct dentry *clnt_dentry = NULL;
+	struct dentry *pipe_dentry = NULL;
+	struct qstr q = QSTR_INIT(files[RPCAUTH_gssd].name,
+				  strlen(files[RPCAUTH_gssd].name));
+
+	/* We should never get this far if "gssd" doesn't exist */
+	gssd_dentry = d_hash_and_lookup(root, &q);
+	if (!gssd_dentry)
+		return ERR_PTR(-ENOENT);
+
+	ret = rpc_populate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1, NULL);
+	if (ret) {
+		pipe_dentry = ERR_PTR(ret);
+		goto out;
+	}
+
+	q.name = gssd_dummy_clnt_dir[0].name;
+	q.len = strlen(gssd_dummy_clnt_dir[0].name);
+	clnt_dentry = d_hash_and_lookup(gssd_dentry, &q);
+	if (!clnt_dentry) {
+		pipe_dentry = ERR_PTR(-ENOENT);
+		goto out;
+	}
+
+	ret = rpc_populate(clnt_dentry, gssd_dummy_info_file, 0, 1, NULL);
+	if (ret) {
+		__rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1);
+		pipe_dentry = ERR_PTR(ret);
+		goto out;
+	}
+
+	pipe_dentry = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data);
+	if (IS_ERR(pipe_dentry)) {
+		__rpc_depopulate(clnt_dentry, gssd_dummy_info_file, 0, 1);
+		__rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1);
+	}
+out:
+	dput(clnt_dentry);
+	dput(gssd_dentry);
+	return pipe_dentry;
+}
+
+static void
+rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry)
+{
+	struct dentry *clnt_dir = pipe_dentry->d_parent;
+	struct dentry *gssd_dir = clnt_dir->d_parent;
+
+	__rpc_rmpipe(clnt_dir->d_inode, pipe_dentry);
+	__rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1);
+	__rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1);
+	dput(pipe_dentry);
+}
+
 static int
 rpc_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct inode *inode;
-	struct dentry *root;
+	struct dentry *root, *gssd_dentry;
 	struct net *net = data;
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	int err;
@@ -1266,6 +1403,13 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 	if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL))
 		return -ENOMEM;
+
+	gssd_dentry = rpc_gssd_dummy_populate(root, sn->gssd_dummy);
+	if (IS_ERR(gssd_dentry)) {
+		__rpc_depopulate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF);
+		return PTR_ERR(gssd_dentry);
+	}
+
 	dprintk("RPC:       sending pipefs MOUNT notification for net %p%s\n",
 		net, NET_NAME(net));
 	mutex_lock(&sn->pipefs_sb_lock);
@@ -1280,6 +1424,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
 	return 0;
 
 err_depopulate:
+	rpc_gssd_dummy_depopulate(gssd_dentry);
 	blocking_notifier_call_chain(&rpc_pipefs_notifier_list,
 					   RPC_PIPEFS_UMOUNT,
 					   sb);
@@ -1289,6 +1434,16 @@ err_depopulate:
 	return err;
 }
 
+bool
+gssd_running(struct net *net)
+{
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
+	struct rpc_pipe *pipe = sn->gssd_dummy;
+
+	return pipe->nreaders || pipe->nwriters;
+}
+EXPORT_SYMBOL_GPL(gssd_running);
+
 static struct dentry *
 rpc_mount(struct file_system_type *fs_type,
 		int flags, const char *dev_name, void *data)
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index ff3cc4bf4b2..c0365c14b85 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -637,7 +637,8 @@ static void __rpc_queue_timer_fn(unsigned long ptr)
 
 static void __rpc_atrun(struct rpc_task *task)
 {
-	task->tk_status = 0;
+	if (task->tk_status == -ETIMEDOUT)
+		task->tk_status = 0;
 }
 
 /*
@@ -831,7 +832,8 @@ static void rpc_async_schedule(struct work_struct *work)
  * @size: requested byte size
  *
  * To prevent rpciod from hanging, this allocator never sleeps,
- * returning NULL if the request cannot be serviced immediately.
+ * returning NULL and suppressing warning if the request cannot be serviced
+ * immediately.
  * The caller can arrange to sleep in a way that is safe for rpciod.
  *
  * Most requests are 'small' (under 2KiB) and can be serviced from a
@@ -844,7 +846,7 @@ static void rpc_async_schedule(struct work_struct *work)
 void *rpc_malloc(struct rpc_task *task, size_t size)
 {
 	struct rpc_buffer *buf;
-	gfp_t gfp = GFP_NOWAIT;
+	gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN;
 
 	if (RPC_IS_SWAPPER(task))
 		gfp |= __GFP_MEMALLOC;
diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c
index 0a648c502fc..2df87f78e51 100644
--- a/net/sunrpc/socklib.c
+++ b/net/sunrpc/socklib.c
@@ -173,7 +173,8 @@ int csum_partial_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
 		return -1;
 	if (csum_fold(desc.csum))
 		return -1;
-	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
+	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+	    !skb->csum_complete_sw)
 		netdev_rx_csum_fault(skb->dev);
 	return 0;
 no_checksum:
diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h
index 14c9f6d1c5f..f2b7cb540e6 100644
--- a/net/sunrpc/sunrpc.h
+++ b/net/sunrpc/sunrpc.h
@@ -43,6 +43,19 @@ static inline int rpc_reply_expected(struct rpc_task *task)
 		(task->tk_msg.rpc_proc->p_decode != NULL);
 }
 
+static inline int sock_is_loopback(struct sock *sk)
+{
+	struct dst_entry *dst;
+	int loopback = 0;
+	rcu_read_lock();
+	dst = rcu_dereference(sk->sk_dst_cache);
+	if (dst && dst->dev &&
+	    (dst->dev->features & NETIF_F_LOOPBACK))
+		loopback = 1;
+	rcu_read_unlock();
+	return loopback;
+}
+
 int svc_send_common(struct socket *sock, struct xdr_buf *xdr,
 		    struct page *headpage, unsigned long headoffset,
 		    struct page *tailpage, unsigned long tailoffset);
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index 3d6498af9ad..cd30120de9e 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -44,12 +44,17 @@ static __net_init int sunrpc_init_net(struct net *net)
 	if (err)
 		goto err_unixgid;
 
-	rpc_pipefs_init_net(net);
+	err = rpc_pipefs_init_net(net);
+	if (err)
+		goto err_pipefs;
+
 	INIT_LIST_HEAD(&sn->all_clients);
 	spin_lock_init(&sn->rpc_client_lock);
 	spin_lock_init(&sn->rpcb_clnt_lock);
 	return 0;
 
+err_pipefs:
+	unix_gid_cache_destroy(net);
 err_unixgid:
 	ip_map_cache_destroy(net);
 err_ipmap:
@@ -60,6 +65,7 @@ err_proc:
 
 static __net_exit void sunrpc_exit_net(struct net *net)
 {
+	rpc_pipefs_exit_net(net);
 	unix_gid_cache_destroy(net);
 	ip_map_cache_destroy(net);
 	rpc_proc_exit(net);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index e7fbe368b4a..5de6801cd92 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -916,9 +916,6 @@ static int __svc_register(struct net *net, const char *progname,
 #endif
 	}
 
-	if (error < 0)
-		printk(KERN_WARNING "svc: failed to register %sv%u RPC "
-			"service (errno %d).\n", progname, version, -error);
 	return error;
 }
 
@@ -937,6 +934,7 @@ int svc_register(const struct svc_serv *serv, struct net *net,
 		 const unsigned short port)
 {
 	struct svc_program	*progp;
+	struct svc_version	*vers;
 	unsigned int		i;
 	int			error = 0;
 
@@ -946,7 +944,8 @@ int svc_register(const struct svc_serv *serv, struct net *net,
 
 	for (progp = serv->sv_program; progp; progp = progp->pg_next) {
 		for (i = 0; i < progp->pg_nvers; i++) {
-			if (progp->pg_vers[i] == NULL)
+			vers = progp->pg_vers[i];
+			if (vers == NULL)
 				continue;
 
 			dprintk("svc: svc_register(%sv%d, %s, %u, %u)%s\n",
@@ -955,16 +954,26 @@ int svc_register(const struct svc_serv *serv, struct net *net,
 					proto == IPPROTO_UDP?  "udp" : "tcp",
 					port,
 					family,
-					progp->pg_vers[i]->vs_hidden?
-						" (but not telling portmap)" : "");
+					vers->vs_hidden ?
+					" (but not telling portmap)" : "");
 
-			if (progp->pg_vers[i]->vs_hidden)
+			if (vers->vs_hidden)
 				continue;
 
 			error = __svc_register(net, progp->pg_name, progp->pg_prog,
 						i, family, proto, port);
-			if (error < 0)
+
+			if (vers->vs_rpcb_optnl) {
+				error = 0;
+				continue;
+			}
+
+			if (error < 0) {
+				printk(KERN_WARNING "svc: failed to register "
+					"%sv%u RPC service (errno %d).\n",
+					progp->pg_name, i, -error);
 				break;
+			}
 		}
 	}
 
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 80a6640f329..b4737fbdec1 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -571,7 +571,7 @@ static void svc_check_conn_limits(struct svc_serv *serv)
 	}
 }
 
-int svc_alloc_arg(struct svc_rqst *rqstp)
+static int svc_alloc_arg(struct svc_rqst *rqstp)
 {
 	struct svc_serv *serv = rqstp->rq_server;
 	struct xdr_buf *arg;
@@ -597,6 +597,7 @@ int svc_alloc_arg(struct svc_rqst *rqstp)
 			}
 			rqstp->rq_pages[i] = p;
 		}
+	rqstp->rq_page_end = &rqstp->rq_pages[i];
 	rqstp->rq_pages[i++] = NULL; /* this might be seen in nfs_read_actor */
 
 	/* Make arg->head point to first page and arg->pages point to rest */
@@ -612,7 +613,7 @@ int svc_alloc_arg(struct svc_rqst *rqstp)
 	return 0;
 }
 
-struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
+static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 {
 	struct svc_xprt *xprt;
 	struct svc_pool		*pool = rqstp->rq_pool;
@@ -691,7 +692,7 @@ struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 	return xprt;
 }
 
-void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
+static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
 {
 	spin_lock_bh(&serv->sv_lock);
 	set_bit(XPT_TEMP, &newxpt->xpt_flags);
@@ -730,6 +731,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 		newxpt = xprt->xpt_ops->xpo_accept(xprt);
 		if (newxpt)
 			svc_add_new_temp_xprt(serv, newxpt);
+		else
+			module_put(xprt->xpt_class->xcl_owner);
 	} else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
 		/* XPT_DATA|XPT_DEFERRED case: */
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
@@ -793,7 +796,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 
 	clear_bit(XPT_OLD, &xprt->xpt_flags);
 
-	rqstp->rq_secure = svc_port_is_privileged(svc_addr(rqstp));
+	rqstp->rq_secure = xprt->xpt_ops->xpo_secure_port(rqstp);
 	rqstp->rq_chandle.defer = svc_defer;
 
 	if (serv->sv_stats)
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index 2af7b0cba43..79c0f3459b5 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -54,6 +54,8 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
 	}
 	spin_unlock(&authtab_lock);
 
+	rqstp->rq_auth_slack = 0;
+
 	rqstp->rq_authop = aops;
 	return aops->accept(rqstp, authp);
 }
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b6e59f0a947..b507cd327d9 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -60,7 +60,7 @@
 
 static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
 					 int flags);
-static void		svc_udp_data_ready(struct sock *, int);
+static void		svc_udp_data_ready(struct sock *);
 static int		svc_udp_recvfrom(struct svc_rqst *);
 static int		svc_udp_sendto(struct svc_rqst *);
 static void		svc_sock_detach(struct svc_xprt *);
@@ -400,17 +400,23 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
 	release_sock(sock->sk);
 #endif
 }
+
+static int svc_sock_secure_port(struct svc_rqst *rqstp)
+{
+	return svc_port_is_privileged(svc_addr(rqstp));
+}
+
 /*
  * INET callback when data has been received on the socket.
  */
-static void svc_udp_data_ready(struct sock *sk, int count)
+static void svc_udp_data_ready(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
 	wait_queue_head_t *wq = sk_sleep(sk);
 
 	if (svsk) {
-		dprintk("svc: socket %p(inet %p), count=%d, busy=%d\n",
-			svsk, sk, count,
+		dprintk("svc: socket %p(inet %p), busy=%d\n",
+			svsk, sk,
 			test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 		svc_xprt_enqueue(&svsk->sk_xprt);
@@ -678,6 +684,7 @@ static struct svc_xprt_ops svc_udp_ops = {
 	.xpo_prep_reply_hdr = svc_udp_prep_reply_hdr,
 	.xpo_has_wspace = svc_udp_has_wspace,
 	.xpo_accept = svc_udp_accept,
+	.xpo_secure_port = svc_sock_secure_port,
 };
 
 static struct svc_xprt_class svc_udp_class = {
@@ -731,7 +738,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
  * A data_ready event on a listening socket means there's a connection
  * pending. Do not use state_change as a substitute for it.
  */
-static void svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
+static void svc_tcp_listen_data_ready(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
 	wait_queue_head_t *wq;
@@ -783,7 +790,7 @@ static void svc_tcp_state_change(struct sock *sk)
 		wake_up_interruptible_all(wq);
 }
 
-static void svc_tcp_data_ready(struct sock *sk, int count)
+static void svc_tcp_data_ready(struct sock *sk)
 {
 	struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
 	wait_queue_head_t *wq = sk_sleep(sk);
@@ -842,8 +849,7 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	 * tell us anything.  For now just warn about unpriv connections.
 	 */
 	if (!svc_port_is_privileged(sin)) {
-		dprintk(KERN_WARNING
-			"%s: connect from unprivileged port: %s\n",
+		dprintk("%s: connect from unprivileged port: %s\n",
 			serv->sv_name,
 			__svc_print_addr(sin, buf, sizeof(buf)));
 	}
@@ -867,6 +873,10 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	}
 	svc_xprt_set_local(&newsvsk->sk_xprt, sin, slen);
 
+	if (sock_is_loopback(newsock->sk))
+		set_bit(XPT_LOCAL, &newsvsk->sk_xprt.xpt_flags);
+	else
+		clear_bit(XPT_LOCAL, &newsvsk->sk_xprt.xpt_flags);
 	if (serv->sv_stats)
 		serv->sv_stats->nettcpconn++;
 
@@ -1112,6 +1122,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 
 	rqstp->rq_xprt_ctxt   = NULL;
 	rqstp->rq_prot	      = IPPROTO_TCP;
+	rqstp->rq_local	      = !!test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags);
 
 	p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
 	calldir = p[1];
@@ -1234,6 +1245,7 @@ static struct svc_xprt_ops svc_tcp_bc_ops = {
 	.xpo_detach = svc_bc_tcp_sock_detach,
 	.xpo_free = svc_bc_sock_free,
 	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
+	.xpo_secure_port = svc_sock_secure_port,
 };
 
 static struct svc_xprt_class svc_tcp_bc_class = {
@@ -1272,6 +1284,7 @@ static struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
 	.xpo_has_wspace = svc_tcp_has_wspace,
 	.xpo_accept = svc_tcp_accept,
+	.xpo_secure_port = svc_sock_secure_port,
 };
 
 static struct svc_xprt_class svc_tcp_class = {
@@ -1397,6 +1410,22 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	return svsk;
 }
 
+bool svc_alien_sock(struct net *net, int fd)
+{
+	int err;
+	struct socket *sock = sockfd_lookup(fd, &err);
+	bool ret = false;
+
+	if (!sock)
+		goto out;
+	if (sock_net(sock->sk) != net)
+		ret = true;
+	sockfd_put(sock);
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(svc_alien_sock);
+
 /**
  * svc_addsock - add a listener socket to an RPC service
  * @serv: pointer to RPC service to which to add a new listener
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 1504bb11e4f..23fb4e75e24 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -462,6 +462,7 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
 	struct kvec *iov = buf->head;
 	int scratch_len = buf->buflen - buf->page_len - buf->tail[0].iov_len;
 
+	xdr_set_scratch_buffer(xdr, NULL, 0);
 	BUG_ON(scratch_len < 0);
 	xdr->buf = buf;
 	xdr->iov = iov;
@@ -482,6 +483,73 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
 EXPORT_SYMBOL_GPL(xdr_init_encode);
 
 /**
+ * xdr_commit_encode - Ensure all data is written to buffer
+ * @xdr: pointer to xdr_stream
+ *
+ * We handle encoding across page boundaries by giving the caller a
+ * temporary location to write to, then later copying the data into
+ * place; xdr_commit_encode does that copying.
+ *
+ * Normally the caller doesn't need to call this directly, as the
+ * following xdr_reserve_space will do it.  But an explicit call may be
+ * required at the end of encoding, or any other time when the xdr_buf
+ * data might be read.
+ */
+void xdr_commit_encode(struct xdr_stream *xdr)
+{
+	int shift = xdr->scratch.iov_len;
+	void *page;
+
+	if (shift == 0)
+		return;
+	page = page_address(*xdr->page_ptr);
+	memcpy(xdr->scratch.iov_base, page, shift);
+	memmove(page, page + shift, (void *)xdr->p - page);
+	xdr->scratch.iov_len = 0;
+}
+EXPORT_SYMBOL_GPL(xdr_commit_encode);
+
+__be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, size_t nbytes)
+{
+	static __be32 *p;
+	int space_left;
+	int frag1bytes, frag2bytes;
+
+	if (nbytes > PAGE_SIZE)
+		return NULL; /* Bigger buffers require special handling */
+	if (xdr->buf->len + nbytes > xdr->buf->buflen)
+		return NULL; /* Sorry, we're totally out of space */
+	frag1bytes = (xdr->end - xdr->p) << 2;
+	frag2bytes = nbytes - frag1bytes;
+	if (xdr->iov)
+		xdr->iov->iov_len += frag1bytes;
+	else
+		xdr->buf->page_len += frag1bytes;
+	xdr->page_ptr++;
+	xdr->iov = NULL;
+	/*
+	 * If the last encode didn't end exactly on a page boundary, the
+	 * next one will straddle boundaries.  Encode into the next
+	 * page, then copy it back later in xdr_commit_encode.  We use
+	 * the "scratch" iov to track any temporarily unused fragment of
+	 * space at the end of the previous buffer:
+	 */
+	xdr->scratch.iov_base = xdr->p;
+	xdr->scratch.iov_len = frag1bytes;
+	p = page_address(*xdr->page_ptr);
+	/*
+	 * Note this is where the next encode will start after we've
+	 * shifted this one back:
+	 */
+	xdr->p = (void *)p + frag2bytes;
+	space_left = xdr->buf->buflen - xdr->buf->len;
+	xdr->end = (void *)p + min_t(int, space_left, PAGE_SIZE);
+	xdr->buf->page_len += frag2bytes;
+	xdr->buf->len += nbytes;
+	return p;
+}
+
+/**
  * xdr_reserve_space - Reserve buffer space for sending
  * @xdr: pointer to xdr_stream
  * @nbytes: number of bytes to reserve
@@ -495,20 +563,122 @@ __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
 	__be32 *p = xdr->p;
 	__be32 *q;
 
+	xdr_commit_encode(xdr);
 	/* align nbytes on the next 32-bit boundary */
 	nbytes += 3;
 	nbytes &= ~3;
 	q = p + (nbytes >> 2);
 	if (unlikely(q > xdr->end || q < p))
-		return NULL;
+		return xdr_get_next_encode_buffer(xdr, nbytes);
 	xdr->p = q;
-	xdr->iov->iov_len += nbytes;
+	if (xdr->iov)
+		xdr->iov->iov_len += nbytes;
+	else
+		xdr->buf->page_len += nbytes;
 	xdr->buf->len += nbytes;
 	return p;
 }
 EXPORT_SYMBOL_GPL(xdr_reserve_space);
 
 /**
+ * xdr_truncate_encode - truncate an encode buffer
+ * @xdr: pointer to xdr_stream
+ * @len: new length of buffer
+ *
+ * Truncates the xdr stream, so that xdr->buf->len == len,
+ * and xdr->p points at offset len from the start of the buffer, and
+ * head, tail, and page lengths are adjusted to correspond.
+ *
+ * If this means moving xdr->p to a different buffer, we assume that
+ * that the end pointer should be set to the end of the current page,
+ * except in the case of the head buffer when we assume the head
+ * buffer's current length represents the end of the available buffer.
+ *
+ * This is *not* safe to use on a buffer that already has inlined page
+ * cache pages (as in a zero-copy server read reply), except for the
+ * simple case of truncating from one position in the tail to another.
+ *
+ */
+void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
+{
+	struct xdr_buf *buf = xdr->buf;
+	struct kvec *head = buf->head;
+	struct kvec *tail = buf->tail;
+	int fraglen;
+	int new, old;
+
+	if (len > buf->len) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+	xdr_commit_encode(xdr);
+
+	fraglen = min_t(int, buf->len - len, tail->iov_len);
+	tail->iov_len -= fraglen;
+	buf->len -= fraglen;
+	if (tail->iov_len && buf->len == len) {
+		xdr->p = tail->iov_base + tail->iov_len;
+		/* xdr->end, xdr->iov should be set already */
+		return;
+	}
+	WARN_ON_ONCE(fraglen);
+	fraglen = min_t(int, buf->len - len, buf->page_len);
+	buf->page_len -= fraglen;
+	buf->len -= fraglen;
+
+	new = buf->page_base + buf->page_len;
+	old = new + fraglen;
+	xdr->page_ptr -= (old >> PAGE_SHIFT) - (new >> PAGE_SHIFT);
+
+	if (buf->page_len && buf->len == len) {
+		xdr->p = page_address(*xdr->page_ptr);
+		xdr->end = (void *)xdr->p + PAGE_SIZE;
+		xdr->p = (void *)xdr->p + (new % PAGE_SIZE);
+		/* xdr->iov should already be NULL */
+		return;
+	}
+	if (fraglen) {
+		xdr->end = head->iov_base + head->iov_len;
+		xdr->page_ptr--;
+	}
+	/* (otherwise assume xdr->end is already set) */
+	head->iov_len = len;
+	buf->len = len;
+	xdr->p = head->iov_base + head->iov_len;
+	xdr->iov = buf->head;
+}
+EXPORT_SYMBOL(xdr_truncate_encode);
+
+/**
+ * xdr_restrict_buflen - decrease available buffer space
+ * @xdr: pointer to xdr_stream
+ * @newbuflen: new maximum number of bytes available
+ *
+ * Adjust our idea of how much space is available in the buffer.
+ * If we've already used too much space in the buffer, returns -1.
+ * If the available space is already smaller than newbuflen, returns 0
+ * and does nothing.  Otherwise, adjusts xdr->buf->buflen to newbuflen
+ * and ensures xdr->end is set at most offset newbuflen from the start
+ * of the buffer.
+ */
+int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen)
+{
+	struct xdr_buf *buf = xdr->buf;
+	int left_in_this_buf = (void *)xdr->end - (void *)xdr->p;
+	int end_offset = buf->len + left_in_this_buf;
+
+	if (newbuflen < 0 || newbuflen < buf->len)
+		return -1;
+	if (newbuflen > buf->buflen)
+		return 0;
+	if (newbuflen < end_offset)
+		xdr->end = (void *)xdr->end + newbuflen - end_offset;
+	buf->buflen = newbuflen;
+	return 0;
+}
+EXPORT_SYMBOL(xdr_restrict_buflen);
+
+/**
  * xdr_write_pages - Insert a list of pages into an XDR buffer for sending
  * @xdr: pointer to xdr_stream
  * @pages: list of pages
@@ -833,8 +1003,20 @@ xdr_buf_from_iov(struct kvec *iov, struct xdr_buf *buf)
 }
 EXPORT_SYMBOL_GPL(xdr_buf_from_iov);
 
-/* Sets subbuf to the portion of buf of length len beginning base bytes
- * from the start of buf. Returns -1 if base of length are out of bounds. */
+/**
+ * xdr_buf_subsegment - set subbuf to a portion of buf
+ * @buf: an xdr buffer
+ * @subbuf: the result buffer
+ * @base: beginning of range in bytes
+ * @len: length of range in bytes
+ *
+ * sets @subbuf to an xdr buffer representing the portion of @buf of
+ * length @len starting at offset @base.
+ *
+ * @buf and @subbuf may be pointers to the same struct xdr_buf.
+ *
+ * Returns -1 if base of length are out of bounds.
+ */
 int
 xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 			unsigned int base, unsigned int len)
@@ -847,9 +1029,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 		len -= subbuf->head[0].iov_len;
 		base = 0;
 	} else {
-		subbuf->head[0].iov_base = NULL;
-		subbuf->head[0].iov_len = 0;
 		base -= buf->head[0].iov_len;
+		subbuf->head[0].iov_len = 0;
 	}
 
 	if (base < buf->page_len) {
@@ -871,9 +1052,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 		len -= subbuf->tail[0].iov_len;
 		base = 0;
 	} else {
-		subbuf->tail[0].iov_base = NULL;
-		subbuf->tail[0].iov_len = 0;
 		base -= buf->tail[0].iov_len;
+		subbuf->tail[0].iov_len = 0;
 	}
 
 	if (base || len)
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 04199bc8416..c3b2b3369e5 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -71,24 +71,6 @@ static void	 xprt_destroy(struct rpc_xprt *xprt);
 static DEFINE_SPINLOCK(xprt_list_lock);
 static LIST_HEAD(xprt_list);
 
-/*
- * The transport code maintains an estimate on the maximum number of out-
- * standing RPC requests, using a smoothed version of the congestion
- * avoidance implemented in 44BSD. This is basically the Van Jacobson
- * congestion algorithm: If a retransmit occurs, the congestion window is
- * halved; otherwise, it is incremented by 1/cwnd when
- *
- *	-	a reply is received and
- *	-	a full number of requests are outstanding and
- *	-	the congestion window hasn't been updated recently.
- */
-#define RPC_CWNDSHIFT		(8U)
-#define RPC_CWNDSCALE		(1U << RPC_CWNDSHIFT)
-#define RPC_INITCWND		RPC_CWNDSCALE
-#define RPC_MAXCWND(xprt)	((xprt)->max_reqs << RPC_CWNDSHIFT)
-
-#define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)
-
 /**
  * xprt_register_transport - register a transport implementation
  * @transport: transport to register
@@ -230,9 +212,9 @@ static void xprt_clear_locked(struct rpc_xprt *xprt)
 {
 	xprt->snd_task = NULL;
 	if (!test_bit(XPRT_CLOSE_WAIT, &xprt->state)) {
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(XPRT_LOCKED, &xprt->state);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 	} else
 		queue_work(rpciod_workqueue, &xprt->task_cleanup);
 }
@@ -446,7 +428,15 @@ EXPORT_SYMBOL_GPL(xprt_release_rqst_cong);
  * @task: recently completed RPC request used to adjust window
  * @result: result code of completed RPC request
  *
- * We use a time-smoothed congestion estimator to avoid heavy oscillation.
+ * The transport code maintains an estimate on the maximum number of out-
+ * standing RPC requests, using a smoothed version of the congestion
+ * avoidance implemented in 44BSD. This is basically the Van Jacobson
+ * congestion algorithm: If a retransmit occurs, the congestion window is
+ * halved; otherwise, it is incremented by 1/cwnd when
+ *
+ *	-	a reply is received and
+ *	-	a full number of requests are outstanding and
+ *	-	the congestion window hasn't been updated recently.
  */
 void xprt_adjust_cwnd(struct rpc_xprt *xprt, struct rpc_task *task, int result)
 {
@@ -749,6 +739,11 @@ static void xprt_connect_status(struct rpc_task *task)
 	}
 
 	switch (task->tk_status) {
+	case -ECONNREFUSED:
+	case -ECONNRESET:
+	case -ECONNABORTED:
+	case -ENETUNREACH:
+	case -EHOSTUNREACH:
 	case -EAGAIN:
 		dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid);
 		break;
@@ -1188,7 +1183,7 @@ static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt)
 
 static inline void xprt_init_xid(struct rpc_xprt *xprt)
 {
-	xprt->xid = net_random();
+	xprt->xid = prandom_u32();
 }
 
 static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt)
@@ -1378,15 +1373,3 @@ void xprt_put(struct rpc_xprt *xprt)
 	if (atomic_dec_and_test(&xprt->count))
 		xprt_destroy(xprt);
 }
-
-/**
- * xprt_get - return a reference to an RPC transport.
- * @xprt: pointer to the transport
- *
- */
-struct rpc_xprt *xprt_get(struct rpc_xprt *xprt)
-{
-	if (atomic_inc_not_zero(&xprt->count))
-		return xprt;
-	return NULL;
-}
diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile
index 5a8f268bdd3..da5136fd569 100644
--- a/net/sunrpc/xprtrdma/Makefile
+++ b/net/sunrpc/xprtrdma/Makefile
@@ -1,8 +1,8 @@
-obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma.o
+obj-$(CONFIG_SUNRPC_XPRT_RDMA_CLIENT) += xprtrdma.o
 
 xprtrdma-y := transport.o rpc_rdma.o verbs.o
 
-obj-$(CONFIG_SUNRPC_XPRT_RDMA) += svcrdma.o
+obj-$(CONFIG_SUNRPC_XPRT_RDMA_SERVER) += svcrdma.o
 
 svcrdma-y := svc_rdma.o svc_rdma_transport.o \
 	svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index e03725bfe2b..693966d3f33 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -78,8 +78,7 @@ static const char transfertypes[][12] = {
  * elements. Segments are then coalesced when registered, if possible
  * within the selected memreg mode.
  *
- * Note, this routine is never called if the connection's memory
- * registration strategy is 0 (bounce buffers).
+ * Returns positive number of segments converted, or a negative errno.
  */
 
 static int
@@ -102,10 +101,17 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 	page_base = xdrbuf->page_base & ~PAGE_MASK;
 	p = 0;
 	while (len && n < nsegs) {
+		if (!ppages[p]) {
+			/* alloc the pagelist for receiving buffer */
+			ppages[p] = alloc_page(GFP_ATOMIC);
+			if (!ppages[p])
+				return -ENOMEM;
+		}
 		seg[n].mr_page = ppages[p];
 		seg[n].mr_offset = (void *)(unsigned long) page_base;
 		seg[n].mr_len = min_t(u32, PAGE_SIZE - page_base, len);
-		BUG_ON(seg[n].mr_len > PAGE_SIZE);
+		if (seg[n].mr_len > PAGE_SIZE)
+			return -EIO;
 		len -= seg[n].mr_len;
 		++n;
 		++p;
@@ -114,7 +120,7 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 
 	/* Message overflows the seg array */
 	if (len && n == nsegs)
-		return 0;
+		return -EIO;
 
 	if (xdrbuf->tail[0].iov_len) {
 		/* the rpcrdma protocol allows us to omit any trailing
@@ -123,7 +129,7 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 			return n;
 		if (n == nsegs)
 			/* Tail remains, but we're out of segments */
-			return 0;
+			return -EIO;
 		seg[n].mr_page = NULL;
 		seg[n].mr_offset = xdrbuf->tail[0].iov_base;
 		seg[n].mr_len = xdrbuf->tail[0].iov_len;
@@ -164,15 +170,17 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
  *  Reply chunk (a counted array):
  *   N elements:
  *    1 - N - HLOO - HLOO - ... - HLOO
+ *
+ * Returns positive RPC/RDMA header size, or negative errno.
  */
 
-static unsigned int
+static ssize_t
 rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 		struct rpcrdma_msg *headerp, enum rpcrdma_chunktype type)
 {
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt);
-	int nsegs, nchunks = 0;
+	int n, nsegs, nchunks = 0;
 	unsigned int pos;
 	struct rpcrdma_mr_seg *seg = req->rl_segments;
 	struct rpcrdma_read_chunk *cur_rchunk = NULL;
@@ -198,12 +206,11 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 		pos = target->head[0].iov_len;
 
 	nsegs = rpcrdma_convert_iovs(target, pos, type, seg, RPCRDMA_MAX_SEGS);
-	if (nsegs == 0)
-		return 0;
+	if (nsegs < 0)
+		return nsegs;
 
 	do {
-		/* bind/register the memory, then build chunk from result. */
-		int n = rpcrdma_register_external(seg, nsegs,
+		n = rpcrdma_register_external(seg, nsegs,
 						cur_wchunk != NULL, r_xprt);
 		if (n <= 0)
 			goto out;
@@ -248,10 +255,6 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	/* success. all failures return above */
 	req->rl_nchunks = nchunks;
 
-	BUG_ON(nchunks == 0);
-	BUG_ON((r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
-	       && (nchunks > 3));
-
 	/*
 	 * finish off header. If write, marshal discrim and nchunks.
 	 */
@@ -278,8 +281,8 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 out:
 	for (pos = 0; nchunks--;)
 		pos += rpcrdma_deregister_external(
-				&req->rl_segments[pos], r_xprt, NULL);
-	return 0;
+				&req->rl_segments[pos], r_xprt);
+	return n;
 }
 
 /*
@@ -361,6 +364,8 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad)
  *  [1] -- the RPC header/data, marshaled by RPC and the NFS protocol.
  *  [2] -- optional padding.
  *  [3] -- if padded, header only in [1] and data here.
+ *
+ * Returns zero on success, otherwise a negative errno.
  */
 
 int
@@ -370,7 +375,8 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	char *base;
-	size_t hdrlen, rpclen, padlen;
+	size_t rpclen, padlen;
+	ssize_t hdrlen;
 	enum rpcrdma_chunktype rtype, wtype;
 	struct rpcrdma_msg *headerp;
 
@@ -441,14 +447,10 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	/* The following simplification is not true forever */
 	if (rtype != rpcrdma_noch && wtype == rpcrdma_replych)
 		wtype = rpcrdma_noch;
-	BUG_ON(rtype != rpcrdma_noch && wtype != rpcrdma_noch);
-
-	if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_BOUNCEBUFFERS &&
-	    (rtype != rpcrdma_noch || wtype != rpcrdma_noch)) {
-		/* forced to "pure inline"? */
-		dprintk("RPC:       %s: too much data (%d/%d) for inline\n",
-			__func__, rqst->rq_rcv_buf.len, rqst->rq_snd_buf.len);
-		return -1;
+	if (rtype != rpcrdma_noch && wtype != rpcrdma_noch) {
+		dprintk("RPC:       %s: cannot marshal multiple chunk lists\n",
+			__func__);
+		return -EIO;
 	}
 
 	hdrlen = 28; /*sizeof *headerp;*/
@@ -474,8 +476,11 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 			headerp->rm_body.rm_padded.rm_pempty[1] = xdr_zero;
 			headerp->rm_body.rm_padded.rm_pempty[2] = xdr_zero;
 			hdrlen += 2 * sizeof(u32); /* extra words in padhdr */
-			BUG_ON(wtype != rpcrdma_noch);
-
+			if (wtype != rpcrdma_noch) {
+				dprintk("RPC:       %s: invalid chunk list\n",
+					__func__);
+				return -EIO;
+			}
 		} else {
 			headerp->rm_body.rm_nochunks.rm_empty[0] = xdr_zero;
 			headerp->rm_body.rm_nochunks.rm_empty[1] = xdr_zero;
@@ -492,8 +497,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 			 * on receive. Therefore, we request a reply chunk
 			 * for non-writes wherever feasible and efficient.
 			 */
-			if (wtype == rpcrdma_noch &&
-			    r_xprt->rx_ia.ri_memreg_strategy > RPCRDMA_REGISTER)
+			if (wtype == rpcrdma_noch)
 				wtype = rpcrdma_replych;
 		}
 	}
@@ -511,9 +515,8 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 		hdrlen = rpcrdma_create_chunks(rqst,
 					&rqst->rq_rcv_buf, headerp, wtype);
 	}
-
-	if (hdrlen == 0)
-		return -1;
+	if (hdrlen < 0)
+		return hdrlen;
 
 	dprintk("RPC:       %s: %s: hdrlen %zd rpclen %zd padlen %zd"
 		" headerp 0x%p base 0x%p lkey 0x%x\n",
@@ -649,9 +652,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
 				break;
 			page_base = 0;
 		}
-		rqst->rq_rcv_buf.page_len = olen - copy_len;
-	} else
-		rqst->rq_rcv_buf.page_len = 0;
+	}
 
 	if (copy_len && rqst->rq_rcv_buf.tail[0].iov_len) {
 		curlen = copy_len;
@@ -682,15 +683,11 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
 	rqst->rq_private_buf = rqst->rq_rcv_buf;
 }
 
-/*
- * This function is called when an async event is posted to
- * the connection which changes the connection state. All it
- * does at this point is mark the connection up/down, the rpc
- * timers do the rest.
- */
 void
-rpcrdma_conn_func(struct rpcrdma_ep *ep)
+rpcrdma_connect_worker(struct work_struct *work)
 {
+	struct rpcrdma_ep *ep =
+		container_of(work, struct rpcrdma_ep, rep_connect_worker.work);
 	struct rpc_xprt *xprt = ep->rep_xprt;
 
 	spin_lock_bh(&xprt->transport_lock);
@@ -707,13 +704,15 @@ rpcrdma_conn_func(struct rpcrdma_ep *ep)
 }
 
 /*
- * This function is called when memory window unbind which we are waiting
- * for completes. Just use rr_func (zeroed by upcall) to signal completion.
+ * This function is called when an async event is posted to
+ * the connection which changes the connection state. All it
+ * does at this point is mark the connection up/down, the rpc
+ * timers do the rest.
  */
-static void
-rpcrdma_unbind_func(struct rpcrdma_rep *rep)
+void
+rpcrdma_conn_func(struct rpcrdma_ep *ep)
 {
-	wake_up(&rep->rr_unbind);
+	schedule_delayed_work(&ep->rep_connect_worker, 0);
 }
 
 /*
@@ -730,7 +729,8 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	struct rpc_xprt *xprt = rep->rr_xprt;
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	__be32 *iptr;
-	int i, rdmalen, status;
+	int rdmalen, status;
+	unsigned long cwnd;
 
 	/* Check status. If bad, signal disconnect and return rep to pool */
 	if (rep->rr_len == ~0U) {
@@ -785,6 +785,7 @@ repost:
 
 	/* from here on, the reply is no longer an orphan */
 	req->rl_reply = rep;
+	xprt->reestablish_timeout = 0;
 
 	/* check for expected message types */
 	/* The order of some of these tests is important. */
@@ -859,26 +860,10 @@ badheader:
 		break;
 	}
 
-	/* If using mw bind, start the deregister process now. */
-	/* (Note: if mr_free(), cannot perform it here, in tasklet context) */
-	if (req->rl_nchunks) switch (r_xprt->rx_ia.ri_memreg_strategy) {
-	case RPCRDMA_MEMWINDOWS:
-		for (i = 0; req->rl_nchunks-- > 1;)
-			i += rpcrdma_deregister_external(
-				&req->rl_segments[i], r_xprt, NULL);
-		/* Optionally wait (not here) for unbinds to complete */
-		rep->rr_func = rpcrdma_unbind_func;
-		(void) rpcrdma_deregister_external(&req->rl_segments[i],
-						   r_xprt, rep);
-		break;
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-		for (i = 0; req->rl_nchunks--;)
-			i += rpcrdma_deregister_external(&req->rl_segments[i],
-							 r_xprt, NULL);
-		break;
-	default:
-		break;
-	}
+	cwnd = xprt->cwnd;
+	xprt->cwnd = atomic_read(&r_xprt->rx_buf.rb_credits) << RPC_CWNDSHIFT;
+	if (xprt->cwnd > cwnd)
+		xprt_release_rqst_cong(rqst->rq_task);
 
 	dprintk("RPC:       %s: xprt_complete_rqst(0x%p, 0x%p, %d)\n",
 			__func__, xprt, rqst, status);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 0ce75524ed2..8f92a61ee2d 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved.
  * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -69,7 +70,8 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 
 	/* Set up the XDR head */
 	rqstp->rq_arg.head[0].iov_base = page_address(page);
-	rqstp->rq_arg.head[0].iov_len = min(byte_count, ctxt->sge[0].length);
+	rqstp->rq_arg.head[0].iov_len =
+		min_t(size_t, byte_count, ctxt->sge[0].length);
 	rqstp->rq_arg.len = byte_count;
 	rqstp->rq_arg.buflen = byte_count;
 
@@ -85,11 +87,12 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 		page = ctxt->pages[sge_no];
 		put_page(rqstp->rq_pages[sge_no]);
 		rqstp->rq_pages[sge_no] = page;
-		bc -= min(bc, ctxt->sge[sge_no].length);
+		bc -= min_t(u32, bc, ctxt->sge[sge_no].length);
 		rqstp->rq_arg.buflen += ctxt->sge[sge_no].length;
 		sge_no++;
 	}
 	rqstp->rq_respages = &rqstp->rq_pages[sge_no];
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
 	/* We should never run out of SGE because the limit is defined to
 	 * support the max allowed RPC data length
@@ -112,289 +115,265 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	rqstp->rq_arg.tail[0].iov_len = 0;
 }
 
-/* Encode a read-chunk-list as an array of IB SGE
- *
- * Assumptions:
- * - chunk[0]->position points to pages[0] at an offset of 0
- * - pages[] is not physically or virtually contiguous and consists of
- *   PAGE_SIZE elements.
- *
- * Output:
- * - sge array pointing into pages[] array.
- * - chunk_sge array specifying sge index and count for each
- *   chunk in the read list
- *
- */
-static int map_read_chunks(struct svcxprt_rdma *xprt,
-			   struct svc_rqst *rqstp,
-			   struct svc_rdma_op_ctxt *head,
-			   struct rpcrdma_msg *rmsgp,
-			   struct svc_rdma_req_map *rpl_map,
-			   struct svc_rdma_req_map *chl_map,
-			   int ch_count,
-			   int byte_count)
+static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count)
 {
-	int sge_no;
-	int sge_bytes;
-	int page_off;
-	int page_no;
-	int ch_bytes;
-	int ch_no;
-	struct rpcrdma_read_chunk *ch;
+	if (rdma_node_get_transport(xprt->sc_cm_id->device->node_type) ==
+	     RDMA_TRANSPORT_IWARP)
+		return 1;
+	else
+		return min_t(int, sge_count, xprt->sc_max_sge);
+}
 
-	sge_no = 0;
-	page_no = 0;
-	page_off = 0;
-	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-	ch_no = 0;
-	ch_bytes = ntohl(ch->rc_target.rs_length);
-	head->arg.head[0] = rqstp->rq_arg.head[0];
-	head->arg.tail[0] = rqstp->rq_arg.tail[0];
-	head->arg.pages = &head->pages[head->count];
-	head->hdr_count = head->count; /* save count of hdr pages */
-	head->arg.page_base = 0;
-	head->arg.page_len = ch_bytes;
-	head->arg.len = rqstp->rq_arg.len + ch_bytes;
-	head->arg.buflen = rqstp->rq_arg.buflen + ch_bytes;
-	head->count++;
-	chl_map->ch[0].start = 0;
-	while (byte_count) {
-		rpl_map->sge[sge_no].iov_base =
-			page_address(rqstp->rq_arg.pages[page_no]) + page_off;
-		sge_bytes = min_t(int, PAGE_SIZE-page_off, ch_bytes);
-		rpl_map->sge[sge_no].iov_len = sge_bytes;
-		/*
-		 * Don't bump head->count here because the same page
-		 * may be used by multiple SGE.
-		 */
-		head->arg.pages[page_no] = rqstp->rq_arg.pages[page_no];
-		rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1];
+typedef int (*rdma_reader_fn)(struct svcxprt_rdma *xprt,
+			      struct svc_rqst *rqstp,
+			      struct svc_rdma_op_ctxt *head,
+			      int *page_no,
+			      u32 *page_offset,
+			      u32 rs_handle,
+			      u32 rs_length,
+			      u64 rs_offset,
+			      int last);
+
+/* Issue an RDMA_READ using the local lkey to map the data sink */
+static int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
+			       struct svc_rqst *rqstp,
+			       struct svc_rdma_op_ctxt *head,
+			       int *page_no,
+			       u32 *page_offset,
+			       u32 rs_handle,
+			       u32 rs_length,
+			       u64 rs_offset,
+			       int last)
+{
+	struct ib_send_wr read_wr;
+	int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
+	struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt);
+	int ret, read, pno;
+	u32 pg_off = *page_offset;
+	u32 pg_no = *page_no;
 
-		byte_count -= sge_bytes;
-		ch_bytes -= sge_bytes;
-		sge_no++;
-		/*
-		 * If all bytes for this chunk have been mapped to an
-		 * SGE, move to the next SGE
-		 */
-		if (ch_bytes == 0) {
-			chl_map->ch[ch_no].count =
-				sge_no - chl_map->ch[ch_no].start;
-			ch_no++;
-			ch++;
-			chl_map->ch[ch_no].start = sge_no;
-			ch_bytes = ntohl(ch->rc_target.rs_length);
-			/* If bytes remaining account for next chunk */
-			if (byte_count) {
-				head->arg.page_len += ch_bytes;
-				head->arg.len += ch_bytes;
-				head->arg.buflen += ch_bytes;
-			}
+	ctxt->direction = DMA_FROM_DEVICE;
+	ctxt->read_hdr = head;
+	pages_needed =
+		min_t(int, pages_needed, rdma_read_max_sge(xprt, pages_needed));
+	read = min_t(int, pages_needed << PAGE_SHIFT, rs_length);
+
+	for (pno = 0; pno < pages_needed; pno++) {
+		int len = min_t(int, rs_length, PAGE_SIZE - pg_off);
+
+		head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no];
+		head->arg.page_len += len;
+		head->arg.len += len;
+		if (!pg_off)
+			head->count++;
+		rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1];
+		rqstp->rq_next_page = rqstp->rq_respages + 1;
+		ctxt->sge[pno].addr =
+			ib_dma_map_page(xprt->sc_cm_id->device,
+					head->arg.pages[pg_no], pg_off,
+					PAGE_SIZE - pg_off,
+					DMA_FROM_DEVICE);
+		ret = ib_dma_mapping_error(xprt->sc_cm_id->device,
+					   ctxt->sge[pno].addr);
+		if (ret)
+			goto err;
+		atomic_inc(&xprt->sc_dma_used);
+
+		/* The lkey here is either a local dma lkey or a dma_mr lkey */
+		ctxt->sge[pno].lkey = xprt->sc_dma_lkey;
+		ctxt->sge[pno].length = len;
+		ctxt->count++;
+
+		/* adjust offset and wrap to next page if needed */
+		pg_off += len;
+		if (pg_off == PAGE_SIZE) {
+			pg_off = 0;
+			pg_no++;
 		}
-		/*
-		 * If this SGE consumed all of the page, move to the
-		 * next page
-		 */
-		if ((sge_bytes + page_off) == PAGE_SIZE) {
-			page_no++;
-			page_off = 0;
-			/*
-			 * If there are still bytes left to map, bump
-			 * the page count
-			 */
-			if (byte_count)
-				head->count++;
-		} else
-			page_off += sge_bytes;
+		rs_length -= len;
 	}
-	BUG_ON(byte_count != 0);
-	return sge_no;
+
+	if (last && rs_length == 0)
+		set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
+	else
+		clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
+
+	memset(&read_wr, 0, sizeof(read_wr));
+	read_wr.wr_id = (unsigned long)ctxt;
+	read_wr.opcode = IB_WR_RDMA_READ;
+	ctxt->wr_op = read_wr.opcode;
+	read_wr.send_flags = IB_SEND_SIGNALED;
+	read_wr.wr.rdma.rkey = rs_handle;
+	read_wr.wr.rdma.remote_addr = rs_offset;
+	read_wr.sg_list = ctxt->sge;
+	read_wr.num_sge = pages_needed;
+
+	ret = svc_rdma_send(xprt, &read_wr);
+	if (ret) {
+		pr_err("svcrdma: Error %d posting RDMA_READ\n", ret);
+		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+		goto err;
+	}
+
+	/* return current location in page array */
+	*page_no = pg_no;
+	*page_offset = pg_off;
+	ret = read;
+	atomic_inc(&rdma_stat_read);
+	return ret;
+ err:
+	svc_rdma_unmap_dma(ctxt);
+	svc_rdma_put_context(ctxt, 0);
+	return ret;
 }
 
-/* Map a read-chunk-list to an XDR and fast register the page-list.
- *
- * Assumptions:
- * - chunk[0]	position points to pages[0] at an offset of 0
- * - pages[]	will be made physically contiguous by creating a one-off memory
- *		region using the fastreg verb.
- * - byte_count is # of bytes in read-chunk-list
- * - ch_count	is # of chunks in read-chunk-list
- *
- * Output:
- * - sge array pointing into pages[] array.
- * - chunk_sge array specifying sge index and count for each
- *   chunk in the read list
- */
-static int fast_reg_read_chunks(struct svcxprt_rdma *xprt,
+/* Issue an RDMA_READ using an FRMR to map the data sink */
+static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 				struct svc_rqst *rqstp,
 				struct svc_rdma_op_ctxt *head,
-				struct rpcrdma_msg *rmsgp,
-				struct svc_rdma_req_map *rpl_map,
-				struct svc_rdma_req_map *chl_map,
-				int ch_count,
-				int byte_count)
+				int *page_no,
+				u32 *page_offset,
+				u32 rs_handle,
+				u32 rs_length,
+				u64 rs_offset,
+				int last)
 {
-	int page_no;
-	int ch_no;
-	u32 offset;
-	struct rpcrdma_read_chunk *ch;
-	struct svc_rdma_fastreg_mr *frmr;
-	int ret = 0;
+	struct ib_send_wr read_wr;
+	struct ib_send_wr inv_wr;
+	struct ib_send_wr fastreg_wr;
+	u8 key;
+	int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
+	struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt);
+	struct svc_rdma_fastreg_mr *frmr = svc_rdma_get_frmr(xprt);
+	int ret, read, pno;
+	u32 pg_off = *page_offset;
+	u32 pg_no = *page_no;
 
-	frmr = svc_rdma_get_frmr(xprt);
 	if (IS_ERR(frmr))
 		return -ENOMEM;
 
-	head->frmr = frmr;
-	head->arg.head[0] = rqstp->rq_arg.head[0];
-	head->arg.tail[0] = rqstp->rq_arg.tail[0];
-	head->arg.pages = &head->pages[head->count];
-	head->hdr_count = head->count; /* save count of hdr pages */
-	head->arg.page_base = 0;
-	head->arg.page_len = byte_count;
-	head->arg.len = rqstp->rq_arg.len + byte_count;
-	head->arg.buflen = rqstp->rq_arg.buflen + byte_count;
+	ctxt->direction = DMA_FROM_DEVICE;
+	ctxt->frmr = frmr;
+	pages_needed = min_t(int, pages_needed, xprt->sc_frmr_pg_list_len);
+	read = min_t(int, pages_needed << PAGE_SHIFT, rs_length);
 
-	/* Fast register the page list */
-	frmr->kva = page_address(rqstp->rq_arg.pages[0]);
+	frmr->kva = page_address(rqstp->rq_arg.pages[pg_no]);
 	frmr->direction = DMA_FROM_DEVICE;
 	frmr->access_flags = (IB_ACCESS_LOCAL_WRITE|IB_ACCESS_REMOTE_WRITE);
-	frmr->map_len = byte_count;
-	frmr->page_list_len = PAGE_ALIGN(byte_count) >> PAGE_SHIFT;
-	for (page_no = 0; page_no < frmr->page_list_len; page_no++) {
-		frmr->page_list->page_list[page_no] =
+	frmr->map_len = pages_needed << PAGE_SHIFT;
+	frmr->page_list_len = pages_needed;
+
+	for (pno = 0; pno < pages_needed; pno++) {
+		int len = min_t(int, rs_length, PAGE_SIZE - pg_off);
+
+		head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no];
+		head->arg.page_len += len;
+		head->arg.len += len;
+		if (!pg_off)
+			head->count++;
+		rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1];
+		rqstp->rq_next_page = rqstp->rq_respages + 1;
+		frmr->page_list->page_list[pno] =
 			ib_dma_map_page(xprt->sc_cm_id->device,
-					rqstp->rq_arg.pages[page_no], 0,
+					head->arg.pages[pg_no], 0,
 					PAGE_SIZE, DMA_FROM_DEVICE);
-		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-					 frmr->page_list->page_list[page_no]))
-			goto fatal_err;
+		ret = ib_dma_mapping_error(xprt->sc_cm_id->device,
+					   frmr->page_list->page_list[pno]);
+		if (ret)
+			goto err;
 		atomic_inc(&xprt->sc_dma_used);
-		head->arg.pages[page_no] = rqstp->rq_arg.pages[page_no];
-	}
-	head->count += page_no;
 
-	/* rq_respages points one past arg pages */
-	rqstp->rq_respages = &rqstp->rq_arg.pages[page_no];
-
-	/* Create the reply and chunk maps */
-	offset = 0;
-	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-	for (ch_no = 0; ch_no < ch_count; ch_no++) {
-		int len = ntohl(ch->rc_target.rs_length);
-		rpl_map->sge[ch_no].iov_base = frmr->kva + offset;
-		rpl_map->sge[ch_no].iov_len = len;
-		chl_map->ch[ch_no].count = 1;
-		chl_map->ch[ch_no].start = ch_no;
-		offset += len;
-		ch++;
+		/* adjust offset and wrap to next page if needed */
+		pg_off += len;
+		if (pg_off == PAGE_SIZE) {
+			pg_off = 0;
+			pg_no++;
+		}
+		rs_length -= len;
 	}
 
-	ret = svc_rdma_fastreg(xprt, frmr);
-	if (ret)
-		goto fatal_err;
-
-	return ch_no;
-
- fatal_err:
-	printk("svcrdma: error fast registering xdr for xprt %p", xprt);
-	svc_rdma_put_frmr(xprt, frmr);
-	return -EIO;
-}
-
-static int rdma_set_ctxt_sge(struct svcxprt_rdma *xprt,
-			     struct svc_rdma_op_ctxt *ctxt,
-			     struct svc_rdma_fastreg_mr *frmr,
-			     struct kvec *vec,
-			     u64 *sgl_offset,
-			     int count)
-{
-	int i;
-	unsigned long off;
+	if (last && rs_length == 0)
+		set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
+	else
+		clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
 
-	ctxt->count = count;
-	ctxt->direction = DMA_FROM_DEVICE;
-	for (i = 0; i < count; i++) {
-		ctxt->sge[i].length = 0; /* in case map fails */
-		if (!frmr) {
-			BUG_ON(!virt_to_page(vec[i].iov_base));
-			off = (unsigned long)vec[i].iov_base & ~PAGE_MASK;
-			ctxt->sge[i].addr =
-				ib_dma_map_page(xprt->sc_cm_id->device,
-						virt_to_page(vec[i].iov_base),
-						off,
-						vec[i].iov_len,
-						DMA_FROM_DEVICE);
-			if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-						 ctxt->sge[i].addr))
-				return -EINVAL;
-			ctxt->sge[i].lkey = xprt->sc_dma_lkey;
-			atomic_inc(&xprt->sc_dma_used);
-		} else {
-			ctxt->sge[i].addr = (unsigned long)vec[i].iov_base;
-			ctxt->sge[i].lkey = frmr->mr->lkey;
-		}
-		ctxt->sge[i].length = vec[i].iov_len;
-		*sgl_offset = *sgl_offset + vec[i].iov_len;
+	/* Bump the key */
+	key = (u8)(frmr->mr->lkey & 0x000000FF);
+	ib_update_fast_reg_key(frmr->mr, ++key);
+
+	ctxt->sge[0].addr = (unsigned long)frmr->kva + *page_offset;
+	ctxt->sge[0].lkey = frmr->mr->lkey;
+	ctxt->sge[0].length = read;
+	ctxt->count = 1;
+	ctxt->read_hdr = head;
+
+	/* Prepare FASTREG WR */
+	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
+	fastreg_wr.opcode = IB_WR_FAST_REG_MR;
+	fastreg_wr.send_flags = IB_SEND_SIGNALED;
+	fastreg_wr.wr.fast_reg.iova_start = (unsigned long)frmr->kva;
+	fastreg_wr.wr.fast_reg.page_list = frmr->page_list;
+	fastreg_wr.wr.fast_reg.page_list_len = frmr->page_list_len;
+	fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
+	fastreg_wr.wr.fast_reg.length = frmr->map_len;
+	fastreg_wr.wr.fast_reg.access_flags = frmr->access_flags;
+	fastreg_wr.wr.fast_reg.rkey = frmr->mr->lkey;
+	fastreg_wr.next = &read_wr;
+
+	/* Prepare RDMA_READ */
+	memset(&read_wr, 0, sizeof(read_wr));
+	read_wr.send_flags = IB_SEND_SIGNALED;
+	read_wr.wr.rdma.rkey = rs_handle;
+	read_wr.wr.rdma.remote_addr = rs_offset;
+	read_wr.sg_list = ctxt->sge;
+	read_wr.num_sge = 1;
+	if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_READ_W_INV) {
+		read_wr.opcode = IB_WR_RDMA_READ_WITH_INV;
+		read_wr.wr_id = (unsigned long)ctxt;
+		read_wr.ex.invalidate_rkey = ctxt->frmr->mr->lkey;
+	} else {
+		read_wr.opcode = IB_WR_RDMA_READ;
+		read_wr.next = &inv_wr;
+		/* Prepare invalidate */
+		memset(&inv_wr, 0, sizeof(inv_wr));
+		inv_wr.wr_id = (unsigned long)ctxt;
+		inv_wr.opcode = IB_WR_LOCAL_INV;
+		inv_wr.send_flags = IB_SEND_SIGNALED | IB_SEND_FENCE;
+		inv_wr.ex.invalidate_rkey = frmr->mr->lkey;
+	}
+	ctxt->wr_op = read_wr.opcode;
+
+	/* Post the chain */
+	ret = svc_rdma_send(xprt, &fastreg_wr);
+	if (ret) {
+		pr_err("svcrdma: Error %d posting RDMA_READ\n", ret);
+		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+		goto err;
 	}
-	return 0;
-}
 
-static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count)
-{
-	if ((rdma_node_get_transport(xprt->sc_cm_id->device->node_type) ==
-	     RDMA_TRANSPORT_IWARP) &&
-	    sge_count > 1)
-		return 1;
-	else
-		return min_t(int, sge_count, xprt->sc_max_sge);
+	/* return current location in page array */
+	*page_no = pg_no;
+	*page_offset = pg_off;
+	ret = read;
+	atomic_inc(&rdma_stat_read);
+	return ret;
+ err:
+	svc_rdma_unmap_dma(ctxt);
+	svc_rdma_put_context(ctxt, 0);
+	svc_rdma_put_frmr(xprt, frmr);
+	return ret;
 }
 
-/*
- * Use RDMA_READ to read data from the advertised client buffer into the
- * XDR stream starting at rq_arg.head[0].iov_base.
- * Each chunk in the array
- * contains the following fields:
- * discrim      - '1', This isn't used for data placement
- * position     - The xdr stream offset (the same for every chunk)
- * handle       - RMR for client memory region
- * length       - data transfer length
- * offset       - 64 bit tagged offset in remote memory region
- *
- * On our side, we need to read into a pagelist. The first page immediately
- * follows the RPC header.
- *
- * This function returns:
- * 0 - No error and no read-list found.
- *
- * 1 - Successful read-list processing. The data is not yet in
- * the pagelist and therefore the RPC request must be deferred. The
- * I/O completion will enqueue the transport again and
- * svc_rdma_recvfrom will complete the request.
- *
- * <0 - Error processing/posting read-list.
- *
- * NOTE: The ctxt must not be touched after the last WR has been posted
- * because the I/O completion processing may occur on another
- * processor and free / modify the context. Ne touche pas!
- */
-static int rdma_read_xdr(struct svcxprt_rdma *xprt,
-			 struct rpcrdma_msg *rmsgp,
-			 struct svc_rqst *rqstp,
-			 struct svc_rdma_op_ctxt *hdr_ctxt)
+static int rdma_read_chunks(struct svcxprt_rdma *xprt,
+			    struct rpcrdma_msg *rmsgp,
+			    struct svc_rqst *rqstp,
+			    struct svc_rdma_op_ctxt *head)
 {
-	struct ib_send_wr read_wr;
-	struct ib_send_wr inv_wr;
-	int err = 0;
-	int ch_no;
-	int ch_count;
-	int byte_count;
-	int sge_count;
-	u64 sgl_offset;
+	int page_no, ch_count, ret;
 	struct rpcrdma_read_chunk *ch;
-	struct svc_rdma_op_ctxt *ctxt = NULL;
-	struct svc_rdma_req_map *rpl_map;
-	struct svc_rdma_req_map *chl_map;
+	u32 page_offset, byte_count;
+	u64 rs_offset;
+	rdma_reader_fn reader;
 
 	/* If no read list is present, return 0 */
 	ch = svc_rdma_get_read_chunk(rmsgp);
@@ -405,129 +384,55 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt,
 	if (ch_count > RPCSVC_MAXPAGES)
 		return -EINVAL;
 
-	/* Allocate temporary reply and chunk maps */
-	rpl_map = svc_rdma_get_req_map();
-	chl_map = svc_rdma_get_req_map();
+	/* The request is completed when the RDMA_READs complete. The
+	 * head context keeps all the pages that comprise the
+	 * request.
+	 */
+	head->arg.head[0] = rqstp->rq_arg.head[0];
+	head->arg.tail[0] = rqstp->rq_arg.tail[0];
+	head->arg.pages = &head->pages[head->count];
+	head->hdr_count = head->count;
+	head->arg.page_base = 0;
+	head->arg.page_len = 0;
+	head->arg.len = rqstp->rq_arg.len;
+	head->arg.buflen = rqstp->rq_arg.buflen;
 
-	if (!xprt->sc_frmr_pg_list_len)
-		sge_count = map_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp,
-					    rpl_map, chl_map, ch_count,
-					    byte_count);
+	/* Use FRMR if supported */
+	if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)
+		reader = rdma_read_chunk_frmr;
 	else
-		sge_count = fast_reg_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp,
-						 rpl_map, chl_map, ch_count,
-						 byte_count);
-	if (sge_count < 0) {
-		err = -EIO;
-		goto out;
-	}
-
-	sgl_offset = 0;
-	ch_no = 0;
+		reader = rdma_read_chunk_lcl;
 
+	page_no = 0; page_offset = 0;
 	for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-	     ch->rc_discrim != 0; ch++, ch_no++) {
-		u64 rs_offset;
-next_sge:
-		ctxt = svc_rdma_get_context(xprt);
-		ctxt->direction = DMA_FROM_DEVICE;
-		ctxt->frmr = hdr_ctxt->frmr;
-		ctxt->read_hdr = NULL;
-		clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
-		clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
+	     ch->rc_discrim != 0; ch++) {
 
-		/* Prepare READ WR */
-		memset(&read_wr, 0, sizeof read_wr);
-		read_wr.wr_id = (unsigned long)ctxt;
-		read_wr.opcode = IB_WR_RDMA_READ;
-		ctxt->wr_op = read_wr.opcode;
-		read_wr.send_flags = IB_SEND_SIGNALED;
-		read_wr.wr.rdma.rkey = ntohl(ch->rc_target.rs_handle);
 		xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
 				 &rs_offset);
-		read_wr.wr.rdma.remote_addr = rs_offset + sgl_offset;
-		read_wr.sg_list = ctxt->sge;
-		read_wr.num_sge =
-			rdma_read_max_sge(xprt, chl_map->ch[ch_no].count);
-		err = rdma_set_ctxt_sge(xprt, ctxt, hdr_ctxt->frmr,
-					&rpl_map->sge[chl_map->ch[ch_no].start],
-					&sgl_offset,
-					read_wr.num_sge);
-		if (err) {
-			svc_rdma_unmap_dma(ctxt);
-			svc_rdma_put_context(ctxt, 0);
-			goto out;
-		}
-		if (((ch+1)->rc_discrim == 0) &&
-		    (read_wr.num_sge == chl_map->ch[ch_no].count)) {
-			/*
-			 * Mark the last RDMA_READ with a bit to
-			 * indicate all RPC data has been fetched from
-			 * the client and the RPC needs to be enqueued.
-			 */
-			set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
-			if (hdr_ctxt->frmr) {
-				set_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
-				/*
-				 * Invalidate the local MR used to map the data
-				 * sink.
-				 */
-				if (xprt->sc_dev_caps &
-				    SVCRDMA_DEVCAP_READ_W_INV) {
-					read_wr.opcode =
-						IB_WR_RDMA_READ_WITH_INV;
-					ctxt->wr_op = read_wr.opcode;
-					read_wr.ex.invalidate_rkey =
-						ctxt->frmr->mr->lkey;
-				} else {
-					/* Prepare INVALIDATE WR */
-					memset(&inv_wr, 0, sizeof inv_wr);
-					inv_wr.opcode = IB_WR_LOCAL_INV;
-					inv_wr.send_flags = IB_SEND_SIGNALED;
-					inv_wr.ex.invalidate_rkey =
-						hdr_ctxt->frmr->mr->lkey;
-					read_wr.next = &inv_wr;
-				}
-			}
-			ctxt->read_hdr = hdr_ctxt;
+		byte_count = ntohl(ch->rc_target.rs_length);
+
+		while (byte_count > 0) {
+			ret = reader(xprt, rqstp, head,
+				     &page_no, &page_offset,
+				     ntohl(ch->rc_target.rs_handle),
+				     byte_count, rs_offset,
+				     ((ch+1)->rc_discrim == 0) /* last */
+				     );
+			if (ret < 0)
+				goto err;
+			byte_count -= ret;
+			rs_offset += ret;
+			head->arg.buflen += ret;
 		}
-		/* Post the read */
-		err = svc_rdma_send(xprt, &read_wr);
-		if (err) {
-			printk(KERN_ERR "svcrdma: Error %d posting RDMA_READ\n",
-			       err);
-			set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
-			svc_rdma_unmap_dma(ctxt);
-			svc_rdma_put_context(ctxt, 0);
-			goto out;
-		}
-		atomic_inc(&rdma_stat_read);
-
-		if (read_wr.num_sge < chl_map->ch[ch_no].count) {
-			chl_map->ch[ch_no].count -= read_wr.num_sge;
-			chl_map->ch[ch_no].start += read_wr.num_sge;
-			goto next_sge;
-		}
-		sgl_offset = 0;
-		err = 1;
 	}
-
- out:
-	svc_rdma_put_req_map(rpl_map);
-	svc_rdma_put_req_map(chl_map);
-
+	ret = 1;
+ err:
 	/* Detach arg pages. svc_recv will replenish them */
-	for (ch_no = 0; &rqstp->rq_pages[ch_no] < rqstp->rq_respages; ch_no++)
-		rqstp->rq_pages[ch_no] = NULL;
-
-	/*
-	 * Detach res pages. If svc_release sees any it will attempt to
-	 * put them.
-	 */
-	while (rqstp->rq_next_page != rqstp->rq_respages)
-		*(--rqstp->rq_next_page) = NULL;
+	for (page_no = 0;
+	     &rqstp->rq_pages[page_no] < rqstp->rq_respages; page_no++)
+		rqstp->rq_pages[page_no] = NULL;
 
-	return err;
+	return ret;
 }
 
 static int rdma_read_complete(struct svc_rqst *rqstp,
@@ -550,7 +455,7 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
 
 	/* rq_respages starts after the last arg page */
 	rqstp->rq_respages = &rqstp->rq_arg.pages[page_no];
-	rqstp->rq_next_page = &rqstp->rq_arg.pages[page_no];
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
 	/* Rebuild rq_arg head and tail. */
 	rqstp->rq_arg.head[0] = head->arg.head[0];
@@ -599,13 +504,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 				  struct svc_rdma_op_ctxt,
 				  dto_q);
 		list_del_init(&ctxt->dto_q);
-	}
-	if (ctxt) {
 		spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock);
 		return rdma_read_complete(rqstp, ctxt);
-	}
-
-	if (!list_empty(&rdma_xprt->sc_rq_dto_q)) {
+	} else if (!list_empty(&rdma_xprt->sc_rq_dto_q)) {
 		ctxt = list_entry(rdma_xprt->sc_rq_dto_q.next,
 				  struct svc_rdma_op_ctxt,
 				  dto_q);
@@ -625,7 +526,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		if (test_bit(XPT_CLOSE, &xprt->xpt_flags))
 			goto close_out;
 
-		BUG_ON(ret);
 		goto out;
 	}
 	dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p, status=%d\n",
@@ -648,12 +548,11 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	}
 
 	/* Read read-list data. */
-	ret = rdma_read_xdr(rdma_xprt, rmsgp, rqstp, ctxt);
+	ret = rdma_read_chunks(rdma_xprt, rmsgp, rqstp, ctxt);
 	if (ret > 0) {
 		/* read-list posted, defer until data received from client. */
 		goto defer;
-	}
-	if (ret < 0) {
+	} else if (ret < 0) {
 		/* Post of read-list failed, free context. */
 		svc_rdma_put_context(ctxt, 1);
 		return 0;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index c1d124dc772..49fd21a5c21 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved.
  * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -49,152 +50,6 @@
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
-/* Encode an XDR as an array of IB SGE
- *
- * Assumptions:
- * - head[0] is physically contiguous.
- * - tail[0] is physically contiguous.
- * - pages[] is not physically or virtually contiguous and consists of
- *   PAGE_SIZE elements.
- *
- * Output:
- * SGE[0]              reserved for RCPRDMA header
- * SGE[1]              data from xdr->head[]
- * SGE[2..sge_count-2] data from xdr->pages[]
- * SGE[sge_count-1]    data from xdr->tail.
- *
- * The max SGE we need is the length of the XDR / pagesize + one for
- * head + one for tail + one for RPCRDMA header. Since RPCSVC_MAXPAGES
- * reserves a page for both the request and the reply header, and this
- * array is only concerned with the reply we are assured that we have
- * on extra page for the RPCRMDA header.
- */
-static int fast_reg_xdr(struct svcxprt_rdma *xprt,
-			struct xdr_buf *xdr,
-			struct svc_rdma_req_map *vec)
-{
-	int sge_no;
-	u32 sge_bytes;
-	u32 page_bytes;
-	u32 page_off;
-	int page_no = 0;
-	u8 *frva;
-	struct svc_rdma_fastreg_mr *frmr;
-
-	frmr = svc_rdma_get_frmr(xprt);
-	if (IS_ERR(frmr))
-		return -ENOMEM;
-	vec->frmr = frmr;
-
-	/* Skip the RPCRDMA header */
-	sge_no = 1;
-
-	/* Map the head. */
-	frva = (void *)((unsigned long)(xdr->head[0].iov_base) & PAGE_MASK);
-	vec->sge[sge_no].iov_base = xdr->head[0].iov_base;
-	vec->sge[sge_no].iov_len = xdr->head[0].iov_len;
-	vec->count = 2;
-	sge_no++;
-
-	/* Map the XDR head */
-	frmr->kva = frva;
-	frmr->direction = DMA_TO_DEVICE;
-	frmr->access_flags = 0;
-	frmr->map_len = PAGE_SIZE;
-	frmr->page_list_len = 1;
-	page_off = (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK;
-	frmr->page_list->page_list[page_no] =
-		ib_dma_map_page(xprt->sc_cm_id->device,
-				virt_to_page(xdr->head[0].iov_base),
-				page_off,
-				PAGE_SIZE - page_off,
-				DMA_TO_DEVICE);
-	if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-				 frmr->page_list->page_list[page_no]))
-		goto fatal_err;
-	atomic_inc(&xprt->sc_dma_used);
-
-	/* Map the XDR page list */
-	page_off = xdr->page_base;
-	page_bytes = xdr->page_len + page_off;
-	if (!page_bytes)
-		goto encode_tail;
-
-	/* Map the pages */
-	vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off;
-	vec->sge[sge_no].iov_len = page_bytes;
-	sge_no++;
-	while (page_bytes) {
-		struct page *page;
-
-		page = xdr->pages[page_no++];
-		sge_bytes = min_t(u32, page_bytes, (PAGE_SIZE - page_off));
-		page_bytes -= sge_bytes;
-
-		frmr->page_list->page_list[page_no] =
-			ib_dma_map_page(xprt->sc_cm_id->device,
-					page, page_off,
-					sge_bytes, DMA_TO_DEVICE);
-		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-					 frmr->page_list->page_list[page_no]))
-			goto fatal_err;
-
-		atomic_inc(&xprt->sc_dma_used);
-		page_off = 0; /* reset for next time through loop */
-		frmr->map_len += PAGE_SIZE;
-		frmr->page_list_len++;
-	}
-	vec->count++;
-
- encode_tail:
-	/* Map tail */
-	if (0 == xdr->tail[0].iov_len)
-		goto done;
-
-	vec->count++;
-	vec->sge[sge_no].iov_len = xdr->tail[0].iov_len;
-
-	if (((unsigned long)xdr->tail[0].iov_base & PAGE_MASK) ==
-	    ((unsigned long)xdr->head[0].iov_base & PAGE_MASK)) {
-		/*
-		 * If head and tail use the same page, we don't need
-		 * to map it again.
-		 */
-		vec->sge[sge_no].iov_base = xdr->tail[0].iov_base;
-	} else {
-		void *va;
-
-		/* Map another page for the tail */
-		page_off = (unsigned long)xdr->tail[0].iov_base & ~PAGE_MASK;
-		va = (void *)((unsigned long)xdr->tail[0].iov_base & PAGE_MASK);
-		vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off;
-
-		frmr->page_list->page_list[page_no] =
-		    ib_dma_map_page(xprt->sc_cm_id->device, virt_to_page(va),
-				    page_off,
-				    PAGE_SIZE,
-				    DMA_TO_DEVICE);
-		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-					 frmr->page_list->page_list[page_no]))
-			goto fatal_err;
-		atomic_inc(&xprt->sc_dma_used);
-		frmr->map_len += PAGE_SIZE;
-		frmr->page_list_len++;
-	}
-
- done:
-	if (svc_rdma_fastreg(xprt, frmr))
-		goto fatal_err;
-
-	return 0;
-
- fatal_err:
-	printk("svcrdma: Error fast registering memory for xprt %p\n", xprt);
-	vec->frmr = NULL;
-	svc_rdma_put_frmr(xprt, frmr);
-	return -EIO;
-}
-
 static int map_xdr(struct svcxprt_rdma *xprt,
 		   struct xdr_buf *xdr,
 		   struct svc_rdma_req_map *vec)
@@ -208,9 +63,6 @@ static int map_xdr(struct svcxprt_rdma *xprt,
 	BUG_ON(xdr->len !=
 	       (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len));
 
-	if (xprt->sc_frmr_pg_list_len)
-		return fast_reg_xdr(xprt, xdr, vec);
-
 	/* Skip the first sge, this is for the RPCRDMA header */
 	sge_no = 1;
 
@@ -265,6 +117,7 @@ static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt,
 		xdr_off -= xdr->head[0].iov_len;
 		if (xdr_off < xdr->page_len) {
 			/* This offset is in the page list */
+			xdr_off += xdr->page_base;
 			page = xdr->pages[xdr_off >> PAGE_SHIFT];
 			xdr_off &= ~PAGE_MASK;
 		} else {
@@ -281,8 +134,6 @@ static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt,
 }
 
 /* Assumptions:
- * - We are using FRMR
- *     - or -
  * - The specified write_len can be represented in sc_max_sge * PAGE_SIZE
  */
 static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
@@ -326,23 +177,16 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 		sge_bytes = min_t(size_t,
 			  bc, vec->sge[xdr_sge_no].iov_len-sge_off);
 		sge[sge_no].length = sge_bytes;
-		if (!vec->frmr) {
-			sge[sge_no].addr =
-				dma_map_xdr(xprt, &rqstp->rq_res, xdr_off,
-					    sge_bytes, DMA_TO_DEVICE);
-			xdr_off += sge_bytes;
-			if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-						 sge[sge_no].addr))
-				goto err;
-			atomic_inc(&xprt->sc_dma_used);
-			sge[sge_no].lkey = xprt->sc_dma_lkey;
-		} else {
-			sge[sge_no].addr = (unsigned long)
-				vec->sge[xdr_sge_no].iov_base + sge_off;
-			sge[sge_no].lkey = vec->frmr->mr->lkey;
-		}
+		sge[sge_no].addr =
+			dma_map_xdr(xprt, &rqstp->rq_res, xdr_off,
+				    sge_bytes, DMA_TO_DEVICE);
+		xdr_off += sge_bytes;
+		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
+					 sge[sge_no].addr))
+			goto err;
+		atomic_inc(&xprt->sc_dma_used);
+		sge[sge_no].lkey = xprt->sc_dma_lkey;
 		ctxt->count++;
-		ctxt->frmr = vec->frmr;
 		sge_off = 0;
 		sge_no++;
 		xdr_sge_no++;
@@ -368,7 +212,6 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 	return 0;
  err:
 	svc_rdma_unmap_dma(ctxt);
-	svc_rdma_put_frmr(xprt, vec->frmr);
 	svc_rdma_put_context(ctxt, 0);
 	/* Fatal error, close transport */
 	return -EIO;
@@ -396,10 +239,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt,
 	res_ary = (struct rpcrdma_write_array *)
 		&rdma_resp->rm_body.rm_chunks[1];
 
-	if (vec->frmr)
-		max_write = vec->frmr->map_len;
-	else
-		max_write = xprt->sc_max_sge * PAGE_SIZE;
+	max_write = xprt->sc_max_sge * PAGE_SIZE;
 
 	/* Write chunks start at the pagelist */
 	for (xdr_off = rqstp->rq_res.head[0].iov_len, chunk_no = 0;
@@ -471,10 +311,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt,
 	res_ary = (struct rpcrdma_write_array *)
 		&rdma_resp->rm_body.rm_chunks[2];
 
-	if (vec->frmr)
-		max_write = vec->frmr->map_len;
-	else
-		max_write = xprt->sc_max_sge * PAGE_SIZE;
+	max_write = xprt->sc_max_sge * PAGE_SIZE;
 
 	/* xdr offset starts at RPC message */
 	nchunks = ntohl(arg_ary->wc_nchunks);
@@ -544,7 +381,6 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		      int byte_count)
 {
 	struct ib_send_wr send_wr;
-	struct ib_send_wr inv_wr;
 	int sge_no;
 	int sge_bytes;
 	int page_no;
@@ -558,7 +394,6 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		       "svcrdma: could not post a receive buffer, err=%d."
 		       "Closing transport %p.\n", ret, rdma);
 		set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
-		svc_rdma_put_frmr(rdma, vec->frmr);
 		svc_rdma_put_context(ctxt, 0);
 		return -ENOTCONN;
 	}
@@ -566,11 +401,6 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	/* Prepare the context */
 	ctxt->pages[0] = page;
 	ctxt->count = 1;
-	ctxt->frmr = vec->frmr;
-	if (vec->frmr)
-		set_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
-	else
-		clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
 
 	/* Prepare the SGE for the RPCRDMA Header */
 	ctxt->sge[0].lkey = rdma->sc_dma_lkey;
@@ -589,21 +419,15 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		int xdr_off = 0;
 		sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
 		byte_count -= sge_bytes;
-		if (!vec->frmr) {
-			ctxt->sge[sge_no].addr =
-				dma_map_xdr(rdma, &rqstp->rq_res, xdr_off,
-					    sge_bytes, DMA_TO_DEVICE);
-			xdr_off += sge_bytes;
-			if (ib_dma_mapping_error(rdma->sc_cm_id->device,
-						 ctxt->sge[sge_no].addr))
-				goto err;
-			atomic_inc(&rdma->sc_dma_used);
-			ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey;
-		} else {
-			ctxt->sge[sge_no].addr = (unsigned long)
-				vec->sge[sge_no].iov_base;
-			ctxt->sge[sge_no].lkey = vec->frmr->mr->lkey;
-		}
+		ctxt->sge[sge_no].addr =
+			dma_map_xdr(rdma, &rqstp->rq_res, xdr_off,
+				    sge_bytes, DMA_TO_DEVICE);
+		xdr_off += sge_bytes;
+		if (ib_dma_mapping_error(rdma->sc_cm_id->device,
+					 ctxt->sge[sge_no].addr))
+			goto err;
+		atomic_inc(&rdma->sc_dma_used);
+		ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey;
 		ctxt->sge[sge_no].length = sge_bytes;
 	}
 	BUG_ON(byte_count != 0);
@@ -625,6 +449,8 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		if (page_no+1 >= sge_no)
 			ctxt->sge[page_no+1].length = 0;
 	}
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
+
 	BUG_ON(sge_no > rdma->sc_max_sge);
 	memset(&send_wr, 0, sizeof send_wr);
 	ctxt->wr_op = IB_WR_SEND;
@@ -633,15 +459,6 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	send_wr.num_sge = sge_no;
 	send_wr.opcode = IB_WR_SEND;
 	send_wr.send_flags =  IB_SEND_SIGNALED;
-	if (vec->frmr) {
-		/* Prepare INVALIDATE WR */
-		memset(&inv_wr, 0, sizeof inv_wr);
-		inv_wr.opcode = IB_WR_LOCAL_INV;
-		inv_wr.send_flags = IB_SEND_SIGNALED;
-		inv_wr.ex.invalidate_rkey =
-			vec->frmr->mr->lkey;
-		send_wr.next = &inv_wr;
-	}
 
 	ret = svc_rdma_send(rdma, &send_wr);
 	if (ret)
@@ -651,7 +468,6 @@ static int send_reply(struct svcxprt_rdma *rdma,
 
  err:
 	svc_rdma_unmap_dma(ctxt);
-	svc_rdma_put_frmr(rdma, vec->frmr);
 	svc_rdma_put_context(ctxt, 1);
 	return -EIO;
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 62e4f9bcc38..e7323fbbd34 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved.
  * Copyright (c) 2005-2007 Network Appliance, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -65,6 +66,7 @@ static void dto_tasklet_func(unsigned long data);
 static void svc_rdma_detach(struct svc_xprt *xprt);
 static void svc_rdma_free(struct svc_xprt *xprt);
 static int svc_rdma_has_wspace(struct svc_xprt *xprt);
+static int svc_rdma_secure_port(struct svc_rqst *);
 static void rq_cq_reap(struct svcxprt_rdma *xprt);
 static void sq_cq_reap(struct svcxprt_rdma *xprt);
 
@@ -82,6 +84,7 @@ static struct svc_xprt_ops svc_rdma_ops = {
 	.xpo_prep_reply_hdr = svc_rdma_prep_reply_hdr,
 	.xpo_has_wspace = svc_rdma_has_wspace,
 	.xpo_accept = svc_rdma_accept,
+	.xpo_secure_port = svc_rdma_secure_port,
 };
 
 struct svc_xprt_class svc_rdma_class = {
@@ -160,7 +163,6 @@ struct svc_rdma_req_map *svc_rdma_get_req_map(void)
 		schedule_timeout_uninterruptible(msecs_to_jiffies(500));
 	}
 	map->count = 0;
-	map->frmr = NULL;
 	return map;
 }
 
@@ -336,22 +338,21 @@ static void process_context(struct svcxprt_rdma *xprt,
 
 	switch (ctxt->wr_op) {
 	case IB_WR_SEND:
-		if (test_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags))
-			svc_rdma_put_frmr(xprt, ctxt->frmr);
+		BUG_ON(ctxt->frmr);
 		svc_rdma_put_context(ctxt, 1);
 		break;
 
 	case IB_WR_RDMA_WRITE:
+		BUG_ON(ctxt->frmr);
 		svc_rdma_put_context(ctxt, 0);
 		break;
 
 	case IB_WR_RDMA_READ:
 	case IB_WR_RDMA_READ_WITH_INV:
+		svc_rdma_put_frmr(xprt, ctxt->frmr);
 		if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) {
 			struct svc_rdma_op_ctxt *read_hdr = ctxt->read_hdr;
 			BUG_ON(!read_hdr);
-			if (test_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags))
-				svc_rdma_put_frmr(xprt, ctxt->frmr);
 			spin_lock_bh(&xprt->sc_rq_dto_lock);
 			set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
 			list_add_tail(&read_hdr->dto_q,
@@ -363,6 +364,7 @@ static void process_context(struct svcxprt_rdma *xprt,
 		break;
 
 	default:
+		BUG_ON(1);
 		printk(KERN_ERR "svcrdma: unexpected completion type, "
 		       "opcode=%d\n",
 		       ctxt->wr_op);
@@ -378,29 +380,42 @@ static void process_context(struct svcxprt_rdma *xprt,
 static void sq_cq_reap(struct svcxprt_rdma *xprt)
 {
 	struct svc_rdma_op_ctxt *ctxt = NULL;
-	struct ib_wc wc;
+	struct ib_wc wc_a[6];
+	struct ib_wc *wc;
 	struct ib_cq *cq = xprt->sc_sq_cq;
 	int ret;
 
+	memset(wc_a, 0, sizeof(wc_a));
+
 	if (!test_and_clear_bit(RDMAXPRT_SQ_PENDING, &xprt->sc_flags))
 		return;
 
 	ib_req_notify_cq(xprt->sc_sq_cq, IB_CQ_NEXT_COMP);
 	atomic_inc(&rdma_stat_sq_poll);
-	while ((ret = ib_poll_cq(cq, 1, &wc)) > 0) {
-		if (wc.status != IB_WC_SUCCESS)
-			/* Close the transport */
-			set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+	while ((ret = ib_poll_cq(cq, ARRAY_SIZE(wc_a), wc_a)) > 0) {
+		int i;
 
-		/* Decrement used SQ WR count */
-		atomic_dec(&xprt->sc_sq_count);
-		wake_up(&xprt->sc_send_wait);
+		for (i = 0; i < ret; i++) {
+			wc = &wc_a[i];
+			if (wc->status != IB_WC_SUCCESS) {
+				dprintk("svcrdma: sq wc err status %d\n",
+					wc->status);
 
-		ctxt = (struct svc_rdma_op_ctxt *)(unsigned long)wc.wr_id;
-		if (ctxt)
-			process_context(xprt, ctxt);
+				/* Close the transport */
+				set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+			}
 
-		svc_xprt_put(&xprt->sc_xprt);
+			/* Decrement used SQ WR count */
+			atomic_dec(&xprt->sc_sq_count);
+			wake_up(&xprt->sc_send_wait);
+
+			ctxt = (struct svc_rdma_op_ctxt *)
+				(unsigned long)wc->wr_id;
+			if (ctxt)
+				process_context(xprt, ctxt);
+
+			svc_xprt_put(&xprt->sc_xprt);
+		}
 	}
 
 	if (ctxt)
@@ -477,8 +492,7 @@ struct page *svc_rdma_get_page(void)
 
 	while ((page = alloc_page(GFP_KERNEL)) == NULL) {
 		/* If we can't get memory, wait a bit and try again */
-		printk(KERN_INFO "svcrdma: out of memory...retrying in 1000 "
-		       "jiffies.\n");
+		printk(KERN_INFO "svcrdma: out of memory...retrying in 1s\n");
 		schedule_timeout_uninterruptible(msecs_to_jiffies(1000));
 	}
 	return page;
@@ -994,7 +1008,11 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 			need_dma_mr = 0;
 		break;
 	case RDMA_TRANSPORT_IB:
-		if (!(devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)) {
+		if (!(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)) {
+			need_dma_mr = 1;
+			dma_mr_acc = IB_ACCESS_LOCAL_WRITE;
+		} else if (!(devattr.device_cap_flags &
+			     IB_DEVICE_LOCAL_DMA_LKEY)) {
 			need_dma_mr = 1;
 			dma_mr_acc = IB_ACCESS_LOCAL_WRITE;
 		} else
@@ -1191,14 +1209,7 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt)
 		container_of(xprt, struct svcxprt_rdma, sc_xprt);
 
 	/*
-	 * If there are fewer SQ WR available than required to send a
-	 * simple response, return false.
-	 */
-	if ((rdma->sc_sq_depth - atomic_read(&rdma->sc_sq_count) < 3))
-		return 0;
-
-	/*
-	 * ...or there are already waiters on the SQ,
+	 * If there are already waiters on the SQ,
 	 * return false.
 	 */
 	if (waitqueue_active(&rdma->sc_send_wait))
@@ -1208,6 +1219,11 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt)
 	return 1;
 }
 
+static int svc_rdma_secure_port(struct svc_rqst *rqstp)
+{
+	return 1;
+}
+
 /*
  * Attempt to register the kvec representing the RPC memory with the
  * device.
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 285dc088411..66f91f0d071 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -149,6 +149,11 @@ static struct ctl_table sunrpc_table[] = {
 
 #endif
 
+#define RPCRDMA_BIND_TO		(60U * HZ)
+#define RPCRDMA_INIT_REEST_TO	(5U * HZ)
+#define RPCRDMA_MAX_REEST_TO	(30U * HZ)
+#define RPCRDMA_IDLE_DISC_TO	(5U * 60 * HZ)
+
 static struct rpc_xprt_ops xprt_rdma_procs;	/* forward reference */
 
 static void
@@ -229,7 +234,6 @@ static void
 xprt_rdma_destroy(struct rpc_xprt *xprt)
 {
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
-	int rc;
 
 	dprintk("RPC:       %s: called\n", __func__);
 
@@ -238,10 +242,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt)
 	xprt_clear_connected(xprt);
 
 	rpcrdma_buffer_destroy(&r_xprt->rx_buf);
-	rc = rpcrdma_ep_destroy(&r_xprt->rx_ep, &r_xprt->rx_ia);
-	if (rc)
-		dprintk("RPC:       %s: rpcrdma_ep_destroy returned %i\n",
-			__func__, rc);
+	rpcrdma_ep_destroy(&r_xprt->rx_ep, &r_xprt->rx_ia);
 	rpcrdma_ia_close(&r_xprt->rx_ia);
 
 	xprt_rdma_free_addresses(xprt);
@@ -289,9 +290,9 @@ xprt_setup_rdma(struct xprt_create *args)
 
 	/* 60 second timeout, no retries */
 	xprt->timeout = &xprt_rdma_default_timeout;
-	xprt->bind_timeout = (60U * HZ);
-	xprt->reestablish_timeout = (5U * HZ);
-	xprt->idle_timeout = (5U * 60 * HZ);
+	xprt->bind_timeout = RPCRDMA_BIND_TO;
+	xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
+	xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO;
 
 	xprt->resvport = 0;		/* privileged port not needed */
 	xprt->tsh_size = 0;		/* RPC-RDMA handles framing */
@@ -391,7 +392,7 @@ out4:
 	xprt_rdma_free_addresses(xprt);
 	rc = -EINVAL;
 out3:
-	(void) rpcrdma_ep_destroy(new_ep, &new_xprt->rx_ia);
+	rpcrdma_ep_destroy(new_ep, &new_xprt->rx_ia);
 out2:
 	rpcrdma_ia_close(&new_xprt->rx_ia);
 out1:
@@ -436,10 +437,10 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 		schedule_delayed_work(&r_xprt->rdma_connect,
 			xprt->reestablish_timeout);
 		xprt->reestablish_timeout <<= 1;
-		if (xprt->reestablish_timeout > (30 * HZ))
-			xprt->reestablish_timeout = (30 * HZ);
-		else if (xprt->reestablish_timeout < (5 * HZ))
-			xprt->reestablish_timeout = (5 * HZ);
+		if (xprt->reestablish_timeout > RPCRDMA_MAX_REEST_TO)
+			xprt->reestablish_timeout = RPCRDMA_MAX_REEST_TO;
+		else if (xprt->reestablish_timeout < RPCRDMA_INIT_REEST_TO)
+			xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
 	} else {
 		schedule_delayed_work(&r_xprt->rdma_connect, 0);
 		if (!RPC_IS_ASYNC(task))
@@ -447,23 +448,6 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 	}
 }
 
-static int
-xprt_rdma_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
-{
-	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
-	int credits = atomic_read(&r_xprt->rx_buf.rb_credits);
-
-	/* == RPC_CWNDSCALE @ init, but *after* setup */
-	if (r_xprt->rx_buf.rb_cwndscale == 0UL) {
-		r_xprt->rx_buf.rb_cwndscale = xprt->cwnd;
-		dprintk("RPC:       %s: cwndscale %lu\n", __func__,
-			r_xprt->rx_buf.rb_cwndscale);
-		BUG_ON(r_xprt->rx_buf.rb_cwndscale <= 0);
-	}
-	xprt->cwnd = credits * r_xprt->rx_buf.rb_cwndscale;
-	return xprt_reserve_xprt_cong(xprt, task);
-}
-
 /*
  * The RDMA allocate/free functions need the task structure as a place
  * to hide the struct rpcrdma_req, which is necessary for the actual send/recv
@@ -479,7 +463,8 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size)
 	struct rpcrdma_req *req, *nreq;
 
 	req = rpcrdma_buffer_get(&rpcx_to_rdmax(xprt)->rx_buf);
-	BUG_ON(NULL == req);
+	if (req == NULL)
+		return NULL;
 
 	if (size > req->rl_size) {
 		dprintk("RPC:       %s: size %zd too large for buffer[%zd]: "
@@ -503,18 +488,6 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size)
 		 * If the allocation or registration fails, the RPC framework
 		 * will (doggedly) retry.
 		 */
-		if (rpcx_to_rdmax(xprt)->rx_ia.ri_memreg_strategy ==
-				RPCRDMA_BOUNCEBUFFERS) {
-			/* forced to "pure inline" */
-			dprintk("RPC:       %s: too much data (%zd) for inline "
-					"(r/w max %d/%d)\n", __func__, size,
-					rpcx_to_rdmad(xprt).inline_rsize,
-					rpcx_to_rdmad(xprt).inline_wsize);
-			size = req->rl_size;
-			rpc_exit(task, -EIO);		/* fail the operation */
-			rpcx_to_rdmax(xprt)->rx_stats.failed_marshal_count++;
-			goto out;
-		}
 		if (task->tk_flags & RPC_TASK_SWAPPER)
 			nreq = kmalloc(sizeof *req + size, GFP_ATOMIC);
 		else
@@ -543,7 +516,6 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size)
 		req = nreq;
 	}
 	dprintk("RPC:       %s: size %zd, request 0x%p\n", __func__, size, req);
-out:
 	req->rl_connect_cookie = 0;	/* our reserved value */
 	return req->rl_xdr_buf;
 
@@ -579,9 +551,7 @@ xprt_rdma_free(void *buffer)
 		__func__, rep, (rep && rep->rr_func) ? " (with waiter)" : "");
 
 	/*
-	 * Finish the deregistration. When using mw bind, this was
-	 * begun in rpcrdma_reply_handler(). In all other modes, we
-	 * do it here, in thread context. The process is considered
+	 * Finish the deregistration.  The process is considered
 	 * complete when the rr_func vector becomes NULL - this
 	 * was put in place during rpcrdma_reply_handler() - the wait
 	 * call below will not block if the dereg is "done". If
@@ -590,12 +560,7 @@ xprt_rdma_free(void *buffer)
 	for (i = 0; req->rl_nchunks;) {
 		--req->rl_nchunks;
 		i += rpcrdma_deregister_external(
-			&req->rl_segments[i], r_xprt, NULL);
-	}
-
-	if (rep && wait_event_interruptible(rep->rr_unbind, !rep->rr_func)) {
-		rep->rr_func = NULL;	/* abandon the callback */
-		req->rl_reply = NULL;
+			&req->rl_segments[i], r_xprt);
 	}
 
 	if (req->rl_iov.length == 0) {	/* see allocate above */
@@ -630,13 +595,12 @@ xprt_rdma_send_request(struct rpc_task *task)
 	struct rpc_xprt *xprt = rqst->rq_xprt;
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	int rc;
 
-	/* marshal the send itself */
-	if (req->rl_niovs == 0 && rpcrdma_marshal_req(rqst) != 0) {
-		r_xprt->rx_stats.failed_marshal_count++;
-		dprintk("RPC:       %s: rpcrdma_marshal_req failed\n",
-			__func__);
-		return -EIO;
+	if (req->rl_niovs == 0) {
+		rc = rpcrdma_marshal_req(rqst);
+		if (rc < 0)
+			goto failed_marshal;
 	}
 
 	if (req->rl_reply == NULL) 		/* e.g. reconnection */
@@ -660,6 +624,12 @@ xprt_rdma_send_request(struct rpc_task *task)
 	rqst->rq_bytes_sent = 0;
 	return 0;
 
+failed_marshal:
+	r_xprt->rx_stats.failed_marshal_count++;
+	dprintk("RPC:       %s: rpcrdma_marshal_req failed, status %i\n",
+		__func__, rc);
+	if (rc == -EIO)
+		return -EIO;
 drop_connection:
 	xprt_disconnect_done(xprt);
 	return -ENOTCONN;	/* implies disconnect */
@@ -705,7 +675,7 @@ static void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
  */
 
 static struct rpc_xprt_ops xprt_rdma_procs = {
-	.reserve_xprt		= xprt_rdma_reserve_xprt,
+	.reserve_xprt		= xprt_reserve_xprt_cong,
 	.release_xprt		= xprt_release_xprt_cong, /* sunrpc/xprt.c */
 	.alloc_slot		= xprt_alloc_slot,
 	.release_request	= xprt_release_rqst_cong,       /* ditto */
@@ -733,7 +703,7 @@ static void __exit xprt_rdma_cleanup(void)
 {
 	int rc;
 
-	dprintk(KERN_INFO "RPCRDMA Module Removed, deregister RPC RDMA transport\n");
+	dprintk("RPCRDMA Module Removed, deregister RPC RDMA transport\n");
 #ifdef RPC_DEBUG
 	if (sunrpc_table_header) {
 		unregister_sysctl_table(sunrpc_table_header);
@@ -755,14 +725,14 @@ static int __init xprt_rdma_init(void)
 	if (rc)
 		return rc;
 
-	dprintk(KERN_INFO "RPCRDMA Module Init, register RPC RDMA transport\n");
+	dprintk("RPCRDMA Module Init, register RPC RDMA transport\n");
 
-	dprintk(KERN_INFO "Defaults:\n");
-	dprintk(KERN_INFO "\tSlots %d\n"
+	dprintk("Defaults:\n");
+	dprintk("\tSlots %d\n"
 		"\tMaxInlineRead %d\n\tMaxInlineWrite %d\n",
 		xprt_rdma_slot_table_entries,
 		xprt_rdma_max_inline_read, xprt_rdma_max_inline_write);
-	dprintk(KERN_INFO "\tPadding %d\n\tMemreg %d\n",
+	dprintk("\tPadding %d\n\tMemreg %d\n",
 		xprt_rdma_inline_write_padding, xprt_rdma_memreg_strategy);
 
 #ifdef RPC_DEBUG
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 93726560eaa..13dbd1c389f 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -48,8 +48,8 @@
  */
 
 #include <linux/interrupt.h>
-#include <linux/pci.h>	/* for Tavor hack below */
 #include <linux/slab.h>
+#include <asm/bitops.h>
 
 #include "xprt_rdma.h"
 
@@ -142,98 +142,139 @@ rpcrdma_cq_async_error_upcall(struct ib_event *event, void *context)
 	}
 }
 
-static inline
-void rpcrdma_event_process(struct ib_wc *wc)
+static void
+rpcrdma_sendcq_process_wc(struct ib_wc *wc)
 {
-	struct rpcrdma_mw *frmr;
-	struct rpcrdma_rep *rep =
-			(struct rpcrdma_rep *)(unsigned long) wc->wr_id;
+	struct rpcrdma_mw *frmr = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
 
-	dprintk("RPC:       %s: event rep %p status %X opcode %X length %u\n",
-		__func__, rep, wc->status, wc->opcode, wc->byte_len);
+	dprintk("RPC:       %s: frmr %p status %X opcode %d\n",
+		__func__, frmr, wc->status, wc->opcode);
 
-	if (!rep) /* send or bind completion that we don't care about */
+	if (wc->wr_id == 0ULL)
 		return;
-
-	if (IB_WC_SUCCESS != wc->status) {
-		dprintk("RPC:       %s: WC opcode %d status %X, connection lost\n",
-			__func__, wc->opcode, wc->status);
-		rep->rr_len = ~0U;
-		if (wc->opcode != IB_WC_FAST_REG_MR && wc->opcode != IB_WC_LOCAL_INV)
-			rpcrdma_schedule_tasklet(rep);
+	if (wc->status != IB_WC_SUCCESS)
 		return;
-	}
 
-	switch (wc->opcode) {
-	case IB_WC_FAST_REG_MR:
-		frmr = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
+	if (wc->opcode == IB_WC_FAST_REG_MR)
 		frmr->r.frmr.state = FRMR_IS_VALID;
-		break;
-	case IB_WC_LOCAL_INV:
-		frmr = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
+	else if (wc->opcode == IB_WC_LOCAL_INV)
 		frmr->r.frmr.state = FRMR_IS_INVALID;
-		break;
-	case IB_WC_RECV:
-		rep->rr_len = wc->byte_len;
-		ib_dma_sync_single_for_cpu(
-			rdmab_to_ia(rep->rr_buffer)->ri_id->device,
-			rep->rr_iov.addr, rep->rr_len, DMA_FROM_DEVICE);
-		/* Keep (only) the most recent credits, after check validity */
-		if (rep->rr_len >= 16) {
-			struct rpcrdma_msg *p =
-					(struct rpcrdma_msg *) rep->rr_base;
-			unsigned int credits = ntohl(p->rm_credit);
-			if (credits == 0) {
-				dprintk("RPC:       %s: server"
-					" dropped credits to 0!\n", __func__);
-				/* don't deadlock */
-				credits = 1;
-			} else if (credits > rep->rr_buffer->rb_max_requests) {
-				dprintk("RPC:       %s: server"
-					" over-crediting: %d (%d)\n",
-					__func__, credits,
-					rep->rr_buffer->rb_max_requests);
-				credits = rep->rr_buffer->rb_max_requests;
-			}
-			atomic_set(&rep->rr_buffer->rb_credits, credits);
-		}
-		/* fall through */
-	case IB_WC_BIND_MW:
-		rpcrdma_schedule_tasklet(rep);
-		break;
-	default:
-		dprintk("RPC:       %s: unexpected WC event %X\n",
-			__func__, wc->opcode);
-		break;
-	}
 }
 
-static inline int
-rpcrdma_cq_poll(struct ib_cq *cq)
+static int
+rpcrdma_sendcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep)
 {
-	struct ib_wc wc;
-	int rc;
+	struct ib_wc *wcs;
+	int budget, count, rc;
 
-	for (;;) {
-		rc = ib_poll_cq(cq, 1, &wc);
-		if (rc < 0) {
-			dprintk("RPC:       %s: ib_poll_cq failed %i\n",
-				__func__, rc);
+	budget = RPCRDMA_WC_BUDGET / RPCRDMA_POLLSIZE;
+	do {
+		wcs = ep->rep_send_wcs;
+
+		rc = ib_poll_cq(cq, RPCRDMA_POLLSIZE, wcs);
+		if (rc <= 0)
 			return rc;
-		}
-		if (rc == 0)
-			break;
 
-		rpcrdma_event_process(&wc);
+		count = rc;
+		while (count-- > 0)
+			rpcrdma_sendcq_process_wc(wcs++);
+	} while (rc == RPCRDMA_POLLSIZE && --budget);
+	return 0;
+}
+
+/*
+ * Handle send, fast_reg_mr, and local_inv completions.
+ *
+ * Send events are typically suppressed and thus do not result
+ * in an upcall. Occasionally one is signaled, however. This
+ * prevents the provider's completion queue from wrapping and
+ * losing a completion.
+ */
+static void
+rpcrdma_sendcq_upcall(struct ib_cq *cq, void *cq_context)
+{
+	struct rpcrdma_ep *ep = (struct rpcrdma_ep *)cq_context;
+	int rc;
+
+	rc = rpcrdma_sendcq_poll(cq, ep);
+	if (rc) {
+		dprintk("RPC:       %s: ib_poll_cq failed: %i\n",
+			__func__, rc);
+		return;
 	}
 
+	rc = ib_req_notify_cq(cq,
+			IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
+	if (rc == 0)
+		return;
+	if (rc < 0) {
+		dprintk("RPC:       %s: ib_req_notify_cq failed: %i\n",
+			__func__, rc);
+		return;
+	}
+
+	rpcrdma_sendcq_poll(cq, ep);
+}
+
+static void
+rpcrdma_recvcq_process_wc(struct ib_wc *wc)
+{
+	struct rpcrdma_rep *rep =
+			(struct rpcrdma_rep *)(unsigned long)wc->wr_id;
+
+	dprintk("RPC:       %s: rep %p status %X opcode %X length %u\n",
+		__func__, rep, wc->status, wc->opcode, wc->byte_len);
+
+	if (wc->status != IB_WC_SUCCESS) {
+		rep->rr_len = ~0U;
+		goto out_schedule;
+	}
+	if (wc->opcode != IB_WC_RECV)
+		return;
+
+	rep->rr_len = wc->byte_len;
+	ib_dma_sync_single_for_cpu(rdmab_to_ia(rep->rr_buffer)->ri_id->device,
+			rep->rr_iov.addr, rep->rr_len, DMA_FROM_DEVICE);
+
+	if (rep->rr_len >= 16) {
+		struct rpcrdma_msg *p = (struct rpcrdma_msg *)rep->rr_base;
+		unsigned int credits = ntohl(p->rm_credit);
+
+		if (credits == 0)
+			credits = 1;	/* don't deadlock */
+		else if (credits > rep->rr_buffer->rb_max_requests)
+			credits = rep->rr_buffer->rb_max_requests;
+		atomic_set(&rep->rr_buffer->rb_credits, credits);
+	}
+
+out_schedule:
+	rpcrdma_schedule_tasklet(rep);
+}
+
+static int
+rpcrdma_recvcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep)
+{
+	struct ib_wc *wcs;
+	int budget, count, rc;
+
+	budget = RPCRDMA_WC_BUDGET / RPCRDMA_POLLSIZE;
+	do {
+		wcs = ep->rep_recv_wcs;
+
+		rc = ib_poll_cq(cq, RPCRDMA_POLLSIZE, wcs);
+		if (rc <= 0)
+			return rc;
+
+		count = rc;
+		while (count-- > 0)
+			rpcrdma_recvcq_process_wc(wcs++);
+	} while (rc == RPCRDMA_POLLSIZE && --budget);
 	return 0;
 }
 
 /*
- * rpcrdma_cq_event_upcall
+ * Handle receive completions.
  *
- * This upcall handles recv, send, bind and unbind events.
  * It is reentrant but processes single events in order to maintain
  * ordering of receives to keep server credits.
  *
@@ -242,26 +283,31 @@ rpcrdma_cq_poll(struct ib_cq *cq)
  * connection shutdown. That is, the structures required for
  * the completion of the reply handler must remain intact until
  * all memory has been reclaimed.
- *
- * Note that send events are suppressed and do not result in an upcall.
  */
 static void
-rpcrdma_cq_event_upcall(struct ib_cq *cq, void *context)
+rpcrdma_recvcq_upcall(struct ib_cq *cq, void *cq_context)
 {
+	struct rpcrdma_ep *ep = (struct rpcrdma_ep *)cq_context;
 	int rc;
 
-	rc = rpcrdma_cq_poll(cq);
-	if (rc)
+	rc = rpcrdma_recvcq_poll(cq, ep);
+	if (rc) {
+		dprintk("RPC:       %s: ib_poll_cq failed: %i\n",
+			__func__, rc);
 		return;
+	}
 
-	rc = ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
-	if (rc) {
-		dprintk("RPC:       %s: ib_req_notify_cq failed %i\n",
+	rc = ib_req_notify_cq(cq,
+			IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
+	if (rc == 0)
+		return;
+	if (rc < 0) {
+		dprintk("RPC:       %s: ib_req_notify_cq failed: %i\n",
 			__func__, rc);
 		return;
 	}
 
-	rpcrdma_cq_poll(cq);
+	rpcrdma_recvcq_poll(cq, ep);
 }
 
 #ifdef RPC_DEBUG
@@ -493,54 +539,32 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 		ia->ri_dma_lkey = ia->ri_id->device->local_dma_lkey;
 	}
 
-	switch (memreg) {
-	case RPCRDMA_MEMWINDOWS:
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-		if (!(devattr.device_cap_flags & IB_DEVICE_MEM_WINDOW)) {
-			dprintk("RPC:       %s: MEMWINDOWS registration "
-				"specified but not supported by adapter, "
-				"using slower RPCRDMA_REGISTER\n",
-				__func__);
-			memreg = RPCRDMA_REGISTER;
-		}
-		break;
-	case RPCRDMA_MTHCAFMR:
-		if (!ia->ri_id->device->alloc_fmr) {
-#if RPCRDMA_PERSISTENT_REGISTRATION
-			dprintk("RPC:       %s: MTHCAFMR registration "
-				"specified but not supported by adapter, "
-				"using riskier RPCRDMA_ALLPHYSICAL\n",
-				__func__);
-			memreg = RPCRDMA_ALLPHYSICAL;
-#else
-			dprintk("RPC:       %s: MTHCAFMR registration "
-				"specified but not supported by adapter, "
-				"using slower RPCRDMA_REGISTER\n",
-				__func__);
-			memreg = RPCRDMA_REGISTER;
-#endif
-		}
-		break;
-	case RPCRDMA_FRMR:
+	if (memreg == RPCRDMA_FRMR) {
 		/* Requires both frmr reg and local dma lkey */
 		if ((devattr.device_cap_flags &
 		     (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) !=
 		    (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) {
-#if RPCRDMA_PERSISTENT_REGISTRATION
 			dprintk("RPC:       %s: FRMR registration "
-				"specified but not supported by adapter, "
-				"using riskier RPCRDMA_ALLPHYSICAL\n",
-				__func__);
+				"not supported by HCA\n", __func__);
+			memreg = RPCRDMA_MTHCAFMR;
+		} else {
+			/* Mind the ia limit on FRMR page list depth */
+			ia->ri_max_frmr_depth = min_t(unsigned int,
+				RPCRDMA_MAX_DATA_SEGS,
+				devattr.max_fast_reg_page_list_len);
+		}
+	}
+	if (memreg == RPCRDMA_MTHCAFMR) {
+		if (!ia->ri_id->device->alloc_fmr) {
+			dprintk("RPC:       %s: MTHCAFMR registration "
+				"not supported by HCA\n", __func__);
+#if RPCRDMA_PERSISTENT_REGISTRATION
 			memreg = RPCRDMA_ALLPHYSICAL;
 #else
-			dprintk("RPC:       %s: FRMR registration "
-				"specified but not supported by adapter, "
-				"using slower RPCRDMA_REGISTER\n",
-				__func__);
-			memreg = RPCRDMA_REGISTER;
+			rc = -ENOMEM;
+			goto out2;
 #endif
 		}
-		break;
 	}
 
 	/*
@@ -552,8 +576,6 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 	 * adapter.
 	 */
 	switch (memreg) {
-	case RPCRDMA_BOUNCEBUFFERS:
-	case RPCRDMA_REGISTER:
 	case RPCRDMA_FRMR:
 		break;
 #if RPCRDMA_PERSISTENT_REGISTRATION
@@ -563,30 +585,26 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 				IB_ACCESS_REMOTE_READ;
 		goto register_setup;
 #endif
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		mem_priv = IB_ACCESS_LOCAL_WRITE |
-				IB_ACCESS_MW_BIND;
-		goto register_setup;
 	case RPCRDMA_MTHCAFMR:
 		if (ia->ri_have_dma_lkey)
 			break;
 		mem_priv = IB_ACCESS_LOCAL_WRITE;
+#if RPCRDMA_PERSISTENT_REGISTRATION
 	register_setup:
+#endif
 		ia->ri_bind_mem = ib_get_dma_mr(ia->ri_pd, mem_priv);
 		if (IS_ERR(ia->ri_bind_mem)) {
 			printk(KERN_ALERT "%s: ib_get_dma_mr for "
-				"phys register failed with %lX\n\t"
-				"Will continue with degraded performance\n",
+				"phys register failed with %lX\n",
 				__func__, PTR_ERR(ia->ri_bind_mem));
-			memreg = RPCRDMA_REGISTER;
-			ia->ri_bind_mem = NULL;
+			rc = -ENOMEM;
+			goto out2;
 		}
 		break;
 	default:
-		printk(KERN_ERR "%s: invalid memory registration mode %d\n",
-				__func__, memreg);
-		rc = -EINVAL;
+		printk(KERN_ERR "RPC: Unsupported memory "
+				"registration mode: %d\n", memreg);
+		rc = -ENOMEM;
 		goto out2;
 	}
 	dprintk("RPC:       %s: memory registration strategy is %d\n",
@@ -640,6 +658,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 				struct rpcrdma_create_data_internal *cdata)
 {
 	struct ib_device_attr devattr;
+	struct ib_cq *sendcq, *recvcq;
 	int rc, err;
 
 	rc = ib_query_device(ia->ri_id->device, &devattr);
@@ -659,32 +678,42 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	ep->rep_attr.srq = NULL;
 	ep->rep_attr.cap.max_send_wr = cdata->max_requests;
 	switch (ia->ri_memreg_strategy) {
-	case RPCRDMA_FRMR:
+	case RPCRDMA_FRMR: {
+		int depth = 7;
+
 		/* Add room for frmr register and invalidate WRs.
 		 * 1. FRMR reg WR for head
 		 * 2. FRMR invalidate WR for head
-		 * 3. FRMR reg WR for pagelist
-		 * 4. FRMR invalidate WR for pagelist
+		 * 3. N FRMR reg WRs for pagelist
+		 * 4. N FRMR invalidate WRs for pagelist
 		 * 5. FRMR reg WR for tail
 		 * 6. FRMR invalidate WR for tail
 		 * 7. The RDMA_SEND WR
 		 */
-		ep->rep_attr.cap.max_send_wr *= 7;
+
+		/* Calculate N if the device max FRMR depth is smaller than
+		 * RPCRDMA_MAX_DATA_SEGS.
+		 */
+		if (ia->ri_max_frmr_depth < RPCRDMA_MAX_DATA_SEGS) {
+			int delta = RPCRDMA_MAX_DATA_SEGS -
+				    ia->ri_max_frmr_depth;
+
+			do {
+				depth += 2; /* FRMR reg + invalidate */
+				delta -= ia->ri_max_frmr_depth;
+			} while (delta > 0);
+
+		}
+		ep->rep_attr.cap.max_send_wr *= depth;
 		if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr) {
-			cdata->max_requests = devattr.max_qp_wr / 7;
+			cdata->max_requests = devattr.max_qp_wr / depth;
 			if (!cdata->max_requests)
 				return -EINVAL;
-			ep->rep_attr.cap.max_send_wr = cdata->max_requests * 7;
+			ep->rep_attr.cap.max_send_wr = cdata->max_requests *
+						       depth;
 		}
 		break;
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		/* Add room for mw_binds+unbinds - overkill! */
-		ep->rep_attr.cap.max_send_wr++;
-		ep->rep_attr.cap.max_send_wr *= (2 * RPCRDMA_MAX_SEGS);
-		if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr)
-			return -EINVAL;
-		break;
+	}
 	default:
 		break;
 	}
@@ -705,46 +734,51 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 		ep->rep_attr.cap.max_recv_sge);
 
 	/* set trigger for requesting send completion */
-	ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 /*  - 1*/;
-	switch (ia->ri_memreg_strategy) {
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		ep->rep_cqinit -= RPCRDMA_MAX_SEGS;
-		break;
-	default:
-		break;
-	}
+	ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1;
 	if (ep->rep_cqinit <= 2)
 		ep->rep_cqinit = 0;
 	INIT_CQCOUNT(ep);
 	ep->rep_ia = ia;
 	init_waitqueue_head(&ep->rep_connect_wait);
+	INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker);
 
-	/*
-	 * Create a single cq for receive dto and mw_bind (only ever
-	 * care about unbind, really). Send completions are suppressed.
-	 * Use single threaded tasklet upcalls to maintain ordering.
-	 */
-	ep->rep_cq = ib_create_cq(ia->ri_id->device, rpcrdma_cq_event_upcall,
-				  rpcrdma_cq_async_error_upcall, NULL,
-				  ep->rep_attr.cap.max_recv_wr +
+	sendcq = ib_create_cq(ia->ri_id->device, rpcrdma_sendcq_upcall,
+				  rpcrdma_cq_async_error_upcall, ep,
 				  ep->rep_attr.cap.max_send_wr + 1, 0);
-	if (IS_ERR(ep->rep_cq)) {
-		rc = PTR_ERR(ep->rep_cq);
-		dprintk("RPC:       %s: ib_create_cq failed: %i\n",
+	if (IS_ERR(sendcq)) {
+		rc = PTR_ERR(sendcq);
+		dprintk("RPC:       %s: failed to create send CQ: %i\n",
 			__func__, rc);
 		goto out1;
 	}
 
-	rc = ib_req_notify_cq(ep->rep_cq, IB_CQ_NEXT_COMP);
+	rc = ib_req_notify_cq(sendcq, IB_CQ_NEXT_COMP);
+	if (rc) {
+		dprintk("RPC:       %s: ib_req_notify_cq failed: %i\n",
+			__func__, rc);
+		goto out2;
+	}
+
+	recvcq = ib_create_cq(ia->ri_id->device, rpcrdma_recvcq_upcall,
+				  rpcrdma_cq_async_error_upcall, ep,
+				  ep->rep_attr.cap.max_recv_wr + 1, 0);
+	if (IS_ERR(recvcq)) {
+		rc = PTR_ERR(recvcq);
+		dprintk("RPC:       %s: failed to create recv CQ: %i\n",
+			__func__, rc);
+		goto out2;
+	}
+
+	rc = ib_req_notify_cq(recvcq, IB_CQ_NEXT_COMP);
 	if (rc) {
 		dprintk("RPC:       %s: ib_req_notify_cq failed: %i\n",
 			__func__, rc);
+		ib_destroy_cq(recvcq);
 		goto out2;
 	}
 
-	ep->rep_attr.send_cq = ep->rep_cq;
-	ep->rep_attr.recv_cq = ep->rep_cq;
+	ep->rep_attr.send_cq = sendcq;
+	ep->rep_attr.recv_cq = recvcq;
 
 	/* Initialize cma parameters */
 
@@ -754,9 +788,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 
 	/* Client offers RDMA Read but does not initiate */
 	ep->rep_remote_cma.initiator_depth = 0;
-	if (ia->ri_memreg_strategy == RPCRDMA_BOUNCEBUFFERS)
-		ep->rep_remote_cma.responder_resources = 0;
-	else if (devattr.max_qp_rd_atom > 32)	/* arbitrary but <= 255 */
+	if (devattr.max_qp_rd_atom > 32)	/* arbitrary but <= 255 */
 		ep->rep_remote_cma.responder_resources = 32;
 	else
 		ep->rep_remote_cma.responder_resources = devattr.max_qp_rd_atom;
@@ -768,7 +800,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	return 0;
 
 out2:
-	err = ib_destroy_cq(ep->rep_cq);
+	err = ib_destroy_cq(sendcq);
 	if (err)
 		dprintk("RPC:       %s: ib_destroy_cq returned %i\n",
 			__func__, err);
@@ -782,11 +814,8 @@ out1:
  * Disconnect and destroy endpoint. After this, the only
  * valid operations on the ep are to free it (if dynamically
  * allocated) or re-create it.
- *
- * The caller's error handling must be sure to not leak the endpoint
- * if this function fails.
  */
-int
+void
 rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 {
 	int rc;
@@ -794,6 +823,8 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 	dprintk("RPC:       %s: entering, connected is %d\n",
 		__func__, ep->rep_connected);
 
+	cancel_delayed_work_sync(&ep->rep_connect_worker);
+
 	if (ia->ri_id->qp) {
 		rc = rpcrdma_ep_disconnect(ep, ia);
 		if (rc)
@@ -809,13 +840,17 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 		ep->rep_pad_mr = NULL;
 	}
 
-	rpcrdma_clean_cq(ep->rep_cq);
-	rc = ib_destroy_cq(ep->rep_cq);
+	rpcrdma_clean_cq(ep->rep_attr.recv_cq);
+	rc = ib_destroy_cq(ep->rep_attr.recv_cq);
 	if (rc)
 		dprintk("RPC:       %s: ib_destroy_cq returned %i\n",
 			__func__, rc);
 
-	return rc;
+	rpcrdma_clean_cq(ep->rep_attr.send_cq);
+	rc = ib_destroy_cq(ep->rep_attr.send_cq);
+	if (rc)
+		dprintk("RPC:       %s: ib_destroy_cq returned %i\n",
+			__func__, rc);
 }
 
 /*
@@ -831,17 +866,20 @@ rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 	if (ep->rep_connected != 0) {
 		struct rpcrdma_xprt *xprt;
 retry:
+		dprintk("RPC:       %s: reconnecting...\n", __func__);
 		rc = rpcrdma_ep_disconnect(ep, ia);
 		if (rc && rc != -ENOTCONN)
 			dprintk("RPC:       %s: rpcrdma_ep_disconnect"
 				" status %i\n", __func__, rc);
-		rpcrdma_clean_cq(ep->rep_cq);
+
+		rpcrdma_clean_cq(ep->rep_attr.recv_cq);
+		rpcrdma_clean_cq(ep->rep_attr.send_cq);
 
 		xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
 		id = rpcrdma_create_id(xprt, ia,
 				(struct sockaddr *)&xprt->rx_data.addr);
 		if (IS_ERR(id)) {
-			rc = PTR_ERR(id);
+			rc = -EHOSTUNREACH;
 			goto out;
 		}
 		/* TEMP TEMP TEMP - fail if new device:
@@ -855,35 +893,32 @@ retry:
 			printk("RPC:       %s: can't reconnect on "
 				"different device!\n", __func__);
 			rdma_destroy_id(id);
-			rc = -ENETDOWN;
+			rc = -ENETUNREACH;
 			goto out;
 		}
 		/* END TEMP */
+		rc = rdma_create_qp(id, ia->ri_pd, &ep->rep_attr);
+		if (rc) {
+			dprintk("RPC:       %s: rdma_create_qp failed %i\n",
+				__func__, rc);
+			rdma_destroy_id(id);
+			rc = -ENETUNREACH;
+			goto out;
+		}
 		rdma_destroy_qp(ia->ri_id);
 		rdma_destroy_id(ia->ri_id);
 		ia->ri_id = id;
+	} else {
+		dprintk("RPC:       %s: connecting...\n", __func__);
+		rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr);
+		if (rc) {
+			dprintk("RPC:       %s: rdma_create_qp failed %i\n",
+				__func__, rc);
+			/* do not update ep->rep_connected */
+			return -ENETUNREACH;
+		}
 	}
 
-	rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr);
-	if (rc) {
-		dprintk("RPC:       %s: rdma_create_qp failed %i\n",
-			__func__, rc);
-		goto out;
-	}
-
-/* XXX Tavor device performs badly with 2K MTU! */
-if (strnicmp(ia->ri_id->device->dma_device->bus->name, "pci", 3) == 0) {
-	struct pci_dev *pcid = to_pci_dev(ia->ri_id->device->dma_device);
-	if (pcid->device == PCI_DEVICE_ID_MELLANOX_TAVOR &&
-	    (pcid->vendor == PCI_VENDOR_ID_MELLANOX ||
-	     pcid->vendor == PCI_VENDOR_ID_TOPSPIN)) {
-		struct ib_qp_attr attr = {
-			.path_mtu = IB_MTU_1024
-		};
-		rc = ib_modify_qp(ia->ri_id->qp, &attr, IB_QP_PATH_MTU);
-	}
-}
-
 	ep->rep_connected = 0;
 
 	rc = rdma_connect(ia->ri_id, &ep->rep_remote_cma);
@@ -944,7 +979,8 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 {
 	int rc;
 
-	rpcrdma_clean_cq(ep->rep_cq);
+	rpcrdma_clean_cq(ep->rep_attr.recv_cq);
+	rpcrdma_clean_cq(ep->rep_attr.send_cq);
 	rc = rdma_disconnect(ia->ri_id);
 	if (!rc) {
 		/* returns without wait if not connected */
@@ -967,7 +1003,7 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 	struct rpcrdma_ia *ia, struct rpcrdma_create_data_internal *cdata)
 {
 	char *p;
-	size_t len;
+	size_t len, rlen, wlen;
 	int i, rc;
 	struct rpcrdma_mw *r;
 
@@ -997,11 +1033,6 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 		len += (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS *
 				sizeof(struct rpcrdma_mw);
 		break;
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		len += (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS *
-				sizeof(struct rpcrdma_mw);
-		break;
 	default:
 		break;
 	}
@@ -1032,32 +1063,29 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 	}
 	p += cdata->padding;
 
-	/*
-	 * Allocate the fmr's, or mw's for mw_bind chunk registration.
-	 * We "cycle" the mw's in order to minimize rkey reuse,
-	 * and also reduce unbind-to-bind collision.
-	 */
 	INIT_LIST_HEAD(&buf->rb_mws);
 	r = (struct rpcrdma_mw *)p;
 	switch (ia->ri_memreg_strategy) {
 	case RPCRDMA_FRMR:
 		for (i = buf->rb_max_requests * RPCRDMA_MAX_SEGS; i; i--) {
 			r->r.frmr.fr_mr = ib_alloc_fast_reg_mr(ia->ri_pd,
-							 RPCRDMA_MAX_SEGS);
+						ia->ri_max_frmr_depth);
 			if (IS_ERR(r->r.frmr.fr_mr)) {
 				rc = PTR_ERR(r->r.frmr.fr_mr);
 				dprintk("RPC:       %s: ib_alloc_fast_reg_mr"
 					" failed %i\n", __func__, rc);
 				goto out;
 			}
-			r->r.frmr.fr_pgl =
-				ib_alloc_fast_reg_page_list(ia->ri_id->device,
-							    RPCRDMA_MAX_SEGS);
+			r->r.frmr.fr_pgl = ib_alloc_fast_reg_page_list(
+						ia->ri_id->device,
+						ia->ri_max_frmr_depth);
 			if (IS_ERR(r->r.frmr.fr_pgl)) {
 				rc = PTR_ERR(r->r.frmr.fr_pgl);
 				dprintk("RPC:       %s: "
 					"ib_alloc_fast_reg_page_list "
 					"failed %i\n", __func__, rc);
+
+				ib_dereg_mr(r->r.frmr.fr_mr);
 				goto out;
 			}
 			list_add(&r->mw_list, &buf->rb_mws);
@@ -1082,21 +1110,6 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 			++r;
 		}
 		break;
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		/* Allocate one extra request's worth, for full cycling */
-		for (i = (buf->rb_max_requests+1) * RPCRDMA_MAX_SEGS; i; i--) {
-			r->r.mw = ib_alloc_mw(ia->ri_pd, IB_MW_TYPE_1);
-			if (IS_ERR(r->r.mw)) {
-				rc = PTR_ERR(r->r.mw);
-				dprintk("RPC:       %s: ib_alloc_mw"
-					" failed %i\n", __func__, rc);
-				goto out;
-			}
-			list_add(&r->mw_list, &buf->rb_mws);
-			++r;
-		}
-		break;
 	default:
 		break;
 	}
@@ -1105,16 +1118,16 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 	 * Allocate/init the request/reply buffers. Doing this
 	 * using kmalloc for now -- one for each buf.
 	 */
+	wlen = 1 << fls(cdata->inline_wsize + sizeof(struct rpcrdma_req));
+	rlen = 1 << fls(cdata->inline_rsize + sizeof(struct rpcrdma_rep));
+	dprintk("RPC:       %s: wlen = %zu, rlen = %zu\n",
+		__func__, wlen, rlen);
+
 	for (i = 0; i < buf->rb_max_requests; i++) {
 		struct rpcrdma_req *req;
 		struct rpcrdma_rep *rep;
 
-		len = cdata->inline_wsize + sizeof(struct rpcrdma_req);
-		/* RPC layer requests *double* size + 1K RPC_SLACK_SPACE! */
-		/* Typical ~2400b, so rounding up saves work later */
-		if (len < 4096)
-			len = 4096;
-		req = kmalloc(len, GFP_KERNEL);
+		req = kmalloc(wlen, GFP_KERNEL);
 		if (req == NULL) {
 			dprintk("RPC:       %s: request buffer %d alloc"
 				" failed\n", __func__, i);
@@ -1126,16 +1139,16 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 		buf->rb_send_bufs[i]->rl_buffer = buf;
 
 		rc = rpcrdma_register_internal(ia, req->rl_base,
-				len - offsetof(struct rpcrdma_req, rl_base),
+				wlen - offsetof(struct rpcrdma_req, rl_base),
 				&buf->rb_send_bufs[i]->rl_handle,
 				&buf->rb_send_bufs[i]->rl_iov);
 		if (rc)
 			goto out;
 
-		buf->rb_send_bufs[i]->rl_size = len-sizeof(struct rpcrdma_req);
+		buf->rb_send_bufs[i]->rl_size = wlen -
+						sizeof(struct rpcrdma_req);
 
-		len = cdata->inline_rsize + sizeof(struct rpcrdma_rep);
-		rep = kmalloc(len, GFP_KERNEL);
+		rep = kmalloc(rlen, GFP_KERNEL);
 		if (rep == NULL) {
 			dprintk("RPC:       %s: reply buffer %d alloc failed\n",
 				__func__, i);
@@ -1145,10 +1158,9 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 		memset(rep, 0, sizeof(struct rpcrdma_rep));
 		buf->rb_recv_bufs[i] = rep;
 		buf->rb_recv_bufs[i]->rr_buffer = buf;
-		init_waitqueue_head(&rep->rr_unbind);
 
 		rc = rpcrdma_register_internal(ia, rep->rr_base,
-				len - offsetof(struct rpcrdma_rep, rr_base),
+				rlen - offsetof(struct rpcrdma_rep, rr_base),
 				&buf->rb_recv_bufs[i]->rr_handle,
 				&buf->rb_recv_bufs[i]->rr_iov);
 		if (rc)
@@ -1179,7 +1191,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 
 	/* clean up in reverse order from create
 	 *   1.  recv mr memory (mr free, then kfree)
-	 *   1a. bind mw memory
 	 *   2.  send mr memory (mr free, then kfree)
 	 *   3.  padding (if any) [moved to rpcrdma_ep_destroy]
 	 *   4.  arrays
@@ -1194,41 +1205,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 			kfree(buf->rb_recv_bufs[i]);
 		}
 		if (buf->rb_send_bufs && buf->rb_send_bufs[i]) {
-			while (!list_empty(&buf->rb_mws)) {
-				r = list_entry(buf->rb_mws.next,
-					struct rpcrdma_mw, mw_list);
-				list_del(&r->mw_list);
-				switch (ia->ri_memreg_strategy) {
-				case RPCRDMA_FRMR:
-					rc = ib_dereg_mr(r->r.frmr.fr_mr);
-					if (rc)
-						dprintk("RPC:       %s:"
-							" ib_dereg_mr"
-							" failed %i\n",
-							__func__, rc);
-					ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
-					break;
-				case RPCRDMA_MTHCAFMR:
-					rc = ib_dealloc_fmr(r->r.fmr);
-					if (rc)
-						dprintk("RPC:       %s:"
-							" ib_dealloc_fmr"
-							" failed %i\n",
-							__func__, rc);
-					break;
-				case RPCRDMA_MEMWINDOWS_ASYNC:
-				case RPCRDMA_MEMWINDOWS:
-					rc = ib_dealloc_mw(r->r.mw);
-					if (rc)
-						dprintk("RPC:       %s:"
-							" ib_dealloc_mw"
-							" failed %i\n",
-							__func__, rc);
-					break;
-				default:
-					break;
-				}
-			}
 			rpcrdma_deregister_internal(ia,
 					buf->rb_send_bufs[i]->rl_handle,
 					&buf->rb_send_bufs[i]->rl_iov);
@@ -1236,6 +1212,33 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 		}
 	}
 
+	while (!list_empty(&buf->rb_mws)) {
+		r = list_entry(buf->rb_mws.next,
+			struct rpcrdma_mw, mw_list);
+		list_del(&r->mw_list);
+		switch (ia->ri_memreg_strategy) {
+		case RPCRDMA_FRMR:
+			rc = ib_dereg_mr(r->r.frmr.fr_mr);
+			if (rc)
+				dprintk("RPC:       %s:"
+					" ib_dereg_mr"
+					" failed %i\n",
+					__func__, rc);
+			ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
+			break;
+		case RPCRDMA_MTHCAFMR:
+			rc = ib_dealloc_fmr(r->r.fmr);
+			if (rc)
+				dprintk("RPC:       %s:"
+					" ib_dealloc_fmr"
+					" failed %i\n",
+					__func__, rc);
+			break;
+		default:
+			break;
+		}
+	}
+
 	kfree(buf->rb_pool);
 }
 
@@ -1299,21 +1302,17 @@ rpcrdma_buffer_put(struct rpcrdma_req *req)
 	int i;
 	unsigned long flags;
 
-	BUG_ON(req->rl_nchunks != 0);
 	spin_lock_irqsave(&buffers->rb_lock, flags);
 	buffers->rb_send_bufs[--buffers->rb_send_index] = req;
 	req->rl_niovs = 0;
 	if (req->rl_reply) {
 		buffers->rb_recv_bufs[--buffers->rb_recv_index] = req->rl_reply;
-		init_waitqueue_head(&req->rl_reply->rr_unbind);
 		req->rl_reply->rr_func = NULL;
 		req->rl_reply = NULL;
 	}
 	switch (ia->ri_memreg_strategy) {
 	case RPCRDMA_FRMR:
 	case RPCRDMA_MTHCAFMR:
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
 		/*
 		 * Cycle mw's back in reverse order, and "spin" them.
 		 * This delays and scrambles reuse as much as possible.
@@ -1358,8 +1357,7 @@ rpcrdma_recv_buffer_get(struct rpcrdma_req *req)
 
 /*
  * Put reply buffers back into pool when not attached to
- * request. This happens in error conditions, and when
- * aborting unbinds. Pre-decrement counter/array index.
+ * request. This happens in error conditions.
  */
 void
 rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep)
@@ -1498,8 +1496,8 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
 	seg1->mr_offset -= pageoff;	/* start of page */
 	seg1->mr_len += pageoff;
 	len = -pageoff;
-	if (*nsegs > RPCRDMA_MAX_DATA_SEGS)
-		*nsegs = RPCRDMA_MAX_DATA_SEGS;
+	if (*nsegs > ia->ri_max_frmr_depth)
+		*nsegs = ia->ri_max_frmr_depth;
 	for (page_no = i = 0; i < *nsegs;) {
 		rpcrdma_map_one(ia, seg, writing);
 		pa = seg->mr_dma;
@@ -1536,10 +1534,6 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
 	} else
 		post_wr = &frmr_wr;
 
-	/* Bump the key */
-	key = (u8)(seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey & 0x000000FF);
-	ib_update_fast_reg_key(seg1->mr_chunk.rl_mw->r.frmr.fr_mr, ++key);
-
 	/* Prepare FRMR WR */
 	memset(&frmr_wr, 0, sizeof frmr_wr);
 	frmr_wr.wr_id = (unsigned long)(void *)seg1->mr_chunk.rl_mw;
@@ -1550,7 +1544,16 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
 	frmr_wr.wr.fast_reg.page_list_len = page_no;
 	frmr_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
 	frmr_wr.wr.fast_reg.length = page_no << PAGE_SHIFT;
-	BUG_ON(frmr_wr.wr.fast_reg.length < len);
+	if (frmr_wr.wr.fast_reg.length < len) {
+		while (seg1->mr_nsegs--)
+			rpcrdma_unmap_one(ia, seg++);
+		return -EIO;
+	}
+
+	/* Bump the key */
+	key = (u8)(seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey & 0x000000FF);
+	ib_update_fast_reg_key(seg1->mr_chunk.rl_mw->r.frmr.fr_mr, ++key);
+
 	frmr_wr.wr.fast_reg.access_flags = (writing ?
 				IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
 				IB_ACCESS_REMOTE_READ);
@@ -1661,135 +1664,6 @@ rpcrdma_deregister_fmr_external(struct rpcrdma_mr_seg *seg,
 	return rc;
 }
 
-static int
-rpcrdma_register_memwin_external(struct rpcrdma_mr_seg *seg,
-			int *nsegs, int writing, struct rpcrdma_ia *ia,
-			struct rpcrdma_xprt *r_xprt)
-{
-	int mem_priv = (writing ? IB_ACCESS_REMOTE_WRITE :
-				  IB_ACCESS_REMOTE_READ);
-	struct ib_mw_bind param;
-	int rc;
-
-	*nsegs = 1;
-	rpcrdma_map_one(ia, seg, writing);
-	param.bind_info.mr = ia->ri_bind_mem;
-	param.wr_id = 0ULL;	/* no send cookie */
-	param.bind_info.addr = seg->mr_dma;
-	param.bind_info.length = seg->mr_len;
-	param.send_flags = 0;
-	param.bind_info.mw_access_flags = mem_priv;
-
-	DECR_CQCOUNT(&r_xprt->rx_ep);
-	rc = ib_bind_mw(ia->ri_id->qp, seg->mr_chunk.rl_mw->r.mw, &param);
-	if (rc) {
-		dprintk("RPC:       %s: failed ib_bind_mw "
-			"%u@0x%llx status %i\n",
-			__func__, seg->mr_len,
-			(unsigned long long)seg->mr_dma, rc);
-		rpcrdma_unmap_one(ia, seg);
-	} else {
-		seg->mr_rkey = seg->mr_chunk.rl_mw->r.mw->rkey;
-		seg->mr_base = param.bind_info.addr;
-		seg->mr_nsegs = 1;
-	}
-	return rc;
-}
-
-static int
-rpcrdma_deregister_memwin_external(struct rpcrdma_mr_seg *seg,
-			struct rpcrdma_ia *ia,
-			struct rpcrdma_xprt *r_xprt, void **r)
-{
-	struct ib_mw_bind param;
-	LIST_HEAD(l);
-	int rc;
-
-	BUG_ON(seg->mr_nsegs != 1);
-	param.bind_info.mr = ia->ri_bind_mem;
-	param.bind_info.addr = 0ULL;	/* unbind */
-	param.bind_info.length = 0;
-	param.bind_info.mw_access_flags = 0;
-	if (*r) {
-		param.wr_id = (u64) (unsigned long) *r;
-		param.send_flags = IB_SEND_SIGNALED;
-		INIT_CQCOUNT(&r_xprt->rx_ep);
-	} else {
-		param.wr_id = 0ULL;
-		param.send_flags = 0;
-		DECR_CQCOUNT(&r_xprt->rx_ep);
-	}
-	rc = ib_bind_mw(ia->ri_id->qp, seg->mr_chunk.rl_mw->r.mw, &param);
-	rpcrdma_unmap_one(ia, seg);
-	if (rc)
-		dprintk("RPC:       %s: failed ib_(un)bind_mw,"
-			" status %i\n", __func__, rc);
-	else
-		*r = NULL;	/* will upcall on completion */
-	return rc;
-}
-
-static int
-rpcrdma_register_default_external(struct rpcrdma_mr_seg *seg,
-			int *nsegs, int writing, struct rpcrdma_ia *ia)
-{
-	int mem_priv = (writing ? IB_ACCESS_REMOTE_WRITE :
-				  IB_ACCESS_REMOTE_READ);
-	struct rpcrdma_mr_seg *seg1 = seg;
-	struct ib_phys_buf ipb[RPCRDMA_MAX_DATA_SEGS];
-	int len, i, rc = 0;
-
-	if (*nsegs > RPCRDMA_MAX_DATA_SEGS)
-		*nsegs = RPCRDMA_MAX_DATA_SEGS;
-	for (len = 0, i = 0; i < *nsegs;) {
-		rpcrdma_map_one(ia, seg, writing);
-		ipb[i].addr = seg->mr_dma;
-		ipb[i].size = seg->mr_len;
-		len += seg->mr_len;
-		++seg;
-		++i;
-		/* Check for holes */
-		if ((i < *nsegs && offset_in_page(seg->mr_offset)) ||
-		    offset_in_page((seg-1)->mr_offset+(seg-1)->mr_len))
-			break;
-	}
-	seg1->mr_base = seg1->mr_dma;
-	seg1->mr_chunk.rl_mr = ib_reg_phys_mr(ia->ri_pd,
-				ipb, i, mem_priv, &seg1->mr_base);
-	if (IS_ERR(seg1->mr_chunk.rl_mr)) {
-		rc = PTR_ERR(seg1->mr_chunk.rl_mr);
-		dprintk("RPC:       %s: failed ib_reg_phys_mr "
-			"%u@0x%llx (%d)... status %i\n",
-			__func__, len,
-			(unsigned long long)seg1->mr_dma, i, rc);
-		while (i--)
-			rpcrdma_unmap_one(ia, --seg);
-	} else {
-		seg1->mr_rkey = seg1->mr_chunk.rl_mr->rkey;
-		seg1->mr_nsegs = i;
-		seg1->mr_len = len;
-	}
-	*nsegs = i;
-	return rc;
-}
-
-static int
-rpcrdma_deregister_default_external(struct rpcrdma_mr_seg *seg,
-			struct rpcrdma_ia *ia)
-{
-	struct rpcrdma_mr_seg *seg1 = seg;
-	int rc;
-
-	rc = ib_dereg_mr(seg1->mr_chunk.rl_mr);
-	seg1->mr_chunk.rl_mr = NULL;
-	while (seg1->mr_nsegs--)
-		rpcrdma_unmap_one(ia, seg++);
-	if (rc)
-		dprintk("RPC:       %s: failed ib_dereg_mr,"
-			" status %i\n", __func__, rc);
-	return rc;
-}
-
 int
 rpcrdma_register_external(struct rpcrdma_mr_seg *seg,
 			int nsegs, int writing, struct rpcrdma_xprt *r_xprt)
@@ -1819,16 +1693,8 @@ rpcrdma_register_external(struct rpcrdma_mr_seg *seg,
 		rc = rpcrdma_register_fmr_external(seg, &nsegs, writing, ia);
 		break;
 
-	/* Registration using memory windows */
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		rc = rpcrdma_register_memwin_external(seg, &nsegs, writing, ia, r_xprt);
-		break;
-
-	/* Default registration each time */
 	default:
-		rc = rpcrdma_register_default_external(seg, &nsegs, writing, ia);
-		break;
+		return -1;
 	}
 	if (rc)
 		return -1;
@@ -1838,7 +1704,7 @@ rpcrdma_register_external(struct rpcrdma_mr_seg *seg,
 
 int
 rpcrdma_deregister_external(struct rpcrdma_mr_seg *seg,
-		struct rpcrdma_xprt *r_xprt, void *r)
+		struct rpcrdma_xprt *r_xprt)
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	int nsegs = seg->mr_nsegs, rc;
@@ -1847,9 +1713,7 @@ rpcrdma_deregister_external(struct rpcrdma_mr_seg *seg,
 
 #if RPCRDMA_PERSISTENT_REGISTRATION
 	case RPCRDMA_ALLPHYSICAL:
-		BUG_ON(nsegs != 1);
 		rpcrdma_unmap_one(ia, seg);
-		rc = 0;
 		break;
 #endif
 
@@ -1861,21 +1725,9 @@ rpcrdma_deregister_external(struct rpcrdma_mr_seg *seg,
 		rc = rpcrdma_deregister_fmr_external(seg, ia);
 		break;
 
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		rc = rpcrdma_deregister_memwin_external(seg, ia, r_xprt, &r);
-		break;
-
 	default:
-		rc = rpcrdma_deregister_default_external(seg, ia);
 		break;
 	}
-	if (r) {
-		struct rpcrdma_rep *rep = r;
-		void (*func)(struct rpcrdma_rep *) = rep->rr_func;
-		rep->rr_func = NULL;
-		func(rep);	/* dereg done, callback now */
-	}
 	return nsegs;
 }
 
@@ -1950,7 +1802,6 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia,
 	ib_dma_sync_single_for_cpu(ia->ri_id->device,
 		rep->rr_iov.addr, rep->rr_iov.length, DMA_BIDIRECTIONAL);
 
-	DECR_CQCOUNT(ep);
 	rc = ib_post_recv(ia->ri_id->qp, &recv_wr, &recv_wr_fail);
 
 	if (rc)
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index cc1445dc1d1..89e7cd47970 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -43,6 +43,7 @@
 #include <linux/wait.h> 		/* wait_queue_head_t, etc */
 #include <linux/spinlock.h> 		/* spinlock_t, etc */
 #include <linux/atomic.h>			/* atomic_t, etc */
+#include <linux/workqueue.h>		/* struct work_struct */
 
 #include <rdma/rdma_cm.h>		/* RDMA connection api */
 #include <rdma/ib_verbs.h>		/* RDMA verbs api */
@@ -66,18 +67,21 @@ struct rpcrdma_ia {
 	struct completion	ri_done;
 	int			ri_async_rc;
 	enum rpcrdma_memreg	ri_memreg_strategy;
+	unsigned int		ri_max_frmr_depth;
 };
 
 /*
  * RDMA Endpoint -- one per transport instance
  */
 
+#define RPCRDMA_WC_BUDGET	(128)
+#define RPCRDMA_POLLSIZE	(16)
+
 struct rpcrdma_ep {
 	atomic_t		rep_cqcount;
 	int			rep_cqinit;
 	int			rep_connected;
 	struct rpcrdma_ia	*rep_ia;
-	struct ib_cq		*rep_cq;
 	struct ib_qp_init_attr	rep_attr;
 	wait_queue_head_t 	rep_connect_wait;
 	struct ib_sge		rep_pad;	/* holds zeroed pad */
@@ -86,6 +90,9 @@ struct rpcrdma_ep {
 	struct rpc_xprt		*rep_xprt;	/* for rep_func */
 	struct rdma_conn_param	rep_remote_cma;
 	struct sockaddr_storage	rep_remote_addr;
+	struct delayed_work	rep_connect_worker;
+	struct ib_wc		rep_send_wcs[RPCRDMA_POLLSIZE];
+	struct ib_wc		rep_recv_wcs[RPCRDMA_POLLSIZE];
 };
 
 #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit)
@@ -124,7 +131,6 @@ struct rpcrdma_rep {
 	struct rpc_xprt	*rr_xprt;	/* needed for request/reply matching */
 	void (*rr_func)(struct rpcrdma_rep *);/* called by tasklet in softint */
 	struct list_head rr_list;	/* tasklet list */
-	wait_queue_head_t rr_unbind;	/* optional unbind wait */
 	struct ib_sge	rr_iov;		/* for posting */
 	struct ib_mr	*rr_handle;	/* handle for mem in rr_iov */
 	char	rr_base[MAX_RPCRDMAHDR]; /* minimal inline receive buffer */
@@ -159,7 +165,6 @@ struct rpcrdma_mr_seg {		/* chunk descriptors */
 		struct ib_mr	*rl_mr;		/* if registered directly */
 		struct rpcrdma_mw {		/* if registered from region */
 			union {
-				struct ib_mw	*mw;
 				struct ib_fmr	*fmr;
 				struct {
 					struct ib_fast_reg_page_list *fr_pgl;
@@ -207,7 +212,6 @@ struct rpcrdma_req {
 struct rpcrdma_buffer {
 	spinlock_t	rb_lock;	/* protects indexes */
 	atomic_t	rb_credits;	/* most recent server credits */
-	unsigned long	rb_cwndscale;	/* cached framework rpc_cwndscale */
 	int		rb_max_requests;/* client max requests */
 	struct list_head rb_mws;	/* optional memory windows/fmrs/frmrs */
 	int		rb_send_index;
@@ -300,7 +304,7 @@ void rpcrdma_ia_close(struct rpcrdma_ia *);
  */
 int rpcrdma_ep_create(struct rpcrdma_ep *, struct rpcrdma_ia *,
 				struct rpcrdma_create_data_internal *);
-int rpcrdma_ep_destroy(struct rpcrdma_ep *, struct rpcrdma_ia *);
+void rpcrdma_ep_destroy(struct rpcrdma_ep *, struct rpcrdma_ia *);
 int rpcrdma_ep_connect(struct rpcrdma_ep *, struct rpcrdma_ia *);
 int rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *);
 
@@ -330,11 +334,12 @@ int rpcrdma_deregister_internal(struct rpcrdma_ia *,
 int rpcrdma_register_external(struct rpcrdma_mr_seg *,
 				int, int, struct rpcrdma_xprt *);
 int rpcrdma_deregister_external(struct rpcrdma_mr_seg *,
-				struct rpcrdma_xprt *, void *);
+				struct rpcrdma_xprt *);
 
 /*
  * RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c
  */
+void rpcrdma_connect_worker(struct work_struct *);
 void rpcrdma_conn_func(struct rpcrdma_ep *);
 void rpcrdma_reply_handler(struct rpcrdma_rep *);
 
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index dd9d295813c..be8bbd5d65e 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -254,9 +254,10 @@ struct sock_xprt {
 	/*
 	 * Saved socket callback addresses
 	 */
-	void			(*old_data_ready)(struct sock *, int);
+	void			(*old_data_ready)(struct sock *);
 	void			(*old_state_change)(struct sock *);
 	void			(*old_write_space)(struct sock *);
+	void			(*old_error_report)(struct sock *);
 };
 
 /*
@@ -274,6 +275,11 @@ struct sock_xprt {
  */
 #define TCP_RPC_REPLY		(1UL << 6)
 
+static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
+{
+	return (struct rpc_xprt *) sk->sk_user_data;
+}
+
 static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt)
 {
 	return (struct sockaddr *) &xprt->addr;
@@ -504,6 +510,7 @@ static int xs_nospace(struct rpc_task *task)
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+	struct sock *sk = transport->inet;
 	int ret = -EAGAIN;
 
 	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
@@ -521,7 +528,7 @@ static int xs_nospace(struct rpc_task *task)
 			 * window size
 			 */
 			set_bit(SOCK_NOSPACE, &transport->sock->flags);
-			transport->inet->sk_write_pending++;
+			sk->sk_write_pending++;
 			/* ...and wait for more buffer space */
 			xprt_wait_for_buffer_space(task, xs_nospace_callback);
 		}
@@ -531,6 +538,9 @@ static int xs_nospace(struct rpc_task *task)
 	}
 
 	spin_unlock_bh(&xprt->transport_lock);
+
+	/* Race breaker in case memory is freed before above code is called */
+	sk->sk_write_space(sk);
 	return ret;
 }
 
@@ -799,6 +809,7 @@ static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk)
 	transport->old_data_ready = sk->sk_data_ready;
 	transport->old_state_change = sk->sk_state_change;
 	transport->old_write_space = sk->sk_write_space;
+	transport->old_error_report = sk->sk_error_report;
 }
 
 static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk)
@@ -806,6 +817,34 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s
 	sk->sk_data_ready = transport->old_data_ready;
 	sk->sk_state_change = transport->old_state_change;
 	sk->sk_write_space = transport->old_write_space;
+	sk->sk_error_report = transport->old_error_report;
+}
+
+/**
+ * xs_error_report - callback to handle TCP socket state errors
+ * @sk: socket
+ *
+ * Note: we don't call sock_error() since there may be a rpc_task
+ * using the socket, and so we don't want to clear sk->sk_err.
+ */
+static void xs_error_report(struct sock *sk)
+{
+	struct rpc_xprt *xprt;
+	int err;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	if (!(xprt = xprt_from_sock(sk)))
+		goto out;
+
+	err = -sk->sk_err;
+	if (err == 0)
+		goto out;
+	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
+			xprt, -err);
+	trace_rpc_socket_error(xprt, sk->sk_socket, err);
+	xprt_wake_pending_tasks(xprt, err);
+ out:
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 static void xs_reset_transport(struct sock_xprt *transport)
@@ -827,8 +866,6 @@ static void xs_reset_transport(struct sock_xprt *transport)
 	xs_restore_old_callbacks(transport, sk);
 	write_unlock_bh(&sk->sk_callback_lock);
 
-	sk->sk_no_check = 0;
-
 	trace_rpc_socket_close(&transport->xprt, sock);
 	sock_release(sock);
 }
@@ -854,11 +891,11 @@ static void xs_close(struct rpc_xprt *xprt)
 	xs_reset_transport(transport);
 	xprt->reestablish_timeout = 0;
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
 	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	clear_bit(XPRT_CLOSING, &xprt->state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	xprt_disconnect_done(xprt);
 }
 
@@ -870,6 +907,12 @@ static void xs_tcp_close(struct rpc_xprt *xprt)
 		xs_tcp_shutdown(xprt);
 }
 
+static void xs_xprt_free(struct rpc_xprt *xprt)
+{
+	xs_free_peer_addresses(xprt);
+	xprt_free(xprt);
+}
+
 /**
  * xs_destroy - prepare to shutdown a transport
  * @xprt: doomed transport
@@ -880,16 +923,10 @@ static void xs_destroy(struct rpc_xprt *xprt)
 	dprintk("RPC:       xs_destroy xprt %p\n", xprt);
 
 	xs_close(xprt);
-	xs_free_peer_addresses(xprt);
-	xprt_free(xprt);
+	xs_xprt_free(xprt);
 	module_put(THIS_MODULE);
 }
 
-static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
-{
-	return (struct rpc_xprt *) sk->sk_user_data;
-}
-
 static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
 {
 	struct xdr_skb_reader desc = {
@@ -912,7 +949,7 @@ static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
  *
  * Currently this assumes we can read the whole reply in a single gulp.
  */
-static void xs_local_data_ready(struct sock *sk, int len)
+static void xs_local_data_ready(struct sock *sk)
 {
 	struct rpc_task *task;
 	struct rpc_xprt *xprt;
@@ -975,7 +1012,7 @@ static void xs_local_data_ready(struct sock *sk, int len)
  * @len: how much data to read
  *
  */
-static void xs_udp_data_ready(struct sock *sk, int len)
+static void xs_udp_data_ready(struct sock *sk)
 {
 	struct rpc_task *task;
 	struct rpc_xprt *xprt;
@@ -1272,41 +1309,29 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt,
  * If we're unable to obtain the rpc_rqst we schedule the closing of the
  * connection and return -1.
  */
-static inline int xs_tcp_read_callback(struct rpc_xprt *xprt,
+static int xs_tcp_read_callback(struct rpc_xprt *xprt,
 				       struct xdr_skb_reader *desc)
 {
 	struct sock_xprt *transport =
 				container_of(xprt, struct sock_xprt, xprt);
 	struct rpc_rqst *req;
 
-	req = xprt_alloc_bc_request(xprt);
+	/* Look up and lock the request corresponding to the given XID */
+	spin_lock(&xprt->transport_lock);
+	req = xprt_lookup_bc_request(xprt, transport->tcp_xid);
 	if (req == NULL) {
+		spin_unlock(&xprt->transport_lock);
 		printk(KERN_WARNING "Callback slot table overflowed\n");
 		xprt_force_disconnect(xprt);
 		return -1;
 	}
 
-	req->rq_xid = transport->tcp_xid;
 	dprintk("RPC:       read callback  XID %08x\n", ntohl(req->rq_xid));
 	xs_tcp_read_common(xprt, desc, req);
 
-	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) {
-		struct svc_serv *bc_serv = xprt->bc_serv;
-
-		/*
-		 * Add callback request to callback list.  The callback
-		 * service sleeps on the sv_cb_waitq waiting for new
-		 * requests.  Wake it up after adding enqueing the
-		 * request.
-		 */
-		dprintk("RPC:       add callback request to list\n");
-		spin_lock(&bc_serv->sv_cb_lock);
-		list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
-		spin_unlock(&bc_serv->sv_cb_lock);
-		wake_up(&bc_serv->sv_cb_waitq);
-	}
-
-	req->rq_private_buf.len = transport->tcp_copied;
+	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
+		xprt_complete_bc_request(req, transport->tcp_copied);
+	spin_unlock(&xprt->transport_lock);
 
 	return 0;
 }
@@ -1410,7 +1435,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns
  * @bytes: how much data to read
  *
  */
-static void xs_tcp_data_ready(struct sock *sk, int bytes)
+static void xs_tcp_data_ready(struct sock *sk)
 {
 	struct rpc_xprt *xprt;
 	read_descriptor_t rd_desc;
@@ -1470,12 +1495,12 @@ static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt)
 
 static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
 	clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
 	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	clear_bit(XPRT_CLOSING, &xprt->state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static void xs_sock_mark_closed(struct rpc_xprt *xprt)
@@ -1529,10 +1554,10 @@ static void xs_tcp_state_change(struct sock *sk)
 		xprt->connect_cookie++;
 		xprt->reestablish_timeout = 0;
 		set_bit(XPRT_CLOSING, &xprt->state);
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(XPRT_CONNECTED, &xprt->state);
 		clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
 		break;
 	case TCP_CLOSE_WAIT:
@@ -1551,9 +1576,9 @@ static void xs_tcp_state_change(struct sock *sk)
 	case TCP_LAST_ACK:
 		set_bit(XPRT_CLOSING, &xprt->state);
 		xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(XPRT_CONNECTED, &xprt->state);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		break;
 	case TCP_CLOSE:
 		xs_tcp_cancel_linger_timeout(xprt);
@@ -1674,7 +1699,7 @@ static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task)
 static unsigned short xs_get_random_port(void)
 {
 	unsigned short range = xprt_max_resvport - xprt_min_resvport;
-	unsigned short rand = (unsigned short) net_random() % range;
+	unsigned short rand = (unsigned short) prandom_u32() % range;
 	return rand + xprt_min_resvport;
 }
 
@@ -1869,6 +1894,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt,
 		sk->sk_user_data = xprt;
 		sk->sk_data_ready = xs_local_data_ready;
 		sk->sk_write_space = xs_udp_write_space;
+		sk->sk_error_report = xs_error_report;
 		sk->sk_allocation = GFP_ATOMIC;
 
 		xprt_clear_connected(xprt);
@@ -2018,7 +2044,6 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		sk->sk_user_data = xprt;
 		sk->sk_data_ready = xs_udp_data_ready;
 		sk->sk_write_space = xs_udp_write_space;
-		sk->sk_no_check = UDP_CSUM_NORCV;
 		sk->sk_allocation = GFP_ATOMIC;
 
 		xprt_set_connected(xprt);
@@ -2146,6 +2171,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		sk->sk_data_ready = xs_tcp_data_ready;
 		sk->sk_state_change = xs_tcp_state_change;
 		sk->sk_write_space = xs_tcp_write_space;
+		sk->sk_error_report = xs_error_report;
 		sk->sk_allocation = GFP_ATOMIC;
 
 		/* socket options */
@@ -2508,6 +2534,10 @@ static void bc_close(struct rpc_xprt *xprt)
 
 static void bc_destroy(struct rpc_xprt *xprt)
 {
+	dprintk("RPC:       bc_destroy xprt %p\n", xprt);
+
+	xs_xprt_free(xprt);
+	module_put(THIS_MODULE);
 }
 
 static struct rpc_xprt_ops xs_local_ops = {
@@ -2708,7 +2738,7 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args)
 		return xprt;
 	ret = ERR_PTR(-EINVAL);
 out_err:
-	xprt_free(xprt);
+	xs_xprt_free(xprt);
 	return ret;
 }
 
@@ -2786,7 +2816,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args)
 		return xprt;
 	ret = ERR_PTR(-EINVAL);
 out_err:
-	xprt_free(xprt);
+	xs_xprt_free(xprt);
 	return ret;
 }
 
@@ -2861,12 +2891,11 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
 				xprt->address_strings[RPC_DISPLAY_ADDR],
 				xprt->address_strings[RPC_DISPLAY_PROTO]);
 
-
 	if (try_module_get(THIS_MODULE))
 		return xprt;
 	ret = ERR_PTR(-EINVAL);
 out_err:
-	xprt_free(xprt);
+	xs_xprt_free(xprt);
 	return ret;
 }
 
@@ -2883,15 +2912,6 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 	struct svc_sock *bc_sock;
 	struct rpc_xprt *ret;
 
-	if (args->bc_xprt->xpt_bc_xprt) {
-		/*
-		 * This server connection already has a backchannel
-		 * transport; we can't create a new one, as we wouldn't
-		 * be able to match replies based on xid any more.  So,
-		 * reuse the already-existing one:
-		 */
-		 return args->bc_xprt->xpt_bc_xprt;
-	}
 	xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries,
 			xprt_tcp_slot_table_entries);
 	if (IS_ERR(xprt))
@@ -2932,10 +2952,9 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 
 	/*
 	 * Once we've associated a backchannel xprt with a connection,
-	 * we want to keep it around as long as long as the connection
-	 * lasts, in case we need to start using it for a backchannel
-	 * again; this reference won't be dropped until bc_xprt is
-	 * destroyed.
+	 * we want to keep it around as long as the connection lasts,
+	 * in case we need to start using it for a backchannel again;
+	 * this reference won't be dropped until bc_xprt is destroyed.
 	 */
 	xprt_get(xprt);
 	args->bc_xprt->xpt_bc_xprt = xprt;
@@ -2950,13 +2969,14 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 	 */
 	xprt_set_connected(xprt);
 
-
 	if (try_module_get(THIS_MODULE))
 		return xprt;
+
+	args->bc_xprt->xpt_bc_xprt = NULL;
 	xprt_put(xprt);
 	ret = ERR_PTR(-EINVAL);
 out_err:
-	xprt_free(xprt);
+	xs_xprt_free(xprt);
 	return ret;
 }
 
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index b282f7130d2..a080c66d819 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_TIPC) := tipc.o
 
 tipc-y	+= addr.o bcast.o bearer.o config.o \
-	   core.o handler.o link.o discover.o msg.o  \
+	   core.o link.o discover.o msg.o  \
 	   name_distr.o  subscr.o name_table.o net.o  \
 	   netlink.o node.o node_subscr.o port.o ref.o  \
 	   socket.o log.o eth_media.o server.o
diff --git a/net/tipc/addr.h b/net/tipc/addr.h
index 60b00ab93d7..a74acf9ee80 100644
--- a/net/tipc/addr.h
+++ b/net/tipc/addr.h
@@ -37,6 +37,8 @@
 #ifndef _TIPC_ADDR_H
 #define _TIPC_ADDR_H
 
+#include "core.h"
+
 #define TIPC_ZONE_MASK		0xff000000u
 #define TIPC_CLUSTER_MASK	0xfffff000u
 
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 4c2a80b3c01..55c6c9d3e1c 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -41,9 +41,9 @@
 #include "bcast.h"
 #include "name_distr.h"
 
-#define MAX_PKT_DEFAULT_MCAST 1500	/* bcast link max packet size (fixed) */
-
-#define BCLINK_WIN_DEFAULT 20		/* bcast link window size (default) */
+#define	MAX_PKT_DEFAULT_MCAST	1500	/* bcast link max packet size (fixed) */
+#define	BCLINK_WIN_DEFAULT	20	/* bcast link window size (default) */
+#define	BCBEARER		MAX_BEARERS
 
 /**
  * struct tipc_bcbearer_pair - a pair of bearers used by broadcast link
@@ -71,7 +71,7 @@ struct tipc_bcbearer_pair {
  * Note: The fields labelled "temporary" are incorporated into the bearer
  * to avoid consuming potentially limited stack space through the use of
  * large local variables within multicast routines.  Concurrent access is
- * prevented through use of the spinlock "bc_lock".
+ * prevented through use of the spinlock "bclink_lock".
  */
 struct tipc_bcbearer {
 	struct tipc_bearer bearer;
@@ -84,34 +84,64 @@ struct tipc_bcbearer {
 
 /**
  * struct tipc_bclink - link used for broadcast messages
+ * @lock: spinlock governing access to structure
  * @link: (non-standard) broadcast link structure
  * @node: (non-standard) node structure representing b'cast link's peer node
+ * @flags: represent bclink states
  * @bcast_nodes: map of broadcast-capable nodes
  * @retransmit_to: node that most recently requested a retransmit
  *
  * Handles sequence numbering, fragmentation, bundling, etc.
  */
 struct tipc_bclink {
+	spinlock_t lock;
 	struct tipc_link link;
 	struct tipc_node node;
+	unsigned int flags;
 	struct tipc_node_map bcast_nodes;
 	struct tipc_node *retransmit_to;
 };
 
-static struct tipc_bcbearer bcast_bearer;
-static struct tipc_bclink bcast_link;
-
-static struct tipc_bcbearer *bcbearer = &bcast_bearer;
-static struct tipc_bclink *bclink = &bcast_link;
-static struct tipc_link *bcl = &bcast_link.link;
-
-static DEFINE_SPINLOCK(bc_lock);
+static struct tipc_bcbearer *bcbearer;
+static struct tipc_bclink *bclink;
+static struct tipc_link *bcl;
 
 const char tipc_bclink_name[] = "broadcast-link";
 
 static void tipc_nmap_diff(struct tipc_node_map *nm_a,
 			   struct tipc_node_map *nm_b,
 			   struct tipc_node_map *nm_diff);
+static void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node);
+static void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node);
+
+static void tipc_bclink_lock(void)
+{
+	spin_lock_bh(&bclink->lock);
+}
+
+static void tipc_bclink_unlock(void)
+{
+	struct tipc_node *node = NULL;
+
+	if (likely(!bclink->flags)) {
+		spin_unlock_bh(&bclink->lock);
+		return;
+	}
+
+	if (bclink->flags & TIPC_BCLINK_RESET) {
+		bclink->flags &= ~TIPC_BCLINK_RESET;
+		node = tipc_bclink_retransmit_to();
+	}
+	spin_unlock_bh(&bclink->lock);
+
+	if (node)
+		tipc_link_reset_all(node);
+}
+
+void tipc_bclink_set_flags(unsigned int flags)
+{
+	bclink->flags |= flags;
+}
 
 static u32 bcbuf_acks(struct sk_buff *buf)
 {
@@ -130,16 +160,16 @@ static void bcbuf_decr_acks(struct sk_buff *buf)
 
 void tipc_bclink_add_node(u32 addr)
 {
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 	tipc_nmap_add(&bclink->bcast_nodes, addr);
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 }
 
 void tipc_bclink_remove_node(u32 addr)
 {
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 	tipc_nmap_remove(&bclink->bcast_nodes, addr);
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 }
 
 static void bclink_set_last_sent(void)
@@ -165,7 +195,7 @@ static void bclink_update_last_sent(struct tipc_node *node, u32 seqno)
 /**
  * tipc_bclink_retransmit_to - get most recent node to request retransmission
  *
- * Called with bc_lock locked
+ * Called with bclink_lock locked
  */
 struct tipc_node *tipc_bclink_retransmit_to(void)
 {
@@ -177,7 +207,7 @@ struct tipc_node *tipc_bclink_retransmit_to(void)
  * @after: sequence number of last packet to *not* retransmit
  * @to: sequence number of last packet to retransmit
  *
- * Called with bc_lock locked
+ * Called with bclink_lock locked
  */
 static void bclink_retransmit_pkt(u32 after, u32 to)
 {
@@ -194,7 +224,7 @@ static void bclink_retransmit_pkt(u32 after, u32 to)
  * @n_ptr: node that sent acknowledgement info
  * @acked: broadcast sequence # that has been acknowledged
  *
- * Node is locked, bc_lock unlocked.
+ * Node is locked, bclink_lock unlocked.
  */
 void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
 {
@@ -202,8 +232,7 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
 	struct sk_buff *next;
 	unsigned int released = 0;
 
-	spin_lock_bh(&bc_lock);
-
+	tipc_bclink_lock();
 	/* Bail out if tx queue is empty (no clean up is required) */
 	crs = bcl->first_out;
 	if (!crs)
@@ -267,13 +296,13 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
 	if (unlikely(released && !list_empty(&bcl->waiting_ports)))
 		tipc_link_wakeup_ports(bcl, 0);
 exit:
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 }
 
 /**
  * tipc_bclink_update_link_state - update broadcast link state
  *
- * tipc_net_lock and node lock set
+ * RCU and node lock set
  */
 void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent)
 {
@@ -320,10 +349,10 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent)
 				 ? buf_seqno(n_ptr->bclink.deferred_head) - 1
 				 : n_ptr->bclink.last_sent);
 
-		spin_lock_bh(&bc_lock);
-		tipc_bearer_send(&bcbearer->bearer, buf, NULL);
+		tipc_bclink_lock();
+		tipc_bearer_send(MAX_BEARERS, buf, NULL);
 		bcl->stats.sent_nacks++;
-		spin_unlock_bh(&bc_lock);
+		tipc_bclink_unlock();
 		kfree_skb(buf);
 
 		n_ptr->bclink.oos_state++;
@@ -335,8 +364,6 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent)
  *
  * Delay any upcoming NACK by this node if another node has already
  * requested the first message this node is going to ask for.
- *
- * Only tipc_net_lock set.
  */
 static void bclink_peek_nack(struct tipc_msg *msg)
 {
@@ -356,13 +383,13 @@ static void bclink_peek_nack(struct tipc_msg *msg)
 }
 
 /*
- * tipc_bclink_send_msg - broadcast a packet to all nodes in cluster
+ * tipc_bclink_xmit - broadcast a packet to all nodes in cluster
  */
-int tipc_bclink_send_msg(struct sk_buff *buf)
+int tipc_bclink_xmit(struct sk_buff *buf)
 {
 	int res;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 
 	if (!bclink->bcast_nodes.count) {
 		res = msg_data_sz(buf_msg(buf));
@@ -370,21 +397,21 @@ int tipc_bclink_send_msg(struct sk_buff *buf)
 		goto exit;
 	}
 
-	res = tipc_link_send_buf(bcl, buf);
+	res = __tipc_link_xmit(bcl, buf);
 	if (likely(res >= 0)) {
 		bclink_set_last_sent();
 		bcl->stats.queue_sz_counts++;
 		bcl->stats.accu_queue_sz += bcl->out_queue_size;
 	}
 exit:
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 	return res;
 }
 
 /**
  * bclink_accept_pkt - accept an incoming, in-sequence broadcast packet
  *
- * Called with both sending node's lock and bc_lock taken.
+ * Called with both sending node's lock and bclink_lock taken.
  */
 static void bclink_accept_pkt(struct tipc_node *node, u32 seqno)
 {
@@ -399,19 +426,18 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno)
 	 */
 
 	if (((seqno - tipc_own_addr) % TIPC_MIN_LINK_WIN) == 0) {
-		tipc_link_send_proto_msg(
-			node->active_links[node->addr & 1],
-			STATE_MSG, 0, 0, 0, 0, 0);
+		tipc_link_proto_xmit(node->active_links[node->addr & 1],
+				     STATE_MSG, 0, 0, 0, 0, 0);
 		bcl->stats.sent_acks++;
 	}
 }
 
 /**
- * tipc_bclink_recv_pkt - receive a broadcast packet, and deliver upwards
+ * tipc_bclink_rcv - receive a broadcast packet, and deliver upwards
  *
- * tipc_net_lock is read_locked, no other locks set
+ * RCU is locked, no other locks set
  */
-void tipc_bclink_recv_pkt(struct sk_buff *buf)
+void tipc_bclink_rcv(struct sk_buff *buf)
 {
 	struct tipc_msg *msg = buf_msg(buf);
 	struct tipc_node *node;
@@ -440,12 +466,12 @@ void tipc_bclink_recv_pkt(struct sk_buff *buf)
 		if (msg_destnode(msg) == tipc_own_addr) {
 			tipc_bclink_acknowledge(node, msg_bcast_ack(msg));
 			tipc_node_unlock(node);
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bcl->stats.recv_nacks++;
 			bclink->retransmit_to = node;
 			bclink_retransmit_pkt(msg_bcgap_after(msg),
 					      msg_bcgap_to(msg));
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 		} else {
 			tipc_node_unlock(node);
 			bclink_peek_nack(msg);
@@ -463,51 +489,47 @@ receive:
 		/* Deliver message to destination */
 
 		if (likely(msg_isdata(msg))) {
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bclink_accept_pkt(node, seqno);
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 			tipc_node_unlock(node);
 			if (likely(msg_mcast(msg)))
-				tipc_port_recv_mcast(buf, NULL);
+				tipc_port_mcast_rcv(buf, NULL);
 			else
 				kfree_skb(buf);
 		} else if (msg_user(msg) == MSG_BUNDLER) {
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bclink_accept_pkt(node, seqno);
 			bcl->stats.recv_bundles++;
 			bcl->stats.recv_bundled += msg_msgcnt(msg);
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 			tipc_node_unlock(node);
-			tipc_link_recv_bundle(buf);
+			tipc_link_bundle_rcv(buf);
 		} else if (msg_user(msg) == MSG_FRAGMENTER) {
-			int ret;
-			ret = tipc_link_recv_fragment(&node->bclink.reasm_head,
-						      &node->bclink.reasm_tail,
-						      &buf);
-			if (ret == LINK_REASM_ERROR)
+			tipc_buf_append(&node->bclink.reasm_buf, &buf);
+			if (unlikely(!buf && !node->bclink.reasm_buf))
 				goto unlock;
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bclink_accept_pkt(node, seqno);
 			bcl->stats.recv_fragments++;
-			if (ret == LINK_REASM_COMPLETE) {
+			if (buf) {
 				bcl->stats.recv_fragmented++;
-				/* Point msg to inner header */
 				msg = buf_msg(buf);
-				spin_unlock_bh(&bc_lock);
+				tipc_bclink_unlock();
 				goto receive;
 			}
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 			tipc_node_unlock(node);
 		} else if (msg_user(msg) == NAME_DISTRIBUTOR) {
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bclink_accept_pkt(node, seqno);
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 			tipc_node_unlock(node);
-			tipc_named_recv(buf);
+			tipc_named_rcv(buf);
 		} else {
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bclink_accept_pkt(node, seqno);
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 			tipc_node_unlock(node);
 			kfree_skb(buf);
 		}
@@ -537,6 +559,7 @@ receive:
 
 		buf = node->bclink.deferred_head;
 		node->bclink.deferred_head = buf->next;
+		buf->next = NULL;
 		node->bclink.deferred_size--;
 		goto receive;
 	}
@@ -553,14 +576,14 @@ receive:
 	} else
 		deferred = 0;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 
 	if (deferred)
 		bcl->stats.deferred_recv++;
 	else
 		bcl->stats.duplicates++;
 
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 
 unlock:
 	tipc_node_unlock(node);
@@ -628,13 +651,13 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1,
 
 		if (bp_index == 0) {
 			/* Use original buffer for first bearer */
-			tipc_bearer_send(b, buf, &b->bcast_addr);
+			tipc_bearer_send(b->identity, buf, &b->bcast_addr);
 		} else {
 			/* Avoid concurrent buffer access */
-			tbuf = pskb_copy(buf, GFP_ATOMIC);
+			tbuf = pskb_copy_for_clone(buf, GFP_ATOMIC);
 			if (!tbuf)
 				break;
-			tipc_bearer_send(b, tbuf, &b->bcast_addr);
+			tipc_bearer_send(b->identity, tbuf, &b->bcast_addr);
 			kfree_skb(tbuf); /* Bearer keeps a clone */
 		}
 
@@ -656,22 +679,28 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1,
 /**
  * tipc_bcbearer_sort - create sets of bearer pairs used by broadcast bearer
  */
-void tipc_bcbearer_sort(void)
+void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action)
 {
 	struct tipc_bcbearer_pair *bp_temp = bcbearer->bpairs_temp;
 	struct tipc_bcbearer_pair *bp_curr;
+	struct tipc_bearer *b;
 	int b_index;
 	int pri;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
+
+	if (action)
+		tipc_nmap_add(nm_ptr, node);
+	else
+		tipc_nmap_remove(nm_ptr, node);
 
 	/* Group bearers by priority (can assume max of two per priority) */
 	memset(bp_temp, 0, sizeof(bcbearer->bpairs_temp));
 
+	rcu_read_lock();
 	for (b_index = 0; b_index < MAX_BEARERS; b_index++) {
-		struct tipc_bearer *b = &tipc_bearers[b_index];
-
-		if (!b->active || !b->nodes.count)
+		b = rcu_dereference_rtnl(bearer_list[b_index]);
+		if (!b || !b->nodes.count)
 			continue;
 
 		if (!bp_temp[b->priority].primary)
@@ -679,6 +708,7 @@ void tipc_bcbearer_sort(void)
 		else
 			bp_temp[b->priority].secondary = b;
 	}
+	rcu_read_unlock();
 
 	/* Create array of bearer pairs for broadcasting */
 	bp_curr = bcbearer->bpairs;
@@ -704,7 +734,7 @@ void tipc_bcbearer_sort(void)
 		bp_curr++;
 	}
 
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 }
 
 
@@ -716,7 +746,7 @@ int tipc_bclink_stats(char *buf, const u32 buf_size)
 	if (!bcl)
 		return 0;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 
 	s = &bcl->stats;
 
@@ -745,7 +775,7 @@ int tipc_bclink_stats(char *buf, const u32 buf_size)
 			     s->queue_sz_counts ?
 			     (s->accu_queue_sz / s->queue_sz_counts) : 0);
 
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 	return ret;
 }
 
@@ -754,9 +784,9 @@ int tipc_bclink_reset_stats(void)
 	if (!bcl)
 		return -ENOPROTOOPT;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 	memset(&bcl->stats, 0, sizeof(bcl->stats));
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 	return 0;
 }
 
@@ -767,45 +797,59 @@ int tipc_bclink_set_queue_limits(u32 limit)
 	if ((limit < TIPC_MIN_LINK_WIN) || (limit > TIPC_MAX_LINK_WIN))
 		return -EINVAL;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 	tipc_link_set_queue_limits(bcl, limit);
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 	return 0;
 }
 
-void tipc_bclink_init(void)
+int tipc_bclink_init(void)
 {
+	bcbearer = kzalloc(sizeof(*bcbearer), GFP_ATOMIC);
+	if (!bcbearer)
+		return -ENOMEM;
+
+	bclink = kzalloc(sizeof(*bclink), GFP_ATOMIC);
+	if (!bclink) {
+		kfree(bcbearer);
+		return -ENOMEM;
+	}
+
+	bcl = &bclink->link;
 	bcbearer->bearer.media = &bcbearer->media;
 	bcbearer->media.send_msg = tipc_bcbearer_send;
 	sprintf(bcbearer->media.name, "tipc-broadcast");
 
+	spin_lock_init(&bclink->lock);
 	INIT_LIST_HEAD(&bcl->waiting_ports);
 	bcl->next_out_no = 1;
 	spin_lock_init(&bclink->node.lock);
 	bcl->owner = &bclink->node;
 	bcl->max_pkt = MAX_PKT_DEFAULT_MCAST;
 	tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT);
-	spin_lock_init(&bcbearer->bearer.lock);
-	bcl->b_ptr = &bcbearer->bearer;
+	bcl->bearer_id = MAX_BEARERS;
+	rcu_assign_pointer(bearer_list[MAX_BEARERS], &bcbearer->bearer);
 	bcl->state = WORKING_WORKING;
 	strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME);
+	return 0;
 }
 
 void tipc_bclink_stop(void)
 {
-	spin_lock_bh(&bc_lock);
-	tipc_link_stop(bcl);
-	spin_unlock_bh(&bc_lock);
-
-	memset(bclink, 0, sizeof(*bclink));
-	memset(bcbearer, 0, sizeof(*bcbearer));
+	tipc_bclink_lock();
+	tipc_link_purge_queues(bcl);
+	tipc_bclink_unlock();
+
+	RCU_INIT_POINTER(bearer_list[BCBEARER], NULL);
+	synchronize_net();
+	kfree(bcbearer);
+	kfree(bclink);
 }
 
-
 /**
  * tipc_nmap_add - add a node to a node map
  */
-void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node)
+static void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node)
 {
 	int n = tipc_node(node);
 	int w = n / WSIZE;
@@ -820,7 +864,7 @@ void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node)
 /**
  * tipc_nmap_remove - remove a node from a node map
  */
-void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node)
+static void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node)
 {
 	int n = tipc_node(node);
 	int w = n / WSIZE;
diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h
index 6ee587b469f..00330c45df3 100644
--- a/net/tipc/bcast.h
+++ b/net/tipc/bcast.h
@@ -39,6 +39,7 @@
 
 #define MAX_NODES 4096
 #define WSIZE 32
+#define TIPC_BCLINK_RESET 1
 
 /**
  * struct tipc_node_map - set of node identifiers
@@ -69,9 +70,6 @@ struct tipc_node;
 
 extern const char tipc_bclink_name[];
 
-void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node);
-void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node);
-
 /**
  * tipc_nmap_equal - test for equality of node maps
  */
@@ -84,20 +82,21 @@ static inline int tipc_nmap_equal(struct tipc_node_map *nm_a,
 void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port);
 void tipc_port_list_free(struct tipc_port_list *pl_ptr);
 
-void tipc_bclink_init(void);
+int tipc_bclink_init(void);
 void tipc_bclink_stop(void);
+void tipc_bclink_set_flags(unsigned int flags);
 void tipc_bclink_add_node(u32 addr);
 void tipc_bclink_remove_node(u32 addr);
 struct tipc_node *tipc_bclink_retransmit_to(void);
 void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked);
-int  tipc_bclink_send_msg(struct sk_buff *buf);
-void tipc_bclink_recv_pkt(struct sk_buff *buf);
+int  tipc_bclink_xmit(struct sk_buff *buf);
+void tipc_bclink_rcv(struct sk_buff *buf);
 u32  tipc_bclink_get_last_sent(void);
 u32  tipc_bclink_acks_missing(struct tipc_node *n_ptr);
 void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent);
 int  tipc_bclink_stats(char *stats_buf, const u32 buf_size);
 int  tipc_bclink_reset_stats(void);
 int  tipc_bclink_set_queue_limits(u32 limit);
-void tipc_bcbearer_sort(void);
+void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action);
 
 #endif
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index c2101c0bfd6..264474394f9 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1,8 +1,8 @@
 /*
  * net/tipc/bearer.c: TIPC bearer code
  *
- * Copyright (c) 1996-2006, Ericsson AB
- * Copyright (c) 2004-2006, 2010-2011, Wind River Systems
+ * Copyright (c) 1996-2006, 2013, Ericsson AB
+ * Copyright (c) 2004-2006, 2010-2013, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -41,12 +41,17 @@
 
 #define MAX_ADDR_STR 60
 
-static struct tipc_media *media_list[MAX_MEDIA];
-static u32 media_count;
+static struct tipc_media * const media_info_array[] = {
+	&eth_media_info,
+#ifdef CONFIG_TIPC_MEDIA_IB
+	&ib_media_info,
+#endif
+	NULL
+};
 
-struct tipc_bearer tipc_bearers[MAX_BEARERS];
+struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1];
 
-static void bearer_disable(struct tipc_bearer *b_ptr);
+static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down);
 
 /**
  * tipc_media_find - locates specified media object by name
@@ -55,11 +60,11 @@ struct tipc_media *tipc_media_find(const char *name)
 {
 	u32 i;
 
-	for (i = 0; i < media_count; i++) {
-		if (!strcmp(media_list[i]->name, name))
-			return media_list[i];
+	for (i = 0; media_info_array[i] != NULL; i++) {
+		if (!strcmp(media_info_array[i]->name, name))
+			break;
 	}
-	return NULL;
+	return media_info_array[i];
 }
 
 /**
@@ -69,44 +74,11 @@ static struct tipc_media *media_find_id(u8 type)
 {
 	u32 i;
 
-	for (i = 0; i < media_count; i++) {
-		if (media_list[i]->type_id == type)
-			return media_list[i];
+	for (i = 0; media_info_array[i] != NULL; i++) {
+		if (media_info_array[i]->type_id == type)
+			break;
 	}
-	return NULL;
-}
-
-/**
- * tipc_register_media - register a media type
- *
- * Bearers for this media type must be activated separately at a later stage.
- */
-int tipc_register_media(struct tipc_media *m_ptr)
-{
-	int res = -EINVAL;
-
-	write_lock_bh(&tipc_net_lock);
-
-	if ((strlen(m_ptr->name) + 1) > TIPC_MAX_MEDIA_NAME)
-		goto exit;
-	if (m_ptr->priority > TIPC_MAX_LINK_PRI)
-		goto exit;
-	if ((m_ptr->tolerance < TIPC_MIN_LINK_TOL) ||
-	    (m_ptr->tolerance > TIPC_MAX_LINK_TOL))
-		goto exit;
-	if (media_count >= MAX_MEDIA)
-		goto exit;
-	if (tipc_media_find(m_ptr->name) || media_find_id(m_ptr->type_id))
-		goto exit;
-
-	media_list[media_count] = m_ptr;
-	media_count++;
-	res = 0;
-exit:
-	write_unlock_bh(&tipc_net_lock);
-	if (res)
-		pr_warn("Media <%s> registration error\n", m_ptr->name);
-	return res;
+	return media_info_array[i];
 }
 
 /**
@@ -144,13 +116,11 @@ struct sk_buff *tipc_media_get_names(void)
 	if (!buf)
 		return NULL;
 
-	read_lock_bh(&tipc_net_lock);
-	for (i = 0; i < media_count; i++) {
+	for (i = 0; media_info_array[i] != NULL; i++) {
 		tipc_cfg_append_tlv(buf, TIPC_TLV_MEDIA_NAME,
-				    media_list[i]->name,
-				    strlen(media_list[i]->name) + 1);
+				    media_info_array[i]->name,
+				    strlen(media_info_array[i]->name) + 1);
 	}
-	read_unlock_bh(&tipc_net_lock);
 	return buf;
 }
 
@@ -207,27 +177,9 @@ struct tipc_bearer *tipc_bearer_find(const char *name)
 	struct tipc_bearer *b_ptr;
 	u32 i;
 
-	for (i = 0, b_ptr = tipc_bearers; i < MAX_BEARERS; i++, b_ptr++) {
-		if (b_ptr->active && (!strcmp(b_ptr->name, name)))
-			return b_ptr;
-	}
-	return NULL;
-}
-
-/**
- * tipc_bearer_find_interface - locates bearer object with matching interface name
- */
-struct tipc_bearer *tipc_bearer_find_interface(const char *if_name)
-{
-	struct tipc_bearer *b_ptr;
-	char *b_if_name;
-	u32 i;
-
-	for (i = 0, b_ptr = tipc_bearers; i < MAX_BEARERS; i++, b_ptr++) {
-		if (!b_ptr->active)
-			continue;
-		b_if_name = strchr(b_ptr->name, ':') + 1;
-		if (!strcmp(b_if_name, if_name))
+	for (i = 0; i < MAX_BEARERS; i++) {
+		b_ptr = rtnl_dereference(bearer_list[i]);
+		if (b_ptr && (!strcmp(b_ptr->name, name)))
 			return b_ptr;
 	}
 	return NULL;
@@ -239,40 +191,52 @@ struct tipc_bearer *tipc_bearer_find_interface(const char *if_name)
 struct sk_buff *tipc_bearer_get_names(void)
 {
 	struct sk_buff *buf;
-	struct tipc_bearer *b_ptr;
+	struct tipc_bearer *b;
 	int i, j;
 
 	buf = tipc_cfg_reply_alloc(MAX_BEARERS * TLV_SPACE(TIPC_MAX_BEARER_NAME));
 	if (!buf)
 		return NULL;
 
-	read_lock_bh(&tipc_net_lock);
-	for (i = 0; i < media_count; i++) {
+	for (i = 0; media_info_array[i] != NULL; i++) {
 		for (j = 0; j < MAX_BEARERS; j++) {
-			b_ptr = &tipc_bearers[j];
-			if (b_ptr->active && (b_ptr->media == media_list[i])) {
+			b = rtnl_dereference(bearer_list[j]);
+			if (!b)
+				continue;
+			if (b->media == media_info_array[i]) {
 				tipc_cfg_append_tlv(buf, TIPC_TLV_BEARER_NAME,
-						    b_ptr->name,
-						    strlen(b_ptr->name) + 1);
+						    b->name,
+						    strlen(b->name) + 1);
 			}
 		}
 	}
-	read_unlock_bh(&tipc_net_lock);
 	return buf;
 }
 
-void tipc_bearer_add_dest(struct tipc_bearer *b_ptr, u32 dest)
+void tipc_bearer_add_dest(u32 bearer_id, u32 dest)
 {
-	tipc_nmap_add(&b_ptr->nodes, dest);
-	tipc_bcbearer_sort();
-	tipc_disc_add_dest(b_ptr->link_req);
+	struct tipc_bearer *b_ptr;
+
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]);
+	if (b_ptr) {
+		tipc_bcbearer_sort(&b_ptr->nodes, dest, true);
+		tipc_disc_add_dest(b_ptr->link_req);
+	}
+	rcu_read_unlock();
 }
 
-void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest)
+void tipc_bearer_remove_dest(u32 bearer_id, u32 dest)
 {
-	tipc_nmap_remove(&b_ptr->nodes, dest);
-	tipc_bcbearer_sort();
-	tipc_disc_remove_dest(b_ptr->link_req);
+	struct tipc_bearer *b_ptr;
+
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]);
+	if (b_ptr) {
+		tipc_bcbearer_sort(&b_ptr->nodes, dest, false);
+		tipc_disc_remove_dest(b_ptr->link_req);
+	}
+	rcu_read_unlock();
 }
 
 /**
@@ -317,13 +281,11 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority)
 		return -EINVAL;
 	}
 
-	write_lock_bh(&tipc_net_lock);
-
 	m_ptr = tipc_media_find(b_names.media_name);
 	if (!m_ptr) {
 		pr_warn("Bearer <%s> rejected, media <%s> not registered\n",
 			name, b_names.media_name);
-		goto exit;
+		return -EINVAL;
 	}
 
 	if (priority == TIPC_MEDIA_LINK_PRI)
@@ -333,21 +295,22 @@ restart:
 	bearer_id = MAX_BEARERS;
 	with_this_prio = 1;
 	for (i = MAX_BEARERS; i-- != 0; ) {
-		if (!tipc_bearers[i].active) {
+		b_ptr = rtnl_dereference(bearer_list[i]);
+		if (!b_ptr) {
 			bearer_id = i;
 			continue;
 		}
-		if (!strcmp(name, tipc_bearers[i].name)) {
+		if (!strcmp(name, b_ptr->name)) {
 			pr_warn("Bearer <%s> rejected, already enabled\n",
 				name);
-			goto exit;
+			return -EINVAL;
 		}
-		if ((tipc_bearers[i].priority == priority) &&
+		if ((b_ptr->priority == priority) &&
 		    (++with_this_prio > 2)) {
 			if (priority-- == 0) {
 				pr_warn("Bearer <%s> rejected, duplicate priority\n",
 					name);
-				goto exit;
+				return -EINVAL;
 			}
 			pr_warn("Bearer <%s> priority adjustment required %u->%u\n",
 				name, priority + 1, priority);
@@ -357,91 +320,79 @@ restart:
 	if (bearer_id >= MAX_BEARERS) {
 		pr_warn("Bearer <%s> rejected, bearer limit reached (%u)\n",
 			name, MAX_BEARERS);
-		goto exit;
+		return -EINVAL;
 	}
 
-	b_ptr = &tipc_bearers[bearer_id];
+	b_ptr = kzalloc(sizeof(*b_ptr), GFP_ATOMIC);
+	if (!b_ptr)
+		return -ENOMEM;
+
 	strcpy(b_ptr->name, name);
+	b_ptr->media = m_ptr;
 	res = m_ptr->enable_media(b_ptr);
 	if (res) {
 		pr_warn("Bearer <%s> rejected, enable failure (%d)\n",
 			name, -res);
-		goto exit;
+		return -EINVAL;
 	}
 
 	b_ptr->identity = bearer_id;
-	b_ptr->media = m_ptr;
 	b_ptr->tolerance = m_ptr->tolerance;
 	b_ptr->window = m_ptr->window;
+	b_ptr->domain = disc_domain;
 	b_ptr->net_plane = bearer_id + 'A';
-	b_ptr->active = 1;
 	b_ptr->priority = priority;
-	INIT_LIST_HEAD(&b_ptr->links);
-	spin_lock_init(&b_ptr->lock);
 
-	res = tipc_disc_create(b_ptr, &b_ptr->bcast_addr, disc_domain);
+	res = tipc_disc_create(b_ptr, &b_ptr->bcast_addr);
 	if (res) {
-		bearer_disable(b_ptr);
+		bearer_disable(b_ptr, false);
 		pr_warn("Bearer <%s> rejected, discovery object creation failed\n",
 			name);
-		goto exit;
+		return -EINVAL;
 	}
+
+	rcu_assign_pointer(bearer_list[bearer_id], b_ptr);
+
 	pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n",
 		name,
 		tipc_addr_string_fill(addr_string, disc_domain), priority);
-exit:
-	write_unlock_bh(&tipc_net_lock);
 	return res;
 }
 
 /**
  * tipc_reset_bearer - Reset all links established over this bearer
  */
-int tipc_reset_bearer(struct tipc_bearer *b_ptr)
+static int tipc_reset_bearer(struct tipc_bearer *b_ptr)
 {
-	struct tipc_link *l_ptr;
-	struct tipc_link *temp_l_ptr;
-
-	read_lock_bh(&tipc_net_lock);
 	pr_info("Resetting bearer <%s>\n", b_ptr->name);
-	spin_lock_bh(&b_ptr->lock);
-	list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) {
-		struct tipc_node *n_ptr = l_ptr->owner;
-
-		spin_lock_bh(&n_ptr->lock);
-		tipc_link_reset(l_ptr);
-		spin_unlock_bh(&n_ptr->lock);
-	}
-	spin_unlock_bh(&b_ptr->lock);
-	read_unlock_bh(&tipc_net_lock);
+	tipc_link_reset_list(b_ptr->identity);
+	tipc_disc_reset(b_ptr);
 	return 0;
 }
 
 /**
  * bearer_disable
  *
- * Note: This routine assumes caller holds tipc_net_lock.
+ * Note: This routine assumes caller holds RTNL lock.
  */
-static void bearer_disable(struct tipc_bearer *b_ptr)
+static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down)
 {
-	struct tipc_link *l_ptr;
-	struct tipc_link *temp_l_ptr;
-	struct tipc_link_req *temp_req;
+	u32 i;
 
 	pr_info("Disabling bearer <%s>\n", b_ptr->name);
-	spin_lock_bh(&b_ptr->lock);
 	b_ptr->media->disable_media(b_ptr);
-	list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) {
-		tipc_link_delete(l_ptr);
-	}
-	temp_req = b_ptr->link_req;
-	b_ptr->link_req = NULL;
-	spin_unlock_bh(&b_ptr->lock);
 
-	if (temp_req)
-		tipc_disc_delete(temp_req);
+	tipc_link_delete_list(b_ptr->identity, shutting_down);
+	if (b_ptr->link_req)
+		tipc_disc_delete(b_ptr->link_req);
 
-	memset(b_ptr, 0, sizeof(struct tipc_bearer));
+	for (i = 0; i < MAX_BEARERS; i++) {
+		if (b_ptr == rtnl_dereference(bearer_list[i])) {
+			RCU_INIT_POINTER(bearer_list[i], NULL);
+			break;
+		}
+	}
+	kfree_rcu(b_ptr, rcu);
 }
 
 int tipc_disable_bearer(const char *name)
@@ -449,28 +400,230 @@ int tipc_disable_bearer(const char *name)
 	struct tipc_bearer *b_ptr;
 	int res;
 
-	write_lock_bh(&tipc_net_lock);
 	b_ptr = tipc_bearer_find(name);
 	if (b_ptr == NULL) {
 		pr_warn("Attempt to disable unknown bearer <%s>\n", name);
 		res = -EINVAL;
 	} else {
-		bearer_disable(b_ptr);
+		bearer_disable(b_ptr, false);
 		res = 0;
 	}
-	write_unlock_bh(&tipc_net_lock);
 	return res;
 }
 
+int tipc_enable_l2_media(struct tipc_bearer *b)
+{
+	struct net_device *dev;
+	char *driver_name = strchr((const char *)b->name, ':') + 1;
+
+	/* Find device with specified name */
+	dev = dev_get_by_name(&init_net, driver_name);
+	if (!dev)
+		return -ENODEV;
+
+	/* Associate TIPC bearer with L2 bearer */
+	rcu_assign_pointer(b->media_ptr, dev);
+	memset(&b->bcast_addr, 0, sizeof(b->bcast_addr));
+	memcpy(b->bcast_addr.value, dev->broadcast, b->media->hwaddr_len);
+	b->bcast_addr.media_id = b->media->type_id;
+	b->bcast_addr.broadcast = 1;
+	b->mtu = dev->mtu;
+	b->media->raw2addr(b, &b->addr, (char *)dev->dev_addr);
+	rcu_assign_pointer(dev->tipc_ptr, b);
+	return 0;
+}
 
+/* tipc_disable_l2_media - detach TIPC bearer from an L2 interface
+ *
+ * Mark L2 bearer as inactive so that incoming buffers are thrown away,
+ * then get worker thread to complete bearer cleanup.  (Can't do cleanup
+ * here because cleanup code needs to sleep and caller holds spinlocks.)
+ */
+void tipc_disable_l2_media(struct tipc_bearer *b)
+{
+	struct net_device *dev;
+
+	dev = (struct net_device *)rtnl_dereference(b->media_ptr);
+	RCU_INIT_POINTER(b->media_ptr, NULL);
+	RCU_INIT_POINTER(dev->tipc_ptr, NULL);
+	synchronize_net();
+	dev_put(dev);
+}
+
+/**
+ * tipc_l2_send_msg - send a TIPC packet out over an L2 interface
+ * @buf: the packet to be sent
+ * @b_ptr: the bearer through which the packet is to be sent
+ * @dest: peer destination address
+ */
+int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b,
+		     struct tipc_media_addr *dest)
+{
+	struct sk_buff *clone;
+	struct net_device *dev;
+	int delta;
+
+	dev = (struct net_device *)rcu_dereference_rtnl(b->media_ptr);
+	if (!dev)
+		return 0;
+
+	clone = skb_clone(buf, GFP_ATOMIC);
+	if (!clone)
+		return 0;
+
+	delta = dev->hard_header_len - skb_headroom(buf);
+	if ((delta > 0) &&
+	    pskb_expand_head(clone, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
+		kfree_skb(clone);
+		return 0;
+	}
+
+	skb_reset_network_header(clone);
+	clone->dev = dev;
+	clone->protocol = htons(ETH_P_TIPC);
+	dev_hard_header(clone, dev, ETH_P_TIPC, dest->value,
+			dev->dev_addr, clone->len);
+	dev_queue_xmit(clone);
+	return 0;
+}
+
+/* tipc_bearer_send- sends buffer to destination over bearer
+ *
+ * IMPORTANT:
+ * The media send routine must not alter the buffer being passed in
+ * as it may be needed for later retransmission!
+ */
+void tipc_bearer_send(u32 bearer_id, struct sk_buff *buf,
+		      struct tipc_media_addr *dest)
+{
+	struct tipc_bearer *b_ptr;
+
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]);
+	if (likely(b_ptr))
+		b_ptr->media->send_msg(buf, b_ptr, dest);
+	rcu_read_unlock();
+}
+
+/**
+ * tipc_l2_rcv_msg - handle incoming TIPC message from an interface
+ * @buf: the received packet
+ * @dev: the net device that the packet was received on
+ * @pt: the packet_type structure which was used to register this handler
+ * @orig_dev: the original receive net device in case the device is a bond
+ *
+ * Accept only packets explicitly sent to this node, or broadcast packets;
+ * ignores packets sent using interface multicast, and traffic sent to other
+ * nodes (which can happen if interface is running in promiscuous mode).
+ */
+static int tipc_l2_rcv_msg(struct sk_buff *buf, struct net_device *dev,
+			   struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct tipc_bearer *b_ptr;
+
+	if (!net_eq(dev_net(dev), &init_net)) {
+		kfree_skb(buf);
+		return NET_RX_DROP;
+	}
+
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(dev->tipc_ptr);
+	if (likely(b_ptr)) {
+		if (likely(buf->pkt_type <= PACKET_BROADCAST)) {
+			buf->next = NULL;
+			tipc_rcv(buf, b_ptr);
+			rcu_read_unlock();
+			return NET_RX_SUCCESS;
+		}
+	}
+	rcu_read_unlock();
+
+	kfree_skb(buf);
+	return NET_RX_DROP;
+}
+
+/**
+ * tipc_l2_device_event - handle device events from network device
+ * @nb: the context of the notification
+ * @evt: the type of event
+ * @ptr: the net device that the event was on
+ *
+ * This function is called by the Ethernet driver in case of link
+ * change event.
+ */
+static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
+				void *ptr)
+{
+	struct tipc_bearer *b_ptr;
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	if (!net_eq(dev_net(dev), &init_net))
+		return NOTIFY_DONE;
+
+	b_ptr = rtnl_dereference(dev->tipc_ptr);
+	if (!b_ptr)
+		return NOTIFY_DONE;
+
+	b_ptr->mtu = dev->mtu;
+
+	switch (evt) {
+	case NETDEV_CHANGE:
+		if (netif_carrier_ok(dev))
+			break;
+	case NETDEV_DOWN:
+	case NETDEV_CHANGEMTU:
+		tipc_reset_bearer(b_ptr);
+		break;
+	case NETDEV_CHANGEADDR:
+		b_ptr->media->raw2addr(b_ptr, &b_ptr->addr,
+				       (char *)dev->dev_addr);
+		tipc_reset_bearer(b_ptr);
+		break;
+	case NETDEV_UNREGISTER:
+	case NETDEV_CHANGENAME:
+		bearer_disable(b_ptr, false);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct packet_type tipc_packet_type __read_mostly = {
+	.type = htons(ETH_P_TIPC),
+	.func = tipc_l2_rcv_msg,
+};
+
+static struct notifier_block notifier = {
+	.notifier_call  = tipc_l2_device_event,
+	.priority	= 0,
+};
+
+int tipc_bearer_setup(void)
+{
+	int err;
+
+	err = register_netdevice_notifier(&notifier);
+	if (err)
+		return err;
+	dev_add_pack(&tipc_packet_type);
+	return 0;
+}
+
+void tipc_bearer_cleanup(void)
+{
+	unregister_netdevice_notifier(&notifier);
+	dev_remove_pack(&tipc_packet_type);
+}
 
 void tipc_bearer_stop(void)
 {
+	struct tipc_bearer *b_ptr;
 	u32 i;
 
 	for (i = 0; i < MAX_BEARERS; i++) {
-		if (tipc_bearers[i].active)
-			bearer_disable(&tipc_bearers[i]);
+		b_ptr = rtnl_dereference(bearer_list[i]);
+		if (b_ptr) {
+			bearer_disable(b_ptr, true);
+			bearer_list[i] = NULL;
+		}
 	}
-	media_count = 0;
 }
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index cc780bbedbb..78fccc49de2 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/bearer.h: Include file for TIPC bearer code
  *
- * Copyright (c) 1996-2006, Ericsson AB
+ * Copyright (c) 1996-2006, 2013, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -42,14 +42,12 @@
 #define MAX_BEARERS	2
 #define MAX_MEDIA	2
 
-/*
- * Identifiers associated with TIPC message header media address info
- *
- * - address info field is 20 bytes long
- * - media type identifier located at offset 3
- * - remaining bytes vary according to media type
+/* Identifiers associated with TIPC message header media address info
+ * - address info field is 32 bytes long
+ * - the field's actual content and length is defined per media
+ * - remaining unused bytes in the field are set to zero
  */
-#define TIPC_MEDIA_ADDR_SIZE	20
+#define TIPC_MEDIA_ADDR_SIZE	32
 #define TIPC_MEDIA_TYPE_OFFSET	3
 
 /*
@@ -73,18 +71,19 @@ struct tipc_media_addr {
 struct tipc_bearer;
 
 /**
- * struct tipc_media - TIPC media information available to internal users
+ * struct tipc_media - Media specific info exposed to generic bearer layer
  * @send_msg: routine which handles buffer transmission
  * @enable_media: routine which enables a media
  * @disable_media: routine which disables a media
- * @addr2str: routine which converts media address to string
- * @addr2msg: routine which converts media address to protocol message area
- * @msg2addr: routine which converts media address from protocol message area
- * @bcast_addr: media address used in broadcasting
+ * @addr2str: convert media address format to string
+ * @addr2msg: convert from media addr format to discovery msg addr format
+ * @msg2addr: convert from discovery msg addr format to media addr format
+ * @raw2addr: convert from raw addr format to media addr format
  * @priority: default link (and bearer) priority
  * @tolerance: default time (in ms) before declaring link failure
  * @window: default window (in packets) before declaring link congestion
  * @type_id: TIPC media identifier
+ * @hwaddr_len: TIPC media address len
  * @name: media name
  */
 struct tipc_media {
@@ -93,32 +92,39 @@ struct tipc_media {
 			struct tipc_media_addr *dest);
 	int (*enable_media)(struct tipc_bearer *b_ptr);
 	void (*disable_media)(struct tipc_bearer *b_ptr);
-	int (*addr2str)(struct tipc_media_addr *a, char *str_buf, int str_size);
-	int (*addr2msg)(struct tipc_media_addr *a, char *msg_area);
-	int (*msg2addr)(const struct tipc_bearer *b_ptr,
-			struct tipc_media_addr *a, char *msg_area);
+	int (*addr2str)(struct tipc_media_addr *addr,
+			char *strbuf,
+			int bufsz);
+	int (*addr2msg)(char *msg, struct tipc_media_addr *addr);
+	int (*msg2addr)(struct tipc_bearer *b,
+			struct tipc_media_addr *addr,
+			char *msg);
+	int (*raw2addr)(struct tipc_bearer *b,
+			struct tipc_media_addr *addr,
+			char *raw);
 	u32 priority;
 	u32 tolerance;
 	u32 window;
 	u32 type_id;
+	u32 hwaddr_len;
 	char name[TIPC_MAX_MEDIA_NAME];
 };
 
 /**
- * struct tipc_bearer - TIPC bearer structure
- * @usr_handle: pointer to additional media-specific information about bearer
+ * struct tipc_bearer - Generic TIPC bearer structure
+ * @media_ptr: pointer to additional media-specific information about bearer
  * @mtu: max packet size bearer can support
- * @lock: spinlock for controlling access to bearer
  * @addr: media-specific address associated with bearer
  * @name: bearer name (format = media:interface)
  * @media: ptr to media structure associated with bearer
+ * @bcast_addr: media address used in broadcasting
+ * @rcu: rcu struct for tipc_bearer
  * @priority: default link priority for bearer
  * @window: default window size for bearer
  * @tolerance: default link tolerance for bearer
+ * @domain: network domain to which links can be established
  * @identity: array index of this bearer within TIPC bearer array
  * @link_req: ptr to (optional) structure making periodic link setup requests
- * @links: list of non-congested links associated with bearer
- * @active: non-zero if bearer structure is represents a bearer
  * @net_plane: network plane ('A' through 'H') currently associated with bearer
  * @nodes: indicates which nodes in cluster can be reached through bearer
  *
@@ -127,20 +133,19 @@ struct tipc_media {
  * care of initializing all other fields.
  */
 struct tipc_bearer {
-	void *usr_handle;			/* initalized by media */
+	void __rcu *media_ptr;			/* initalized by media */
 	u32 mtu;				/* initalized by media */
 	struct tipc_media_addr addr;		/* initalized by media */
 	char name[TIPC_MAX_BEARER_NAME];
-	spinlock_t lock;
 	struct tipc_media *media;
 	struct tipc_media_addr bcast_addr;
+	struct rcu_head rcu;
 	u32 priority;
 	u32 window;
 	u32 tolerance;
+	u32 domain;
 	u32 identity;
 	struct tipc_link_req *link_req;
-	struct list_head links;
-	int active;
 	char net_plane;
 	struct tipc_node_map nodes;
 };
@@ -152,58 +157,43 @@ struct tipc_bearer_names {
 
 struct tipc_link;
 
-extern struct tipc_bearer tipc_bearers[];
+extern struct tipc_bearer __rcu *bearer_list[];
 
 /*
  * TIPC routines available to supported media types
  */
-int tipc_register_media(struct tipc_media *m_ptr);
-
-void tipc_recv_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr);
-
-int  tipc_reset_bearer(struct tipc_bearer *b_ptr);
 
+void tipc_rcv(struct sk_buff *buf, struct tipc_bearer *tb_ptr);
 int tipc_enable_bearer(const char *bearer_name, u32 disc_domain, u32 priority);
 int tipc_disable_bearer(const char *name);
 
 /*
  * Routines made available to TIPC by supported media types
  */
-int  tipc_eth_media_start(void);
-void tipc_eth_media_stop(void);
+extern struct tipc_media eth_media_info;
 
 #ifdef CONFIG_TIPC_MEDIA_IB
-int  tipc_ib_media_start(void);
-void tipc_ib_media_stop(void);
-#else
-static inline int tipc_ib_media_start(void) { return 0; }
-static inline void tipc_ib_media_stop(void) { return; }
+extern struct tipc_media ib_media_info;
 #endif
 
 int tipc_media_set_priority(const char *name, u32 new_value);
 int tipc_media_set_window(const char *name, u32 new_value);
 void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a);
 struct sk_buff *tipc_media_get_names(void);
+int tipc_enable_l2_media(struct tipc_bearer *b);
+void tipc_disable_l2_media(struct tipc_bearer *b);
+int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b,
+		     struct tipc_media_addr *dest);
 
 struct sk_buff *tipc_bearer_get_names(void);
-void tipc_bearer_add_dest(struct tipc_bearer *b_ptr, u32 dest);
-void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest);
+void tipc_bearer_add_dest(u32 bearer_id, u32 dest);
+void tipc_bearer_remove_dest(u32 bearer_id, u32 dest);
 struct tipc_bearer *tipc_bearer_find(const char *name);
-struct tipc_bearer *tipc_bearer_find_interface(const char *if_name);
 struct tipc_media *tipc_media_find(const char *name);
+int tipc_bearer_setup(void);
+void tipc_bearer_cleanup(void);
 void tipc_bearer_stop(void);
-
-/**
- * tipc_bearer_send- sends buffer to destination over bearer
- *
- * IMPORTANT:
- * The media send routine must not alter the buffer being passed in
- * as it may be needed for later retransmission!
- */
-static inline void tipc_bearer_send(struct tipc_bearer *b, struct sk_buff *buf,
-				   struct tipc_media_addr *dest)
-{
-	b->media->send_msg(buf, b, dest);
-}
+void tipc_bearer_send(u32 bearer_id, struct sk_buff *buf,
+		      struct tipc_media_addr *dest);
 
 #endif	/* _TIPC_BEARER_H */
diff --git a/net/tipc/config.c b/net/tipc/config.c
index c301a9a592d..2b42403ad33 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -42,14 +42,10 @@
 
 #define REPLY_TRUNCATED "<truncated>\n"
 
-static DEFINE_MUTEX(config_mutex);
-static struct tipc_server cfgsrv;
-
 static const void *req_tlv_area;	/* request message TLV area */
 static int req_tlv_space;		/* request message TLV area size */
 static int rep_headroom;		/* reply message headroom to use */
 
-
 struct sk_buff *tipc_cfg_reply_alloc(int payload_size)
 {
 	struct sk_buff *buf;
@@ -181,20 +177,10 @@ static struct sk_buff *cfg_set_own_addr(void)
 	if (tipc_own_addr)
 		return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
 						   " (cannot change node address once assigned)");
-	tipc_core_start_net(addr);
-	return tipc_cfg_reply_none();
-}
-
-static struct sk_buff *cfg_set_remote_mng(void)
-{
-	u32 value;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
+	if (!tipc_net_start(addr))
+		return tipc_cfg_reply_none();
 
-	value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area));
-	tipc_remote_management = (value != 0);
-	return tipc_cfg_reply_none();
+	return tipc_cfg_reply_error_string("cannot change to network mode");
 }
 
 static struct sk_buff *cfg_set_max_ports(void)
@@ -237,7 +223,7 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
 {
 	struct sk_buff *rep_tlv_buf;
 
-	mutex_lock(&config_mutex);
+	rtnl_lock();
 
 	/* Save request and reply details in a well-known location */
 	req_tlv_area = request_area;
@@ -247,21 +233,10 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
 	/* Check command authorization */
 	if (likely(in_own_node(orig_node))) {
 		/* command is permitted */
-	} else if (cmd >= 0x8000) {
+	} else {
 		rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
 							  " (cannot be done remotely)");
 		goto exit;
-	} else if (!tipc_remote_management) {
-		rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NO_REMOTE);
-		goto exit;
-	} else if (cmd >= 0x4000) {
-		u32 domain = 0;
-
-		if ((tipc_nametbl_translate(TIPC_ZM_SRV, 0, &domain) == 0) ||
-		    (domain != orig_node)) {
-			rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_ZONE_MSTR);
-			goto exit;
-		}
 	}
 
 	/* Call appropriate processing routine */
@@ -310,18 +285,12 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
 	case TIPC_CMD_SET_NODE_ADDR:
 		rep_tlv_buf = cfg_set_own_addr();
 		break;
-	case TIPC_CMD_SET_REMOTE_MNG:
-		rep_tlv_buf = cfg_set_remote_mng();
-		break;
 	case TIPC_CMD_SET_MAX_PORTS:
 		rep_tlv_buf = cfg_set_max_ports();
 		break;
 	case TIPC_CMD_SET_NETID:
 		rep_tlv_buf = cfg_set_netid();
 		break;
-	case TIPC_CMD_GET_REMOTE_MNG:
-		rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_remote_management);
-		break;
 	case TIPC_CMD_GET_MAX_PORTS:
 		rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_ports);
 		break;
@@ -345,6 +314,8 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
 	case TIPC_CMD_SET_MAX_PUBL:
 	case TIPC_CMD_GET_MAX_PUBL:
 	case TIPC_CMD_SET_LOG_SIZE:
+	case TIPC_CMD_SET_REMOTE_MNG:
+	case TIPC_CMD_GET_REMOTE_MNG:
 	case TIPC_CMD_DUMP_LOG:
 		rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
 							  " (obsolete command)");
@@ -366,83 +337,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
 
 	/* Return reply buffer */
 exit:
-	mutex_unlock(&config_mutex);
+	rtnl_unlock();
 	return rep_tlv_buf;
 }
-
-static void cfg_conn_msg_event(int conid, struct sockaddr_tipc *addr,
-			       void *usr_data, void *buf, size_t len)
-{
-	struct tipc_cfg_msg_hdr *req_hdr;
-	struct tipc_cfg_msg_hdr *rep_hdr;
-	struct sk_buff *rep_buf;
-	int ret;
-
-	/* Validate configuration message header (ignore invalid message) */
-	req_hdr = (struct tipc_cfg_msg_hdr *)buf;
-	if ((len < sizeof(*req_hdr)) ||
-	    (len != TCM_ALIGN(ntohl(req_hdr->tcm_len))) ||
-	    (ntohs(req_hdr->tcm_flags) != TCM_F_REQUEST)) {
-		pr_warn("Invalid configuration message discarded\n");
-		return;
-	}
-
-	/* Generate reply for request (if can't, return request) */
-	rep_buf = tipc_cfg_do_cmd(addr->addr.id.node, ntohs(req_hdr->tcm_type),
-				  buf + sizeof(*req_hdr),
-				  len - sizeof(*req_hdr),
-				  BUF_HEADROOM + MAX_H_SIZE + sizeof(*rep_hdr));
-	if (rep_buf) {
-		skb_push(rep_buf, sizeof(*rep_hdr));
-		rep_hdr = (struct tipc_cfg_msg_hdr *)rep_buf->data;
-		memcpy(rep_hdr, req_hdr, sizeof(*rep_hdr));
-		rep_hdr->tcm_len = htonl(rep_buf->len);
-		rep_hdr->tcm_flags &= htons(~TCM_F_REQUEST);
-
-		ret = tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data,
-					rep_buf->len);
-		if (ret < 0)
-			pr_err("Sending cfg reply message failed, no memory\n");
-
-		kfree_skb(rep_buf);
-	}
-}
-
-static struct sockaddr_tipc cfgsrv_addr __read_mostly = {
-	.family			= AF_TIPC,
-	.addrtype		= TIPC_ADDR_NAMESEQ,
-	.addr.nameseq.type	= TIPC_CFG_SRV,
-	.addr.nameseq.lower	= 0,
-	.addr.nameseq.upper	= 0,
-	.scope			= TIPC_ZONE_SCOPE
-};
-
-static struct tipc_server cfgsrv __read_mostly = {
-	.saddr			= &cfgsrv_addr,
-	.imp			= TIPC_CRITICAL_IMPORTANCE,
-	.type			= SOCK_RDM,
-	.max_rcvbuf_size	= 64 * 1024,
-	.name			= "cfg_server",
-	.tipc_conn_recvmsg	= cfg_conn_msg_event,
-	.tipc_conn_new		= NULL,
-	.tipc_conn_shutdown	= NULL
-};
-
-int tipc_cfg_init(void)
-{
-	return tipc_server_start(&cfgsrv);
-}
-
-void tipc_cfg_reinit(void)
-{
-	tipc_server_stop(&cfgsrv);
-
-	cfgsrv_addr.addr.nameseq.lower = tipc_own_addr;
-	cfgsrv_addr.addr.nameseq.upper = tipc_own_addr;
-	tipc_server_start(&cfgsrv);
-}
-
-void tipc_cfg_stop(void)
-{
-	tipc_server_stop(&cfgsrv);
-}
diff --git a/net/tipc/config.h b/net/tipc/config.h
index 1f252f3fa05..47b1bf18161 100644
--- a/net/tipc/config.h
+++ b/net/tipc/config.h
@@ -64,9 +64,4 @@ static inline struct sk_buff *tipc_cfg_reply_ultra_string(char *string)
 struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd,
 				const void *req_tlv_area, int req_tlv_space,
 				int headroom);
-
-int  tipc_cfg_init(void);
-void tipc_cfg_reinit(void);
-void tipc_cfg_stop(void);
-
 #endif
diff --git a/net/tipc/core.c b/net/tipc/core.c
index fd4eeeaa972..676d18015dd 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/core.c: TIPC module code
  *
- * Copyright (c) 2003-2006, Ericsson AB
+ * Copyright (c) 2003-2006, 2013, Ericsson AB
  * Copyright (c) 2005-2006, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -50,7 +50,6 @@ int tipc_random __read_mostly;
 u32 tipc_own_addr __read_mostly;
 int tipc_max_ports __read_mostly;
 int tipc_net_id __read_mostly;
-int tipc_remote_management __read_mostly;
 int sysctl_tipc_rmem[3] __read_mostly;	/* min/default/max */
 
 /**
@@ -77,44 +76,13 @@ struct sk_buff *tipc_buf_acquire(u32 size)
 }
 
 /**
- * tipc_core_stop_net - shut down TIPC networking sub-systems
- */
-static void tipc_core_stop_net(void)
-{
-	tipc_net_stop();
-	tipc_eth_media_stop();
-	tipc_ib_media_stop();
-}
-
-/**
- * start_net - start TIPC networking sub-systems
- */
-int tipc_core_start_net(unsigned long addr)
-{
-	int res;
-
-	tipc_net_start(addr);
-	res = tipc_eth_media_start();
-	if (res < 0)
-		goto err;
-	res = tipc_ib_media_start();
-	if (res < 0)
-		goto err;
-	return res;
-
-err:
-	tipc_core_stop_net();
-	return res;
-}
-
-/**
  * tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode
  */
 static void tipc_core_stop(void)
 {
+	tipc_net_stop();
+	tipc_bearer_cleanup();
 	tipc_netlink_stop();
-	tipc_handler_stop();
-	tipc_cfg_stop();
 	tipc_subscr_stop();
 	tipc_nametbl_stop();
 	tipc_ref_table_stop();
@@ -127,29 +95,53 @@ static void tipc_core_stop(void)
  */
 static int tipc_core_start(void)
 {
-	int res;
+	int err;
 
 	get_random_bytes(&tipc_random, sizeof(tipc_random));
 
-	res = tipc_handler_start();
-	if (!res)
-		res = tipc_ref_table_init(tipc_max_ports, tipc_random);
-	if (!res)
-		res = tipc_nametbl_init();
-	if (!res)
-		res = tipc_netlink_start();
-	if (!res)
-		res = tipc_socket_init();
-	if (!res)
-		res = tipc_register_sysctl();
-	if (!res)
-		res = tipc_subscr_start();
-	if (!res)
-		res = tipc_cfg_init();
-	if (res)
-		tipc_core_stop();
+	err = tipc_ref_table_init(tipc_max_ports, tipc_random);
+	if (err)
+		goto out_reftbl;
 
-	return res;
+	err = tipc_nametbl_init();
+	if (err)
+		goto out_nametbl;
+
+	err = tipc_netlink_start();
+	if (err)
+		goto out_netlink;
+
+	err = tipc_socket_init();
+	if (err)
+		goto out_socket;
+
+	err = tipc_register_sysctl();
+	if (err)
+		goto out_sysctl;
+
+	err = tipc_subscr_start();
+	if (err)
+		goto out_subscr;
+
+	err = tipc_bearer_setup();
+	if (err)
+		goto out_bearer;
+
+	return 0;
+out_bearer:
+	tipc_subscr_stop();
+out_subscr:
+	tipc_unregister_sysctl();
+out_sysctl:
+	tipc_socket_stop();
+out_socket:
+	tipc_netlink_stop();
+out_netlink:
+	tipc_nametbl_stop();
+out_nametbl:
+	tipc_ref_table_stop();
+out_reftbl:
+	return err;
 }
 
 static int __init tipc_init(void)
@@ -159,14 +151,14 @@ static int __init tipc_init(void)
 	pr_info("Activated (version " TIPC_MOD_VER ")\n");
 
 	tipc_own_addr = 0;
-	tipc_remote_management = 1;
 	tipc_max_ports = CONFIG_TIPC_PORTS;
 	tipc_net_id = 4711;
 
-	sysctl_tipc_rmem[0] = CONN_OVERLOAD_LIMIT >> 4 << TIPC_LOW_IMPORTANCE;
-	sysctl_tipc_rmem[1] = CONN_OVERLOAD_LIMIT >> 4 <<
+	sysctl_tipc_rmem[0] = TIPC_CONN_OVERLOAD_LIMIT >> 4 <<
+			      TIPC_LOW_IMPORTANCE;
+	sysctl_tipc_rmem[1] = TIPC_CONN_OVERLOAD_LIMIT >> 4 <<
 			      TIPC_CRITICAL_IMPORTANCE;
-	sysctl_tipc_rmem[2] = CONN_OVERLOAD_LIMIT;
+	sysctl_tipc_rmem[2] = TIPC_CONN_OVERLOAD_LIMIT;
 
 	res = tipc_core_start();
 	if (res)
@@ -178,7 +170,6 @@ static int __init tipc_init(void)
 
 static void __exit tipc_exit(void)
 {
-	tipc_core_stop_net();
 	tipc_core_stop();
 	pr_info("Deactivated\n");
 }
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 94895d4e86a..bb26ed1ee96 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -47,7 +47,7 @@
 #include <linux/mm.h>
 #include <linux/timer.h>
 #include <linux/string.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/interrupt.h>
 #include <linux/atomic.h>
 #include <asm/hardirq.h>
@@ -56,7 +56,8 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
-
+#include <linux/rtnetlink.h>
+#include <linux/etherdevice.h>
 
 #define TIPC_MOD_VER "2.0.0"
 
@@ -79,7 +80,6 @@ int tipc_snprintf(char *buf, int len, const char *fmt, ...);
 extern u32 tipc_own_addr __read_mostly;
 extern int tipc_max_ports __read_mostly;
 extern int tipc_net_id __read_mostly;
-extern int tipc_remote_management __read_mostly;
 extern int sysctl_tipc_rmem[3] __read_mostly;
 
 /*
@@ -90,9 +90,6 @@ extern int tipc_random __read_mostly;
 /*
  * Routines available to privileged subsystems
  */
-int tipc_core_start_net(unsigned long);
-int tipc_handler_start(void);
-void tipc_handler_stop(void);
 int tipc_netlink_start(void);
 void tipc_netlink_stop(void);
 int tipc_socket_init(void);
@@ -111,12 +108,10 @@ void tipc_unregister_sysctl(void);
 #endif
 
 /*
- * TIPC timer and signal code
+ * TIPC timer code
  */
 typedef void (*Handler) (unsigned long);
 
-u32 tipc_k_signal(Handler routine, unsigned long argument);
-
 /**
  * k_init_timer - initialize a timer
  * @timer: pointer to timer structure
@@ -192,6 +187,8 @@ static inline void k_term_timer(struct timer_list *timer)
 
 struct tipc_skb_cb {
 	void *handle;
+	bool deferred;
+	struct sk_buff *tail;
 };
 
 #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index bc849f1efa1..aa722a42ef8 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/discover.c
  *
- * Copyright (c) 2003-2006, Ericsson AB
+ * Copyright (c) 2003-2006, 2014, Ericsson AB
  * Copyright (c) 2005-2006, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -46,19 +46,21 @@
 
 /**
  * struct tipc_link_req - information about an ongoing link setup request
- * @bearer: bearer issuing requests
+ * @bearer_id: identity of bearer issuing requests
  * @dest: destination address for request messages
  * @domain: network domain to which links can be established
  * @num_nodes: number of nodes currently discovered (i.e. with an active link)
+ * @lock: spinlock for controlling access to requests
  * @buf: request message to be (repeatedly) sent
  * @timer: timer governing period between requests
  * @timer_intv: current interval between requests (in ms)
  */
 struct tipc_link_req {
-	struct tipc_bearer *bearer;
+	u32 bearer_id;
 	struct tipc_media_addr dest;
 	u32 domain;
 	int num_nodes;
+	spinlock_t lock;
 	struct sk_buff *buf;
 	struct timer_list timer;
 	unsigned int timer_intv;
@@ -67,25 +69,21 @@ struct tipc_link_req {
 /**
  * tipc_disc_init_msg - initialize a link setup message
  * @type: message type (request or response)
- * @dest_domain: network domain of node(s) which should respond to message
  * @b_ptr: ptr to bearer issuing message
  */
-static struct sk_buff *tipc_disc_init_msg(u32 type, u32 dest_domain,
-					  struct tipc_bearer *b_ptr)
+static void tipc_disc_init_msg(struct sk_buff *buf, u32 type,
+			       struct tipc_bearer *b_ptr)
 {
-	struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE);
 	struct tipc_msg *msg;
-
-	if (buf) {
-		msg = buf_msg(buf);
-		tipc_msg_init(msg, LINK_CONFIG, type, INT_H_SIZE, dest_domain);
-		msg_set_non_seq(msg, 1);
-		msg_set_node_sig(msg, tipc_random);
-		msg_set_dest_domain(msg, dest_domain);
-		msg_set_bc_netid(msg, tipc_net_id);
-		b_ptr->media->addr2msg(&b_ptr->addr, msg_media_addr(msg));
-	}
-	return buf;
+	u32 dest_domain = b_ptr->domain;
+
+	msg = buf_msg(buf);
+	tipc_msg_init(msg, LINK_CONFIG, type, INT_H_SIZE, dest_domain);
+	msg_set_non_seq(msg, 1);
+	msg_set_node_sig(msg, tipc_random);
+	msg_set_dest_domain(msg, dest_domain);
+	msg_set_bc_netid(msg, tipc_net_id);
+	b_ptr->media->addr2msg(msg_media_addr(msg), &b_ptr->addr);
 }
 
 /**
@@ -108,146 +106,150 @@ static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr,
 }
 
 /**
- * tipc_disc_recv_msg - handle incoming link setup message (request or response)
+ * tipc_disc_rcv - handle incoming discovery message (request or response)
  * @buf: buffer containing message
- * @b_ptr: bearer that message arrived on
+ * @bearer: bearer that message arrived on
  */
-void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr)
+void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer)
 {
-	struct tipc_node *n_ptr;
+	struct tipc_node *node;
 	struct tipc_link *link;
-	struct tipc_media_addr media_addr;
+	struct tipc_media_addr maddr;
 	struct sk_buff *rbuf;
 	struct tipc_msg *msg = buf_msg(buf);
-	u32 dest = msg_dest_domain(msg);
-	u32 orig = msg_prevnode(msg);
+	u32 ddom = msg_dest_domain(msg);
+	u32 onode = msg_prevnode(msg);
 	u32 net_id = msg_bc_netid(msg);
-	u32 type = msg_type(msg);
+	u32 mtyp = msg_type(msg);
 	u32 signature = msg_node_sig(msg);
-	int addr_mismatch;
-	int link_fully_up;
-
-	media_addr.broadcast = 1;
-	b_ptr->media->msg2addr(b_ptr, &media_addr, msg_media_addr(msg));
+	bool addr_match = false;
+	bool sign_match = false;
+	bool link_up = false;
+	bool accept_addr = false;
+	bool accept_sign = false;
+	bool respond = false;
+
+	bearer->media->msg2addr(bearer, &maddr, msg_media_addr(msg));
 	kfree_skb(buf);
 
 	/* Ensure message from node is valid and communication is permitted */
 	if (net_id != tipc_net_id)
 		return;
-	if (media_addr.broadcast)
+	if (maddr.broadcast)
 		return;
-	if (!tipc_addr_domain_valid(dest))
+	if (!tipc_addr_domain_valid(ddom))
 		return;
-	if (!tipc_addr_node_valid(orig))
+	if (!tipc_addr_node_valid(onode))
 		return;
-	if (orig == tipc_own_addr) {
-		if (memcmp(&media_addr, &b_ptr->addr, sizeof(media_addr)))
-			disc_dupl_alert(b_ptr, tipc_own_addr, &media_addr);
+
+	if (in_own_node(onode)) {
+		if (memcmp(&maddr, &bearer->addr, sizeof(maddr)))
+			disc_dupl_alert(bearer, tipc_own_addr, &maddr);
 		return;
 	}
-	if (!tipc_in_scope(dest, tipc_own_addr))
+	if (!tipc_in_scope(ddom, tipc_own_addr))
 		return;
-	if (!tipc_in_scope(b_ptr->link_req->domain, orig))
+	if (!tipc_in_scope(bearer->domain, onode))
 		return;
 
-	/* Locate structure corresponding to requesting node */
-	n_ptr = tipc_node_find(orig);
-	if (!n_ptr) {
-		n_ptr = tipc_node_create(orig);
-		if (!n_ptr)
-			return;
-	}
-	tipc_node_lock(n_ptr);
+	/* Locate, or if necessary, create, node: */
+	node = tipc_node_find(onode);
+	if (!node)
+		node = tipc_node_create(onode);
+	if (!node)
+		return;
 
-	/* Prepare to validate requesting node's signature and media address */
-	link = n_ptr->links[b_ptr->identity];
-	addr_mismatch = (link != NULL) &&
-		memcmp(&link->media_addr, &media_addr, sizeof(media_addr));
+	tipc_node_lock(node);
+	link = node->links[bearer->identity];
 
-	/*
-	 * Ensure discovery message's signature is correct
-	 *
-	 * If signature is incorrect and there is no working link to the node,
-	 * accept the new signature but invalidate all existing links to the
-	 * node so they won't re-activate without a new discovery message.
-	 *
-	 * If signature is incorrect and the requested link to the node is
-	 * working, accept the new signature. (This is an instance of delayed
-	 * rediscovery, where a link endpoint was able to re-establish contact
-	 * with its peer endpoint on a node that rebooted before receiving a
-	 * discovery message from that node.)
-	 *
-	 * If signature is incorrect and there is a working link to the node
-	 * that is not the requested link, reject the request (must be from
-	 * a duplicate node).
-	 */
-	if (signature != n_ptr->signature) {
-		if (n_ptr->working_links == 0) {
-			struct tipc_link *curr_link;
-			int i;
-
-			for (i = 0; i < MAX_BEARERS; i++) {
-				curr_link = n_ptr->links[i];
-				if (curr_link) {
-					memset(&curr_link->media_addr, 0,
-					       sizeof(media_addr));
-					tipc_link_reset(curr_link);
-				}
-			}
-			addr_mismatch = (link != NULL);
-		} else if (tipc_link_is_up(link) && !addr_mismatch) {
-			/* delayed rediscovery */
-		} else {
-			disc_dupl_alert(b_ptr, orig, &media_addr);
-			tipc_node_unlock(n_ptr);
-			return;
-		}
-		n_ptr->signature = signature;
+	/* Prepare to validate requesting node's signature and media address */
+	sign_match = (signature == node->signature);
+	addr_match = link && !memcmp(&link->media_addr, &maddr, sizeof(maddr));
+	link_up = link && tipc_link_is_up(link);
+
+
+	/* These three flags give us eight permutations: */
+
+	if (sign_match && addr_match && link_up) {
+		/* All is fine. Do nothing. */
+	} else if (sign_match && addr_match && !link_up) {
+		/* Respond. The link will come up in due time */
+		respond = true;
+	} else if (sign_match && !addr_match && link_up) {
+		/* Peer has changed i/f address without rebooting.
+		 * If so, the link will reset soon, and the next
+		 * discovery will be accepted. So we can ignore it.
+		 * It may also be an cloned or malicious peer having
+		 * chosen the same node address and signature as an
+		 * existing one.
+		 * Ignore requests until the link goes down, if ever.
+		 */
+		disc_dupl_alert(bearer, onode, &maddr);
+	} else if (sign_match && !addr_match && !link_up) {
+		/* Peer link has changed i/f address without rebooting.
+		 * It may also be a cloned or malicious peer; we can't
+		 * distinguish between the two.
+		 * The signature is correct, so we must accept.
+		 */
+		accept_addr = true;
+		respond = true;
+	} else if (!sign_match && addr_match && link_up) {
+		/* Peer node rebooted. Two possibilities:
+		 *  - Delayed re-discovery; this link endpoint has already
+		 *    reset and re-established contact with the peer, before
+		 *    receiving a discovery message from that node.
+		 *    (The peer happened to receive one from this node first).
+		 *  - The peer came back so fast that our side has not
+		 *    discovered it yet. Probing from this side will soon
+		 *    reset the link, since there can be no working link
+		 *    endpoint at the peer end, and the link will re-establish.
+		 *  Accept the signature, since it comes from a known peer.
+		 */
+		accept_sign = true;
+	} else if (!sign_match && addr_match && !link_up) {
+		/*  The peer node has rebooted.
+		 *  Accept signature, since it is a known peer.
+		 */
+		accept_sign = true;
+		respond = true;
+	} else if (!sign_match && !addr_match && link_up) {
+		/* Peer rebooted with new address, or a new/duplicate peer.
+		 * Ignore until the link goes down, if ever.
+		 */
+		disc_dupl_alert(bearer, onode, &maddr);
+	} else if (!sign_match && !addr_match && !link_up) {
+		/* Peer rebooted with new address, or it is a new peer.
+		 * Accept signature and address.
+		*/
+		accept_sign = true;
+		accept_addr = true;
+		respond = true;
 	}
 
-	/*
-	 * Ensure requesting node's media address is correct
-	 *
-	 * If media address doesn't match and the link is working, reject the
-	 * request (must be from a duplicate node).
-	 *
-	 * If media address doesn't match and the link is not working, accept
-	 * the new media address and reset the link to ensure it starts up
-	 * cleanly.
-	 */
-	if (addr_mismatch) {
-		if (tipc_link_is_up(link)) {
-			disc_dupl_alert(b_ptr, orig, &media_addr);
-			tipc_node_unlock(n_ptr);
-			return;
-		} else {
-			memcpy(&link->media_addr, &media_addr,
-			       sizeof(media_addr));
-			tipc_link_reset(link);
-		}
-	}
+	if (accept_sign)
+		node->signature = signature;
 
-	/* Create a link endpoint for this bearer, if necessary */
-	if (!link) {
-		link = tipc_link_create(n_ptr, b_ptr, &media_addr);
-		if (!link) {
-			tipc_node_unlock(n_ptr);
-			return;
+	if (accept_addr) {
+		if (!link)
+			link = tipc_link_create(node, bearer, &maddr);
+		if (link) {
+			memcpy(&link->media_addr, &maddr, sizeof(maddr));
+			tipc_link_reset(link);
+		} else {
+			respond = false;
 		}
 	}
 
-	/* Accept discovery message & send response, if necessary */
-	link_fully_up = link_working_working(link);
-
-	if ((type == DSC_REQ_MSG) && !link_fully_up) {
-		rbuf = tipc_disc_init_msg(DSC_RESP_MSG, orig, b_ptr);
+	/* Send response, if necessary */
+	if (respond && (mtyp == DSC_REQ_MSG)) {
+		rbuf = tipc_buf_acquire(INT_H_SIZE);
 		if (rbuf) {
-			tipc_bearer_send(b_ptr, rbuf, &media_addr);
+			tipc_disc_init_msg(rbuf, DSC_RESP_MSG, bearer);
+			tipc_bearer_send(bearer->identity, rbuf, &maddr);
 			kfree_skb(rbuf);
 		}
 	}
-
-	tipc_node_unlock(n_ptr);
+	tipc_node_unlock(node);
 }
 
 /**
@@ -274,7 +276,9 @@ static void disc_update(struct tipc_link_req *req)
  */
 void tipc_disc_add_dest(struct tipc_link_req *req)
 {
+	spin_lock_bh(&req->lock);
 	req->num_nodes++;
+	spin_unlock_bh(&req->lock);
 }
 
 /**
@@ -283,8 +287,10 @@ void tipc_disc_add_dest(struct tipc_link_req *req)
  */
 void tipc_disc_remove_dest(struct tipc_link_req *req)
 {
+	spin_lock_bh(&req->lock);
 	req->num_nodes--;
 	disc_update(req);
+	spin_unlock_bh(&req->lock);
 }
 
 /**
@@ -297,7 +303,7 @@ static void disc_timeout(struct tipc_link_req *req)
 {
 	int max_delay;
 
-	spin_lock_bh(&req->bearer->lock);
+	spin_lock_bh(&req->lock);
 
 	/* Stop searching if only desired node has been found */
 	if (tipc_node(req->domain) && req->num_nodes) {
@@ -312,7 +318,7 @@ static void disc_timeout(struct tipc_link_req *req)
 	 * hold at fast polling rate if don't have any associated nodes,
 	 * otherwise hold at slow polling rate
 	 */
-	tipc_bearer_send(req->bearer, req->buf, &req->dest);
+	tipc_bearer_send(req->bearer_id, req->buf, &req->dest);
 
 
 	req->timer_intv *= 2;
@@ -325,7 +331,7 @@ static void disc_timeout(struct tipc_link_req *req)
 
 	k_start_timer(&req->timer, req->timer_intv);
 exit:
-	spin_unlock_bh(&req->bearer->lock);
+	spin_unlock_bh(&req->lock);
 }
 
 /**
@@ -336,8 +342,7 @@ exit:
  *
  * Returns 0 if successful, otherwise -errno.
  */
-int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest,
-		     u32 dest_domain)
+int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest)
 {
 	struct tipc_link_req *req;
 
@@ -345,21 +350,23 @@ int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest,
 	if (!req)
 		return -ENOMEM;
 
-	req->buf = tipc_disc_init_msg(DSC_REQ_MSG, dest_domain, b_ptr);
+	req->buf = tipc_buf_acquire(INT_H_SIZE);
 	if (!req->buf) {
 		kfree(req);
-		return -ENOMSG;
+		return -ENOMEM;
 	}
 
+	tipc_disc_init_msg(req->buf, DSC_REQ_MSG, b_ptr);
 	memcpy(&req->dest, dest, sizeof(*dest));
-	req->bearer = b_ptr;
-	req->domain = dest_domain;
+	req->bearer_id = b_ptr->identity;
+	req->domain = b_ptr->domain;
 	req->num_nodes = 0;
 	req->timer_intv = TIPC_LINK_REQ_INIT;
+	spin_lock_init(&req->lock);
 	k_init_timer(&req->timer, (Handler)disc_timeout, (unsigned long)req);
 	k_start_timer(&req->timer, req->timer_intv);
 	b_ptr->link_req = req;
-	tipc_bearer_send(req->bearer, req->buf, &req->dest);
+	tipc_bearer_send(req->bearer_id, req->buf, &req->dest);
 	return 0;
 }
 
@@ -374,3 +381,23 @@ void tipc_disc_delete(struct tipc_link_req *req)
 	kfree_skb(req->buf);
 	kfree(req);
 }
+
+/**
+ * tipc_disc_reset - reset object to send periodic link setup requests
+ * @b_ptr: ptr to bearer issuing requests
+ * @dest_domain: network domain to which links can be established
+ */
+void tipc_disc_reset(struct tipc_bearer *b_ptr)
+{
+	struct tipc_link_req *req = b_ptr->link_req;
+
+	spin_lock_bh(&req->lock);
+	tipc_disc_init_msg(req->buf, DSC_REQ_MSG, b_ptr);
+	req->bearer_id = b_ptr->identity;
+	req->domain = b_ptr->domain;
+	req->num_nodes = 0;
+	req->timer_intv = TIPC_LINK_REQ_INIT;
+	k_start_timer(&req->timer, req->timer_intv);
+	tipc_bearer_send(req->bearer_id, req->buf, &req->dest);
+	spin_unlock_bh(&req->lock);
+}
diff --git a/net/tipc/discover.h b/net/tipc/discover.h
index 75b67c403aa..515b57392f4 100644
--- a/net/tipc/discover.h
+++ b/net/tipc/discover.h
@@ -39,11 +39,11 @@
 
 struct tipc_link_req;
 
-int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest,
-		     u32 dest_domain);
+int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest);
 void tipc_disc_delete(struct tipc_link_req *req);
+void tipc_disc_reset(struct tipc_bearer *b_ptr);
 void tipc_disc_add_dest(struct tipc_link_req *req);
 void tipc_disc_remove_dest(struct tipc_link_req *req);
-void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr);
+void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr);
 
 #endif
diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c
index 1e3c33250db..5e1426f1751 100644
--- a/net/tipc/eth_media.c
+++ b/net/tipc/eth_media.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/eth_media.c: Ethernet bearer support for TIPC
  *
- * Copyright (c) 2001-2007, Ericsson AB
+ * Copyright (c) 2001-2007, 2013-2014, Ericsson AB
  * Copyright (c) 2005-2008, 2011-2013, Wind River Systems
  * All rights reserved.
  *
@@ -37,330 +37,65 @@
 #include "core.h"
 #include "bearer.h"
 
-#define MAX_ETH_MEDIA		MAX_BEARERS
+#define ETH_ADDR_OFFSET  4  /* MAC addr position inside address field */
 
-#define ETH_ADDR_OFFSET	4	/* message header offset of MAC address */
-
-/**
- * struct eth_media - Ethernet bearer data structure
- * @bearer: ptr to associated "generic" bearer structure
- * @dev: ptr to associated Ethernet network device
- * @tipc_packet_type: used in binding TIPC to Ethernet driver
- * @setup: work item used when enabling bearer
- * @cleanup: work item used when disabling bearer
- */
-struct eth_media {
-	struct tipc_bearer *bearer;
-	struct net_device *dev;
-	struct packet_type tipc_packet_type;
-	struct work_struct setup;
-	struct work_struct cleanup;
-};
-
-static struct tipc_media eth_media_info;
-static struct eth_media eth_media_array[MAX_ETH_MEDIA];
-static int eth_started;
-
-static int recv_notification(struct notifier_block *nb, unsigned long evt,
-			     void *dv);
-/*
- * Network device notifier info
- */
-static struct notifier_block notifier = {
-	.notifier_call	= recv_notification,
-	.priority	= 0
-};
-
-/**
- * eth_media_addr_set - initialize Ethernet media address structure
- *
- * Media-dependent "value" field stores MAC address in first 6 bytes
- * and zeroes out the remaining bytes.
- */
-static void eth_media_addr_set(const struct tipc_bearer *tb_ptr,
-			       struct tipc_media_addr *a, char *mac)
+/* Convert Ethernet address (media address format) to string */
+static int tipc_eth_addr2str(struct tipc_media_addr *addr,
+			     char *strbuf, int bufsz)
 {
-	memcpy(a->value, mac, ETH_ALEN);
-	memset(a->value + ETH_ALEN, 0, sizeof(a->value) - ETH_ALEN);
-	a->media_id = TIPC_MEDIA_TYPE_ETH;
-	a->broadcast = !memcmp(mac, tb_ptr->bcast_addr.value, ETH_ALEN);
-}
-
-/**
- * send_msg - send a TIPC message out over an Ethernet interface
- */
-static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr,
-		    struct tipc_media_addr *dest)
-{
-	struct sk_buff *clone;
-	struct net_device *dev;
-	int delta;
-
-	clone = skb_clone(buf, GFP_ATOMIC);
-	if (!clone)
-		return 0;
-
-	dev = ((struct eth_media *)(tb_ptr->usr_handle))->dev;
-	delta = dev->hard_header_len - skb_headroom(buf);
-
-	if ((delta > 0) &&
-	    pskb_expand_head(clone, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
-		kfree_skb(clone);
-		return 0;
-	}
+	if (bufsz < 18)	/* 18 = strlen("aa:bb:cc:dd:ee:ff\0") */
+		return 1;
 
-	skb_reset_network_header(clone);
-	clone->dev = dev;
-	clone->protocol = htons(ETH_P_TIPC);
-	dev_hard_header(clone, dev, ETH_P_TIPC, dest->value,
-			dev->dev_addr, clone->len);
-	dev_queue_xmit(clone);
+	sprintf(strbuf, "%pM", addr->value);
 	return 0;
 }
 
-/**
- * recv_msg - handle incoming TIPC message from an Ethernet interface
- *
- * Accept only packets explicitly sent to this node, or broadcast packets;
- * ignores packets sent using Ethernet multicast, and traffic sent to other
- * nodes (which can happen if interface is running in promiscuous mode).
- */
-static int recv_msg(struct sk_buff *buf, struct net_device *dev,
-		    struct packet_type *pt, struct net_device *orig_dev)
-{
-	struct eth_media *eb_ptr = (struct eth_media *)pt->af_packet_priv;
-
-	if (!net_eq(dev_net(dev), &init_net)) {
-		kfree_skb(buf);
-		return NET_RX_DROP;
-	}
-
-	if (likely(eb_ptr->bearer)) {
-		if (likely(buf->pkt_type <= PACKET_BROADCAST)) {
-			buf->next = NULL;
-			tipc_recv_msg(buf, eb_ptr->bearer);
-			return NET_RX_SUCCESS;
-		}
-	}
-	kfree_skb(buf);
-	return NET_RX_DROP;
-}
-
-/**
- * setup_media - setup association between Ethernet bearer and interface
- */
-static void setup_media(struct work_struct *work)
-{
-	struct eth_media *eb_ptr =
-		container_of(work, struct eth_media, setup);
-
-	dev_add_pack(&eb_ptr->tipc_packet_type);
-}
-
-/**
- * enable_media - attach TIPC bearer to an Ethernet interface
- */
-static int enable_media(struct tipc_bearer *tb_ptr)
+/* Convert from media address format to discovery message addr format */
+static int tipc_eth_addr2msg(char *msg, struct tipc_media_addr *addr)
 {
-	struct net_device *dev;
-	struct eth_media *eb_ptr = &eth_media_array[0];
-	struct eth_media *stop = &eth_media_array[MAX_ETH_MEDIA];
-	char *driver_name = strchr((const char *)tb_ptr->name, ':') + 1;
-	int pending_dev = 0;
-
-	/* Find unused Ethernet bearer structure */
-	while (eb_ptr->dev) {
-		if (!eb_ptr->bearer)
-			pending_dev++;
-		if (++eb_ptr == stop)
-			return pending_dev ? -EAGAIN : -EDQUOT;
-	}
-
-	/* Find device with specified name */
-	dev = dev_get_by_name(&init_net, driver_name);
-	if (!dev)
-		return -ENODEV;
-
-	/* Create Ethernet bearer for device */
-	eb_ptr->dev = dev;
-	eb_ptr->tipc_packet_type.type = htons(ETH_P_TIPC);
-	eb_ptr->tipc_packet_type.dev = dev;
-	eb_ptr->tipc_packet_type.func = recv_msg;
-	eb_ptr->tipc_packet_type.af_packet_priv = eb_ptr;
-	INIT_LIST_HEAD(&(eb_ptr->tipc_packet_type.list));
-	INIT_WORK(&eb_ptr->setup, setup_media);
-	schedule_work(&eb_ptr->setup);
-
-	/* Associate TIPC bearer with Ethernet bearer */
-	eb_ptr->bearer = tb_ptr;
-	tb_ptr->usr_handle = (void *)eb_ptr;
-	memset(tb_ptr->bcast_addr.value, 0, sizeof(tb_ptr->bcast_addr.value));
-	memcpy(tb_ptr->bcast_addr.value, dev->broadcast, ETH_ALEN);
-	tb_ptr->bcast_addr.media_id = TIPC_MEDIA_TYPE_ETH;
-	tb_ptr->bcast_addr.broadcast = 1;
-	tb_ptr->mtu = dev->mtu;
-	eth_media_addr_set(tb_ptr, &tb_ptr->addr, (char *)dev->dev_addr);
+	memset(msg, 0, TIPC_MEDIA_ADDR_SIZE);
+	msg[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_ETH;
+	memcpy(msg + ETH_ADDR_OFFSET, addr->value, ETH_ALEN);
 	return 0;
 }
 
-/**
- * cleanup_media - break association between Ethernet bearer and interface
- *
- * This routine must be invoked from a work queue because it can sleep.
- */
-static void cleanup_media(struct work_struct *work)
+/* Convert raw mac address format to media addr format */
+static int tipc_eth_raw2addr(struct tipc_bearer *b,
+			     struct tipc_media_addr *addr,
+			     char *msg)
 {
-	struct eth_media *eb_ptr =
-		container_of(work, struct eth_media, cleanup);
-
-	dev_remove_pack(&eb_ptr->tipc_packet_type);
-	dev_put(eb_ptr->dev);
-	eb_ptr->dev = NULL;
-}
+	char bcast_mac[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
 
-/**
- * disable_media - detach TIPC bearer from an Ethernet interface
- *
- * Mark Ethernet bearer as inactive so that incoming buffers are thrown away,
- * then get worker thread to complete bearer cleanup.  (Can't do cleanup
- * here because cleanup code needs to sleep and caller holds spinlocks.)
- */
-static void disable_media(struct tipc_bearer *tb_ptr)
-{
-	struct eth_media *eb_ptr = (struct eth_media *)tb_ptr->usr_handle;
-
-	eb_ptr->bearer = NULL;
-	INIT_WORK(&eb_ptr->cleanup, cleanup_media);
-	schedule_work(&eb_ptr->cleanup);
-}
-
-/**
- * recv_notification - handle device updates from OS
- *
- * Change the state of the Ethernet bearer (if any) associated with the
- * specified device.
- */
-static int recv_notification(struct notifier_block *nb, unsigned long evt,
-			     void *ptr)
-{
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct eth_media *eb_ptr = &eth_media_array[0];
-	struct eth_media *stop = &eth_media_array[MAX_ETH_MEDIA];
-
-	if (!net_eq(dev_net(dev), &init_net))
-		return NOTIFY_DONE;
-
-	while ((eb_ptr->dev != dev)) {
-		if (++eb_ptr == stop)
-			return NOTIFY_DONE;	/* couldn't find device */
-	}
-	if (!eb_ptr->bearer)
-		return NOTIFY_DONE;		/* bearer had been disabled */
-
-	eb_ptr->bearer->mtu = dev->mtu;
-
-	switch (evt) {
-	case NETDEV_CHANGE:
-		if (netif_carrier_ok(dev))
-			break;
-	case NETDEV_DOWN:
-	case NETDEV_CHANGEMTU:
-	case NETDEV_CHANGEADDR:
-		tipc_reset_bearer(eb_ptr->bearer);
-		break;
-	case NETDEV_UNREGISTER:
-	case NETDEV_CHANGENAME:
-		tipc_disable_bearer(eb_ptr->bearer->name);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-/**
- * eth_addr2str - convert Ethernet address to string
- */
-static int eth_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size)
-{
-	if (str_size < 18)	/* 18 = strlen("aa:bb:cc:dd:ee:ff\0") */
-		return 1;
-
-	sprintf(str_buf, "%pM", a->value);
+	memset(addr, 0, sizeof(*addr));
+	ether_addr_copy(addr->value, msg);
+	addr->media_id = TIPC_MEDIA_TYPE_ETH;
+	addr->broadcast = !memcmp(addr->value, bcast_mac, ETH_ALEN);
 	return 0;
 }
 
-/**
- * eth_str2addr - convert Ethernet address format to message header format
- */
-static int eth_addr2msg(struct tipc_media_addr *a, char *msg_area)
+/* Convert discovery msg addr format to Ethernet media addr format */
+static int tipc_eth_msg2addr(struct tipc_bearer *b,
+			     struct tipc_media_addr *addr,
+			     char *msg)
 {
-	memset(msg_area, 0, TIPC_MEDIA_ADDR_SIZE);
-	msg_area[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_ETH;
-	memcpy(msg_area + ETH_ADDR_OFFSET, a->value, ETH_ALEN);
-	return 0;
+	/* Skip past preamble: */
+	msg += ETH_ADDR_OFFSET;
+	return tipc_eth_raw2addr(b, addr, msg);
 }
 
-/**
- * eth_str2addr - convert message header address format to Ethernet format
- */
-static int eth_msg2addr(const struct tipc_bearer *tb_ptr,
-			struct tipc_media_addr *a, char *msg_area)
-{
-	if (msg_area[TIPC_MEDIA_TYPE_OFFSET] != TIPC_MEDIA_TYPE_ETH)
-		return 1;
-
-	eth_media_addr_set(tb_ptr, a, msg_area + ETH_ADDR_OFFSET);
-	return 0;
-}
-
-/*
- * Ethernet media registration info
- */
-static struct tipc_media eth_media_info = {
-	.send_msg	= send_msg,
-	.enable_media	= enable_media,
-	.disable_media	= disable_media,
-	.addr2str	= eth_addr2str,
-	.addr2msg	= eth_addr2msg,
-	.msg2addr	= eth_msg2addr,
+/* Ethernet media registration info */
+struct tipc_media eth_media_info = {
+	.send_msg	= tipc_l2_send_msg,
+	.enable_media	= tipc_enable_l2_media,
+	.disable_media	= tipc_disable_l2_media,
+	.addr2str	= tipc_eth_addr2str,
+	.addr2msg	= tipc_eth_addr2msg,
+	.msg2addr	= tipc_eth_msg2addr,
+	.raw2addr	= tipc_eth_raw2addr,
 	.priority	= TIPC_DEF_LINK_PRI,
 	.tolerance	= TIPC_DEF_LINK_TOL,
 	.window		= TIPC_DEF_LINK_WIN,
 	.type_id	= TIPC_MEDIA_TYPE_ETH,
+	.hwaddr_len	= ETH_ALEN,
 	.name		= "eth"
 };
-
-/**
- * tipc_eth_media_start - activate Ethernet bearer support
- *
- * Register Ethernet media type with TIPC bearer code.  Also register
- * with OS for notifications about device state changes.
- */
-int tipc_eth_media_start(void)
-{
-	int res;
-
-	if (eth_started)
-		return -EINVAL;
-
-	res = tipc_register_media(&eth_media_info);
-	if (res)
-		return res;
-
-	res = register_netdevice_notifier(&notifier);
-	if (!res)
-		eth_started = 1;
-	return res;
-}
-
-/**
- * tipc_eth_media_stop - deactivate Ethernet bearer support
- */
-void tipc_eth_media_stop(void)
-{
-	if (!eth_started)
-		return;
-
-	flush_scheduled_work();
-	unregister_netdevice_notifier(&notifier);
-	eth_started = 0;
-}
diff --git a/net/tipc/handler.c b/net/tipc/handler.c
deleted file mode 100644
index b36f0fcd9bd..00000000000
--- a/net/tipc/handler.c
+++ /dev/null
@@ -1,130 +0,0 @@
-/*
- * net/tipc/handler.c: TIPC signal handling
- *
- * Copyright (c) 2000-2006, Ericsson AB
- * Copyright (c) 2005, Wind River Systems
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include "core.h"
-
-struct queue_item {
-	struct list_head next_signal;
-	void (*handler) (unsigned long);
-	unsigned long data;
-};
-
-static struct kmem_cache *tipc_queue_item_cache;
-static struct list_head signal_queue_head;
-static DEFINE_SPINLOCK(qitem_lock);
-static int handler_enabled __read_mostly;
-
-static void process_signal_queue(unsigned long dummy);
-
-static DECLARE_TASKLET_DISABLED(tipc_tasklet, process_signal_queue, 0);
-
-
-unsigned int tipc_k_signal(Handler routine, unsigned long argument)
-{
-	struct queue_item *item;
-
-	if (!handler_enabled) {
-		pr_err("Signal request ignored by handler\n");
-		return -ENOPROTOOPT;
-	}
-
-	spin_lock_bh(&qitem_lock);
-	item = kmem_cache_alloc(tipc_queue_item_cache, GFP_ATOMIC);
-	if (!item) {
-		pr_err("Signal queue out of memory\n");
-		spin_unlock_bh(&qitem_lock);
-		return -ENOMEM;
-	}
-	item->handler = routine;
-	item->data = argument;
-	list_add_tail(&item->next_signal, &signal_queue_head);
-	spin_unlock_bh(&qitem_lock);
-	tasklet_schedule(&tipc_tasklet);
-	return 0;
-}
-
-static void process_signal_queue(unsigned long dummy)
-{
-	struct queue_item *__volatile__ item;
-	struct list_head *l, *n;
-
-	spin_lock_bh(&qitem_lock);
-	list_for_each_safe(l, n, &signal_queue_head) {
-		item = list_entry(l, struct queue_item, next_signal);
-		list_del(&item->next_signal);
-		spin_unlock_bh(&qitem_lock);
-		item->handler(item->data);
-		spin_lock_bh(&qitem_lock);
-		kmem_cache_free(tipc_queue_item_cache, item);
-	}
-	spin_unlock_bh(&qitem_lock);
-}
-
-int tipc_handler_start(void)
-{
-	tipc_queue_item_cache =
-		kmem_cache_create("tipc_queue_items", sizeof(struct queue_item),
-				  0, SLAB_HWCACHE_ALIGN, NULL);
-	if (!tipc_queue_item_cache)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&signal_queue_head);
-	tasklet_enable(&tipc_tasklet);
-	handler_enabled = 1;
-	return 0;
-}
-
-void tipc_handler_stop(void)
-{
-	struct list_head *l, *n;
-	struct queue_item *item;
-
-	if (!handler_enabled)
-		return;
-
-	handler_enabled = 0;
-	tasklet_kill(&tipc_tasklet);
-
-	spin_lock_bh(&qitem_lock);
-	list_for_each_safe(l, n, &signal_queue_head) {
-		item = list_entry(l, struct queue_item, next_signal);
-		list_del(&item->next_signal);
-		kmem_cache_free(tipc_queue_item_cache, item);
-	}
-	spin_unlock_bh(&qitem_lock);
-
-	kmem_cache_destroy(tipc_queue_item_cache);
-}
diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c
index cbe7fe15cc7..8522eef9c13 100644
--- a/net/tipc/ib_media.c
+++ b/net/tipc/ib_media.c
@@ -42,242 +42,9 @@
 #include "core.h"
 #include "bearer.h"
 
-#define MAX_IB_MEDIA		MAX_BEARERS
-
-/**
- * struct ib_media - Infiniband media data structure
- * @bearer: ptr to associated "generic" bearer structure
- * @dev: ptr to associated Infiniband network device
- * @tipc_packet_type: used in binding TIPC to Infiniband driver
- * @cleanup: work item used when disabling bearer
- */
-
-struct ib_media {
-	struct tipc_bearer *bearer;
-	struct net_device *dev;
-	struct packet_type tipc_packet_type;
-	struct work_struct setup;
-	struct work_struct cleanup;
-};
-
-static struct tipc_media ib_media_info;
-static struct ib_media ib_media_array[MAX_IB_MEDIA];
-static int ib_started;
-
-/**
- * ib_media_addr_set - initialize Infiniband media address structure
- *
- * Media-dependent "value" field stores MAC address in first 6 bytes
- * and zeroes out the remaining bytes.
- */
-static void ib_media_addr_set(const struct tipc_bearer *tb_ptr,
-			      struct tipc_media_addr *a, char *mac)
-{
-	BUILD_BUG_ON(sizeof(a->value) < INFINIBAND_ALEN);
-	memcpy(a->value, mac, INFINIBAND_ALEN);
-	a->media_id = TIPC_MEDIA_TYPE_IB;
-	a->broadcast = !memcmp(mac, tb_ptr->bcast_addr.value, INFINIBAND_ALEN);
-}
-
-/**
- * send_msg - send a TIPC message out over an InfiniBand interface
- */
-static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr,
-		    struct tipc_media_addr *dest)
-{
-	struct sk_buff *clone;
-	struct net_device *dev;
-	int delta;
-
-	clone = skb_clone(buf, GFP_ATOMIC);
-	if (!clone)
-		return 0;
-
-	dev = ((struct ib_media *)(tb_ptr->usr_handle))->dev;
-	delta = dev->hard_header_len - skb_headroom(buf);
-
-	if ((delta > 0) &&
-	    pskb_expand_head(clone, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
-		kfree_skb(clone);
-		return 0;
-	}
-
-	skb_reset_network_header(clone);
-	clone->dev = dev;
-	clone->protocol = htons(ETH_P_TIPC);
-	dev_hard_header(clone, dev, ETH_P_TIPC, dest->value,
-			dev->dev_addr, clone->len);
-	dev_queue_xmit(clone);
-	return 0;
-}
-
-/**
- * recv_msg - handle incoming TIPC message from an InfiniBand interface
- *
- * Accept only packets explicitly sent to this node, or broadcast packets;
- * ignores packets sent using InfiniBand multicast, and traffic sent to other
- * nodes (which can happen if interface is running in promiscuous mode).
- */
-static int recv_msg(struct sk_buff *buf, struct net_device *dev,
-		    struct packet_type *pt, struct net_device *orig_dev)
-{
-	struct ib_media *ib_ptr = (struct ib_media *)pt->af_packet_priv;
-
-	if (!net_eq(dev_net(dev), &init_net)) {
-		kfree_skb(buf);
-		return NET_RX_DROP;
-	}
-
-	if (likely(ib_ptr->bearer)) {
-		if (likely(buf->pkt_type <= PACKET_BROADCAST)) {
-			buf->next = NULL;
-			tipc_recv_msg(buf, ib_ptr->bearer);
-			return NET_RX_SUCCESS;
-		}
-	}
-	kfree_skb(buf);
-	return NET_RX_DROP;
-}
-
-/**
- * setup_bearer - setup association between InfiniBand bearer and interface
- */
-static void setup_media(struct work_struct *work)
-{
-	struct ib_media *ib_ptr =
-		container_of(work, struct ib_media, setup);
-
-	dev_add_pack(&ib_ptr->tipc_packet_type);
-}
-
-/**
- * enable_media - attach TIPC bearer to an InfiniBand interface
- */
-static int enable_media(struct tipc_bearer *tb_ptr)
-{
-	struct net_device *dev;
-	struct ib_media *ib_ptr = &ib_media_array[0];
-	struct ib_media *stop = &ib_media_array[MAX_IB_MEDIA];
-	char *driver_name = strchr((const char *)tb_ptr->name, ':') + 1;
-	int pending_dev = 0;
-
-	/* Find unused InfiniBand bearer structure */
-	while (ib_ptr->dev) {
-		if (!ib_ptr->bearer)
-			pending_dev++;
-		if (++ib_ptr == stop)
-			return pending_dev ? -EAGAIN : -EDQUOT;
-	}
-
-	/* Find device with specified name */
-	dev = dev_get_by_name(&init_net, driver_name);
-	if (!dev)
-		return -ENODEV;
-
-	/* Create InfiniBand bearer for device */
-	ib_ptr->dev = dev;
-	ib_ptr->tipc_packet_type.type = htons(ETH_P_TIPC);
-	ib_ptr->tipc_packet_type.dev = dev;
-	ib_ptr->tipc_packet_type.func = recv_msg;
-	ib_ptr->tipc_packet_type.af_packet_priv = ib_ptr;
-	INIT_LIST_HEAD(&(ib_ptr->tipc_packet_type.list));
-	INIT_WORK(&ib_ptr->setup, setup_media);
-	schedule_work(&ib_ptr->setup);
-
-	/* Associate TIPC bearer with InfiniBand bearer */
-	ib_ptr->bearer = tb_ptr;
-	tb_ptr->usr_handle = (void *)ib_ptr;
-	memset(tb_ptr->bcast_addr.value, 0, sizeof(tb_ptr->bcast_addr.value));
-	memcpy(tb_ptr->bcast_addr.value, dev->broadcast, INFINIBAND_ALEN);
-	tb_ptr->bcast_addr.media_id = TIPC_MEDIA_TYPE_IB;
-	tb_ptr->bcast_addr.broadcast = 1;
-	tb_ptr->mtu = dev->mtu;
-	ib_media_addr_set(tb_ptr, &tb_ptr->addr, (char *)dev->dev_addr);
-	return 0;
-}
-
-/**
- * cleanup_bearer - break association between InfiniBand bearer and interface
- *
- * This routine must be invoked from a work queue because it can sleep.
- */
-static void cleanup_bearer(struct work_struct *work)
-{
-	struct ib_media *ib_ptr =
-		container_of(work, struct ib_media, cleanup);
-
-	dev_remove_pack(&ib_ptr->tipc_packet_type);
-	dev_put(ib_ptr->dev);
-	ib_ptr->dev = NULL;
-}
-
-/**
- * disable_media - detach TIPC bearer from an InfiniBand interface
- *
- * Mark InfiniBand bearer as inactive so that incoming buffers are thrown away,
- * then get worker thread to complete bearer cleanup.  (Can't do cleanup
- * here because cleanup code needs to sleep and caller holds spinlocks.)
- */
-static void disable_media(struct tipc_bearer *tb_ptr)
-{
-	struct ib_media *ib_ptr = (struct ib_media *)tb_ptr->usr_handle;
-
-	ib_ptr->bearer = NULL;
-	INIT_WORK(&ib_ptr->cleanup, cleanup_bearer);
-	schedule_work(&ib_ptr->cleanup);
-}
-
-/**
- * recv_notification - handle device updates from OS
- *
- * Change the state of the InfiniBand bearer (if any) associated with the
- * specified device.
- */
-static int recv_notification(struct notifier_block *nb, unsigned long evt,
-			     void *ptr)
-{
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct ib_media *ib_ptr = &ib_media_array[0];
-	struct ib_media *stop = &ib_media_array[MAX_IB_MEDIA];
-
-	if (!net_eq(dev_net(dev), &init_net))
-		return NOTIFY_DONE;
-
-	while ((ib_ptr->dev != dev)) {
-		if (++ib_ptr == stop)
-			return NOTIFY_DONE;	/* couldn't find device */
-	}
-	if (!ib_ptr->bearer)
-		return NOTIFY_DONE;		/* bearer had been disabled */
-
-	ib_ptr->bearer->mtu = dev->mtu;
-
-	switch (evt) {
-	case NETDEV_CHANGE:
-		if (netif_carrier_ok(dev))
-			break;
-	case NETDEV_DOWN:
-	case NETDEV_CHANGEMTU:
-	case NETDEV_CHANGEADDR:
-		tipc_reset_bearer(ib_ptr->bearer);
-		break;
-	case NETDEV_UNREGISTER:
-	case NETDEV_CHANGENAME:
-		tipc_disable_bearer(ib_ptr->bearer->name);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block notifier = {
-	.notifier_call	= recv_notification,
-	.priority	= 0,
-};
-
-/**
- * ib_addr2str - convert InfiniBand address to string
- */
-static int ib_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size)
+/* convert InfiniBand address (media address format) media address to string */
+static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf,
+			    int str_size)
 {
 	if (str_size < 60)	/* 60 = 19 * strlen("xx:") + strlen("xx\0") */
 		return 1;
@@ -287,76 +54,48 @@ static int ib_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size)
 	return 0;
 }
 
-/**
- * ib_addr2msg - convert InfiniBand address format to message header format
- */
-static int ib_addr2msg(struct tipc_media_addr *a, char *msg_area)
+/* Convert from media address format to discovery message addr format */
+static int tipc_ib_addr2msg(char *msg, struct tipc_media_addr *addr)
 {
-	memset(msg_area, 0, TIPC_MEDIA_ADDR_SIZE);
-	msg_area[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_IB;
-	memcpy(msg_area, a->value, INFINIBAND_ALEN);
+	memset(msg, 0, TIPC_MEDIA_ADDR_SIZE);
+	memcpy(msg, addr->value, INFINIBAND_ALEN);
 	return 0;
 }
 
-/**
- * ib_msg2addr - convert message header address format to InfiniBand format
- */
-static int ib_msg2addr(const struct tipc_bearer *tb_ptr,
-		       struct tipc_media_addr *a, char *msg_area)
+/* Convert raw InfiniBand address format to media addr format */
+static int tipc_ib_raw2addr(struct tipc_bearer *b,
+			    struct tipc_media_addr *addr,
+			    char *msg)
 {
-	ib_media_addr_set(tb_ptr, a, msg_area);
+	memset(addr, 0, sizeof(*addr));
+	memcpy(addr->value, msg, INFINIBAND_ALEN);
+	addr->media_id = TIPC_MEDIA_TYPE_IB;
+	addr->broadcast = !memcmp(msg, b->bcast_addr.value,
+				  INFINIBAND_ALEN);
 	return 0;
 }
 
-/*
- * InfiniBand media registration info
- */
-static struct tipc_media ib_media_info = {
-	.send_msg	= send_msg,
-	.enable_media	= enable_media,
-	.disable_media	= disable_media,
-	.addr2str	= ib_addr2str,
-	.addr2msg	= ib_addr2msg,
-	.msg2addr	= ib_msg2addr,
+/* Convert discovery msg addr format to InfiniBand media addr format */
+static int tipc_ib_msg2addr(struct tipc_bearer *b,
+			    struct tipc_media_addr *addr,
+			    char *msg)
+{
+	return tipc_ib_raw2addr(b, addr, msg);
+}
+
+/* InfiniBand media registration info */
+struct tipc_media ib_media_info = {
+	.send_msg	= tipc_l2_send_msg,
+	.enable_media	= tipc_enable_l2_media,
+	.disable_media	= tipc_disable_l2_media,
+	.addr2str	= tipc_ib_addr2str,
+	.addr2msg	= tipc_ib_addr2msg,
+	.msg2addr	= tipc_ib_msg2addr,
+	.raw2addr	= tipc_ib_raw2addr,
 	.priority	= TIPC_DEF_LINK_PRI,
 	.tolerance	= TIPC_DEF_LINK_TOL,
 	.window		= TIPC_DEF_LINK_WIN,
 	.type_id	= TIPC_MEDIA_TYPE_IB,
+	.hwaddr_len	= INFINIBAND_ALEN,
 	.name		= "ib"
 };
-
-/**
- * tipc_ib_media_start - activate InfiniBand bearer support
- *
- * Register InfiniBand media type with TIPC bearer code.  Also register
- * with OS for notifications about device state changes.
- */
-int tipc_ib_media_start(void)
-{
-	int res;
-
-	if (ib_started)
-		return -EINVAL;
-
-	res = tipc_register_media(&ib_media_info);
-	if (res)
-		return res;
-
-	res = register_netdevice_notifier(&notifier);
-	if (!res)
-		ib_started = 1;
-	return res;
-}
-
-/**
- * tipc_ib_media_stop - deactivate InfiniBand bearer support
- */
-void tipc_ib_media_stop(void)
-{
-	if (!ib_started)
-		return;
-
-	flush_scheduled_work();
-	unregister_netdevice_notifier(&notifier);
-	ib_started = 0;
-}
diff --git a/net/tipc/link.c b/net/tipc/link.c
index fd340ad742e..ad2c57f5868 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/link.c: TIPC link code
  *
- * Copyright (c) 1996-2007, 2012, Ericsson AB
+ * Copyright (c) 1996-2007, 2012-2014, Ericsson AB
  * Copyright (c) 2004-2007, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -37,6 +37,7 @@
 #include "core.h"
 #include "link.h"
 #include "port.h"
+#include "socket.h"
 #include "name_distr.h"
 #include "discover.h"
 #include "config.h"
@@ -77,20 +78,19 @@ static const char *link_unk_evt = "Unknown link event ";
 
 static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr,
 				       struct sk_buff *buf);
-static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf);
-static int  link_recv_changeover_msg(struct tipc_link **l_ptr,
-				     struct sk_buff **buf);
+static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf);
+static int  tipc_link_tunnel_rcv(struct tipc_node *n_ptr,
+				 struct sk_buff **buf);
 static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance);
-static int  link_send_sections_long(struct tipc_port *sender,
-				    struct iovec const *msg_sect,
-				    unsigned int len, u32 destnode);
+static int  tipc_link_iovec_long_xmit(struct tipc_port *sender,
+				      struct iovec const *msg_sect,
+				      unsigned int len, u32 destnode);
 static void link_state_event(struct tipc_link *l_ptr, u32 event);
 static void link_reset_statistics(struct tipc_link *l_ptr);
 static void link_print(struct tipc_link *l_ptr, const char *str);
-static void link_start(struct tipc_link *l_ptr);
-static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf);
-static void tipc_link_send_sync(struct tipc_link *l);
-static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf);
+static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf);
+static void tipc_link_sync_xmit(struct tipc_link *l);
+static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf);
 
 /*
  *  Simple link routines
@@ -102,9 +102,18 @@ static unsigned int align(unsigned int i)
 
 static void link_init_max_pkt(struct tipc_link *l_ptr)
 {
+	struct tipc_bearer *b_ptr;
 	u32 max_pkt;
 
-	max_pkt = (l_ptr->b_ptr->mtu & ~3);
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(bearer_list[l_ptr->bearer_id]);
+	if (!b_ptr) {
+		rcu_read_unlock();
+		return;
+	}
+	max_pkt = (b_ptr->mtu & ~3);
+	rcu_read_unlock();
+
 	if (max_pkt > MAX_MSG_SIZE)
 		max_pkt = MAX_MSG_SIZE;
 
@@ -148,11 +157,6 @@ int tipc_link_is_active(struct tipc_link *l_ptr)
 /**
  * link_timeout - handle expiration of link timer
  * @l_ptr: pointer to link
- *
- * This routine must not grab "tipc_net_lock" to avoid a potential deadlock conflict
- * with tipc_link_delete().  (There is no risk that the node will be deleted by
- * another thread because tipc_link_delete() always cancels the link timer before
- * tipc_node_delete() is called.)
  */
 static void link_timeout(struct tipc_link *l_ptr)
 {
@@ -214,8 +218,8 @@ static void link_set_timer(struct tipc_link *l_ptr, u32 time)
  * Returns pointer to link.
  */
 struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
-			      struct tipc_bearer *b_ptr,
-			      const struct tipc_media_addr *media_addr)
+				   struct tipc_bearer *b_ptr,
+				   const struct tipc_media_addr *media_addr)
 {
 	struct tipc_link *l_ptr;
 	struct tipc_msg *msg;
@@ -254,7 +258,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
 	l_ptr->owner = n_ptr;
 	l_ptr->checkpoint = 1;
 	l_ptr->peer_session = INVALID_SESSION;
-	l_ptr->b_ptr = b_ptr;
+	l_ptr->bearer_id = b_ptr->identity;
 	link_set_supervision_props(l_ptr, b_ptr->tolerance);
 	l_ptr->state = RESET_UNKNOWN;
 
@@ -269,6 +273,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
 	l_ptr->priority = b_ptr->priority;
 	tipc_link_set_queue_limits(l_ptr, b_ptr->window);
 
+	l_ptr->net_plane = b_ptr->net_plane;
 	link_init_max_pkt(l_ptr);
 
 	l_ptr->next_out_no = 1;
@@ -278,45 +283,44 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
 
 	tipc_node_attach_link(n_ptr, l_ptr);
 
-	k_init_timer(&l_ptr->timer, (Handler)link_timeout, (unsigned long)l_ptr);
-	list_add_tail(&l_ptr->link_list, &b_ptr->links);
-	tipc_k_signal((Handler)link_start, (unsigned long)l_ptr);
+	k_init_timer(&l_ptr->timer, (Handler)link_timeout,
+		     (unsigned long)l_ptr);
+
+	link_state_event(l_ptr, STARTING_EVT);
 
 	return l_ptr;
 }
 
-/**
- * tipc_link_delete - delete a link
- * @l_ptr: pointer to link
- *
- * Note: 'tipc_net_lock' is write_locked, bearer is locked.
- * This routine must not grab the node lock until after link timer cancellation
- * to avoid a potential deadlock situation.
- */
-void tipc_link_delete(struct tipc_link *l_ptr)
+void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down)
 {
-	if (!l_ptr) {
-		pr_err("Attempt to delete non-existent link\n");
-		return;
-	}
-
-	k_cancel_timer(&l_ptr->timer);
+	struct tipc_link *l_ptr;
+	struct tipc_node *n_ptr;
 
-	tipc_node_lock(l_ptr->owner);
-	tipc_link_reset(l_ptr);
-	tipc_node_detach_link(l_ptr->owner, l_ptr);
-	tipc_link_stop(l_ptr);
-	list_del_init(&l_ptr->link_list);
-	tipc_node_unlock(l_ptr->owner);
-	k_term_timer(&l_ptr->timer);
-	kfree(l_ptr);
-}
+	rcu_read_lock();
+	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
+		tipc_node_lock(n_ptr);
+		l_ptr = n_ptr->links[bearer_id];
+		if (l_ptr) {
+			tipc_link_reset(l_ptr);
+			if (shutting_down || !tipc_node_is_up(n_ptr)) {
+				tipc_node_detach_link(l_ptr->owner, l_ptr);
+				tipc_link_reset_fragments(l_ptr);
+				tipc_node_unlock(n_ptr);
 
-static void link_start(struct tipc_link *l_ptr)
-{
-	tipc_node_lock(l_ptr->owner);
-	link_state_event(l_ptr, STARTING_EVT);
-	tipc_node_unlock(l_ptr->owner);
+				/* Nobody else can access this link now: */
+				del_timer_sync(&l_ptr->timer);
+				kfree(l_ptr);
+			} else {
+				/* Detach/delete when failover is finished: */
+				l_ptr->flags |= LINK_STOPPED;
+				tipc_node_unlock(n_ptr);
+				del_timer_sync(&l_ptr->timer);
+			}
+			continue;
+		}
+		tipc_node_unlock(n_ptr);
+	}
+	rcu_read_unlock();
 }
 
 /**
@@ -335,8 +339,6 @@ static int link_schedule_port(struct tipc_link *l_ptr, u32 origport, u32 sz)
 	spin_lock_bh(&tipc_port_list_lock);
 	p_ptr = tipc_port_lock(origport);
 	if (p_ptr) {
-		if (!p_ptr->wakeup)
-			goto exit;
 		if (!list_empty(&p_ptr->wait_list))
 			goto exit;
 		p_ptr->congested = 1;
@@ -371,7 +373,7 @@ void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all)
 		list_del_init(&p_ptr->wait_list);
 		spin_lock_bh(p_ptr->lock);
 		p_ptr->congested = 0;
-		p_ptr->wakeup(p_ptr);
+		tipc_port_wakeup(p_ptr);
 		win -= p_ptr->waiting_pkts;
 		spin_unlock_bh(p_ptr->lock);
 	}
@@ -386,14 +388,7 @@ exit:
  */
 static void link_release_outqueue(struct tipc_link *l_ptr)
 {
-	struct sk_buff *buf = l_ptr->first_out;
-	struct sk_buff *next;
-
-	while (buf) {
-		next = buf->next;
-		kfree_skb(buf);
-		buf = next;
-	}
+	kfree_skb_list(l_ptr->first_out);
 	l_ptr->first_out = NULL;
 	l_ptr->out_queue_size = 0;
 }
@@ -404,43 +399,25 @@ static void link_release_outqueue(struct tipc_link *l_ptr)
  */
 void tipc_link_reset_fragments(struct tipc_link *l_ptr)
 {
-	kfree_skb(l_ptr->reasm_head);
-	l_ptr->reasm_head = NULL;
-	l_ptr->reasm_tail = NULL;
+	kfree_skb(l_ptr->reasm_buf);
+	l_ptr->reasm_buf = NULL;
 }
 
 /**
- * tipc_link_stop - purge all inbound and outbound messages associated with link
+ * tipc_link_purge_queues - purge all pkt queues associated with link
  * @l_ptr: pointer to link
  */
-void tipc_link_stop(struct tipc_link *l_ptr)
+void tipc_link_purge_queues(struct tipc_link *l_ptr)
 {
-	struct sk_buff *buf;
-	struct sk_buff *next;
-
-	buf = l_ptr->oldest_deferred_in;
-	while (buf) {
-		next = buf->next;
-		kfree_skb(buf);
-		buf = next;
-	}
-
-	buf = l_ptr->first_out;
-	while (buf) {
-		next = buf->next;
-		kfree_skb(buf);
-		buf = next;
-	}
-
+	kfree_skb_list(l_ptr->oldest_deferred_in);
+	kfree_skb_list(l_ptr->first_out);
 	tipc_link_reset_fragments(l_ptr);
-
 	kfree_skb(l_ptr->proto_msg_queue);
 	l_ptr->proto_msg_queue = NULL;
 }
 
 void tipc_link_reset(struct tipc_link *l_ptr)
 {
-	struct sk_buff *buf;
 	u32 prev_state = l_ptr->state;
 	u32 checkpoint = l_ptr->next_in_no;
 	int was_active_link = tipc_link_is_active(l_ptr);
@@ -459,10 +436,9 @@ void tipc_link_reset(struct tipc_link *l_ptr)
 		return;
 
 	tipc_node_link_down(l_ptr->owner, l_ptr);
-	tipc_bearer_remove_dest(l_ptr->b_ptr, l_ptr->addr);
+	tipc_bearer_remove_dest(l_ptr->bearer_id, l_ptr->addr);
 
-	if (was_active_link && tipc_node_active_links(l_ptr->owner) &&
-	    l_ptr->owner->permit_changeover) {
+	if (was_active_link && tipc_node_active_links(l_ptr->owner)) {
 		l_ptr->reset_checkpoint = checkpoint;
 		l_ptr->exp_msg_count = START_CHANGEOVER;
 	}
@@ -471,12 +447,7 @@ void tipc_link_reset(struct tipc_link *l_ptr)
 	link_release_outqueue(l_ptr);
 	kfree_skb(l_ptr->proto_msg_queue);
 	l_ptr->proto_msg_queue = NULL;
-	buf = l_ptr->oldest_deferred_in;
-	while (buf) {
-		struct sk_buff *next = buf->next;
-		kfree_skb(buf);
-		buf = next;
-	}
+	kfree_skb_list(l_ptr->oldest_deferred_in);
 	if (!list_empty(&l_ptr->waiting_ports))
 		tipc_link_wakeup_ports(l_ptr, 1);
 
@@ -496,12 +467,27 @@ void tipc_link_reset(struct tipc_link *l_ptr)
 	link_reset_statistics(l_ptr);
 }
 
+void tipc_link_reset_list(unsigned int bearer_id)
+{
+	struct tipc_link *l_ptr;
+	struct tipc_node *n_ptr;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
+		tipc_node_lock(n_ptr);
+		l_ptr = n_ptr->links[bearer_id];
+		if (l_ptr)
+			tipc_link_reset(l_ptr);
+		tipc_node_unlock(n_ptr);
+	}
+	rcu_read_unlock();
+}
 
 static void link_activate(struct tipc_link *l_ptr)
 {
 	l_ptr->next_in_no = l_ptr->stats.recv_info = 1;
 	tipc_node_link_up(l_ptr->owner, l_ptr);
-	tipc_bearer_add_dest(l_ptr->b_ptr, l_ptr->addr);
+	tipc_bearer_add_dest(l_ptr->bearer_id, l_ptr->addr);
 }
 
 /**
@@ -514,13 +500,17 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 	struct tipc_link *other;
 	u32 cont_intv = l_ptr->continuity_interval;
 
-	if (!l_ptr->started && (event != STARTING_EVT))
+	if (l_ptr->flags & LINK_STOPPED)
+		return;
+
+	if (!(l_ptr->flags & LINK_STARTED) && (event != STARTING_EVT))
 		return;		/* Not yet. */
 
-	if (link_blocked(l_ptr)) {
+	/* Check whether changeover is going on */
+	if (l_ptr->exp_msg_count) {
 		if (event == TIMEOUT_EVT)
 			link_set_timer(l_ptr, cont_intv);
-		return;	  /* Changeover going on */
+		return;
 	}
 
 	switch (l_ptr->state) {
@@ -533,12 +523,12 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 			if (l_ptr->next_in_no != l_ptr->checkpoint) {
 				l_ptr->checkpoint = l_ptr->next_in_no;
 				if (tipc_bclink_acks_missing(l_ptr->owner)) {
-					tipc_link_send_proto_msg(l_ptr, STATE_MSG,
-								 0, 0, 0, 0, 0);
+					tipc_link_proto_xmit(l_ptr, STATE_MSG,
+							     0, 0, 0, 0, 0);
 					l_ptr->fsm_msg_cnt++;
 				} else if (l_ptr->max_pkt < l_ptr->max_pkt_target) {
-					tipc_link_send_proto_msg(l_ptr, STATE_MSG,
-								 1, 0, 0, 0, 0);
+					tipc_link_proto_xmit(l_ptr, STATE_MSG,
+							     1, 0, 0, 0, 0);
 					l_ptr->fsm_msg_cnt++;
 				}
 				link_set_timer(l_ptr, cont_intv);
@@ -546,7 +536,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 			}
 			l_ptr->state = WORKING_UNKNOWN;
 			l_ptr->fsm_msg_cnt = 0;
-			tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv / 4);
 			break;
@@ -556,7 +546,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 			tipc_link_reset(l_ptr);
 			l_ptr->state = RESET_RESET;
 			l_ptr->fsm_msg_cnt = 0;
-			tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
+					     0, 0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv);
 			break;
@@ -578,7 +569,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 			tipc_link_reset(l_ptr);
 			l_ptr->state = RESET_RESET;
 			l_ptr->fsm_msg_cnt = 0;
-			tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
+					     0, 0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv);
 			break;
@@ -588,14 +580,14 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 				l_ptr->fsm_msg_cnt = 0;
 				l_ptr->checkpoint = l_ptr->next_in_no;
 				if (tipc_bclink_acks_missing(l_ptr->owner)) {
-					tipc_link_send_proto_msg(l_ptr, STATE_MSG,
-								 0, 0, 0, 0, 0);
+					tipc_link_proto_xmit(l_ptr, STATE_MSG,
+							     0, 0, 0, 0, 0);
 					l_ptr->fsm_msg_cnt++;
 				}
 				link_set_timer(l_ptr, cont_intv);
 			} else if (l_ptr->fsm_msg_cnt < l_ptr->abort_limit) {
-				tipc_link_send_proto_msg(l_ptr, STATE_MSG,
-							 1, 0, 0, 0, 0);
+				tipc_link_proto_xmit(l_ptr, STATE_MSG,
+						     1, 0, 0, 0, 0);
 				l_ptr->fsm_msg_cnt++;
 				link_set_timer(l_ptr, cont_intv / 4);
 			} else {	/* Link has failed */
@@ -604,8 +596,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 				tipc_link_reset(l_ptr);
 				l_ptr->state = RESET_UNKNOWN;
 				l_ptr->fsm_msg_cnt = 0;
-				tipc_link_send_proto_msg(l_ptr, RESET_MSG,
-							 0, 0, 0, 0, 0);
+				tipc_link_proto_xmit(l_ptr, RESET_MSG,
+						     0, 0, 0, 0, 0);
 				l_ptr->fsm_msg_cnt++;
 				link_set_timer(l_ptr, cont_intv);
 			}
@@ -625,24 +617,25 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 			l_ptr->state = WORKING_WORKING;
 			l_ptr->fsm_msg_cnt = 0;
 			link_activate(l_ptr);
-			tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			if (l_ptr->owner->working_links == 1)
-				tipc_link_send_sync(l_ptr);
+				tipc_link_sync_xmit(l_ptr);
 			link_set_timer(l_ptr, cont_intv);
 			break;
 		case RESET_MSG:
 			l_ptr->state = RESET_RESET;
 			l_ptr->fsm_msg_cnt = 0;
-			tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 1, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
+					     1, 0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv);
 			break;
 		case STARTING_EVT:
-			l_ptr->started = 1;
+			l_ptr->flags |= LINK_STARTED;
 			/* fall through */
 		case TIMEOUT_EVT:
-			tipc_link_send_proto_msg(l_ptr, RESET_MSG, 0, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv);
 			break;
@@ -660,16 +653,17 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
 			l_ptr->state = WORKING_WORKING;
 			l_ptr->fsm_msg_cnt = 0;
 			link_activate(l_ptr);
-			tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			if (l_ptr->owner->working_links == 1)
-				tipc_link_send_sync(l_ptr);
+				tipc_link_sync_xmit(l_ptr);
 			link_set_timer(l_ptr, cont_intv);
 			break;
 		case RESET_MSG:
 			break;
 		case TIMEOUT_EVT:
-			tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG,
+					     0, 0, 0, 0, 0);
 			l_ptr->fsm_msg_cnt++;
 			link_set_timer(l_ptr, cont_intv);
 			break;
@@ -755,11 +749,11 @@ static void link_add_chain_to_outqueue(struct tipc_link *l_ptr,
 }
 
 /*
- * tipc_link_send_buf() is the 'full path' for messages, called from
- * inside TIPC when the 'fast path' in tipc_send_buf
+ * tipc_link_xmit() is the 'full path' for messages, called from
+ * inside TIPC when the 'fast path' in tipc_send_xmit
  * has failed, and from link_send()
  */
-int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf)
+int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf)
 {
 	struct tipc_msg *msg = buf_msg(buf);
 	u32 size = msg_size(msg);
@@ -787,13 +781,13 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf)
 
 	/* Fragmentation needed ? */
 	if (size > max_packet)
-		return link_send_long_buf(l_ptr, buf);
+		return tipc_link_frag_xmit(l_ptr, buf);
 
 	/* Packet can be queued or sent. */
 	if (likely(!link_congested(l_ptr))) {
 		link_add_to_outqueue(l_ptr, buf, msg);
 
-		tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+		tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
 		l_ptr->unacked_window = 0;
 		return dsz;
 	}
@@ -831,42 +825,40 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf)
 }
 
 /*
- * tipc_link_send(): same as tipc_link_send_buf(), but the link to use has
- * not been selected yet, and the the owner node is not locked
+ * tipc_link_xmit(): same as __tipc_link_xmit(), but the link to use
+ * has not been selected yet, and the the owner node is not locked
  * Called by TIPC internal users, e.g. the name distributor
  */
-int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector)
+int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector)
 {
 	struct tipc_link *l_ptr;
 	struct tipc_node *n_ptr;
 	int res = -ELINKCONG;
 
-	read_lock_bh(&tipc_net_lock);
 	n_ptr = tipc_node_find(dest);
 	if (n_ptr) {
 		tipc_node_lock(n_ptr);
 		l_ptr = n_ptr->active_links[selector & 1];
 		if (l_ptr)
-			res = tipc_link_send_buf(l_ptr, buf);
+			res = __tipc_link_xmit(l_ptr, buf);
 		else
 			kfree_skb(buf);
 		tipc_node_unlock(n_ptr);
 	} else {
 		kfree_skb(buf);
 	}
-	read_unlock_bh(&tipc_net_lock);
 	return res;
 }
 
 /*
- * tipc_link_send_sync - synchronize broadcast link endpoints.
+ * tipc_link_sync_xmit - synchronize broadcast link endpoints.
  *
  * Give a newly added peer node the sequence number where it should
  * start receiving and acking broadcast packets.
  *
  * Called with node locked
  */
-static void tipc_link_send_sync(struct tipc_link *l)
+static void tipc_link_sync_xmit(struct tipc_link *l)
 {
 	struct sk_buff *buf;
 	struct tipc_msg *msg;
@@ -883,14 +875,14 @@ static void tipc_link_send_sync(struct tipc_link *l)
 }
 
 /*
- * tipc_link_recv_sync - synchronize broadcast link endpoints.
+ * tipc_link_sync_rcv - synchronize broadcast link endpoints.
  * Receive the sequence number where we should start receiving and
  * acking broadcast packets from a newly added peer node, and open
  * up for reception of such packets.
  *
  * Called with node locked
  */
-static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf)
+static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf)
 {
 	struct tipc_msg *msg = buf_msg(buf);
 
@@ -900,7 +892,7 @@ static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf)
 }
 
 /*
- * tipc_link_send_names - send name table entries to new neighbor
+ * tipc_link_names_xmit - send name table entries to new neighbor
  *
  * Send routine for bulk delivery of name table messages when contact
  * with a new neighbor occurs. No link congestion checking is performed
@@ -908,7 +900,7 @@ static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf)
  * small enough not to require fragmentation.
  * Called without any locks held.
  */
-void tipc_link_send_names(struct list_head *message_list, u32 dest)
+void tipc_link_names_xmit(struct list_head *message_list, u32 dest)
 {
 	struct tipc_node *n_ptr;
 	struct tipc_link *l_ptr;
@@ -918,7 +910,6 @@ void tipc_link_send_names(struct list_head *message_list, u32 dest)
 	if (list_empty(message_list))
 		return;
 
-	read_lock_bh(&tipc_net_lock);
 	n_ptr = tipc_node_find(dest);
 	if (n_ptr) {
 		tipc_node_lock(n_ptr);
@@ -933,7 +924,6 @@ void tipc_link_send_names(struct list_head *message_list, u32 dest)
 		}
 		tipc_node_unlock(n_ptr);
 	}
-	read_unlock_bh(&tipc_net_lock);
 
 	/* discard the messages if they couldn't be sent */
 	list_for_each_safe(buf, temp_buf, ((struct sk_buff *)message_list)) {
@@ -943,13 +933,13 @@ void tipc_link_send_names(struct list_head *message_list, u32 dest)
 }
 
 /*
- * link_send_buf_fast: Entry for data messages where the
+ * tipc_link_xmit_fast: Entry for data messages where the
  * destination link is known and the header is complete,
  * inclusive total message length. Very time critical.
  * Link is locked. Returns user data length.
  */
-static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf,
-			      u32 *used_max_pkt)
+static int tipc_link_xmit_fast(struct tipc_link *l_ptr, struct sk_buff *buf,
+			       u32 *used_max_pkt)
 {
 	struct tipc_msg *msg = buf_msg(buf);
 	int res = msg_data_sz(msg);
@@ -957,7 +947,7 @@ static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf,
 	if (likely(!link_congested(l_ptr))) {
 		if (likely(msg_size(msg) <= l_ptr->max_pkt)) {
 			link_add_to_outqueue(l_ptr, buf, msg);
-			tipc_bearer_send(l_ptr->b_ptr, buf,
+			tipc_bearer_send(l_ptr->bearer_id, buf,
 					 &l_ptr->media_addr);
 			l_ptr->unacked_window = 0;
 			return res;
@@ -965,18 +955,18 @@ static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf,
 		else
 			*used_max_pkt = l_ptr->max_pkt;
 	}
-	return tipc_link_send_buf(l_ptr, buf);  /* All other cases */
+	return __tipc_link_xmit(l_ptr, buf);  /* All other cases */
 }
 
 /*
- * tipc_link_send_sections_fast: Entry for messages where the
+ * tipc_link_iovec_xmit_fast: Entry for messages where the
  * destination processor is known and the header is complete,
  * except for total message length.
  * Returns user data length or errno.
  */
-int tipc_link_send_sections_fast(struct tipc_port *sender,
-				 struct iovec const *msg_sect,
-				 unsigned int len, u32 destaddr)
+int tipc_link_iovec_xmit_fast(struct tipc_port *sender,
+			      struct iovec const *msg_sect,
+			      unsigned int len, u32 destaddr)
 {
 	struct tipc_msg *hdr = &sender->phdr;
 	struct tipc_link *l_ptr;
@@ -995,18 +985,16 @@ again:
 	if (unlikely(res < 0))
 		return res;
 
-	read_lock_bh(&tipc_net_lock);
 	node = tipc_node_find(destaddr);
 	if (likely(node)) {
 		tipc_node_lock(node);
 		l_ptr = node->active_links[selector];
 		if (likely(l_ptr)) {
 			if (likely(buf)) {
-				res = link_send_buf_fast(l_ptr, buf,
-							 &sender->max_pkt);
+				res = tipc_link_xmit_fast(l_ptr, buf,
+							  &sender->max_pkt);
 exit:
 				tipc_node_unlock(node);
-				read_unlock_bh(&tipc_net_lock);
 				return res;
 			}
 
@@ -1023,30 +1011,25 @@ exit:
 			 */
 			sender->max_pkt = l_ptr->max_pkt;
 			tipc_node_unlock(node);
-			read_unlock_bh(&tipc_net_lock);
 
 
 			if ((msg_hdr_sz(hdr) + res) <= sender->max_pkt)
 				goto again;
 
-			return link_send_sections_long(sender, msg_sect, len,
-						       destaddr);
+			return tipc_link_iovec_long_xmit(sender, msg_sect,
+							 len, destaddr);
 		}
 		tipc_node_unlock(node);
 	}
-	read_unlock_bh(&tipc_net_lock);
 
 	/* Couldn't find a link to the destination node */
-	if (buf)
-		return tipc_reject_msg(buf, TIPC_ERR_NO_NODE);
-	if (res >= 0)
-		return tipc_port_reject_sections(sender, hdr, msg_sect,
-						 len, TIPC_ERR_NO_NODE);
-	return res;
+	kfree_skb(buf);
+	tipc_port_iovec_reject(sender, hdr, msg_sect, len, TIPC_ERR_NO_NODE);
+	return -ENETUNREACH;
 }
 
 /*
- * link_send_sections_long(): Entry for long messages where the
+ * tipc_link_iovec_long_xmit(): Entry for long messages where the
  * destination node is known and the header is complete,
  * inclusive total message length.
  * Link and bearer congestion status have been checked to be ok,
@@ -1059,9 +1042,9 @@ exit:
  *
  * Returns user data length or errno.
  */
-static int link_send_sections_long(struct tipc_port *sender,
-				   struct iovec const *msg_sect,
-				   unsigned int len, u32 destaddr)
+static int tipc_link_iovec_long_xmit(struct tipc_port *sender,
+				     struct iovec const *msg_sect,
+				     unsigned int len, u32 destaddr)
 {
 	struct tipc_link *l_ptr;
 	struct tipc_node *node;
@@ -1124,10 +1107,7 @@ again:
 		if (copy_from_user(buf->data + fragm_crs, sect_crs, sz)) {
 			res = -EFAULT;
 error:
-			for (; buf_chain; buf_chain = buf) {
-				buf = buf_chain->next;
-				kfree_skb(buf_chain);
-			}
+			kfree_skb_list(buf_chain);
 			return res;
 		}
 		sect_crs += sz;
@@ -1177,20 +1157,15 @@ error:
 		if (l_ptr->max_pkt < max_pkt) {
 			sender->max_pkt = l_ptr->max_pkt;
 			tipc_node_unlock(node);
-			for (; buf_chain; buf_chain = buf) {
-				buf = buf_chain->next;
-				kfree_skb(buf_chain);
-			}
+			kfree_skb_list(buf_chain);
 			goto again;
 		}
 	} else {
 reject:
-		for (; buf_chain; buf_chain = buf) {
-			buf = buf_chain->next;
-			kfree_skb(buf_chain);
-		}
-		return tipc_port_reject_sections(sender, hdr, msg_sect,
-						 len, TIPC_ERR_NO_NODE);
+		kfree_skb_list(buf_chain);
+		tipc_port_iovec_reject(sender, hdr, msg_sect, len,
+				       TIPC_ERR_NO_NODE);
+		return -ENETUNREACH;
 	}
 
 	/* Append chain of fragments to send queue & send them */
@@ -1206,7 +1181,7 @@ reject:
 /*
  * tipc_link_push_packet: Push one unsent packet to the media
  */
-u32 tipc_link_push_packet(struct tipc_link *l_ptr)
+static u32 tipc_link_push_packet(struct tipc_link *l_ptr)
 {
 	struct sk_buff *buf = l_ptr->first_out;
 	u32 r_q_size = l_ptr->retransm_queue_size;
@@ -1231,7 +1206,7 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr)
 	if (r_q_size && buf) {
 		msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1));
 		msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in);
-		tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+		tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
 		l_ptr->retransm_queue_head = mod(++r_q_head);
 		l_ptr->retransm_queue_size = --r_q_size;
 		l_ptr->stats.retransmitted++;
@@ -1243,7 +1218,7 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr)
 	if (buf) {
 		msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1));
 		msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in);
-		tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+		tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
 		l_ptr->unacked_window = 0;
 		kfree_skb(buf);
 		l_ptr->proto_msg_queue = NULL;
@@ -1260,7 +1235,8 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr)
 		if (mod(next - first) < l_ptr->queue_limit[0]) {
 			msg_set_ack(msg, mod(l_ptr->next_in_no - 1));
 			msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in);
-			tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+			tipc_bearer_send(l_ptr->bearer_id, buf,
+					 &l_ptr->media_addr);
 			if (msg_user(msg) == MSG_BUNDLER)
 				msg_set_type(msg, CLOSED_MSG);
 			l_ptr->next_out = buf->next;
@@ -1283,33 +1259,24 @@ void tipc_link_push_queue(struct tipc_link *l_ptr)
 	} while (!res);
 }
 
-static void link_reset_all(unsigned long addr)
+void tipc_link_reset_all(struct tipc_node *node)
 {
-	struct tipc_node *n_ptr;
 	char addr_string[16];
 	u32 i;
 
-	read_lock_bh(&tipc_net_lock);
-	n_ptr = tipc_node_find((u32)addr);
-	if (!n_ptr) {
-		read_unlock_bh(&tipc_net_lock);
-		return;	/* node no longer exists */
-	}
-
-	tipc_node_lock(n_ptr);
+	tipc_node_lock(node);
 
 	pr_warn("Resetting all links to %s\n",
-		tipc_addr_string_fill(addr_string, n_ptr->addr));
+		tipc_addr_string_fill(addr_string, node->addr));
 
 	for (i = 0; i < MAX_BEARERS; i++) {
-		if (n_ptr->links[i]) {
-			link_print(n_ptr->links[i], "Resetting link\n");
-			tipc_link_reset(n_ptr->links[i]);
+		if (node->links[i]) {
+			link_print(node->links[i], "Resetting link\n");
+			tipc_link_reset(node->links[i]);
 		}
 	}
 
-	tipc_node_unlock(n_ptr);
-	read_unlock_bh(&tipc_net_lock);
+	tipc_node_unlock(node);
 }
 
 static void link_retransmit_failure(struct tipc_link *l_ptr,
@@ -1346,10 +1313,9 @@ static void link_retransmit_failure(struct tipc_link *l_ptr,
 			n_ptr->bclink.oos_state,
 			n_ptr->bclink.last_sent);
 
-		tipc_k_signal((Handler)link_reset_all, (unsigned long)n_ptr->addr);
-
 		tipc_node_unlock(n_ptr);
 
+		tipc_bclink_set_flags(TIPC_BCLINK_RESET);
 		l_ptr->stale_count = 0;
 	}
 }
@@ -1379,7 +1345,7 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf,
 		msg = buf_msg(buf);
 		msg_set_ack(msg, mod(l_ptr->next_in_no - 1));
 		msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in);
-		tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+		tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
 		buf = buf->next;
 		retransmits--;
 		l_ptr->stats.retransmitted++;
@@ -1434,6 +1400,12 @@ static int link_recv_buf_validate(struct sk_buff *buf)
 	u32 hdr_size;
 	u32 min_hdr_size;
 
+	/* If this packet comes from the defer queue, the skb has already
+	 * been validated
+	 */
+	if (unlikely(TIPC_SKB_CB(buf)->deferred))
+		return 1;
+
 	if (unlikely(buf->len < MIN_H_SIZE))
 		return 0;
 
@@ -1459,16 +1431,15 @@ static int link_recv_buf_validate(struct sk_buff *buf)
 }
 
 /**
- * tipc_recv_msg - process TIPC messages arriving from off-node
+ * tipc_rcv - process TIPC packets/messages arriving from off-node
  * @head: pointer to message buffer chain
- * @tb_ptr: pointer to bearer message arrived on
+ * @b_ptr: pointer to bearer message arrived on
  *
  * Invoked with no locks held.  Bearer pointer must point to a valid bearer
  * structure (i.e. cannot be NULL), but bearer can be inactive.
  */
-void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr)
+void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr)
 {
-	read_lock_bh(&tipc_net_lock);
 	while (head) {
 		struct tipc_node *n_ptr;
 		struct tipc_link *l_ptr;
@@ -1478,13 +1449,9 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr)
 		u32 seq_no;
 		u32 ackd;
 		u32 released = 0;
-		int type;
 
 		head = head->next;
-
-		/* Ensure bearer is still enabled */
-		if (unlikely(!b_ptr->active))
-			goto discard;
+		buf->next = NULL;
 
 		/* Ensure message is well-formed */
 		if (unlikely(!link_recv_buf_validate(buf)))
@@ -1499,9 +1466,9 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr)
 
 		if (unlikely(msg_non_seq(msg))) {
 			if (msg_user(msg) ==  LINK_CONFIG)
-				tipc_disc_recv_msg(buf, b_ptr);
+				tipc_disc_rcv(buf, b_ptr);
 			else
-				tipc_bclink_recv_pkt(buf);
+				tipc_bclink_rcv(buf);
 			continue;
 		}
 
@@ -1522,14 +1489,14 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr)
 			goto unlock_discard;
 
 		/* Verify that communication with node is currently allowed */
-		if ((n_ptr->block_setup & WAIT_PEER_DOWN) &&
-			msg_user(msg) == LINK_PROTOCOL &&
-			(msg_type(msg) == RESET_MSG ||
-					msg_type(msg) == ACTIVATE_MSG) &&
-			!msg_redundant_link(msg))
-			n_ptr->block_setup &= ~WAIT_PEER_DOWN;
-
-		if (n_ptr->block_setup)
+		if ((n_ptr->action_flags & TIPC_WAIT_PEER_LINKS_DOWN) &&
+		    msg_user(msg) == LINK_PROTOCOL &&
+		    (msg_type(msg) == RESET_MSG ||
+		    msg_type(msg) == ACTIVATE_MSG) &&
+		    !msg_redundant_link(msg))
+			n_ptr->action_flags &= ~TIPC_WAIT_PEER_LINKS_DOWN;
+
+		if (tipc_node_blocked(n_ptr))
 			goto unlock_discard;
 
 		/* Validate message sequence number info */
@@ -1544,7 +1511,6 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr)
 		while ((crs != l_ptr->next_out) &&
 		       less_eq(buf_seqno(crs), ackd)) {
 			struct sk_buff *next = crs->next;
-
 			kfree_skb(crs);
 			crs = next;
 			released++;
@@ -1557,18 +1523,19 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr)
 		/* Try sending any messages link endpoint has pending */
 		if (unlikely(l_ptr->next_out))
 			tipc_link_push_queue(l_ptr);
+
 		if (unlikely(!list_empty(&l_ptr->waiting_ports)))
 			tipc_link_wakeup_ports(l_ptr, 0);
+
 		if (unlikely(++l_ptr->unacked_window >= TIPC_MIN_LINK_WIN)) {
 			l_ptr->stats.sent_acks++;
-			tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
 		}
 
-		/* Now (finally!) process the incoming message */
-protocol_check:
+		/* Process the incoming packet */
 		if (unlikely(!link_working_working(l_ptr))) {
 			if (msg_user(msg) == LINK_PROTOCOL) {
-				link_recv_proto_msg(l_ptr, buf);
+				tipc_link_proto_rcv(l_ptr, buf);
 				head = link_insert_deferred_queue(l_ptr, head);
 				tipc_node_unlock(n_ptr);
 				continue;
@@ -1597,72 +1564,64 @@ protocol_check:
 		l_ptr->next_in_no++;
 		if (unlikely(l_ptr->oldest_deferred_in))
 			head = link_insert_deferred_queue(l_ptr, head);
-deliver:
-		if (likely(msg_isdata(msg))) {
-			tipc_node_unlock(n_ptr);
-			tipc_port_recv_msg(buf);
-			continue;
+
+		/* Deliver packet/message to correct user: */
+		if (unlikely(msg_user(msg) ==  CHANGEOVER_PROTOCOL)) {
+			if (!tipc_link_tunnel_rcv(n_ptr, &buf)) {
+				tipc_node_unlock(n_ptr);
+				continue;
+			}
+			msg = buf_msg(buf);
+		} else if (msg_user(msg) == MSG_FRAGMENTER) {
+			l_ptr->stats.recv_fragments++;
+			if (tipc_buf_append(&l_ptr->reasm_buf, &buf)) {
+				l_ptr->stats.recv_fragmented++;
+				msg = buf_msg(buf);
+			} else {
+				if (!l_ptr->reasm_buf)
+					tipc_link_reset(l_ptr);
+				tipc_node_unlock(n_ptr);
+				continue;
+			}
 		}
+
 		switch (msg_user(msg)) {
-			int ret;
+		case TIPC_LOW_IMPORTANCE:
+		case TIPC_MEDIUM_IMPORTANCE:
+		case TIPC_HIGH_IMPORTANCE:
+		case TIPC_CRITICAL_IMPORTANCE:
+			tipc_node_unlock(n_ptr);
+			tipc_sk_rcv(buf);
+			continue;
 		case MSG_BUNDLER:
 			l_ptr->stats.recv_bundles++;
 			l_ptr->stats.recv_bundled += msg_msgcnt(msg);
 			tipc_node_unlock(n_ptr);
-			tipc_link_recv_bundle(buf);
+			tipc_link_bundle_rcv(buf);
 			continue;
 		case NAME_DISTRIBUTOR:
 			n_ptr->bclink.recv_permitted = true;
 			tipc_node_unlock(n_ptr);
-			tipc_named_recv(buf);
-			continue;
-		case BCAST_PROTOCOL:
-			tipc_link_recv_sync(n_ptr, buf);
-			tipc_node_unlock(n_ptr);
+			tipc_named_rcv(buf);
 			continue;
 		case CONN_MANAGER:
 			tipc_node_unlock(n_ptr);
-			tipc_port_recv_proto_msg(buf);
-			continue;
-		case MSG_FRAGMENTER:
-			l_ptr->stats.recv_fragments++;
-			ret = tipc_link_recv_fragment(&l_ptr->reasm_head,
-						      &l_ptr->reasm_tail,
-						      &buf);
-			if (ret == LINK_REASM_COMPLETE) {
-				l_ptr->stats.recv_fragmented++;
-				msg = buf_msg(buf);
-				goto deliver;
-			}
-			if (ret == LINK_REASM_ERROR)
-				tipc_link_reset(l_ptr);
-			tipc_node_unlock(n_ptr);
+			tipc_port_proto_rcv(buf);
 			continue;
-		case CHANGEOVER_PROTOCOL:
-			type = msg_type(msg);
-			if (link_recv_changeover_msg(&l_ptr, &buf)) {
-				msg = buf_msg(buf);
-				seq_no = msg_seqno(msg);
-				if (type == ORIGINAL_MSG)
-					goto deliver;
-				goto protocol_check;
-			}
+		case BCAST_PROTOCOL:
+			tipc_link_sync_rcv(n_ptr, buf);
 			break;
 		default:
 			kfree_skb(buf);
-			buf = NULL;
 			break;
 		}
 		tipc_node_unlock(n_ptr);
-		tipc_net_route_msg(buf);
 		continue;
 unlock_discard:
-
 		tipc_node_unlock(n_ptr);
 discard:
 		kfree_skb(buf);
 	}
-	read_unlock_bh(&tipc_net_lock);
 }
 
 /**
@@ -1724,7 +1683,7 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr,
 	u32 seq_no = buf_seqno(buf);
 
 	if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) {
-		link_recv_proto_msg(l_ptr, buf);
+		tipc_link_proto_rcv(l_ptr, buf);
 		return;
 	}
 
@@ -1745,8 +1704,9 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr,
 				&l_ptr->newest_deferred_in, buf)) {
 		l_ptr->deferred_inqueue_sz++;
 		l_ptr->stats.deferred_recv++;
+		TIPC_SKB_CB(buf)->deferred = true;
 		if ((l_ptr->deferred_inqueue_sz % 16) == 1)
-			tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0);
 	} else
 		l_ptr->stats.duplicates++;
 }
@@ -1754,9 +1714,8 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr,
 /*
  * Send protocol message to the other endpoint.
  */
-void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ,
-			      int probe_msg, u32 gap, u32 tolerance,
-			      u32 priority, u32 ack_mtu)
+void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg,
+			  u32 gap, u32 tolerance, u32 priority, u32 ack_mtu)
 {
 	struct sk_buff *buf = NULL;
 	struct tipc_msg *msg = l_ptr->pmsg;
@@ -1769,16 +1728,17 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ,
 		l_ptr->proto_msg_queue = NULL;
 	}
 
-	if (link_blocked(l_ptr))
+	/* Don't send protocol message during link changeover */
+	if (l_ptr->exp_msg_count)
 		return;
 
 	/* Abort non-RESET send if communication with node is prohibited */
-	if ((l_ptr->owner->block_setup) && (msg_typ != RESET_MSG))
+	if ((tipc_node_blocked(l_ptr->owner)) && (msg_typ != RESET_MSG))
 		return;
 
 	/* Create protocol message with "out-of-sequence" sequence number */
 	msg_set_type(msg, msg_typ);
-	msg_set_net_plane(msg, l_ptr->b_ptr->net_plane);
+	msg_set_net_plane(msg, l_ptr->net_plane);
 	msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in);
 	msg_set_last_bcast(msg, tipc_bclink_get_last_sent());
 
@@ -1844,7 +1804,7 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ,
 	skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg));
 	buf->priority = TC_PRIO_CONTROL;
 
-	tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+	tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
 	l_ptr->unacked_window = 0;
 	kfree_skb(buf);
 }
@@ -1854,7 +1814,7 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ,
  * Note that network plane id propagates through the network, and may
  * change at any time. The node with lowest address rules
  */
-static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf)
+static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf)
 {
 	u32 rec_gap = 0;
 	u32 max_pkt_info;
@@ -1862,17 +1822,13 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf)
 	u32 msg_tol;
 	struct tipc_msg *msg = buf_msg(buf);
 
-	if (link_blocked(l_ptr))
+	/* Discard protocol message during link changeover */
+	if (l_ptr->exp_msg_count)
 		goto exit;
 
-	/* record unnumbered packet arrival (force mismatch on next timeout) */
-	l_ptr->checkpoint--;
-
-	if (l_ptr->b_ptr->net_plane != msg_net_plane(msg))
+	if (l_ptr->net_plane != msg_net_plane(msg))
 		if (tipc_own_addr > msg_prevnode(msg))
-			l_ptr->b_ptr->net_plane = msg_net_plane(msg);
-
-	l_ptr->owner->permit_changeover = msg_redundant_link(msg);
+			l_ptr->net_plane = msg_net_plane(msg);
 
 	switch (msg_type(msg)) {
 
@@ -1889,7 +1845,7 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf)
 			 * peer has lost contact -- don't allow peer's links
 			 * to reactivate before we recognize loss & clean up
 			 */
-			l_ptr->owner->block_setup = WAIT_NODE_DOWN;
+			l_ptr->owner->action_flags |= TIPC_WAIT_OWN_LINKS_DOWN;
 		}
 
 		link_state_event(l_ptr, RESET_MSG);
@@ -1945,6 +1901,10 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf)
 			tipc_link_reset(l_ptr); /* Enforce change to take effect */
 			break;
 		}
+
+		/* Record reception; force mismatch at next timeout: */
+		l_ptr->checkpoint--;
+
 		link_state_event(l_ptr, TRAFFIC_MSG_EVT);
 		l_ptr->stats.recv_states++;
 		if (link_reset_unknown(l_ptr))
@@ -1974,8 +1934,8 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf)
 						      msg_last_bcast(msg));
 
 		if (rec_gap || (msg_probe(msg))) {
-			tipc_link_send_proto_msg(l_ptr, STATE_MSG,
-						 0, rec_gap, 0, 0, max_pkt_ack);
+			tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, rec_gap, 0,
+					     0, max_pkt_ack);
 		}
 		if (msg_seq_gap(msg)) {
 			l_ptr->stats.recv_nacks++;
@@ -1989,13 +1949,13 @@ exit:
 }
 
 
-/*
- * tipc_link_tunnel(): Send one message via a link belonging to
- * another bearer. Owner node is locked.
+/* tipc_link_tunnel_xmit(): Tunnel one packet via a link belonging to
+ * a different bearer. Owner node is locked.
  */
-static void tipc_link_tunnel(struct tipc_link *l_ptr,
-			     struct tipc_msg *tunnel_hdr, struct tipc_msg *msg,
-			     u32 selector)
+static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr,
+				  struct tipc_msg *tunnel_hdr,
+				  struct tipc_msg *msg,
+				  u32 selector)
 {
 	struct tipc_link *tunnel;
 	struct sk_buff *buf;
@@ -2014,16 +1974,17 @@ static void tipc_link_tunnel(struct tipc_link *l_ptr,
 	}
 	skb_copy_to_linear_data(buf, tunnel_hdr, INT_H_SIZE);
 	skb_copy_to_linear_data_offset(buf, INT_H_SIZE, msg, length);
-	tipc_link_send_buf(tunnel, buf);
+	__tipc_link_xmit(tunnel, buf);
 }
 
 
-
-/*
- * changeover(): Send whole message queue via the remaining link
- *               Owner node is locked.
+/* tipc_link_failover_send_queue(): A link has gone down, but a second
+ * link is still active. We can do failover. Tunnel the failing link's
+ * whole send queue via the remaining link. This way, we don't lose
+ * any packets, and sequence order is preserved for subsequent traffic
+ * sent over the remaining link. Owner node is locked.
  */
-void tipc_link_changeover(struct tipc_link *l_ptr)
+void tipc_link_failover_send_queue(struct tipc_link *l_ptr)
 {
 	u32 msgcount = l_ptr->out_queue_size;
 	struct sk_buff *crs = l_ptr->first_out;
@@ -2034,11 +1995,6 @@ void tipc_link_changeover(struct tipc_link *l_ptr)
 	if (!tunnel)
 		return;
 
-	if (!l_ptr->owner->permit_changeover) {
-		pr_warn("%speer did not permit changeover\n", link_co_err);
-		return;
-	}
-
 	tipc_msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL,
 		 ORIGINAL_MSG, INT_H_SIZE, l_ptr->addr);
 	msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id);
@@ -2051,7 +2007,7 @@ void tipc_link_changeover(struct tipc_link *l_ptr)
 		if (buf) {
 			skb_copy_to_linear_data(buf, &tunnel_hdr, INT_H_SIZE);
 			msg_set_size(&tunnel_hdr, INT_H_SIZE);
-			tipc_link_send_buf(tunnel, buf);
+			__tipc_link_xmit(tunnel, buf);
 		} else {
 			pr_warn("%sunable to send changeover msg\n",
 				link_co_err);
@@ -2072,20 +2028,30 @@ void tipc_link_changeover(struct tipc_link *l_ptr)
 			msgcount = msg_msgcnt(msg);
 			while (msgcount--) {
 				msg_set_seqno(m, msg_seqno(msg));
-				tipc_link_tunnel(l_ptr, &tunnel_hdr, m,
-						 msg_link_selector(m));
+				tipc_link_tunnel_xmit(l_ptr, &tunnel_hdr, m,
+						      msg_link_selector(m));
 				pos += align(msg_size(m));
 				m = (struct tipc_msg *)pos;
 			}
 		} else {
-			tipc_link_tunnel(l_ptr, &tunnel_hdr, msg,
-					 msg_link_selector(msg));
+			tipc_link_tunnel_xmit(l_ptr, &tunnel_hdr, msg,
+					      msg_link_selector(msg));
 		}
 		crs = crs->next;
 	}
 }
 
-void tipc_link_send_duplicate(struct tipc_link *l_ptr, struct tipc_link *tunnel)
+/* tipc_link_dup_queue_xmit(): A second link has become active. Tunnel a
+ * duplicate of the first link's send queue via the new link. This way, we
+ * are guaranteed that currently queued packets from a socket are delivered
+ * before future traffic from the same socket, even if this is using the
+ * new link. The last arriving copy of each duplicate packet is dropped at
+ * the receiving end by the regular protocol check, so packet cardinality
+ * and sequence order is preserved per sender/receiver socket pair.
+ * Owner node is locked.
+ */
+void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr,
+			      struct tipc_link *tunnel)
 {
 	struct sk_buff *iter;
 	struct tipc_msg tunnel_hdr;
@@ -2114,7 +2080,7 @@ void tipc_link_send_duplicate(struct tipc_link *l_ptr, struct tipc_link *tunnel)
 		skb_copy_to_linear_data(outbuf, &tunnel_hdr, INT_H_SIZE);
 		skb_copy_to_linear_data_offset(outbuf, INT_H_SIZE, iter->data,
 					       length);
-		tipc_link_send_buf(tunnel, outbuf);
+		__tipc_link_xmit(tunnel, outbuf);
 		if (!tipc_link_is_up(l_ptr))
 			return;
 		iter = iter->next;
@@ -2141,87 +2107,112 @@ static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos)
 	return eb;
 }
 
-/*
- *  link_recv_changeover_msg(): Receive tunneled packet sent
- *  via other link. Node is locked. Return extracted buffer.
+
+
+/* tipc_link_dup_rcv(): Receive a tunnelled DUPLICATE_MSG packet.
+ * Owner node is locked.
  */
-static int link_recv_changeover_msg(struct tipc_link **l_ptr,
-				    struct sk_buff **buf)
+static void tipc_link_dup_rcv(struct tipc_link *l_ptr,
+			      struct sk_buff *t_buf)
 {
-	struct sk_buff *tunnel_buf = *buf;
-	struct tipc_link *dest_link;
-	struct tipc_msg *msg;
-	struct tipc_msg *tunnel_msg = buf_msg(tunnel_buf);
-	u32 msg_typ = msg_type(tunnel_msg);
-	u32 msg_count = msg_msgcnt(tunnel_msg);
-	u32 bearer_id = msg_bearer_id(tunnel_msg);
+	struct sk_buff *buf;
 
-	if (bearer_id >= MAX_BEARERS)
-		goto exit;
-	dest_link = (*l_ptr)->owner->links[bearer_id];
-	if (!dest_link)
-		goto exit;
-	if (dest_link == *l_ptr) {
-		pr_err("Unexpected changeover message on link <%s>\n",
-		       (*l_ptr)->name);
-		goto exit;
+	if (!tipc_link_is_up(l_ptr))
+		return;
+
+	buf = buf_extract(t_buf, INT_H_SIZE);
+	if (buf == NULL) {
+		pr_warn("%sfailed to extract inner dup pkt\n", link_co_err);
+		return;
 	}
-	*l_ptr = dest_link;
-	msg = msg_get_wrapped(tunnel_msg);
 
-	if (msg_typ == DUPLICATE_MSG) {
-		if (less(msg_seqno(msg), mod(dest_link->next_in_no)))
-			goto exit;
-		*buf = buf_extract(tunnel_buf, INT_H_SIZE);
-		if (*buf == NULL) {
-			pr_warn("%sduplicate msg dropped\n", link_co_err);
+	/* Add buffer to deferred queue, if applicable: */
+	link_handle_out_of_seq_msg(l_ptr, buf);
+}
+
+/*  tipc_link_failover_rcv(): Receive a tunnelled ORIGINAL_MSG packet
+ *  Owner node is locked.
+ */
+static struct sk_buff *tipc_link_failover_rcv(struct tipc_link *l_ptr,
+					      struct sk_buff *t_buf)
+{
+	struct tipc_msg *t_msg = buf_msg(t_buf);
+	struct sk_buff *buf = NULL;
+	struct tipc_msg *msg;
+
+	if (tipc_link_is_up(l_ptr))
+		tipc_link_reset(l_ptr);
+
+	/* First failover packet? */
+	if (l_ptr->exp_msg_count == START_CHANGEOVER)
+		l_ptr->exp_msg_count = msg_msgcnt(t_msg);
+
+	/* Should there be an inner packet? */
+	if (l_ptr->exp_msg_count) {
+		l_ptr->exp_msg_count--;
+		buf = buf_extract(t_buf, INT_H_SIZE);
+		if (buf == NULL) {
+			pr_warn("%sno inner failover pkt\n", link_co_err);
 			goto exit;
 		}
-		kfree_skb(tunnel_buf);
-		return 1;
-	}
+		msg = buf_msg(buf);
 
-	/* First original message ?: */
-	if (tipc_link_is_up(dest_link)) {
-		pr_info("%s<%s>, changeover initiated by peer\n", link_rst_msg,
-			dest_link->name);
-		tipc_link_reset(dest_link);
-		dest_link->exp_msg_count = msg_count;
-		if (!msg_count)
-			goto exit;
-	} else if (dest_link->exp_msg_count == START_CHANGEOVER) {
-		dest_link->exp_msg_count = msg_count;
-		if (!msg_count)
+		if (less(msg_seqno(msg), l_ptr->reset_checkpoint)) {
+			kfree_skb(buf);
+			buf = NULL;
 			goto exit;
+		}
+		if (msg_user(msg) == MSG_FRAGMENTER) {
+			l_ptr->stats.recv_fragments++;
+			tipc_buf_append(&l_ptr->reasm_buf, &buf);
+		}
 	}
+exit:
+	if ((l_ptr->exp_msg_count == 0) && (l_ptr->flags & LINK_STOPPED)) {
+		tipc_node_detach_link(l_ptr->owner, l_ptr);
+		kfree(l_ptr);
+	}
+	return buf;
+}
+
+/*  tipc_link_tunnel_rcv(): Receive a tunnelled packet, sent
+ *  via other link as result of a failover (ORIGINAL_MSG) or
+ *  a new active link (DUPLICATE_MSG). Failover packets are
+ *  returned to the active link for delivery upwards.
+ *  Owner node is locked.
+ */
+static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr,
+				struct sk_buff **buf)
+{
+	struct sk_buff *t_buf = *buf;
+	struct tipc_link *l_ptr;
+	struct tipc_msg *t_msg = buf_msg(t_buf);
+	u32 bearer_id = msg_bearer_id(t_msg);
 
-	/* Receive original message */
-	if (dest_link->exp_msg_count == 0) {
-		pr_warn("%sgot too many tunnelled messages\n", link_co_err);
+	*buf = NULL;
+
+	if (bearer_id >= MAX_BEARERS)
 		goto exit;
-	}
-	dest_link->exp_msg_count--;
-	if (less(msg_seqno(msg), dest_link->reset_checkpoint)) {
+
+	l_ptr = n_ptr->links[bearer_id];
+	if (!l_ptr)
 		goto exit;
-	} else {
-		*buf = buf_extract(tunnel_buf, INT_H_SIZE);
-		if (*buf != NULL) {
-			kfree_skb(tunnel_buf);
-			return 1;
-		} else {
-			pr_warn("%soriginal msg dropped\n", link_co_err);
-		}
-	}
+
+	if (msg_type(t_msg) == DUPLICATE_MSG)
+		tipc_link_dup_rcv(l_ptr, t_buf);
+	else if (msg_type(t_msg) == ORIGINAL_MSG)
+		*buf = tipc_link_failover_rcv(l_ptr, t_buf);
+	else
+		pr_warn("%sunknown tunnel pkt received\n", link_co_err);
 exit:
-	*buf = NULL;
-	kfree_skb(tunnel_buf);
-	return 0;
+	kfree_skb(t_buf);
+	return *buf != NULL;
 }
 
 /*
  *  Bundler functionality:
  */
-void tipc_link_recv_bundle(struct sk_buff *buf)
+void tipc_link_bundle_rcv(struct sk_buff *buf)
 {
 	u32 msgcount = msg_msgcnt(buf_msg(buf));
 	u32 pos = INT_H_SIZE;
@@ -2244,11 +2235,11 @@ void tipc_link_recv_bundle(struct sk_buff *buf)
  */
 
 /*
- * link_send_long_buf: Entry for buffers needing fragmentation.
+ * tipc_link_frag_xmit: Entry for buffers needing fragmentation.
  * The buffer is complete, inclusive total message length.
  * Returns user data length.
  */
-static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf)
+static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf)
 {
 	struct sk_buff *buf_chain = NULL;
 	struct sk_buff *buf_chain_tail = (struct sk_buff *)&buf_chain;
@@ -2283,11 +2274,7 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf)
 		fragm = tipc_buf_acquire(fragm_sz + INT_H_SIZE);
 		if (fragm == NULL) {
 			kfree_skb(buf);
-			while (buf_chain) {
-				buf = buf_chain;
-				buf_chain = buf_chain->next;
-				kfree_skb(buf);
-			}
+			kfree_skb_list(buf_chain);
 			return -ENOMEM;
 		}
 		msg_set_size(&fragm_hdr, fragm_sz + INT_H_SIZE);
@@ -2315,51 +2302,6 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf)
 	return dsz;
 }
 
-/*
- * tipc_link_recv_fragment(): Called with node lock on. Returns
- * the reassembled buffer if message is complete.
- */
-int tipc_link_recv_fragment(struct sk_buff **head, struct sk_buff **tail,
-			    struct sk_buff **fbuf)
-{
-	struct sk_buff *frag = *fbuf;
-	struct tipc_msg *msg = buf_msg(frag);
-	u32 fragid = msg_type(msg);
-	bool headstolen;
-	int delta;
-
-	skb_pull(frag, msg_hdr_sz(msg));
-	if (fragid == FIRST_FRAGMENT) {
-		if (*head || skb_unclone(frag, GFP_ATOMIC))
-			goto out_free;
-		*head = frag;
-		skb_frag_list_init(*head);
-		return 0;
-	} else if (*head &&
-		   skb_try_coalesce(*head, frag, &headstolen, &delta)) {
-		kfree_skb_partial(frag, headstolen);
-	} else {
-		if (!*head)
-			goto out_free;
-		if (!skb_has_frag_list(*head))
-			skb_shinfo(*head)->frag_list = frag;
-		else
-			(*tail)->next = frag;
-		*tail = frag;
-		(*head)->truesize += frag->truesize;
-	}
-	if (fragid == LAST_FRAGMENT) {
-		*fbuf = *head;
-		*tail = *head = NULL;
-		return LINK_REASM_COMPLETE;
-	}
-	return 0;
-out_free:
-	pr_warn_ratelimited("Link unable to reassemble fragmented message\n");
-	kfree_skb(*fbuf);
-	return LINK_REASM_ERROR;
-}
-
 static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance)
 {
 	if ((tolerance < TIPC_MIN_LINK_TOL) || (tolerance > TIPC_MAX_LINK_TOL))
@@ -2390,35 +2332,39 @@ void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window)
 	l_ptr->queue_limit[MSG_FRAGMENTER] = 4000;
 }
 
-/**
- * link_find_link - locate link by name
- * @name: ptr to link name string
- * @node: ptr to area to be filled with ptr to associated node
+/* tipc_link_find_owner - locate owner node of link by link's name
+ * @name: pointer to link name string
+ * @bearer_id: pointer to index in 'node->links' array where the link was found.
  *
- * Caller must hold 'tipc_net_lock' to ensure node and bearer are not deleted;
- * this also prevents link deletion.
- *
- * Returns pointer to link (or 0 if invalid link name).
+ * Returns pointer to node owning the link, or 0 if no matching link is found.
  */
-static struct tipc_link *link_find_link(const char *name,
-					struct tipc_node **node)
+static struct tipc_node *tipc_link_find_owner(const char *link_name,
+					      unsigned int *bearer_id)
 {
 	struct tipc_link *l_ptr;
 	struct tipc_node *n_ptr;
+	struct tipc_node *found_node = 0;
 	int i;
 
-	list_for_each_entry(n_ptr, &tipc_node_list, list) {
+	*bearer_id = 0;
+	rcu_read_lock();
+	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
+		tipc_node_lock(n_ptr);
 		for (i = 0; i < MAX_BEARERS; i++) {
 			l_ptr = n_ptr->links[i];
-			if (l_ptr && !strcmp(l_ptr->name, name))
-				goto found;
+			if (l_ptr && !strcmp(l_ptr->name, link_name)) {
+				*bearer_id = i;
+				found_node = n_ptr;
+				break;
+			}
 		}
+		tipc_node_unlock(n_ptr);
+		if (found_node)
+			break;
 	}
-	l_ptr = NULL;
-	n_ptr = NULL;
-found:
-	*node = n_ptr;
-	return l_ptr;
+	rcu_read_unlock();
+
+	return found_node;
 }
 
 /**
@@ -2450,7 +2396,7 @@ static int link_value_is_valid(u16 cmd, u32 new_value)
  * @new_value: new value of link, bearer, or media setting
  * @cmd: which link, bearer, or media attribute to set (TIPC_CMD_SET_LINK_*)
  *
- * Caller must hold 'tipc_net_lock' to ensure link/bearer/media is not deleted.
+ * Caller must hold RTNL lock to ensure link/bearer/media is not deleted.
  *
  * Returns 0 if value updated and negative value on error.
  */
@@ -2460,32 +2406,33 @@ static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd)
 	struct tipc_link *l_ptr;
 	struct tipc_bearer *b_ptr;
 	struct tipc_media *m_ptr;
+	int bearer_id;
 	int res = 0;
 
-	l_ptr = link_find_link(name, &node);
-	if (l_ptr) {
-		/*
-		 * acquire node lock for tipc_link_send_proto_msg().
-		 * see "TIPC locking policy" in net.c.
-		 */
+	node = tipc_link_find_owner(name, &bearer_id);
+	if (node) {
 		tipc_node_lock(node);
-		switch (cmd) {
-		case TIPC_CMD_SET_LINK_TOL:
-			link_set_supervision_props(l_ptr, new_value);
-			tipc_link_send_proto_msg(l_ptr,
-				STATE_MSG, 0, 0, new_value, 0, 0);
-			break;
-		case TIPC_CMD_SET_LINK_PRI:
-			l_ptr->priority = new_value;
-			tipc_link_send_proto_msg(l_ptr,
-				STATE_MSG, 0, 0, 0, new_value, 0);
-			break;
-		case TIPC_CMD_SET_LINK_WINDOW:
-			tipc_link_set_queue_limits(l_ptr, new_value);
-			break;
-		default:
-			res = -EINVAL;
-			break;
+		l_ptr = node->links[bearer_id];
+
+		if (l_ptr) {
+			switch (cmd) {
+			case TIPC_CMD_SET_LINK_TOL:
+				link_set_supervision_props(l_ptr, new_value);
+				tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0,
+						     new_value, 0, 0);
+				break;
+			case TIPC_CMD_SET_LINK_PRI:
+				l_ptr->priority = new_value;
+				tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0,
+						     0, new_value, 0);
+				break;
+			case TIPC_CMD_SET_LINK_WINDOW:
+				tipc_link_set_queue_limits(l_ptr, new_value);
+				break;
+			default:
+				res = -EINVAL;
+				break;
+			}
 		}
 		tipc_node_unlock(node);
 		return res;
@@ -2555,9 +2502,7 @@ struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space
 						   " (cannot change setting on broadcast link)");
 	}
 
-	read_lock_bh(&tipc_net_lock);
 	res = link_cmd_set_value(args->name, new_value, cmd);
-	read_unlock_bh(&tipc_net_lock);
 	if (res)
 		return tipc_cfg_reply_error_string("cannot change link setting");
 
@@ -2580,6 +2525,7 @@ struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_
 	char *link_name;
 	struct tipc_link *l_ptr;
 	struct tipc_node *node;
+	unsigned int bearer_id;
 
 	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME))
 		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
@@ -2590,18 +2536,18 @@ struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_
 			return tipc_cfg_reply_error_string("link not found");
 		return tipc_cfg_reply_none();
 	}
+	node = tipc_link_find_owner(link_name, &bearer_id);
+	if (!node)
+		return tipc_cfg_reply_error_string("link not found");
 
-	read_lock_bh(&tipc_net_lock);
-	l_ptr = link_find_link(link_name, &node);
+	tipc_node_lock(node);
+	l_ptr = node->links[bearer_id];
 	if (!l_ptr) {
-		read_unlock_bh(&tipc_net_lock);
+		tipc_node_unlock(node);
 		return tipc_cfg_reply_error_string("link not found");
 	}
-
-	tipc_node_lock(node);
 	link_reset_statistics(l_ptr);
 	tipc_node_unlock(node);
-	read_unlock_bh(&tipc_net_lock);
 	return tipc_cfg_reply_none();
 }
 
@@ -2628,18 +2574,24 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size)
 	struct tipc_node *node;
 	char *status;
 	u32 profile_total = 0;
+	unsigned int bearer_id;
 	int ret;
 
 	if (!strcmp(name, tipc_bclink_name))
 		return tipc_bclink_stats(buf, buf_size);
 
-	read_lock_bh(&tipc_net_lock);
-	l = link_find_link(name, &node);
+	node = tipc_link_find_owner(name, &bearer_id);
+	if (!node)
+		return 0;
+
+	tipc_node_lock(node);
+
+	l = node->links[bearer_id];
 	if (!l) {
-		read_unlock_bh(&tipc_net_lock);
+		tipc_node_unlock(node);
 		return 0;
 	}
-	tipc_node_lock(node);
+
 	s = &l->stats;
 
 	if (tipc_link_is_active(l))
@@ -2702,7 +2654,6 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size)
 			     (s->accu_queue_sz / s->queue_sz_counts) : 0);
 
 	tipc_node_unlock(node);
-	read_unlock_bh(&tipc_net_lock);
 	return ret;
 }
 
@@ -2753,7 +2704,6 @@ u32 tipc_link_get_max_pkt(u32 dest, u32 selector)
 	if (dest == tipc_own_addr)
 		return MAX_MSG_SIZE;
 
-	read_lock_bh(&tipc_net_lock);
 	n_ptr = tipc_node_find(dest);
 	if (n_ptr) {
 		tipc_node_lock(n_ptr);
@@ -2762,13 +2712,18 @@ u32 tipc_link_get_max_pkt(u32 dest, u32 selector)
 			res = l_ptr->max_pkt;
 		tipc_node_unlock(n_ptr);
 	}
-	read_unlock_bh(&tipc_net_lock);
 	return res;
 }
 
 static void link_print(struct tipc_link *l_ptr, const char *str)
 {
-	pr_info("%s Link %x<%s>:", str, l_ptr->addr, l_ptr->b_ptr->name);
+	struct tipc_bearer *b_ptr;
+
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(bearer_list[l_ptr->bearer_id]);
+	if (b_ptr)
+		pr_info("%s Link %x<%s>:", str, l_ptr->addr, b_ptr->name);
+	rcu_read_unlock();
 
 	if (link_working_unknown(l_ptr))
 		pr_cont(":WU\n");
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 8a6c1026644..200d518b218 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/link.h: Include file for TIPC link code
  *
- * Copyright (c) 1995-2006, Ericsson AB
+ * Copyright (c) 1995-2006, 2013, Ericsson AB
  * Copyright (c) 2004-2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -40,27 +40,23 @@
 #include "msg.h"
 #include "node.h"
 
-/*
- * Link reassembly status codes
- */
-#define LINK_REASM_ERROR	-1
-#define LINK_REASM_COMPLETE	1
-
-/*
- * Out-of-range value for link sequence numbers
+/* Out-of-range value for link sequence numbers
  */
 #define INVALID_LINK_SEQ 0x10000
 
-/*
- * Link states
+/* Link working states
  */
 #define WORKING_WORKING 560810u
 #define WORKING_UNKNOWN 560811u
 #define RESET_UNKNOWN   560812u
 #define RESET_RESET     560813u
 
-/*
- * Starting value for maximum packet size negotiation on unicast links
+/* Link endpoint execution states
+ */
+#define LINK_STARTED    0x0001
+#define LINK_STOPPED    0x0002
+
+/* Starting value for maximum packet size negotiation on unicast links
  * (unless bearer MTU is less)
  */
 #define MAX_PKT_DEFAULT 1500
@@ -102,21 +98,20 @@ struct tipc_stats {
  * @media_addr: media address to use when sending messages over link
  * @timer: link timer
  * @owner: pointer to peer node
- * @link_list: adjacent links in bearer's list of links
- * @started: indicates if link has been started
+ * @flags: execution state flags for link endpoint instance
  * @checkpoint: reference point for triggering link continuity checking
  * @peer_session: link session # being used by peer end of link
  * @peer_bearer_id: bearer id used by link's peer endpoint
- * @b_ptr: pointer to bearer used by link
+ * @bearer_id: local bearer id used by link
  * @tolerance: minimum link continuity loss needed to reset link [in ms]
  * @continuity_interval: link continuity testing interval [in ms]
  * @abort_limit: # of unacknowledged continuity probes needed to reset link
  * @state: current state of link FSM
- * @blocked: indicates if link has been administratively blocked
  * @fsm_msg_cnt: # of protocol messages link FSM has sent in current state
  * @proto_msg: template for control messages generated by link
  * @pmsg: convenience pointer to "proto_msg" field
  * @priority: current link priority
+ * @net_plane: current link network plane ('A' through 'H')
  * @queue_limit: outbound message queue congestion thresholds (indexed by user)
  * @exp_msg_count: # of tunnelled messages expected during link changeover
  * @reset_checkpoint: seq # of last acknowledged message at time of link reset
@@ -140,8 +135,7 @@ struct tipc_stats {
  * @next_out: ptr to first unsent outbound message in queue
  * @waiting_ports: linked list of ports waiting for link congestion to abate
  * @long_msg_seq_no: next identifier to use for outbound fragmented messages
- * @reasm_head: list head of partially reassembled inbound message fragments
- * @reasm_tail: last fragment received
+ * @reasm_buf: head of partially reassembled inbound message fragments
  * @stats: collects statistics regarding link activity
  */
 struct tipc_link {
@@ -150,19 +144,17 @@ struct tipc_link {
 	struct tipc_media_addr media_addr;
 	struct timer_list timer;
 	struct tipc_node *owner;
-	struct list_head link_list;
 
 	/* Management and link supervision data */
-	int started;
+	unsigned int flags;
 	u32 checkpoint;
 	u32 peer_session;
 	u32 peer_bearer_id;
-	struct tipc_bearer *b_ptr;
+	u32 bearer_id;
 	u32 tolerance;
 	u32 continuity_interval;
 	u32 abort_limit;
 	int state;
-	int blocked;
 	u32 fsm_msg_cnt;
 	struct {
 		unchar hdr[INT_H_SIZE];
@@ -170,6 +162,7 @@ struct tipc_link {
 	} proto_msg;
 	struct tipc_msg *pmsg;
 	u32 priority;
+	char net_plane;
 	u32 queue_limit[15];	/* queue_limit[0]==window limit */
 
 	/* Changeover */
@@ -205,8 +198,7 @@ struct tipc_link {
 
 	/* Fragmentation/reassembly */
 	u32 long_msg_seq_no;
-	struct sk_buff *reasm_head;
-	struct sk_buff *reasm_tail;
+	struct sk_buff *reasm_buf;
 
 	/* Statistics */
 	struct tipc_stats stats;
@@ -217,35 +209,37 @@ struct tipc_port;
 struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
 			      struct tipc_bearer *b_ptr,
 			      const struct tipc_media_addr *media_addr);
-void tipc_link_delete(struct tipc_link *l_ptr);
-void tipc_link_changeover(struct tipc_link *l_ptr);
-void tipc_link_send_duplicate(struct tipc_link *l_ptr, struct tipc_link *dest);
+void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down);
+void tipc_link_failover_send_queue(struct tipc_link *l_ptr);
+void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *dest);
 void tipc_link_reset_fragments(struct tipc_link *l_ptr);
 int tipc_link_is_up(struct tipc_link *l_ptr);
 int tipc_link_is_active(struct tipc_link *l_ptr);
-u32 tipc_link_push_packet(struct tipc_link *l_ptr);
-void tipc_link_stop(struct tipc_link *l_ptr);
-struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space, u16 cmd);
-struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_space);
-struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space);
+void tipc_link_purge_queues(struct tipc_link *l_ptr);
+struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area,
+				     int req_tlv_space,
+				     u16 cmd);
+struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area,
+					 int req_tlv_space);
+struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area,
+					  int req_tlv_space);
+void tipc_link_reset_all(struct tipc_node *node);
 void tipc_link_reset(struct tipc_link *l_ptr);
-int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector);
-void tipc_link_send_names(struct list_head *message_list, u32 dest);
+void tipc_link_reset_list(unsigned int bearer_id);
+int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector);
+void tipc_link_names_xmit(struct list_head *message_list, u32 dest);
+int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf);
 int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf);
 u32 tipc_link_get_max_pkt(u32 dest, u32 selector);
-int tipc_link_send_sections_fast(struct tipc_port *sender,
-				 struct iovec const *msg_sect,
-				 unsigned int len, u32 destnode);
-void tipc_link_recv_bundle(struct sk_buff *buf);
-int  tipc_link_recv_fragment(struct sk_buff **reasm_head,
-			     struct sk_buff **reasm_tail,
-			     struct sk_buff **fbuf);
-void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, int prob,
-			      u32 gap, u32 tolerance, u32 priority,
-			      u32 acked_mtu);
+int tipc_link_iovec_xmit_fast(struct tipc_port *sender,
+			      struct iovec const *msg_sect,
+			      unsigned int len, u32 destnode);
+void tipc_link_bundle_rcv(struct sk_buff *buf);
+void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob,
+			  u32 gap, u32 tolerance, u32 priority, u32 acked_mtu);
 void tipc_link_push_queue(struct tipc_link *l_ptr);
 u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail,
-		   struct sk_buff *buf);
+			struct sk_buff *buf);
 void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all);
 void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window);
 void tipc_link_retransmit(struct tipc_link *l_ptr,
@@ -312,11 +306,6 @@ static inline int link_reset_reset(struct tipc_link *l_ptr)
 	return l_ptr->state == RESET_RESET;
 }
 
-static inline int link_blocked(struct tipc_link *l_ptr)
-{
-	return l_ptr->exp_msg_count || l_ptr->blocked;
-}
-
 static inline int link_congested(struct tipc_link *l_ptr)
 {
 	return l_ptr->out_queue_size >= l_ptr->queue_limit[0];
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index e525f8ce1de..0a37a472c29 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/msg.c: TIPC message header routines
  *
- * Copyright (c) 2000-2006, Ericsson AB
+ * Copyright (c) 2000-2006, 2014, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -99,3 +99,61 @@ int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect,
 	}
 	return dsz;
 }
+
+/* tipc_buf_append(): Append a buffer to the fragment list of another buffer
+ * @*headbuf: in:  NULL for first frag, otherwise value returned from prev call
+ *            out: set when successful non-complete reassembly, otherwise NULL
+ * @*buf:     in:  the buffer to append. Always defined
+ *            out: head buf after sucessful complete reassembly, otherwise NULL
+ * Returns 1 when reassembly complete, otherwise 0
+ */
+int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
+{
+	struct sk_buff *head = *headbuf;
+	struct sk_buff *frag = *buf;
+	struct sk_buff *tail;
+	struct tipc_msg *msg = buf_msg(frag);
+	u32 fragid = msg_type(msg);
+	bool headstolen;
+	int delta;
+
+	skb_pull(frag, msg_hdr_sz(msg));
+
+	if (fragid == FIRST_FRAGMENT) {
+		if (head || skb_unclone(frag, GFP_ATOMIC))
+			goto out_free;
+		head = *headbuf = frag;
+		skb_frag_list_init(head);
+		*buf = NULL;
+		return 0;
+	}
+	if (!head)
+		goto out_free;
+	tail = TIPC_SKB_CB(head)->tail;
+	if (skb_try_coalesce(head, frag, &headstolen, &delta)) {
+		kfree_skb_partial(frag, headstolen);
+	} else {
+		if (!skb_has_frag_list(head))
+			skb_shinfo(head)->frag_list = frag;
+		else
+			tail->next = frag;
+		head->truesize += frag->truesize;
+		head->data_len += frag->len;
+		head->len += frag->len;
+		TIPC_SKB_CB(head)->tail = frag;
+	}
+	if (fragid == LAST_FRAGMENT) {
+		*buf = head;
+		TIPC_SKB_CB(head)->tail = NULL;
+		*headbuf = NULL;
+		return 1;
+	}
+	*buf = NULL;
+	return 0;
+out_free:
+	pr_warn_ratelimited("Unable to build fragment list\n");
+	kfree_skb(*buf);
+	kfree_skb(*headbuf);
+	*buf = *headbuf = NULL;
+	return 0;
+}
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 76d1269b944..503511903d1 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/msg.h: Include file for TIPC message header routines
  *
- * Copyright (c) 2000-2007, Ericsson AB
+ * Copyright (c) 2000-2007, 2014, Ericsson AB
  * Copyright (c) 2005-2008, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -711,4 +711,7 @@ void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize,
 		   u32 destnode);
 int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect,
 		   unsigned int len, int max_size, struct sk_buff **buf);
+
+int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf);
+
 #endif
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index e0d08055754..8ce730984aa 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -38,34 +38,6 @@
 #include "link.h"
 #include "name_distr.h"
 
-#define ITEM_SIZE sizeof(struct distr_item)
-
-/**
- * struct distr_item - publication info distributed to other nodes
- * @type: name sequence type
- * @lower: name sequence lower bound
- * @upper: name sequence upper bound
- * @ref: publishing port reference
- * @key: publication key
- *
- * ===> All fields are stored in network byte order. <===
- *
- * First 3 fields identify (name or) name sequence being published.
- * Reference field uniquely identifies port that published name sequence.
- * Key field uniquely identifies publication, in the event a port has
- * multiple publications of the same name sequence.
- *
- * Note: There is no field that identifies the publishing node because it is
- * the same for all items contained within a publication message.
- */
-struct distr_item {
-	__be32 type;
-	__be32 lower;
-	__be32 upper;
-	__be32 ref;
-	__be32 key;
-};
-
 /**
  * struct publ_list - list of publications made by this node
  * @list: circular list of publications
@@ -127,20 +99,28 @@ static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest)
 	return buf;
 }
 
-static void named_cluster_distribute(struct sk_buff *buf)
+void named_cluster_distribute(struct sk_buff *buf)
 {
 	struct sk_buff *buf_copy;
 	struct tipc_node *n_ptr;
+	struct tipc_link *l_ptr;
 
-	list_for_each_entry(n_ptr, &tipc_node_list, list) {
-		if (tipc_node_active_links(n_ptr)) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
+		tipc_node_lock(n_ptr);
+		l_ptr = n_ptr->active_links[n_ptr->addr & 1];
+		if (l_ptr) {
 			buf_copy = skb_copy(buf, GFP_ATOMIC);
-			if (!buf_copy)
+			if (!buf_copy) {
+				tipc_node_unlock(n_ptr);
 				break;
+			}
 			msg_set_destnode(buf_msg(buf_copy), n_ptr->addr);
-			tipc_link_send(buf_copy, n_ptr->addr, n_ptr->addr);
+			__tipc_link_xmit(l_ptr, buf_copy);
 		}
+		tipc_node_unlock(n_ptr);
 	}
+	rcu_read_unlock();
 
 	kfree_skb(buf);
 }
@@ -148,7 +128,7 @@ static void named_cluster_distribute(struct sk_buff *buf)
 /**
  * tipc_named_publish - tell other nodes about a new publication by this node
  */
-void tipc_named_publish(struct publication *publ)
+struct sk_buff *tipc_named_publish(struct publication *publ)
 {
 	struct sk_buff *buf;
 	struct distr_item *item;
@@ -157,23 +137,23 @@ void tipc_named_publish(struct publication *publ)
 	publ_lists[publ->scope]->size++;
 
 	if (publ->scope == TIPC_NODE_SCOPE)
-		return;
+		return NULL;
 
 	buf = named_prepare_buf(PUBLICATION, ITEM_SIZE, 0);
 	if (!buf) {
 		pr_warn("Publication distribution failure\n");
-		return;
+		return NULL;
 	}
 
 	item = (struct distr_item *)msg_data(buf_msg(buf));
 	publ_to_item(item, publ);
-	named_cluster_distribute(buf);
+	return buf;
 }
 
 /**
  * tipc_named_withdraw - tell other nodes about a withdrawn publication by this node
  */
-void tipc_named_withdraw(struct publication *publ)
+struct sk_buff *tipc_named_withdraw(struct publication *publ)
 {
 	struct sk_buff *buf;
 	struct distr_item *item;
@@ -182,17 +162,17 @@ void tipc_named_withdraw(struct publication *publ)
 	publ_lists[publ->scope]->size--;
 
 	if (publ->scope == TIPC_NODE_SCOPE)
-		return;
+		return NULL;
 
 	buf = named_prepare_buf(WITHDRAWAL, ITEM_SIZE, 0);
 	if (!buf) {
 		pr_warn("Withdrawal distribution failure\n");
-		return;
+		return NULL;
 	}
 
 	item = (struct distr_item *)msg_data(buf_msg(buf));
 	publ_to_item(item, publ);
-	named_cluster_distribute(buf);
+	return buf;
 }
 
 /*
@@ -231,38 +211,16 @@ static void named_distribute(struct list_head *message_list, u32 node,
 /**
  * tipc_named_node_up - tell specified node about all publications by this node
  */
-void tipc_named_node_up(unsigned long nodearg)
+void tipc_named_node_up(u32 max_item_buf, u32 node)
 {
-	struct tipc_node *n_ptr;
-	struct tipc_link *l_ptr;
-	struct list_head message_list;
-	u32 node = (u32)nodearg;
-	u32 max_item_buf = 0;
-
-	/* compute maximum amount of publication data to send per message */
-	read_lock_bh(&tipc_net_lock);
-	n_ptr = tipc_node_find(node);
-	if (n_ptr) {
-		tipc_node_lock(n_ptr);
-		l_ptr = n_ptr->active_links[0];
-		if (l_ptr)
-			max_item_buf = ((l_ptr->max_pkt - INT_H_SIZE) /
-				ITEM_SIZE) * ITEM_SIZE;
-		tipc_node_unlock(n_ptr);
-	}
-	read_unlock_bh(&tipc_net_lock);
-	if (!max_item_buf)
-		return;
-
-	/* create list of publication messages, then send them as a unit */
-	INIT_LIST_HEAD(&message_list);
+	LIST_HEAD(message_list);
 
 	read_lock_bh(&tipc_nametbl_lock);
 	named_distribute(&message_list, node, &publ_cluster, max_item_buf);
 	named_distribute(&message_list, node, &publ_zone, max_item_buf);
 	read_unlock_bh(&tipc_nametbl_lock);
 
-	tipc_link_send_names(&message_list, node);
+	tipc_link_names_xmit(&message_list, node);
 }
 
 /**
@@ -293,9 +251,9 @@ static void named_purge_publ(struct publication *publ)
 }
 
 /**
- * tipc_named_recv - process name table update message sent by another node
+ * tipc_named_rcv - process name table update message sent by another node
  */
-void tipc_named_recv(struct sk_buff *buf)
+void tipc_named_rcv(struct sk_buff *buf)
 {
 	struct publication *publ;
 	struct tipc_msg *msg = buf_msg(buf);
diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h
index 1e41bdd4f25..b2eed4ec152 100644
--- a/net/tipc/name_distr.h
+++ b/net/tipc/name_distr.h
@@ -39,10 +39,39 @@
 
 #include "name_table.h"
 
-void tipc_named_publish(struct publication *publ);
-void tipc_named_withdraw(struct publication *publ);
-void tipc_named_node_up(unsigned long node);
-void tipc_named_recv(struct sk_buff *buf);
+#define ITEM_SIZE sizeof(struct distr_item)
+
+/**
+ * struct distr_item - publication info distributed to other nodes
+ * @type: name sequence type
+ * @lower: name sequence lower bound
+ * @upper: name sequence upper bound
+ * @ref: publishing port reference
+ * @key: publication key
+ *
+ * ===> All fields are stored in network byte order. <===
+ *
+ * First 3 fields identify (name or) name sequence being published.
+ * Reference field uniquely identifies port that published name sequence.
+ * Key field uniquely identifies publication, in the event a port has
+ * multiple publications of the same name sequence.
+ *
+ * Note: There is no field that identifies the publishing node because it is
+ * the same for all items contained within a publication message.
+ */
+struct distr_item {
+	__be32 type;
+	__be32 lower;
+	__be32 upper;
+	__be32 ref;
+	__be32 key;
+};
+
+struct sk_buff *tipc_named_publish(struct publication *publ);
+struct sk_buff *tipc_named_withdraw(struct publication *publ);
+void named_cluster_distribute(struct sk_buff *buf);
+void tipc_named_node_up(u32 max_item_buf, u32 node);
+void tipc_named_rcv(struct sk_buff *buf);
 void tipc_named_reinit(void);
 
 #endif
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 09dcd54b04e..9d7d37d9518 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -148,8 +148,7 @@ static struct publication *publ_create(u32 type, u32 lower, u32 upper,
  */
 static struct sub_seq *tipc_subseq_alloc(u32 cnt)
 {
-	struct sub_seq *sseq = kcalloc(cnt, sizeof(struct sub_seq), GFP_ATOMIC);
-	return sseq;
+	return kcalloc(cnt, sizeof(struct sub_seq), GFP_ATOMIC);
 }
 
 /**
@@ -665,6 +664,7 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
 					 u32 scope, u32 port_ref, u32 key)
 {
 	struct publication *publ;
+	struct sk_buff *buf = NULL;
 
 	if (table.local_publ_count >= TIPC_MAX_PUBLICATIONS) {
 		pr_warn("Publication failed, local publication limit reached (%u)\n",
@@ -677,9 +677,12 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
 				   tipc_own_addr, port_ref, key);
 	if (likely(publ)) {
 		table.local_publ_count++;
-		tipc_named_publish(publ);
+		buf = tipc_named_publish(publ);
 	}
 	write_unlock_bh(&tipc_nametbl_lock);
+
+	if (buf)
+		named_cluster_distribute(buf);
 	return publ;
 }
 
@@ -689,15 +692,19 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
 int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key)
 {
 	struct publication *publ;
+	struct sk_buff *buf;
 
 	write_lock_bh(&tipc_nametbl_lock);
 	publ = tipc_nametbl_remove_publ(type, lower, tipc_own_addr, ref, key);
 	if (likely(publ)) {
 		table.local_publ_count--;
-		tipc_named_withdraw(publ);
+		buf = tipc_named_withdraw(publ);
 		write_unlock_bh(&tipc_nametbl_lock);
 		list_del_init(&publ->pport_list);
 		kfree(publ);
+
+		if (buf)
+			named_cluster_distribute(buf);
 		return 1;
 	}
 	write_unlock_bh(&tipc_nametbl_lock);
@@ -942,20 +949,48 @@ int tipc_nametbl_init(void)
 	return 0;
 }
 
-void tipc_nametbl_stop(void)
+/**
+ * tipc_purge_publications - remove all publications for a given type
+ *
+ * tipc_nametbl_lock must be held when calling this function
+ */
+static void tipc_purge_publications(struct name_seq *seq)
 {
-	u32 i;
+	struct publication *publ, *safe;
+	struct sub_seq *sseq;
+	struct name_info *info;
 
-	if (!table.types)
+	if (!seq->sseqs) {
+		nameseq_delete_empty(seq);
 		return;
+	}
+	sseq = seq->sseqs;
+	info = sseq->info;
+	list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) {
+		tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node,
+					 publ->ref, publ->key);
+		kfree(publ);
+	}
+}
+
+void tipc_nametbl_stop(void)
+{
+	u32 i;
+	struct name_seq *seq;
+	struct hlist_head *seq_head;
+	struct hlist_node *safe;
 
-	/* Verify name table is empty, then release it */
+	/* Verify name table is empty and purge any lingering
+	 * publications, then release the name table
+	 */
 	write_lock_bh(&tipc_nametbl_lock);
 	for (i = 0; i < TIPC_NAMETBL_SIZE; i++) {
 		if (hlist_empty(&table.types[i]))
 			continue;
-		pr_err("nametbl_stop(): orphaned hash chain detected\n");
-		break;
+		seq_head = &table.types[i];
+		hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) {
+			tipc_purge_publications(seq);
+		}
 	}
 	kfree(table.types);
 	table.types = NULL;
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 7d305ecc09c..f64375e7f99 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -39,45 +39,41 @@
 #include "name_distr.h"
 #include "subscr.h"
 #include "port.h"
+#include "socket.h"
 #include "node.h"
 #include "config.h"
 
 /*
  * The TIPC locking policy is designed to ensure a very fine locking
  * granularity, permitting complete parallel access to individual
- * port and node/link instances. The code consists of three major
+ * port and node/link instances. The code consists of four major
  * locking domains, each protected with their own disjunct set of locks.
  *
- * 1: The routing hierarchy.
- *    Comprises the structures 'zone', 'cluster', 'node', 'link'
- *    and 'bearer'. The whole hierarchy is protected by a big
- *    read/write lock, tipc_net_lock, to enssure that nothing is added
- *    or removed while code is accessing any of these structures.
- *    This layer must not be called from the two others while they
- *    hold any of their own locks.
- *    Neither must it itself do any upcalls to the other two before
- *    it has released tipc_net_lock and other protective locks.
+ * 1: The bearer level.
+ *    RTNL lock is used to serialize the process of configuring bearer
+ *    on update side, and RCU lock is applied on read side to make
+ *    bearer instance valid on both paths of message transmission and
+ *    reception.
  *
- *   Within the tipc_net_lock domain there are two sub-domains;'node' and
- *   'bearer', where local write operations are permitted,
- *   provided that those are protected by individual spin_locks
- *   per instance. Code holding tipc_net_lock(read) and a node spin_lock
- *   is permitted to poke around in both the node itself and its
- *   subordinate links. I.e, it can update link counters and queues,
- *   change link state, send protocol messages, and alter the
- *   "active_links" array in the node; but it can _not_ remove a link
- *   or a node from the overall structure.
- *   Correspondingly, individual bearers may change status within a
- *   tipc_net_lock(read), protected by an individual spin_lock ber bearer
- *   instance, but it needs tipc_net_lock(write) to remove/add any bearers.
+ * 2: The node and link level.
+ *    All node instances are saved into two tipc_node_list and node_htable
+ *    lists. The two lists are protected by node_list_lock on write side,
+ *    and they are guarded with RCU lock on read side. Especially node
+ *    instance is destroyed only when TIPC module is removed, and we can
+ *    confirm that there has no any user who is accessing the node at the
+ *    moment. Therefore, Except for iterating the two lists within RCU
+ *    protection, it's no needed to hold RCU that we access node instance
+ *    in other places.
  *
+ *    In addition, all members in node structure including link instances
+ *    are protected by node spin lock.
  *
- *  2: The transport level of the protocol.
- *     This consists of the structures port, (and its user level
- *     representations, such as user_port and tipc_sock), reference and
- *     tipc_user (port.c, reg.c, socket.c).
+ * 3: The transport level of the protocol.
+ *    This consists of the structures port, (and its user level
+ *    representations, such as user_port and tipc_sock), reference and
+ *    tipc_user (port.c, reg.c, socket.c).
  *
- *     This layer has four different locks:
+ *    This layer has four different locks:
  *     - The tipc_port spin_lock. This is protecting each port instance
  *       from parallel data access and removal. Since we can not place
  *       this lock in the port itself, it has been placed in the
@@ -96,7 +92,7 @@
  *       There are two such lists; 'port_list', which is used for management,
  *       and 'wait_list', which is used to queue ports during congestion.
  *
- *  3: The name table (name_table.c, name_distr.c, subscription.c)
+ *  4: The name table (name_table.c, name_distr.c, subscription.c)
  *     - There is one big read/write-lock (tipc_nametbl_lock) protecting the
  *       overall name table structure. Nothing must be added/removed to
  *       this structure without holding write access to it.
@@ -108,8 +104,6 @@
  *     - A local spin_lock protecting the queue of subscriber events.
 */
 
-DEFINE_RWLOCK(tipc_net_lock);
-
 static void net_route_named_msg(struct sk_buff *buf)
 {
 	struct tipc_msg *msg = buf_msg(buf);
@@ -146,19 +140,19 @@ void tipc_net_route_msg(struct sk_buff *buf)
 	if (tipc_in_scope(dnode, tipc_own_addr)) {
 		if (msg_isdata(msg)) {
 			if (msg_mcast(msg))
-				tipc_port_recv_mcast(buf, NULL);
+				tipc_port_mcast_rcv(buf, NULL);
 			else if (msg_destport(msg))
-				tipc_port_recv_msg(buf);
+				tipc_sk_rcv(buf);
 			else
 				net_route_named_msg(buf);
 			return;
 		}
 		switch (msg_user(msg)) {
 		case NAME_DISTRIBUTOR:
-			tipc_named_recv(buf);
+			tipc_named_rcv(buf);
 			break;
 		case CONN_MANAGER:
-			tipc_port_recv_proto_msg(buf);
+			tipc_port_proto_rcv(buf);
 			break;
 		default:
 			kfree_skb(buf);
@@ -168,38 +162,41 @@ void tipc_net_route_msg(struct sk_buff *buf)
 
 	/* Handle message for another node */
 	skb_trim(buf, msg_size(msg));
-	tipc_link_send(buf, dnode, msg_link_selector(msg));
+	tipc_link_xmit(buf, dnode, msg_link_selector(msg));
 }
 
-void tipc_net_start(u32 addr)
+int tipc_net_start(u32 addr)
 {
 	char addr_string[16];
+	int res;
 
-	write_lock_bh(&tipc_net_lock);
 	tipc_own_addr = addr;
 	tipc_named_reinit();
 	tipc_port_reinit();
-	tipc_bclink_init();
-	write_unlock_bh(&tipc_net_lock);
+	res = tipc_bclink_init();
+	if (res)
+		return res;
 
-	tipc_cfg_reinit();
+	tipc_nametbl_publish(TIPC_CFG_SRV, tipc_own_addr, tipc_own_addr,
+			     TIPC_ZONE_SCOPE, 0, tipc_own_addr);
 
 	pr_info("Started in network mode\n");
 	pr_info("Own node address %s, network identity %u\n",
 		tipc_addr_string_fill(addr_string, tipc_own_addr), tipc_net_id);
+	return 0;
 }
 
 void tipc_net_stop(void)
 {
-	struct tipc_node *node, *t_node;
-
 	if (!tipc_own_addr)
 		return;
-	write_lock_bh(&tipc_net_lock);
+
+	tipc_nametbl_withdraw(TIPC_CFG_SRV, tipc_own_addr, 0, tipc_own_addr);
+	rtnl_lock();
 	tipc_bearer_stop();
 	tipc_bclink_stop();
-	list_for_each_entry_safe(node, t_node, &tipc_node_list, list)
-		tipc_node_delete(node);
-	write_unlock_bh(&tipc_net_lock);
+	tipc_node_stop();
+	rtnl_unlock();
+
 	pr_info("Left network mode\n");
 }
diff --git a/net/tipc/net.h b/net/tipc/net.h
index 079daadb3f7..c6c2b46f7c2 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -37,11 +37,9 @@
 #ifndef _TIPC_NET_H
 #define _TIPC_NET_H
 
-extern rwlock_t tipc_net_lock;
-
 void tipc_net_route_msg(struct sk_buff *buf);
 
-void tipc_net_start(u32 addr);
+int tipc_net_start(u32 addr);
 void tipc_net_stop(void);
 
 #endif
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 9f72a637636..ad844d36534 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -47,7 +47,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
 	int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
 	u16 cmd;
 
-	if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN)))
+	if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN)))
 		cmd = TIPC_CMD_NOT_NET_ADMIN;
 	else
 		cmd = req_userhdr->cmd;
@@ -83,8 +83,6 @@ static struct genl_ops tipc_genl_ops[] = {
 	},
 };
 
-static int tipc_genl_family_registered;
-
 int tipc_netlink_start(void)
 {
 	int res;
@@ -94,16 +92,10 @@ int tipc_netlink_start(void)
 		pr_err("Failed to register netlink interface\n");
 		return res;
 	}
-
-	tipc_genl_family_registered = 1;
 	return 0;
 }
 
 void tipc_netlink_stop(void)
 {
-	if (!tipc_genl_family_registered)
-		return;
-
 	genl_unregister_family(&tipc_genl_family);
-	tipc_genl_family_registered = 0;
 }
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 25100c0a6fe..5b44c3041be 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -2,7 +2,7 @@
  * net/tipc/node.c: TIPC node management routines
  *
  * Copyright (c) 2000-2006, 2012 Ericsson AB
- * Copyright (c) 2005-2006, 2010-2011, Wind River Systems
+ * Copyright (c) 2005-2006, 2010-2014, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -44,13 +44,11 @@
 static void node_lost_contact(struct tipc_node *n_ptr);
 static void node_established_contact(struct tipc_node *n_ptr);
 
-static DEFINE_SPINLOCK(node_create_lock);
-
 static struct hlist_head node_htable[NODE_HTABLE_SIZE];
 LIST_HEAD(tipc_node_list);
 static u32 tipc_num_nodes;
-
-static atomic_t tipc_num_links = ATOMIC_INIT(0);
+static u32 tipc_num_links;
+static DEFINE_SPINLOCK(node_list_lock);
 
 /*
  * A trivial power-of-two bitmask technique is used for speed, since this
@@ -73,37 +71,26 @@ struct tipc_node *tipc_node_find(u32 addr)
 	if (unlikely(!in_own_cluster_exact(addr)))
 		return NULL;
 
-	hlist_for_each_entry(node, &node_htable[tipc_hashfn(addr)], hash) {
-		if (node->addr == addr)
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(node, &node_htable[tipc_hashfn(addr)], hash) {
+		if (node->addr == addr) {
+			rcu_read_unlock();
 			return node;
+		}
 	}
+	rcu_read_unlock();
 	return NULL;
 }
 
-/**
- * tipc_node_create - create neighboring node
- *
- * Currently, this routine is called by neighbor discovery code, which holds
- * net_lock for reading only.  We must take node_create_lock to ensure a node
- * isn't created twice if two different bearers discover the node at the same
- * time.  (It would be preferable to switch to holding net_lock in write mode,
- * but this is a non-trivial change.)
- */
 struct tipc_node *tipc_node_create(u32 addr)
 {
 	struct tipc_node *n_ptr, *temp_node;
 
-	spin_lock_bh(&node_create_lock);
-
-	n_ptr = tipc_node_find(addr);
-	if (n_ptr) {
-		spin_unlock_bh(&node_create_lock);
-		return n_ptr;
-	}
+	spin_lock_bh(&node_list_lock);
 
 	n_ptr = kzalloc(sizeof(*n_ptr), GFP_ATOMIC);
 	if (!n_ptr) {
-		spin_unlock_bh(&node_create_lock);
+		spin_unlock_bh(&node_list_lock);
 		pr_warn("Node creation failed, no memory\n");
 		return NULL;
 	}
@@ -114,31 +101,41 @@ struct tipc_node *tipc_node_create(u32 addr)
 	INIT_LIST_HEAD(&n_ptr->list);
 	INIT_LIST_HEAD(&n_ptr->nsub);
 
-	hlist_add_head(&n_ptr->hash, &node_htable[tipc_hashfn(addr)]);
+	hlist_add_head_rcu(&n_ptr->hash, &node_htable[tipc_hashfn(addr)]);
 
-	list_for_each_entry(temp_node, &tipc_node_list, list) {
+	list_for_each_entry_rcu(temp_node, &tipc_node_list, list) {
 		if (n_ptr->addr < temp_node->addr)
 			break;
 	}
-	list_add_tail(&n_ptr->list, &temp_node->list);
-	n_ptr->block_setup = WAIT_PEER_DOWN;
+	list_add_tail_rcu(&n_ptr->list, &temp_node->list);
+	n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN;
 	n_ptr->signature = INVALID_NODE_SIG;
 
 	tipc_num_nodes++;
 
-	spin_unlock_bh(&node_create_lock);
+	spin_unlock_bh(&node_list_lock);
 	return n_ptr;
 }
 
-void tipc_node_delete(struct tipc_node *n_ptr)
+static void tipc_node_delete(struct tipc_node *n_ptr)
 {
-	list_del(&n_ptr->list);
-	hlist_del(&n_ptr->hash);
-	kfree(n_ptr);
+	list_del_rcu(&n_ptr->list);
+	hlist_del_rcu(&n_ptr->hash);
+	kfree_rcu(n_ptr, rcu);
 
 	tipc_num_nodes--;
 }
 
+void tipc_node_stop(void)
+{
+	struct tipc_node *node, *t_node;
+
+	spin_lock_bh(&node_list_lock);
+	list_for_each_entry_safe(node, t_node, &tipc_node_list, list)
+		tipc_node_delete(node);
+	spin_unlock_bh(&node_list_lock);
+}
+
 /**
  * tipc_node_link_up - handle addition of link
  *
@@ -147,11 +144,13 @@ void tipc_node_delete(struct tipc_node *n_ptr)
 void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 {
 	struct tipc_link **active = &n_ptr->active_links[0];
+	u32 addr = n_ptr->addr;
 
 	n_ptr->working_links++;
-
+	tipc_nametbl_publish(TIPC_LINK_STATE, addr, addr, TIPC_NODE_SCOPE,
+			     l_ptr->bearer_id, addr);
 	pr_info("Established link <%s> on network plane %c\n",
-		l_ptr->name, l_ptr->b_ptr->net_plane);
+		l_ptr->name, l_ptr->net_plane);
 
 	if (!active[0]) {
 		active[0] = active[1] = l_ptr;
@@ -162,7 +161,7 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 		pr_info("New link <%s> becomes standby\n", l_ptr->name);
 		return;
 	}
-	tipc_link_send_duplicate(active[0], l_ptr);
+	tipc_link_dup_queue_xmit(active[0], l_ptr);
 	if (l_ptr->priority == active[0]->priority) {
 		active[0] = l_ptr;
 		return;
@@ -206,16 +205,18 @@ static void node_select_active_links(struct tipc_node *n_ptr)
 void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 {
 	struct tipc_link **active;
+	u32 addr = n_ptr->addr;
 
 	n_ptr->working_links--;
+	tipc_nametbl_withdraw(TIPC_LINK_STATE, addr, l_ptr->bearer_id, addr);
 
 	if (!tipc_link_is_active(l_ptr)) {
 		pr_info("Lost standby link <%s> on network plane %c\n",
-			l_ptr->name, l_ptr->b_ptr->net_plane);
+			l_ptr->name, l_ptr->net_plane);
 		return;
 	}
 	pr_info("Lost link <%s> on network plane %c\n",
-		l_ptr->name, l_ptr->b_ptr->net_plane);
+		l_ptr->name, l_ptr->net_plane);
 
 	active = &n_ptr->active_links[0];
 	if (active[0] == l_ptr)
@@ -225,7 +226,7 @@ void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 	if (active[0] == l_ptr)
 		node_select_active_links(n_ptr);
 	if (tipc_node_is_up(n_ptr))
-		tipc_link_changeover(l_ptr);
+		tipc_link_failover_send_queue(l_ptr);
 	else
 		node_lost_contact(n_ptr);
 }
@@ -235,11 +236,6 @@ int tipc_node_active_links(struct tipc_node *n_ptr)
 	return n_ptr->active_links[0] != NULL;
 }
 
-int tipc_node_redundant_links(struct tipc_node *n_ptr)
-{
-	return n_ptr->working_links > 1;
-}
-
 int tipc_node_is_up(struct tipc_node *n_ptr)
 {
 	return tipc_node_active_links(n_ptr);
@@ -247,40 +243,36 @@ int tipc_node_is_up(struct tipc_node *n_ptr)
 
 void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 {
-	n_ptr->links[l_ptr->b_ptr->identity] = l_ptr;
-	atomic_inc(&tipc_num_links);
+	n_ptr->links[l_ptr->bearer_id] = l_ptr;
+	spin_lock_bh(&node_list_lock);
+	tipc_num_links++;
+	spin_unlock_bh(&node_list_lock);
 	n_ptr->link_cnt++;
 }
 
 void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 {
-	n_ptr->links[l_ptr->b_ptr->identity] = NULL;
-	atomic_dec(&tipc_num_links);
-	n_ptr->link_cnt--;
+	int i;
+
+	for (i = 0; i < MAX_BEARERS; i++) {
+		if (l_ptr != n_ptr->links[i])
+			continue;
+		n_ptr->links[i] = NULL;
+		spin_lock_bh(&node_list_lock);
+		tipc_num_links--;
+		spin_unlock_bh(&node_list_lock);
+		n_ptr->link_cnt--;
+	}
 }
 
 static void node_established_contact(struct tipc_node *n_ptr)
 {
-	tipc_k_signal((Handler)tipc_named_node_up, n_ptr->addr);
+	n_ptr->action_flags |= TIPC_NOTIFY_NODE_UP;
 	n_ptr->bclink.oos_state = 0;
 	n_ptr->bclink.acked = tipc_bclink_get_last_sent();
 	tipc_bclink_add_node(n_ptr->addr);
 }
 
-static void node_name_purge_complete(unsigned long node_addr)
-{
-	struct tipc_node *n_ptr;
-
-	read_lock_bh(&tipc_net_lock);
-	n_ptr = tipc_node_find(node_addr);
-	if (n_ptr) {
-		tipc_node_lock(n_ptr);
-		n_ptr->block_setup &= ~WAIT_NAMES_GONE;
-		tipc_node_unlock(n_ptr);
-	}
-	read_unlock_bh(&tipc_net_lock);
-}
-
 static void node_lost_contact(struct tipc_node *n_ptr)
 {
 	char addr_string[16];
@@ -291,17 +283,12 @@ static void node_lost_contact(struct tipc_node *n_ptr)
 
 	/* Flush broadcast link info associated with lost node */
 	if (n_ptr->bclink.recv_permitted) {
-		while (n_ptr->bclink.deferred_head) {
-			struct sk_buff *buf = n_ptr->bclink.deferred_head;
-			n_ptr->bclink.deferred_head = buf->next;
-			kfree_skb(buf);
-		}
+		kfree_skb_list(n_ptr->bclink.deferred_head);
 		n_ptr->bclink.deferred_size = 0;
 
-		if (n_ptr->bclink.reasm_head) {
-			kfree_skb(n_ptr->bclink.reasm_head);
-			n_ptr->bclink.reasm_head = NULL;
-			n_ptr->bclink.reasm_tail = NULL;
+		if (n_ptr->bclink.reasm_buf) {
+			kfree_skb(n_ptr->bclink.reasm_buf);
+			n_ptr->bclink.reasm_buf = NULL;
 		}
 
 		tipc_bclink_remove_node(n_ptr->addr);
@@ -320,12 +307,13 @@ static void node_lost_contact(struct tipc_node *n_ptr)
 		tipc_link_reset_fragments(l_ptr);
 	}
 
-	/* Notify subscribers */
-	tipc_nodesub_notify(n_ptr);
+	n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN;
 
-	/* Prevent re-contact with node until cleanup is done */
-	n_ptr->block_setup = WAIT_PEER_DOWN | WAIT_NAMES_GONE;
-	tipc_k_signal((Handler)node_name_purge_complete, n_ptr->addr);
+	/* Notify subscribers and prevent re-contact with node until
+	 * cleanup is done.
+	 */
+	n_ptr->action_flags |= TIPC_WAIT_PEER_LINKS_DOWN |
+			       TIPC_NOTIFY_NODE_DOWN;
 }
 
 struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space)
@@ -344,27 +332,28 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space)
 		return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE
 						   " (network address)");
 
-	read_lock_bh(&tipc_net_lock);
+	spin_lock_bh(&node_list_lock);
 	if (!tipc_num_nodes) {
-		read_unlock_bh(&tipc_net_lock);
+		spin_unlock_bh(&node_list_lock);
 		return tipc_cfg_reply_none();
 	}
 
 	/* For now, get space for all other nodes */
 	payload_size = TLV_SPACE(sizeof(node_info)) * tipc_num_nodes;
 	if (payload_size > 32768u) {
-		read_unlock_bh(&tipc_net_lock);
+		spin_unlock_bh(&node_list_lock);
 		return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
 						   " (too many nodes)");
 	}
+	spin_unlock_bh(&node_list_lock);
+
 	buf = tipc_cfg_reply_alloc(payload_size);
-	if (!buf) {
-		read_unlock_bh(&tipc_net_lock);
+	if (!buf)
 		return NULL;
-	}
 
 	/* Add TLVs for all nodes in scope */
-	list_for_each_entry(n_ptr, &tipc_node_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
 		if (!tipc_in_scope(domain, n_ptr->addr))
 			continue;
 		node_info.addr = htonl(n_ptr->addr);
@@ -372,8 +361,7 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space)
 		tipc_cfg_append_tlv(buf, TIPC_TLV_NODE_INFO,
 				    &node_info, sizeof(node_info));
 	}
-
-	read_unlock_bh(&tipc_net_lock);
+	rcu_read_unlock();
 	return buf;
 }
 
@@ -396,21 +384,19 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space)
 	if (!tipc_own_addr)
 		return tipc_cfg_reply_none();
 
-	read_lock_bh(&tipc_net_lock);
-
+	spin_lock_bh(&node_list_lock);
 	/* Get space for all unicast links + broadcast link */
-	payload_size = TLV_SPACE(sizeof(link_info)) *
-		(atomic_read(&tipc_num_links) + 1);
+	payload_size = TLV_SPACE((sizeof(link_info)) * (tipc_num_links + 1));
 	if (payload_size > 32768u) {
-		read_unlock_bh(&tipc_net_lock);
+		spin_unlock_bh(&node_list_lock);
 		return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
 						   " (too many links)");
 	}
+	spin_unlock_bh(&node_list_lock);
+
 	buf = tipc_cfg_reply_alloc(payload_size);
-	if (!buf) {
-		read_unlock_bh(&tipc_net_lock);
+	if (!buf)
 		return NULL;
-	}
 
 	/* Add TLV for broadcast link */
 	link_info.dest = htonl(tipc_cluster_mask(tipc_own_addr));
@@ -419,7 +405,8 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space)
 	tipc_cfg_append_tlv(buf, TIPC_TLV_LINK_INFO, &link_info, sizeof(link_info));
 
 	/* Add TLVs for any other links in scope */
-	list_for_each_entry(n_ptr, &tipc_node_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
 		u32 i;
 
 		if (!tipc_in_scope(domain, n_ptr->addr))
@@ -436,7 +423,66 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space)
 		}
 		tipc_node_unlock(n_ptr);
 	}
-
-	read_unlock_bh(&tipc_net_lock);
+	rcu_read_unlock();
 	return buf;
 }
+
+/**
+ * tipc_node_get_linkname - get the name of a link
+ *
+ * @bearer_id: id of the bearer
+ * @node: peer node address
+ * @linkname: link name output buffer
+ *
+ * Returns 0 on success
+ */
+int tipc_node_get_linkname(u32 bearer_id, u32 addr, char *linkname, size_t len)
+{
+	struct tipc_link *link;
+	struct tipc_node *node = tipc_node_find(addr);
+
+	if ((bearer_id >= MAX_BEARERS) || !node)
+		return -EINVAL;
+	tipc_node_lock(node);
+	link = node->links[bearer_id];
+	if (link) {
+		strncpy(linkname, link->name, len);
+		tipc_node_unlock(node);
+		return 0;
+	}
+	tipc_node_unlock(node);
+	return -EINVAL;
+}
+
+void tipc_node_unlock(struct tipc_node *node)
+{
+	LIST_HEAD(nsub_list);
+	struct tipc_link *link;
+	int pkt_sz = 0;
+	u32 addr = 0;
+
+	if (likely(!node->action_flags)) {
+		spin_unlock_bh(&node->lock);
+		return;
+	}
+
+	if (node->action_flags & TIPC_NOTIFY_NODE_DOWN) {
+		list_replace_init(&node->nsub, &nsub_list);
+		node->action_flags &= ~TIPC_NOTIFY_NODE_DOWN;
+	}
+	if (node->action_flags & TIPC_NOTIFY_NODE_UP) {
+		link = node->active_links[0];
+		node->action_flags &= ~TIPC_NOTIFY_NODE_UP;
+		if (link) {
+			pkt_sz = ((link->max_pkt - INT_H_SIZE) / ITEM_SIZE) *
+				  ITEM_SIZE;
+			addr = node->addr;
+		}
+	}
+	spin_unlock_bh(&node->lock);
+
+	if (!list_empty(&nsub_list))
+		tipc_nodesub_notify(&nsub_list);
+	if (pkt_sz)
+		tipc_named_node_up(pkt_sz, addr);
+}
diff --git a/net/tipc/node.h b/net/tipc/node.h
index e5e96c04e16..9087063793f 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -2,7 +2,7 @@
  * net/tipc/node.h: Include file for TIPC node management routines
  *
  * Copyright (c) 2000-2006, Ericsson AB
- * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * Copyright (c) 2005, 2010-2014, Wind River Systems
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -47,87 +47,100 @@
  */
 #define INVALID_NODE_SIG 0x10000
 
-/* Flags used to block (re)establishment of contact with a neighboring node */
-#define WAIT_PEER_DOWN	0x0001	/* wait to see that peer's links are down */
-#define WAIT_NAMES_GONE	0x0002	/* wait for peer's publications to be purged */
-#define WAIT_NODE_DOWN	0x0004	/* wait until peer node is declared down */
+/* Flags used to take different actions according to flag type
+ * TIPC_WAIT_PEER_LINKS_DOWN: wait to see that peer's links are down
+ * TIPC_WAIT_OWN_LINKS_DOWN: wait until peer node is declared down
+ * TIPC_NOTIFY_NODE_DOWN: notify node is down
+ * TIPC_NOTIFY_NODE_UP: notify node is up
+ */
+enum {
+	TIPC_WAIT_PEER_LINKS_DOWN	= (1 << 1),
+	TIPC_WAIT_OWN_LINKS_DOWN	= (1 << 2),
+	TIPC_NOTIFY_NODE_DOWN		= (1 << 3),
+	TIPC_NOTIFY_NODE_UP		= (1 << 4)
+};
+
+/**
+ * struct tipc_node_bclink - TIPC node bclink structure
+ * @acked: sequence # of last outbound b'cast message acknowledged by node
+ * @last_in: sequence # of last in-sequence b'cast message received from node
+ * @last_sent: sequence # of last b'cast message sent by node
+ * @oos_state: state tracker for handling OOS b'cast messages
+ * @deferred_size: number of OOS b'cast messages in deferred queue
+ * @deferred_head: oldest OOS b'cast message received from node
+ * @deferred_tail: newest OOS b'cast message received from node
+ * @reasm_buf: broadcast reassembly queue head from node
+ * @recv_permitted: true if node is allowed to receive b'cast messages
+ */
+struct tipc_node_bclink {
+	u32 acked;
+	u32 last_in;
+	u32 last_sent;
+	u32 oos_state;
+	u32 deferred_size;
+	struct sk_buff *deferred_head;
+	struct sk_buff *deferred_tail;
+	struct sk_buff *reasm_buf;
+	bool recv_permitted;
+};
 
 /**
  * struct tipc_node - TIPC node structure
  * @addr: network address of node
  * @lock: spinlock governing access to structure
  * @hash: links to adjacent nodes in unsorted hash chain
- * @list: links to adjacent nodes in sorted list of cluster's nodes
- * @nsub: list of "node down" subscriptions monitoring node
  * @active_links: pointers to active links to node
  * @links: pointers to all links to node
+ * @action_flags: bit mask of different types of node actions
+ * @bclink: broadcast-related info
+ * @list: links to adjacent nodes in sorted list of cluster's nodes
  * @working_links: number of working links to node (both active and standby)
- * @block_setup: bit mask of conditions preventing link establishment to node
  * @link_cnt: number of links to node
- * @permit_changeover: non-zero if node has redundant links to this system
  * @signature: node instance identifier
- * @bclink: broadcast-related info
- *    @acked: sequence # of last outbound b'cast message acknowledged by node
- *    @last_in: sequence # of last in-sequence b'cast message received from node
- *    @last_sent: sequence # of last b'cast message sent by node
- *    @oos_state: state tracker for handling OOS b'cast messages
- *    @deferred_size: number of OOS b'cast messages in deferred queue
- *    @deferred_head: oldest OOS b'cast message received from node
- *    @deferred_tail: newest OOS b'cast message received from node
- *    @reasm_head: broadcast reassembly queue head from node
- *    @reasm_tail: last broadcast fragment received from node
- *    @recv_permitted: true if node is allowed to receive b'cast messages
+ * @nsub: list of "node down" subscriptions monitoring node
+ * @rcu: rcu struct for tipc_node
  */
 struct tipc_node {
 	u32 addr;
 	spinlock_t lock;
 	struct hlist_node hash;
-	struct list_head list;
-	struct list_head nsub;
 	struct tipc_link *active_links[2];
 	struct tipc_link *links[MAX_BEARERS];
+	unsigned int action_flags;
+	struct tipc_node_bclink bclink;
+	struct list_head list;
 	int link_cnt;
 	int working_links;
-	int block_setup;
-	int permit_changeover;
 	u32 signature;
-	struct {
-		u32 acked;
-		u32 last_in;
-		u32 last_sent;
-		u32 oos_state;
-		u32 deferred_size;
-		struct sk_buff *deferred_head;
-		struct sk_buff *deferred_tail;
-		struct sk_buff *reasm_head;
-		struct sk_buff *reasm_tail;
-		bool recv_permitted;
-	} bclink;
+	struct list_head nsub;
+	struct rcu_head rcu;
 };
 
 extern struct list_head tipc_node_list;
 
 struct tipc_node *tipc_node_find(u32 addr);
 struct tipc_node *tipc_node_create(u32 addr);
-void tipc_node_delete(struct tipc_node *n_ptr);
+void tipc_node_stop(void);
 void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
 void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
 void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
 void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr);
 int tipc_node_active_links(struct tipc_node *n_ptr);
-int tipc_node_redundant_links(struct tipc_node *n_ptr);
 int tipc_node_is_up(struct tipc_node *n_ptr);
 struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space);
 struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space);
+int tipc_node_get_linkname(u32 bearer_id, u32 node, char *linkname, size_t len);
+void tipc_node_unlock(struct tipc_node *node);
 
-static inline void tipc_node_lock(struct tipc_node *n_ptr)
+static inline void tipc_node_lock(struct tipc_node *node)
 {
-	spin_lock_bh(&n_ptr->lock);
+	spin_lock_bh(&node->lock);
 }
 
-static inline void tipc_node_unlock(struct tipc_node *n_ptr)
+static inline bool tipc_node_blocked(struct tipc_node *node)
 {
-	spin_unlock_bh(&n_ptr->lock);
+	return (node->action_flags & (TIPC_WAIT_PEER_LINKS_DOWN |
+		TIPC_NOTIFY_NODE_DOWN | TIPC_WAIT_OWN_LINKS_DOWN));
 }
 
 #endif
diff --git a/net/tipc/node_subscr.c b/net/tipc/node_subscr.c
index 8a7384c04ad..7c59ab1d6ec 100644
--- a/net/tipc/node_subscr.c
+++ b/net/tipc/node_subscr.c
@@ -81,14 +81,13 @@ void tipc_nodesub_unsubscribe(struct tipc_node_subscr *node_sub)
  *
  * Note: node is locked by caller
  */
-void tipc_nodesub_notify(struct tipc_node *node)
+void tipc_nodesub_notify(struct list_head *nsub_list)
 {
-	struct tipc_node_subscr *ns;
+	struct tipc_node_subscr *ns, *safe;
 
-	list_for_each_entry(ns, &node->nsub, nodesub_list) {
+	list_for_each_entry_safe(ns, safe, nsub_list, nodesub_list) {
 		if (ns->handle_node_down) {
-			tipc_k_signal((Handler)ns->handle_node_down,
-				      (unsigned long)ns->usr_handle);
+			ns->handle_node_down(ns->usr_handle);
 			ns->handle_node_down = NULL;
 		}
 	}
diff --git a/net/tipc/node_subscr.h b/net/tipc/node_subscr.h
index c95d20727de..d91b8cc81e3 100644
--- a/net/tipc/node_subscr.h
+++ b/net/tipc/node_subscr.h
@@ -58,6 +58,6 @@ struct tipc_node_subscr {
 void tipc_nodesub_subscribe(struct tipc_node_subscr *node_sub, u32 addr,
 			    void *usr_handle, net_ev_handler handle_down);
 void tipc_nodesub_unsubscribe(struct tipc_node_subscr *node_sub);
-void tipc_nodesub_notify(struct tipc_node *node);
+void tipc_nodesub_notify(struct list_head *nsub_list);
 
 #endif
diff --git a/net/tipc/port.c b/net/tipc/port.c
index c081a763230..5fd7acce01e 100644
--- a/net/tipc/port.c
+++ b/net/tipc/port.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/port.c: TIPC port code
  *
- * Copyright (c) 1992-2007, Ericsson AB
+ * Copyright (c) 1992-2007, 2014, Ericsson AB
  * Copyright (c) 2004-2008, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -38,6 +38,7 @@
 #include "config.h"
 #include "port.h"
 #include "name_table.h"
+#include "socket.h"
 
 /* Connection management: */
 #define PROBING_INTERVAL 3600000	/* [ms] => 1 h */
@@ -54,17 +55,6 @@ static struct sk_buff *port_build_self_abort_msg(struct tipc_port *, u32 err);
 static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *, u32 err);
 static void port_timeout(unsigned long ref);
 
-
-static u32 port_peernode(struct tipc_port *p_ptr)
-{
-	return msg_destnode(&p_ptr->phdr);
-}
-
-static u32 port_peerport(struct tipc_port *p_ptr)
-{
-	return msg_destport(&p_ptr->phdr);
-}
-
 /**
  * tipc_port_peer_msg - verify message was sent by connected port's peer
  *
@@ -76,33 +66,32 @@ int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg)
 	u32 peernode;
 	u32 orignode;
 
-	if (msg_origport(msg) != port_peerport(p_ptr))
+	if (msg_origport(msg) != tipc_port_peerport(p_ptr))
 		return 0;
 
 	orignode = msg_orignode(msg);
-	peernode = port_peernode(p_ptr);
+	peernode = tipc_port_peernode(p_ptr);
 	return (orignode == peernode) ||
 		(!orignode && (peernode == tipc_own_addr)) ||
 		(!peernode && (orignode == tipc_own_addr));
 }
 
 /**
- * tipc_multicast - send a multicast message to local and remote destinations
+ * tipc_port_mcast_xmit - send a multicast message to local and remote
+ * destinations
  */
-int tipc_multicast(u32 ref, struct tipc_name_seq const *seq,
-		   struct iovec const *msg_sect, unsigned int len)
+int tipc_port_mcast_xmit(struct tipc_port *oport,
+			 struct tipc_name_seq const *seq,
+			 struct iovec const *msg_sect,
+			 unsigned int len)
 {
 	struct tipc_msg *hdr;
 	struct sk_buff *buf;
 	struct sk_buff *ibuf = NULL;
 	struct tipc_port_list dports = {0, NULL, };
-	struct tipc_port *oport = tipc_port_deref(ref);
 	int ext_targets;
 	int res;
 
-	if (unlikely(!oport))
-		return -EINVAL;
-
 	/* Create multicast message */
 	hdr = &oport->phdr;
 	msg_set_type(hdr, TIPC_MCAST_MSG);
@@ -131,7 +120,7 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq,
 				return -ENOMEM;
 			}
 		}
-		res = tipc_bclink_send_msg(buf);
+		res = tipc_bclink_xmit(buf);
 		if ((res < 0) && (dports.count != 0))
 			kfree_skb(ibuf);
 	} else {
@@ -140,7 +129,7 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq,
 
 	if (res >= 0) {
 		if (ibuf)
-			tipc_port_recv_mcast(ibuf, &dports);
+			tipc_port_mcast_rcv(ibuf, &dports);
 	} else {
 		tipc_port_list_free(&dports);
 	}
@@ -148,11 +137,11 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq,
 }
 
 /**
- * tipc_port_recv_mcast - deliver multicast message to all destination ports
+ * tipc_port_mcast_rcv - deliver multicast message to all destination ports
  *
  * If there is no port list, perform a lookup to create one
  */
-void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp)
+void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp)
 {
 	struct tipc_msg *msg;
 	struct tipc_port_list dports = {0, NULL, };
@@ -176,7 +165,7 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp)
 		msg_set_destnode(msg, tipc_own_addr);
 		if (dp->count == 1) {
 			msg_set_destport(msg, dp->ports[0]);
-			tipc_port_recv_msg(buf);
+			tipc_sk_rcv(buf);
 			tipc_port_list_free(dp);
 			return;
 		}
@@ -191,7 +180,7 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp)
 			if ((index == 0) && (cnt != 0))
 				item = item->next;
 			msg_set_destport(buf_msg(b), item->ports[index]);
-			tipc_port_recv_msg(b);
+			tipc_sk_rcv(b);
 		}
 	}
 exit:
@@ -199,40 +188,32 @@ exit:
 	tipc_port_list_free(dp);
 }
 
-/**
- * tipc_createport - create a generic TIPC port
+
+void tipc_port_wakeup(struct tipc_port *port)
+{
+	tipc_sock_wakeup(tipc_port_to_sock(port));
+}
+
+/* tipc_port_init - intiate TIPC port and lock it
  *
- * Returns pointer to (locked) TIPC port, or NULL if unable to create it
+ * Returns obtained reference if initialization is successful, zero otherwise
  */
-struct tipc_port *tipc_createport(struct sock *sk,
-				  u32 (*dispatcher)(struct tipc_port *,
-				  struct sk_buff *),
-				  void (*wakeup)(struct tipc_port *),
-				  const u32 importance)
+u32 tipc_port_init(struct tipc_port *p_ptr,
+		   const unsigned int importance)
 {
-	struct tipc_port *p_ptr;
 	struct tipc_msg *msg;
 	u32 ref;
 
-	p_ptr = kzalloc(sizeof(*p_ptr), GFP_ATOMIC);
-	if (!p_ptr) {
-		pr_warn("Port creation failed, no memory\n");
-		return NULL;
-	}
 	ref = tipc_ref_acquire(p_ptr, &p_ptr->lock);
 	if (!ref) {
-		pr_warn("Port creation failed, ref. table exhausted\n");
-		kfree(p_ptr);
-		return NULL;
+		pr_warn("Port registration failed, ref. table exhausted\n");
+		return 0;
 	}
 
-	p_ptr->sk = sk;
 	p_ptr->max_pkt = MAX_PKT_DEFAULT;
 	p_ptr->ref = ref;
 	INIT_LIST_HEAD(&p_ptr->wait_list);
 	INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list);
-	p_ptr->dispatcher = dispatcher;
-	p_ptr->wakeup = wakeup;
 	k_init_timer(&p_ptr->timer, (Handler)port_timeout, ref);
 	INIT_LIST_HEAD(&p_ptr->publications);
 	INIT_LIST_HEAD(&p_ptr->port_list);
@@ -248,21 +229,18 @@ struct tipc_port *tipc_createport(struct sock *sk,
 	msg_set_origport(msg, ref);
 	list_add_tail(&p_ptr->port_list, &ports);
 	spin_unlock_bh(&tipc_port_list_lock);
-	return p_ptr;
+	return ref;
 }
 
-int tipc_deleteport(u32 ref)
+void tipc_port_destroy(struct tipc_port *p_ptr)
 {
-	struct tipc_port *p_ptr;
 	struct sk_buff *buf = NULL;
 
-	tipc_withdraw(ref, 0, NULL);
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
-		return -EINVAL;
+	tipc_withdraw(p_ptr, 0, NULL);
 
-	tipc_ref_discard(ref);
-	tipc_port_unlock(p_ptr);
+	spin_lock_bh(p_ptr->lock);
+	tipc_ref_discard(p_ptr->ref);
+	spin_unlock_bh(p_ptr->lock);
 
 	k_cancel_timer(&p_ptr->timer);
 	if (p_ptr->connected) {
@@ -275,67 +253,7 @@ int tipc_deleteport(u32 ref)
 	list_del(&p_ptr->wait_list);
 	spin_unlock_bh(&tipc_port_list_lock);
 	k_term_timer(&p_ptr->timer);
-	kfree(p_ptr);
 	tipc_net_route_msg(buf);
-	return 0;
-}
-
-static int port_unreliable(struct tipc_port *p_ptr)
-{
-	return msg_src_droppable(&p_ptr->phdr);
-}
-
-int tipc_portunreliable(u32 ref, unsigned int *isunreliable)
-{
-	struct tipc_port *p_ptr;
-
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
-		return -EINVAL;
-	*isunreliable = port_unreliable(p_ptr);
-	tipc_port_unlock(p_ptr);
-	return 0;
-}
-
-int tipc_set_portunreliable(u32 ref, unsigned int isunreliable)
-{
-	struct tipc_port *p_ptr;
-
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
-		return -EINVAL;
-	msg_set_src_droppable(&p_ptr->phdr, (isunreliable != 0));
-	tipc_port_unlock(p_ptr);
-	return 0;
-}
-
-static int port_unreturnable(struct tipc_port *p_ptr)
-{
-	return msg_dest_droppable(&p_ptr->phdr);
-}
-
-int tipc_portunreturnable(u32 ref, unsigned int *isunrejectable)
-{
-	struct tipc_port *p_ptr;
-
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
-		return -EINVAL;
-	*isunrejectable = port_unreturnable(p_ptr);
-	tipc_port_unlock(p_ptr);
-	return 0;
-}
-
-int tipc_set_portunreturnable(u32 ref, unsigned int isunrejectable)
-{
-	struct tipc_port *p_ptr;
-
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
-		return -EINVAL;
-	msg_set_dest_droppable(&p_ptr->phdr, (isunrejectable != 0));
-	tipc_port_unlock(p_ptr);
-	return 0;
 }
 
 /*
@@ -353,8 +271,8 @@ static struct sk_buff *port_build_proto_msg(struct tipc_port *p_ptr,
 	if (buf) {
 		msg = buf_msg(buf);
 		tipc_msg_init(msg, CONN_MANAGER, type, INT_H_SIZE,
-			      port_peernode(p_ptr));
-		msg_set_destport(msg, port_peerport(p_ptr));
+			      tipc_port_peernode(p_ptr));
+		msg_set_destport(msg, tipc_port_peerport(p_ptr));
 		msg_set_origport(msg, p_ptr->ref);
 		msg_set_msgcnt(msg, ack);
 	}
@@ -425,17 +343,17 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err)
 	/* send returned message & dispose of rejected message */
 	src_node = msg_prevnode(msg);
 	if (in_own_node(src_node))
-		tipc_port_recv_msg(rbuf);
+		tipc_sk_rcv(rbuf);
 	else
-		tipc_link_send(rbuf, src_node, msg_link_selector(rmsg));
+		tipc_link_xmit(rbuf, src_node, msg_link_selector(rmsg));
 exit:
 	kfree_skb(buf);
 	return data_sz;
 }
 
-int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr,
-			      struct iovec const *msg_sect, unsigned int len,
-			      int err)
+int tipc_port_iovec_reject(struct tipc_port *p_ptr, struct tipc_msg *hdr,
+			   struct iovec const *msg_sect, unsigned int len,
+			   int err)
 {
 	struct sk_buff *buf;
 	int res;
@@ -522,7 +440,7 @@ static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *p_ptr, u32 er
 	return buf;
 }
 
-void tipc_port_recv_proto_msg(struct sk_buff *buf)
+void tipc_port_proto_rcv(struct sk_buff *buf)
 {
 	struct tipc_msg *msg = buf_msg(buf);
 	struct tipc_port *p_ptr;
@@ -550,13 +468,12 @@ void tipc_port_recv_proto_msg(struct sk_buff *buf)
 	/* Process protocol message sent by peer */
 	switch (msg_type(msg)) {
 	case CONN_ACK:
-		wakeable = tipc_port_congested(p_ptr) && p_ptr->congested &&
-			p_ptr->wakeup;
+		wakeable = tipc_port_congested(p_ptr) && p_ptr->congested;
 		p_ptr->acked += msg_msgcnt(msg);
 		if (!tipc_port_congested(p_ptr)) {
 			p_ptr->congested = 0;
 			if (wakeable)
-				p_ptr->wakeup(p_ptr);
+				tipc_port_wakeup(p_ptr);
 		}
 		break;
 	case CONN_PROBE:
@@ -587,8 +504,8 @@ static int port_print(struct tipc_port *p_ptr, char *buf, int len, int full_id)
 		ret = tipc_snprintf(buf, len, "%-10u:", p_ptr->ref);
 
 	if (p_ptr->connected) {
-		u32 dport = port_peerport(p_ptr);
-		u32 destnode = port_peernode(p_ptr);
+		u32 dport = tipc_port_peerport(p_ptr);
+		u32 destnode = tipc_port_peernode(p_ptr);
 
 		ret += tipc_snprintf(buf + ret, len - ret,
 				     " connected to <%u.%u.%u:%u>",
@@ -676,75 +593,36 @@ void tipc_acknowledge(u32 ref, u32 ack)
 	tipc_net_route_msg(buf);
 }
 
-int tipc_portimportance(u32 ref, unsigned int *importance)
-{
-	struct tipc_port *p_ptr;
-
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
-		return -EINVAL;
-	*importance = (unsigned int)msg_importance(&p_ptr->phdr);
-	tipc_port_unlock(p_ptr);
-	return 0;
-}
-
-int tipc_set_portimportance(u32 ref, unsigned int imp)
-{
-	struct tipc_port *p_ptr;
-
-	if (imp > TIPC_CRITICAL_IMPORTANCE)
-		return -EINVAL;
-
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
-		return -EINVAL;
-	msg_set_importance(&p_ptr->phdr, (u32)imp);
-	tipc_port_unlock(p_ptr);
-	return 0;
-}
-
-
-int tipc_publish(u32 ref, unsigned int scope, struct tipc_name_seq const *seq)
+int tipc_publish(struct tipc_port *p_ptr, unsigned int scope,
+		 struct tipc_name_seq const *seq)
 {
-	struct tipc_port *p_ptr;
 	struct publication *publ;
 	u32 key;
-	int res = -EINVAL;
 
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
+	if (p_ptr->connected)
 		return -EINVAL;
+	key = p_ptr->ref + p_ptr->pub_count + 1;
+	if (key == p_ptr->ref)
+		return -EADDRINUSE;
 
-	if (p_ptr->connected)
-		goto exit;
-	key = ref + p_ptr->pub_count + 1;
-	if (key == ref) {
-		res = -EADDRINUSE;
-		goto exit;
-	}
 	publ = tipc_nametbl_publish(seq->type, seq->lower, seq->upper,
 				    scope, p_ptr->ref, key);
 	if (publ) {
 		list_add(&publ->pport_list, &p_ptr->publications);
 		p_ptr->pub_count++;
 		p_ptr->published = 1;
-		res = 0;
+		return 0;
 	}
-exit:
-	tipc_port_unlock(p_ptr);
-	return res;
+	return -EINVAL;
 }
 
-int tipc_withdraw(u32 ref, unsigned int scope, struct tipc_name_seq const *seq)
+int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope,
+		  struct tipc_name_seq const *seq)
 {
-	struct tipc_port *p_ptr;
 	struct publication *publ;
 	struct publication *tpubl;
 	int res = -EINVAL;
 
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
-		return -EINVAL;
 	if (!seq) {
 		list_for_each_entry_safe(publ, tpubl,
 					 &p_ptr->publications, pport_list) {
@@ -771,11 +649,10 @@ int tipc_withdraw(u32 ref, unsigned int scope, struct tipc_name_seq const *seq)
 	}
 	if (list_empty(&p_ptr->publications))
 		p_ptr->published = 0;
-	tipc_port_unlock(p_ptr);
 	return res;
 }
 
-int tipc_connect(u32 ref, struct tipc_portid const *peer)
+int tipc_port_connect(u32 ref, struct tipc_portid const *peer)
 {
 	struct tipc_port *p_ptr;
 	int res;
@@ -783,17 +660,17 @@ int tipc_connect(u32 ref, struct tipc_portid const *peer)
 	p_ptr = tipc_port_lock(ref);
 	if (!p_ptr)
 		return -EINVAL;
-	res = __tipc_connect(ref, p_ptr, peer);
+	res = __tipc_port_connect(ref, p_ptr, peer);
 	tipc_port_unlock(p_ptr);
 	return res;
 }
 
 /*
- * __tipc_connect - connect to a remote peer
+ * __tipc_port_connect - connect to a remote peer
  *
  * Port must be locked.
  */
-int __tipc_connect(u32 ref, struct tipc_port *p_ptr,
+int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr,
 			struct tipc_portid const *peer)
 {
 	struct tipc_msg *msg;
@@ -830,26 +707,23 @@ exit:
  *
  * Port must be locked.
  */
-int __tipc_disconnect(struct tipc_port *tp_ptr)
+int __tipc_port_disconnect(struct tipc_port *tp_ptr)
 {
-	int res;
-
 	if (tp_ptr->connected) {
 		tp_ptr->connected = 0;
 		/* let timer expire on it's own to avoid deadlock! */
 		tipc_nodesub_unsubscribe(&tp_ptr->subscription);
-		res = 0;
-	} else {
-		res = -ENOTCONN;
+		return 0;
 	}
-	return res;
+
+	return -ENOTCONN;
 }
 
 /*
- * tipc_disconnect(): Disconnect port form peer.
+ * tipc_port_disconnect(): Disconnect port form peer.
  *                    This is a node local operation.
  */
-int tipc_disconnect(u32 ref)
+int tipc_port_disconnect(u32 ref)
 {
 	struct tipc_port *p_ptr;
 	int res;
@@ -857,15 +731,15 @@ int tipc_disconnect(u32 ref)
 	p_ptr = tipc_port_lock(ref);
 	if (!p_ptr)
 		return -EINVAL;
-	res = __tipc_disconnect(p_ptr);
+	res = __tipc_port_disconnect(p_ptr);
 	tipc_port_unlock(p_ptr);
 	return res;
 }
 
 /*
- * tipc_shutdown(): Send a SHUTDOWN msg to peer and disconnect
+ * tipc_port_shutdown(): Send a SHUTDOWN msg to peer and disconnect
  */
-int tipc_shutdown(u32 ref)
+int tipc_port_shutdown(u32 ref)
 {
 	struct tipc_port *p_ptr;
 	struct sk_buff *buf = NULL;
@@ -877,78 +751,47 @@ int tipc_shutdown(u32 ref)
 	buf = port_build_peer_abort_msg(p_ptr, TIPC_CONN_SHUTDOWN);
 	tipc_port_unlock(p_ptr);
 	tipc_net_route_msg(buf);
-	return tipc_disconnect(ref);
-}
-
-/**
- * tipc_port_recv_msg - receive message from lower layer and deliver to port user
- */
-int tipc_port_recv_msg(struct sk_buff *buf)
-{
-	struct tipc_port *p_ptr;
-	struct tipc_msg *msg = buf_msg(buf);
-	u32 destport = msg_destport(msg);
-	u32 dsz = msg_data_sz(msg);
-	u32 err;
-
-	/* forward unresolved named message */
-	if (unlikely(!destport)) {
-		tipc_net_route_msg(buf);
-		return dsz;
-	}
-
-	/* validate destination & pass to port, otherwise reject message */
-	p_ptr = tipc_port_lock(destport);
-	if (likely(p_ptr)) {
-		err = p_ptr->dispatcher(p_ptr, buf);
-		tipc_port_unlock(p_ptr);
-		if (likely(!err))
-			return dsz;
-	} else {
-		err = TIPC_ERR_NO_PORT;
-	}
-
-	return tipc_reject_msg(buf, err);
+	return tipc_port_disconnect(ref);
 }
 
 /*
- *  tipc_port_recv_sections(): Concatenate and deliver sectioned
- *                        message for this node.
+ *  tipc_port_iovec_rcv: Concatenate and deliver sectioned
+ *                       message for this node.
  */
-static int tipc_port_recv_sections(struct tipc_port *sender,
-				   struct iovec const *msg_sect,
-				   unsigned int len)
+static int tipc_port_iovec_rcv(struct tipc_port *sender,
+			       struct iovec const *msg_sect,
+			       unsigned int len)
 {
 	struct sk_buff *buf;
 	int res;
 
 	res = tipc_msg_build(&sender->phdr, msg_sect, len, MAX_MSG_SIZE, &buf);
 	if (likely(buf))
-		tipc_port_recv_msg(buf);
+		tipc_sk_rcv(buf);
 	return res;
 }
 
 /**
  * tipc_send - send message sections on connection
  */
-int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len)
+int tipc_send(struct tipc_port *p_ptr,
+	      struct iovec const *msg_sect,
+	      unsigned int len)
 {
-	struct tipc_port *p_ptr;
 	u32 destnode;
 	int res;
 
-	p_ptr = tipc_port_deref(ref);
-	if (!p_ptr || !p_ptr->connected)
+	if (!p_ptr->connected)
 		return -EINVAL;
 
 	p_ptr->congested = 1;
 	if (!tipc_port_congested(p_ptr)) {
-		destnode = port_peernode(p_ptr);
+		destnode = tipc_port_peernode(p_ptr);
 		if (likely(!in_own_node(destnode)))
-			res = tipc_link_send_sections_fast(p_ptr, msg_sect,
-							   len, destnode);
+			res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len,
+							destnode);
 		else
-			res = tipc_port_recv_sections(p_ptr, msg_sect, len);
+			res = tipc_port_iovec_rcv(p_ptr, msg_sect, len);
 
 		if (likely(res != -ELINKCONG)) {
 			p_ptr->congested = 0;
@@ -957,7 +800,7 @@ int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len)
 			return res;
 		}
 	}
-	if (port_unreliable(p_ptr)) {
+	if (tipc_port_unreliable(p_ptr)) {
 		p_ptr->congested = 0;
 		return len;
 	}
@@ -967,17 +810,18 @@ int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len)
 /**
  * tipc_send2name - send message sections to port name
  */
-int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain,
-		   struct iovec const *msg_sect, unsigned int len)
+int tipc_send2name(struct tipc_port *p_ptr,
+		   struct tipc_name const *name,
+		   unsigned int domain,
+		   struct iovec const *msg_sect,
+		   unsigned int len)
 {
-	struct tipc_port *p_ptr;
 	struct tipc_msg *msg;
 	u32 destnode = domain;
 	u32 destport;
 	int res;
 
-	p_ptr = tipc_port_deref(ref);
-	if (!p_ptr || p_ptr->connected)
+	if (p_ptr->connected)
 		return -EINVAL;
 
 	msg = &p_ptr->phdr;
@@ -992,39 +836,39 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain,
 
 	if (likely(destport || destnode)) {
 		if (likely(in_own_node(destnode)))
-			res = tipc_port_recv_sections(p_ptr, msg_sect, len);
+			res = tipc_port_iovec_rcv(p_ptr, msg_sect, len);
 		else if (tipc_own_addr)
-			res = tipc_link_send_sections_fast(p_ptr, msg_sect,
-							   len, destnode);
+			res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len,
+							destnode);
 		else
-			res = tipc_port_reject_sections(p_ptr, msg, msg_sect,
-							len, TIPC_ERR_NO_NODE);
+			res = tipc_port_iovec_reject(p_ptr, msg, msg_sect,
+						     len, TIPC_ERR_NO_NODE);
 		if (likely(res != -ELINKCONG)) {
 			if (res > 0)
 				p_ptr->sent++;
 			return res;
 		}
-		if (port_unreliable(p_ptr)) {
+		if (tipc_port_unreliable(p_ptr))
 			return len;
-		}
+
 		return -ELINKCONG;
 	}
-	return tipc_port_reject_sections(p_ptr, msg, msg_sect, len,
-					 TIPC_ERR_NO_NAME);
+	return tipc_port_iovec_reject(p_ptr, msg, msg_sect, len,
+				      TIPC_ERR_NO_NAME);
 }
 
 /**
  * tipc_send2port - send message sections to port identity
  */
-int tipc_send2port(u32 ref, struct tipc_portid const *dest,
-		   struct iovec const *msg_sect, unsigned int len)
+int tipc_send2port(struct tipc_port *p_ptr,
+		   struct tipc_portid const *dest,
+		   struct iovec const *msg_sect,
+		   unsigned int len)
 {
-	struct tipc_port *p_ptr;
 	struct tipc_msg *msg;
 	int res;
 
-	p_ptr = tipc_port_deref(ref);
-	if (!p_ptr || p_ptr->connected)
+	if (p_ptr->connected)
 		return -EINVAL;
 
 	msg = &p_ptr->phdr;
@@ -1035,20 +879,20 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest,
 	msg_set_hdr_sz(msg, BASIC_H_SIZE);
 
 	if (in_own_node(dest->node))
-		res =  tipc_port_recv_sections(p_ptr, msg_sect, len);
+		res =  tipc_port_iovec_rcv(p_ptr, msg_sect, len);
 	else if (tipc_own_addr)
-		res = tipc_link_send_sections_fast(p_ptr, msg_sect, len,
-						   dest->node);
+		res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len,
+						dest->node);
 	else
-		res = tipc_port_reject_sections(p_ptr, msg, msg_sect, len,
+		res = tipc_port_iovec_reject(p_ptr, msg, msg_sect, len,
 						TIPC_ERR_NO_NODE);
 	if (likely(res != -ELINKCONG)) {
 		if (res > 0)
 			p_ptr->sent++;
 		return res;
 	}
-	if (port_unreliable(p_ptr)) {
+	if (tipc_port_unreliable(p_ptr))
 		return len;
-	}
+
 	return -ELINKCONG;
 }
diff --git a/net/tipc/port.h b/net/tipc/port.h
index 91225359734..cf4ca5b1d9a 100644
--- a/net/tipc/port.h
+++ b/net/tipc/port.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/port.h: Include file for TIPC port code
  *
- * Copyright (c) 1994-2007, Ericsson AB
+ * Copyright (c) 1994-2007, 2014, Ericsson AB
  * Copyright (c) 2004-2007, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -42,13 +42,13 @@
 #include "msg.h"
 #include "node_subscr.h"
 
-#define TIPC_FLOW_CONTROL_WIN 512
-#define CONN_OVERLOAD_LIMIT	((TIPC_FLOW_CONTROL_WIN * 2 + 1) * \
-				SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE))
+#define TIPC_CONNACK_INTV         256
+#define TIPC_FLOWCTRL_WIN        (TIPC_CONNACK_INTV * 2)
+#define TIPC_CONN_OVERLOAD_LIMIT ((TIPC_FLOWCTRL_WIN * 2 + 1) * \
+				  SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE))
 
 /**
  * struct tipc_port - TIPC port structure
- * @sk: pointer to socket handle
  * @lock: pointer to spinlock for controlling access to port
  * @connected: non-zero if port is currently connected to a peer port
  * @conn_type: TIPC type used when connection was established
@@ -60,8 +60,6 @@
  * @ref: unique reference to port in TIPC object registry
  * @phdr: preformatted message header used when sending messages
  * @port_list: adjacent ports in TIPC's global list of ports
- * @dispatcher: ptr to routine which handles received messages
- * @wakeup: ptr to routine to call when port is no longer congested
  * @wait_list: adjacent ports in list of ports waiting on link congestion
  * @waiting_pkts:
  * @sent: # of non-empty messages sent by port
@@ -74,7 +72,6 @@
  * @subscription: "node down" subscription used to terminate failed connections
  */
 struct tipc_port {
-	struct sock *sk;
 	spinlock_t *lock;
 	int connected;
 	u32 conn_type;
@@ -86,8 +83,6 @@ struct tipc_port {
 	u32 ref;
 	struct tipc_msg phdr;
 	struct list_head port_list;
-	u32 (*dispatcher)(struct tipc_port *, struct sk_buff *);
-	void (*wakeup)(struct tipc_port *);
 	struct list_head wait_list;
 	u32 waiting_pkts;
 	u32 sent;
@@ -106,68 +101,70 @@ struct tipc_port_list;
 /*
  * TIPC port manipulation routines
  */
-struct tipc_port *tipc_createport(struct sock *sk,
-				  u32 (*dispatcher)(struct tipc_port *,
-				  struct sk_buff *),
-				  void (*wakeup)(struct tipc_port *),
-				  const u32 importance);
+u32 tipc_port_init(struct tipc_port *p_ptr,
+		   const unsigned int importance);
 
 int tipc_reject_msg(struct sk_buff *buf, u32 err);
 
 void tipc_acknowledge(u32 port_ref, u32 ack);
 
-int tipc_deleteport(u32 portref);
+void tipc_port_destroy(struct tipc_port *p_ptr);
 
-int tipc_portimportance(u32 portref, unsigned int *importance);
-int tipc_set_portimportance(u32 portref, unsigned int importance);
-
-int tipc_portunreliable(u32 portref, unsigned int *isunreliable);
-int tipc_set_portunreliable(u32 portref, unsigned int isunreliable);
-
-int tipc_portunreturnable(u32 portref, unsigned int *isunreturnable);
-int tipc_set_portunreturnable(u32 portref, unsigned int isunreturnable);
-
-int tipc_publish(u32 portref, unsigned int scope,
+int tipc_publish(struct tipc_port *p_ptr, unsigned int scope,
 		 struct tipc_name_seq const *name_seq);
-int tipc_withdraw(u32 portref, unsigned int scope,
+
+int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope,
 		  struct tipc_name_seq const *name_seq);
 
-int tipc_connect(u32 portref, struct tipc_portid const *port);
+int tipc_port_connect(u32 portref, struct tipc_portid const *port);
 
-int tipc_disconnect(u32 portref);
+int tipc_port_disconnect(u32 portref);
 
-int tipc_shutdown(u32 ref);
+int tipc_port_shutdown(u32 ref);
 
+void tipc_port_wakeup(struct tipc_port *port);
 
 /*
  * The following routines require that the port be locked on entry
  */
-int __tipc_disconnect(struct tipc_port *tp_ptr);
-int __tipc_connect(u32 ref, struct tipc_port *p_ptr,
+int __tipc_port_disconnect(struct tipc_port *tp_ptr);
+int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr,
 		   struct tipc_portid const *peer);
 int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg);
 
 /*
  * TIPC messaging routines
  */
-int tipc_port_recv_msg(struct sk_buff *buf);
-int tipc_send(u32 portref, struct iovec const *msg_sect, unsigned int len);
 
-int tipc_send2name(u32 portref, struct tipc_name const *name, u32 domain,
-		   struct iovec const *msg_sect, unsigned int len);
+int tipc_send(struct tipc_port *port,
+	      struct iovec const *msg_sect,
+	      unsigned int len);
 
-int tipc_send2port(u32 portref, struct tipc_portid const *dest,
-		   struct iovec const *msg_sect, unsigned int len);
+int tipc_send2name(struct tipc_port *port,
+		   struct tipc_name const *name,
+		   u32 domain,
+		   struct iovec const *msg_sect,
+		   unsigned int len);
 
-int tipc_multicast(u32 portref, struct tipc_name_seq const *seq,
-		   struct iovec const *msg, unsigned int len);
+int tipc_send2port(struct tipc_port *port,
+		   struct tipc_portid const *dest,
+		   struct iovec const *msg_sect,
+		   unsigned int len);
+
+int tipc_port_mcast_xmit(struct tipc_port *port,
+			 struct tipc_name_seq const *seq,
+			 struct iovec const *msg,
+			 unsigned int len);
+
+int tipc_port_iovec_reject(struct tipc_port *p_ptr,
+			   struct tipc_msg *hdr,
+			   struct iovec const *msg_sect,
+			   unsigned int len,
+			   int err);
 
-int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr,
-			      struct iovec const *msg_sect, unsigned int len,
-			      int err);
 struct sk_buff *tipc_port_get_ports(void);
-void tipc_port_recv_proto_msg(struct sk_buff *buf);
-void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp);
+void tipc_port_proto_rcv(struct sk_buff *buf);
+void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp);
 void tipc_port_reinit(void);
 
 /**
@@ -188,14 +185,53 @@ static inline void tipc_port_unlock(struct tipc_port *p_ptr)
 	spin_unlock_bh(p_ptr->lock);
 }
 
-static inline struct tipc_port *tipc_port_deref(u32 ref)
+static inline int tipc_port_congested(struct tipc_port *p_ptr)
 {
-	return (struct tipc_port *)tipc_ref_deref(ref);
+	return ((p_ptr->sent - p_ptr->acked) >= TIPC_FLOWCTRL_WIN);
 }
 
-static inline int tipc_port_congested(struct tipc_port *p_ptr)
+
+static inline u32 tipc_port_peernode(struct tipc_port *p_ptr)
+{
+	return msg_destnode(&p_ptr->phdr);
+}
+
+static inline u32 tipc_port_peerport(struct tipc_port *p_ptr)
+{
+	return msg_destport(&p_ptr->phdr);
+}
+
+static inline  bool tipc_port_unreliable(struct tipc_port *port)
+{
+	return msg_src_droppable(&port->phdr) != 0;
+}
+
+static inline void tipc_port_set_unreliable(struct tipc_port *port,
+					    bool unreliable)
+{
+	msg_set_src_droppable(&port->phdr, unreliable ? 1 : 0);
+}
+
+static inline bool tipc_port_unreturnable(struct tipc_port *port)
+{
+	return msg_dest_droppable(&port->phdr) != 0;
+}
+
+static inline void tipc_port_set_unreturnable(struct tipc_port *port,
+					     bool unreturnable)
+{
+	msg_set_dest_droppable(&port->phdr, unreturnable ? 1 : 0);
+}
+
+
+static inline int tipc_port_importance(struct tipc_port *port)
+{
+	return msg_importance(&port->phdr);
+}
+
+static inline void tipc_port_set_importance(struct tipc_port *port, int imp)
 {
-	return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2);
+	msg_set_importance(&port->phdr, (u32)imp);
 }
 
 #endif
diff --git a/net/tipc/ref.c b/net/tipc/ref.c
index 2a2a938dc22..3d4ecd754ee 100644
--- a/net/tipc/ref.c
+++ b/net/tipc/ref.c
@@ -89,7 +89,7 @@ struct ref_table {
 
 static struct ref_table tipc_ref_table;
 
-static DEFINE_RWLOCK(ref_table_lock);
+static DEFINE_SPINLOCK(ref_table_lock);
 
 /**
  * tipc_ref_table_init - create reference table for objects
@@ -126,9 +126,6 @@ int tipc_ref_table_init(u32 requested_size, u32 start)
  */
 void tipc_ref_table_stop(void)
 {
-	if (!tipc_ref_table.entries)
-		return;
-
 	vfree(tipc_ref_table.entries);
 	tipc_ref_table.entries = NULL;
 }
@@ -162,7 +159,7 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock)
 	}
 
 	/* take a free entry, if available; otherwise initialize a new entry */
-	write_lock_bh(&ref_table_lock);
+	spin_lock_bh(&ref_table_lock);
 	if (tipc_ref_table.first_free) {
 		index = tipc_ref_table.first_free;
 		entry = &(tipc_ref_table.entries[index]);
@@ -178,7 +175,7 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock)
 	} else {
 		ref = 0;
 	}
-	write_unlock_bh(&ref_table_lock);
+	spin_unlock_bh(&ref_table_lock);
 
 	/*
 	 * Grab the lock so no one else can modify this entry
@@ -219,7 +216,7 @@ void tipc_ref_discard(u32 ref)
 	index = ref & index_mask;
 	entry = &(tipc_ref_table.entries[index]);
 
-	write_lock_bh(&ref_table_lock);
+	spin_lock_bh(&ref_table_lock);
 
 	if (!entry->object) {
 		pr_err("Attempt to discard ref. to non-existent obj\n");
@@ -245,7 +242,7 @@ void tipc_ref_discard(u32 ref)
 	tipc_ref_table.last_free = index;
 
 exit:
-	write_unlock_bh(&ref_table_lock);
+	spin_unlock_bh(&ref_table_lock);
 }
 
 /**
@@ -267,20 +264,3 @@ void *tipc_ref_lock(u32 ref)
 	}
 	return NULL;
 }
-
-
-/**
- * tipc_ref_deref - return pointer referenced object (without locking it)
- */
-void *tipc_ref_deref(u32 ref)
-{
-	if (likely(tipc_ref_table.entries)) {
-		struct reference *entry;
-
-		entry = &tipc_ref_table.entries[ref &
-						tipc_ref_table.index_mask];
-		if (likely(entry->ref == ref))
-			return entry->object;
-	}
-	return NULL;
-}
diff --git a/net/tipc/ref.h b/net/tipc/ref.h
index 5bc8e7ab84d..d01aa1df63b 100644
--- a/net/tipc/ref.h
+++ b/net/tipc/ref.h
@@ -44,6 +44,5 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock);
 void tipc_ref_discard(u32 ref);
 
 void *tipc_ref_lock(u32 ref);
-void *tipc_ref_deref(u32 ref);
 
 #endif
diff --git a/net/tipc/server.c b/net/tipc/server.c
index fd3fa57a410..a538a02f869 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -55,7 +55,7 @@
  * @usr_data: user-specified field
  * @rx_action: what to do when connection socket is active
  * @outqueue: pointer to first outbound message in queue
- * @outqueue_lock: controll access to the outqueue
+ * @outqueue_lock: control access to the outqueue
  * @outqueue: list of connection objects for its server
  * @swork: send work item
  */
@@ -87,7 +87,6 @@ static void tipc_clean_outqueues(struct tipc_conn *con);
 static void tipc_conn_kref_release(struct kref *kref)
 {
 	struct tipc_conn *con = container_of(kref, struct tipc_conn, kref);
-	struct tipc_server *s = con->server;
 
 	if (con->sock) {
 		tipc_sock_release_local(con->sock);
@@ -95,10 +94,6 @@ static void tipc_conn_kref_release(struct kref *kref)
 	}
 
 	tipc_clean_outqueues(con);
-
-	if (con->conid)
-		s->tipc_conn_shutdown(con->conid, con->usr_data);
-
 	kfree(con);
 }
 
@@ -124,7 +119,7 @@ static struct tipc_conn *tipc_conn_lookup(struct tipc_server *s, int conid)
 	return con;
 }
 
-static void sock_data_ready(struct sock *sk, int unused)
+static void sock_data_ready(struct sock *sk)
 {
 	struct tipc_conn *con;
 
@@ -181,6 +176,9 @@ static void tipc_close_conn(struct tipc_conn *con)
 	struct tipc_server *s = con->server;
 
 	if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {
+		if (con->conid)
+			s->tipc_conn_shutdown(con->conid, con->usr_data);
+
 		spin_lock_bh(&s->idr_lock);
 		idr_remove(&s->conn_idr, con->conid);
 		s->idr_in_use--;
@@ -299,7 +297,7 @@ static int tipc_accept_from_sock(struct tipc_conn *con)
 	newcon->usr_data = s->tipc_conn_new(newcon->conid);
 
 	/* Wake up receive process in case of 'SYN+' message */
-	newsock->sk->sk_data_ready(newsock->sk, 0);
+	newsock->sk->sk_data_ready(newsock->sk);
 	return ret;
 }
 
@@ -429,10 +427,12 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid,
 	list_add_tail(&e->list, &con->outqueue);
 	spin_unlock_bh(&con->outqueue_lock);
 
-	if (test_bit(CF_CONNECTED, &con->flags))
+	if (test_bit(CF_CONNECTED, &con->flags)) {
 		if (!queue_work(s->send_wq, &con->swork))
 			conn_put(con);
-
+	} else {
+		conn_put(con);
+	}
 	return 0;
 }
 
@@ -573,7 +573,6 @@ int tipc_server_start(struct tipc_server *s)
 		kmem_cache_destroy(s->rcvbuf_cache);
 		return ret;
 	}
-	s->enabled = 1;
 	return ret;
 }
 
@@ -583,10 +582,6 @@ void tipc_server_stop(struct tipc_server *s)
 	int total = 0;
 	int id;
 
-	if (!s->enabled)
-		return;
-
-	s->enabled = 0;
 	spin_lock_bh(&s->idr_lock);
 	for (id = 0; total < s->idr_in_use; id++) {
 		con = idr_find(&s->conn_idr, id);
diff --git a/net/tipc/server.h b/net/tipc/server.h
index 98b23f20bc0..be817b0b547 100644
--- a/net/tipc/server.h
+++ b/net/tipc/server.h
@@ -56,7 +56,6 @@
  * @name: server name
  * @imp: message importance
  * @type: socket type
- * @enabled: identify whether server is launched or not
  */
 struct tipc_server {
 	struct idr conn_idr;
@@ -74,7 +73,6 @@ struct tipc_server {
 	const char name[TIPC_SERVER_NAME_LEN];
 	int imp;
 	int type;
-	int enabled;
 };
 
 int tipc_conn_sendmsg(struct tipc_server *s, int conid,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3b61851bb92..ef0475568f9 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/socket.c: TIPC socket API
  *
- * Copyright (c) 2001-2007, 2012 Ericsson AB
+ * Copyright (c) 2001-2007, 2012-2014, Ericsson AB
  * Copyright (c) 2004-2008, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -36,35 +36,20 @@
 
 #include "core.h"
 #include "port.h"
+#include "node.h"
 
 #include <linux/export.h>
-#include <net/sock.h>
 
 #define SS_LISTENING	-1	/* socket is listening */
 #define SS_READY	-2	/* socket is connectionless */
 
 #define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */
 
-struct tipc_sock {
-	struct sock sk;
-	struct tipc_port *p;
-	struct tipc_portid peer_name;
-	unsigned int conn_timeout;
-};
-
-#define tipc_sk(sk) ((struct tipc_sock *)(sk))
-#define tipc_sk_port(sk) (tipc_sk(sk)->p)
-
-#define tipc_rx_ready(sock) (!skb_queue_empty(&sock->sk->sk_receive_queue) || \
-			(sock->state == SS_DISCONNECTING))
-
-static int backlog_rcv(struct sock *sk, struct sk_buff *skb);
-static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf);
-static void wakeupdispatch(struct tipc_port *tport);
-static void tipc_data_ready(struct sock *sk, int len);
+static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+static void tipc_data_ready(struct sock *sk);
 static void tipc_write_space(struct sock *sk);
-static int release(struct socket *sock);
-static int accept(struct socket *sock, struct socket *new_sock, int flags);
+static int tipc_release(struct socket *sock);
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
 
 static const struct proto_ops packet_ops;
 static const struct proto_ops stream_ops;
@@ -73,8 +58,6 @@ static const struct proto_ops msg_ops;
 static struct proto tipc_proto;
 static struct proto tipc_proto_kern;
 
-static int sockets_enabled;
-
 /*
  * Revised TIPC socket locking policy:
  *
@@ -120,6 +103,8 @@ static int sockets_enabled;
  *   - port reference
  */
 
+#include "socket.h"
+
 /**
  * advance_rx_queue - discard first buffer in socket receive queue
  *
@@ -155,13 +140,15 @@ static void reject_rx_queue(struct sock *sk)
  *
  * Returns 0 on success, errno otherwise
  */
-static int tipc_sk_create(struct net *net, struct socket *sock, int protocol,
-			  int kern)
+static int tipc_sk_create(struct net *net, struct socket *sock,
+			  int protocol, int kern)
 {
 	const struct proto_ops *ops;
 	socket_state state;
 	struct sock *sk;
-	struct tipc_port *tp_ptr;
+	struct tipc_sock *tsk;
+	struct tipc_port *port;
+	u32 ref;
 
 	/* Validate arguments */
 	if (unlikely(protocol != 0))
@@ -194,10 +181,12 @@ static int tipc_sk_create(struct net *net, struct socket *sock, int protocol,
 	if (sk == NULL)
 		return -ENOMEM;
 
-	/* Allocate TIPC port for socket to use */
-	tp_ptr = tipc_createport(sk, &dispatch, &wakeupdispatch,
-				 TIPC_LOW_IMPORTANCE);
-	if (unlikely(!tp_ptr)) {
+	tsk = tipc_sk(sk);
+	port = &tsk->port;
+
+	ref = tipc_port_init(port, TIPC_LOW_IMPORTANCE);
+	if (!ref) {
+		pr_warn("Socket registration failed, ref. table exhausted\n");
 		sk_free(sk);
 		return -ENOMEM;
 	}
@@ -207,21 +196,19 @@ static int tipc_sk_create(struct net *net, struct socket *sock, int protocol,
 	sock->state = state;
 
 	sock_init_data(sock, sk);
-	sk->sk_backlog_rcv = backlog_rcv;
+	sk->sk_backlog_rcv = tipc_backlog_rcv;
 	sk->sk_rcvbuf = sysctl_tipc_rmem[1];
 	sk->sk_data_ready = tipc_data_ready;
 	sk->sk_write_space = tipc_write_space;
-	tipc_sk(sk)->p = tp_ptr;
-	tipc_sk(sk)->conn_timeout = CONN_TIMEOUT_DEFAULT;
-
-	spin_unlock_bh(tp_ptr->lock);
+	tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
+	atomic_set(&tsk->dupl_rcvcnt, 0);
+	tipc_port_unlock(port);
 
 	if (sock->state == SS_READY) {
-		tipc_set_portunreturnable(tp_ptr->ref, 1);
+		tipc_port_set_unreturnable(port, true);
 		if (sock->type == SOCK_DGRAM)
-			tipc_set_portunreliable(tp_ptr->ref, 1);
+			tipc_port_set_unreliable(port, true);
 	}
-
 	return 0;
 }
 
@@ -239,7 +226,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock, int protocol,
 int tipc_sock_create_local(int type, struct socket **res)
 {
 	int rc;
-	struct sock *sk;
 
 	rc = sock_create_lite(AF_TIPC, type, 0, res);
 	if (rc < 0) {
@@ -248,8 +234,6 @@ int tipc_sock_create_local(int type, struct socket **res)
 	}
 	tipc_sk_create(&init_net, *res, 0, 1);
 
-	sk = (*res)->sk;
-
 	return 0;
 }
 
@@ -262,7 +246,7 @@ int tipc_sock_create_local(int type, struct socket **res)
  */
 void tipc_sock_release_local(struct socket *sock)
 {
-	release(sock);
+	tipc_release(sock);
 	sock->ops = NULL;
 	sock_release(sock);
 }
@@ -288,7 +272,7 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock,
 	if (ret < 0)
 		return ret;
 
-	ret = accept(sock, *newsock, flags);
+	ret = tipc_accept(sock, *newsock, flags);
 	if (ret < 0) {
 		sock_release(*newsock);
 		return ret;
@@ -298,7 +282,7 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock,
 }
 
 /**
- * release - destroy a TIPC socket
+ * tipc_release - destroy a TIPC socket
  * @sock: socket to destroy
  *
  * This routine cleans up any messages that are still queued on the socket.
@@ -313,12 +297,12 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock,
  *
  * Returns 0 on success, errno otherwise
  */
-static int release(struct socket *sock)
+static int tipc_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_port *tport;
+	struct tipc_sock *tsk;
+	struct tipc_port *port;
 	struct sk_buff *buf;
-	int res;
 
 	/*
 	 * Exit if socket isn't fully initialized (occurs when a failed accept()
@@ -327,7 +311,8 @@ static int release(struct socket *sock)
 	if (sk == NULL)
 		return 0;
 
-	tport = tipc_sk_port(sk);
+	tsk = tipc_sk(sk);
+	port = &tsk->port;
 	lock_sock(sk);
 
 	/*
@@ -344,17 +329,16 @@ static int release(struct socket *sock)
 			if ((sock->state == SS_CONNECTING) ||
 			    (sock->state == SS_CONNECTED)) {
 				sock->state = SS_DISCONNECTING;
-				tipc_disconnect(tport->ref);
+				tipc_port_disconnect(port->ref);
 			}
 			tipc_reject_msg(buf, TIPC_ERR_NO_PORT);
 		}
 	}
 
-	/*
-	 * Delete TIPC port; this ensures no more messages are queued
-	 * (also disconnects an active connection & sends a 'FIN-' to peer)
+	/* Destroy TIPC port; also disconnects an active connection and
+	 * sends a 'FIN-' to peer.
 	 */
-	res = tipc_deleteport(tport->ref);
+	tipc_port_destroy(port);
 
 	/* Discard any remaining (connection-based) messages in receive queue */
 	__skb_queue_purge(&sk->sk_receive_queue);
@@ -366,11 +350,11 @@ static int release(struct socket *sock)
 	sock_put(sk);
 	sock->sk = NULL;
 
-	return res;
+	return 0;
 }
 
 /**
- * bind - associate or disassocate TIPC name(s) with a socket
+ * tipc_bind - associate or disassocate TIPC name(s) with a socket
  * @sock: socket structure
  * @uaddr: socket address describing name(s) and desired operation
  * @uaddr_len: size of socket address data structure
@@ -384,36 +368,53 @@ static int release(struct socket *sock)
  * NOTE: This routine doesn't need to take the socket lock since it doesn't
  *       access any non-constant socket information.
  */
-static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len)
+static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
+		     int uaddr_len)
 {
+	struct sock *sk = sock->sk;
 	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
-	u32 portref = tipc_sk_port(sock->sk)->ref;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	int res = -EINVAL;
 
-	if (unlikely(!uaddr_len))
-		return tipc_withdraw(portref, 0, NULL);
+	lock_sock(sk);
+	if (unlikely(!uaddr_len)) {
+		res = tipc_withdraw(&tsk->port, 0, NULL);
+		goto exit;
+	}
 
-	if (uaddr_len < sizeof(struct sockaddr_tipc))
-		return -EINVAL;
-	if (addr->family != AF_TIPC)
-		return -EAFNOSUPPORT;
+	if (uaddr_len < sizeof(struct sockaddr_tipc)) {
+		res = -EINVAL;
+		goto exit;
+	}
+	if (addr->family != AF_TIPC) {
+		res = -EAFNOSUPPORT;
+		goto exit;
+	}
 
 	if (addr->addrtype == TIPC_ADDR_NAME)
 		addr->addr.nameseq.upper = addr->addr.nameseq.lower;
-	else if (addr->addrtype != TIPC_ADDR_NAMESEQ)
-		return -EAFNOSUPPORT;
+	else if (addr->addrtype != TIPC_ADDR_NAMESEQ) {
+		res = -EAFNOSUPPORT;
+		goto exit;
+	}
 
 	if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) &&
 	    (addr->addr.nameseq.type != TIPC_TOP_SRV) &&
-	    (addr->addr.nameseq.type != TIPC_CFG_SRV))
-		return -EACCES;
+	    (addr->addr.nameseq.type != TIPC_CFG_SRV)) {
+		res = -EACCES;
+		goto exit;
+	}
 
-	return (addr->scope > 0) ?
-		tipc_publish(portref, addr->scope, &addr->addr.nameseq) :
-		tipc_withdraw(portref, -addr->scope, &addr->addr.nameseq);
+	res = (addr->scope > 0) ?
+		tipc_publish(&tsk->port, addr->scope, &addr->addr.nameseq) :
+		tipc_withdraw(&tsk->port, -addr->scope, &addr->addr.nameseq);
+exit:
+	release_sock(sk);
+	return res;
 }
 
 /**
- * get_name - get port ID of socket or peer socket
+ * tipc_getname - get port ID of socket or peer socket
  * @sock: socket structure
  * @uaddr: area for returned socket address
  * @uaddr_len: area for returned length of socket address
@@ -425,21 +426,21 @@ static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len)
  *       accesses socket information that is unchanging (or which changes in
  *       a completely predictable manner).
  */
-static int get_name(struct socket *sock, struct sockaddr *uaddr,
-		    int *uaddr_len, int peer)
+static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
+			int *uaddr_len, int peer)
 {
 	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
-	struct tipc_sock *tsock = tipc_sk(sock->sk);
+	struct tipc_sock *tsk = tipc_sk(sock->sk);
 
 	memset(addr, 0, sizeof(*addr));
 	if (peer) {
 		if ((sock->state != SS_CONNECTED) &&
 			((peer != 2) || (sock->state != SS_DISCONNECTING)))
 			return -ENOTCONN;
-		addr->addr.id.ref = tsock->peer_name.ref;
-		addr->addr.id.node = tsock->peer_name.node;
+		addr->addr.id.ref = tipc_port_peerport(&tsk->port);
+		addr->addr.id.node = tipc_port_peernode(&tsk->port);
 	} else {
-		addr->addr.id.ref = tsock->p->ref;
+		addr->addr.id.ref = tsk->port.ref;
 		addr->addr.id.node = tipc_own_addr;
 	}
 
@@ -453,7 +454,7 @@ static int get_name(struct socket *sock, struct sockaddr *uaddr,
 }
 
 /**
- * poll - read and possibly block on pollmask
+ * tipc_poll - read and possibly block on pollmask
  * @file: file structure associated with the socket
  * @sock: socket for which to calculate the poll bits
  * @wait: ???
@@ -492,22 +493,23 @@ static int get_name(struct socket *sock, struct sockaddr *uaddr,
  * imply that the operation will succeed, merely that it should be performed
  * and will not block.
  */
-static unsigned int poll(struct file *file, struct socket *sock,
-			 poll_table *wait)
+static unsigned int tipc_poll(struct file *file, struct socket *sock,
+			      poll_table *wait)
 {
 	struct sock *sk = sock->sk;
+	struct tipc_sock *tsk = tipc_sk(sk);
 	u32 mask = 0;
 
 	sock_poll_wait(file, sk_sleep(sk), wait);
 
 	switch ((int)sock->state) {
 	case SS_UNCONNECTED:
-		if (!tipc_sk_port(sk)->congested)
+		if (!tsk->port.congested)
 			mask |= POLLOUT;
 		break;
 	case SS_READY:
 	case SS_CONNECTED:
-		if (!tipc_sk_port(sk)->congested)
+		if (!tsk->port.congested)
 			mask |= POLLOUT;
 		/* fall thru' */
 	case SS_CONNECTING:
@@ -554,8 +556,34 @@ static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m)
 	return 0;
 }
 
+static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p)
+{
+	struct sock *sk = sock->sk;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	DEFINE_WAIT(wait);
+	int done;
+
+	do {
+		int err = sock_error(sk);
+		if (err)
+			return err;
+		if (sock->state == SS_DISCONNECTING)
+			return -EPIPE;
+		if (!*timeo_p)
+			return -EAGAIN;
+		if (signal_pending(current))
+			return sock_intr_errno(*timeo_p);
+
+		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+		done = sk_wait_event(sk, timeo_p, !tsk->port.congested);
+		finish_wait(sk_sleep(sk), &wait);
+	} while (!done);
+	return 0;
+}
+
+
 /**
- * send_msg - send message in connectionless manner
+ * tipc_sendmsg - send message in connectionless manner
  * @iocb: if NULL, indicates that socket lock is already held
  * @sock: socket structure
  * @m: message to send
@@ -568,14 +596,15 @@ static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m)
  *
  * Returns the number of bytes sent on success, or errno otherwise
  */
-static int send_msg(struct kiocb *iocb, struct socket *sock,
-		    struct msghdr *m, size_t total_len)
+static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
+			struct msghdr *m, size_t total_len)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_port *tport = tipc_sk_port(sk);
-	struct sockaddr_tipc *dest = (struct sockaddr_tipc *)m->msg_name;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_port *port = &tsk->port;
+	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
 	int needs_conn;
-	long timeout_val;
+	long timeo;
 	int res = -EINVAL;
 
 	if (unlikely(!dest))
@@ -599,33 +628,32 @@ static int send_msg(struct kiocb *iocb, struct socket *sock,
 			res = -EISCONN;
 			goto exit;
 		}
-		if (tport->published) {
+		if (tsk->port.published) {
 			res = -EOPNOTSUPP;
 			goto exit;
 		}
 		if (dest->addrtype == TIPC_ADDR_NAME) {
-			tport->conn_type = dest->addr.name.name.type;
-			tport->conn_instance = dest->addr.name.name.instance;
+			tsk->port.conn_type = dest->addr.name.name.type;
+			tsk->port.conn_instance = dest->addr.name.name.instance;
 		}
 
 		/* Abort any pending connection attempts (very unlikely) */
 		reject_rx_queue(sk);
 	}
 
-	timeout_val = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
-
+	timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
 	do {
 		if (dest->addrtype == TIPC_ADDR_NAME) {
 			res = dest_name_check(dest, m);
 			if (res)
 				break;
-			res = tipc_send2name(tport->ref,
+			res = tipc_send2name(port,
 					     &dest->addr.name.name,
 					     dest->addr.name.domain,
 					     m->msg_iov,
 					     total_len);
 		} else if (dest->addrtype == TIPC_ADDR_ID) {
-			res = tipc_send2port(tport->ref,
+			res = tipc_send2port(port,
 					     &dest->addr.id,
 					     m->msg_iov,
 					     total_len);
@@ -637,24 +665,19 @@ static int send_msg(struct kiocb *iocb, struct socket *sock,
 			res = dest_name_check(dest, m);
 			if (res)
 				break;
-			res = tipc_multicast(tport->ref,
-					     &dest->addr.nameseq,
-					     m->msg_iov,
-					     total_len);
+			res = tipc_port_mcast_xmit(port,
+						   &dest->addr.nameseq,
+						   m->msg_iov,
+						   total_len);
 		}
 		if (likely(res != -ELINKCONG)) {
 			if (needs_conn && (res >= 0))
 				sock->state = SS_CONNECTING;
 			break;
 		}
-		if (timeout_val <= 0L) {
-			res = timeout_val ? timeout_val : -EWOULDBLOCK;
+		res = tipc_wait_for_sndmsg(sock, &timeo);
+		if (res)
 			break;
-		}
-		release_sock(sk);
-		timeout_val = wait_event_interruptible_timeout(*sk_sleep(sk),
-					       !tport->congested, timeout_val);
-		lock_sock(sk);
 	} while (1);
 
 exit:
@@ -663,8 +686,37 @@ exit:
 	return res;
 }
 
+static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p)
+{
+	struct sock *sk = sock->sk;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_port *port = &tsk->port;
+	DEFINE_WAIT(wait);
+	int done;
+
+	do {
+		int err = sock_error(sk);
+		if (err)
+			return err;
+		if (sock->state == SS_DISCONNECTING)
+			return -EPIPE;
+		else if (sock->state != SS_CONNECTED)
+			return -ENOTCONN;
+		if (!*timeo_p)
+			return -EAGAIN;
+		if (signal_pending(current))
+			return sock_intr_errno(*timeo_p);
+
+		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+		done = sk_wait_event(sk, timeo_p,
+				     (!port->congested || !port->connected));
+		finish_wait(sk_sleep(sk), &wait);
+	} while (!done);
+	return 0;
+}
+
 /**
- * send_packet - send a connection-oriented message
+ * tipc_send_packet - send a connection-oriented message
  * @iocb: if NULL, indicates that socket lock is already held
  * @sock: socket structure
  * @m: message to send
@@ -674,18 +726,18 @@ exit:
  *
  * Returns the number of bytes sent on success, or errno otherwise
  */
-static int send_packet(struct kiocb *iocb, struct socket *sock,
-		       struct msghdr *m, size_t total_len)
+static int tipc_send_packet(struct kiocb *iocb, struct socket *sock,
+			    struct msghdr *m, size_t total_len)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_port *tport = tipc_sk_port(sk);
-	struct sockaddr_tipc *dest = (struct sockaddr_tipc *)m->msg_name;
-	long timeout_val;
-	int res;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
+	int res = -EINVAL;
+	long timeo;
 
 	/* Handle implied connection establishment */
 	if (unlikely(dest))
-		return send_msg(iocb, sock, m, total_len);
+		return tipc_sendmsg(iocb, sock, m, total_len);
 
 	if (total_len > TIPC_MAX_USER_MSG_SIZE)
 		return -EMSGSIZE;
@@ -693,37 +745,31 @@ static int send_packet(struct kiocb *iocb, struct socket *sock,
 	if (iocb)
 		lock_sock(sk);
 
-	timeout_val = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
+	if (unlikely(sock->state != SS_CONNECTED)) {
+		if (sock->state == SS_DISCONNECTING)
+			res = -EPIPE;
+		else
+			res = -ENOTCONN;
+		goto exit;
+	}
 
+	timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
 	do {
-		if (unlikely(sock->state != SS_CONNECTED)) {
-			if (sock->state == SS_DISCONNECTING)
-				res = -EPIPE;
-			else
-				res = -ENOTCONN;
-			break;
-		}
-
-		res = tipc_send(tport->ref, m->msg_iov, total_len);
+		res = tipc_send(&tsk->port, m->msg_iov, total_len);
 		if (likely(res != -ELINKCONG))
 			break;
-		if (timeout_val <= 0L) {
-			res = timeout_val ? timeout_val : -EWOULDBLOCK;
+		res = tipc_wait_for_sndpkt(sock, &timeo);
+		if (res)
 			break;
-		}
-		release_sock(sk);
-		timeout_val = wait_event_interruptible_timeout(*sk_sleep(sk),
-			(!tport->congested || !tport->connected), timeout_val);
-		lock_sock(sk);
 	} while (1);
-
+exit:
 	if (iocb)
 		release_sock(sk);
 	return res;
 }
 
 /**
- * send_stream - send stream-oriented data
+ * tipc_send_stream - send stream-oriented data
  * @iocb: (unused)
  * @sock: socket structure
  * @m: data to send
@@ -734,11 +780,11 @@ static int send_packet(struct kiocb *iocb, struct socket *sock,
  * Returns the number of bytes sent on success (or partial success),
  * or errno if no data sent
  */
-static int send_stream(struct kiocb *iocb, struct socket *sock,
-		       struct msghdr *m, size_t total_len)
+static int tipc_send_stream(struct kiocb *iocb, struct socket *sock,
+			    struct msghdr *m, size_t total_len)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_port *tport = tipc_sk_port(sk);
+	struct tipc_sock *tsk = tipc_sk(sk);
 	struct msghdr my_msg;
 	struct iovec my_iov;
 	struct iovec *curr_iov;
@@ -754,16 +800,11 @@ static int send_stream(struct kiocb *iocb, struct socket *sock,
 
 	/* Handle special cases where there is no connection */
 	if (unlikely(sock->state != SS_CONNECTED)) {
-		if (sock->state == SS_UNCONNECTED) {
-			res = send_packet(NULL, sock, m, total_len);
-			goto exit;
-		} else if (sock->state == SS_DISCONNECTING) {
-			res = -EPIPE;
-			goto exit;
-		} else {
-			res = -ENOTCONN;
-			goto exit;
-		}
+		if (sock->state == SS_UNCONNECTED)
+			res = tipc_send_packet(NULL, sock, m, total_len);
+		else
+			res = sock->state == SS_DISCONNECTING ? -EPIPE : -ENOTCONN;
+		goto exit;
 	}
 
 	if (unlikely(m->msg_name)) {
@@ -791,21 +832,22 @@ static int send_stream(struct kiocb *iocb, struct socket *sock,
 	my_msg.msg_name = NULL;
 	bytes_sent = 0;
 
-	hdr_size = msg_hdr_sz(&tport->phdr);
+	hdr_size = msg_hdr_sz(&tsk->port.phdr);
 
 	while (curr_iovlen--) {
 		curr_start = curr_iov->iov_base;
 		curr_left = curr_iov->iov_len;
 
 		while (curr_left) {
-			bytes_to_send = tport->max_pkt - hdr_size;
+			bytes_to_send = tsk->port.max_pkt - hdr_size;
 			if (bytes_to_send > TIPC_MAX_USER_MSG_SIZE)
 				bytes_to_send = TIPC_MAX_USER_MSG_SIZE;
 			if (curr_left < bytes_to_send)
 				bytes_to_send = curr_left;
 			my_iov.iov_base = curr_start;
 			my_iov.iov_len = bytes_to_send;
-			res = send_packet(NULL, sock, &my_msg, bytes_to_send);
+			res = tipc_send_packet(NULL, sock, &my_msg,
+					       bytes_to_send);
 			if (res < 0) {
 				if (bytes_sent)
 					res = bytes_sent;
@@ -826,27 +868,25 @@ exit:
 
 /**
  * auto_connect - complete connection setup to a remote port
- * @sock: socket structure
+ * @tsk: tipc socket structure
  * @msg: peer's response message
  *
  * Returns 0 on success, errno otherwise
  */
-static int auto_connect(struct socket *sock, struct tipc_msg *msg)
+static int auto_connect(struct tipc_sock *tsk, struct tipc_msg *msg)
 {
-	struct tipc_sock *tsock = tipc_sk(sock->sk);
-	struct tipc_port *p_ptr;
+	struct tipc_port *port = &tsk->port;
+	struct socket *sock = tsk->sk.sk_socket;
+	struct tipc_portid peer;
 
-	tsock->peer_name.ref = msg_origport(msg);
-	tsock->peer_name.node = msg_orignode(msg);
-	p_ptr = tipc_port_deref(tsock->p->ref);
-	if (!p_ptr)
-		return -EINVAL;
+	peer.ref = msg_origport(msg);
+	peer.node = msg_orignode(msg);
 
-	__tipc_connect(tsock->p->ref, p_ptr, &tsock->peer_name);
+	__tipc_port_connect(port->ref, port, &peer);
 
 	if (msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE)
 		return -EINVAL;
-	msg_set_importance(&p_ptr->phdr, (u32)msg_importance(msg));
+	msg_set_importance(&port->phdr, (u32)msg_importance(msg));
 	sock->state = SS_CONNECTED;
 	return 0;
 }
@@ -860,7 +900,7 @@ static int auto_connect(struct socket *sock, struct tipc_msg *msg)
  */
 static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg)
 {
-	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)m->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_tipc *, addr, m->msg_name);
 
 	if (addr) {
 		addr->family = AF_TIPC;
@@ -945,8 +985,41 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
 	return 0;
 }
 
+static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
+{
+	struct sock *sk = sock->sk;
+	DEFINE_WAIT(wait);
+	long timeo = *timeop;
+	int err;
+
+	for (;;) {
+		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
+			if (sock->state == SS_DISCONNECTING) {
+				err = -ENOTCONN;
+				break;
+			}
+			release_sock(sk);
+			timeo = schedule_timeout(timeo);
+			lock_sock(sk);
+		}
+		err = 0;
+		if (!skb_queue_empty(&sk->sk_receive_queue))
+			break;
+		err = sock_intr_errno(timeo);
+		if (signal_pending(current))
+			break;
+		err = -EAGAIN;
+		if (!timeo)
+			break;
+	}
+	finish_wait(sk_sleep(sk), &wait);
+	*timeop = timeo;
+	return err;
+}
+
 /**
- * recv_msg - receive packet-oriented message
+ * tipc_recvmsg - receive packet-oriented message
  * @iocb: (unused)
  * @m: descriptor for message info
  * @buf_len: total size of user buffer area
@@ -957,14 +1030,15 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
  *
  * Returns size of returned message data, errno otherwise
  */
-static int recv_msg(struct kiocb *iocb, struct socket *sock,
-		    struct msghdr *m, size_t buf_len, int flags)
+static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock,
+			struct msghdr *m, size_t buf_len, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_port *tport = tipc_sk_port(sk);
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_port *port = &tsk->port;
 	struct sk_buff *buf;
 	struct tipc_msg *msg;
-	long timeout;
+	long timeo;
 	unsigned int sz;
 	u32 err;
 	int res;
@@ -980,25 +1054,13 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock,
 		goto exit;
 	}
 
-	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 restart:
 
 	/* Look for a message in receive queue; wait if necessary */
-	while (skb_queue_empty(&sk->sk_receive_queue)) {
-		if (sock->state == SS_DISCONNECTING) {
-			res = -ENOTCONN;
-			goto exit;
-		}
-		if (timeout <= 0L) {
-			res = timeout ? timeout : -EWOULDBLOCK;
-			goto exit;
-		}
-		release_sock(sk);
-		timeout = wait_event_interruptible_timeout(*sk_sleep(sk),
-							   tipc_rx_ready(sock),
-							   timeout);
-		lock_sock(sk);
-	}
+	res = tipc_wait_for_rcvmsg(sock, &timeo);
+	if (res)
+		goto exit;
 
 	/* Look at first message in receive queue */
 	buf = skb_peek(&sk->sk_receive_queue);
@@ -1016,7 +1078,7 @@ restart:
 	set_orig_addr(m, msg);
 
 	/* Capture ancillary data (optional) */
-	res = anc_data_recv(m, msg, tport);
+	res = anc_data_recv(m, msg, port);
 	if (res)
 		goto exit;
 
@@ -1042,8 +1104,8 @@ restart:
 	/* Consume received message (optional) */
 	if (likely(!(flags & MSG_PEEK))) {
 		if ((sock->state != SS_READY) &&
-		    (++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
-			tipc_acknowledge(tport->ref, tport->conn_unacked);
+		    (++port->conn_unacked >= TIPC_CONNACK_INTV))
+			tipc_acknowledge(port->ref, port->conn_unacked);
 		advance_rx_queue(sk);
 	}
 exit:
@@ -1052,7 +1114,7 @@ exit:
 }
 
 /**
- * recv_stream - receive stream-oriented data
+ * tipc_recv_stream - receive stream-oriented data
  * @iocb: (unused)
  * @m: descriptor for message info
  * @buf_len: total size of user buffer area
@@ -1063,14 +1125,15 @@ exit:
  *
  * Returns size of returned message data, errno otherwise
  */
-static int recv_stream(struct kiocb *iocb, struct socket *sock,
-		       struct msghdr *m, size_t buf_len, int flags)
+static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock,
+			    struct msghdr *m, size_t buf_len, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_port *tport = tipc_sk_port(sk);
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_port *port = &tsk->port;
 	struct sk_buff *buf;
 	struct tipc_msg *msg;
-	long timeout;
+	long timeo;
 	unsigned int sz;
 	int sz_to_copy, target, needed;
 	int sz_copied = 0;
@@ -1083,31 +1146,19 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock,
 
 	lock_sock(sk);
 
-	if (unlikely((sock->state == SS_UNCONNECTED))) {
+	if (unlikely(sock->state == SS_UNCONNECTED)) {
 		res = -ENOTCONN;
 		goto exit;
 	}
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
-	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
 restart:
 	/* Look for a message in receive queue; wait if necessary */
-	while (skb_queue_empty(&sk->sk_receive_queue)) {
-		if (sock->state == SS_DISCONNECTING) {
-			res = -ENOTCONN;
-			goto exit;
-		}
-		if (timeout <= 0L) {
-			res = timeout ? timeout : -EWOULDBLOCK;
-			goto exit;
-		}
-		release_sock(sk);
-		timeout = wait_event_interruptible_timeout(*sk_sleep(sk),
-							   tipc_rx_ready(sock),
-							   timeout);
-		lock_sock(sk);
-	}
+	res = tipc_wait_for_rcvmsg(sock, &timeo);
+	if (res)
+		goto exit;
 
 	/* Look at first message in receive queue */
 	buf = skb_peek(&sk->sk_receive_queue);
@@ -1124,7 +1175,7 @@ restart:
 	/* Optionally capture sender's address & ancillary data of first msg */
 	if (sz_copied == 0) {
 		set_orig_addr(m, msg);
-		res = anc_data_recv(m, msg, tport);
+		res = anc_data_recv(m, msg, port);
 		if (res)
 			goto exit;
 	}
@@ -1162,8 +1213,8 @@ restart:
 
 	/* Consume received message (optional) */
 	if (likely(!(flags & MSG_PEEK))) {
-		if (unlikely(++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
-			tipc_acknowledge(tport->ref, tport->conn_unacked);
+		if (unlikely(++port->conn_unacked >= TIPC_CONNACK_INTV))
+			tipc_acknowledge(port->ref, port->conn_unacked);
 		advance_rx_queue(sk);
 	}
 
@@ -1201,7 +1252,7 @@ static void tipc_write_space(struct sock *sk)
  * @sk: socket
  * @len: the length of messages
  */
-static void tipc_data_ready(struct sock *sk, int len)
+static void tipc_data_ready(struct sock *sk)
 {
 	struct socket_wq *wq;
 
@@ -1215,17 +1266,19 @@ static void tipc_data_ready(struct sock *sk, int len)
 
 /**
  * filter_connect - Handle all incoming messages for a connection-based socket
- * @tsock: TIPC socket
+ * @tsk: TIPC socket
  * @msg: message
  *
  * Returns TIPC error status code and socket error status code
  * once it encounters some errors
  */
-static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf)
+static u32 filter_connect(struct tipc_sock *tsk, struct sk_buff **buf)
 {
-	struct socket *sock = tsock->sk.sk_socket;
+	struct sock *sk = &tsk->sk;
+	struct tipc_port *port = &tsk->port;
+	struct socket *sock = sk->sk_socket;
 	struct tipc_msg *msg = buf_msg(*buf);
-	struct sock *sk = &tsock->sk;
+
 	u32 retval = TIPC_ERR_NO_PORT;
 	int res;
 
@@ -1235,10 +1288,10 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf)
 	switch ((int)sock->state) {
 	case SS_CONNECTED:
 		/* Accept only connection-based messages sent by peer */
-		if (msg_connected(msg) && tipc_port_peer_msg(tsock->p, msg)) {
+		if (msg_connected(msg) && tipc_port_peer_msg(port, msg)) {
 			if (unlikely(msg_errcode(msg))) {
 				sock->state = SS_DISCONNECTING;
-				__tipc_disconnect(tsock->p);
+				__tipc_port_disconnect(port);
 			}
 			retval = TIPC_OK;
 		}
@@ -1255,7 +1308,7 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf)
 		if (unlikely(!msg_connected(msg)))
 			break;
 
-		res = auto_connect(sock, msg);
+		res = auto_connect(tsk, msg);
 		if (res) {
 			sock->state = SS_DISCONNECTING;
 			sk->sk_err = -res;
@@ -1311,14 +1364,12 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf)
 static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf)
 {
 	struct tipc_msg *msg = buf_msg(buf);
-	unsigned int limit;
 
 	if (msg_connected(msg))
-		limit = sysctl_tipc_rmem[2];
-	else
-		limit = sk->sk_rcvbuf >> TIPC_CRITICAL_IMPORTANCE <<
-			msg_importance(msg);
-	return limit;
+		return sysctl_tipc_rmem[2];
+
+	return sk->sk_rcvbuf >> TIPC_CRITICAL_IMPORTANCE <<
+		msg_importance(msg);
 }
 
 /**
@@ -1336,6 +1387,7 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf)
 static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
 {
 	struct socket *sock = sk->sk_socket;
+	struct tipc_sock *tsk = tipc_sk(sk);
 	struct tipc_msg *msg = buf_msg(buf);
 	unsigned int limit = rcvbuf_limit(sk, buf);
 	u32 res = TIPC_OK;
@@ -1348,7 +1400,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
 		if (msg_connected(msg))
 			return TIPC_ERR_NO_PORT;
 	} else {
-		res = filter_connect(tipc_sk(sk), &buf);
+		res = filter_connect(tsk, &buf);
 		if (res != TIPC_OK || buf == NULL)
 			return res;
 	}
@@ -1362,12 +1414,12 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
 	__skb_queue_tail(&sk->sk_receive_queue, buf);
 	skb_set_owner_r(buf, sk);
 
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 	return TIPC_OK;
 }
 
 /**
- * backlog_rcv - handle incoming message from backlog queue
+ * tipc_backlog_rcv - handle incoming message from backlog queue
  * @sk: socket
  * @buf: message
  *
@@ -1375,65 +1427,100 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
  *
  * Returns 0
  */
-static int backlog_rcv(struct sock *sk, struct sk_buff *buf)
+static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *buf)
 {
 	u32 res;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	uint truesize = buf->truesize;
 
 	res = filter_rcv(sk, buf);
-	if (res)
+	if (unlikely(res))
 		tipc_reject_msg(buf, res);
+
+	if (atomic_read(&tsk->dupl_rcvcnt) < TIPC_CONN_OVERLOAD_LIMIT)
+		atomic_add(truesize, &tsk->dupl_rcvcnt);
+
 	return 0;
 }
 
 /**
- * dispatch - handle incoming message
- * @tport: TIPC port that received message
- * @buf: message
- *
- * Called with port lock already taken.
- *
- * Returns TIPC error status code (TIPC_OK if message is not to be rejected)
+ * tipc_sk_rcv - handle incoming message
+ * @buf: buffer containing arriving message
+ * Consumes buffer
+ * Returns 0 if success, or errno: -EHOSTUNREACH
  */
-static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf)
+int tipc_sk_rcv(struct sk_buff *buf)
 {
-	struct sock *sk = tport->sk;
-	u32 res;
+	struct tipc_sock *tsk;
+	struct tipc_port *port;
+	struct sock *sk;
+	u32 dport = msg_destport(buf_msg(buf));
+	int err = TIPC_OK;
+	uint limit;
 
-	/*
-	 * Process message if socket is unlocked; otherwise add to backlog queue
-	 *
-	 * This code is based on sk_receive_skb(), but must be distinct from it
-	 * since a TIPC-specific filter/reject mechanism is utilized
-	 */
+	/* Forward unresolved named message */
+	if (unlikely(!dport)) {
+		tipc_net_route_msg(buf);
+		return 0;
+	}
+
+	/* Validate destination */
+	port = tipc_port_lock(dport);
+	if (unlikely(!port)) {
+		err = TIPC_ERR_NO_PORT;
+		goto exit;
+	}
+
+	tsk = tipc_port_to_sock(port);
+	sk = &tsk->sk;
+
+	/* Queue message */
 	bh_lock_sock(sk);
+
 	if (!sock_owned_by_user(sk)) {
-		res = filter_rcv(sk, buf);
+		err = filter_rcv(sk, buf);
 	} else {
-		if (sk_add_backlog(sk, buf, rcvbuf_limit(sk, buf)))
-			res = TIPC_ERR_OVERLOAD;
-		else
-			res = TIPC_OK;
+		if (sk->sk_backlog.len == 0)
+			atomic_set(&tsk->dupl_rcvcnt, 0);
+		limit = rcvbuf_limit(sk, buf) + atomic_read(&tsk->dupl_rcvcnt);
+		if (sk_add_backlog(sk, buf, limit))
+			err = TIPC_ERR_OVERLOAD;
 	}
+
 	bh_unlock_sock(sk);
+	tipc_port_unlock(port);
 
-	return res;
+	if (likely(!err))
+		return 0;
+exit:
+	tipc_reject_msg(buf, err);
+	return -EHOSTUNREACH;
 }
 
-/**
- * wakeupdispatch - wake up port after congestion
- * @tport: port to wakeup
- *
- * Called with port lock already taken.
- */
-static void wakeupdispatch(struct tipc_port *tport)
+static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
 {
-	struct sock *sk = tport->sk;
+	struct sock *sk = sock->sk;
+	DEFINE_WAIT(wait);
+	int done;
 
-	sk->sk_write_space(sk);
+	do {
+		int err = sock_error(sk);
+		if (err)
+			return err;
+		if (!*timeo_p)
+			return -ETIMEDOUT;
+		if (signal_pending(current))
+			return sock_intr_errno(*timeo_p);
+
+		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+		done = sk_wait_event(sk, timeo_p, sock->state != SS_CONNECTING);
+		finish_wait(sk_sleep(sk), &wait);
+	} while (!done);
+	return 0;
 }
 
 /**
- * connect - establish a connection to another TIPC port
+ * tipc_connect - establish a connection to another TIPC port
  * @sock: socket structure
  * @dest: socket address for destination port
  * @destlen: size of socket address data structure
@@ -1441,13 +1528,14 @@ static void wakeupdispatch(struct tipc_port *tport)
  *
  * Returns 0 on success, errno otherwise
  */
-static int connect(struct socket *sock, struct sockaddr *dest, int destlen,
-		   int flags)
+static int tipc_connect(struct socket *sock, struct sockaddr *dest,
+			int destlen, int flags)
 {
 	struct sock *sk = sock->sk;
 	struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest;
 	struct msghdr m = {NULL,};
-	unsigned int timeout;
+	long timeout = (flags & O_NONBLOCK) ? 0 : tipc_sk(sk)->conn_timeout;
+	socket_state previous;
 	int res;
 
 	lock_sock(sk);
@@ -1469,8 +1557,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen,
 		goto exit;
 	}
 
-	timeout = (flags & O_NONBLOCK) ? 0 : tipc_sk(sk)->conn_timeout;
-
+	previous = sock->state;
 	switch (sock->state) {
 	case SS_UNCONNECTED:
 		/* Send a 'SYN-' to destination */
@@ -1483,7 +1570,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen,
 		if (!timeout)
 			m.msg_flags = MSG_DONTWAIT;
 
-		res = send_msg(NULL, sock, &m, 0);
+		res = tipc_sendmsg(NULL, sock, &m, 0);
 		if ((res < 0) && (res != -EWOULDBLOCK))
 			goto exit;
 
@@ -1492,56 +1579,35 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen,
 		 * case is EINPROGRESS, rather than EALREADY.
 		 */
 		res = -EINPROGRESS;
-		break;
 	case SS_CONNECTING:
-		res = -EALREADY;
+		if (previous == SS_CONNECTING)
+			res = -EALREADY;
+		if (!timeout)
+			goto exit;
+		timeout = msecs_to_jiffies(timeout);
+		/* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */
+		res = tipc_wait_for_connect(sock, &timeout);
 		break;
 	case SS_CONNECTED:
 		res = -EISCONN;
 		break;
 	default:
 		res = -EINVAL;
-		goto exit;
-	}
-
-	if (sock->state == SS_CONNECTING) {
-		if (!timeout)
-			goto exit;
-
-		/* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */
-		release_sock(sk);
-		res = wait_event_interruptible_timeout(*sk_sleep(sk),
-				sock->state != SS_CONNECTING,
-				timeout ? (long)msecs_to_jiffies(timeout)
-					: MAX_SCHEDULE_TIMEOUT);
-		lock_sock(sk);
-		if (res <= 0) {
-			if (res == 0)
-				res = -ETIMEDOUT;
-			else
-				; /* leave "res" unchanged */
-			goto exit;
-		}
+		break;
 	}
-
-	if (unlikely(sock->state == SS_DISCONNECTING))
-		res = sock_error(sk);
-	else
-		res = 0;
-
 exit:
 	release_sock(sk);
 	return res;
 }
 
 /**
- * listen - allow socket to listen for incoming connections
+ * tipc_listen - allow socket to listen for incoming connections
  * @sock: socket structure
  * @len: (unused)
  *
  * Returns 0 on success, errno otherwise
  */
-static int listen(struct socket *sock, int len)
+static int tipc_listen(struct socket *sock, int len)
 {
 	struct sock *sk = sock->sk;
 	int res;
@@ -1559,23 +1625,59 @@ static int listen(struct socket *sock, int len)
 	return res;
 }
 
+static int tipc_wait_for_accept(struct socket *sock, long timeo)
+{
+	struct sock *sk = sock->sk;
+	DEFINE_WAIT(wait);
+	int err;
+
+	/* True wake-one mechanism for incoming connections: only
+	 * one process gets woken up, not the 'whole herd'.
+	 * Since we do not 'race & poll' for established sockets
+	 * anymore, the common case will execute the loop only once.
+	*/
+	for (;;) {
+		prepare_to_wait_exclusive(sk_sleep(sk), &wait,
+					  TASK_INTERRUPTIBLE);
+		if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
+			release_sock(sk);
+			timeo = schedule_timeout(timeo);
+			lock_sock(sk);
+		}
+		err = 0;
+		if (!skb_queue_empty(&sk->sk_receive_queue))
+			break;
+		err = -EINVAL;
+		if (sock->state != SS_LISTENING)
+			break;
+		err = sock_intr_errno(timeo);
+		if (signal_pending(current))
+			break;
+		err = -EAGAIN;
+		if (!timeo)
+			break;
+	}
+	finish_wait(sk_sleep(sk), &wait);
+	return err;
+}
+
 /**
- * accept - wait for connection request
+ * tipc_accept - wait for connection request
  * @sock: listening socket
  * @newsock: new socket that is to be connected
  * @flags: file-related flags associated with socket
  *
  * Returns 0 on success, errno otherwise
  */
-static int accept(struct socket *sock, struct socket *new_sock, int flags)
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
 {
 	struct sock *new_sk, *sk = sock->sk;
 	struct sk_buff *buf;
-	struct tipc_sock *new_tsock;
-	struct tipc_port *new_tport;
+	struct tipc_port *new_port;
 	struct tipc_msg *msg;
+	struct tipc_portid peer;
 	u32 new_ref;
-
+	long timeo;
 	int res;
 
 	lock_sock(sk);
@@ -1584,19 +1686,10 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags)
 		res = -EINVAL;
 		goto exit;
 	}
-
-	while (skb_queue_empty(&sk->sk_receive_queue)) {
-		if (flags & O_NONBLOCK) {
-			res = -EWOULDBLOCK;
-			goto exit;
-		}
-		release_sock(sk);
-		res = wait_event_interruptible(*sk_sleep(sk),
-				(!skb_queue_empty(&sk->sk_receive_queue)));
-		lock_sock(sk);
-		if (res)
-			goto exit;
-	}
+	timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
+	res = tipc_wait_for_accept(sock, timeo);
+	if (res)
+		goto exit;
 
 	buf = skb_peek(&sk->sk_receive_queue);
 
@@ -1605,9 +1698,8 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags)
 		goto exit;
 
 	new_sk = new_sock->sk;
-	new_tsock = tipc_sk(new_sk);
-	new_tport = new_tsock->p;
-	new_ref = new_tport->ref;
+	new_port = &tipc_sk(new_sk)->port;
+	new_ref = new_port->ref;
 	msg = buf_msg(buf);
 
 	/* we lock on new_sk; but lockdep sees the lock on sk */
@@ -1620,15 +1712,15 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags)
 	reject_rx_queue(new_sk);
 
 	/* Connect new socket to it's peer */
-	new_tsock->peer_name.ref = msg_origport(msg);
-	new_tsock->peer_name.node = msg_orignode(msg);
-	tipc_connect(new_ref, &new_tsock->peer_name);
+	peer.ref = msg_origport(msg);
+	peer.node = msg_orignode(msg);
+	tipc_port_connect(new_ref, &peer);
 	new_sock->state = SS_CONNECTED;
 
-	tipc_set_portimportance(new_ref, msg_importance(msg));
+	tipc_port_set_importance(new_port, msg_importance(msg));
 	if (msg_named(msg)) {
-		new_tport->conn_type = msg_nametype(msg);
-		new_tport->conn_instance = msg_nameinst(msg);
+		new_port->conn_type = msg_nametype(msg);
+		new_port->conn_instance = msg_nameinst(msg);
 	}
 
 	/*
@@ -1639,21 +1731,20 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags)
 		struct msghdr m = {NULL,};
 
 		advance_rx_queue(sk);
-		send_packet(NULL, new_sock, &m, 0);
+		tipc_send_packet(NULL, new_sock, &m, 0);
 	} else {
 		__skb_dequeue(&sk->sk_receive_queue);
 		__skb_queue_head(&new_sk->sk_receive_queue, buf);
 		skb_set_owner_r(buf, new_sk);
 	}
 	release_sock(new_sk);
-
 exit:
 	release_sock(sk);
 	return res;
 }
 
 /**
- * shutdown - shutdown socket connection
+ * tipc_shutdown - shutdown socket connection
  * @sock: socket structure
  * @how: direction to close (must be SHUT_RDWR)
  *
@@ -1661,10 +1752,11 @@ exit:
  *
  * Returns 0 on success, errno otherwise
  */
-static int shutdown(struct socket *sock, int how)
+static int tipc_shutdown(struct socket *sock, int how)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_port *tport = tipc_sk_port(sk);
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_port *port = &tsk->port;
 	struct sk_buff *buf;
 	int res;
 
@@ -1685,10 +1777,10 @@ restart:
 				kfree_skb(buf);
 				goto restart;
 			}
-			tipc_disconnect(tport->ref);
+			tipc_port_disconnect(port->ref);
 			tipc_reject_msg(buf, TIPC_CONN_SHUTDOWN);
 		} else {
-			tipc_shutdown(tport->ref);
+			tipc_port_shutdown(port->ref);
 		}
 
 		sock->state = SS_DISCONNECTING;
@@ -1714,7 +1806,7 @@ restart:
 }
 
 /**
- * setsockopt - set socket option
+ * tipc_setsockopt - set socket option
  * @sock: socket structure
  * @lvl: option level
  * @opt: option identifier
@@ -1726,11 +1818,12 @@ restart:
  *
  * Returns 0 on success, errno otherwise
  */
-static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
-		      unsigned int ol)
+static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
+			   char __user *ov, unsigned int ol)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_port *tport = tipc_sk_port(sk);
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_port *port = &tsk->port;
 	u32 value;
 	int res;
 
@@ -1748,16 +1841,16 @@ static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
 
 	switch (opt) {
 	case TIPC_IMPORTANCE:
-		res = tipc_set_portimportance(tport->ref, value);
+		tipc_port_set_importance(port, value);
 		break;
 	case TIPC_SRC_DROPPABLE:
 		if (sock->type != SOCK_STREAM)
-			res = tipc_set_portunreliable(tport->ref, value);
+			tipc_port_set_unreliable(port, value);
 		else
 			res = -ENOPROTOOPT;
 		break;
 	case TIPC_DEST_DROPPABLE:
-		res = tipc_set_portunreturnable(tport->ref, value);
+		tipc_port_set_unreturnable(port, value);
 		break;
 	case TIPC_CONN_TIMEOUT:
 		tipc_sk(sk)->conn_timeout = value;
@@ -1773,7 +1866,7 @@ static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
 }
 
 /**
- * getsockopt - get socket option
+ * tipc_getsockopt - get socket option
  * @sock: socket structure
  * @lvl: option level
  * @opt: option identifier
@@ -1785,11 +1878,12 @@ static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
  *
  * Returns 0 on success, errno otherwise
  */
-static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
-		      int __user *ol)
+static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
+			   char __user *ov, int __user *ol)
 {
 	struct sock *sk = sock->sk;
-	struct tipc_port *tport = tipc_sk_port(sk);
+	struct tipc_sock *tsk = tipc_sk(sk);
+	struct tipc_port *port = &tsk->port;
 	int len;
 	u32 value;
 	int res;
@@ -1806,13 +1900,13 @@ static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
 
 	switch (opt) {
 	case TIPC_IMPORTANCE:
-		res = tipc_portimportance(tport->ref, &value);
+		value = tipc_port_importance(port);
 		break;
 	case TIPC_SRC_DROPPABLE:
-		res = tipc_portunreliable(tport->ref, &value);
+		value = tipc_port_unreliable(port);
 		break;
 	case TIPC_DEST_DROPPABLE:
-		res = tipc_portunreturnable(tport->ref, &value);
+		value = tipc_port_unreturnable(port);
 		break;
 	case TIPC_CONN_TIMEOUT:
 		value = tipc_sk(sk)->conn_timeout;
@@ -1842,25 +1936,47 @@ static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov,
 	return put_user(sizeof(value), ol);
 }
 
+int tipc_ioctl(struct socket *sk, unsigned int cmd, unsigned long arg)
+{
+	struct tipc_sioc_ln_req lnr;
+	void __user *argp = (void __user *)arg;
+
+	switch (cmd) {
+	case SIOCGETLINKNAME:
+		if (copy_from_user(&lnr, argp, sizeof(lnr)))
+			return -EFAULT;
+		if (!tipc_node_get_linkname(lnr.bearer_id, lnr.peer,
+					    lnr.linkname, TIPC_MAX_LINK_NAME)) {
+			if (copy_to_user(argp, &lnr, sizeof(lnr)))
+				return -EFAULT;
+			return 0;
+		}
+		return -EADDRNOTAVAIL;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
 /* Protocol switches for the various types of TIPC sockets */
 
 static const struct proto_ops msg_ops = {
 	.owner		= THIS_MODULE,
 	.family		= AF_TIPC,
-	.release	= release,
-	.bind		= bind,
-	.connect	= connect,
+	.release	= tipc_release,
+	.bind		= tipc_bind,
+	.connect	= tipc_connect,
 	.socketpair	= sock_no_socketpair,
 	.accept		= sock_no_accept,
-	.getname	= get_name,
-	.poll		= poll,
-	.ioctl		= sock_no_ioctl,
+	.getname	= tipc_getname,
+	.poll		= tipc_poll,
+	.ioctl		= tipc_ioctl,
 	.listen		= sock_no_listen,
-	.shutdown	= shutdown,
-	.setsockopt	= setsockopt,
-	.getsockopt	= getsockopt,
-	.sendmsg	= send_msg,
-	.recvmsg	= recv_msg,
+	.shutdown	= tipc_shutdown,
+	.setsockopt	= tipc_setsockopt,
+	.getsockopt	= tipc_getsockopt,
+	.sendmsg	= tipc_sendmsg,
+	.recvmsg	= tipc_recvmsg,
 	.mmap		= sock_no_mmap,
 	.sendpage	= sock_no_sendpage
 };
@@ -1868,20 +1984,20 @@ static const struct proto_ops msg_ops = {
 static const struct proto_ops packet_ops = {
 	.owner		= THIS_MODULE,
 	.family		= AF_TIPC,
-	.release	= release,
-	.bind		= bind,
-	.connect	= connect,
+	.release	= tipc_release,
+	.bind		= tipc_bind,
+	.connect	= tipc_connect,
 	.socketpair	= sock_no_socketpair,
-	.accept		= accept,
-	.getname	= get_name,
-	.poll		= poll,
-	.ioctl		= sock_no_ioctl,
-	.listen		= listen,
-	.shutdown	= shutdown,
-	.setsockopt	= setsockopt,
-	.getsockopt	= getsockopt,
-	.sendmsg	= send_packet,
-	.recvmsg	= recv_msg,
+	.accept		= tipc_accept,
+	.getname	= tipc_getname,
+	.poll		= tipc_poll,
+	.ioctl		= tipc_ioctl,
+	.listen		= tipc_listen,
+	.shutdown	= tipc_shutdown,
+	.setsockopt	= tipc_setsockopt,
+	.getsockopt	= tipc_getsockopt,
+	.sendmsg	= tipc_send_packet,
+	.recvmsg	= tipc_recvmsg,
 	.mmap		= sock_no_mmap,
 	.sendpage	= sock_no_sendpage
 };
@@ -1889,20 +2005,20 @@ static const struct proto_ops packet_ops = {
 static const struct proto_ops stream_ops = {
 	.owner		= THIS_MODULE,
 	.family		= AF_TIPC,
-	.release	= release,
-	.bind		= bind,
-	.connect	= connect,
+	.release	= tipc_release,
+	.bind		= tipc_bind,
+	.connect	= tipc_connect,
 	.socketpair	= sock_no_socketpair,
-	.accept		= accept,
-	.getname	= get_name,
-	.poll		= poll,
-	.ioctl		= sock_no_ioctl,
-	.listen		= listen,
-	.shutdown	= shutdown,
-	.setsockopt	= setsockopt,
-	.getsockopt	= getsockopt,
-	.sendmsg	= send_stream,
-	.recvmsg	= recv_stream,
+	.accept		= tipc_accept,
+	.getname	= tipc_getname,
+	.poll		= tipc_poll,
+	.ioctl		= tipc_ioctl,
+	.listen		= tipc_listen,
+	.shutdown	= tipc_shutdown,
+	.setsockopt	= tipc_setsockopt,
+	.getsockopt	= tipc_getsockopt,
+	.sendmsg	= tipc_send_stream,
+	.recvmsg	= tipc_recv_stream,
 	.mmap		= sock_no_mmap,
 	.sendpage	= sock_no_sendpage
 };
@@ -1947,8 +2063,6 @@ int tipc_socket_init(void)
 		proto_unregister(&tipc_proto);
 		goto out;
 	}
-
-	sockets_enabled = 1;
  out:
 	return res;
 }
@@ -1958,10 +2072,6 @@ int tipc_socket_init(void)
  */
 void tipc_socket_stop(void)
 {
-	if (!sockets_enabled)
-		return;
-
-	sockets_enabled = 0;
 	sock_unregister(tipc_family_ops.family);
 	proto_unregister(&tipc_proto);
 }
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
new file mode 100644
index 00000000000..3afcd2a70b3
--- /dev/null
+++ b/net/tipc/socket.h
@@ -0,0 +1,74 @@
+/* net/tipc/socket.h: Include file for TIPC socket code
+ *
+ * Copyright (c) 2014, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _TIPC_SOCK_H
+#define _TIPC_SOCK_H
+
+#include "port.h"
+#include <net/sock.h>
+
+/**
+ * struct tipc_sock - TIPC socket structure
+ * @sk: socket - interacts with 'port' and with user via the socket API
+ * @port: port - interacts with 'sk' and with the rest of the TIPC stack
+ * @peer_name: the peer of the connection, if any
+ * @conn_timeout: the time we can wait for an unresponded setup request
+ * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
+ */
+
+struct tipc_sock {
+	struct sock sk;
+	struct tipc_port port;
+	unsigned int conn_timeout;
+	atomic_t dupl_rcvcnt;
+};
+
+static inline struct tipc_sock *tipc_sk(const struct sock *sk)
+{
+	return container_of(sk, struct tipc_sock, sk);
+}
+
+static inline struct tipc_sock *tipc_port_to_sock(const struct tipc_port *port)
+{
+	return container_of(port, struct tipc_sock, port);
+}
+
+static inline void tipc_sock_wakeup(struct tipc_sock *tsk)
+{
+	tsk->sk.sk_write_space(&tsk->sk);
+}
+
+int tipc_sk_rcv(struct sk_buff *buf);
+
+#endif
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index d38bb45d82e..642437231ad 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -42,7 +42,7 @@
 /**
  * struct tipc_subscriber - TIPC network topology subscriber
  * @conid: connection identifier to server connecting to subscriber
- * @lock: controll access to subscriber
+ * @lock: control access to subscriber
  * @subscription_list: list of subscription objects for this subscriber
  */
 struct tipc_subscriber {
@@ -96,20 +96,16 @@ static void subscr_send_event(struct tipc_subscription *sub, u32 found_lower,
 {
 	struct tipc_subscriber *subscriber = sub->subscriber;
 	struct kvec msg_sect;
-	int ret;
 
 	msg_sect.iov_base = (void *)&sub->evt;
 	msg_sect.iov_len = sizeof(struct tipc_event);
-
 	sub->evt.event = htohl(event, sub->swap);
 	sub->evt.found_lower = htohl(found_lower, sub->swap);
 	sub->evt.found_upper = htohl(found_upper, sub->swap);
 	sub->evt.port.ref = htohl(port_ref, sub->swap);
 	sub->evt.port.node = htohl(node, sub->swap);
-	ret = tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL,
-				msg_sect.iov_base, msg_sect.iov_len);
-	if (ret < 0)
-		pr_err("Sending subscription event failed, no memory\n");
+	tipc_conn_sendmsg(&topsrv, subscriber->conid, NULL, msg_sect.iov_base,
+			  msg_sect.iov_len);
 }
 
 /**
@@ -153,14 +149,6 @@ static void subscr_timeout(struct tipc_subscription *sub)
 	/* The spin lock per subscriber is used to protect its members */
 	spin_lock_bh(&subscriber->lock);
 
-	/* Validate if the connection related to the subscriber is
-	 * closed (in case subscriber is terminating)
-	 */
-	if (subscriber->conid == 0) {
-		spin_unlock_bh(&subscriber->lock);
-		return;
-	}
-
 	/* Validate timeout (in case subscription is being cancelled) */
 	if (sub->timeout == TIPC_WAIT_FOREVER) {
 		spin_unlock_bh(&subscriber->lock);
@@ -215,9 +203,6 @@ static void subscr_release(struct tipc_subscriber *subscriber)
 
 	spin_lock_bh(&subscriber->lock);
 
-	/* Invalidate subscriber reference */
-	subscriber->conid = 0;
-
 	/* Destroy any existing subscriptions for subscriber */
 	list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list,
 				 subscription_list) {
@@ -278,9 +263,9 @@ static void subscr_cancel(struct tipc_subscr *s,
  *
  * Called with subscriber lock held.
  */
-static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s,
-					     struct tipc_subscriber *subscriber)
-{
+static int subscr_subscribe(struct tipc_subscr *s,
+			    struct tipc_subscriber *subscriber,
+			    struct tipc_subscription **sub_p) {
 	struct tipc_subscription *sub;
 	int swap;
 
@@ -291,23 +276,21 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s,
 	if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) {
 		s->filter &= ~htohl(TIPC_SUB_CANCEL, swap);
 		subscr_cancel(s, subscriber);
-		return NULL;
+		return 0;
 	}
 
 	/* Refuse subscription if global limit exceeded */
 	if (atomic_read(&subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) {
 		pr_warn("Subscription rejected, limit reached (%u)\n",
 			TIPC_MAX_SUBSCRIPTIONS);
-		subscr_terminate(subscriber);
-		return NULL;
+		return -EINVAL;
 	}
 
 	/* Allocate subscription object */
 	sub = kmalloc(sizeof(*sub), GFP_ATOMIC);
 	if (!sub) {
 		pr_warn("Subscription rejected, no memory\n");
-		subscr_terminate(subscriber);
-		return NULL;
+		return -ENOMEM;
 	}
 
 	/* Initialize subscription object */
@@ -321,8 +304,7 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s,
 	    (sub->seq.lower > sub->seq.upper)) {
 		pr_warn("Subscription rejected, illegal request\n");
 		kfree(sub);
-		subscr_terminate(subscriber);
-		return NULL;
+		return -EINVAL;
 	}
 	INIT_LIST_HEAD(&sub->nameseq_list);
 	list_add(&sub->subscription_list, &subscriber->subscription_list);
@@ -335,8 +317,8 @@ static struct tipc_subscription *subscr_subscribe(struct tipc_subscr *s,
 			     (Handler)subscr_timeout, (unsigned long)sub);
 		k_start_timer(&sub->timer, sub->timeout);
 	}
-
-	return sub;
+	*sub_p = sub;
+	return 0;
 }
 
 /* Handle one termination request for the subscriber */
@@ -350,10 +332,14 @@ static void subscr_conn_msg_event(int conid, struct sockaddr_tipc *addr,
 				  void *usr_data, void *buf, size_t len)
 {
 	struct tipc_subscriber *subscriber = usr_data;
-	struct tipc_subscription *sub;
+	struct tipc_subscription *sub = NULL;
 
 	spin_lock_bh(&subscriber->lock);
-	sub = subscr_subscribe((struct tipc_subscr *)buf, subscriber);
+	if (subscr_subscribe((struct tipc_subscr *)buf, subscriber, &sub) < 0) {
+		spin_unlock_bh(&subscriber->lock);
+		subscr_terminate(subscriber);
+		return;
+	}
 	if (sub)
 		tipc_nametbl_subscribe(sub);
 	spin_unlock_bh(&subscriber->lock);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 81362229631..e9688438073 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -163,9 +163,8 @@ static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
 
 static inline unsigned int unix_hash_fold(__wsum n)
 {
-	unsigned int hash = (__force unsigned int)n;
+	unsigned int hash = (__force unsigned int)csum_fold(n);
 
-	hash ^= hash>>16;
 	hash ^= hash>>8;
 	return hash&(UNIX_HASH_SIZE-1);
 }
@@ -532,13 +531,17 @@ static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *,
 static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *,
 				  struct msghdr *, size_t, int);
 
-static void unix_set_peek_off(struct sock *sk, int val)
+static int unix_set_peek_off(struct sock *sk, int val)
 {
 	struct unix_sock *u = unix_sk(sk);
 
-	mutex_lock(&u->readlock);
+	if (mutex_lock_interruptible(&u->readlock))
+		return -EINTR;
+
 	sk->sk_peek_off = val;
 	mutex_unlock(&u->readlock);
+
+	return 0;
 }
 
 
@@ -716,7 +719,9 @@ static int unix_autobind(struct socket *sock)
 	int err;
 	unsigned int retries = 0;
 
-	mutex_lock(&u->readlock);
+	err = mutex_lock_interruptible(&u->readlock);
+	if (err)
+		return err;
 
 	err = 0;
 	if (u->addr)
@@ -875,7 +880,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
-	mutex_lock(&u->readlock);
+	err = mutex_lock_interruptible(&u->readlock);
+	if (err)
+		goto out;
 
 	err = -EINVAL;
 	if (u->addr)
@@ -1200,7 +1207,7 @@ restart:
 	sk->sk_state	= TCP_ESTABLISHED;
 	sock_hold(newsk);
 
-	smp_mb__after_atomic_inc();	/* sock_hold() does an atomic_inc() */
+	smp_mb__after_atomic();	/* sock_hold() does an atomic_inc() */
 	unix_peer(sk)	= newsk;
 
 	unix_state_unlock(sk);
@@ -1210,7 +1217,7 @@ restart:
 	__skb_queue_tail(&other->sk_receive_queue, skb);
 	spin_unlock(&other->sk_receive_queue.lock);
 	unix_state_unlock(other);
-	other->sk_data_ready(other, 0);
+	other->sk_data_ready(other);
 	sock_put(other);
 	return 0;
 
@@ -1442,7 +1449,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct net *net = sock_net(sk);
 	struct unix_sock *u = unix_sk(sk);
-	struct sockaddr_un *sunaddr = msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
 	struct sock *other = NULL;
 	int namelen = 0; /* fake GCC */
 	int err;
@@ -1485,10 +1492,14 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (len > sk->sk_sndbuf - 32)
 		goto out;
 
-	if (len > SKB_MAX_ALLOC)
+	if (len > SKB_MAX_ALLOC) {
 		data_len = min_t(size_t,
 				 len - SKB_MAX_ALLOC,
 				 MAX_SKB_FRAGS * PAGE_SIZE);
+		data_len = PAGE_ALIGN(data_len);
+
+		BUILD_BUG_ON(SKB_MAX_ALLOC < PAGE_SIZE);
+	}
 
 	skb = sock_alloc_send_pskb(sk, len - data_len, data_len,
 				   msg->msg_flags & MSG_DONTWAIT, &err,
@@ -1593,7 +1604,7 @@ restart:
 	if (max_level > unix_sk(other)->recursion_level)
 		unix_sk(other)->recursion_level = max_level;
 	unix_state_unlock(other);
-	other->sk_data_ready(other, len);
+	other->sk_data_ready(other);
 	sock_put(other);
 	scm_destroy(siocb->scm);
 	return len;
@@ -1663,6 +1674,8 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 
 		data_len = max_t(int, 0, size - SKB_MAX_HEAD(0));
 
+		data_len = min_t(size_t, size, PAGE_ALIGN(data_len));
+
 		skb = sock_alloc_send_pskb(sk, size - data_len, data_len,
 					   msg->msg_flags & MSG_DONTWAIT, &err,
 					   get_order(UNIX_SKB_FRAGS_SZ));
@@ -1699,7 +1712,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		if (max_level > unix_sk(other)->recursion_level)
 			unix_sk(other)->recursion_level = max_level;
 		unix_state_unlock(other);
-		other->sk_data_ready(other, size);
+		other->sk_data_ready(other);
 		sent += size;
 	}
 
@@ -1780,8 +1793,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}
 
@@ -1904,8 +1920,9 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct scm_cookie tmp_scm;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
-	struct sockaddr_un *sunaddr = msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
 	int copied = 0;
+	int noblock = flags & MSG_DONTWAIT;
 	int check_creds = 0;
 	int target;
 	int err = 0;
@@ -1921,7 +1938,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 
 	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
-	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
+	timeo = sock_rcvtimeo(sk, noblock);
 
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
@@ -1933,8 +1950,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(timeo);
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 5adfd94c5b8..85d232bed87 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1925,9 +1925,23 @@ static struct miscdevice vsock_device = {
 	.fops		= &vsock_device_ops,
 };
 
-static int __vsock_core_init(void)
+int __vsock_core_init(const struct vsock_transport *t, struct module *owner)
 {
-	int err;
+	int err = mutex_lock_interruptible(&vsock_register_mutex);
+
+	if (err)
+		return err;
+
+	if (transport) {
+		err = -EBUSY;
+		goto err_busy;
+	}
+
+	/* Transport must be the owner of the protocol so that it can't
+	 * unload while there are open sockets.
+	 */
+	vsock_proto.owner = owner;
+	transport = t;
 
 	vsock_init_tables();
 
@@ -1951,36 +1965,19 @@ static int __vsock_core_init(void)
 		goto err_unregister_proto;
 	}
 
+	mutex_unlock(&vsock_register_mutex);
 	return 0;
 
 err_unregister_proto:
 	proto_unregister(&vsock_proto);
 err_misc_deregister:
 	misc_deregister(&vsock_device);
-	return err;
-}
-
-int vsock_core_init(const struct vsock_transport *t)
-{
-	int retval = mutex_lock_interruptible(&vsock_register_mutex);
-	if (retval)
-		return retval;
-
-	if (transport) {
-		retval = -EBUSY;
-		goto out;
-	}
-
-	transport = t;
-	retval = __vsock_core_init();
-	if (retval)
-		transport = NULL;
-
-out:
+	transport = NULL;
+err_busy:
 	mutex_unlock(&vsock_register_mutex);
-	return retval;
+	return err;
 }
-EXPORT_SYMBOL_GPL(vsock_core_init);
+EXPORT_SYMBOL_GPL(__vsock_core_init);
 
 void vsock_core_exit(void)
 {
@@ -2000,5 +1997,5 @@ EXPORT_SYMBOL_GPL(vsock_core_exit);
 
 MODULE_AUTHOR("VMware, Inc.");
 MODULE_DESCRIPTION("VMware Virtual Socket Family");
-MODULE_VERSION("1.0.0.0-k");
+MODULE_VERSION("1.0.1.0-k");
 MODULE_LICENSE("GPL v2");
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 687360da62d..9bb63ffec4f 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1779,10 +1779,8 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb,
 		goto out;
 
 	if (msg->msg_name) {
-		struct sockaddr_vm *vm_addr;
-
 		/* Provide the address of the sender. */
-		vm_addr = (struct sockaddr_vm *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_vm *, vm_addr, msg->msg_name);
 		vsock_addr_init(vm_addr, dg->src.context, dg->src.resource);
 		msg->msg_namelen = sizeof(*vm_addr);
 	}
diff --git a/net/vmw_vsock/vmci_transport_notify.c b/net/vmw_vsock/vmci_transport_notify.c
index 9a730744e7b..9b7f207f2be 100644
--- a/net/vmw_vsock/vmci_transport_notify.c
+++ b/net/vmw_vsock/vmci_transport_notify.c
@@ -315,7 +315,7 @@ vmci_transport_handle_wrote(struct sock *sk,
 	struct vsock_sock *vsk = vsock_sk(sk);
 	PKT_FIELD(vsk, sent_waiting_read) = false;
 #endif
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 }
 
 static void vmci_transport_notify_pkt_socket_init(struct sock *sk)
diff --git a/net/vmw_vsock/vmci_transport_notify_qstate.c b/net/vmw_vsock/vmci_transport_notify_qstate.c
index 622bd7aa101..dc9c7929a2f 100644
--- a/net/vmw_vsock/vmci_transport_notify_qstate.c
+++ b/net/vmw_vsock/vmci_transport_notify_qstate.c
@@ -92,7 +92,7 @@ vmci_transport_handle_wrote(struct sock *sk,
 			    bool bottom_half,
 			    struct sockaddr_vm *dst, struct sockaddr_vm *src)
 {
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 }
 
 static void vsock_block_update_write_window(struct sock *sk)
@@ -290,7 +290,7 @@ vmci_transport_notify_pkt_recv_post_dequeue(
 		/* See the comment in
 		 * vmci_transport_notify_pkt_send_post_enqueue().
 		 */
-		sk->sk_data_ready(sk, 0);
+		sk->sk_data_ready(sk);
 	}
 
 	return err;
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index 16d08b39921..405f3c4cf70 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -95,6 +95,43 @@ config CFG80211_CERTIFICATION_ONUS
 	  you are a wireless researcher and are working in a controlled
 	  and approved environment by your local regulatory agency.
 
+config CFG80211_REG_CELLULAR_HINTS
+	bool "cfg80211 regulatory support for cellular base station hints"
+	depends on CFG80211_CERTIFICATION_ONUS
+	---help---
+	  This option enables support for parsing regulatory hints
+	  from cellular base stations. If enabled and at least one driver
+	  claims support for parsing cellular base station hints the
+	  regulatory core will allow and parse these regulatory hints.
+	  The regulatory core will only apply these regulatory hints on
+	  drivers that support this feature. You should only enable this
+	  feature if you have tested and validated this feature on your
+	  systems.
+
+config CFG80211_REG_RELAX_NO_IR
+	bool "cfg80211 support for NO_IR relaxation"
+	depends on CFG80211_CERTIFICATION_ONUS
+	---help---
+	 This option enables support for relaxation of the NO_IR flag for
+	 situations that certain regulatory bodies have provided clarifications
+	 on how relaxation can occur. This feature has an inherent dependency on
+	 userspace features which must have been properly tested and as such is
+	 not enabled by default.
+
+	 A relaxation feature example is allowing the operation of a P2P group
+	 owner (GO) on channels marked with NO_IR if there is an additional BSS
+	 interface which associated to an AP which userspace assumes or confirms
+	 to be an authorized master, i.e., with radar detection support and DFS
+	 capabilities. However, note that in order to not create daisy chain
+	 scenarios, this relaxation is not allowed in cases that the BSS client
+	 is associated to P2P GO and in addition the P2P GO instantiated on
+	 a channel due to this relaxation should not allow connection from
+	 non P2P clients.
+
+	 The regulatory core will apply these relaxations only for drivers that
+	 support this feature by declaring the appropriate channel flags and
+	 capabilities in their registration flow.
+
 config CFG80211_DEFAULT_PS
 	bool "enable powersave by default"
 	depends on CFG80211
diff --git a/net/wireless/ap.c b/net/wireless/ap.c
index 324e8d851dc..bdad1f95156 100644
--- a/net/wireless/ap.c
+++ b/net/wireless/ap.c
@@ -6,8 +6,8 @@
 #include "rdev-ops.h"
 
 
-static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
-			      struct net_device *dev)
+int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
+		       struct net_device *dev, bool notify)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	int err;
@@ -27,21 +27,24 @@ static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
 	err = rdev_stop_ap(rdev, dev);
 	if (!err) {
 		wdev->beacon_interval = 0;
-		wdev->channel = NULL;
+		memset(&wdev->chandef, 0, sizeof(wdev->chandef));
 		wdev->ssid_len = 0;
+		rdev_set_qos_map(rdev, dev, NULL);
+		if (notify)
+			nl80211_send_ap_stopped(wdev);
 	}
 
 	return err;
 }
 
 int cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
-		     struct net_device *dev)
+		     struct net_device *dev, bool notify)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	int err;
 
 	wdev_lock(wdev);
-	err = __cfg80211_stop_ap(rdev, dev);
+	err = __cfg80211_stop_ap(rdev, dev, notify);
 	wdev_unlock(wdev);
 
 	return err;
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 78559b5bbd1..992b34070bc 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -326,28 +326,57 @@ static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy,
 
 
 int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
-				  const struct cfg80211_chan_def *chandef)
+				  const struct cfg80211_chan_def *chandef,
+				  enum nl80211_iftype iftype)
 {
 	int width;
-	int r;
+	int ret;
 
 	if (WARN_ON(!cfg80211_chandef_valid(chandef)))
 		return -EINVAL;
 
-	width = cfg80211_chandef_get_width(chandef);
-	if (width < 0)
-		return -EINVAL;
+	switch (iftype) {
+	case NL80211_IFTYPE_ADHOC:
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_P2P_GO:
+	case NL80211_IFTYPE_MESH_POINT:
+		width = cfg80211_chandef_get_width(chandef);
+		if (width < 0)
+			return -EINVAL;
 
-	r = cfg80211_get_chans_dfs_required(wiphy, chandef->center_freq1,
-					    width);
-	if (r)
-		return r;
+		ret = cfg80211_get_chans_dfs_required(wiphy,
+						      chandef->center_freq1,
+						      width);
+		if (ret < 0)
+			return ret;
+		else if (ret > 0)
+			return BIT(chandef->width);
 
-	if (!chandef->center_freq2)
-		return 0;
+		if (!chandef->center_freq2)
+			return 0;
 
-	return cfg80211_get_chans_dfs_required(wiphy, chandef->center_freq2,
-					       width);
+		ret = cfg80211_get_chans_dfs_required(wiphy,
+						      chandef->center_freq2,
+						      width);
+		if (ret < 0)
+			return ret;
+		else if (ret > 0)
+			return BIT(chandef->width);
+
+		break;
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+	case NL80211_IFTYPE_MONITOR:
+	case NL80211_IFTYPE_AP_VLAN:
+	case NL80211_IFTYPE_WDS:
+	case NL80211_IFTYPE_P2P_DEVICE:
+		break;
+	case NL80211_IFTYPE_UNSPECIFIED:
+	case NUM_NL80211_IFTYPES:
+		WARN_ON(1);
+	}
+
+	return 0;
 }
 EXPORT_SYMBOL(cfg80211_chandef_dfs_required);
 
@@ -490,6 +519,62 @@ static bool cfg80211_chandef_dfs_available(struct wiphy *wiphy,
 	return r;
 }
 
+static unsigned int cfg80211_get_chans_dfs_cac_time(struct wiphy *wiphy,
+						    u32 center_freq,
+						    u32 bandwidth)
+{
+	struct ieee80211_channel *c;
+	u32 start_freq, end_freq, freq;
+	unsigned int dfs_cac_ms = 0;
+
+	start_freq = cfg80211_get_start_freq(center_freq, bandwidth);
+	end_freq = cfg80211_get_end_freq(center_freq, bandwidth);
+
+	for (freq = start_freq; freq <= end_freq; freq += 20) {
+		c = ieee80211_get_channel(wiphy, freq);
+		if (!c)
+			return 0;
+
+		if (c->flags & IEEE80211_CHAN_DISABLED)
+			return 0;
+
+		if (!(c->flags & IEEE80211_CHAN_RADAR))
+			continue;
+
+		if (c->dfs_cac_ms > dfs_cac_ms)
+			dfs_cac_ms = c->dfs_cac_ms;
+	}
+
+	return dfs_cac_ms;
+}
+
+unsigned int
+cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy,
+			      const struct cfg80211_chan_def *chandef)
+{
+	int width;
+	unsigned int t1 = 0, t2 = 0;
+
+	if (WARN_ON(!cfg80211_chandef_valid(chandef)))
+		return 0;
+
+	width = cfg80211_chandef_get_width(chandef);
+	if (width < 0)
+		return 0;
+
+	t1 = cfg80211_get_chans_dfs_cac_time(wiphy,
+					     chandef->center_freq1,
+					     width);
+
+	if (!chandef->center_freq2)
+		return t1;
+
+	t2 = cfg80211_get_chans_dfs_cac_time(wiphy,
+					     chandef->center_freq2,
+					     width);
+
+	return max(t1, t2);
+}
 
 static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy,
 					u32 center_freq, u32 bandwidth,
@@ -531,12 +616,14 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 		width = 5;
 		break;
 	case NL80211_CHAN_WIDTH_10:
+		prohibited_flags |= IEEE80211_CHAN_NO_10MHZ;
 		width = 10;
 		break;
 	case NL80211_CHAN_WIDTH_20:
 		if (!ht_cap->ht_supported)
 			return false;
 	case NL80211_CHAN_WIDTH_20_NOHT:
+		prohibited_flags |= IEEE80211_CHAN_NO_20MHZ;
 		width = 20;
 		break;
 	case NL80211_CHAN_WIDTH_40:
@@ -605,17 +692,111 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 }
 EXPORT_SYMBOL(cfg80211_chandef_usable);
 
+/*
+ * For GO only, check if the channel can be used under permissive conditions
+ * mandated by the some regulatory bodies, i.e., the channel is marked with
+ * IEEE80211_CHAN_GO_CONCURRENT and there is an additional station interface
+ * associated to an AP on the same channel or on the same UNII band
+ * (assuming that the AP is an authorized master).
+ * In addition allow the GO to operate on a channel on which indoor operation is
+ * allowed, iff we are currently operating in an indoor environment.
+ */
+static bool cfg80211_go_permissive_chan(struct cfg80211_registered_device *rdev,
+					struct ieee80211_channel *chan)
+{
+	struct wireless_dev *wdev_iter;
+	struct wiphy *wiphy = wiphy_idx_to_wiphy(rdev->wiphy_idx);
+
+	ASSERT_RTNL();
+
+	if (!config_enabled(CONFIG_CFG80211_REG_RELAX_NO_IR) ||
+	    !(wiphy->regulatory_flags & REGULATORY_ENABLE_RELAX_NO_IR))
+		return false;
+
+	if (regulatory_indoor_allowed() &&
+	    (chan->flags & IEEE80211_CHAN_INDOOR_ONLY))
+		return true;
+
+	if (!(chan->flags & IEEE80211_CHAN_GO_CONCURRENT))
+		return false;
+
+	/*
+	 * Generally, it is possible to rely on another device/driver to allow
+	 * the GO concurrent relaxation, however, since the device can further
+	 * enforce the relaxation (by doing a similar verifications as this),
+	 * and thus fail the GO instantiation, consider only the interfaces of
+	 * the current registered device.
+	 */
+	list_for_each_entry(wdev_iter, &rdev->wdev_list, list) {
+		struct ieee80211_channel *other_chan = NULL;
+		int r1, r2;
+
+		if (wdev_iter->iftype != NL80211_IFTYPE_STATION ||
+		    !netif_running(wdev_iter->netdev))
+			continue;
+
+		wdev_lock(wdev_iter);
+		if (wdev_iter->current_bss)
+			other_chan = wdev_iter->current_bss->pub.channel;
+		wdev_unlock(wdev_iter);
+
+		if (!other_chan)
+			continue;
+
+		if (chan == other_chan)
+			return true;
+
+		if (chan->band != IEEE80211_BAND_5GHZ)
+			continue;
+
+		r1 = cfg80211_get_unii(chan->center_freq);
+		r2 = cfg80211_get_unii(other_chan->center_freq);
+
+		if (r1 != -EINVAL && r1 == r2) {
+			/*
+			 * At some locations channels 149-165 are considered a
+			 * bundle, but at other locations, e.g., Indonesia,
+			 * channels 149-161 are considered a bundle while
+			 * channel 165 is left out and considered to be in a
+			 * different bundle. Thus, in case that there is a
+			 * station interface connected to an AP on channel 165,
+			 * it is assumed that channels 149-161 are allowed for
+			 * GO operations. However, having a station interface
+			 * connected to an AP on channels 149-161, does not
+			 * allow GO operation on channel 165.
+			 */
+			if (chan->center_freq == 5825 &&
+			    other_chan->center_freq != 5825)
+				continue;
+			return true;
+		}
+	}
+
+	return false;
+}
+
 bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
-			     struct cfg80211_chan_def *chandef)
+			     struct cfg80211_chan_def *chandef,
+			     enum nl80211_iftype iftype)
 {
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	bool res;
 	u32 prohibited_flags = IEEE80211_CHAN_DISABLED |
-			       IEEE80211_CHAN_NO_IR |
 			       IEEE80211_CHAN_RADAR;
 
-	trace_cfg80211_reg_can_beacon(wiphy, chandef);
+	trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype);
+
+	/*
+	 * Under certain conditions suggested by the some regulatory bodies
+	 * a GO can operate on channels marked with IEEE80211_NO_IR
+	 * so set this flag only if such relaxations are not enabled and
+	 * the conditions are not met.
+	 */
+	if (iftype != NL80211_IFTYPE_P2P_GO ||
+	    !cfg80211_go_permissive_chan(rdev, chandef->chan))
+		prohibited_flags |= IEEE80211_CHAN_NO_IR;
 
-	if (cfg80211_chandef_dfs_required(wiphy, chandef) > 0 &&
+	if (cfg80211_chandef_dfs_required(wiphy, chandef, iftype) > 0 &&
 	    cfg80211_chandef_dfs_available(wiphy, chandef)) {
 		/* We can skip IEEE80211_CHAN_NO_IR if chandef dfs available */
 		prohibited_flags = IEEE80211_CHAN_DISABLED;
@@ -642,8 +823,11 @@ int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev,
 void
 cfg80211_get_chan_state(struct wireless_dev *wdev,
 		        struct ieee80211_channel **chan,
-		        enum cfg80211_chan_mode *chanmode)
+		        enum cfg80211_chan_mode *chanmode,
+		        u8 *radar_detect)
 {
+	int ret;
+
 	*chan = NULL;
 	*chanmode = CHAN_MODE_UNDEFINED;
 
@@ -660,6 +844,11 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
 				     !wdev->ibss_dfs_possible)
 				  ? CHAN_MODE_SHARED
 				  : CHAN_MODE_EXCLUSIVE;
+
+			/* consider worst-case - IBSS can try to return to the
+			 * original user-specified channel as creator */
+			if (wdev->ibss_dfs_possible)
+				*radar_detect |= BIT(wdev->chandef.width);
 			return;
 		}
 		break;
@@ -674,33 +863,42 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_P2P_GO:
 		if (wdev->cac_started) {
-			*chan = wdev->channel;
+			*chan = wdev->chandef.chan;
 			*chanmode = CHAN_MODE_SHARED;
+			*radar_detect |= BIT(wdev->chandef.width);
 		} else if (wdev->beacon_interval) {
-			*chan = wdev->channel;
+			*chan = wdev->chandef.chan;
 			*chanmode = CHAN_MODE_SHARED;
+
+			ret = cfg80211_chandef_dfs_required(wdev->wiphy,
+							    &wdev->chandef,
+							    wdev->iftype);
+			WARN_ON(ret < 0);
+			if (ret > 0)
+				*radar_detect |= BIT(wdev->chandef.width);
 		}
 		return;
 	case NL80211_IFTYPE_MESH_POINT:
 		if (wdev->mesh_id_len) {
-			*chan = wdev->channel;
+			*chan = wdev->chandef.chan;
 			*chanmode = CHAN_MODE_SHARED;
+
+			ret = cfg80211_chandef_dfs_required(wdev->wiphy,
+							    &wdev->chandef,
+							    wdev->iftype);
+			WARN_ON(ret < 0);
+			if (ret > 0)
+				*radar_detect |= BIT(wdev->chandef.width);
 		}
 		return;
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_AP_VLAN:
 	case NL80211_IFTYPE_WDS:
-		/* these interface types don't really have a channel */
-		return;
 	case NL80211_IFTYPE_P2P_DEVICE:
-		if (wdev->wiphy->features &
-				NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL)
-			*chanmode = CHAN_MODE_EXCLUSIVE;
+		/* these interface types don't really have a channel */
 		return;
 	case NL80211_IFTYPE_UNSPECIFIED:
 	case NUM_NL80211_IFTYPES:
 		WARN_ON(1);
 	}
-
-	return;
 }
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 06db6eb5258..a1c40654dd9 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -69,7 +69,7 @@ struct cfg80211_registered_device *cfg80211_rdev_by_wiphy_idx(int wiphy_idx)
 
 int get_wiphy_idx(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	return rdev->wiphy_idx;
 }
@@ -130,7 +130,7 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
 			    newname))
 		pr_err("failed to rename debugfs dir to %s!\n", newname);
 
-	nl80211_notify_dev_rename(rdev);
+	nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY);
 
 	return 0;
 }
@@ -204,27 +204,18 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev,
 	rdev->opencount--;
 
 	if (rdev->scan_req && rdev->scan_req->wdev == wdev) {
-		/*
-		 * If the scan request wasn't notified as done, set it
-		 * to aborted and leak it after a warning. The driver
-		 * should have notified us that it ended at the latest
-		 * during rdev_stop_p2p_device().
-		 */
 		if (WARN_ON(!rdev->scan_req->notified))
 			rdev->scan_req->aborted = true;
-		___cfg80211_scan_done(rdev, !rdev->scan_req->notified);
+		___cfg80211_scan_done(rdev, false);
 	}
 }
 
-static int cfg80211_rfkill_set_block(void *data, bool blocked)
+void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = data;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct wireless_dev *wdev;
 
-	if (!blocked)
-		return 0;
-
-	rtnl_lock();
+	ASSERT_RTNL();
 
 	list_for_each_entry(wdev, &rdev->wdev_list, list) {
 		if (wdev->netdev) {
@@ -240,7 +231,18 @@ static int cfg80211_rfkill_set_block(void *data, bool blocked)
 			break;
 		}
 	}
+}
+EXPORT_SYMBOL_GPL(cfg80211_shutdown_all_interfaces);
+
+static int cfg80211_rfkill_set_block(void *data, bool blocked)
+{
+	struct cfg80211_registered_device *rdev = data;
+
+	if (!blocked)
+		return 0;
 
+	rtnl_lock();
+	cfg80211_shutdown_all_interfaces(&rdev->wiphy);
 	rtnl_unlock();
 
 	return 0;
@@ -266,6 +268,45 @@ static void cfg80211_event_work(struct work_struct *work)
 	rtnl_unlock();
 }
 
+void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev)
+{
+	struct cfg80211_iface_destroy *item;
+
+	ASSERT_RTNL();
+
+	spin_lock_irq(&rdev->destroy_list_lock);
+	while ((item = list_first_entry_or_null(&rdev->destroy_list,
+						struct cfg80211_iface_destroy,
+						list))) {
+		struct wireless_dev *wdev, *tmp;
+		u32 nlportid = item->nlportid;
+
+		list_del(&item->list);
+		kfree(item);
+		spin_unlock_irq(&rdev->destroy_list_lock);
+
+		list_for_each_entry_safe(wdev, tmp, &rdev->wdev_list, list) {
+			if (nlportid == wdev->owner_nlportid)
+				rdev_del_virtual_intf(rdev, wdev);
+		}
+
+		spin_lock_irq(&rdev->destroy_list_lock);
+	}
+	spin_unlock_irq(&rdev->destroy_list_lock);
+}
+
+static void cfg80211_destroy_iface_wk(struct work_struct *work)
+{
+	struct cfg80211_registered_device *rdev;
+
+	rdev = container_of(work, struct cfg80211_registered_device,
+			    destroy_work);
+
+	rtnl_lock();
+	cfg80211_destroy_ifaces(rdev);
+	rtnl_unlock();
+}
+
 /* exported functions */
 
 struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
@@ -324,6 +365,10 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 	rdev->wiphy.dev.class = &ieee80211_class;
 	rdev->wiphy.dev.platform_data = rdev;
 
+	INIT_LIST_HEAD(&rdev->destroy_list);
+	spin_lock_init(&rdev->destroy_list_lock);
+	INIT_WORK(&rdev->destroy_work, cfg80211_destroy_iface_wk);
+
 #ifdef CONFIG_CFG80211_DEFAULT_PS
 	rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
 #endif
@@ -357,6 +402,8 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 	rdev->wiphy.rts_threshold = (u32) -1;
 	rdev->wiphy.coverage_class = 0;
 
+	rdev->wiphy.max_num_csa_counters = 1;
+
 	return &rdev->wiphy;
 }
 EXPORT_SYMBOL(wiphy_new);
@@ -402,10 +449,7 @@ static int wiphy_verify_combinations(struct wiphy *wiphy)
 		for (j = 0; j < c->n_limits; j++) {
 			u16 types = c->limits[j].types;
 
-			/*
-			 * interface types shouldn't overlap, this is
-			 * used in cfg80211_can_change_interface()
-			 */
+			/* interface types shouldn't overlap */
 			if (WARN_ON(types & all_iftypes))
 				return -EINVAL;
 			all_iftypes |= types;
@@ -441,7 +485,7 @@ static int wiphy_verify_combinations(struct wiphy *wiphy)
 
 int wiphy_register(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	int res;
 	enum ieee80211_band band;
 	struct ieee80211_supported_band *sband;
@@ -449,9 +493,6 @@ int wiphy_register(struct wiphy *wiphy)
 	int i;
 	u16 ifmodes = wiphy->interface_modes;
 
-	/* support for 5/10 MHz is broken due to nl80211 API mess - disable */
-	wiphy->flags &= ~WIPHY_FLAG_SUPPORTS_5_10_MHZ;
-
 	/*
 	 * There are major locking problems in nl80211/mac80211 for CSA,
 	 * disable for all drivers until this has been reworked.
@@ -619,13 +660,15 @@ int wiphy_register(struct wiphy *wiphy)
 		return res;
 	}
 
+	nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY);
+
 	return 0;
 }
 EXPORT_SYMBOL(wiphy_register);
 
 void wiphy_rfkill_start_polling(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	if (!rdev->ops->rfkill_poll)
 		return;
@@ -636,7 +679,7 @@ EXPORT_SYMBOL(wiphy_rfkill_start_polling);
 
 void wiphy_rfkill_stop_polling(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	rfkill_pause_polling(rdev->rfkill);
 }
@@ -644,7 +687,7 @@ EXPORT_SYMBOL(wiphy_rfkill_stop_polling);
 
 void wiphy_unregister(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	wait_event(rdev->dev_wait, ({
 		int __count;
@@ -657,9 +700,10 @@ void wiphy_unregister(struct wiphy *wiphy)
 		rfkill_unregister(rdev->rfkill);
 
 	rtnl_lock();
+	nl80211_notify_wiphy(rdev, NL80211_CMD_DEL_WIPHY);
 	rdev->wiphy.registered = false;
 
-	BUG_ON(!list_empty(&rdev->wdev_list));
+	WARN_ON(!list_empty(&rdev->wdev_list));
 
 	/*
 	 * First remove the hardware from everywhere, this makes
@@ -684,6 +728,7 @@ void wiphy_unregister(struct wiphy *wiphy)
 	cancel_work_sync(&rdev->conn_work);
 	flush_work(&rdev->event_work);
 	cancel_delayed_work_sync(&rdev->dfs_update_channels_wk);
+	flush_work(&rdev->destroy_work);
 
 #ifdef CONFIG_PM
 	if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup)
@@ -716,7 +761,7 @@ EXPORT_SYMBOL(wiphy_free);
 
 void wiphy_rfkill_set_hw_state(struct wiphy *wiphy, bool blocked)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	if (rfkill_set_hw_state(rdev->rfkill, blocked))
 		schedule_work(&rdev->rfkill_sync);
@@ -725,7 +770,7 @@ EXPORT_SYMBOL(wiphy_rfkill_set_hw_state);
 
 void cfg80211_unregister_wdev(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	ASSERT_RTNL();
 
@@ -746,7 +791,7 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev)
 }
 EXPORT_SYMBOL(cfg80211_unregister_wdev);
 
-static struct device_type wiphy_type = {
+static const struct device_type wiphy_type = {
 	.name	= "wlan",
 };
 
@@ -760,20 +805,23 @@ void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev,
 		rdev->num_running_monitor_ifaces += num;
 }
 
-void cfg80211_leave(struct cfg80211_registered_device *rdev,
-		    struct wireless_dev *wdev)
+void __cfg80211_leave(struct cfg80211_registered_device *rdev,
+		      struct wireless_dev *wdev)
 {
 	struct net_device *dev = wdev->netdev;
 
+	ASSERT_RTNL();
+	ASSERT_WDEV_LOCK(wdev);
+
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_ADHOC:
-		cfg80211_leave_ibss(rdev, dev, true);
+		__cfg80211_leave_ibss(rdev, dev, true);
 		break;
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_STATION:
-		__cfg80211_stop_sched_scan(rdev, false);
+		if (rdev->sched_scan_req && dev == rdev->sched_scan_req->dev)
+			__cfg80211_stop_sched_scan(rdev, false);
 
-		wdev_lock(wdev);
 #ifdef CONFIG_CFG80211_WEXT
 		kfree(wdev->wext.ie);
 		wdev->wext.ie = NULL;
@@ -782,21 +830,48 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev,
 #endif
 		cfg80211_disconnect(rdev, dev,
 				    WLAN_REASON_DEAUTH_LEAVING, true);
-		wdev_unlock(wdev);
 		break;
 	case NL80211_IFTYPE_MESH_POINT:
-		cfg80211_leave_mesh(rdev, dev);
+		__cfg80211_leave_mesh(rdev, dev);
 		break;
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_P2P_GO:
-		cfg80211_stop_ap(rdev, dev);
+		__cfg80211_stop_ap(rdev, dev, true);
 		break;
 	default:
 		break;
 	}
+}
+
+void cfg80211_leave(struct cfg80211_registered_device *rdev,
+		    struct wireless_dev *wdev)
+{
+	wdev_lock(wdev);
+	__cfg80211_leave(rdev, wdev);
+	wdev_unlock(wdev);
+}
 
-	wdev->beacon_interval = 0;
+void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev,
+			 gfp_t gfp)
+{
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+	struct cfg80211_event *ev;
+	unsigned long flags;
+
+	trace_cfg80211_stop_iface(wiphy, wdev);
+
+	ev = kzalloc(sizeof(*ev), gfp);
+	if (!ev)
+		return;
+
+	ev->type = EVENT_STOPPED;
+
+	spin_lock_irqsave(&wdev->event_lock, flags);
+	list_add_tail(&ev->list, &wdev->event_list);
+	spin_unlock_irqrestore(&wdev->event_lock, flags);
+	queue_work(cfg80211_wq, &rdev->event_work);
 }
+EXPORT_SYMBOL(cfg80211_stop_iface);
 
 static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 					 unsigned long state, void *ptr)
@@ -804,12 +879,11 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev;
-	int ret;
 
 	if (!wdev)
 		return NOTIFY_DONE;
 
-	rdev = wiphy_to_dev(wdev->wiphy);
+	rdev = wiphy_to_rdev(wdev->wiphy);
 
 	WARN_ON(wdev->iftype == NL80211_IFTYPE_UNSPECIFIED);
 
@@ -868,7 +942,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		if (rdev->scan_req && rdev->scan_req->wdev == wdev) {
 			if (WARN_ON(!rdev->scan_req->notified))
 				rdev->scan_req->aborted = true;
-			___cfg80211_scan_done(rdev, true);
+			___cfg80211_scan_done(rdev, false);
 		}
 
 		if (WARN_ON(rdev->sched_scan_req &&
@@ -967,13 +1041,14 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 	case NETDEV_PRE_UP:
 		if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)))
 			return notifier_from_errno(-EOPNOTSUPP);
-		ret = cfg80211_can_add_interface(rdev, wdev->iftype);
-		if (ret)
-			return notifier_from_errno(ret);
+		if (rfkill_blocked(rdev->rfkill))
+			return notifier_from_errno(-ERFKILL);
 		break;
+	default:
+		return NOTIFY_DONE;
 	}
 
-	return NOTIFY_DONE;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block cfg80211_netdev_notifier = {
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 0a277c33bb0..7e3a3cef7df 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -62,14 +62,13 @@ struct cfg80211_registered_device {
 	struct rb_root bss_tree;
 	u32 bss_generation;
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
+	struct sk_buff *scan_msg;
 	struct cfg80211_sched_scan_request *sched_scan_req;
 	unsigned long suspend_at;
 	struct work_struct scan_done_wk;
 	struct work_struct sched_scan_results_wk;
 
-#ifdef CONFIG_NL80211_TESTMODE
-	struct genl_info *testmode_info;
-#endif
+	struct genl_info *cur_cmd_info;
 
 	struct work_struct conn_work;
 	struct work_struct event_work;
@@ -81,13 +80,17 @@ struct cfg80211_registered_device {
 
 	struct cfg80211_coalesce *coalesce;
 
+	spinlock_t destroy_list_lock;
+	struct list_head destroy_list;
+	struct work_struct destroy_work;
+
 	/* must be last because of the way we do wiphy_priv(),
 	 * and it should at least be aligned to NETDEV_ALIGN */
 	struct wiphy wiphy __aligned(NETDEV_ALIGN);
 };
 
 static inline
-struct cfg80211_registered_device *wiphy_to_dev(struct wiphy *wiphy)
+struct cfg80211_registered_device *wiphy_to_rdev(struct wiphy *wiphy)
 {
 	BUG_ON(!wiphy);
 	return container_of(wiphy, struct cfg80211_registered_device, wiphy);
@@ -167,7 +170,6 @@ static inline void wdev_unlock(struct wireless_dev *wdev)
 	mutex_unlock(&wdev->mtx);
 }
 
-#define ASSERT_RDEV_LOCK(rdev) ASSERT_RTNL()
 #define ASSERT_WDEV_LOCK(wdev) lockdep_assert_held(&(wdev)->mtx)
 
 static inline bool cfg80211_has_monitors_only(struct cfg80211_registered_device *rdev)
@@ -183,6 +185,7 @@ enum cfg80211_event_type {
 	EVENT_ROAMED,
 	EVENT_DISCONNECTED,
 	EVENT_IBSS_JOINED,
+	EVENT_STOPPED,
 };
 
 struct cfg80211_event {
@@ -212,6 +215,7 @@ struct cfg80211_event {
 		} dc;
 		struct {
 			u8 bssid[ETH_ALEN];
+			struct ieee80211_channel *channel;
 		} ij;
 	};
 };
@@ -233,6 +237,13 @@ struct cfg80211_beacon_registration {
 	u32 nlportid;
 };
 
+struct cfg80211_iface_destroy {
+	struct list_head list;
+	u32 nlportid;
+};
+
+void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev);
+
 /* free object */
 void cfg80211_dev_free(struct cfg80211_registered_device *rdev);
 
@@ -241,15 +252,11 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
 
 void ieee80211_set_bitrate_flags(struct wiphy *wiphy);
 
-void cfg80211_bss_expire(struct cfg80211_registered_device *dev);
-void cfg80211_bss_age(struct cfg80211_registered_device *dev,
+void cfg80211_bss_expire(struct cfg80211_registered_device *rdev);
+void cfg80211_bss_age(struct cfg80211_registered_device *rdev,
                       unsigned long age_secs);
 
 /* IBSS */
-int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
-			 struct net_device *dev,
-			 struct cfg80211_ibss_params *params,
-			 struct cfg80211_cached_keys *connkeys);
 int cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 		       struct net_device *dev,
 		       struct cfg80211_ibss_params *params,
@@ -259,7 +266,8 @@ int __cfg80211_leave_ibss(struct cfg80211_registered_device *rdev,
 			  struct net_device *dev, bool nowext);
 int cfg80211_leave_ibss(struct cfg80211_registered_device *rdev,
 			struct net_device *dev, bool nowext);
-void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid);
+void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid,
+			    struct ieee80211_channel *channel);
 int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev,
 			    struct wireless_dev *wdev);
 
@@ -274,6 +282,8 @@ int cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 		       struct net_device *dev,
 		       struct mesh_setup *setup,
 		       const struct mesh_config *conf);
+int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
+			  struct net_device *dev);
 int cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
 			struct net_device *dev);
 int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
@@ -281,8 +291,10 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
 			      struct cfg80211_chan_def *chandef);
 
 /* AP */
+int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
+		       struct net_device *dev, bool notify);
 int cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
-		     struct net_device *dev);
+		     struct net_device *dev, bool notify);
 
 /* MLME */
 int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
@@ -363,7 +375,8 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 				   struct key_params *params, int key_idx,
 				   bool pairwise, const u8 *mac_addr);
 void __cfg80211_scan_done(struct work_struct *wk);
-void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak);
+void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
+			   bool send_message);
 void __cfg80211_sched_scan_results(struct work_struct *wk);
 int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
 			       bool driver_initiated);
@@ -400,35 +413,9 @@ void cfg80211_set_dfs_state(struct wiphy *wiphy,
 
 void cfg80211_dfs_channels_update_work(struct work_struct *work);
 
-
-static inline int
-cfg80211_can_change_interface(struct cfg80211_registered_device *rdev,
-			      struct wireless_dev *wdev,
-			      enum nl80211_iftype iftype)
-{
-	return cfg80211_can_use_iftype_chan(rdev, wdev, iftype, NULL,
-					    CHAN_MODE_UNDEFINED, 0);
-}
-
-static inline int
-cfg80211_can_add_interface(struct cfg80211_registered_device *rdev,
-			   enum nl80211_iftype iftype)
-{
-	if (rfkill_blocked(rdev->rfkill))
-		return -ERFKILL;
-
-	return cfg80211_can_change_interface(rdev, NULL, iftype);
-}
-
-static inline int
-cfg80211_can_use_chan(struct cfg80211_registered_device *rdev,
-		      struct wireless_dev *wdev,
-		      struct ieee80211_channel *chan,
-		      enum cfg80211_chan_mode chanmode)
-{
-	return cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
-					    chan, chanmode, 0);
-}
+unsigned int
+cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy,
+			      const struct cfg80211_chan_def *chandef);
 
 static inline unsigned int elapsed_jiffies_msecs(unsigned long start)
 {
@@ -437,13 +424,14 @@ static inline unsigned int elapsed_jiffies_msecs(unsigned long start)
 	if (end >= start)
 		return jiffies_to_msecs(end - start);
 
-	return jiffies_to_msecs(end + (MAX_JIFFY_OFFSET - start) + 1);
+	return jiffies_to_msecs(end + (ULONG_MAX - start) + 1);
 }
 
 void
 cfg80211_get_chan_state(struct wireless_dev *wdev,
 		        struct ieee80211_channel **chan,
-		        enum cfg80211_chan_mode *chanmode);
+		        enum cfg80211_chan_mode *chanmode,
+		        u8 *radar_detect);
 
 int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev,
 				 struct cfg80211_chan_def *chandef);
@@ -458,6 +446,8 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
 void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev,
 			       enum nl80211_iftype iftype, int num);
 
+void __cfg80211_leave(struct cfg80211_registered_device *rdev,
+		      struct wireless_dev *wdev);
 void cfg80211_leave(struct cfg80211_registered_device *rdev,
 		    struct wireless_dev *wdev);
 
diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c
index e37862f1b12..d4860bfc020 100644
--- a/net/wireless/ethtool.c
+++ b/net/wireless/ethtool.c
@@ -43,7 +43,7 @@ static void cfg80211_get_ringparam(struct net_device *dev,
 				   struct ethtool_ringparam *rp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	memset(rp, 0, sizeof(*rp));
 
@@ -56,7 +56,7 @@ static int cfg80211_set_ringparam(struct net_device *dev,
 				  struct ethtool_ringparam *rp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (rp->rx_mini_pending != 0 || rp->rx_jumbo_pending != 0)
 		return -EINVAL;
@@ -70,7 +70,7 @@ static int cfg80211_set_ringparam(struct net_device *dev,
 static int cfg80211_get_sset_count(struct net_device *dev, int sset)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	if (rdev->ops->get_et_sset_count)
 		return rdev_get_et_sset_count(rdev, dev, sset);
 	return -EOPNOTSUPP;
@@ -80,7 +80,7 @@ static void cfg80211_get_stats(struct net_device *dev,
 			       struct ethtool_stats *stats, u64 *data)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	if (rdev->ops->get_et_stats)
 		rdev_get_et_stats(rdev, dev, stats, data);
 }
@@ -88,7 +88,7 @@ static void cfg80211_get_stats(struct net_device *dev,
 static void cfg80211_get_strings(struct net_device *dev, u32 sset, u8 *data)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	if (rdev->ops->get_et_strings)
 		rdev_get_et_strings(rdev, dev, sset, data);
 }
diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk
index 9a8217d2a90..40c37fc5b67 100644
--- a/net/wireless/genregdb.awk
+++ b/net/wireless/genregdb.awk
@@ -66,19 +66,15 @@ function parse_reg_rule()
 	units = $8
 	sub(/\)/, "", units)
 	sub(/,/, "", units)
+	dfs_cac = $9
 	if (units == "mW") {
-		if (power == 100) {
-			power = 20
-		} else if (power == 200) {
-			power = 23
-		} else if (power == 500) {
-			power = 27
-		} else if (power == 1000) {
-			power = 30
-		} else {
-			print "Unknown power value in database!"
-		}
+		power = 10 * log(power)/log(10)
+	} else {
+		dfs_cac = $8
 	}
+	sub(/,/, "", dfs_cac)
+	sub(/\(/, "", dfs_cac)
+	sub(/\)/, "", dfs_cac)
 	flagstr = ""
 	for (i=8; i<=NF; i++)
 		flagstr = flagstr $i
@@ -105,11 +101,13 @@ function parse_reg_rule()
 			flags = flags "\n\t\t\tNL80211_RRF_NO_IR | "
 		} else if (flagarray[arg] == "NO-IR") {
 			flags = flags "\n\t\t\tNL80211_RRF_NO_IR | "
+		} else if (flagarray[arg] == "AUTO-BW") {
+			flags = flags "\n\t\t\tNL80211_RRF_AUTO_BW | "
 		}
 
 	}
 	flags = flags "0"
-	printf "\t\tREG_RULE(%d, %d, %d, %d, %d, %s),\n", start, end, bw, gain, power, flags
+	printf "\t\tREG_RULE_EXT(%d, %d, %d, %d, %.0f, %d, %s),\n", start, end, bw, gain, power, dfs_cac, flags
 	rules++
 }
 
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index 730147ed8e6..8f345da3ea5 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -14,7 +14,8 @@
 #include "rdev-ops.h"
 
 
-void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid)
+void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid,
+			    struct ieee80211_channel *channel)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_bss *bss;
@@ -28,8 +29,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid)
 	if (!wdev->ssid_len)
 		return;
 
-	bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid,
-			       wdev->ssid, wdev->ssid_len,
+	bss = cfg80211_get_bss(wdev->wiphy, channel, bssid, NULL, 0,
 			       WLAN_CAPABILITY_IBSS, WLAN_CAPABILITY_IBSS);
 
 	if (WARN_ON(!bss))
@@ -45,7 +45,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid)
 
 	cfg80211_upload_connect_keys(wdev);
 
-	nl80211_send_ibss_bssid(wiphy_to_dev(wdev->wiphy), dev, bssid,
+	nl80211_send_ibss_bssid(wiphy_to_rdev(wdev->wiphy), dev, bssid,
 				GFP_KERNEL);
 #ifdef CONFIG_CFG80211_WEXT
 	memset(&wrqu, 0, sizeof(wrqu));
@@ -54,21 +54,26 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid)
 #endif
 }
 
-void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp)
+void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid,
+			  struct ieee80211_channel *channel, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_event *ev;
 	unsigned long flags;
 
-	trace_cfg80211_ibss_joined(dev, bssid);
+	trace_cfg80211_ibss_joined(dev, bssid, channel);
+
+	if (WARN_ON(!channel))
+		return;
 
 	ev = kzalloc(sizeof(*ev), gfp);
 	if (!ev)
 		return;
 
 	ev->type = EVENT_IBSS_JOINED;
-	memcpy(ev->cr.bssid, bssid, ETH_ALEN);
+	memcpy(ev->ij.bssid, bssid, ETH_ALEN);
+	ev->ij.channel = channel;
 
 	spin_lock_irqsave(&wdev->event_lock, flags);
 	list_add_tail(&ev->list, &wdev->event_list);
@@ -77,14 +82,12 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp)
 }
 EXPORT_SYMBOL(cfg80211_ibss_joined);
 
-int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
-			 struct net_device *dev,
-			 struct cfg80211_ibss_params *params,
-			 struct cfg80211_cached_keys *connkeys)
+static int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
+				struct net_device *dev,
+				struct cfg80211_ibss_params *params,
+				struct cfg80211_cached_keys *connkeys)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct ieee80211_channel *check_chan;
-	u8 radar_detect_width = 0;
 	int err;
 
 	ASSERT_WDEV_LOCK(wdev);
@@ -117,32 +120,10 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 
 	wdev->ibss_fixed = params->channel_fixed;
 	wdev->ibss_dfs_possible = params->userspace_handles_dfs;
+	wdev->chandef = params->chandef;
 #ifdef CONFIG_CFG80211_WEXT
 	wdev->wext.ibss.chandef = params->chandef;
 #endif
-	check_chan = params->chandef.chan;
-	if (params->userspace_handles_dfs) {
-		/* use channel NULL to check for radar even if the current
-		 * channel is not a radar channel - it might decide to change
-		 * to DFS channel later.
-		 */
-		radar_detect_width = BIT(params->chandef.width);
-		check_chan = NULL;
-	}
-
-	err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
-					   check_chan,
-					   (params->channel_fixed &&
-					    !radar_detect_width)
-					   ? CHAN_MODE_SHARED
-					   : CHAN_MODE_EXCLUSIVE,
-					   radar_detect_width);
-
-	if (err) {
-		wdev->connect_keys = NULL;
-		return err;
-	}
-
 	err = rdev_join_ibss(rdev, dev, params);
 	if (err) {
 		wdev->connect_keys = NULL;
@@ -175,7 +156,7 @@ int cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int i;
 
 	ASSERT_WDEV_LOCK(wdev);
@@ -183,6 +164,8 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext)
 	kfree(wdev->connect_keys);
 	wdev->connect_keys = NULL;
 
+	rdev_set_qos_map(rdev, dev, NULL);
+
 	/*
 	 * Delete all the keys ... pairwise keys can't really
 	 * exist any more anyway, but default keys might.
@@ -198,6 +181,7 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext)
 
 	wdev->current_bss = NULL;
 	wdev->ssid_len = 0;
+	memset(&wdev->chandef, 0, sizeof(wdev->chandef));
 #ifdef CONFIG_CFG80211_WEXT
 	if (!nowext)
 		wdev->wext.ibss.ssid_len = 0;
@@ -327,7 +311,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
 			       struct iw_freq *wextfreq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct ieee80211_channel *chan = NULL;
 	int err, freq;
 
@@ -338,7 +322,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
 	if (!rdev->ops->join_ibss)
 		return -EOPNOTSUPP;
 
-	freq = cfg80211_wext_freq(wdev->wiphy, wextfreq);
+	freq = cfg80211_wext_freq(wextfreq);
 	if (freq < 0)
 		return freq;
 
@@ -412,7 +396,7 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev,
 				struct iw_point *data, char *ssid)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	size_t len = data->length;
 	int err;
 
@@ -436,8 +420,8 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev,
 	if (len > 0 && ssid[len - 1] == '\0')
 		len--;
 
+	memcpy(wdev->ssid, ssid, len);
 	wdev->wext.ibss.ssid = wdev->ssid;
-	memcpy(wdev->wext.ibss.ssid, ssid, len);
 	wdev->wext.ibss.ssid_len = len;
 
 	wdev_lock(wdev);
@@ -479,7 +463,7 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev,
 			     struct sockaddr *ap_addr, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u8 *bssid = ap_addr->sa_data;
 	int err;
 
@@ -497,6 +481,9 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev,
 	if (is_zero_ether_addr(bssid) || is_broadcast_ether_addr(bssid))
 		bssid = NULL;
 
+	if (bssid && !is_valid_ether_addr(bssid))
+		return -EINVAL;
+
 	/* both automatic */
 	if (!bssid && !wdev->wext.ibss.bssid)
 		return 0;
diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
index b0e1869de7d..092300b30c3 100644
--- a/net/wireless/mesh.c
+++ b/net/wireless/mesh.c
@@ -174,19 +174,15 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 							       scan_width);
 	}
 
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &setup->chandef))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &setup->chandef,
+				     NL80211_IFTYPE_MESH_POINT))
 		return -EINVAL;
 
-	err = cfg80211_can_use_chan(rdev, wdev, setup->chandef.chan,
-				    CHAN_MODE_SHARED);
-	if (err)
-		return err;
-
 	err = rdev_join_mesh(rdev, dev, conf, setup);
 	if (!err) {
 		memcpy(wdev->ssid, setup->mesh_id, setup->mesh_id_len);
 		wdev->mesh_id_len = setup->mesh_id_len;
-		wdev->channel = setup->chandef.chan;
+		wdev->chandef = setup->chandef;
 	}
 
 	return err;
@@ -227,15 +223,10 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
 		if (!netif_running(wdev->netdev))
 			return -ENETDOWN;
 
-		err = cfg80211_can_use_chan(rdev, wdev, chandef->chan,
-					    CHAN_MODE_SHARED);
-		if (err)
-			return err;
-
 		err = rdev_libertas_set_mesh_channel(rdev, wdev->netdev,
 						     chandef->chan);
 		if (!err)
-			wdev->channel = chandef->chan;
+			wdev->chandef = *chandef;
 
 		return err;
 	}
@@ -247,8 +238,8 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
 	return 0;
 }
 
-static int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
-				 struct net_device *dev)
+int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
+			  struct net_device *dev)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	int err;
@@ -267,7 +258,8 @@ static int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
 	err = rdev_leave_mesh(rdev, dev);
 	if (!err) {
 		wdev->mesh_id_len = 0;
-		wdev->channel = NULL;
+		memset(&wdev->chandef, 0, sizeof(wdev->chandef));
+		rdev_set_qos_map(rdev, dev, NULL);
 	}
 
 	return err;
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 52cca05044a..266766b8d80 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -23,7 +23,7 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	u8 *ie = mgmt->u.assoc_resp.variable;
 	int ieoffs = offsetof(struct ieee80211_mgmt, u.assoc_resp.variable);
@@ -54,7 +54,7 @@ EXPORT_SYMBOL(cfg80211_rx_assoc_resp);
 static void cfg80211_process_auth(struct wireless_dev *wdev,
 				  const u8 *buf, size_t len)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	nl80211_send_rx_auth(rdev, wdev->netdev, buf, len, GFP_KERNEL);
 	cfg80211_sme_rx_auth(wdev, buf, len);
@@ -63,7 +63,7 @@ static void cfg80211_process_auth(struct wireless_dev *wdev,
 static void cfg80211_process_deauth(struct wireless_dev *wdev,
 				    const u8 *buf, size_t len)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	const u8 *bssid = mgmt->bssid;
 	u16 reason_code = le16_to_cpu(mgmt->u.deauth.reason_code);
@@ -82,7 +82,7 @@ static void cfg80211_process_deauth(struct wireless_dev *wdev,
 static void cfg80211_process_disassoc(struct wireless_dev *wdev,
 				      const u8 *buf, size_t len)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	const u8 *bssid = mgmt->bssid;
 	u16 reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code);
@@ -123,7 +123,7 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_send_auth_timeout(dev, addr);
 
@@ -136,7 +136,7 @@ void cfg80211_assoc_timeout(struct net_device *dev, struct cfg80211_bss *bss)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_send_assoc_timeout(dev, bss->bssid);
 
@@ -172,7 +172,7 @@ void cfg80211_michael_mic_failure(struct net_device *dev, const u8 *addr,
 				  const u8 *tsc, gfp_t gfp)
 {
 	struct wiphy *wiphy = dev->ieee80211_ptr->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 #ifdef CONFIG_CFG80211_WEXT
 	union iwreq_data wrqu;
 	char *buf = kmalloc(128, gfp);
@@ -233,14 +233,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
 	if (!req.bss)
 		return -ENOENT;
 
-	err = cfg80211_can_use_chan(rdev, wdev, req.bss->channel,
-				    CHAN_MODE_SHARED);
-	if (err)
-		goto out;
-
 	err = rdev_auth(rdev, dev, &req);
 
-out:
 	cfg80211_put_bss(&rdev->wiphy, req.bss);
 	return err;
 }
@@ -306,16 +300,10 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev,
 	if (!req->bss)
 		return -ENOENT;
 
-	err = cfg80211_can_use_chan(rdev, wdev, chan, CHAN_MODE_SHARED);
-	if (err)
-		goto out;
-
 	err = rdev_assoc(rdev, dev, req);
 	if (!err)
 		cfg80211_hold_bss(bss_from_pub(req->bss));
-
-out:
-	if (err)
+	else
 		cfg80211_put_bss(&rdev->wiphy, req->bss);
 
 	return err;
@@ -414,7 +402,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
 				int match_len)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_mgmt_registration *reg, *nreg;
 	int err = 0;
 	u16 mgmt_type;
@@ -473,7 +461,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
 void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_mgmt_registration *reg, *tmp;
 
 	spin_lock_bh(&wdev->mgmt_registrations_lock);
@@ -620,7 +608,7 @@ bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm,
 		      const u8 *buf, size_t len, u32 flags, gfp_t gfp)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_mgmt_registration *reg;
 	const struct ieee80211_txrx_stypes *stypes =
 		&wiphy->mgmt_stypes[wdev->iftype];
@@ -739,7 +727,7 @@ void cfg80211_radar_event(struct wiphy *wiphy,
 			  struct cfg80211_chan_def *chandef,
 			  gfp_t gfp)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	unsigned long timeout;
 
 	trace_cfg80211_radar_event(wiphy, chandef);
@@ -764,7 +752,7 @@ void cfg80211_cac_event(struct net_device *netdev,
 {
 	struct wireless_dev *wdev = netdev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	unsigned long timeout;
 
 	trace_cfg80211_cac_event(netdev, event);
@@ -772,13 +760,13 @@ void cfg80211_cac_event(struct net_device *netdev,
 	if (WARN_ON(!wdev->cac_started))
 		return;
 
-	if (WARN_ON(!wdev->channel))
+	if (WARN_ON(!wdev->chandef.chan))
 		return;
 
 	switch (event) {
 	case NL80211_RADAR_CAC_FINISHED:
 		timeout = wdev->cac_start_time +
-			  msecs_to_jiffies(IEEE80211_DFS_MIN_CAC_TIME_MS);
+			  msecs_to_jiffies(wdev->cac_time_ms);
 		WARN_ON(!time_after_eq(jiffies, timeout));
 		cfg80211_set_dfs_state(wiphy, chandef, NL80211_DFS_AVAILABLE);
 		break;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index a693f86e597..6668daf6932 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -53,6 +53,7 @@ enum nl80211_multicast_groups {
 	NL80211_MCGRP_SCAN,
 	NL80211_MCGRP_REGULATORY,
 	NL80211_MCGRP_MLME,
+	NL80211_MCGRP_VENDOR,
 	NL80211_MCGRP_TESTMODE /* keep last - ifdef! */
 };
 
@@ -61,6 +62,7 @@ static const struct genl_multicast_group nl80211_mcgrps[] = {
 	[NL80211_MCGRP_SCAN] = { .name = "scan", },
 	[NL80211_MCGRP_REGULATORY] = { .name = "regulatory", },
 	[NL80211_MCGRP_MLME] = { .name = "mlme", },
+	[NL80211_MCGRP_VENDOR] = { .name = "vendor", },
 #ifdef CONFIG_NL80211_TESTMODE
 	[NL80211_MCGRP_TESTMODE] = { .name = "testmode", }
 #endif
@@ -163,16 +165,14 @@ __cfg80211_rdev_from_attrs(struct net *netns, struct nlattr **attrs)
 
 	if (attrs[NL80211_ATTR_IFINDEX]) {
 		int ifindex = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]);
-		netdev = dev_get_by_index(netns, ifindex);
+		netdev = __dev_get_by_index(netns, ifindex);
 		if (netdev) {
 			if (netdev->ieee80211_ptr)
-				tmp = wiphy_to_dev(
-						netdev->ieee80211_ptr->wiphy);
+				tmp = wiphy_to_rdev(
+					netdev->ieee80211_ptr->wiphy);
 			else
 				tmp = NULL;
 
-			dev_put(netdev);
-
 			/* not wireless device -- return error */
 			if (!tmp)
 				return ERR_PTR(-EINVAL);
@@ -371,11 +371,22 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 },
 	[NL80211_ATTR_CH_SWITCH_BLOCK_TX] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CSA_IES] = { .type = NLA_NESTED },
-	[NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_U16 },
-	[NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_U16 },
+	[NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_BINARY },
+	[NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_BINARY },
 	[NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY },
 	[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY },
 	[NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG },
+	[NL80211_ATTR_OPMODE_NOTIF] = { .type = NLA_U8 },
+	[NL80211_ATTR_VENDOR_ID] = { .type = NLA_U32 },
+	[NL80211_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 },
+	[NL80211_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },
+	[NL80211_ATTR_QOS_MAP] = { .type = NLA_BINARY,
+				   .len = IEEE80211_QOS_MAP_LEN_MAX },
+	[NL80211_ATTR_MAC_HINT] = { .len = ETH_ALEN },
+	[NL80211_ATTR_WIPHY_FREQ_HINT] = { .type = NLA_U32 },
+	[NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 },
+	[NL80211_ATTR_IFACE_SOCKET_OWNER] = { .type = NLA_FLAG },
+	[NL80211_ATTR_CSA_C_OFFSETS_TX] = { .type = NLA_BINARY },
 };
 
 /* policy for the key attributes */
@@ -475,7 +486,7 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 			err = PTR_ERR(*wdev);
 			goto out_unlock;
 		}
-		*rdev = wiphy_to_dev((*wdev)->wiphy);
+		*rdev = wiphy_to_rdev((*wdev)->wiphy);
 		/* 0 is the first index - add 1 to parse only once */
 		cb->args[0] = (*rdev)->wiphy_idx + 1;
 		cb->args[1] = (*wdev)->identifier;
@@ -488,7 +499,7 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 			err = -ENODEV;
 			goto out_unlock;
 		}
-		*rdev = wiphy_to_dev(wiphy);
+		*rdev = wiphy_to_rdev(wiphy);
 		*wdev = NULL;
 
 		list_for_each_entry(tmp, &(*rdev)->wdev_list, list) {
@@ -557,6 +568,13 @@ static int nl80211_msg_put_channel(struct sk_buff *msg,
 				   struct ieee80211_channel *chan,
 				   bool large)
 {
+	/* Some channels must be completely excluded from the
+	 * list to protect old user-space tools from breaking
+	 */
+	if (!large && chan->flags &
+	    (IEEE80211_CHAN_NO_10MHZ | IEEE80211_CHAN_NO_20MHZ))
+		return 0;
+
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_FREQ,
 			chan->center_freq))
 		goto nla_put_failure;
@@ -584,6 +602,10 @@ static int nl80211_msg_put_channel(struct sk_buff *msg,
 			if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_DFS_TIME,
 					time))
 				goto nla_put_failure;
+			if (nla_put_u32(msg,
+					NL80211_FREQUENCY_ATTR_DFS_CAC_TIME,
+					chan->dfs_cac_ms))
+				goto nla_put_failure;
 		}
 	}
 
@@ -600,6 +622,18 @@ static int nl80211_msg_put_channel(struct sk_buff *msg,
 		if ((chan->flags & IEEE80211_CHAN_NO_160MHZ) &&
 		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_160MHZ))
 			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_INDOOR_ONLY) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_INDOOR_ONLY))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_GO_CONCURRENT) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_GO_CONCURRENT))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_NO_20MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_20MHZ))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_NO_10MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_10MHZ))
+			goto nla_put_failure;
 	}
 
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER,
@@ -849,6 +883,19 @@ static int nl80211_key_allowed(struct wireless_dev *wdev)
 	return 0;
 }
 
+static struct ieee80211_channel *nl80211_get_valid_chan(struct wiphy *wiphy,
+							struct nlattr *tb)
+{
+	struct ieee80211_channel *chan;
+
+	if (tb == NULL)
+		return NULL;
+	chan = ieee80211_get_channel(wiphy, nla_get_u32(tb));
+	if (!chan || chan->flags & IEEE80211_CHAN_DISABLED)
+		return NULL;
+	return chan;
+}
+
 static int nl80211_put_iftypes(struct sk_buff *msg, u32 attr, u16 ifmodes)
 {
 	struct nlattr *nl_modes = nla_nest_start(msg, attr);
@@ -924,8 +971,10 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy,
 				c->max_interfaces))
 			goto nla_put_failure;
 		if (large &&
-		    nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS,
-				c->radar_detect_widths))
+		    (nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS,
+				c->radar_detect_widths) ||
+		     nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_REGIONS,
+				c->radar_detect_regions)))
 			goto nla_put_failure;
 
 		nla_nest_end(msg, nl_combi);
@@ -980,42 +1029,42 @@ static int nl80211_send_wowlan_tcp_caps(struct cfg80211_registered_device *rdev,
 }
 
 static int nl80211_send_wowlan(struct sk_buff *msg,
-			       struct cfg80211_registered_device *dev,
+			       struct cfg80211_registered_device *rdev,
 			       bool large)
 {
 	struct nlattr *nl_wowlan;
 
-	if (!dev->wiphy.wowlan)
+	if (!rdev->wiphy.wowlan)
 		return 0;
 
 	nl_wowlan = nla_nest_start(msg, NL80211_ATTR_WOWLAN_TRIGGERS_SUPPORTED);
 	if (!nl_wowlan)
 		return -ENOBUFS;
 
-	if (((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_ANY) &&
+	if (((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_ANY) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_ANY)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_DISCONNECT) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_DISCONNECT) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_DISCONNECT)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_MAGIC_PKT) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_MAGIC_PKT) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_MAGIC_PKT)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_SUPPORTS_GTK_REKEY) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_SUPPORTS_GTK_REKEY) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_GTK_REKEY_SUPPORTED)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_GTK_REKEY_FAILURE)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_EAP_IDENTITY_REQ) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_EAP_IDENTITY_REQ) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_EAP_IDENT_REQUEST)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_4WAY_HANDSHAKE) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_4WAY_HANDSHAKE) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_RFKILL_RELEASE) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_RFKILL_RELEASE) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_RFKILL_RELEASE)))
 		return -ENOBUFS;
 
-	if (dev->wiphy.wowlan->n_patterns) {
+	if (rdev->wiphy.wowlan->n_patterns) {
 		struct nl80211_pattern_support pat = {
-			.max_patterns = dev->wiphy.wowlan->n_patterns,
-			.min_pattern_len = dev->wiphy.wowlan->pattern_min_len,
-			.max_pattern_len = dev->wiphy.wowlan->pattern_max_len,
-			.max_pkt_offset = dev->wiphy.wowlan->max_pkt_offset,
+			.max_patterns = rdev->wiphy.wowlan->n_patterns,
+			.min_pattern_len = rdev->wiphy.wowlan->pattern_min_len,
+			.max_pattern_len = rdev->wiphy.wowlan->pattern_max_len,
+			.max_pkt_offset = rdev->wiphy.wowlan->max_pkt_offset,
 		};
 
 		if (nla_put(msg, NL80211_WOWLAN_TRIG_PKT_PATTERN,
@@ -1023,7 +1072,7 @@ static int nl80211_send_wowlan(struct sk_buff *msg,
 			return -ENOBUFS;
 	}
 
-	if (large && nl80211_send_wowlan_tcp_caps(dev, msg))
+	if (large && nl80211_send_wowlan_tcp_caps(rdev, msg))
 		return -ENOBUFS;
 
 	nla_nest_end(msg, nl_wowlan);
@@ -1033,19 +1082,19 @@ static int nl80211_send_wowlan(struct sk_buff *msg,
 #endif
 
 static int nl80211_send_coalesce(struct sk_buff *msg,
-				 struct cfg80211_registered_device *dev)
+				 struct cfg80211_registered_device *rdev)
 {
 	struct nl80211_coalesce_rule_support rule;
 
-	if (!dev->wiphy.coalesce)
+	if (!rdev->wiphy.coalesce)
 		return 0;
 
-	rule.max_rules = dev->wiphy.coalesce->n_rules;
-	rule.max_delay = dev->wiphy.coalesce->max_delay;
-	rule.pat.max_patterns = dev->wiphy.coalesce->n_patterns;
-	rule.pat.min_pattern_len = dev->wiphy.coalesce->pattern_min_len;
-	rule.pat.max_pattern_len = dev->wiphy.coalesce->pattern_max_len;
-	rule.pat.max_pkt_offset = dev->wiphy.coalesce->max_pkt_offset;
+	rule.max_rules = rdev->wiphy.coalesce->n_rules;
+	rule.max_delay = rdev->wiphy.coalesce->max_delay;
+	rule.pat.max_patterns = rdev->wiphy.coalesce->n_patterns;
+	rule.pat.min_pattern_len = rdev->wiphy.coalesce->pattern_min_len;
+	rule.pat.max_pattern_len = rdev->wiphy.coalesce->pattern_max_len;
+	rule.pat.max_pkt_offset = rdev->wiphy.coalesce->max_pkt_offset;
 
 	if (nla_put(msg, NL80211_ATTR_COALESCE_RULE, sizeof(rule), &rule))
 		return -ENOBUFS;
@@ -1176,7 +1225,8 @@ struct nl80211_dump_wiphy_state {
 	bool split;
 };
 
-static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
+static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
+			      enum nl80211_commands cmd,
 			      struct sk_buff *msg, u32 portid, u32 seq,
 			      int flags, struct nl80211_dump_wiphy_state *state)
 {
@@ -1188,63 +1238,66 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 	struct ieee80211_channel *chan;
 	int i;
 	const struct ieee80211_txrx_stypes *mgmt_stypes =
-				dev->wiphy.mgmt_stypes;
+				rdev->wiphy.mgmt_stypes;
 	u32 features;
 
-	hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_WIPHY);
+	hdr = nl80211hdr_put(msg, portid, seq, flags, cmd);
 	if (!hdr)
 		return -ENOBUFS;
 
 	if (WARN_ON(!state))
 		return -EINVAL;
 
-	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, dev->wiphy_idx) ||
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
 	    nla_put_string(msg, NL80211_ATTR_WIPHY_NAME,
-			   wiphy_name(&dev->wiphy)) ||
+			   wiphy_name(&rdev->wiphy)) ||
 	    nla_put_u32(msg, NL80211_ATTR_GENERATION,
 			cfg80211_rdev_list_generation))
 		goto nla_put_failure;
 
+	if (cmd != NL80211_CMD_NEW_WIPHY)
+		goto finish;
+
 	switch (state->split_start) {
 	case 0:
 		if (nla_put_u8(msg, NL80211_ATTR_WIPHY_RETRY_SHORT,
-			       dev->wiphy.retry_short) ||
+			       rdev->wiphy.retry_short) ||
 		    nla_put_u8(msg, NL80211_ATTR_WIPHY_RETRY_LONG,
-			       dev->wiphy.retry_long) ||
+			       rdev->wiphy.retry_long) ||
 		    nla_put_u32(msg, NL80211_ATTR_WIPHY_FRAG_THRESHOLD,
-				dev->wiphy.frag_threshold) ||
+				rdev->wiphy.frag_threshold) ||
 		    nla_put_u32(msg, NL80211_ATTR_WIPHY_RTS_THRESHOLD,
-				dev->wiphy.rts_threshold) ||
+				rdev->wiphy.rts_threshold) ||
 		    nla_put_u8(msg, NL80211_ATTR_WIPHY_COVERAGE_CLASS,
-			       dev->wiphy.coverage_class) ||
+			       rdev->wiphy.coverage_class) ||
 		    nla_put_u8(msg, NL80211_ATTR_MAX_NUM_SCAN_SSIDS,
-			       dev->wiphy.max_scan_ssids) ||
+			       rdev->wiphy.max_scan_ssids) ||
 		    nla_put_u8(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_SSIDS,
-			       dev->wiphy.max_sched_scan_ssids) ||
+			       rdev->wiphy.max_sched_scan_ssids) ||
 		    nla_put_u16(msg, NL80211_ATTR_MAX_SCAN_IE_LEN,
-				dev->wiphy.max_scan_ie_len) ||
+				rdev->wiphy.max_scan_ie_len) ||
 		    nla_put_u16(msg, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN,
-				dev->wiphy.max_sched_scan_ie_len) ||
+				rdev->wiphy.max_sched_scan_ie_len) ||
 		    nla_put_u8(msg, NL80211_ATTR_MAX_MATCH_SETS,
-			       dev->wiphy.max_match_sets))
+			       rdev->wiphy.max_match_sets))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) &&
 		    nla_put_flag(msg, NL80211_ATTR_SUPPORT_IBSS_RSN))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_MESH_AUTH) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_MESH_AUTH) &&
 		    nla_put_flag(msg, NL80211_ATTR_SUPPORT_MESH_AUTH))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_AP_UAPSD) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_AP_UAPSD) &&
 		    nla_put_flag(msg, NL80211_ATTR_SUPPORT_AP_UAPSD))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_FW_ROAM) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_FW_ROAM) &&
 		    nla_put_flag(msg, NL80211_ATTR_ROAM_SUPPORT))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) &&
 		    nla_put_flag(msg, NL80211_ATTR_TDLS_SUPPORT))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_TDLS_EXTERNAL_SETUP) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_TDLS_EXTERNAL_SETUP) &&
 		    nla_put_flag(msg, NL80211_ATTR_TDLS_EXTERNAL_SETUP))
 			goto nla_put_failure;
 		state->split_start++;
@@ -1252,35 +1305,35 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 			break;
 	case 1:
 		if (nla_put(msg, NL80211_ATTR_CIPHER_SUITES,
-			    sizeof(u32) * dev->wiphy.n_cipher_suites,
-			    dev->wiphy.cipher_suites))
+			    sizeof(u32) * rdev->wiphy.n_cipher_suites,
+			    rdev->wiphy.cipher_suites))
 			goto nla_put_failure;
 
 		if (nla_put_u8(msg, NL80211_ATTR_MAX_NUM_PMKIDS,
-			       dev->wiphy.max_num_pmkids))
+			       rdev->wiphy.max_num_pmkids))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.flags & WIPHY_FLAG_CONTROL_PORT_PROTOCOL) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_CONTROL_PORT_PROTOCOL) &&
 		    nla_put_flag(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE))
 			goto nla_put_failure;
 
 		if (nla_put_u32(msg, NL80211_ATTR_WIPHY_ANTENNA_AVAIL_TX,
-				dev->wiphy.available_antennas_tx) ||
+				rdev->wiphy.available_antennas_tx) ||
 		    nla_put_u32(msg, NL80211_ATTR_WIPHY_ANTENNA_AVAIL_RX,
-				dev->wiphy.available_antennas_rx))
+				rdev->wiphy.available_antennas_rx))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.flags & WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD) &&
 		    nla_put_u32(msg, NL80211_ATTR_PROBE_RESP_OFFLOAD,
-				dev->wiphy.probe_resp_offload))
+				rdev->wiphy.probe_resp_offload))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.available_antennas_tx ||
-		     dev->wiphy.available_antennas_rx) &&
-		    dev->ops->get_antenna) {
+		if ((rdev->wiphy.available_antennas_tx ||
+		     rdev->wiphy.available_antennas_rx) &&
+		    rdev->ops->get_antenna) {
 			u32 tx_ant = 0, rx_ant = 0;
 			int res;
-			res = rdev_get_antenna(dev, &tx_ant, &rx_ant);
+			res = rdev_get_antenna(rdev, &tx_ant, &rx_ant);
 			if (!res) {
 				if (nla_put_u32(msg,
 						NL80211_ATTR_WIPHY_ANTENNA_TX,
@@ -1297,7 +1350,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 			break;
 	case 2:
 		if (nl80211_put_iftypes(msg, NL80211_ATTR_SUPPORTED_IFTYPES,
-					dev->wiphy.interface_modes))
+					rdev->wiphy.interface_modes))
 				goto nla_put_failure;
 		state->split_start++;
 		if (state->split)
@@ -1311,7 +1364,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		     band < IEEE80211_NUM_BANDS; band++) {
 			struct ieee80211_supported_band *sband;
 
-			sband = dev->wiphy.bands[band];
+			sband = rdev->wiphy.bands[band];
 
 			if (!sband)
 				continue;
@@ -1388,7 +1441,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		i = 0;
 #define CMD(op, n)							\
 		 do {							\
-			if (dev->ops->op) {				\
+			if (rdev->ops->op) {				\
 				i++;					\
 				if (nla_put_u32(msg, i, NL80211_CMD_ ## n)) \
 					goto nla_put_failure;		\
@@ -1412,58 +1465,58 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		CMD(set_pmksa, SET_PMKSA);
 		CMD(del_pmksa, DEL_PMKSA);
 		CMD(flush_pmksa, FLUSH_PMKSA);
-		if (dev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)
+		if (rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)
 			CMD(remain_on_channel, REMAIN_ON_CHANNEL);
 		CMD(set_bitrate_mask, SET_TX_BITRATE_MASK);
 		CMD(mgmt_tx, FRAME);
 		CMD(mgmt_tx_cancel_wait, FRAME_WAIT_CANCEL);
-		if (dev->wiphy.flags & WIPHY_FLAG_NETNS_OK) {
+		if (rdev->wiphy.flags & WIPHY_FLAG_NETNS_OK) {
 			i++;
 			if (nla_put_u32(msg, i, NL80211_CMD_SET_WIPHY_NETNS))
 				goto nla_put_failure;
 		}
-		if (dev->ops->set_monitor_channel || dev->ops->start_ap ||
-		    dev->ops->join_mesh) {
+		if (rdev->ops->set_monitor_channel || rdev->ops->start_ap ||
+		    rdev->ops->join_mesh) {
 			i++;
 			if (nla_put_u32(msg, i, NL80211_CMD_SET_CHANNEL))
 				goto nla_put_failure;
 		}
 		CMD(set_wds_peer, SET_WDS_PEER);
-		if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) {
+		if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) {
 			CMD(tdls_mgmt, TDLS_MGMT);
 			CMD(tdls_oper, TDLS_OPER);
 		}
-		if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
+		if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
 			CMD(sched_scan_start, START_SCHED_SCAN);
 		CMD(probe_client, PROBE_CLIENT);
 		CMD(set_noack_map, SET_NOACK_MAP);
-		if (dev->wiphy.flags & WIPHY_FLAG_REPORTS_OBSS) {
+		if (rdev->wiphy.flags & WIPHY_FLAG_REPORTS_OBSS) {
 			i++;
 			if (nla_put_u32(msg, i, NL80211_CMD_REGISTER_BEACONS))
 				goto nla_put_failure;
 		}
 		CMD(start_p2p_device, START_P2P_DEVICE);
 		CMD(set_mcast_rate, SET_MCAST_RATE);
+#ifdef CONFIG_NL80211_TESTMODE
+		CMD(testmode_cmd, TESTMODE);
+#endif
 		if (state->split) {
 			CMD(crit_proto_start, CRIT_PROTOCOL_START);
 			CMD(crit_proto_stop, CRIT_PROTOCOL_STOP);
-			if (dev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH)
+			if (rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH)
 				CMD(channel_switch, CHANNEL_SWITCH);
+			CMD(set_qos_map, SET_QOS_MAP);
 		}
-
-#ifdef CONFIG_NL80211_TESTMODE
-		CMD(testmode_cmd, TESTMODE);
-#endif
-
+		/* add into the if now */
 #undef CMD
 
-		if (dev->ops->connect || dev->ops->auth) {
+		if (rdev->ops->connect || rdev->ops->auth) {
 			i++;
 			if (nla_put_u32(msg, i, NL80211_CMD_CONNECT))
 				goto nla_put_failure;
 		}
 
-		if (dev->ops->disconnect || dev->ops->deauth) {
+		if (rdev->ops->disconnect || rdev->ops->deauth) {
 			i++;
 			if (nla_put_u32(msg, i, NL80211_CMD_DISCONNECT))
 				goto nla_put_failure;
@@ -1474,14 +1527,14 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		if (state->split)
 			break;
 	case 5:
-		if (dev->ops->remain_on_channel &&
-		    (dev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL) &&
+		if (rdev->ops->remain_on_channel &&
+		    (rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL) &&
 		    nla_put_u32(msg,
 				NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION,
-				dev->wiphy.max_remain_on_channel_duration))
+				rdev->wiphy.max_remain_on_channel_duration))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX) &&
 		    nla_put_flag(msg, NL80211_ATTR_OFFCHANNEL_TX_OK))
 			goto nla_put_failure;
 
@@ -1492,7 +1545,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 			break;
 	case 6:
 #ifdef CONFIG_PM
-		if (nl80211_send_wowlan(msg, dev, state->split))
+		if (nl80211_send_wowlan(msg, rdev, state->split))
 			goto nla_put_failure;
 		state->split_start++;
 		if (state->split)
@@ -1502,10 +1555,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 #endif
 	case 7:
 		if (nl80211_put_iftypes(msg, NL80211_ATTR_SOFTWARE_IFTYPES,
-					dev->wiphy.software_iftypes))
+					rdev->wiphy.software_iftypes))
 			goto nla_put_failure;
 
-		if (nl80211_put_iface_combinations(&dev->wiphy, msg,
+		if (nl80211_put_iface_combinations(&rdev->wiphy, msg,
 						   state->split))
 			goto nla_put_failure;
 
@@ -1513,12 +1566,12 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		if (state->split)
 			break;
 	case 8:
-		if ((dev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME) &&
 		    nla_put_u32(msg, NL80211_ATTR_DEVICE_AP_SME,
-				dev->wiphy.ap_sme_capa))
+				rdev->wiphy.ap_sme_capa))
 			goto nla_put_failure;
 
-		features = dev->wiphy.features;
+		features = rdev->wiphy.features;
 		/*
 		 * We can only add the per-channel limit information if the
 		 * dump is split, otherwise it makes it too big. Therefore
@@ -1529,16 +1582,16 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		if (nla_put_u32(msg, NL80211_ATTR_FEATURE_FLAGS, features))
 			goto nla_put_failure;
 
-		if (dev->wiphy.ht_capa_mod_mask &&
+		if (rdev->wiphy.ht_capa_mod_mask &&
 		    nla_put(msg, NL80211_ATTR_HT_CAPABILITY_MASK,
-			    sizeof(*dev->wiphy.ht_capa_mod_mask),
-			    dev->wiphy.ht_capa_mod_mask))
+			    sizeof(*rdev->wiphy.ht_capa_mod_mask),
+			    rdev->wiphy.ht_capa_mod_mask))
 			goto nla_put_failure;
 
-		if (dev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME &&
-		    dev->wiphy.max_acl_mac_addrs &&
+		if (rdev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME &&
+		    rdev->wiphy.max_acl_mac_addrs &&
 		    nla_put_u32(msg, NL80211_ATTR_MAC_ACL_MAX,
-				dev->wiphy.max_acl_mac_addrs))
+				rdev->wiphy.max_acl_mac_addrs))
 			goto nla_put_failure;
 
 		/*
@@ -1554,36 +1607,85 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		state->split_start++;
 		break;
 	case 9:
-		if (dev->wiphy.extended_capabilities &&
+		if (rdev->wiphy.extended_capabilities &&
 		    (nla_put(msg, NL80211_ATTR_EXT_CAPA,
-			     dev->wiphy.extended_capabilities_len,
-			     dev->wiphy.extended_capabilities) ||
+			     rdev->wiphy.extended_capabilities_len,
+			     rdev->wiphy.extended_capabilities) ||
 		     nla_put(msg, NL80211_ATTR_EXT_CAPA_MASK,
-			     dev->wiphy.extended_capabilities_len,
-			     dev->wiphy.extended_capabilities_mask)))
+			     rdev->wiphy.extended_capabilities_len,
+			     rdev->wiphy.extended_capabilities_mask)))
 			goto nla_put_failure;
 
-		if (dev->wiphy.vht_capa_mod_mask &&
+		if (rdev->wiphy.vht_capa_mod_mask &&
 		    nla_put(msg, NL80211_ATTR_VHT_CAPABILITY_MASK,
-			    sizeof(*dev->wiphy.vht_capa_mod_mask),
-			    dev->wiphy.vht_capa_mod_mask))
+			    sizeof(*rdev->wiphy.vht_capa_mod_mask),
+			    rdev->wiphy.vht_capa_mod_mask))
 			goto nla_put_failure;
 
 		state->split_start++;
 		break;
 	case 10:
-		if (nl80211_send_coalesce(msg, dev))
+		if (nl80211_send_coalesce(msg, rdev))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_5_10_MHZ) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_5_10_MHZ) &&
 		    (nla_put_flag(msg, NL80211_ATTR_SUPPORT_5_MHZ) ||
 		     nla_put_flag(msg, NL80211_ATTR_SUPPORT_10_MHZ)))
 			goto nla_put_failure;
 
+		if (rdev->wiphy.max_ap_assoc_sta &&
+		    nla_put_u32(msg, NL80211_ATTR_MAX_AP_ASSOC_STA,
+				rdev->wiphy.max_ap_assoc_sta))
+			goto nla_put_failure;
+
+		state->split_start++;
+		break;
+	case 11:
+		if (rdev->wiphy.n_vendor_commands) {
+			const struct nl80211_vendor_cmd_info *info;
+			struct nlattr *nested;
+
+			nested = nla_nest_start(msg, NL80211_ATTR_VENDOR_DATA);
+			if (!nested)
+				goto nla_put_failure;
+
+			for (i = 0; i < rdev->wiphy.n_vendor_commands; i++) {
+				info = &rdev->wiphy.vendor_commands[i].info;
+				if (nla_put(msg, i + 1, sizeof(*info), info))
+					goto nla_put_failure;
+			}
+			nla_nest_end(msg, nested);
+		}
+
+		if (rdev->wiphy.n_vendor_events) {
+			const struct nl80211_vendor_cmd_info *info;
+			struct nlattr *nested;
+
+			nested = nla_nest_start(msg,
+						NL80211_ATTR_VENDOR_EVENTS);
+			if (!nested)
+				goto nla_put_failure;
+
+			for (i = 0; i < rdev->wiphy.n_vendor_events; i++) {
+				info = &rdev->wiphy.vendor_events[i];
+				if (nla_put(msg, i + 1, sizeof(*info), info))
+					goto nla_put_failure;
+			}
+			nla_nest_end(msg, nested);
+		}
+		state->split_start++;
+		break;
+	case 12:
+		if (rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH &&
+		    nla_put_u8(msg, NL80211_ATTR_MAX_CSA_COUNTERS,
+			       rdev->wiphy.max_num_csa_counters))
+			goto nla_put_failure;
+
 		/* done */
 		state->split_start = 0;
 		break;
 	}
+ finish:
 	return genlmsg_end(msg, hdr);
 
  nla_put_failure:
@@ -1612,15 +1714,14 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb,
 		struct cfg80211_registered_device *rdev;
 		int ifidx = nla_get_u32(tb[NL80211_ATTR_IFINDEX]);
 
-		netdev = dev_get_by_index(sock_net(skb->sk), ifidx);
+		netdev = __dev_get_by_index(sock_net(skb->sk), ifidx);
 		if (!netdev)
 			return -ENODEV;
 		if (netdev->ieee80211_ptr) {
-			rdev = wiphy_to_dev(
+			rdev = wiphy_to_rdev(
 				netdev->ieee80211_ptr->wiphy);
 			state->filter_wiphy = rdev->wiphy_idx;
 		}
-		dev_put(netdev);
 	}
 
 	return 0;
@@ -1630,7 +1731,7 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	int idx = 0, ret;
 	struct nl80211_dump_wiphy_state *state = (void *)cb->args[0];
-	struct cfg80211_registered_device *dev;
+	struct cfg80211_registered_device *rdev;
 
 	rtnl_lock();
 	if (!state) {
@@ -1649,17 +1750,18 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb)
 		cb->args[0] = (long)state;
 	}
 
-	list_for_each_entry(dev, &cfg80211_rdev_list, list) {
-		if (!net_eq(wiphy_net(&dev->wiphy), sock_net(skb->sk)))
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		if (!net_eq(wiphy_net(&rdev->wiphy), sock_net(skb->sk)))
 			continue;
 		if (++idx <= state->start)
 			continue;
 		if (state->filter_wiphy != -1 &&
-		    state->filter_wiphy != dev->wiphy_idx)
+		    state->filter_wiphy != rdev->wiphy_idx)
 			continue;
 		/* attempt to fit multiple wiphy data chunks into the skb */
 		do {
-			ret = nl80211_send_wiphy(dev, skb,
+			ret = nl80211_send_wiphy(rdev, NL80211_CMD_NEW_WIPHY,
+						 skb,
 						 NETLINK_CB(cb->skb).portid,
 						 cb->nlh->nlmsg_seq,
 						 NLM_F_MULTI, state);
@@ -1678,9 +1780,10 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb)
 				 * We can then retry with the larger buffer.
 				 */
 				if ((ret == -ENOBUFS || ret == -EMSGSIZE) &&
-				    !skb->len &&
+				    !skb->len && !state->split &&
 				    cb->min_dump_alloc < 4096) {
 					cb->min_dump_alloc = 4096;
+					state->split_start = 0;
 					rtnl_unlock();
 					return 1;
 				}
@@ -1706,14 +1809,15 @@ static int nl80211_dump_wiphy_done(struct netlink_callback *cb)
 static int nl80211_get_wiphy(struct sk_buff *skb, struct genl_info *info)
 {
 	struct sk_buff *msg;
-	struct cfg80211_registered_device *dev = info->user_ptr[0];
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct nl80211_dump_wiphy_state state = {};
 
 	msg = nlmsg_new(4096, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
 
-	if (nl80211_send_wiphy(dev, msg, info->snd_portid, info->snd_seq, 0,
+	if (nl80211_send_wiphy(rdev, NL80211_CMD_NEW_WIPHY, msg,
+			       info->snd_portid, info->snd_seq, 0,
 			       &state) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
@@ -1840,18 +1944,20 @@ static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
 }
 
 static int __nl80211_set_channel(struct cfg80211_registered_device *rdev,
-				 struct wireless_dev *wdev,
+				 struct net_device *dev,
 				 struct genl_info *info)
 {
 	struct cfg80211_chan_def chandef;
 	int result;
 	enum nl80211_iftype iftype = NL80211_IFTYPE_MONITOR;
+	struct wireless_dev *wdev = NULL;
 
-	if (wdev)
-		iftype = wdev->iftype;
-
+	if (dev)
+		wdev = dev->ieee80211_ptr;
 	if (!nl80211_can_set_dev_channel(wdev))
 		return -EOPNOTSUPP;
+	if (wdev)
+		iftype = wdev->iftype;
 
 	result = nl80211_parse_chandef(rdev, info, &chandef);
 	if (result)
@@ -1860,14 +1966,27 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev,
 	switch (iftype) {
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_P2P_GO:
-		if (wdev->beacon_interval) {
-			result = -EBUSY;
-			break;
-		}
-		if (!cfg80211_reg_can_beacon(&rdev->wiphy, &chandef)) {
+		if (!cfg80211_reg_can_beacon(&rdev->wiphy, &chandef, iftype)) {
 			result = -EINVAL;
 			break;
 		}
+		if (wdev->beacon_interval) {
+			if (!dev || !rdev->ops->set_ap_chanwidth ||
+			    !(rdev->wiphy.features &
+			      NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE)) {
+				result = -EBUSY;
+				break;
+			}
+
+			/* Only allow dynamic channel width changes */
+			if (chandef.chan != wdev->preset_chandef.chan) {
+				result = -EBUSY;
+				break;
+			}
+			result = rdev_set_ap_chanwidth(rdev, dev, &chandef);
+			if (result)
+				break;
+		}
 		wdev->preset_chandef = chandef;
 		result = 0;
 		break;
@@ -1889,7 +2008,7 @@ static int nl80211_set_channel(struct sk_buff *skb, struct genl_info *info)
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *netdev = info->user_ptr[1];
 
-	return __nl80211_set_channel(rdev, netdev->ieee80211_ptr, info);
+	return __nl80211_set_channel(rdev, netdev, info);
 }
 
 static int nl80211_set_wds_peer(struct sk_buff *skb, struct genl_info *info)
@@ -1943,9 +2062,9 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_IFINDEX]) {
 		int ifindex = nla_get_u32(info->attrs[NL80211_ATTR_IFINDEX]);
 
-		netdev = dev_get_by_index(genl_info_net(info), ifindex);
+		netdev = __dev_get_by_index(genl_info_net(info), ifindex);
 		if (netdev && netdev->ieee80211_ptr)
-			rdev = wiphy_to_dev(netdev->ieee80211_ptr->wiphy);
+			rdev = wiphy_to_rdev(netdev->ieee80211_ptr->wiphy);
 		else
 			netdev = NULL;
 	}
@@ -1971,57 +2090,52 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 			rdev, nla_data(info->attrs[NL80211_ATTR_WIPHY_NAME]));
 
 	if (result)
-		goto bad_res;
+		return result;
 
 	if (info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS]) {
 		struct ieee80211_txq_params txq_params;
 		struct nlattr *tb[NL80211_TXQ_ATTR_MAX + 1];
 
-		if (!rdev->ops->set_txq_params) {
-			result = -EOPNOTSUPP;
-			goto bad_res;
-		}
+		if (!rdev->ops->set_txq_params)
+			return -EOPNOTSUPP;
 
-		if (!netdev) {
-			result = -EINVAL;
-			goto bad_res;
-		}
+		if (!netdev)
+			return -EINVAL;
 
 		if (netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP &&
-		    netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) {
-			result = -EINVAL;
-			goto bad_res;
-		}
+		    netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO)
+			return -EINVAL;
 
-		if (!netif_running(netdev)) {
-			result = -ENETDOWN;
-			goto bad_res;
-		}
+		if (!netif_running(netdev))
+			return -ENETDOWN;
 
 		nla_for_each_nested(nl_txq_params,
 				    info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS],
 				    rem_txq_params) {
-			nla_parse(tb, NL80211_TXQ_ATTR_MAX,
-				  nla_data(nl_txq_params),
-				  nla_len(nl_txq_params),
-				  txq_params_policy);
+			result = nla_parse(tb, NL80211_TXQ_ATTR_MAX,
+					   nla_data(nl_txq_params),
+					   nla_len(nl_txq_params),
+					   txq_params_policy);
+			if (result)
+				return result;
 			result = parse_txq_params(tb, &txq_params);
 			if (result)
-				goto bad_res;
+				return result;
 
 			result = rdev_set_txq_params(rdev, netdev,
 						     &txq_params);
 			if (result)
-				goto bad_res;
+				return result;
 		}
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) {
-		result = __nl80211_set_channel(rdev,
-				nl80211_can_set_dev_channel(wdev) ? wdev : NULL,
-				info);
+		result = __nl80211_set_channel(
+			rdev,
+			nl80211_can_set_dev_channel(wdev) ? netdev : NULL,
+			info);
 		if (result)
-			goto bad_res;
+			return result;
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_TX_POWER_SETTING]) {
@@ -2032,19 +2146,15 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 		if (!(rdev->wiphy.features & NL80211_FEATURE_VIF_TXPOWER))
 			txp_wdev = NULL;
 
-		if (!rdev->ops->set_tx_power) {
-			result = -EOPNOTSUPP;
-			goto bad_res;
-		}
+		if (!rdev->ops->set_tx_power)
+			return -EOPNOTSUPP;
 
 		idx = NL80211_ATTR_WIPHY_TX_POWER_SETTING;
 		type = nla_get_u32(info->attrs[idx]);
 
 		if (!info->attrs[NL80211_ATTR_WIPHY_TX_POWER_LEVEL] &&
-		    (type != NL80211_TX_POWER_AUTOMATIC)) {
-			result = -EINVAL;
-			goto bad_res;
-		}
+		    (type != NL80211_TX_POWER_AUTOMATIC))
+			return -EINVAL;
 
 		if (type != NL80211_TX_POWER_AUTOMATIC) {
 			idx = NL80211_ATTR_WIPHY_TX_POWER_LEVEL;
@@ -2053,7 +2163,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 
 		result = rdev_set_tx_power(rdev, txp_wdev, type, mbm);
 		if (result)
-			goto bad_res;
+			return result;
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX] &&
@@ -2061,10 +2171,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 		u32 tx_ant, rx_ant;
 		if ((!rdev->wiphy.available_antennas_tx &&
 		     !rdev->wiphy.available_antennas_rx) ||
-		    !rdev->ops->set_antenna) {
-			result = -EOPNOTSUPP;
-			goto bad_res;
-		}
+		    !rdev->ops->set_antenna)
+			return -EOPNOTSUPP;
 
 		tx_ant = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX]);
 		rx_ant = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_ANTENNA_RX]);
@@ -2072,17 +2180,15 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 		/* reject antenna configurations which don't match the
 		 * available antenna masks, except for the "all" mask */
 		if ((~tx_ant && (tx_ant & ~rdev->wiphy.available_antennas_tx)) ||
-		    (~rx_ant && (rx_ant & ~rdev->wiphy.available_antennas_rx))) {
-			result = -EINVAL;
-			goto bad_res;
-		}
+		    (~rx_ant && (rx_ant & ~rdev->wiphy.available_antennas_rx)))
+			return -EINVAL;
 
 		tx_ant = tx_ant & rdev->wiphy.available_antennas_tx;
 		rx_ant = rx_ant & rdev->wiphy.available_antennas_rx;
 
 		result = rdev_set_antenna(rdev, tx_ant, rx_ant);
 		if (result)
-			goto bad_res;
+			return result;
 	}
 
 	changed = 0;
@@ -2090,30 +2196,27 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_WIPHY_RETRY_SHORT]) {
 		retry_short = nla_get_u8(
 			info->attrs[NL80211_ATTR_WIPHY_RETRY_SHORT]);
-		if (retry_short == 0) {
-			result = -EINVAL;
-			goto bad_res;
-		}
+		if (retry_short == 0)
+			return -EINVAL;
+
 		changed |= WIPHY_PARAM_RETRY_SHORT;
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_RETRY_LONG]) {
 		retry_long = nla_get_u8(
 			info->attrs[NL80211_ATTR_WIPHY_RETRY_LONG]);
-		if (retry_long == 0) {
-			result = -EINVAL;
-			goto bad_res;
-		}
+		if (retry_long == 0)
+			return -EINVAL;
+
 		changed |= WIPHY_PARAM_RETRY_LONG;
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_FRAG_THRESHOLD]) {
 		frag_threshold = nla_get_u32(
 			info->attrs[NL80211_ATTR_WIPHY_FRAG_THRESHOLD]);
-		if (frag_threshold < 256) {
-			result = -EINVAL;
-			goto bad_res;
-		}
+		if (frag_threshold < 256)
+			return -EINVAL;
+
 		if (frag_threshold != (u32) -1) {
 			/*
 			 * Fragments (apart from the last one) are required to
@@ -2143,10 +2246,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 		u32 old_frag_threshold, old_rts_threshold;
 		u8 old_coverage_class;
 
-		if (!rdev->ops->set_wiphy_params) {
-			result = -EOPNOTSUPP;
-			goto bad_res;
-		}
+		if (!rdev->ops->set_wiphy_params)
+			return -EOPNOTSUPP;
 
 		old_retry_short = rdev->wiphy.retry_short;
 		old_retry_long = rdev->wiphy.retry_long;
@@ -2174,17 +2275,13 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 			rdev->wiphy.coverage_class = old_coverage_class;
 		}
 	}
-
- bad_res:
-	if (netdev)
-		dev_put(netdev);
-	return result;
+	return 0;
 }
 
 static inline u64 wdev_id(struct wireless_dev *wdev)
 {
 	return (u64)wdev->identifier |
-	       ((u64)wiphy_to_dev(wdev->wiphy)->wiphy_idx << 32);
+	       ((u64)wiphy_to_rdev(wdev->wiphy)->wiphy_idx << 32);
 }
 
 static int nl80211_send_chandef(struct sk_buff *msg,
@@ -2310,7 +2407,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info)
 {
 	struct sk_buff *msg;
-	struct cfg80211_registered_device *dev = info->user_ptr[0];
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct wireless_dev *wdev = info->user_ptr[1];
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -2318,7 +2415,7 @@ static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 
 	if (nl80211_send_iface(msg, info->snd_portid, info->snd_seq, 0,
-			       dev, wdev) < 0) {
+			       rdev, wdev) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
 	}
@@ -2469,6 +2566,9 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 	enum nl80211_iftype type = NL80211_IFTYPE_UNSPECIFIED;
 	u32 flags;
 
+	/* to avoid failing a new interface creation due to pending removal */
+	cfg80211_destroy_ifaces(rdev);
+
 	memset(&params, 0, sizeof(params));
 
 	if (!info->attrs[NL80211_ATTR_IFNAME])
@@ -2518,6 +2618,9 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 		return PTR_ERR(wdev);
 	}
 
+	if (info->attrs[NL80211_ATTR_IFACE_SOCKET_OWNER])
+		wdev->owner_nlportid = info->snd_portid;
+
 	switch (type) {
 	case NL80211_IFTYPE_MESH_POINT:
 		if (!info->attrs[NL80211_ATTR_MESH_ID])
@@ -3097,7 +3200,6 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_ap_settings params;
 	int err;
-	u8 radar_detect_width = 0;
 
 	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP &&
 	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO)
@@ -3213,24 +3315,10 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	} else if (!nl80211_get_ap_channel(rdev, &params))
 		return -EINVAL;
 
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef,
+				     wdev->iftype))
 		return -EINVAL;
 
-	err = cfg80211_chandef_dfs_required(wdev->wiphy, &params.chandef);
-	if (err < 0)
-		return err;
-	if (err) {
-		radar_detect_width = BIT(params.chandef.width);
-		params.radar_required = true;
-	}
-
-	err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
-					   params.chandef.chan,
-					   CHAN_MODE_SHARED,
-					   radar_detect_width);
-	if (err)
-		return err;
-
 	if (info->attrs[NL80211_ATTR_ACL_POLICY]) {
 		params.acl = parse_acl_data(&rdev->wiphy, info);
 		if (IS_ERR(params.acl))
@@ -3242,7 +3330,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	if (!err) {
 		wdev->preset_chandef = params.chandef;
 		wdev->beacon_interval = params.beacon_interval;
-		wdev->channel = params.chandef.chan;
+		wdev->chandef = params.chandef;
 		wdev->ssid_len = params.ssid_len;
 		memcpy(wdev->ssid, params.ssid, wdev->ssid_len);
 	}
@@ -3287,7 +3375,7 @@ static int nl80211_stop_ap(struct sk_buff *skb, struct genl_info *info)
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
 
-	return cfg80211_stop_ap(rdev, dev);
+	return cfg80211_stop_ap(rdev, dev, false);
 }
 
 static const struct nla_policy sta_flags_policy[NL80211_STA_FLAG_MAX + 1] = {
@@ -3568,6 +3656,10 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq,
 	    nla_put_u32(msg, NL80211_STA_INFO_TX_FAILED,
 			sinfo->tx_failed))
 		goto nla_put_failure;
+	if ((sinfo->filled & STATION_INFO_EXPECTED_THROUGHPUT) &&
+	    nla_put_u32(msg, NL80211_STA_INFO_EXPECTED_THROUGHPUT,
+			sinfo->expected_throughput))
+		goto nla_put_failure;
 	if ((sinfo->filled & STATION_INFO_BEACON_LOSS_COUNT) &&
 	    nla_put_u32(msg, NL80211_STA_INFO_BEACON_LOSS,
 			sinfo->beacon_loss_count))
@@ -3630,13 +3722,13 @@ static int nl80211_dump_station(struct sk_buff *skb,
 				struct netlink_callback *cb)
 {
 	struct station_info sinfo;
-	struct cfg80211_registered_device *dev;
+	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
 	u8 mac_addr[ETH_ALEN];
 	int sta_idx = cb->args[2];
 	int err;
 
-	err = nl80211_prepare_wdev_dump(skb, cb, &dev, &wdev);
+	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (err)
 		return err;
 
@@ -3645,14 +3737,14 @@ static int nl80211_dump_station(struct sk_buff *skb,
 		goto out_err;
 	}
 
-	if (!dev->ops->dump_station) {
+	if (!rdev->ops->dump_station) {
 		err = -EOPNOTSUPP;
 		goto out_err;
 	}
 
 	while (1) {
 		memset(&sinfo, 0, sizeof(sinfo));
-		err = rdev_dump_station(dev, wdev->netdev, sta_idx,
+		err = rdev_dump_station(rdev, wdev->netdev, sta_idx,
 					mac_addr, &sinfo);
 		if (err == -ENOENT)
 			break;
@@ -3662,7 +3754,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 		if (nl80211_send_station(skb,
 				NETLINK_CB(cb->skb).portid,
 				cb->nlh->nlmsg_seq, NLM_F_MULTI,
-				dev, wdev->netdev, mac_addr,
+				rdev, wdev->netdev, mac_addr,
 				&sinfo) < 0)
 			goto out;
 
@@ -3674,7 +3766,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 	cb->args[2] = sta_idx;
 	err = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(dev);
+	nl80211_finish_wdev_dump(rdev);
 
 	return err;
 }
@@ -3885,8 +3977,8 @@ static struct net_device *get_vlan(struct genl_info *info,
 	return ERR_PTR(ret);
 }
 
-static struct nla_policy
-nl80211_sta_wme_policy[NL80211_STA_WME_MAX + 1] __read_mostly = {
+static const struct nla_policy
+nl80211_sta_wme_policy[NL80211_STA_WME_MAX + 1] = {
 	[NL80211_STA_WME_UAPSD_QUEUES] = { .type = NLA_U8 },
 	[NL80211_STA_WME_MAX_SP] = { .type = NLA_U8 },
 };
@@ -4151,6 +4243,12 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 		params.vht_capa =
 			nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]);
 
+	if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) {
+		params.opmode_notif_used = true;
+		params.opmode_notif =
+			nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]);
+	}
+
 	if (info->attrs[NL80211_ATTR_STA_PLINK_ACTION]) {
 		params.plink_action =
 			nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_ACTION]);
@@ -4329,18 +4427,18 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 			      struct netlink_callback *cb)
 {
 	struct mpath_info pinfo;
-	struct cfg80211_registered_device *dev;
+	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
 	u8 dst[ETH_ALEN];
 	u8 next_hop[ETH_ALEN];
 	int path_idx = cb->args[2];
 	int err;
 
-	err = nl80211_prepare_wdev_dump(skb, cb, &dev, &wdev);
+	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (err)
 		return err;
 
-	if (!dev->ops->dump_mpath) {
+	if (!rdev->ops->dump_mpath) {
 		err = -EOPNOTSUPP;
 		goto out_err;
 	}
@@ -4351,7 +4449,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 	}
 
 	while (1) {
-		err = rdev_dump_mpath(dev, wdev->netdev, path_idx, dst,
+		err = rdev_dump_mpath(rdev, wdev->netdev, path_idx, dst,
 				      next_hop, &pinfo);
 		if (err == -ENOENT)
 			break;
@@ -4372,7 +4470,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 	cb->args[2] = path_idx;
 	err = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(dev);
+	nl80211_finish_wdev_dump(rdev);
 	return err;
 }
 
@@ -4567,6 +4665,7 @@ static const struct nla_policy reg_rule_policy[NL80211_REG_RULE_ATTR_MAX + 1] =
 	[NL80211_ATTR_FREQ_RANGE_MAX_BW]	= { .type = NLA_U32 },
 	[NL80211_ATTR_POWER_RULE_MAX_ANT_GAIN]	= { .type = NLA_U32 },
 	[NL80211_ATTR_POWER_RULE_MAX_EIRP]	= { .type = NLA_U32 },
+	[NL80211_ATTR_DFS_CAC_TIME]		= { .type = NLA_U32 },
 };
 
 static int parse_reg_rule(struct nlattr *tb[],
@@ -4602,12 +4701,15 @@ static int parse_reg_rule(struct nlattr *tb[],
 		power_rule->max_antenna_gain =
 			nla_get_u32(tb[NL80211_ATTR_POWER_RULE_MAX_ANT_GAIN]);
 
+	if (tb[NL80211_ATTR_DFS_CAC_TIME])
+		reg_rule->dfs_cac_ms =
+			nla_get_u32(tb[NL80211_ATTR_DFS_CAC_TIME]);
+
 	return 0;
 }
 
 static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info)
 {
-	int r;
 	char *data = NULL;
 	enum nl80211_user_reg_hint_type user_reg_hint_type;
 
@@ -4620,11 +4722,6 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info)
 	if (unlikely(!rcu_access_pointer(cfg80211_regdomain)))
 		return -EINPROGRESS;
 
-	if (!info->attrs[NL80211_ATTR_REG_ALPHA2])
-		return -EINVAL;
-
-	data = nla_data(info->attrs[NL80211_ATTR_REG_ALPHA2]);
-
 	if (info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE])
 		user_reg_hint_type =
 		  nla_get_u32(info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE]);
@@ -4634,14 +4731,16 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info)
 	switch (user_reg_hint_type) {
 	case NL80211_USER_REG_HINT_USER:
 	case NL80211_USER_REG_HINT_CELL_BASE:
-		break;
+		if (!info->attrs[NL80211_ATTR_REG_ALPHA2])
+			return -EINVAL;
+
+		data = nla_data(info->attrs[NL80211_ATTR_REG_ALPHA2]);
+		return regulatory_hint_user(data, user_reg_hint_type);
+	case NL80211_USER_REG_HINT_INDOOR:
+		return regulatory_hint_indoor_user();
 	default:
 		return -EINVAL;
 	}
-
-	r = regulatory_hint_user(data, user_reg_hint_type);
-
-	return r;
 }
 
 static int nl80211_get_mesh_config(struct sk_buff *skb,
@@ -5063,6 +5162,7 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info)
 		const struct ieee80211_reg_rule *reg_rule;
 		const struct ieee80211_freq_range *freq_range;
 		const struct ieee80211_power_rule *power_rule;
+		unsigned int max_bandwidth_khz;
 
 		reg_rule = &regdom->reg_rules[i];
 		freq_range = &reg_rule->freq_range;
@@ -5072,6 +5172,11 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info)
 		if (!nl_reg_rule)
 			goto nla_put_failure_rcu;
 
+		max_bandwidth_khz = freq_range->max_bandwidth_khz;
+		if (!max_bandwidth_khz)
+			max_bandwidth_khz = reg_get_max_bandwidth(regdom,
+								  reg_rule);
+
 		if (nla_put_u32(msg, NL80211_ATTR_REG_RULE_FLAGS,
 				reg_rule->flags) ||
 		    nla_put_u32(msg, NL80211_ATTR_FREQ_RANGE_START,
@@ -5079,11 +5184,13 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info)
 		    nla_put_u32(msg, NL80211_ATTR_FREQ_RANGE_END,
 				freq_range->end_freq_khz) ||
 		    nla_put_u32(msg, NL80211_ATTR_FREQ_RANGE_MAX_BW,
-				freq_range->max_bandwidth_khz) ||
+				max_bandwidth_khz) ||
 		    nla_put_u32(msg, NL80211_ATTR_POWER_RULE_MAX_ANT_GAIN,
 				power_rule->max_antenna_gain) ||
 		    nla_put_u32(msg, NL80211_ATTR_POWER_RULE_MAX_EIRP,
-				power_rule->max_eirp))
+				power_rule->max_eirp) ||
+		    nla_put_u32(msg, NL80211_ATTR_DFS_CAC_TIME,
+				reg_rule->dfs_cac_ms))
 			goto nla_put_failure_rcu;
 
 		nla_nest_end(msg, nl_reg_rule);
@@ -5155,9 +5262,11 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info)
 
 	nla_for_each_nested(nl_reg_rule, info->attrs[NL80211_ATTR_REG_RULES],
 			    rem_reg_rules) {
-		nla_parse(tb, NL80211_REG_RULE_ATTR_MAX,
-			  nla_data(nl_reg_rule), nla_len(nl_reg_rule),
-			  reg_rule_policy);
+		r = nla_parse(tb, NL80211_REG_RULE_ATTR_MAX,
+			      nla_data(nl_reg_rule), nla_len(nl_reg_rule),
+			      reg_rule_policy);
+		if (r)
+			goto bad_reg;
 		r = parse_reg_rule(tb, &rd->reg_rules[rule_idx]);
 		if (r)
 			goto bad_reg;
@@ -5222,7 +5331,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	if (!rdev->ops->scan)
 		return -EOPNOTSUPP;
 
-	if (rdev->scan_req) {
+	if (rdev->scan_req || rdev->scan_msg) {
 		err = -EBUSY;
 		goto unlock;
 	}
@@ -5235,12 +5344,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 			goto unlock;
 		}
 	} else {
-		enum ieee80211_band band;
-		n_channels = 0;
-
-		for (band = 0; band < IEEE80211_NUM_BANDS; band++)
-			if (wiphy->bands[band])
-				n_channels += wiphy->bands[band]->n_channels;
+		n_channels = ieee80211_get_num_supported_channels(wiphy);
 	}
 
 	if (info->attrs[NL80211_ATTR_SCAN_SSIDS])
@@ -5425,6 +5529,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	enum ieee80211_band band;
 	size_t ie_len;
 	struct nlattr *tb[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1];
+	s32 default_match_rssi = NL80211_SCAN_RSSI_THOLD_OFF;
 
 	if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) ||
 	    !rdev->ops->sched_scan_start)
@@ -5448,11 +5553,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 		if (!n_channels)
 			return -EINVAL;
 	} else {
-		n_channels = 0;
-
-		for (band = 0; band < IEEE80211_NUM_BANDS; band++)
-			if (wiphy->bands[band])
-				n_channels += wiphy->bands[band]->n_channels;
+		n_channels = ieee80211_get_num_supported_channels(wiphy);
 	}
 
 	if (info->attrs[NL80211_ATTR_SCAN_SSIDS])
@@ -5463,11 +5564,40 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	if (n_ssids > wiphy->max_sched_scan_ssids)
 		return -EINVAL;
 
-	if (info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH])
+	/*
+	 * First, count the number of 'real' matchsets. Due to an issue with
+	 * the old implementation, matchsets containing only the RSSI attribute
+	 * (NL80211_SCHED_SCAN_MATCH_ATTR_RSSI) are considered as the 'default'
+	 * RSSI for all matchsets, rather than their own matchset for reporting
+	 * all APs with a strong RSSI. This is needed to be compatible with
+	 * older userspace that treated a matchset with only the RSSI as the
+	 * global RSSI for all other matchsets - if there are other matchsets.
+	 */
+	if (info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH]) {
 		nla_for_each_nested(attr,
 				    info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH],
-				    tmp)
-			n_match_sets++;
+				    tmp) {
+			struct nlattr *rssi;
+
+			err = nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
+					nla_data(attr), nla_len(attr),
+					nl80211_match_policy);
+			if (err)
+				return err;
+			/* add other standalone attributes here */
+			if (tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID]) {
+				n_match_sets++;
+				continue;
+			}
+			rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI];
+			if (rssi)
+				default_match_rssi = nla_get_s32(rssi);
+		}
+	}
+
+	/* However, if there's no other matchset, add the RSSI one */
+	if (!n_match_sets && default_match_rssi != NL80211_SCAN_RSSI_THOLD_OFF)
+		n_match_sets = 1;
 
 	if (n_match_sets > wiphy->max_match_sets)
 		return -EINVAL;
@@ -5588,11 +5718,22 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 				    tmp) {
 			struct nlattr *ssid, *rssi;
 
-			nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
-				  nla_data(attr), nla_len(attr),
-				  nl80211_match_policy);
+			err = nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
+					nla_data(attr), nla_len(attr),
+					nl80211_match_policy);
+			if (err)
+				goto out_free;
 			ssid = tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID];
 			if (ssid) {
+				if (WARN_ON(i >= n_match_sets)) {
+					/* this indicates a programming error,
+					 * the loop above should have verified
+					 * things properly
+					 */
+					err = -EINVAL;
+					goto out_free;
+				}
+
 				if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) {
 					err = -EINVAL;
 					goto out_free;
@@ -5601,19 +5742,32 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 				       nla_data(ssid), nla_len(ssid));
 				request->match_sets[i].ssid.ssid_len =
 					nla_len(ssid);
+				/* special attribute - old implemenation w/a */
+				request->match_sets[i].rssi_thold =
+					default_match_rssi;
+				rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI];
+				if (rssi)
+					request->match_sets[i].rssi_thold =
+						nla_get_s32(rssi);
 			}
-			rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI];
-			if (rssi)
-				request->rssi_thold = nla_get_u32(rssi);
-			else
-				request->rssi_thold =
-						   NL80211_SCAN_RSSI_THOLD_OFF;
 			i++;
 		}
+
+		/* there was no other matchset, so the RSSI one is alone */
+		if (i == 0)
+			request->match_sets[0].rssi_thold = default_match_rssi;
+
+		request->min_rssi_thold = INT_MAX;
+		for (i = 0; i < n_match_sets; i++)
+			request->min_rssi_thold =
+				min(request->match_sets[i].rssi_thold,
+				    request->min_rssi_thold);
+	} else {
+		request->min_rssi_thold = NL80211_SCAN_RSSI_THOLD_OFF;
 	}
 
-	if (info->attrs[NL80211_ATTR_IE]) {
-		request->ie_len = nla_len(info->attrs[NL80211_ATTR_IE]);
+	if (ie_len) {
+		request->ie_len = ie_len;
 		memcpy((void *)request->ie,
 		       nla_data(info->attrs[NL80211_ATTR_IE]),
 		       request->ie_len);
@@ -5667,8 +5821,14 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 	struct net_device *dev = info->user_ptr[1];
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_chan_def chandef;
+	enum nl80211_dfs_regions dfs_region;
+	unsigned int cac_time_ms;
 	int err;
 
+	dfs_region = reg_get_dfs_region(wdev->wiphy);
+	if (dfs_region == NL80211_DFS_UNSET)
+		return -EINVAL;
+
 	err = nl80211_parse_chandef(rdev, info, &chandef);
 	if (err)
 		return err;
@@ -5679,7 +5839,8 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 	if (wdev->cac_started)
 		return -EBUSY;
 
-	err = cfg80211_chandef_dfs_required(wdev->wiphy, &chandef);
+	err = cfg80211_chandef_dfs_required(wdev->wiphy, &chandef,
+					    wdev->iftype);
 	if (err < 0)
 		return err;
 
@@ -5692,17 +5853,17 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 	if (!rdev->ops->start_radar_detection)
 		return -EOPNOTSUPP;
 
-	err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
-					   chandef.chan, CHAN_MODE_SHARED,
-					   BIT(chandef.width));
-	if (err)
-		return err;
+	cac_time_ms = cfg80211_chandef_dfs_cac_time(&rdev->wiphy, &chandef);
+	if (WARN_ON(!cac_time_ms))
+		cac_time_ms = IEEE80211_DFS_MIN_CAC_TIME_MS;
 
-	err = rdev->ops->start_radar_detection(&rdev->wiphy, dev, &chandef);
+	err = rdev->ops->start_radar_detection(&rdev->wiphy, dev, &chandef,
+					       cac_time_ms);
 	if (!err) {
-		wdev->channel = chandef.chan;
+		wdev->chandef = chandef;
 		wdev->cac_started = true;
 		wdev->cac_start_time = jiffies;
+		wdev->cac_time_ms = cac_time_ms;
 	}
 	return err;
 }
@@ -5720,6 +5881,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 	u8 radar_detect_width = 0;
 	int err;
 	bool need_new_beacon = false;
+	int len, i;
 
 	if (!rdev->ops->channel_switch ||
 	    !(rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH))
@@ -5732,10 +5894,15 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 
 		/* useless if AP is not running */
 		if (!wdev->beacon_interval)
-			return -EINVAL;
+			return -ENOTCONN;
 		break;
 	case NL80211_IFTYPE_ADHOC:
+		if (!wdev->ssid_len)
+			return -ENOTCONN;
+		break;
 	case NL80211_IFTYPE_MESH_POINT:
+		if (!wdev->mesh_id_len)
+			return -ENOTCONN;
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -5773,26 +5940,55 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 	if (!csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON])
 		return -EINVAL;
 
-	params.counter_offset_beacon =
-		nla_get_u16(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]);
-	if (params.counter_offset_beacon >= params.beacon_csa.tail_len)
+	len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]);
+	if (!len || (len % sizeof(u16)))
 		return -EINVAL;
 
-	/* sanity check - counters should be the same */
-	if (params.beacon_csa.tail[params.counter_offset_beacon] !=
-	    params.count)
+	params.n_counter_offsets_beacon = len / sizeof(u16);
+	if (rdev->wiphy.max_num_csa_counters &&
+	    (params.n_counter_offsets_beacon >
+	     rdev->wiphy.max_num_csa_counters))
 		return -EINVAL;
 
+	params.counter_offsets_beacon =
+		nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]);
+
+	/* sanity checks - counters should fit and be the same */
+	for (i = 0; i < params.n_counter_offsets_beacon; i++) {
+		u16 offset = params.counter_offsets_beacon[i];
+
+		if (offset >= params.beacon_csa.tail_len)
+			return -EINVAL;
+
+		if (params.beacon_csa.tail[offset] != params.count)
+			return -EINVAL;
+	}
+
 	if (csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]) {
-		params.counter_offset_presp =
-			nla_get_u16(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]);
-		if (params.counter_offset_presp >=
-		    params.beacon_csa.probe_resp_len)
+		len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]);
+		if (!len || (len % sizeof(u16)))
 			return -EINVAL;
 
-		if (params.beacon_csa.probe_resp[params.counter_offset_presp] !=
-		    params.count)
+		params.n_counter_offsets_presp = len / sizeof(u16);
+		if (rdev->wiphy.max_num_csa_counters &&
+		    (params.n_counter_offsets_beacon >
+		     rdev->wiphy.max_num_csa_counters))
 			return -EINVAL;
+
+		params.counter_offsets_presp =
+			nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]);
+
+		/* sanity checks - counters should fit and be the same */
+		for (i = 0; i < params.n_counter_offsets_presp; i++) {
+			u16 offset = params.counter_offsets_presp[i];
+
+			if (offset >= params.beacon_csa.probe_resp_len)
+				return -EINVAL;
+
+			if (params.beacon_csa.probe_resp[offset] !=
+			    params.count)
+				return -EINVAL;
+		}
 	}
 
 skip_beacons:
@@ -5800,22 +5996,25 @@ skip_beacons:
 	if (err)
 		return err;
 
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef,
+				     wdev->iftype))
 		return -EINVAL;
 
-	if (dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP ||
-	    dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO ||
-	    dev->ieee80211_ptr->iftype == NL80211_IFTYPE_ADHOC) {
-		err = cfg80211_chandef_dfs_required(wdev->wiphy,
-						    &params.chandef);
-		if (err < 0) {
-			return err;
-		} else if (err) {
-			radar_detect_width = BIT(params.chandef.width);
-			params.radar_required = true;
-		}
+	err = cfg80211_chandef_dfs_required(wdev->wiphy,
+					    &params.chandef,
+					    wdev->iftype);
+	if (err < 0)
+		return err;
+
+	if (err > 0) {
+		radar_detect_width = BIT(params.chandef.width);
+		params.radar_required = true;
 	}
 
+	/* TODO: I left this here for now.  With channel switch, the
+	 * verification is a bit more complicated, because we only do
+	 * it later when the channel switch really happens.
+	 */
 	err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
 					   params.chandef.chan,
 					   CHAN_MODE_SHARED,
@@ -6042,12 +6241,12 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 			struct netlink_callback *cb)
 {
 	struct survey_info survey;
-	struct cfg80211_registered_device *dev;
+	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
 	int survey_idx = cb->args[2];
 	int res;
 
-	res = nl80211_prepare_wdev_dump(skb, cb, &dev, &wdev);
+	res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (res)
 		return res;
 
@@ -6056,7 +6255,7 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 		goto out_err;
 	}
 
-	if (!dev->ops->dump_survey) {
+	if (!rdev->ops->dump_survey) {
 		res = -EOPNOTSUPP;
 		goto out_err;
 	}
@@ -6064,7 +6263,7 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 	while (1) {
 		struct ieee80211_channel *chan;
 
-		res = rdev_dump_survey(dev, wdev->netdev, survey_idx, &survey);
+		res = rdev_dump_survey(rdev, wdev->netdev, survey_idx, &survey);
 		if (res == -ENOENT)
 			break;
 		if (res)
@@ -6076,7 +6275,7 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 			goto out;
 		}
 
-		chan = ieee80211_get_channel(&dev->wiphy,
+		chan = ieee80211_get_channel(&rdev->wiphy,
 					     survey.channel->center_freq);
 		if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) {
 			survey_idx++;
@@ -6095,7 +6294,7 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 	cb->args[2] = survey_idx;
 	res = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(dev);
+	nl80211_finish_wdev_dump(rdev);
 	return res;
 }
 
@@ -6173,9 +6372,9 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info)
 		return -EOPNOTSUPP;
 
 	bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
-	chan = ieee80211_get_channel(&rdev->wiphy,
-		nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]));
-	if (!chan || (chan->flags & IEEE80211_CHAN_DISABLED))
+	chan = nl80211_get_valid_chan(&rdev->wiphy,
+				      info->attrs[NL80211_ATTR_WIPHY_FREQ]);
+	if (!chan)
 		return -EINVAL;
 
 	ssid = nla_data(info->attrs[NL80211_ATTR_SSID]);
@@ -6328,9 +6527,9 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 
 	bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
 
-	chan = ieee80211_get_channel(&rdev->wiphy,
-		nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]));
-	if (!chan || (chan->flags & IEEE80211_CHAN_DISABLED))
+	chan = nl80211_get_valid_chan(&rdev->wiphy,
+				      info->attrs[NL80211_ATTR_WIPHY_FREQ]);
+	if (!chan)
 		return -EINVAL;
 
 	ssid = nla_data(info->attrs[NL80211_ATTR_SSID]);
@@ -6571,7 +6770,8 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &ibss.chandef))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &ibss.chandef,
+				     NL80211_IFTYPE_ADHOC))
 		return -EINVAL;
 
 	switch (ibss.chandef.width) {
@@ -6693,6 +6893,101 @@ static int nl80211_set_mcast_rate(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
+static struct sk_buff *
+__cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev,
+			    int approxlen, u32 portid, u32 seq,
+			    enum nl80211_commands cmd,
+			    enum nl80211_attrs attr,
+			    const struct nl80211_vendor_cmd_info *info,
+			    gfp_t gfp)
+{
+	struct sk_buff *skb;
+	void *hdr;
+	struct nlattr *data;
+
+	skb = nlmsg_new(approxlen + 100, gfp);
+	if (!skb)
+		return NULL;
+
+	hdr = nl80211hdr_put(skb, portid, seq, 0, cmd);
+	if (!hdr) {
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx))
+		goto nla_put_failure;
+
+	if (info) {
+		if (nla_put_u32(skb, NL80211_ATTR_VENDOR_ID,
+				info->vendor_id))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, NL80211_ATTR_VENDOR_SUBCMD,
+				info->subcmd))
+			goto nla_put_failure;
+	}
+
+	data = nla_nest_start(skb, attr);
+
+	((void **)skb->cb)[0] = rdev;
+	((void **)skb->cb)[1] = hdr;
+	((void **)skb->cb)[2] = data;
+
+	return skb;
+
+ nla_put_failure:
+	kfree_skb(skb);
+	return NULL;
+}
+
+struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy,
+					   enum nl80211_commands cmd,
+					   enum nl80211_attrs attr,
+					   int vendor_event_idx,
+					   int approxlen, gfp_t gfp)
+{
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+	const struct nl80211_vendor_cmd_info *info;
+
+	switch (cmd) {
+	case NL80211_CMD_TESTMODE:
+		if (WARN_ON(vendor_event_idx != -1))
+			return NULL;
+		info = NULL;
+		break;
+	case NL80211_CMD_VENDOR:
+		if (WARN_ON(vendor_event_idx < 0 ||
+			    vendor_event_idx >= wiphy->n_vendor_events))
+			return NULL;
+		info = &wiphy->vendor_events[vendor_event_idx];
+		break;
+	default:
+		WARN_ON(1);
+		return NULL;
+	}
+
+	return __cfg80211_alloc_vendor_skb(rdev, approxlen, 0, 0,
+					   cmd, attr, info, gfp);
+}
+EXPORT_SYMBOL(__cfg80211_alloc_event_skb);
+
+void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp)
+{
+	struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
+	void *hdr = ((void **)skb->cb)[1];
+	struct nlattr *data = ((void **)skb->cb)[2];
+	enum nl80211_multicast_groups mcgrp = NL80211_MCGRP_TESTMODE;
+
+	nla_nest_end(skb, data);
+	genlmsg_end(skb, hdr);
+
+	if (data->nla_type == NL80211_ATTR_VENDOR_DATA)
+		mcgrp = NL80211_MCGRP_VENDOR;
+
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), skb, 0,
+				mcgrp, gfp);
+}
+EXPORT_SYMBOL(__cfg80211_send_event_skb);
 
 #ifdef CONFIG_NL80211_TESTMODE
 static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info)
@@ -6717,11 +7012,11 @@ static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[NL80211_ATTR_TESTDATA])
 		return -EINVAL;
 
-	rdev->testmode_info = info;
+	rdev->cur_cmd_info = info;
 	err = rdev_testmode_cmd(rdev, wdev,
 				nla_data(info->attrs[NL80211_ATTR_TESTDATA]),
 				nla_len(info->attrs[NL80211_ATTR_TESTDATA]));
-	rdev->testmode_info = NULL;
+	rdev->cur_cmd_info = NULL;
 
 	return err;
 }
@@ -6820,93 +7115,6 @@ static int nl80211_testmode_dump(struct sk_buff *skb,
 	rtnl_unlock();
 	return err;
 }
-
-static struct sk_buff *
-__cfg80211_testmode_alloc_skb(struct cfg80211_registered_device *rdev,
-			      int approxlen, u32 portid, u32 seq, gfp_t gfp)
-{
-	struct sk_buff *skb;
-	void *hdr;
-	struct nlattr *data;
-
-	skb = nlmsg_new(approxlen + 100, gfp);
-	if (!skb)
-		return NULL;
-
-	hdr = nl80211hdr_put(skb, portid, seq, 0, NL80211_CMD_TESTMODE);
-	if (!hdr) {
-		kfree_skb(skb);
-		return NULL;
-	}
-
-	if (nla_put_u32(skb, NL80211_ATTR_WIPHY, rdev->wiphy_idx))
-		goto nla_put_failure;
-	data = nla_nest_start(skb, NL80211_ATTR_TESTDATA);
-
-	((void **)skb->cb)[0] = rdev;
-	((void **)skb->cb)[1] = hdr;
-	((void **)skb->cb)[2] = data;
-
-	return skb;
-
- nla_put_failure:
-	kfree_skb(skb);
-	return NULL;
-}
-
-struct sk_buff *cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy,
-						  int approxlen)
-{
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
-
-	if (WARN_ON(!rdev->testmode_info))
-		return NULL;
-
-	return __cfg80211_testmode_alloc_skb(rdev, approxlen,
-				rdev->testmode_info->snd_portid,
-				rdev->testmode_info->snd_seq,
-				GFP_KERNEL);
-}
-EXPORT_SYMBOL(cfg80211_testmode_alloc_reply_skb);
-
-int cfg80211_testmode_reply(struct sk_buff *skb)
-{
-	struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
-	void *hdr = ((void **)skb->cb)[1];
-	struct nlattr *data = ((void **)skb->cb)[2];
-
-	if (WARN_ON(!rdev->testmode_info)) {
-		kfree_skb(skb);
-		return -EINVAL;
-	}
-
-	nla_nest_end(skb, data);
-	genlmsg_end(skb, hdr);
-	return genlmsg_reply(skb, rdev->testmode_info);
-}
-EXPORT_SYMBOL(cfg80211_testmode_reply);
-
-struct sk_buff *cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy,
-						  int approxlen, gfp_t gfp)
-{
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
-
-	return __cfg80211_testmode_alloc_skb(rdev, approxlen, 0, 0, gfp);
-}
-EXPORT_SYMBOL(cfg80211_testmode_alloc_event_skb);
-
-void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
-{
-	struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
-	void *hdr = ((void **)skb->cb)[1];
-	struct nlattr *data = ((void **)skb->cb)[2];
-
-	nla_nest_end(skb, data);
-	genlmsg_end(skb, hdr);
-	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), skb, 0,
-				NL80211_MCGRP_TESTMODE, gfp);
-}
-EXPORT_SYMBOL(cfg80211_testmode_event);
 #endif
 
 static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
@@ -6958,6 +7166,9 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[NL80211_ATTR_MAC])
 		connect.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
+	else if (info->attrs[NL80211_ATTR_MAC_HINT])
+		connect.bssid_hint =
+			nla_data(info->attrs[NL80211_ATTR_MAC_HINT]);
 	connect.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]);
 	connect.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]);
 
@@ -6976,11 +7187,14 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) {
-		connect.channel =
-			ieee80211_get_channel(wiphy,
-			    nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]));
-		if (!connect.channel ||
-		    connect.channel->flags & IEEE80211_CHAN_DISABLED)
+		connect.channel = nl80211_get_valid_chan(
+			wiphy, info->attrs[NL80211_ATTR_WIPHY_FREQ]);
+		if (!connect.channel)
+			return -EINVAL;
+	} else if (info->attrs[NL80211_ATTR_WIPHY_FREQ_HINT]) {
+		connect.channel_hint = nl80211_get_valid_chan(
+			wiphy, info->attrs[NL80211_ATTR_WIPHY_FREQ_HINT]);
+		if (!connect.channel_hint)
 			return -EINVAL;
 	}
 
@@ -7147,6 +7361,7 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info)
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
 	u8 action_code, dialog_token;
+	u32 peer_capability = 0;
 	u16 status_code;
 	u8 *peer;
 
@@ -7165,9 +7380,12 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info)
 	action_code = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_ACTION]);
 	status_code = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]);
 	dialog_token = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_DIALOG_TOKEN]);
+	if (info->attrs[NL80211_ATTR_TDLS_PEER_CAPABILITY])
+		peer_capability =
+			nla_get_u32(info->attrs[NL80211_ATTR_TDLS_PEER_CAPABILITY]);
 
 	return rdev_tdls_mgmt(rdev, dev, peer, action_code,
-			      dialog_token, status_code,
+			      dialog_token, status_code, peer_capability,
 			      nla_data(info->attrs[NL80211_ATTR_IE]),
 			      nla_len(info->attrs[NL80211_ATTR_IE]));
 }
@@ -7328,11 +7546,73 @@ static bool ht_rateset_to_mask(struct ieee80211_supported_band *sband,
 	return true;
 }
 
+static u16 vht_mcs_map_to_mcs_mask(u8 vht_mcs_map)
+{
+	u16 mcs_mask = 0;
+
+	switch (vht_mcs_map) {
+	case IEEE80211_VHT_MCS_NOT_SUPPORTED:
+		break;
+	case IEEE80211_VHT_MCS_SUPPORT_0_7:
+		mcs_mask = 0x00FF;
+		break;
+	case IEEE80211_VHT_MCS_SUPPORT_0_8:
+		mcs_mask = 0x01FF;
+		break;
+	case IEEE80211_VHT_MCS_SUPPORT_0_9:
+		mcs_mask = 0x03FF;
+		break;
+	default:
+		break;
+	}
+
+	return mcs_mask;
+}
+
+static void vht_build_mcs_mask(u16 vht_mcs_map,
+			       u16 vht_mcs_mask[NL80211_VHT_NSS_MAX])
+{
+	u8 nss;
+
+	for (nss = 0; nss < NL80211_VHT_NSS_MAX; nss++) {
+		vht_mcs_mask[nss] = vht_mcs_map_to_mcs_mask(vht_mcs_map & 0x03);
+		vht_mcs_map >>= 2;
+	}
+}
+
+static bool vht_set_mcs_mask(struct ieee80211_supported_band *sband,
+			     struct nl80211_txrate_vht *txrate,
+			     u16 mcs[NL80211_VHT_NSS_MAX])
+{
+	u16 tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map);
+	u16 tx_mcs_mask[NL80211_VHT_NSS_MAX] = {};
+	u8 i;
+
+	if (!sband->vht_cap.vht_supported)
+		return false;
+
+	memset(mcs, 0, sizeof(u16) * NL80211_VHT_NSS_MAX);
+
+	/* Build vht_mcs_mask from VHT capabilities */
+	vht_build_mcs_mask(tx_mcs_map, tx_mcs_mask);
+
+	for (i = 0; i < NL80211_VHT_NSS_MAX; i++) {
+		if ((tx_mcs_mask[i] & txrate->mcs[i]) == txrate->mcs[i])
+			mcs[i] = txrate->mcs[i];
+		else
+			return false;
+	}
+
+	return true;
+}
+
 static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = {
 	[NL80211_TXRATE_LEGACY] = { .type = NLA_BINARY,
 				    .len = NL80211_MAX_SUPP_RATES },
-	[NL80211_TXRATE_MCS] = { .type = NLA_BINARY,
-				 .len = NL80211_MAX_SUPP_HT_RATES },
+	[NL80211_TXRATE_HT] = { .type = NLA_BINARY,
+				.len = NL80211_MAX_SUPP_HT_RATES },
+	[NL80211_TXRATE_VHT] = { .len = sizeof(struct nl80211_txrate_vht)},
+	[NL80211_TXRATE_GI] = { .type = NLA_U8 },
 };
 
 static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
@@ -7345,9 +7625,7 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 	struct net_device *dev = info->user_ptr[1];
 	struct nlattr *tx_rates;
 	struct ieee80211_supported_band *sband;
-
-	if (info->attrs[NL80211_ATTR_TX_RATES] == NULL)
-		return -EINVAL;
+	u16 vht_tx_mcs_map;
 
 	if (!rdev->ops->set_bitrate_mask)
 		return -EOPNOTSUPP;
@@ -7356,32 +7634,44 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 	/* Default to all rates enabled */
 	for (i = 0; i < IEEE80211_NUM_BANDS; i++) {
 		sband = rdev->wiphy.bands[i];
-		mask.control[i].legacy =
-			sband ? (1 << sband->n_bitrates) - 1 : 0;
-		if (sband)
-			memcpy(mask.control[i].mcs,
-			       sband->ht_cap.mcs.rx_mask,
-			       sizeof(mask.control[i].mcs));
-		else
-			memset(mask.control[i].mcs, 0,
-			       sizeof(mask.control[i].mcs));
+
+		if (!sband)
+			continue;
+
+		mask.control[i].legacy = (1 << sband->n_bitrates) - 1;
+		memcpy(mask.control[i].ht_mcs,
+		       sband->ht_cap.mcs.rx_mask,
+		       sizeof(mask.control[i].ht_mcs));
+
+		if (!sband->vht_cap.vht_supported)
+			continue;
+
+		vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map);
+		vht_build_mcs_mask(vht_tx_mcs_map, mask.control[i].vht_mcs);
 	}
 
+	/* if no rates are given set it back to the defaults */
+	if (!info->attrs[NL80211_ATTR_TX_RATES])
+		goto out;
+
 	/*
 	 * The nested attribute uses enum nl80211_band as the index. This maps
 	 * directly to the enum ieee80211_band values used in cfg80211.
 	 */
 	BUILD_BUG_ON(NL80211_MAX_SUPP_HT_RATES > IEEE80211_HT_MCS_MASK_LEN * 8);
-	nla_for_each_nested(tx_rates, info->attrs[NL80211_ATTR_TX_RATES], rem)
-	{
+	nla_for_each_nested(tx_rates, info->attrs[NL80211_ATTR_TX_RATES], rem) {
 		enum ieee80211_band band = nla_type(tx_rates);
+		int err;
+
 		if (band < 0 || band >= IEEE80211_NUM_BANDS)
 			return -EINVAL;
 		sband = rdev->wiphy.bands[band];
 		if (sband == NULL)
 			return -EINVAL;
-		nla_parse(tb, NL80211_TXRATE_MAX, nla_data(tx_rates),
-			  nla_len(tx_rates), nl80211_txattr_policy);
+		err = nla_parse(tb, NL80211_TXRATE_MAX, nla_data(tx_rates),
+				nla_len(tx_rates), nl80211_txattr_policy);
+		if (err)
+			return err;
 		if (tb[NL80211_TXRATE_LEGACY]) {
 			mask.control[band].legacy = rateset_to_mask(
 				sband,
@@ -7391,31 +7681,50 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 			    nla_len(tb[NL80211_TXRATE_LEGACY]))
 				return -EINVAL;
 		}
-		if (tb[NL80211_TXRATE_MCS]) {
+		if (tb[NL80211_TXRATE_HT]) {
 			if (!ht_rateset_to_mask(
 					sband,
-					nla_data(tb[NL80211_TXRATE_MCS]),
-					nla_len(tb[NL80211_TXRATE_MCS]),
-					mask.control[band].mcs))
+					nla_data(tb[NL80211_TXRATE_HT]),
+					nla_len(tb[NL80211_TXRATE_HT]),
+					mask.control[band].ht_mcs))
+				return -EINVAL;
+		}
+		if (tb[NL80211_TXRATE_VHT]) {
+			if (!vht_set_mcs_mask(
+					sband,
+					nla_data(tb[NL80211_TXRATE_VHT]),
+					mask.control[band].vht_mcs))
+				return -EINVAL;
+		}
+		if (tb[NL80211_TXRATE_GI]) {
+			mask.control[band].gi =
+				nla_get_u8(tb[NL80211_TXRATE_GI]);
+			if (mask.control[band].gi > NL80211_TXRATE_FORCE_LGI)
 				return -EINVAL;
 		}
 
 		if (mask.control[band].legacy == 0) {
-			/* don't allow empty legacy rates if HT
-			 * is not even supported. */
-			if (!rdev->wiphy.bands[band]->ht_cap.ht_supported)
+			/* don't allow empty legacy rates if HT or VHT
+			 * are not even supported.
+			 */
+			if (!(rdev->wiphy.bands[band]->ht_cap.ht_supported ||
+			      rdev->wiphy.bands[band]->vht_cap.vht_supported))
 				return -EINVAL;
 
 			for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++)
-				if (mask.control[band].mcs[i])
-					break;
+				if (mask.control[band].ht_mcs[i])
+					goto out;
+
+			for (i = 0; i < NL80211_VHT_NSS_MAX; i++)
+				if (mask.control[band].vht_mcs[i])
+					goto out;
 
 			/* legacy and mcs rates may not be both empty */
-			if (i == IEEE80211_HT_MCS_MASK_LEN)
-				return -EINVAL;
+			return -EINVAL;
 		}
 	}
 
+out:
 	return rdev_set_bitrate_mask(rdev, dev, NULL, &mask);
 }
 
@@ -7525,6 +7834,27 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 	if (!chandef.chan && params.offchan)
 		return -EINVAL;
 
+	params.buf = nla_data(info->attrs[NL80211_ATTR_FRAME]);
+	params.len = nla_len(info->attrs[NL80211_ATTR_FRAME]);
+
+	if (info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]) {
+		int len = nla_len(info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]);
+		int i;
+
+		if (len % sizeof(u16))
+			return -EINVAL;
+
+		params.n_csa_offsets = len / sizeof(u16);
+		params.csa_offsets =
+			nla_data(info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]);
+
+		/* check that all the offsets fit the frame */
+		for (i = 0; i < params.n_csa_offsets; i++) {
+			if (params.csa_offsets[i] >= params.len)
+				return -EINVAL;
+		}
+	}
+
 	if (!params.dont_wait_for_ack) {
 		msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 		if (!msg)
@@ -7538,8 +7868,6 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	params.buf = nla_data(info->attrs[NL80211_ATTR_FRAME]);
-	params.len = nla_len(info->attrs[NL80211_ATTR_FRAME]);
 	params.chan = chandef.chan;
 	err = cfg80211_mlme_mgmt_tx(rdev, wdev, &params, &cookie);
 	if (err)
@@ -7669,8 +7997,8 @@ static int nl80211_get_power_save(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
-static struct nla_policy
-nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] __read_mostly = {
+static const struct nla_policy
+nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] = {
 	[NL80211_ATTR_CQM_RSSI_THOLD] = { .type = NLA_U32 },
 	[NL80211_ATTR_CQM_RSSI_HYST] = { .type = NLA_U32 },
 	[NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT] = { .type = NLA_U32 },
@@ -8236,6 +8564,8 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 
 		nla_for_each_nested(pat, tb[NL80211_WOWLAN_TRIG_PKT_PATTERN],
 				    rem) {
+			u8 *mask_pat;
+
 			nla_parse(pat_tb, MAX_NL80211_PKTPAT, nla_data(pat),
 				  nla_len(pat), NULL);
 			err = -EINVAL;
@@ -8259,19 +8589,18 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 				goto error;
 			new_triggers.patterns[i].pkt_offset = pkt_offset;
 
-			new_triggers.patterns[i].mask =
-				kmalloc(mask_len + pat_len, GFP_KERNEL);
-			if (!new_triggers.patterns[i].mask) {
+			mask_pat = kmalloc(mask_len + pat_len, GFP_KERNEL);
+			if (!mask_pat) {
 				err = -ENOMEM;
 				goto error;
 			}
-			new_triggers.patterns[i].pattern =
-				new_triggers.patterns[i].mask + mask_len;
-			memcpy(new_triggers.patterns[i].mask,
-			       nla_data(pat_tb[NL80211_PKTPAT_MASK]),
+			new_triggers.patterns[i].mask = mask_pat;
+			memcpy(mask_pat, nla_data(pat_tb[NL80211_PKTPAT_MASK]),
 			       mask_len);
+			mask_pat += mask_len;
+			new_triggers.patterns[i].pattern = mask_pat;
 			new_triggers.patterns[i].pattern_len = pat_len;
-			memcpy(new_triggers.patterns[i].pattern,
+			memcpy(mask_pat,
 			       nla_data(pat_tb[NL80211_PKTPAT_PATTERN]),
 			       pat_len);
 			i++;
@@ -8463,6 +8792,8 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
 
 	nla_for_each_nested(pat, tb[NL80211_ATTR_COALESCE_RULE_PKT_PATTERN],
 			    rem) {
+		u8 *mask_pat;
+
 		nla_parse(pat_tb, MAX_NL80211_PKTPAT, nla_data(pat),
 			  nla_len(pat), NULL);
 		if (!pat_tb[NL80211_PKTPAT_MASK] ||
@@ -8484,17 +8815,19 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
 			return -EINVAL;
 		new_rule->patterns[i].pkt_offset = pkt_offset;
 
-		new_rule->patterns[i].mask =
-			kmalloc(mask_len + pat_len, GFP_KERNEL);
-		if (!new_rule->patterns[i].mask)
+		mask_pat = kmalloc(mask_len + pat_len, GFP_KERNEL);
+		if (!mask_pat)
 			return -ENOMEM;
-		new_rule->patterns[i].pattern =
-			new_rule->patterns[i].mask + mask_len;
-		memcpy(new_rule->patterns[i].mask,
-		       nla_data(pat_tb[NL80211_PKTPAT_MASK]), mask_len);
+
+		new_rule->patterns[i].mask = mask_pat;
+		memcpy(mask_pat, nla_data(pat_tb[NL80211_PKTPAT_MASK]),
+		       mask_len);
+
+		mask_pat += mask_len;
+		new_rule->patterns[i].pattern = mask_pat;
 		new_rule->patterns[i].pattern_len = pat_len;
-		memcpy(new_rule->patterns[i].pattern,
-		       nla_data(pat_tb[NL80211_PKTPAT_PATTERN]), pat_len);
+		memcpy(mask_pat, nla_data(pat_tb[NL80211_PKTPAT_PATTERN]),
+		       pat_len);
 		i++;
 	}
 
@@ -8739,9 +9072,8 @@ static int nl80211_start_p2p_device(struct sk_buff *skb, struct genl_info *info)
 	if (wdev->p2p_started)
 		return 0;
 
-	err = cfg80211_can_add_interface(rdev, wdev->iftype);
-	if (err)
-		return err;
+	if (rfkill_blocked(rdev->rfkill))
+		return -ERFKILL;
 
 	err = rdev_start_p2p_device(rdev, wdev);
 	if (err)
@@ -8875,6 +9207,162 @@ static int nl80211_crit_protocol_stop(struct sk_buff *skb,
 	return 0;
 }
 
+static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct wireless_dev *wdev =
+		__cfg80211_wdev_from_attrs(genl_info_net(info), info->attrs);
+	int i, err;
+	u32 vid, subcmd;
+
+	if (!rdev->wiphy.vendor_commands)
+		return -EOPNOTSUPP;
+
+	if (IS_ERR(wdev)) {
+		err = PTR_ERR(wdev);
+		if (err != -EINVAL)
+			return err;
+		wdev = NULL;
+	} else if (wdev->wiphy != &rdev->wiphy) {
+		return -EINVAL;
+	}
+
+	if (!info->attrs[NL80211_ATTR_VENDOR_ID] ||
+	    !info->attrs[NL80211_ATTR_VENDOR_SUBCMD])
+		return -EINVAL;
+
+	vid = nla_get_u32(info->attrs[NL80211_ATTR_VENDOR_ID]);
+	subcmd = nla_get_u32(info->attrs[NL80211_ATTR_VENDOR_SUBCMD]);
+	for (i = 0; i < rdev->wiphy.n_vendor_commands; i++) {
+		const struct wiphy_vendor_command *vcmd;
+		void *data = NULL;
+		int len = 0;
+
+		vcmd = &rdev->wiphy.vendor_commands[i];
+
+		if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd)
+			continue;
+
+		if (vcmd->flags & (WIPHY_VENDOR_CMD_NEED_WDEV |
+				   WIPHY_VENDOR_CMD_NEED_NETDEV)) {
+			if (!wdev)
+				return -EINVAL;
+			if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_NETDEV &&
+			    !wdev->netdev)
+				return -EINVAL;
+
+			if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) {
+				if (wdev->netdev &&
+				    !netif_running(wdev->netdev))
+					return -ENETDOWN;
+				if (!wdev->netdev && !wdev->p2p_started)
+					return -ENETDOWN;
+			}
+		} else {
+			wdev = NULL;
+		}
+
+		if (info->attrs[NL80211_ATTR_VENDOR_DATA]) {
+			data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]);
+			len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]);
+		}
+
+		rdev->cur_cmd_info = info;
+		err = rdev->wiphy.vendor_commands[i].doit(&rdev->wiphy, wdev,
+							  data, len);
+		rdev->cur_cmd_info = NULL;
+		return err;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy,
+					   enum nl80211_commands cmd,
+					   enum nl80211_attrs attr,
+					   int approxlen)
+{
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+
+	if (WARN_ON(!rdev->cur_cmd_info))
+		return NULL;
+
+	return __cfg80211_alloc_vendor_skb(rdev, approxlen,
+					   rdev->cur_cmd_info->snd_portid,
+					   rdev->cur_cmd_info->snd_seq,
+					   cmd, attr, NULL, GFP_KERNEL);
+}
+EXPORT_SYMBOL(__cfg80211_alloc_reply_skb);
+
+int cfg80211_vendor_cmd_reply(struct sk_buff *skb)
+{
+	struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
+	void *hdr = ((void **)skb->cb)[1];
+	struct nlattr *data = ((void **)skb->cb)[2];
+
+	if (WARN_ON(!rdev->cur_cmd_info)) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	nla_nest_end(skb, data);
+	genlmsg_end(skb, hdr);
+	return genlmsg_reply(skb, rdev->cur_cmd_info);
+}
+EXPORT_SYMBOL_GPL(cfg80211_vendor_cmd_reply);
+
+
+static int nl80211_set_qos_map(struct sk_buff *skb,
+			       struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct cfg80211_qos_map *qos_map = NULL;
+	struct net_device *dev = info->user_ptr[1];
+	u8 *pos, len, num_des, des_len, des;
+	int ret;
+
+	if (!rdev->ops->set_qos_map)
+		return -EOPNOTSUPP;
+
+	if (info->attrs[NL80211_ATTR_QOS_MAP]) {
+		pos = nla_data(info->attrs[NL80211_ATTR_QOS_MAP]);
+		len = nla_len(info->attrs[NL80211_ATTR_QOS_MAP]);
+
+		if (len % 2 || len < IEEE80211_QOS_MAP_LEN_MIN ||
+		    len > IEEE80211_QOS_MAP_LEN_MAX)
+			return -EINVAL;
+
+		qos_map = kzalloc(sizeof(struct cfg80211_qos_map), GFP_KERNEL);
+		if (!qos_map)
+			return -ENOMEM;
+
+		num_des = (len - IEEE80211_QOS_MAP_LEN_MIN) >> 1;
+		if (num_des) {
+			des_len = num_des *
+				sizeof(struct cfg80211_dscp_exception);
+			memcpy(qos_map->dscp_exception, pos, des_len);
+			qos_map->num_des = num_des;
+			for (des = 0; des < num_des; des++) {
+				if (qos_map->dscp_exception[des].up > 7) {
+					kfree(qos_map);
+					return -EINVAL;
+				}
+			}
+			pos += des_len;
+		}
+		memcpy(qos_map->up, pos, IEEE80211_QOS_MAP_LEN_MIN);
+	}
+
+	wdev_lock(dev->ieee80211_ptr);
+	ret = nl80211_key_allowed(dev->ieee80211_ptr);
+	if (!ret)
+		ret = rdev_set_qos_map(rdev, dev, qos_map);
+	wdev_unlock(dev->ieee80211_ptr);
+
+	kfree(qos_map);
+	return ret;
+}
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -8918,7 +9406,7 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
 		}
 
 		dev = wdev->netdev;
-		rdev = wiphy_to_dev(wdev->wiphy);
+		rdev = wiphy_to_rdev(wdev->wiphy);
 
 		if (ops->internal_flags & NL80211_FLAG_NEED_NETDEV) {
 			if (!dev) {
@@ -9599,20 +10087,40 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_VENDOR,
+		.doit = nl80211_vendor_cmd,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_WIPHY |
+				  NL80211_FLAG_NEED_RTNL,
+	},
+	{
+		.cmd = NL80211_CMD_SET_QOS_MAP,
+		.doit = nl80211_set_qos_map,
+		.policy = nl80211_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 /* notification functions */
 
-void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev)
+void nl80211_notify_wiphy(struct cfg80211_registered_device *rdev,
+			  enum nl80211_commands cmd)
 {
 	struct sk_buff *msg;
 	struct nl80211_dump_wiphy_state state = {};
 
+	WARN_ON(cmd != NL80211_CMD_NEW_WIPHY &&
+		cmd != NL80211_CMD_DEL_WIPHY);
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return;
 
-	if (nl80211_send_wiphy(rdev, msg, 0, 0, 0, &state) < 0) {
+	if (nl80211_send_wiphy(rdev, cmd, msg, 0, 0, 0, &state) < 0) {
 		nlmsg_free(msg);
 		return;
 	}
@@ -9732,40 +10240,31 @@ void nl80211_send_scan_start(struct cfg80211_registered_device *rdev,
 				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
-void nl80211_send_scan_done(struct cfg80211_registered_device *rdev,
-			    struct wireless_dev *wdev)
+struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev,
+				       struct wireless_dev *wdev, bool aborted)
 {
 	struct sk_buff *msg;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
-		return;
+		return NULL;
 
 	if (nl80211_send_scan_msg(msg, rdev, wdev, 0, 0, 0,
-				  NL80211_CMD_NEW_SCAN_RESULTS) < 0) {
+				  aborted ? NL80211_CMD_SCAN_ABORTED :
+					    NL80211_CMD_NEW_SCAN_RESULTS) < 0) {
 		nlmsg_free(msg);
-		return;
+		return NULL;
 	}
 
-	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				NL80211_MCGRP_SCAN, GFP_KERNEL);
+	return msg;
 }
 
-void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev,
-			       struct wireless_dev *wdev)
+void nl80211_send_scan_result(struct cfg80211_registered_device *rdev,
+			      struct sk_buff *msg)
 {
-	struct sk_buff *msg;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return;
 
-	if (nl80211_send_scan_msg(msg, rdev, wdev, 0, 0, 0,
-				  NL80211_CMD_SCAN_ABORTED) < 0) {
-		nlmsg_free(msg);
-		return;
-	}
-
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
@@ -9940,7 +10439,7 @@ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	const struct ieee80211_mgmt *mgmt = (void *)buf;
 	u32 cmd;
 
@@ -10162,7 +10661,7 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev, const u8 *addr,
 					const u8* ie, u8 ie_len, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -10342,7 +10841,7 @@ void cfg80211_ready_on_channel(struct wireless_dev *wdev, u64 cookie,
 			       unsigned int duration, gfp_t gfp)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_ready_on_channel(wdev, cookie, chan, duration);
 	nl80211_send_remain_on_chan_event(NL80211_CMD_REMAIN_ON_CHANNEL,
@@ -10356,7 +10855,7 @@ void cfg80211_remain_on_channel_expired(struct wireless_dev *wdev, u64 cookie,
 					gfp_t gfp)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_ready_on_channel_expired(wdev, cookie, chan);
 	nl80211_send_remain_on_chan_event(NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL,
@@ -10368,7 +10867,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
 		      struct station_info *sinfo, gfp_t gfp)
 {
 	struct wiphy *wiphy = dev->ieee80211_ptr->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 
 	trace_cfg80211_new_sta(dev, mac_addr, sinfo);
@@ -10391,7 +10890,7 @@ EXPORT_SYMBOL(cfg80211_new_sta);
 void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp)
 {
 	struct wiphy *wiphy = dev->ieee80211_ptr->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -10428,7 +10927,7 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr,
 			  gfp_t gfp)
 {
 	struct wiphy *wiphy = dev->ieee80211_ptr->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -10463,7 +10962,7 @@ static bool __nl80211_unexpected_frame(struct net_device *dev, u8 cmd,
 				       const u8 *addr, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 	u32 nlportid = ACCESS_ONCE(wdev->ap_unexpected_nlportid);
@@ -10583,7 +11082,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 			     const u8 *buf, size_t len, bool ack, gfp_t gfp)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct net_device *netdev = wdev->netdev;
 	struct sk_buff *msg;
 	void *hdr;
@@ -10627,7 +11126,7 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	struct nlattr *pinfoattr;
 	void *hdr;
@@ -10719,7 +11218,7 @@ void cfg80211_gtk_rekey_notify(struct net_device *dev, const u8 *bssid,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_gtk_rekey_notify(dev, bssid);
 	nl80211_gtk_rekey_notify(rdev, dev, bssid, replay_ctr, gfp);
@@ -10777,7 +11276,7 @@ void cfg80211_pmksa_candidate_notify(struct net_device *dev, int index,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_pmksa_candidate_notify(dev, index, bssid, preauth);
 	nl80211_pmksa_candidate_notify(rdev, dev, index, bssid, preauth, gfp);
@@ -10824,7 +11323,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	ASSERT_WDEV_LOCK(wdev);
 
@@ -10836,7 +11335,8 @@ void cfg80211_ch_switch_notify(struct net_device *dev,
 		    wdev->iftype != NL80211_IFTYPE_MESH_POINT))
 		return;
 
-	wdev->channel = chandef->chan;
+	wdev->chandef = *chandef;
+	wdev->preset_chandef = *chandef;
 	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL);
 }
 EXPORT_SYMBOL(cfg80211_ch_switch_notify);
@@ -10847,7 +11347,7 @@ void cfg80211_cqm_txe_notify(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	struct nlattr *pinfoattr;
 	void *hdr;
@@ -10947,7 +11447,7 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	struct nlattr *pinfoattr;
 	void *hdr;
@@ -10994,7 +11494,7 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
 			   u64 cookie, bool acked, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -11034,7 +11534,7 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy,
 				 const u8 *frame, size_t len,
 				 int freq, int sig_dbm)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 	struct cfg80211_beacon_registration *reg;
@@ -11081,7 +11581,7 @@ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev,
 				   struct cfg80211_wowlan_wakeup *wakeup,
 				   gfp_t gfp)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 	int size = 200;
@@ -11191,7 +11691,7 @@ void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer,
 				u16 reason_code, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -11243,9 +11743,15 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) {
-		list_for_each_entry_rcu(wdev, &rdev->wdev_list, list)
+		bool schedule_destroy_work = false;
+
+		list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) {
 			cfg80211_mlme_unregister_socket(wdev, notify->portid);
 
+			if (wdev->owner_nlportid == notify->portid)
+				schedule_destroy_work = true;
+		}
+
 		spin_lock_bh(&rdev->beacon_registrations_lock);
 		list_for_each_entry_safe(reg, tmp, &rdev->beacon_registrations,
 					 list) {
@@ -11256,11 +11762,24 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 			}
 		}
 		spin_unlock_bh(&rdev->beacon_registrations_lock);
+
+		if (schedule_destroy_work) {
+			struct cfg80211_iface_destroy *destroy;
+
+			destroy = kzalloc(sizeof(*destroy), GFP_ATOMIC);
+			if (destroy) {
+				destroy->nlportid = notify->portid;
+				spin_lock(&rdev->destroy_list_lock);
+				list_add(&destroy->list, &rdev->destroy_list);
+				spin_unlock(&rdev->destroy_list_lock);
+				schedule_work(&rdev->destroy_work);
+			}
+		}
 	}
 
 	rcu_read_unlock();
 
-	return NOTIFY_DONE;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block nl80211_netlink_notifier = {
@@ -11271,7 +11790,7 @@ void cfg80211_ft_event(struct net_device *netdev,
 		       struct cfg80211_ft_event_params *ft_event)
 {
 	struct wiphy *wiphy = netdev->ieee80211_ptr->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -11318,7 +11837,7 @@ void cfg80211_crit_proto_stopped(struct wireless_dev *wdev, gfp_t gfp)
 	void *hdr;
 	u32 nlportid;
 
-	rdev = wiphy_to_dev(wdev->wiphy);
+	rdev = wiphy_to_rdev(wdev->wiphy);
 	if (!rdev->crit_proto_nlportid)
 		return;
 
@@ -11350,6 +11869,35 @@ void cfg80211_crit_proto_stopped(struct wireless_dev *wdev, gfp_t gfp)
 }
 EXPORT_SYMBOL(cfg80211_crit_proto_stopped);
 
+void nl80211_send_ap_stopped(struct wireless_dev *wdev)
+{
+	struct wiphy *wiphy = wdev->wiphy;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+	struct sk_buff *msg;
+	void *hdr;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_STOP_AP);
+	if (!hdr)
+		goto out;
+
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
+	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, wdev->netdev->ifindex) ||
+	    nla_put_u64(msg, NL80211_ATTR_WDEV, wdev_id(wdev)))
+		goto out;
+
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(wiphy), msg, 0,
+				NL80211_MCGRP_MLME, GFP_KERNEL);
+	return;
+ out:
+	nlmsg_free(msg);
+}
+
 /* initialisation/exit functions */
 
 int nl80211_init(void)
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index b1b231324e1..49c9a482dd1 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -5,13 +5,14 @@
 
 int nl80211_init(void);
 void nl80211_exit(void);
-void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev);
+void nl80211_notify_wiphy(struct cfg80211_registered_device *rdev,
+			  enum nl80211_commands cmd);
 void nl80211_send_scan_start(struct cfg80211_registered_device *rdev,
 			     struct wireless_dev *wdev);
-void nl80211_send_scan_done(struct cfg80211_registered_device *rdev,
-			    struct wireless_dev *wdev);
-void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev,
-			       struct wireless_dev *wdev);
+struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev,
+				       struct wireless_dev *wdev, bool aborted);
+void nl80211_send_scan_result(struct cfg80211_registered_device *rdev,
+			      struct sk_buff *msg);
 void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
 			     struct net_device *netdev, u32 cmd);
 void nl80211_send_sched_scan_results(struct cfg80211_registered_device *rdev,
@@ -74,6 +75,8 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev,
 		     enum nl80211_radar_event event,
 		     struct net_device *netdev, gfp_t gfp);
 
+void nl80211_send_ap_stopped(struct wireless_dev *wdev);
+
 void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev);
 
 #endif /* __NET_WIRELESS_NL80211_H */
diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index a271c27fac7..722da616438 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -124,6 +124,10 @@ int ieee80211_radiotap_iterator_init(
 	/* find payload start allowing for extended bitmap(s) */
 
 	if (iterator->_bitmap_shifter & (1<<IEEE80211_RADIOTAP_EXT)) {
+		if ((unsigned long)iterator->_arg -
+		    (unsigned long)iterator->_rtheader + sizeof(uint32_t) >
+		    (unsigned long)iterator->_max_length)
+			return -EINVAL;
 		while (get_unaligned_le32(iterator->_arg) &
 					(1 << IEEE80211_RADIOTAP_EXT)) {
 			iterator->_arg += sizeof(uint32_t);
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index a6c03ab14a0..d95bbe34813 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -199,7 +199,7 @@ static inline int rdev_change_station(struct cfg80211_registered_device *rdev,
 }
 
 static inline int rdev_get_station(struct cfg80211_registered_device *rdev,
-				   struct net_device *dev, u8 *mac,
+				   struct net_device *dev, const u8 *mac,
 				   struct station_info *sinfo)
 {
 	int ret;
@@ -769,13 +769,16 @@ static inline int rdev_set_rekey_data(struct cfg80211_registered_device *rdev,
 static inline int rdev_tdls_mgmt(struct cfg80211_registered_device *rdev,
 				 struct net_device *dev, u8 *peer,
 				 u8 action_code, u8 dialog_token,
-				 u16 status_code, const u8 *buf, size_t len)
+				 u16 status_code, u32 peer_capability,
+				 const u8 *buf, size_t len)
 {
 	int ret;
 	trace_rdev_tdls_mgmt(&rdev->wiphy, dev, peer, action_code,
-			     dialog_token, status_code, buf, len);
+			     dialog_token, status_code, peer_capability,
+			     buf, len);
 	ret = rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, action_code,
-				   dialog_token, status_code, buf, len);
+				   dialog_token, status_code, peer_capability,
+				   buf, len);
 	trace_rdev_return_int(&rdev->wiphy, ret);
 	return ret;
 }
@@ -932,4 +935,32 @@ static inline int rdev_channel_switch(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int rdev_set_qos_map(struct cfg80211_registered_device *rdev,
+				   struct net_device *dev,
+				   struct cfg80211_qos_map *qos_map)
+{
+	int ret = -EOPNOTSUPP;
+
+	if (rdev->ops->set_qos_map) {
+		trace_rdev_set_qos_map(&rdev->wiphy, dev, qos_map);
+		ret = rdev->ops->set_qos_map(&rdev->wiphy, dev, qos_map);
+		trace_rdev_return_int(&rdev->wiphy, ret);
+	}
+
+	return ret;
+}
+
+static inline int
+rdev_set_ap_chanwidth(struct cfg80211_registered_device *rdev,
+		      struct net_device *dev, struct cfg80211_chan_def *chandef)
+{
+	int ret;
+
+	trace_rdev_set_ap_chanwidth(&rdev->wiphy, dev, chandef);
+	ret = rdev->ops->set_ap_chanwidth(&rdev->wiphy, dev, chandef);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+
+	return ret;
+}
+
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index ec54e1aac8e..1afdf45db38 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -65,11 +65,26 @@
 #define REG_DBG_PRINT(args...)
 #endif
 
+/**
+ * enum reg_request_treatment - regulatory request treatment
+ *
+ * @REG_REQ_OK: continue processing the regulatory request
+ * @REG_REQ_IGNORE: ignore the regulatory request
+ * @REG_REQ_INTERSECT: the regulatory domain resulting from this request should
+ *	be intersected with the current one.
+ * @REG_REQ_ALREADY_SET: the regulatory request will not change the current
+ *	regulatory settings, and no further processing is required.
+ * @REG_REQ_USER_HINT_HANDLED: a non alpha2  user hint was handled and no
+ *	further processing is required, i.e., not need to update last_request
+ *	etc. This should be used for user hints that do not provide an alpha2
+ *	but some other type of regulatory hint, i.e., indoor operation.
+ */
 enum reg_request_treatment {
 	REG_REQ_OK,
 	REG_REQ_IGNORE,
 	REG_REQ_INTERSECT,
 	REG_REQ_ALREADY_SET,
+	REG_REQ_USER_HINT_HANDLED,
 };
 
 static struct regulatory_request core_request_world = {
@@ -91,10 +106,6 @@ static struct regulatory_request __rcu *last_request =
 /* To trigger userspace events */
 static struct platform_device *reg_pdev;
 
-static struct device_type reg_device_type = {
-	.uevent = reg_device_uevent,
-};
-
 /*
  * Central wireless core regulatory domains, we only need two,
  * the current one and a world regulatory domain in case we have no
@@ -110,6 +121,14 @@ const struct ieee80211_regdomain __rcu *cfg80211_regdomain;
  */
 static int reg_num_devs_support_basehint;
 
+/*
+ * State variable indicating if the platform on which the devices
+ * are attached is operating in an indoor environment. The state variable
+ * is relevant for all registered devices.
+ * (protected by RTNL)
+ */
+static bool reg_is_indoor;
+
 static const struct ieee80211_regdomain *get_cfg80211_regdom(void)
 {
 	return rtnl_dereference(cfg80211_regdomain);
@@ -135,6 +154,33 @@ static const char *reg_dfs_region_str(enum nl80211_dfs_regions dfs_region)
 	return "Unknown";
 }
 
+enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy)
+{
+	const struct ieee80211_regdomain *regd = NULL;
+	const struct ieee80211_regdomain *wiphy_regd = NULL;
+
+	regd = get_cfg80211_regdom();
+	if (!wiphy)
+		goto out;
+
+	wiphy_regd = get_wiphy_regdom(wiphy);
+	if (!wiphy_regd)
+		goto out;
+
+	if (wiphy_regd->dfs_region == regd->dfs_region)
+		goto out;
+
+	REG_DBG_PRINT("%s: device specific dfs_region "
+		      "(%s) disagrees with cfg80211's "
+		      "central dfs_region (%s)\n",
+		      dev_name(&wiphy->dev),
+		      reg_dfs_region_str(wiphy_regd->dfs_region),
+		      reg_dfs_region_str(regd->dfs_region));
+
+out:
+	return regd->dfs_region;
+}
+
 static void rcu_free_regdom(const struct ieee80211_regdomain *r)
 {
 	if (!r)
@@ -217,11 +263,15 @@ static char user_alpha2[2];
 module_param(ieee80211_regdom, charp, 0444);
 MODULE_PARM_DESC(ieee80211_regdom, "IEEE 802.11 regulatory domain code");
 
-static void reg_kfree_last_request(void)
+static void reg_free_request(struct regulatory_request *request)
 {
-	struct regulatory_request *lr;
+	if (request != get_last_request())
+		kfree(request);
+}
 
-	lr = get_last_request();
+static void reg_free_last_request(void)
+{
+	struct regulatory_request *lr = get_last_request();
 
 	if (lr != &core_request_world && lr)
 		kfree_rcu(lr, rcu_head);
@@ -229,7 +279,13 @@ static void reg_kfree_last_request(void)
 
 static void reg_update_last_request(struct regulatory_request *request)
 {
-	reg_kfree_last_request();
+	struct regulatory_request *lr;
+
+	lr = get_last_request();
+	if (lr == request)
+		return;
+
+	reg_free_last_request();
 	rcu_assign_pointer(last_request, request);
 }
 
@@ -460,11 +516,16 @@ static inline void reg_regdb_query(const char *alpha2) {}
 
 /*
  * This lets us keep regulatory code which is updated on a regulatory
- * basis in userspace. Country information is filled in by
- * reg_device_uevent
+ * basis in userspace.
  */
 static int call_crda(const char *alpha2)
 {
+	char country[12];
+	char *env[] = { country, NULL };
+
+	snprintf(country, sizeof(country), "COUNTRY=%c%c",
+		 alpha2[0], alpha2[1]);
+
 	if (!is_world_regdom((char *) alpha2))
 		pr_info("Calling CRDA for country: %c%c\n",
 			alpha2[0], alpha2[1]);
@@ -474,7 +535,7 @@ static int call_crda(const char *alpha2)
 	/* query internal regulatory database (if it exists) */
 	reg_regdb_query(alpha2);
 
-	return kobject_uevent(&reg_pdev->dev.kobj, KOBJ_CHANGE);
+	return kobject_uevent_env(&reg_pdev->dev.kobj, KOBJ_CHANGE, env);
 }
 
 static enum reg_request_treatment
@@ -495,6 +556,71 @@ bool reg_is_valid_request(const char *alpha2)
 	return alpha2_equal(lr->alpha2, alpha2);
 }
 
+static const struct ieee80211_regdomain *reg_get_regdomain(struct wiphy *wiphy)
+{
+	struct regulatory_request *lr = get_last_request();
+
+	/*
+	 * Follow the driver's regulatory domain, if present, unless a country
+	 * IE has been processed or a user wants to help complaince further
+	 */
+	if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE &&
+	    lr->initiator != NL80211_REGDOM_SET_BY_USER &&
+	    wiphy->regd)
+		return get_wiphy_regdom(wiphy);
+
+	return get_cfg80211_regdom();
+}
+
+unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd,
+				   const struct ieee80211_reg_rule *rule)
+{
+	const struct ieee80211_freq_range *freq_range = &rule->freq_range;
+	const struct ieee80211_freq_range *freq_range_tmp;
+	const struct ieee80211_reg_rule *tmp;
+	u32 start_freq, end_freq, idx, no;
+
+	for (idx = 0; idx < rd->n_reg_rules; idx++)
+		if (rule == &rd->reg_rules[idx])
+			break;
+
+	if (idx == rd->n_reg_rules)
+		return 0;
+
+	/* get start_freq */
+	no = idx;
+
+	while (no) {
+		tmp = &rd->reg_rules[--no];
+		freq_range_tmp = &tmp->freq_range;
+
+		if (freq_range_tmp->end_freq_khz < freq_range->start_freq_khz)
+			break;
+
+		freq_range = freq_range_tmp;
+	}
+
+	start_freq = freq_range->start_freq_khz;
+
+	/* get end_freq */
+	freq_range = &rule->freq_range;
+	no = idx;
+
+	while (no < rd->n_reg_rules - 1) {
+		tmp = &rd->reg_rules[++no];
+		freq_range_tmp = &tmp->freq_range;
+
+		if (freq_range_tmp->start_freq_khz > freq_range->end_freq_khz)
+			break;
+
+		freq_range = freq_range_tmp;
+	}
+
+	end_freq = freq_range->end_freq_khz;
+
+	return end_freq - start_freq;
+}
+
 /* Sanity check on a regulatory rule */
 static bool is_valid_reg_rule(const struct ieee80211_reg_rule *rule)
 {
@@ -603,7 +729,9 @@ reg_intersect_dfs_region(const enum nl80211_dfs_regions dfs_region1,
  * Helper for regdom_intersect(), this does the real
  * mathematical intersection fun
  */
-static int reg_rules_intersect(const struct ieee80211_reg_rule *rule1,
+static int reg_rules_intersect(const struct ieee80211_regdomain *rd1,
+			       const struct ieee80211_regdomain *rd2,
+			       const struct ieee80211_reg_rule *rule1,
 			       const struct ieee80211_reg_rule *rule2,
 			       struct ieee80211_reg_rule *intersected_rule)
 {
@@ -611,7 +739,7 @@ static int reg_rules_intersect(const struct ieee80211_reg_rule *rule1,
 	struct ieee80211_freq_range *freq_range;
 	const struct ieee80211_power_rule *power_rule1, *power_rule2;
 	struct ieee80211_power_rule *power_rule;
-	u32 freq_diff;
+	u32 freq_diff, max_bandwidth1, max_bandwidth2;
 
 	freq_range1 = &rule1->freq_range;
 	freq_range2 = &rule2->freq_range;
@@ -625,8 +753,32 @@ static int reg_rules_intersect(const struct ieee80211_reg_rule *rule1,
 					 freq_range2->start_freq_khz);
 	freq_range->end_freq_khz = min(freq_range1->end_freq_khz,
 				       freq_range2->end_freq_khz);
-	freq_range->max_bandwidth_khz = min(freq_range1->max_bandwidth_khz,
-					    freq_range2->max_bandwidth_khz);
+
+	max_bandwidth1 = freq_range1->max_bandwidth_khz;
+	max_bandwidth2 = freq_range2->max_bandwidth_khz;
+
+	if (rule1->flags & NL80211_RRF_AUTO_BW)
+		max_bandwidth1 = reg_get_max_bandwidth(rd1, rule1);
+	if (rule2->flags & NL80211_RRF_AUTO_BW)
+		max_bandwidth2 = reg_get_max_bandwidth(rd2, rule2);
+
+	freq_range->max_bandwidth_khz = min(max_bandwidth1, max_bandwidth2);
+
+	intersected_rule->flags = rule1->flags | rule2->flags;
+
+	/*
+	 * In case NL80211_RRF_AUTO_BW requested for both rules
+	 * set AUTO_BW in intersected rule also. Next we will
+	 * calculate BW correctly in handle_channel function.
+	 * In other case remove AUTO_BW flag while we calculate
+	 * maximum bandwidth correctly and auto calculation is
+	 * not required.
+	 */
+	if ((rule1->flags & NL80211_RRF_AUTO_BW) &&
+	    (rule2->flags & NL80211_RRF_AUTO_BW))
+		intersected_rule->flags |= NL80211_RRF_AUTO_BW;
+	else
+		intersected_rule->flags &= ~NL80211_RRF_AUTO_BW;
 
 	freq_diff = freq_range->end_freq_khz - freq_range->start_freq_khz;
 	if (freq_range->max_bandwidth_khz > freq_diff)
@@ -637,7 +789,8 @@ static int reg_rules_intersect(const struct ieee80211_reg_rule *rule1,
 	power_rule->max_antenna_gain = min(power_rule1->max_antenna_gain,
 		power_rule2->max_antenna_gain);
 
-	intersected_rule->flags = rule1->flags | rule2->flags;
+	intersected_rule->dfs_cac_ms = max(rule1->dfs_cac_ms,
+					   rule2->dfs_cac_ms);
 
 	if (!is_valid_reg_rule(intersected_rule))
 		return -EINVAL;
@@ -686,7 +839,8 @@ regdom_intersect(const struct ieee80211_regdomain *rd1,
 		rule1 = &rd1->reg_rules[x];
 		for (y = 0; y < rd2->n_reg_rules; y++) {
 			rule2 = &rd2->reg_rules[y];
-			if (!reg_rules_intersect(rule1, rule2, &dummy_rule))
+			if (!reg_rules_intersect(rd1, rd2, rule1, rule2,
+						 &dummy_rule))
 				num_rules++;
 		}
 	}
@@ -711,7 +865,8 @@ regdom_intersect(const struct ieee80211_regdomain *rd1,
 			 * a memcpy()
 			 */
 			intersected_rule = &rd->reg_rules[rule_idx];
-			r = reg_rules_intersect(rule1, rule2, intersected_rule);
+			r = reg_rules_intersect(rd1, rd2, rule1, rule2,
+						intersected_rule);
 			/*
 			 * No need to memset here the intersected rule here as
 			 * we're not using the stack anymore
@@ -749,6 +904,8 @@ static u32 map_regdom_flags(u32 rd_flags)
 		channel_flags |= IEEE80211_CHAN_RADAR;
 	if (rd_flags & NL80211_RRF_NO_OFDM)
 		channel_flags |= IEEE80211_CHAN_NO_OFDM;
+	if (rd_flags & NL80211_RRF_NO_OUTDOOR)
+		channel_flags |= IEEE80211_CHAN_INDOOR_ONLY;
 	return channel_flags;
 }
 
@@ -794,18 +951,8 @@ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy,
 					       u32 center_freq)
 {
 	const struct ieee80211_regdomain *regd;
-	struct regulatory_request *lr = get_last_request();
 
-	/*
-	 * Follow the driver's regulatory domain, if present, unless a country
-	 * IE has been processed or a user wants to help complaince further
-	 */
-	if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE &&
-	    lr->initiator != NL80211_REGDOM_SET_BY_USER &&
-	    wiphy->regd)
-		regd = get_wiphy_regdom(wiphy);
-	else
-		regd = get_cfg80211_regdom();
+	regd = reg_get_regdomain(wiphy);
 
 	return freq_reg_info_regd(wiphy, center_freq, regd);
 }
@@ -830,31 +977,42 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator)
 EXPORT_SYMBOL(reg_initiator_name);
 
 #ifdef CONFIG_CFG80211_REG_DEBUG
-static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan,
+static void chan_reg_rule_print_dbg(const struct ieee80211_regdomain *regd,
+				    struct ieee80211_channel *chan,
 				    const struct ieee80211_reg_rule *reg_rule)
 {
 	const struct ieee80211_power_rule *power_rule;
 	const struct ieee80211_freq_range *freq_range;
-	char max_antenna_gain[32];
+	char max_antenna_gain[32], bw[32];
 
 	power_rule = &reg_rule->power_rule;
 	freq_range = &reg_rule->freq_range;
 
 	if (!power_rule->max_antenna_gain)
-		snprintf(max_antenna_gain, 32, "N/A");
+		snprintf(max_antenna_gain, sizeof(max_antenna_gain), "N/A");
 	else
-		snprintf(max_antenna_gain, 32, "%d", power_rule->max_antenna_gain);
+		snprintf(max_antenna_gain, sizeof(max_antenna_gain), "%d",
+			 power_rule->max_antenna_gain);
+
+	if (reg_rule->flags & NL80211_RRF_AUTO_BW)
+		snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO",
+			 freq_range->max_bandwidth_khz,
+			 reg_get_max_bandwidth(regd, reg_rule));
+	else
+		snprintf(bw, sizeof(bw), "%d KHz",
+			 freq_range->max_bandwidth_khz);
 
 	REG_DBG_PRINT("Updating information on frequency %d MHz with regulatory rule:\n",
 		      chan->center_freq);
 
-	REG_DBG_PRINT("%d KHz - %d KHz @ %d KHz), (%s mBi, %d mBm)\n",
+	REG_DBG_PRINT("%d KHz - %d KHz @ %s), (%s mBi, %d mBm)\n",
 		      freq_range->start_freq_khz, freq_range->end_freq_khz,
-		      freq_range->max_bandwidth_khz, max_antenna_gain,
+		      bw, max_antenna_gain,
 		      power_rule->max_eirp);
 }
 #else
-static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan,
+static void chan_reg_rule_print_dbg(const struct ieee80211_regdomain *regd,
+				    struct ieee80211_channel *chan,
 				    const struct ieee80211_reg_rule *reg_rule)
 {
 	return;
@@ -876,6 +1034,8 @@ static void handle_channel(struct wiphy *wiphy,
 	const struct ieee80211_freq_range *freq_range = NULL;
 	struct wiphy *request_wiphy = NULL;
 	struct regulatory_request *lr = get_last_request();
+	const struct ieee80211_regdomain *regd;
+	u32 max_bandwidth_khz;
 
 	request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx);
 
@@ -912,16 +1072,22 @@ static void handle_channel(struct wiphy *wiphy,
 		return;
 	}
 
-	chan_reg_rule_print_dbg(chan, reg_rule);
+	regd = reg_get_regdomain(wiphy);
+	chan_reg_rule_print_dbg(regd, chan, reg_rule);
 
 	power_rule = &reg_rule->power_rule;
 	freq_range = &reg_rule->freq_range;
 
-	if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(40))
+	max_bandwidth_khz = freq_range->max_bandwidth_khz;
+	/* Check if auto calculation requested */
+	if (reg_rule->flags & NL80211_RRF_AUTO_BW)
+		max_bandwidth_khz = reg_get_max_bandwidth(regd, reg_rule);
+
+	if (max_bandwidth_khz < MHZ_TO_KHZ(40))
 		bw_flags = IEEE80211_CHAN_NO_HT40;
-	if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(80))
+	if (max_bandwidth_khz < MHZ_TO_KHZ(80))
 		bw_flags |= IEEE80211_CHAN_NO_80MHZ;
-	if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(160))
+	if (max_bandwidth_khz < MHZ_TO_KHZ(160))
 		bw_flags |= IEEE80211_CHAN_NO_160MHZ;
 
 	if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER &&
@@ -938,6 +1104,13 @@ static void handle_channel(struct wiphy *wiphy,
 			(int) MBI_TO_DBI(power_rule->max_antenna_gain);
 		chan->max_reg_power = chan->max_power = chan->orig_mpwr =
 			(int) MBM_TO_DBM(power_rule->max_eirp);
+
+		if (chan->flags & IEEE80211_CHAN_RADAR) {
+			chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS;
+			if (reg_rule->dfs_cac_ms)
+				chan->dfs_cac_ms = reg_rule->dfs_cac_ms;
+		}
+
 		return;
 	}
 
@@ -950,6 +1123,14 @@ static void handle_channel(struct wiphy *wiphy,
 		min_t(int, chan->orig_mag,
 		      MBI_TO_DBI(power_rule->max_antenna_gain));
 	chan->max_reg_power = (int) MBM_TO_DBM(power_rule->max_eirp);
+
+	if (chan->flags & IEEE80211_CHAN_RADAR) {
+		if (reg_rule->dfs_cac_ms)
+			chan->dfs_cac_ms = reg_rule->dfs_cac_ms;
+		else
+			chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS;
+	}
+
 	if (chan->orig_mpwr) {
 		/*
 		 * Devices that use REGULATORY_COUNTRY_IE_FOLLOW_POWER
@@ -985,12 +1166,19 @@ static bool reg_request_cell_base(struct regulatory_request *request)
 	return request->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE;
 }
 
+static bool reg_request_indoor(struct regulatory_request *request)
+{
+	if (request->initiator != NL80211_REGDOM_SET_BY_USER)
+		return false;
+	return request->user_reg_hint_type == NL80211_USER_REG_HINT_INDOOR;
+}
+
 bool reg_last_request_cell_base(void)
 {
 	return reg_request_cell_base(get_last_request());
 }
 
-#ifdef CONFIG_CFG80211_CERTIFICATION_ONUS
+#ifdef CONFIG_CFG80211_REG_CELLULAR_HINTS
 /* Core specific check */
 static enum reg_request_treatment
 reg_ignore_cell_hint(struct regulatory_request *pending_request)
@@ -1307,6 +1495,7 @@ static void handle_channel_custom(struct wiphy *wiphy,
 	const struct ieee80211_reg_rule *reg_rule = NULL;
 	const struct ieee80211_power_rule *power_rule = NULL;
 	const struct ieee80211_freq_range *freq_range = NULL;
+	u32 max_bandwidth_khz;
 
 	reg_rule = freq_reg_info_regd(wiphy, MHZ_TO_KHZ(chan->center_freq),
 				      regd);
@@ -1319,16 +1508,21 @@ static void handle_channel_custom(struct wiphy *wiphy,
 		return;
 	}
 
-	chan_reg_rule_print_dbg(chan, reg_rule);
+	chan_reg_rule_print_dbg(regd, chan, reg_rule);
 
 	power_rule = &reg_rule->power_rule;
 	freq_range = &reg_rule->freq_range;
 
-	if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(40))
+	max_bandwidth_khz = freq_range->max_bandwidth_khz;
+	/* Check if auto calculation requested */
+	if (reg_rule->flags & NL80211_RRF_AUTO_BW)
+		max_bandwidth_khz = reg_get_max_bandwidth(regd, reg_rule);
+
+	if (max_bandwidth_khz < MHZ_TO_KHZ(40))
 		bw_flags = IEEE80211_CHAN_NO_HT40;
-	if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(80))
+	if (max_bandwidth_khz < MHZ_TO_KHZ(80))
 		bw_flags |= IEEE80211_CHAN_NO_80MHZ;
-	if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(160))
+	if (max_bandwidth_khz < MHZ_TO_KHZ(160))
 		bw_flags |= IEEE80211_CHAN_NO_160MHZ;
 
 	chan->flags |= map_regdom_flags(reg_rule->flags) | bw_flags;
@@ -1421,6 +1615,11 @@ __reg_process_hint_user(struct regulatory_request *user_request)
 {
 	struct regulatory_request *lr = get_last_request();
 
+	if (reg_request_indoor(user_request)) {
+		reg_is_indoor = true;
+		return REG_REQ_USER_HINT_HANDLED;
+	}
+
 	if (reg_request_cell_base(user_request))
 		return reg_ignore_cell_hint(user_request);
 
@@ -1468,8 +1667,9 @@ reg_process_hint_user(struct regulatory_request *user_request)
 
 	treatment = __reg_process_hint_user(user_request);
 	if (treatment == REG_REQ_IGNORE ||
-	    treatment == REG_REQ_ALREADY_SET) {
-		kfree(user_request);
+	    treatment == REG_REQ_ALREADY_SET ||
+	    treatment == REG_REQ_USER_HINT_HANDLED) {
+		reg_free_request(user_request);
 		return treatment;
 	}
 
@@ -1529,14 +1729,15 @@ reg_process_hint_driver(struct wiphy *wiphy,
 	case REG_REQ_OK:
 		break;
 	case REG_REQ_IGNORE:
-		kfree(driver_request);
+	case REG_REQ_USER_HINT_HANDLED:
+		reg_free_request(driver_request);
 		return treatment;
 	case REG_REQ_INTERSECT:
 		/* fall through */
 	case REG_REQ_ALREADY_SET:
 		regd = reg_copy_regd(get_cfg80211_regdom());
 		if (IS_ERR(regd)) {
-			kfree(driver_request);
+			reg_free_request(driver_request);
 			return REG_REQ_IGNORE;
 		}
 		rcu_assign_pointer(wiphy->regd, regd);
@@ -1628,12 +1829,13 @@ reg_process_hint_country_ie(struct wiphy *wiphy,
 	case REG_REQ_OK:
 		break;
 	case REG_REQ_IGNORE:
+	case REG_REQ_USER_HINT_HANDLED:
 		/* fall through */
 	case REG_REQ_ALREADY_SET:
-		kfree(country_ie_request);
+		reg_free_request(country_ie_request);
 		return treatment;
 	case REG_REQ_INTERSECT:
-		kfree(country_ie_request);
+		reg_free_request(country_ie_request);
 		/*
 		 * This doesn't happen yet, not sure we
 		 * ever want to support it for this case.
@@ -1656,43 +1858,46 @@ static void reg_process_hint(struct regulatory_request *reg_request)
 	struct wiphy *wiphy = NULL;
 	enum reg_request_treatment treatment;
 
-	if (WARN_ON(!reg_request->alpha2))
-		return;
-
 	if (reg_request->wiphy_idx != WIPHY_IDX_INVALID)
 		wiphy = wiphy_idx_to_wiphy(reg_request->wiphy_idx);
 
-	if (reg_request->initiator == NL80211_REGDOM_SET_BY_DRIVER && !wiphy) {
-		kfree(reg_request);
-		return;
-	}
-
 	switch (reg_request->initiator) {
 	case NL80211_REGDOM_SET_BY_CORE:
 		reg_process_hint_core(reg_request);
 		return;
 	case NL80211_REGDOM_SET_BY_USER:
 		treatment = reg_process_hint_user(reg_request);
-		if (treatment == REG_REQ_OK ||
-		    treatment == REG_REQ_ALREADY_SET)
+		if (treatment == REG_REQ_IGNORE ||
+		    treatment == REG_REQ_ALREADY_SET ||
+		    treatment == REG_REQ_USER_HINT_HANDLED)
 			return;
-		schedule_delayed_work(&reg_timeout, msecs_to_jiffies(3142));
+		queue_delayed_work(system_power_efficient_wq,
+				   &reg_timeout, msecs_to_jiffies(3142));
 		return;
 	case NL80211_REGDOM_SET_BY_DRIVER:
+		if (!wiphy)
+			goto out_free;
 		treatment = reg_process_hint_driver(wiphy, reg_request);
 		break;
 	case NL80211_REGDOM_SET_BY_COUNTRY_IE:
+		if (!wiphy)
+			goto out_free;
 		treatment = reg_process_hint_country_ie(wiphy, reg_request);
 		break;
 	default:
 		WARN(1, "invalid initiator %d\n", reg_request->initiator);
-		return;
+		goto out_free;
 	}
 
 	/* This is required so that the orig_* parameters are saved */
 	if (treatment == REG_REQ_ALREADY_SET && wiphy &&
 	    wiphy->regulatory_flags & REGULATORY_STRICT_REG)
 		wiphy_update_regulatory(wiphy, reg_request->initiator);
+
+	return;
+
+out_free:
+	reg_free_request(reg_request);
 }
 
 /*
@@ -1708,7 +1913,7 @@ static void reg_process_pending_hints(void)
 
 	/* When last_request->processed becomes true this will be rescheduled */
 	if (lr && !lr->processed) {
-		REG_DBG_PRINT("Pending regulatory request, waiting for it to be processed...\n");
+		reg_process_hint(lr);
 		return;
 	}
 
@@ -1818,6 +2023,22 @@ int regulatory_hint_user(const char *alpha2,
 	return 0;
 }
 
+int regulatory_hint_indoor_user(void)
+{
+	struct regulatory_request *request;
+
+	request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
+	if (!request)
+		return -ENOMEM;
+
+	request->wiphy_idx = WIPHY_IDX_INVALID;
+	request->initiator = NL80211_REGDOM_SET_BY_USER;
+	request->user_reg_hint_type = NL80211_USER_REG_HINT_INDOOR;
+	queue_regulatory_request(request);
+
+	return 0;
+}
+
 /* Driver hints */
 int regulatory_hint(struct wiphy *wiphy, const char *alpha2)
 {
@@ -1826,6 +2047,8 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2)
 	if (WARN_ON(!alpha2 || !wiphy))
 		return -EINVAL;
 
+	wiphy->regulatory_flags &= ~REGULATORY_CUSTOM_REG;
+
 	request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
 	if (!request)
 		return -ENOMEM;
@@ -1983,6 +2206,8 @@ static void restore_regulatory_settings(bool reset_user)
 
 	ASSERT_RTNL();
 
+	reg_is_indoor = false;
+
 	reset_regdomains(true, &world_regdom);
 	restore_alpha2(alpha2, reset_user);
 
@@ -2118,31 +2343,49 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd)
 	const struct ieee80211_reg_rule *reg_rule = NULL;
 	const struct ieee80211_freq_range *freq_range = NULL;
 	const struct ieee80211_power_rule *power_rule = NULL;
+	char bw[32], cac_time[32];
 
-	pr_info("  (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp)\n");
+	pr_info("  (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n");
 
 	for (i = 0; i < rd->n_reg_rules; i++) {
 		reg_rule = &rd->reg_rules[i];
 		freq_range = &reg_rule->freq_range;
 		power_rule = &reg_rule->power_rule;
 
+		if (reg_rule->flags & NL80211_RRF_AUTO_BW)
+			snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO",
+				 freq_range->max_bandwidth_khz,
+				 reg_get_max_bandwidth(rd, reg_rule));
+		else
+			snprintf(bw, sizeof(bw), "%d KHz",
+				 freq_range->max_bandwidth_khz);
+
+		if (reg_rule->flags & NL80211_RRF_DFS)
+			scnprintf(cac_time, sizeof(cac_time), "%u s",
+				  reg_rule->dfs_cac_ms/1000);
+		else
+			scnprintf(cac_time, sizeof(cac_time), "N/A");
+
+
 		/*
 		 * There may not be documentation for max antenna gain
 		 * in certain regions
 		 */
 		if (power_rule->max_antenna_gain)
-			pr_info("  (%d KHz - %d KHz @ %d KHz), (%d mBi, %d mBm)\n",
+			pr_info("  (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n",
 				freq_range->start_freq_khz,
 				freq_range->end_freq_khz,
-				freq_range->max_bandwidth_khz,
+				bw,
 				power_rule->max_antenna_gain,
-				power_rule->max_eirp);
+				power_rule->max_eirp,
+				cac_time);
 		else
-			pr_info("  (%d KHz - %d KHz @ %d KHz), (N/A, %d mBm)\n",
+			pr_info("  (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n",
 				freq_range->start_freq_khz,
 				freq_range->end_freq_khz,
-				freq_range->max_bandwidth_khz,
-				power_rule->max_eirp);
+				bw,
+				power_rule->max_eirp,
+				cac_time);
 	}
 }
 
@@ -2215,9 +2458,6 @@ static int reg_set_rd_user(const struct ieee80211_regdomain *rd,
 {
 	const struct ieee80211_regdomain *intersected_rd = NULL;
 
-	if (is_world_regdom(rd->alpha2))
-		return -EINVAL;
-
 	if (!regdom_changes(rd->alpha2))
 		return -EALREADY;
 
@@ -2265,7 +2505,8 @@ static int reg_set_rd_driver(const struct ieee80211_regdomain *rd,
 
 	request_wiphy = wiphy_idx_to_wiphy(driver_request->wiphy_idx);
 	if (!request_wiphy) {
-		schedule_delayed_work(&reg_timeout, 0);
+		queue_delayed_work(system_power_efficient_wq,
+				   &reg_timeout, 0);
 		return -ENODEV;
 	}
 
@@ -2325,7 +2566,8 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd,
 
 	request_wiphy = wiphy_idx_to_wiphy(country_ie_request->wiphy_idx);
 	if (!request_wiphy) {
-		schedule_delayed_work(&reg_timeout, 0);
+		queue_delayed_work(system_power_efficient_wq,
+				   &reg_timeout, 0);
 		return -ENODEV;
 	}
 
@@ -2344,6 +2586,7 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd,
 int set_regdom(const struct ieee80211_regdomain *rd)
 {
 	struct regulatory_request *lr;
+	bool user_reset = false;
 	int r;
 
 	if (!reg_is_valid_request(rd->alpha2)) {
@@ -2360,6 +2603,7 @@ int set_regdom(const struct ieee80211_regdomain *rd)
 		break;
 	case NL80211_REGDOM_SET_BY_USER:
 		r = reg_set_rd_user(rd, lr);
+		user_reset = true;
 		break;
 	case NL80211_REGDOM_SET_BY_DRIVER:
 		r = reg_set_rd_driver(rd, lr);
@@ -2373,8 +2617,14 @@ int set_regdom(const struct ieee80211_regdomain *rd)
 	}
 
 	if (r) {
-		if (r == -EALREADY)
+		switch (r) {
+		case -EALREADY:
 			reg_set_request_processed();
+			break;
+		default:
+			/* Back to world regulatory in case of errors */
+			restore_regulatory_settings(user_reset);
+		}
 
 		kfree(rd);
 		return r;
@@ -2396,26 +2646,6 @@ int set_regdom(const struct ieee80211_regdomain *rd)
 	return 0;
 }
 
-int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env)
-{
-	struct regulatory_request *lr;
-	u8 alpha2[2];
-	bool add = false;
-
-	rcu_read_lock();
-	lr = get_last_request();
-	if (lr && !lr->processed) {
-		memcpy(alpha2, lr->alpha2, 2);
-		add = true;
-	}
-	rcu_read_unlock();
-
-	if (add)
-		return add_uevent_var(env, "COUNTRY=%c%c",
-				      alpha2[0], alpha2[1]);
-	return 0;
-}
-
 void wiphy_regulatory_register(struct wiphy *wiphy)
 {
 	struct regulatory_request *lr;
@@ -2438,7 +2668,7 @@ void wiphy_regulatory_deregister(struct wiphy *wiphy)
 		reg_num_devs_support_basehint--;
 
 	rcu_free_regdom(get_wiphy_regdom(wiphy));
-	rcu_assign_pointer(wiphy->regd, NULL);
+	RCU_INIT_POINTER(wiphy->regd, NULL);
 
 	if (lr)
 		request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx);
@@ -2458,6 +2688,40 @@ static void reg_timeout_work(struct work_struct *work)
 	rtnl_unlock();
 }
 
+/*
+ * See http://www.fcc.gov/document/5-ghz-unlicensed-spectrum-unii, for
+ * UNII band definitions
+ */
+int cfg80211_get_unii(int freq)
+{
+	/* UNII-1 */
+	if (freq >= 5150 && freq <= 5250)
+		return 0;
+
+	/* UNII-2A */
+	if (freq > 5250 && freq <= 5350)
+		return 1;
+
+	/* UNII-2B */
+	if (freq > 5350 && freq <= 5470)
+		return 2;
+
+	/* UNII-2C */
+	if (freq > 5470 && freq <= 5725)
+		return 3;
+
+	/* UNII-3 */
+	if (freq > 5725 && freq <= 5825)
+		return 4;
+
+	return -EINVAL;
+}
+
+bool regulatory_indoor_allowed(void)
+{
+	return reg_is_indoor;
+}
+
 int __init regulatory_init(void)
 {
 	int err = 0;
@@ -2466,8 +2730,6 @@ int __init regulatory_init(void)
 	if (IS_ERR(reg_pdev))
 		return PTR_ERR(reg_pdev);
 
-	reg_pdev->dev.type = &reg_device_type;
-
 	spin_lock_init(&reg_requests_lock);
 	spin_lock_init(&reg_pending_beacons_lock);
 
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index cc4c2c0a672..5e48031ccb9 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -21,11 +21,12 @@ extern const struct ieee80211_regdomain __rcu *cfg80211_regdomain;
 bool reg_is_valid_request(const char *alpha2);
 bool is_world_regdom(const char *alpha2);
 bool reg_supported_dfs_region(enum nl80211_dfs_regions dfs_region);
+enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy);
 
 int regulatory_hint_user(const char *alpha2,
 			 enum nl80211_user_reg_hint_type user_reg_hint_type);
+int regulatory_hint_indoor_user(void);
 
-int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env);
 void wiphy_regulatory_register(struct wiphy *wiphy);
 void wiphy_regulatory_deregister(struct wiphy *wiphy);
 
@@ -33,6 +34,8 @@ int __init regulatory_init(void);
 void regulatory_exit(void);
 
 int set_regdom(const struct ieee80211_regdomain *rd);
+unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd,
+				   const struct ieee80211_reg_rule *rule);
 
 bool reg_last_request_cell_base(void);
 
@@ -102,4 +105,21 @@ void regulatory_hint_country_ie(struct wiphy *wiphy,
  */
 void regulatory_hint_disconnect(void);
 
+/**
+ * cfg80211_get_unii - get the U-NII band for the frequency
+ * @freq: the frequency for which we want to get the UNII band.
+
+ * Get a value specifying the U-NII band frequency belongs to.
+ * U-NII bands are defined by the FCC in C.F.R 47 part 15.
+ *
+ * Returns -EINVAL if freq is invalid, 0 for UNII-1, 1 for UNII-2A,
+ * 2 for UNII-2B, 3 for UNII-2C and 4 for UNII-3.
+ */
+int cfg80211_get_unii(int freq);
+
+/**
+ * regulatory_indoor_allowed - is indoor operation allowed
+ */
+bool regulatory_indoor_allowed(void);
+
 #endif  /* __NET_WIRELESS_REG_H */
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index d4397eba540..0798c62e608 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -81,10 +81,10 @@ static void bss_free(struct cfg80211_internal_bss *bss)
 	kfree(bss);
 }
 
-static inline void bss_ref_get(struct cfg80211_registered_device *dev,
+static inline void bss_ref_get(struct cfg80211_registered_device *rdev,
 			       struct cfg80211_internal_bss *bss)
 {
-	lockdep_assert_held(&dev->bss_lock);
+	lockdep_assert_held(&rdev->bss_lock);
 
 	bss->refcount++;
 	if (bss->pub.hidden_beacon_bss) {
@@ -95,10 +95,10 @@ static inline void bss_ref_get(struct cfg80211_registered_device *dev,
 	}
 }
 
-static inline void bss_ref_put(struct cfg80211_registered_device *dev,
+static inline void bss_ref_put(struct cfg80211_registered_device *rdev,
 			       struct cfg80211_internal_bss *bss)
 {
-	lockdep_assert_held(&dev->bss_lock);
+	lockdep_assert_held(&rdev->bss_lock);
 
 	if (bss->pub.hidden_beacon_bss) {
 		struct cfg80211_internal_bss *hbss;
@@ -114,10 +114,10 @@ static inline void bss_ref_put(struct cfg80211_registered_device *dev,
 		bss_free(bss);
 }
 
-static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *dev,
+static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *rdev,
 				  struct cfg80211_internal_bss *bss)
 {
-	lockdep_assert_held(&dev->bss_lock);
+	lockdep_assert_held(&rdev->bss_lock);
 
 	if (!list_empty(&bss->hidden_list)) {
 		/*
@@ -134,45 +134,52 @@ static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *dev,
 	}
 
 	list_del_init(&bss->list);
-	rb_erase(&bss->rbn, &dev->bss_tree);
-	bss_ref_put(dev, bss);
+	rb_erase(&bss->rbn, &rdev->bss_tree);
+	bss_ref_put(rdev, bss);
 	return true;
 }
 
-static void __cfg80211_bss_expire(struct cfg80211_registered_device *dev,
+static void __cfg80211_bss_expire(struct cfg80211_registered_device *rdev,
 				  unsigned long expire_time)
 {
 	struct cfg80211_internal_bss *bss, *tmp;
 	bool expired = false;
 
-	lockdep_assert_held(&dev->bss_lock);
+	lockdep_assert_held(&rdev->bss_lock);
 
-	list_for_each_entry_safe(bss, tmp, &dev->bss_list, list) {
+	list_for_each_entry_safe(bss, tmp, &rdev->bss_list, list) {
 		if (atomic_read(&bss->hold))
 			continue;
 		if (!time_after(expire_time, bss->ts))
 			continue;
 
-		if (__cfg80211_unlink_bss(dev, bss))
+		if (__cfg80211_unlink_bss(rdev, bss))
 			expired = true;
 	}
 
 	if (expired)
-		dev->bss_generation++;
+		rdev->bss_generation++;
 }
 
-void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak)
+void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
+			   bool send_message)
 {
 	struct cfg80211_scan_request *request;
 	struct wireless_dev *wdev;
+	struct sk_buff *msg;
 #ifdef CONFIG_CFG80211_WEXT
 	union iwreq_data wrqu;
 #endif
 
 	ASSERT_RTNL();
 
-	request = rdev->scan_req;
+	if (rdev->scan_msg) {
+		nl80211_send_scan_result(rdev, rdev->scan_msg);
+		rdev->scan_msg = NULL;
+		return;
+	}
 
+	request = rdev->scan_req;
 	if (!request)
 		return;
 
@@ -186,18 +193,16 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak)
 	if (wdev->netdev)
 		cfg80211_sme_scan_done(wdev->netdev);
 
-	if (request->aborted) {
-		nl80211_send_scan_aborted(rdev, wdev);
-	} else {
-		if (request->flags & NL80211_SCAN_FLAG_FLUSH) {
-			/* flush entries from previous scans */
-			spin_lock_bh(&rdev->bss_lock);
-			__cfg80211_bss_expire(rdev, request->scan_start);
-			spin_unlock_bh(&rdev->bss_lock);
-		}
-		nl80211_send_scan_done(rdev, wdev);
+	if (!request->aborted &&
+	    request->flags & NL80211_SCAN_FLAG_FLUSH) {
+		/* flush entries from previous scans */
+		spin_lock_bh(&rdev->bss_lock);
+		__cfg80211_bss_expire(rdev, request->scan_start);
+		spin_unlock_bh(&rdev->bss_lock);
 	}
 
+	msg = nl80211_build_scan_msg(rdev, wdev, request->aborted);
+
 #ifdef CONFIG_CFG80211_WEXT
 	if (wdev->netdev && !request->aborted) {
 		memset(&wrqu, 0, sizeof(wrqu));
@@ -210,17 +215,12 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak)
 		dev_put(wdev->netdev);
 
 	rdev->scan_req = NULL;
+	kfree(request);
 
-	/*
-	 * OK. If this is invoked with "leak" then we can't
-	 * free this ... but we've cleaned it up anyway. The
-	 * driver failed to call the scan_done callback, so
-	 * all bets are off, it might still be trying to use
-	 * the scan request or not ... if it accesses the dev
-	 * in there (it shouldn't anyway) then it may crash.
-	 */
-	if (!leak)
-		kfree(request);
+	if (!send_message)
+		rdev->scan_msg = msg;
+	else
+		nl80211_send_scan_result(rdev, msg);
 }
 
 void __cfg80211_scan_done(struct work_struct *wk)
@@ -231,18 +231,18 @@ void __cfg80211_scan_done(struct work_struct *wk)
 			    scan_done_wk);
 
 	rtnl_lock();
-	___cfg80211_scan_done(rdev, false);
+	___cfg80211_scan_done(rdev, true);
 	rtnl_unlock();
 }
 
 void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted)
 {
 	trace_cfg80211_scan_done(request, aborted);
-	WARN_ON(request != wiphy_to_dev(request->wiphy)->scan_req);
+	WARN_ON(request != wiphy_to_rdev(request->wiphy)->scan_req);
 
 	request->aborted = aborted;
 	request->notified = true;
-	queue_work(cfg80211_wq, &wiphy_to_dev(request->wiphy)->scan_done_wk);
+	queue_work(cfg80211_wq, &wiphy_to_rdev(request->wiphy)->scan_done_wk);
 }
 EXPORT_SYMBOL(cfg80211_scan_done);
 
@@ -278,20 +278,28 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy)
 {
 	trace_cfg80211_sched_scan_results(wiphy);
 	/* ignore if we're not scanning */
-	if (wiphy_to_dev(wiphy)->sched_scan_req)
+	if (wiphy_to_rdev(wiphy)->sched_scan_req)
 		queue_work(cfg80211_wq,
-			   &wiphy_to_dev(wiphy)->sched_scan_results_wk);
+			   &wiphy_to_rdev(wiphy)->sched_scan_results_wk);
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_results);
 
-void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+
+	ASSERT_RTNL();
 
 	trace_cfg80211_sched_scan_stopped(wiphy);
 
-	rtnl_lock();
 	__cfg80211_stop_sched_scan(rdev, true);
+}
+EXPORT_SYMBOL(cfg80211_sched_scan_stopped_rtnl);
+
+void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+{
+	rtnl_lock();
+	cfg80211_sched_scan_stopped_rtnl(wiphy);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_stopped);
@@ -322,21 +330,21 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
 	return 0;
 }
 
-void cfg80211_bss_age(struct cfg80211_registered_device *dev,
+void cfg80211_bss_age(struct cfg80211_registered_device *rdev,
                       unsigned long age_secs)
 {
 	struct cfg80211_internal_bss *bss;
 	unsigned long age_jiffies = msecs_to_jiffies(age_secs * MSEC_PER_SEC);
 
-	spin_lock_bh(&dev->bss_lock);
-	list_for_each_entry(bss, &dev->bss_list, list)
+	spin_lock_bh(&rdev->bss_lock);
+	list_for_each_entry(bss, &rdev->bss_list, list)
 		bss->ts -= age_jiffies;
-	spin_unlock_bh(&dev->bss_lock);
+	spin_unlock_bh(&rdev->bss_lock);
 }
 
-void cfg80211_bss_expire(struct cfg80211_registered_device *dev)
+void cfg80211_bss_expire(struct cfg80211_registered_device *rdev)
 {
-	__cfg80211_bss_expire(dev, jiffies - IEEE80211_SCAN_RESULT_EXPIRE);
+	__cfg80211_bss_expire(rdev, jiffies - IEEE80211_SCAN_RESULT_EXPIRE);
 }
 
 const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len)
@@ -526,32 +534,34 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
 				      const u8 *ssid, size_t ssid_len,
 				      u16 capa_mask, u16 capa_val)
 {
-	struct cfg80211_registered_device *dev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss, *res = NULL;
 	unsigned long now = jiffies;
 
 	trace_cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len, capa_mask,
 			       capa_val);
 
-	spin_lock_bh(&dev->bss_lock);
+	spin_lock_bh(&rdev->bss_lock);
 
-	list_for_each_entry(bss, &dev->bss_list, list) {
+	list_for_each_entry(bss, &rdev->bss_list, list) {
 		if ((bss->pub.capability & capa_mask) != capa_val)
 			continue;
 		if (channel && bss->pub.channel != channel)
 			continue;
+		if (!is_valid_ether_addr(bss->pub.bssid))
+			continue;
 		/* Don't get expired BSS structs */
 		if (time_after(now, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE) &&
 		    !atomic_read(&bss->hold))
 			continue;
 		if (is_bss(&bss->pub, bssid, ssid, ssid_len)) {
 			res = bss;
-			bss_ref_get(dev, res);
+			bss_ref_get(rdev, res);
 			break;
 		}
 	}
 
-	spin_unlock_bh(&dev->bss_lock);
+	spin_unlock_bh(&rdev->bss_lock);
 	if (!res)
 		return NULL;
 	trace_cfg80211_return_bss(&res->pub);
@@ -559,10 +569,10 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
 }
 EXPORT_SYMBOL(cfg80211_get_bss);
 
-static void rb_insert_bss(struct cfg80211_registered_device *dev,
+static void rb_insert_bss(struct cfg80211_registered_device *rdev,
 			  struct cfg80211_internal_bss *bss)
 {
-	struct rb_node **p = &dev->bss_tree.rb_node;
+	struct rb_node **p = &rdev->bss_tree.rb_node;
 	struct rb_node *parent = NULL;
 	struct cfg80211_internal_bss *tbss;
 	int cmp;
@@ -585,15 +595,15 @@ static void rb_insert_bss(struct cfg80211_registered_device *dev,
 	}
 
 	rb_link_node(&bss->rbn, parent, p);
-	rb_insert_color(&bss->rbn, &dev->bss_tree);
+	rb_insert_color(&bss->rbn, &rdev->bss_tree);
 }
 
 static struct cfg80211_internal_bss *
-rb_find_bss(struct cfg80211_registered_device *dev,
+rb_find_bss(struct cfg80211_registered_device *rdev,
 	    struct cfg80211_internal_bss *res,
 	    enum bss_compare_mode mode)
 {
-	struct rb_node *n = dev->bss_tree.rb_node;
+	struct rb_node *n = rdev->bss_tree.rb_node;
 	struct cfg80211_internal_bss *bss;
 	int r;
 
@@ -612,7 +622,7 @@ rb_find_bss(struct cfg80211_registered_device *dev,
 	return NULL;
 }
 
-static bool cfg80211_combine_bsses(struct cfg80211_registered_device *dev,
+static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 				   struct cfg80211_internal_bss *new)
 {
 	const struct cfg80211_bss_ies *ies;
@@ -642,7 +652,7 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *dev,
 
 	/* This is the bad part ... */
 
-	list_for_each_entry(bss, &dev->bss_list, list) {
+	list_for_each_entry(bss, &rdev->bss_list, list) {
 		if (!ether_addr_equal(bss->pub.bssid, new->pub.bssid))
 			continue;
 		if (bss->pub.channel != new->pub.channel)
@@ -659,9 +669,6 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *dev,
 			continue;
 		if (ssidlen && ie[1] != ssidlen)
 			continue;
-		/* that would be odd ... */
-		if (bss->pub.beacon_ies)
-			continue;
 		if (WARN_ON_ONCE(bss->pub.hidden_beacon_bss))
 			continue;
 		if (WARN_ON_ONCE(!list_empty(&bss->hidden_list)))
@@ -679,8 +686,9 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *dev,
 
 /* Returned bss is reference counted and must be cleaned up appropriately. */
 static struct cfg80211_internal_bss *
-cfg80211_bss_update(struct cfg80211_registered_device *dev,
-		    struct cfg80211_internal_bss *tmp)
+cfg80211_bss_update(struct cfg80211_registered_device *rdev,
+		    struct cfg80211_internal_bss *tmp,
+		    bool signal_valid)
 {
 	struct cfg80211_internal_bss *found = NULL;
 
@@ -689,14 +697,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 
 	tmp->ts = jiffies;
 
-	spin_lock_bh(&dev->bss_lock);
+	spin_lock_bh(&rdev->bss_lock);
 
 	if (WARN_ON(!rcu_access_pointer(tmp->pub.ies))) {
-		spin_unlock_bh(&dev->bss_lock);
+		spin_unlock_bh(&rdev->bss_lock);
 		return NULL;
 	}
 
-	found = rb_find_bss(dev, tmp, BSS_CMP_REGULAR);
+	found = rb_find_bss(rdev, tmp, BSS_CMP_REGULAR);
 
 	if (found) {
 		/* Update IEs */
@@ -765,7 +773,12 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 		}
 
 		found->pub.beacon_interval = tmp->pub.beacon_interval;
-		found->pub.signal = tmp->pub.signal;
+		/*
+		 * don't update the signal if beacon was heard on
+		 * adjacent channel.
+		 */
+		if (signal_valid)
+			found->pub.signal = tmp->pub.signal;
 		found->pub.capability = tmp->pub.capability;
 		found->ts = tmp->ts;
 	} else {
@@ -778,7 +791,7 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 		 * is allocated on the stack since it's not needed in the
 		 * more common case of an update
 		 */
-		new = kzalloc(sizeof(*new) + dev->wiphy.bss_priv_size,
+		new = kzalloc(sizeof(*new) + rdev->wiphy.bss_priv_size,
 			      GFP_ATOMIC);
 		if (!new) {
 			ies = (void *)rcu_dereference(tmp->pub.beacon_ies);
@@ -794,9 +807,9 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 		INIT_LIST_HEAD(&new->hidden_list);
 
 		if (rcu_access_pointer(tmp->pub.proberesp_ies)) {
-			hidden = rb_find_bss(dev, tmp, BSS_CMP_HIDE_ZLEN);
+			hidden = rb_find_bss(rdev, tmp, BSS_CMP_HIDE_ZLEN);
 			if (!hidden)
-				hidden = rb_find_bss(dev, tmp,
+				hidden = rb_find_bss(rdev, tmp,
 						     BSS_CMP_HIDE_NUL);
 			if (hidden) {
 				new->pub.hidden_beacon_bss = &hidden->pub;
@@ -813,24 +826,24 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 			 * expensive search for any probe responses that should
 			 * be grouped with this beacon for updates ...
 			 */
-			if (!cfg80211_combine_bsses(dev, new)) {
+			if (!cfg80211_combine_bsses(rdev, new)) {
 				kfree(new);
 				goto drop;
 			}
 		}
 
-		list_add_tail(&new->list, &dev->bss_list);
-		rb_insert_bss(dev, new);
+		list_add_tail(&new->list, &rdev->bss_list);
+		rb_insert_bss(rdev, new);
 		found = new;
 	}
 
-	dev->bss_generation++;
-	bss_ref_get(dev, found);
-	spin_unlock_bh(&dev->bss_lock);
+	rdev->bss_generation++;
+	bss_ref_get(rdev, found);
+	spin_unlock_bh(&rdev->bss_lock);
 
 	return found;
  drop:
-	spin_unlock_bh(&dev->bss_lock);
+	spin_unlock_bh(&rdev->bss_lock);
 	return NULL;
 }
 
@@ -869,14 +882,16 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen,
 /* Returned bss is reference counted and must be cleaned up appropriately. */
 struct cfg80211_bss*
 cfg80211_inform_bss_width(struct wiphy *wiphy,
-			  struct ieee80211_channel *channel,
+			  struct ieee80211_channel *rx_channel,
 			  enum nl80211_bss_scan_width scan_width,
 			  const u8 *bssid, u64 tsf, u16 capability,
 			  u16 beacon_interval, const u8 *ie, size_t ielen,
 			  s32 signal, gfp_t gfp)
 {
 	struct cfg80211_bss_ies *ies;
+	struct ieee80211_channel *channel;
 	struct cfg80211_internal_bss tmp = {}, *res;
+	bool signal_valid;
 
 	if (WARN_ON(!wiphy))
 		return NULL;
@@ -885,7 +900,7 @@ cfg80211_inform_bss_width(struct wiphy *wiphy,
 			(signal < 0 || signal > 100)))
 		return NULL;
 
-	channel = cfg80211_get_bss_channel(wiphy, ie, ielen, channel);
+	channel = cfg80211_get_bss_channel(wiphy, ie, ielen, rx_channel);
 	if (!channel)
 		return NULL;
 
@@ -913,7 +928,9 @@ cfg80211_inform_bss_width(struct wiphy *wiphy,
 	rcu_assign_pointer(tmp.pub.beacon_ies, ies);
 	rcu_assign_pointer(tmp.pub.ies, ies);
 
-	res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp);
+	signal_valid = abs(rx_channel->center_freq - channel->center_freq) <=
+		wiphy->max_adj_channel_rssi_comp;
+	res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid);
 	if (!res)
 		return NULL;
 
@@ -929,20 +946,22 @@ EXPORT_SYMBOL(cfg80211_inform_bss_width);
 /* Returned bss is reference counted and must be cleaned up appropriately. */
 struct cfg80211_bss *
 cfg80211_inform_bss_width_frame(struct wiphy *wiphy,
-				struct ieee80211_channel *channel,
+				struct ieee80211_channel *rx_channel,
 				enum nl80211_bss_scan_width scan_width,
 				struct ieee80211_mgmt *mgmt, size_t len,
 				s32 signal, gfp_t gfp)
 {
 	struct cfg80211_internal_bss tmp = {}, *res;
 	struct cfg80211_bss_ies *ies;
+	struct ieee80211_channel *channel;
+	bool signal_valid;
 	size_t ielen = len - offsetof(struct ieee80211_mgmt,
 				      u.probe_resp.variable);
 
 	BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) !=
 			offsetof(struct ieee80211_mgmt, u.beacon.variable));
 
-	trace_cfg80211_inform_bss_width_frame(wiphy, channel, scan_width, mgmt,
+	trace_cfg80211_inform_bss_width_frame(wiphy, rx_channel, scan_width, mgmt,
 					      len, signal);
 
 	if (WARN_ON(!mgmt))
@@ -959,7 +978,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy,
 		return NULL;
 
 	channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable,
-					   ielen, channel);
+					   ielen, rx_channel);
 	if (!channel)
 		return NULL;
 
@@ -983,7 +1002,9 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy,
 	tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
 	tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
 
-	res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp);
+	signal_valid = abs(rx_channel->center_freq - channel->center_freq) <=
+		wiphy->max_adj_channel_rssi_comp;
+	res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid);
 	if (!res)
 		return NULL;
 
@@ -998,7 +1019,7 @@ EXPORT_SYMBOL(cfg80211_inform_bss_width_frame);
 
 void cfg80211_ref_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 {
-	struct cfg80211_registered_device *dev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss;
 
 	if (!pub)
@@ -1006,15 +1027,15 @@ void cfg80211_ref_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 
 	bss = container_of(pub, struct cfg80211_internal_bss, pub);
 
-	spin_lock_bh(&dev->bss_lock);
-	bss_ref_get(dev, bss);
-	spin_unlock_bh(&dev->bss_lock);
+	spin_lock_bh(&rdev->bss_lock);
+	bss_ref_get(rdev, bss);
+	spin_unlock_bh(&rdev->bss_lock);
 }
 EXPORT_SYMBOL(cfg80211_ref_bss);
 
 void cfg80211_put_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 {
-	struct cfg80211_registered_device *dev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss;
 
 	if (!pub)
@@ -1022,15 +1043,15 @@ void cfg80211_put_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 
 	bss = container_of(pub, struct cfg80211_internal_bss, pub);
 
-	spin_lock_bh(&dev->bss_lock);
-	bss_ref_put(dev, bss);
-	spin_unlock_bh(&dev->bss_lock);
+	spin_lock_bh(&rdev->bss_lock);
+	bss_ref_put(rdev, bss);
+	spin_unlock_bh(&rdev->bss_lock);
 }
 EXPORT_SYMBOL(cfg80211_put_bss);
 
 void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 {
-	struct cfg80211_registered_device *dev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss;
 
 	if (WARN_ON(!pub))
@@ -1038,12 +1059,12 @@ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 
 	bss = container_of(pub, struct cfg80211_internal_bss, pub);
 
-	spin_lock_bh(&dev->bss_lock);
+	spin_lock_bh(&rdev->bss_lock);
 	if (!list_empty(&bss->list)) {
-		if (__cfg80211_unlink_bss(dev, bss))
-			dev->bss_generation++;
+		if (__cfg80211_unlink_bss(rdev, bss))
+			rdev->bss_generation++;
 	}
-	spin_unlock_bh(&dev->bss_lock);
+	spin_unlock_bh(&rdev->bss_lock);
 }
 EXPORT_SYMBOL(cfg80211_unlink_bss);
 
@@ -1060,7 +1081,7 @@ cfg80211_get_dev_from_ifindex(struct net *net, int ifindex)
 	if (!dev)
 		return ERR_PTR(-ENODEV);
 	if (dev->ieee80211_ptr)
-		rdev = wiphy_to_dev(dev->ieee80211_ptr->wiphy);
+		rdev = wiphy_to_rdev(dev->ieee80211_ptr->wiphy);
 	else
 		rdev = ERR_PTR(-ENODEV);
 	dev_put(dev);
@@ -1089,7 +1110,7 @@ int cfg80211_wext_siwscan(struct net_device *dev,
 	if (IS_ERR(rdev))
 		return PTR_ERR(rdev);
 
-	if (rdev->scan_req) {
+	if (rdev->scan_req || rdev->scan_msg) {
 		err = -EBUSY;
 		goto out;
 	}
@@ -1099,11 +1120,8 @@ int cfg80211_wext_siwscan(struct net_device *dev,
 	/* Determine number of channels, needed to allocate creq */
 	if (wreq && wreq->num_channels)
 		n_channels = wreq->num_channels;
-	else {
-		for (band = 0; band < IEEE80211_NUM_BANDS; band++)
-			if (wiphy->bands[band])
-				n_channels += wiphy->bands[band]->n_channels;
-	}
+	else
+		n_channels = ieee80211_get_num_supported_channels(wiphy);
 
 	creq = kzalloc(sizeof(*creq) + sizeof(struct cfg80211_ssid) +
 		       n_channels * sizeof(void *),
@@ -1143,7 +1161,11 @@ int cfg80211_wext_siwscan(struct net_device *dev,
 				int k;
 				int wiphy_freq = wiphy->bands[band]->channels[j].center_freq;
 				for (k = 0; k < wreq->num_channels; k++) {
-					int wext_freq = cfg80211_wext_freq(wiphy, &wreq->channel_list[k]);
+					struct iw_freq *freq =
+						&wreq->channel_list[k];
+					int wext_freq =
+						cfg80211_wext_freq(freq);
+
 					if (wext_freq == wiphy_freq)
 						goto wext_freq_found;
 				}
@@ -1455,7 +1477,7 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 }
 
 
-static int ieee80211_scan_results(struct cfg80211_registered_device *dev,
+static int ieee80211_scan_results(struct cfg80211_registered_device *rdev,
 				  struct iw_request_info *info,
 				  char *buf, size_t len)
 {
@@ -1463,18 +1485,18 @@ static int ieee80211_scan_results(struct cfg80211_registered_device *dev,
 	char *end_buf = buf + len;
 	struct cfg80211_internal_bss *bss;
 
-	spin_lock_bh(&dev->bss_lock);
-	cfg80211_bss_expire(dev);
+	spin_lock_bh(&rdev->bss_lock);
+	cfg80211_bss_expire(rdev);
 
-	list_for_each_entry(bss, &dev->bss_list, list) {
+	list_for_each_entry(bss, &rdev->bss_list, list) {
 		if (buf + len - current_ev <= IW_EV_ADDR_LEN) {
-			spin_unlock_bh(&dev->bss_lock);
+			spin_unlock_bh(&rdev->bss_lock);
 			return -E2BIG;
 		}
-		current_ev = ieee80211_bss(&dev->wiphy, info, bss,
+		current_ev = ieee80211_bss(&rdev->wiphy, info, bss,
 					   current_ev, end_buf);
 	}
-	spin_unlock_bh(&dev->bss_lock);
+	spin_unlock_bh(&rdev->bss_lock);
 	return current_ev - buf;
 }
 
@@ -1494,7 +1516,7 @@ int cfg80211_wext_giwscan(struct net_device *dev,
 	if (IS_ERR(rdev))
 		return PTR_ERR(rdev);
 
-	if (rdev->scan_req)
+	if (rdev->scan_req || rdev->scan_msg)
 		return -EAGAIN;
 
 	res = ieee80211_scan_results(rdev, info, extra, data->length);
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 65f800890d7..8bbeeb30221 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -59,29 +59,21 @@ static void cfg80211_sme_free(struct wireless_dev *wdev)
 
 static int cfg80211_conn_scan(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_scan_request *request;
 	int n_channels, err;
 
 	ASSERT_RTNL();
-	ASSERT_RDEV_LOCK(rdev);
 	ASSERT_WDEV_LOCK(wdev);
 
-	if (rdev->scan_req)
+	if (rdev->scan_req || rdev->scan_msg)
 		return -EBUSY;
 
-	if (wdev->conn->params.channel) {
+	if (wdev->conn->params.channel)
 		n_channels = 1;
-	} else {
-		enum ieee80211_band band;
-		n_channels = 0;
+	else
+		n_channels = ieee80211_get_num_supported_channels(wdev->wiphy);
 
-		for (band = 0; band < IEEE80211_NUM_BANDS; band++) {
-			if (!wdev->wiphy->bands[band])
-				continue;
-			n_channels += wdev->wiphy->bands[band]->n_channels;
-		}
-	}
 	request = kzalloc(sizeof(*request) + sizeof(request->ssids[0]) +
 			  sizeof(request->channels[0]) * n_channels,
 			  GFP_KERNEL);
@@ -138,7 +130,7 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev)
 
 static int cfg80211_conn_do_work(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_connect_params *params;
 	struct cfg80211_assoc_request req = {};
 	int err;
@@ -157,7 +149,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev)
 	case CFG80211_CONN_SCAN_AGAIN:
 		return cfg80211_conn_scan(wdev);
 	case CFG80211_CONN_AUTHENTICATE_NEXT:
-		BUG_ON(!rdev->ops->auth);
+		if (WARN_ON(!rdev->ops->auth))
+			return -EOPNOTSUPP;
 		wdev->conn->state = CFG80211_CONN_AUTHENTICATING;
 		return cfg80211_mlme_auth(rdev, wdev->netdev,
 					  params->channel, params->auth_type,
@@ -169,7 +162,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev)
 	case CFG80211_CONN_AUTH_FAILED:
 		return -ENOTCONN;
 	case CFG80211_CONN_ASSOCIATE_NEXT:
-		BUG_ON(!rdev->ops->assoc);
+		if (WARN_ON(!rdev->ops->assoc))
+			return -EOPNOTSUPP;
 		wdev->conn->state = CFG80211_CONN_ASSOCIATING;
 		if (wdev->conn->prev_bssid_valid)
 			req.prev_bssid = wdev->conn->prev_bssid;
@@ -242,7 +236,6 @@ void cfg80211_conn_work(struct work_struct *work)
 					NULL, 0, NULL, 0,
 					WLAN_STATUS_UNSPECIFIED_FAILURE,
 					false, NULL);
-			cfg80211_sme_free(wdev);
 		}
 		wdev_unlock(wdev);
 	}
@@ -253,7 +246,7 @@ void cfg80211_conn_work(struct work_struct *work)
 /* Returned bss is reference counted and must be cleaned up appropriately. */
 static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_bss *bss;
 	u16 capa = WLAN_CAPABILITY_ESS;
 
@@ -283,7 +276,7 @@ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev)
 static void __cfg80211_sme_scan_done(struct net_device *dev)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_bss *bss;
 
 	ASSERT_WDEV_LOCK(wdev);
@@ -314,7 +307,7 @@ void cfg80211_sme_scan_done(struct net_device *dev)
 void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	u16 status_code = le16_to_cpu(mgmt->u.auth.status_code);
 
@@ -360,7 +353,7 @@ void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len)
 
 bool cfg80211_sme_rx_assoc_resp(struct wireless_dev *wdev, u16 status)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (!wdev->conn)
 		return false;
@@ -394,7 +387,7 @@ void cfg80211_sme_deauth(struct wireless_dev *wdev)
 
 void cfg80211_sme_auth_timeout(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (!wdev->conn)
 		return;
@@ -405,7 +398,7 @@ void cfg80211_sme_auth_timeout(struct wireless_dev *wdev)
 
 void cfg80211_sme_disassoc(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (!wdev->conn)
 		return;
@@ -416,7 +409,7 @@ void cfg80211_sme_disassoc(struct wireless_dev *wdev)
 
 void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (!wdev->conn)
 		return;
@@ -429,7 +422,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev,
 				struct cfg80211_connect_params *connect,
 				const u8 *prev_bssid)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_bss *bss;
 	int err;
 
@@ -476,7 +469,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev,
 	}
 
 	wdev->conn->params.ssid = wdev->ssid;
-	wdev->conn->params.ssid_len = connect->ssid_len;
+	wdev->conn->params.ssid_len = wdev->ssid_len;
 
 	/* see if we have the bss already */
 	bss = cfg80211_get_conn_bss(wdev);
@@ -488,7 +481,6 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev,
 
 	/* we're good if we have a matching bss struct */
 	if (bss) {
-		wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT;
 		err = cfg80211_conn_do_work(wdev);
 		cfg80211_put_bss(wdev->wiphy, bss);
 	} else {
@@ -514,7 +506,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev,
 
 static int cfg80211_sme_disconnect(struct wireless_dev *wdev, u16 reason)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int err;
 
 	if (!wdev->conn)
@@ -602,7 +594,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 		return;
 	}
 
-	nl80211_send_connect_result(wiphy_to_dev(wdev->wiphy), dev,
+	nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev,
 				    bssid, req_ie, req_ie_len,
 				    resp_ie, resp_ie_len,
 				    status, GFP_KERNEL);
@@ -632,6 +624,16 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 	}
 #endif
 
+	if (!bss && (status == WLAN_STATUS_SUCCESS)) {
+		WARN_ON_ONCE(!wiphy_to_rdev(wdev->wiphy)->ops->connect);
+		bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid,
+				       wdev->ssid, wdev->ssid_len,
+				       WLAN_CAPABILITY_ESS,
+				       WLAN_CAPABILITY_ESS);
+		if (bss)
+			cfg80211_hold_bss(bss_from_pub(bss));
+	}
+
 	if (wdev->current_bss) {
 		cfg80211_unhold_bss(wdev->current_bss);
 		cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub);
@@ -646,19 +648,12 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			cfg80211_unhold_bss(bss_from_pub(bss));
 			cfg80211_put_bss(wdev->wiphy, bss);
 		}
+		cfg80211_sme_free(wdev);
 		return;
 	}
 
-	if (!bss) {
-		WARN_ON_ONCE(!wiphy_to_dev(wdev->wiphy)->ops->connect);
-		bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid,
-				       wdev->ssid, wdev->ssid_len,
-				       WLAN_CAPABILITY_ESS,
-				       WLAN_CAPABILITY_ESS);
-		if (WARN_ON(!bss))
-			return;
-		cfg80211_hold_bss(bss_from_pub(bss));
-	}
+	if (WARN_ON(!bss))
+		return;
 
 	wdev->current_bss = bss_from_pub(bss);
 
@@ -693,7 +688,7 @@ void cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			     u16 status, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_event *ev;
 	unsigned long flags;
 
@@ -748,7 +743,8 @@ void __cfg80211_roamed(struct wireless_dev *wdev,
 	cfg80211_hold_bss(bss_from_pub(bss));
 	wdev->current_bss = bss_from_pub(bss);
 
-	nl80211_send_roamed(wiphy_to_dev(wdev->wiphy), wdev->netdev, bss->bssid,
+	nl80211_send_roamed(wiphy_to_rdev(wdev->wiphy),
+			    wdev->netdev, bss->bssid,
 			    req_ie, req_ie_len, resp_ie, resp_ie_len,
 			    GFP_KERNEL);
 
@@ -807,7 +803,7 @@ void cfg80211_roamed_bss(struct net_device *dev,
 			 size_t resp_ie_len, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_event *ev;
 	unsigned long flags;
 
@@ -840,7 +836,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 			     size_t ie_len, u16 reason, bool from_ap)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int i;
 #ifdef CONFIG_CFG80211_WEXT
 	union iwreq_data wrqu;
@@ -870,6 +866,8 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 		for (i = 0; i < 6; i++)
 			rdev_del_key(rdev, dev, i, false, NULL);
 
+	rdev_set_qos_map(rdev, dev, NULL);
+
 #ifdef CONFIG_CFG80211_WEXT
 	memset(&wrqu, 0, sizeof(wrqu));
 	wrqu.ap_addr.sa_family = ARPHRD_ETHER;
@@ -881,10 +879,10 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 }
 
 void cfg80211_disconnected(struct net_device *dev, u16 reason,
-			   u8 *ie, size_t ie_len, gfp_t gfp)
+			   const u8 *ie, size_t ie_len, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_event *ev;
 	unsigned long flags;
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index f7aa7a72d9b..7cc887f9da1 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -186,6 +186,28 @@
 
 #define BOOL_TO_STR(bo) (bo) ? "true" : "false"
 
+#define QOS_MAP_ENTRY __field(u8, num_des)			\
+		      __array(u8, dscp_exception,		\
+			      2 * IEEE80211_QOS_MAP_MAX_EX)	\
+		      __array(u8, up, IEEE80211_QOS_MAP_LEN_MIN)
+#define QOS_MAP_ASSIGN(qos_map)					\
+	do {							\
+		if ((qos_map)) {				\
+			__entry->num_des = (qos_map)->num_des;	\
+			memcpy(__entry->dscp_exception,		\
+			       &(qos_map)->dscp_exception,	\
+			       2 * IEEE80211_QOS_MAP_MAX_EX);	\
+			memcpy(__entry->up, &(qos_map)->up,	\
+			       IEEE80211_QOS_MAP_LEN_MIN);	\
+		} else {					\
+			__entry->num_des = 0;			\
+			memset(__entry->dscp_exception, 0,	\
+			       2 * IEEE80211_QOS_MAP_MAX_EX);	\
+			memset(__entry->up, 0,			\
+			       IEEE80211_QOS_MAP_LEN_MIN);	\
+		}						\
+	} while (0)
+
 /*************************************************************
  *			rdev->ops traces		     *
  *************************************************************/
@@ -1446,9 +1468,10 @@ TRACE_EVENT(rdev_sched_scan_start,
 TRACE_EVENT(rdev_tdls_mgmt,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
 		 u8 *peer, u8 action_code, u8 dialog_token,
-		 u16 status_code, const u8 *buf, size_t len),
+		 u16 status_code, u32 peer_capability,
+		 const u8 *buf, size_t len),
 	TP_ARGS(wiphy, netdev, peer, action_code, dialog_token, status_code,
-		buf, len),
+		peer_capability, buf, len),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		NETDEV_ENTRY
@@ -1456,6 +1479,7 @@ TRACE_EVENT(rdev_tdls_mgmt,
 		__field(u8, action_code)
 		__field(u8, dialog_token)
 		__field(u16, status_code)
+		__field(u32, peer_capability)
 		__dynamic_array(u8, buf, len)
 	),
 	TP_fast_assign(
@@ -1465,13 +1489,15 @@ TRACE_EVENT(rdev_tdls_mgmt,
 		__entry->action_code = action_code;
 		__entry->dialog_token = dialog_token;
 		__entry->status_code = status_code;
+		__entry->peer_capability = peer_capability;
 		memcpy(__get_dynamic_array(buf), buf, len);
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT ", action_code: %u, "
-		  "dialog_token: %u, status_code: %u, buf: %#.2x ",
+		  "dialog_token: %u, status_code: %u, peer_capability: %u buf: %#.2x ",
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer),
 		  __entry->action_code, __entry->dialog_token,
-		  __entry->status_code, ((u8 *)__get_dynamic_array(buf))[0])
+		  __entry->status_code, __entry->peer_capability,
+		  ((u8 *)__get_dynamic_array(buf))[0])
 );
 
 TRACE_EVENT(rdev_dump_survey,
@@ -1850,29 +1876,69 @@ TRACE_EVENT(rdev_channel_switch,
 		WIPHY_ENTRY
 		NETDEV_ENTRY
 		CHAN_DEF_ENTRY
-		__field(u16, counter_offset_beacon)
-		__field(u16, counter_offset_presp)
 		__field(bool, radar_required)
 		__field(bool, block_tx)
 		__field(u8, count)
+		__dynamic_array(u16, bcn_ofs, params->n_counter_offsets_beacon)
+		__dynamic_array(u16, pres_ofs, params->n_counter_offsets_presp)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		NETDEV_ASSIGN;
 		CHAN_DEF_ASSIGN(&params->chandef);
-		__entry->counter_offset_beacon = params->counter_offset_beacon;
-		__entry->counter_offset_presp = params->counter_offset_presp;
 		__entry->radar_required = params->radar_required;
 		__entry->block_tx = params->block_tx;
 		__entry->count = params->count;
+		memcpy(__get_dynamic_array(bcn_ofs),
+		       params->counter_offsets_beacon,
+		       params->n_counter_offsets_beacon * sizeof(u16));
+
+		/* probe response offsets are optional */
+		if (params->n_counter_offsets_presp)
+			memcpy(__get_dynamic_array(pres_ofs),
+			       params->counter_offsets_presp,
+			       params->n_counter_offsets_presp * sizeof(u16));
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT
-		  ", block_tx: %d, count: %u, radar_required: %d"
-		  ", counter offsets (beacon/presp): %u/%u",
+		  ", block_tx: %d, count: %u, radar_required: %d",
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG,
-		  __entry->block_tx, __entry->count, __entry->radar_required,
-		  __entry->counter_offset_beacon,
-		  __entry->counter_offset_presp)
+		  __entry->block_tx, __entry->count, __entry->radar_required)
+);
+
+TRACE_EVENT(rdev_set_qos_map,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct cfg80211_qos_map *qos_map),
+	TP_ARGS(wiphy, netdev, qos_map),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		QOS_MAP_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		QOS_MAP_ASSIGN(qos_map);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", num_des: %u",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->num_des)
+);
+
+TRACE_EVENT(rdev_set_ap_chanwidth,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct cfg80211_chan_def *chandef),
+	TP_ARGS(wiphy, netdev, chandef),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		CHAN_DEF_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		CHAN_DEF_ASSIGN(chandef);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG)
 );
 
 /*************************************************************
@@ -2028,7 +2094,8 @@ TRACE_EVENT(cfg80211_michael_mic_failure,
 		MAC_ASSIGN(addr, addr);
 		__entry->key_type = key_type;
 		__entry->key_id = key_id;
-		memcpy(__entry->tsc, tsc, 6);
+		if (tsc)
+			memcpy(__entry->tsc, tsc, 6);
 	),
 	TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", key type: %d, key id: %d, tsc: %pm",
 		  NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->key_type,
@@ -2149,18 +2216,21 @@ TRACE_EVENT(cfg80211_cqm_rssi_notify,
 );
 
 TRACE_EVENT(cfg80211_reg_can_beacon,
-	TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef),
-	TP_ARGS(wiphy, chandef),
+	TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef,
+		 enum nl80211_iftype iftype),
+	TP_ARGS(wiphy, chandef, iftype),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		CHAN_DEF_ENTRY
+		__field(enum nl80211_iftype, iftype)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		CHAN_DEF_ASSIGN(chandef);
+		__entry->iftype = iftype;
 	),
-	TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT,
-		  WIPHY_PR_ARG, CHAN_DEF_PR_ARG)
+	TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", iftype=%d",
+		  WIPHY_PR_ARG, CHAN_DEF_PR_ARG, __entry->iftype)
 );
 
 TRACE_EVENT(cfg80211_chandef_dfs_required,
@@ -2238,11 +2308,6 @@ DECLARE_EVENT_CLASS(cfg80211_rx_evt,
 	TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT, NETDEV_PR_ARG, MAC_PR_ARG(addr))
 );
 
-DEFINE_EVENT(cfg80211_rx_evt, cfg80211_ibss_joined,
-	TP_PROTO(struct net_device *netdev, const u8 *addr),
-	TP_ARGS(netdev, addr)
-);
-
 DEFINE_EVENT(cfg80211_rx_evt, cfg80211_rx_spurious_frame,
 	TP_PROTO(struct net_device *netdev, const u8 *addr),
 	TP_ARGS(netdev, addr)
@@ -2253,6 +2318,24 @@ DEFINE_EVENT(cfg80211_rx_evt, cfg80211_rx_unexpected_4addr_frame,
 	TP_ARGS(netdev, addr)
 );
 
+TRACE_EVENT(cfg80211_ibss_joined,
+	TP_PROTO(struct net_device *netdev, const u8 *bssid,
+		 struct ieee80211_channel *channel),
+	TP_ARGS(netdev, bssid, channel),
+	TP_STRUCT__entry(
+		NETDEV_ENTRY
+		MAC_ENTRY(bssid)
+		CHAN_ENTRY
+	),
+	TP_fast_assign(
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(bssid, bssid);
+		CHAN_ASSIGN(channel);
+	),
+	TP_printk(NETDEV_PR_FMT ", bssid: " MAC_PR_FMT ", " CHAN_PR_FMT,
+		  NETDEV_PR_ARG, MAC_PR_ARG(bssid), CHAN_PR_ARG)
+);
+
 TRACE_EVENT(cfg80211_probe_status,
 	TP_PROTO(struct net_device *netdev, const u8 *addr, u64 cookie,
 		 bool acked),
@@ -2558,6 +2641,21 @@ TRACE_EVENT(cfg80211_ft_event,
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(target_ap))
 );
 
+TRACE_EVENT(cfg80211_stop_iface,
+	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev),
+	TP_ARGS(wiphy, wdev),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		WDEV_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		WDEV_ASSIGN;
+	),
+	TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT,
+		  WIPHY_PR_ARG, WDEV_PR_ARG)
+);
+
 #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 935dea9485d..728f1c0dc70 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -11,6 +11,7 @@
 #include <net/ip.h>
 #include <net/dsfield.h>
 #include <linux/if_vlan.h>
+#include <linux/mpls.h>
 #include "core.h"
 #include "rdev-ops.h"
 
@@ -475,7 +476,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
 EXPORT_SYMBOL(ieee80211_data_to_8023);
 
 int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
-			     enum nl80211_iftype iftype, u8 *bssid, bool qos)
+			     enum nl80211_iftype iftype,
+			     const u8 *bssid, bool qos)
 {
 	struct ieee80211_hdr hdr;
 	u16 hdrlen, ethertype;
@@ -689,7 +691,8 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 EXPORT_SYMBOL(ieee80211_amsdu_to_8023s);
 
 /* Given a data frame determine the 802.1p/1d tag to use. */
-unsigned int cfg80211_classify8021d(struct sk_buff *skb)
+unsigned int cfg80211_classify8021d(struct sk_buff *skb,
+				    struct cfg80211_qos_map *qos_map)
 {
 	unsigned int dscp;
 	unsigned char vlan_priority;
@@ -716,10 +719,40 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb)
 	case htons(ETH_P_IPV6):
 		dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & 0xfc;
 		break;
+	case htons(ETH_P_MPLS_UC):
+	case htons(ETH_P_MPLS_MC): {
+		struct mpls_label mpls_tmp, *mpls;
+
+		mpls = skb_header_pointer(skb, sizeof(struct ethhdr),
+					  sizeof(*mpls), &mpls_tmp);
+		if (!mpls)
+			return 0;
+
+		return (ntohl(mpls->entry) & MPLS_LS_TC_MASK)
+			>> MPLS_LS_TC_SHIFT;
+	}
+	case htons(ETH_P_80221):
+		/* 802.21 is always network control traffic */
+		return 7;
 	default:
 		return 0;
 	}
 
+	if (qos_map) {
+		unsigned int i, tmp_dscp = dscp >> 2;
+
+		for (i = 0; i < qos_map->num_des; i++) {
+			if (tmp_dscp == qos_map->dscp_exception[i].dscp)
+				return qos_map->dscp_exception[i].up;
+		}
+
+		for (i = 0; i < 8; i++) {
+			if (tmp_dscp >= qos_map->up[i].low &&
+			    tmp_dscp <= qos_map->up[i].high)
+				return i;
+		}
+	}
+
 	return dscp >> 5;
 }
 EXPORT_SYMBOL(cfg80211_classify8021d);
@@ -738,7 +771,7 @@ EXPORT_SYMBOL(ieee80211_bss_get_ie);
 
 void cfg80211_upload_connect_keys(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct net_device *dev = wdev->netdev;
 	int i;
 
@@ -804,7 +837,11 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev)
 						ev->dc.reason, true);
 			break;
 		case EVENT_IBSS_JOINED:
-			__cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid);
+			__cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid,
+					       ev->ij.channel);
+			break;
+		case EVENT_STOPPED:
+			__cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev);
 			break;
 		}
 		wdev_unlock(wdev);
@@ -821,7 +858,6 @@ void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev)
 	struct wireless_dev *wdev;
 
 	ASSERT_RTNL();
-	ASSERT_RDEV_LOCK(rdev);
 
 	list_for_each_entry(wdev, &rdev->wdev_list, list)
 		cfg80211_process_wdev_events(wdev);
@@ -834,7 +870,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 	int err;
 	enum nl80211_iftype otype = dev->ieee80211_ptr->iftype;
 
-	ASSERT_RDEV_LOCK(rdev);
+	ASSERT_RTNL();
 
 	/* don't support changing VLANs, you just re-create them */
 	if (otype == NL80211_IFTYPE_AP_VLAN)
@@ -856,17 +892,15 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 		return -EBUSY;
 
 	if (ntype != otype && netif_running(dev)) {
-		err = cfg80211_can_change_interface(rdev, dev->ieee80211_ptr,
-						    ntype);
-		if (err)
-			return err;
-
 		dev->ieee80211_ptr->use_4addr = false;
 		dev->ieee80211_ptr->mesh_id_up_len = 0;
+		wdev_lock(dev->ieee80211_ptr);
+		rdev_set_qos_map(rdev, dev, NULL);
+		wdev_unlock(dev->ieee80211_ptr);
 
 		switch (otype) {
 		case NL80211_IFTYPE_AP:
-			cfg80211_stop_ap(rdev, dev);
+			cfg80211_stop_ap(rdev, dev, true);
 			break;
 		case NL80211_IFTYPE_ADHOC:
 			cfg80211_leave_ibss(rdev, dev, false);
@@ -1233,6 +1267,120 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
 	return res;
 }
 
+int cfg80211_iter_combinations(struct wiphy *wiphy,
+			       const int num_different_channels,
+			       const u8 radar_detect,
+			       const int iftype_num[NUM_NL80211_IFTYPES],
+			       void (*iter)(const struct ieee80211_iface_combination *c,
+					    void *data),
+			       void *data)
+{
+	const struct ieee80211_regdomain *regdom;
+	enum nl80211_dfs_regions region = 0;
+	int i, j, iftype;
+	int num_interfaces = 0;
+	u32 used_iftypes = 0;
+
+	if (radar_detect) {
+		rcu_read_lock();
+		regdom = rcu_dereference(cfg80211_regdomain);
+		if (regdom)
+			region = regdom->dfs_region;
+		rcu_read_unlock();
+	}
+
+	for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
+		num_interfaces += iftype_num[iftype];
+		if (iftype_num[iftype] > 0 &&
+		    !(wiphy->software_iftypes & BIT(iftype)))
+			used_iftypes |= BIT(iftype);
+	}
+
+	for (i = 0; i < wiphy->n_iface_combinations; i++) {
+		const struct ieee80211_iface_combination *c;
+		struct ieee80211_iface_limit *limits;
+		u32 all_iftypes = 0;
+
+		c = &wiphy->iface_combinations[i];
+
+		if (num_interfaces > c->max_interfaces)
+			continue;
+		if (num_different_channels > c->num_different_channels)
+			continue;
+
+		limits = kmemdup(c->limits, sizeof(limits[0]) * c->n_limits,
+				 GFP_KERNEL);
+		if (!limits)
+			return -ENOMEM;
+
+		for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
+			if (wiphy->software_iftypes & BIT(iftype))
+				continue;
+			for (j = 0; j < c->n_limits; j++) {
+				all_iftypes |= limits[j].types;
+				if (!(limits[j].types & BIT(iftype)))
+					continue;
+				if (limits[j].max < iftype_num[iftype])
+					goto cont;
+				limits[j].max -= iftype_num[iftype];
+			}
+		}
+
+		if (radar_detect != (c->radar_detect_widths & radar_detect))
+			goto cont;
+
+		if (radar_detect && c->radar_detect_regions &&
+		    !(c->radar_detect_regions & BIT(region)))
+			goto cont;
+
+		/* Finally check that all iftypes that we're currently
+		 * using are actually part of this combination. If they
+		 * aren't then we can't use this combination and have
+		 * to continue to the next.
+		 */
+		if ((all_iftypes & used_iftypes) != used_iftypes)
+			goto cont;
+
+		/* This combination covered all interface types and
+		 * supported the requested numbers, so we're good.
+		 */
+
+		(*iter)(c, data);
+ cont:
+		kfree(limits);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(cfg80211_iter_combinations);
+
+static void
+cfg80211_iter_sum_ifcombs(const struct ieee80211_iface_combination *c,
+			  void *data)
+{
+	int *num = data;
+	(*num)++;
+}
+
+int cfg80211_check_combinations(struct wiphy *wiphy,
+				const int num_different_channels,
+				const u8 radar_detect,
+				const int iftype_num[NUM_NL80211_IFTYPES])
+{
+	int err, num = 0;
+
+	err = cfg80211_iter_combinations(wiphy, num_different_channels,
+					 radar_detect, iftype_num,
+					 cfg80211_iter_sum_ifcombs, &num);
+	if (err)
+		return err;
+	if (num == 0)
+		return -EBUSY;
+
+	return 0;
+}
+EXPORT_SYMBOL(cfg80211_check_combinations);
+
 int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 				 struct wireless_dev *wdev,
 				 enum nl80211_iftype iftype,
@@ -1241,7 +1389,6 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 				 u8 radar_detect)
 {
 	struct wireless_dev *wdev_iter;
-	u32 used_iftypes = BIT(iftype);
 	int num[NUM_NL80211_IFTYPES];
 	struct ieee80211_channel
 			*used_channels[CFG80211_MAX_NUM_DIFFERENT_CHANNELS];
@@ -1249,43 +1396,14 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 	enum cfg80211_chan_mode chmode;
 	int num_different_channels = 0;
 	int total = 1;
-	bool radar_required = false;
-	int i, j;
+	int i;
 
 	ASSERT_RTNL();
 
 	if (WARN_ON(hweight32(radar_detect) > 1))
 		return -EINVAL;
 
-	switch (iftype) {
-	case NL80211_IFTYPE_ADHOC:
-	case NL80211_IFTYPE_AP:
-	case NL80211_IFTYPE_AP_VLAN:
-	case NL80211_IFTYPE_MESH_POINT:
-	case NL80211_IFTYPE_P2P_GO:
-	case NL80211_IFTYPE_WDS:
-		/* if the interface could potentially choose a DFS channel,
-		 * then mark DFS as required.
-		 */
-		if (!chan) {
-			if (chanmode != CHAN_MODE_UNDEFINED && radar_detect)
-				radar_required = true;
-			break;
-		}
-		radar_required = !!(chan->flags & IEEE80211_CHAN_RADAR);
-		break;
-	case NL80211_IFTYPE_P2P_CLIENT:
-	case NL80211_IFTYPE_STATION:
-	case NL80211_IFTYPE_P2P_DEVICE:
-	case NL80211_IFTYPE_MONITOR:
-		break;
-	case NUM_NL80211_IFTYPES:
-	case NL80211_IFTYPE_UNSPECIFIED:
-	default:
-		return -EINVAL;
-	}
-
-	if (radar_required && !radar_detect)
+	if (WARN_ON(iftype >= NUM_NL80211_IFTYPES))
 		return -EINVAL;
 
 	/* Always allow software iftypes */
@@ -1300,6 +1418,11 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 
 	num[iftype] = 1;
 
+	/* TODO: We'll probably not need this anymore, since this
+	 * should only be called with CHAN_MODE_UNDEFINED. There are
+	 * still a couple of pending calls where other chanmodes are
+	 * used, but we should get rid of them.
+	 */
 	switch (chanmode) {
 	case CHAN_MODE_UNDEFINED:
 		break;
@@ -1337,7 +1460,7 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 		 */
 		mutex_lock_nested(&wdev_iter->mtx, 1);
 		__acquire(wdev_iter->mtx);
-		cfg80211_get_chan_state(wdev_iter, &ch, &chmode);
+		cfg80211_get_chan_state(wdev_iter, &ch, &chmode, &radar_detect);
 		wdev_unlock(wdev_iter);
 
 		switch (chmode) {
@@ -1363,65 +1486,13 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 
 		num[wdev_iter->iftype]++;
 		total++;
-		used_iftypes |= BIT(wdev_iter->iftype);
 	}
 
 	if (total == 1 && !radar_detect)
 		return 0;
 
-	for (i = 0; i < rdev->wiphy.n_iface_combinations; i++) {
-		const struct ieee80211_iface_combination *c;
-		struct ieee80211_iface_limit *limits;
-		u32 all_iftypes = 0;
-
-		c = &rdev->wiphy.iface_combinations[i];
-
-		if (total > c->max_interfaces)
-			continue;
-		if (num_different_channels > c->num_different_channels)
-			continue;
-
-		limits = kmemdup(c->limits, sizeof(limits[0]) * c->n_limits,
-				 GFP_KERNEL);
-		if (!limits)
-			return -ENOMEM;
-
-		for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
-			if (rdev->wiphy.software_iftypes & BIT(iftype))
-				continue;
-			for (j = 0; j < c->n_limits; j++) {
-				all_iftypes |= limits[j].types;
-				if (!(limits[j].types & BIT(iftype)))
-					continue;
-				if (limits[j].max < num[iftype])
-					goto cont;
-				limits[j].max -= num[iftype];
-			}
-		}
-
-		if (radar_detect && !(c->radar_detect_widths & radar_detect))
-			goto cont;
-
-		/*
-		 * Finally check that all iftypes that we're currently
-		 * using are actually part of this combination. If they
-		 * aren't then we can't use this combination and have
-		 * to continue to the next.
-		 */
-		if ((all_iftypes & used_iftypes) != used_iftypes)
-			goto cont;
-
-		/*
-		 * This combination covered all interface types and
-		 * supported the requested numbers, so we're good.
-		 */
-		kfree(limits);
-		return 0;
- cont:
-		kfree(limits);
-	}
-
-	return -EBUSY;
+	return cfg80211_check_combinations(&rdev->wiphy, num_different_channels,
+					   radar_detect, num);
 }
 
 int ieee80211_get_ratemask(struct ieee80211_supported_band *sband,
@@ -1462,6 +1533,37 @@ int ieee80211_get_ratemask(struct ieee80211_supported_band *sband,
 	return 0;
 }
 
+unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy)
+{
+	enum ieee80211_band band;
+	unsigned int n_channels = 0;
+
+	for (band = 0; band < IEEE80211_NUM_BANDS; band++)
+		if (wiphy->bands[band])
+			n_channels += wiphy->bands[band]->n_channels;
+
+	return n_channels;
+}
+EXPORT_SYMBOL(ieee80211_get_num_supported_channels);
+
+int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr,
+			 struct station_info *sinfo)
+{
+	struct cfg80211_registered_device *rdev;
+	struct wireless_dev *wdev;
+
+	wdev = dev->ieee80211_ptr;
+	if (!wdev)
+		return -EOPNOTSUPP;
+
+	rdev = wiphy_to_rdev(wdev->wiphy);
+	if (!rdev->ops->get_station)
+		return -EOPNOTSUPP;
+
+	return rdev_get_station(rdev, dev, mac_addr, sinfo);
+}
+EXPORT_SYMBOL(cfg80211_get_station);
+
 /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */
 /* Ethernet-II snap header (RFC1042 for most EtherTypes) */
 const unsigned char rfc1042_header[] __aligned(2) =
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index e7c6e862580..11120bb1416 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -73,7 +73,7 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info,
 	struct vif_params vifparams;
 	enum nl80211_iftype type;
 
-	rdev = wiphy_to_dev(wdev->wiphy);
+	rdev = wiphy_to_rdev(wdev->wiphy);
 
 	switch (*mode) {
 	case IW_MODE_INFRA:
@@ -253,12 +253,12 @@ EXPORT_SYMBOL_GPL(cfg80211_wext_giwrange);
 
 /**
  * cfg80211_wext_freq - get wext frequency for non-"auto"
- * @wiphy: the wiphy
+ * @dev: the net device
  * @freq: the wext freq encoding
  *
  * Returns a frequency, or a negative error code, or 0 for auto.
  */
-int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq)
+int cfg80211_wext_freq(struct iw_freq *freq)
 {
 	/*
 	 * Parse frequency - return 0 for auto and
@@ -286,7 +286,7 @@ int cfg80211_wext_siwrts(struct net_device *dev,
 			 struct iw_param *rts, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u32 orts = wdev->wiphy->rts_threshold;
 	int err;
 
@@ -324,7 +324,7 @@ int cfg80211_wext_siwfrag(struct net_device *dev,
 			  struct iw_param *frag, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u32 ofrag = wdev->wiphy->frag_threshold;
 	int err;
 
@@ -364,13 +364,13 @@ static int cfg80211_wext_siwretry(struct net_device *dev,
 				  struct iw_param *retry, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u32 changed = 0;
 	u8 olong = wdev->wiphy->retry_long;
 	u8 oshort = wdev->wiphy->retry_short;
 	int err;
 
-	if (retry->disabled ||
+	if (retry->disabled || retry->value < 1 || retry->value > 255 ||
 	    (retry->flags & IW_RETRY_TYPE) != IW_RETRY_LIMIT)
 		return -EINVAL;
 
@@ -412,9 +412,9 @@ int cfg80211_wext_giwretry(struct net_device *dev,
 		 * First return short value, iwconfig will ask long value
 		 * later if needed
 		 */
-		retry->flags |= IW_RETRY_LIMIT;
+		retry->flags |= IW_RETRY_LIMIT | IW_RETRY_SHORT;
 		retry->value = wdev->wiphy->retry_short;
-		if (wdev->wiphy->retry_long != wdev->wiphy->retry_short)
+		if (wdev->wiphy->retry_long == wdev->wiphy->retry_short)
 			retry->flags |= IW_RETRY_LONG;
 
 		return 0;
@@ -587,7 +587,7 @@ static int cfg80211_wext_siwencode(struct net_device *dev,
 				   struct iw_point *erq, char *keybuf)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int idx, err;
 	bool remove = false;
 	struct key_params params;
@@ -647,7 +647,7 @@ static int cfg80211_wext_siwencodeext(struct net_device *dev,
 				      struct iw_point *erq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct iw_encode_ext *ext = (struct iw_encode_ext *) extra;
 	const u8 *addr;
 	int idx;
@@ -775,7 +775,7 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 				 struct iw_freq *wextfreq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_chan_def chandef = {
 		.width = NL80211_CHAN_WIDTH_20_NOHT,
 	};
@@ -787,7 +787,7 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 	case NL80211_IFTYPE_ADHOC:
 		return cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra);
 	case NL80211_IFTYPE_MONITOR:
-		freq = cfg80211_wext_freq(wdev->wiphy, wextfreq);
+		freq = cfg80211_wext_freq(wextfreq);
 		if (freq < 0)
 			return freq;
 		if (freq == 0)
@@ -798,7 +798,7 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 			return -EINVAL;
 		return cfg80211_set_monitor_channel(rdev, &chandef);
 	case NL80211_IFTYPE_MESH_POINT:
-		freq = cfg80211_wext_freq(wdev->wiphy, wextfreq);
+		freq = cfg80211_wext_freq(wextfreq);
 		if (freq < 0)
 			return freq;
 		if (freq == 0)
@@ -818,7 +818,7 @@ static int cfg80211_wext_giwfreq(struct net_device *dev,
 				 struct iw_freq *freq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_chan_def chandef;
 	int ret;
 
@@ -847,7 +847,7 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev,
 				    union iwreq_data *data, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	enum nl80211_tx_power_setting type;
 	int dbm = 0;
 
@@ -899,7 +899,7 @@ static int cfg80211_wext_giwtxpower(struct net_device *dev,
 				    union iwreq_data *data, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int err, val;
 
 	if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM)
@@ -1119,7 +1119,7 @@ static int cfg80211_wext_siwpower(struct net_device *dev,
 				  struct iw_param *wrq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	bool ps = wdev->ps;
 	int timeout = wdev->ps_timeout;
 	int err;
@@ -1177,7 +1177,7 @@ static int cfg80211_wds_wext_siwap(struct net_device *dev,
 				   struct sockaddr *addr, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int err;
 
 	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS))
@@ -1221,7 +1221,7 @@ static int cfg80211_wext_siwrate(struct net_device *dev,
 				 struct iw_param *rate, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_bitrate_mask mask;
 	u32 fixed, maxrate;
 	struct ieee80211_supported_band *sband;
@@ -1272,7 +1272,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev,
 				 struct iw_param *rate, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	/* we are under RTNL - globally locked - so can use a static struct */
 	static struct station_info sinfo;
 	u8 addr[ETH_ALEN];
@@ -1310,7 +1310,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev,
 static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	/* we are under RTNL - globally locked - so can use static structs */
 	static struct iw_statistics wstats;
 	static struct station_info sinfo;
@@ -1449,7 +1449,7 @@ static int cfg80211_wext_siwpmksa(struct net_device *dev,
 				  struct iw_point *data, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_pmksa cfg_pmksa;
 	struct iw_pmksa *pmksa = (struct iw_pmksa *)extra;
 
diff --git a/net/wireless/wext-compat.h b/net/wireless/wext-compat.h
index 5d766b0118e..ebcacca2f73 100644
--- a/net/wireless/wext-compat.h
+++ b/net/wireless/wext-compat.h
@@ -50,7 +50,7 @@ int cfg80211_wext_siwgenie(struct net_device *dev,
 			   struct iw_point *data, char *extra);
 
 
-int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq);
+int cfg80211_wext_freq(struct iw_freq *freq);
 
 
 extern const struct iw_handler_def cfg80211_wext_handler;
diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c
index 14c9a2583ba..c7e5c8eb4f2 100644
--- a/net/wireless/wext-sme.c
+++ b/net/wireless/wext-sme.c
@@ -21,7 +21,7 @@ int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev,
 	const u8 *prev_bssid = NULL;
 	int err, i;
 
-	ASSERT_RDEV_LOCK(rdev);
+	ASSERT_RTNL();
 	ASSERT_WDEV_LOCK(wdev);
 
 	if (!netif_running(wdev->netdev))
@@ -67,7 +67,7 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev,
 			      struct iw_freq *wextfreq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct ieee80211_channel *chan = NULL;
 	int err, freq;
 
@@ -75,7 +75,7 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev,
 	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION))
 		return -EINVAL;
 
-	freq = cfg80211_wext_freq(wdev->wiphy, wextfreq);
+	freq = cfg80211_wext_freq(wextfreq);
 	if (freq < 0)
 		return freq;
 
@@ -169,7 +169,7 @@ int cfg80211_mgd_wext_siwessid(struct net_device *dev,
 			       struct iw_point *data, char *ssid)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	size_t len = data->length;
 	int err;
 
@@ -260,7 +260,7 @@ int cfg80211_mgd_wext_siwap(struct net_device *dev,
 			    struct sockaddr *ap_addr, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u8 *bssid = ap_addr->sa_data;
 	int err;
 
@@ -333,7 +333,7 @@ int cfg80211_wext_siwgenie(struct net_device *dev,
 			   struct iw_point *data, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u8 *ie = extra;
 	int ie_len = data->length, err;
 
@@ -390,7 +390,7 @@ int cfg80211_wext_siwmlme(struct net_device *dev,
 	if (!wdev)
 		return -EOPNOTSUPP;
 
-	rdev = wiphy_to_dev(wdev->wiphy);
+	rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (wdev->iftype != NL80211_IFTYPE_STATION)
 		return -EINVAL;
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index c8a8297cd4b..5ad4418ef09 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1064,7 +1064,7 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb,
 	x25_start_heartbeat(make);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 	rc = 1;
 	sock_put(sk);
 out:
@@ -1082,7 +1082,7 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct x25_sock *x25 = x25_sk(sk);
-	struct sockaddr_x25 *usx25 = (struct sockaddr_x25 *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_x25 *, usx25, msg->msg_name);
 	struct sockaddr_x25 sx25;
 	struct sk_buff *skb;
 	unsigned char *asmptr;
@@ -1258,7 +1258,7 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct x25_sock *x25 = x25_sk(sk);
-	struct sockaddr_x25 *sx25 = (struct sockaddr_x25 *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_x25 *, sx25, msg->msg_name);
 	size_t copied;
 	int qbit, header_len;
 	struct sk_buff *skb;
diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c
index d1b0dc79bb6..7ac50098a37 100644
--- a/net/x25/x25_in.c
+++ b/net/x25/x25_in.c
@@ -79,7 +79,7 @@ static int x25_queue_rx_frame(struct sock *sk, struct sk_buff *skb, int more)
 	skb_set_owner_r(skbn, sk);
 	skb_queue_tail(&sk->sk_receive_queue, skbn);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skbn->len);
+		sk->sk_data_ready(sk);
 
 	return 0;
 }
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 88843996f93..85d1d476461 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -16,6 +16,81 @@
 
 static struct kmem_cache *secpath_cachep __read_mostly;
 
+static DEFINE_SPINLOCK(xfrm_input_afinfo_lock);
+static struct xfrm_input_afinfo __rcu *xfrm_input_afinfo[NPROTO];
+
+int xfrm_input_register_afinfo(struct xfrm_input_afinfo *afinfo)
+{
+	int err = 0;
+
+	if (unlikely(afinfo == NULL))
+		return -EINVAL;
+	if (unlikely(afinfo->family >= NPROTO))
+		return -EAFNOSUPPORT;
+	spin_lock_bh(&xfrm_input_afinfo_lock);
+	if (unlikely(xfrm_input_afinfo[afinfo->family] != NULL))
+		err = -ENOBUFS;
+	else
+		rcu_assign_pointer(xfrm_input_afinfo[afinfo->family], afinfo);
+	spin_unlock_bh(&xfrm_input_afinfo_lock);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_input_register_afinfo);
+
+int xfrm_input_unregister_afinfo(struct xfrm_input_afinfo *afinfo)
+{
+	int err = 0;
+
+	if (unlikely(afinfo == NULL))
+		return -EINVAL;
+	if (unlikely(afinfo->family >= NPROTO))
+		return -EAFNOSUPPORT;
+	spin_lock_bh(&xfrm_input_afinfo_lock);
+	if (likely(xfrm_input_afinfo[afinfo->family] != NULL)) {
+		if (unlikely(xfrm_input_afinfo[afinfo->family] != afinfo))
+			err = -EINVAL;
+		else
+			RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->family], NULL);
+	}
+	spin_unlock_bh(&xfrm_input_afinfo_lock);
+	synchronize_rcu();
+	return err;
+}
+EXPORT_SYMBOL(xfrm_input_unregister_afinfo);
+
+static struct xfrm_input_afinfo *xfrm_input_get_afinfo(unsigned int family)
+{
+	struct xfrm_input_afinfo *afinfo;
+
+	if (unlikely(family >= NPROTO))
+		return NULL;
+	rcu_read_lock();
+	afinfo = rcu_dereference(xfrm_input_afinfo[family]);
+	if (unlikely(!afinfo))
+		rcu_read_unlock();
+	return afinfo;
+}
+
+static void xfrm_input_put_afinfo(struct xfrm_input_afinfo *afinfo)
+{
+	rcu_read_unlock();
+}
+
+static int xfrm_rcv_cb(struct sk_buff *skb, unsigned int family, u8 protocol,
+		       int err)
+{
+	int ret;
+	struct xfrm_input_afinfo *afinfo = xfrm_input_get_afinfo(family);
+
+	if (!afinfo)
+		return -EAFNOSUPPORT;
+
+	ret = afinfo->callback(skb, protocol, err);
+	xfrm_input_put_afinfo(afinfo);
+
+	return ret;
+}
+
 void __secpath_destroy(struct sec_path *sp)
 {
 	int i;
@@ -67,7 +142,7 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq)
 	case IPPROTO_COMP:
 		if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr)))
 			return -EINVAL;
-		*spi = htonl(ntohs(*(__be16*)(skb_transport_header(skb) + 2)));
+		*spi = htonl(ntohs(*(__be16 *)(skb_transport_header(skb) + 2)));
 		*seq = 0;
 		return 0;
 	default:
@@ -77,8 +152,8 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq)
 	if (!pskb_may_pull(skb, hlen))
 		return -EINVAL;
 
-	*spi = *(__be32*)(skb_transport_header(skb) + offset);
-	*seq = *(__be32*)(skb_transport_header(skb) + offset_seq);
+	*spi = *(__be32 *)(skb_transport_header(skb) + offset);
+	*seq = *(__be32 *)(skb_transport_header(skb) + offset_seq);
 	return 0;
 }
 
@@ -108,7 +183,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 	int err;
 	__be32 seq;
 	__be32 seq_hi;
-	struct xfrm_state *x;
+	struct xfrm_state *x = NULL;
 	xfrm_address_t *daddr;
 	struct xfrm_mode *inner_mode;
 	unsigned int family;
@@ -120,9 +195,14 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		async = 1;
 		x = xfrm_input_state(skb);
 		seq = XFRM_SKB_CB(skb)->seq.input.low;
+		family = x->outer_mode->afinfo->family;
 		goto resume;
 	}
 
+	daddr = (xfrm_address_t *)(skb_network_header(skb) +
+				   XFRM_SPI_SKB_CB(skb)->daddroff);
+	family = XFRM_SPI_SKB_CB(skb)->family;
+
 	/* Allocate new secpath or COW existing one. */
 	if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) {
 		struct sec_path *sp;
@@ -137,10 +217,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		skb->sp = sp;
 	}
 
-	daddr = (xfrm_address_t *)(skb_network_header(skb) +
-				   XFRM_SPI_SKB_CB(skb)->daddroff);
-	family = XFRM_SPI_SKB_CB(skb)->family;
-
 	seq = 0;
 	if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
@@ -162,6 +238,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		skb->sp->xvec[skb->sp->len++] = x;
 
+		if (xfrm_tunnel_check(skb, x, family)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
+			goto drop;
+		}
+
 		spin_lock(&x->lock);
 		if (unlikely(x->km.state == XFRM_STATE_ACQ)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
@@ -201,7 +282,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 		if (nexthdr == -EINPROGRESS)
 			return 0;
-
 resume:
 		spin_lock(&x->lock);
 		if (nexthdr <= 0) {
@@ -263,6 +343,10 @@ resume:
 		}
 	} while (!err);
 
+	err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
+	if (err)
+		goto drop;
+
 	nf_reset(skb);
 
 	if (decaps) {
@@ -276,6 +360,7 @@ resume:
 drop_unlock:
 	spin_unlock(&x->lock);
 drop:
+	xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1);
 	kfree_skb(skb);
 	return 0;
 }
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 3bb2cdc13b4..c51e8f7b865 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -199,6 +199,7 @@ int xfrm_output(struct sk_buff *skb)
 
 	return xfrm_output2(skb);
 }
+EXPORT_SYMBOL_GPL(xfrm_output);
 
 int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 {
@@ -213,6 +214,7 @@ int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 		return -EAFNOSUPPORT;
 	return inner_mode->afinfo->extract_output(x, skb);
 }
+EXPORT_SYMBOL_GPL(xfrm_inner_extract_output);
 
 void xfrm_local_error(struct sk_buff *skb, int mtu)
 {
@@ -233,7 +235,4 @@ void xfrm_local_error(struct sk_buff *skb, int mtu)
 	afinfo->local_error(skb, mtu);
 	xfrm_state_put_afinfo(afinfo);
 }
-
-EXPORT_SYMBOL_GPL(xfrm_output);
-EXPORT_SYMBOL_GPL(xfrm_inner_extract_output);
 EXPORT_SYMBOL_GPL(xfrm_local_error);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 9a91f7431c4..0525d78ba32 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -39,13 +39,6 @@
 #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ))
 #define XFRM_MAX_QUEUE_LEN	100
 
-DEFINE_MUTEX(xfrm_cfg_mutex);
-EXPORT_SYMBOL(xfrm_cfg_mutex);
-
-static DEFINE_SPINLOCK(xfrm_policy_sk_bundle_lock);
-static struct dst_entry *xfrm_policy_sk_bundles;
-static DEFINE_RWLOCK(xfrm_policy_lock);
-
 static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
 static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO]
 						__read_mostly;
@@ -176,7 +169,7 @@ static inline unsigned long make_jiffies(long secs)
 
 static void xfrm_policy_timer(unsigned long data)
 {
-	struct xfrm_policy *xp = (struct xfrm_policy*)data;
+	struct xfrm_policy *xp = (struct xfrm_policy *)data;
 	unsigned long now = get_seconds();
 	long next = LONG_MAX;
 	int warn = 0;
@@ -438,7 +431,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
 	if (!ndst)
 		return;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
 	for (i = hmask; i >= 0; i--)
 		xfrm_dst_hash_transfer(odst + i, ndst, nhashmask);
@@ -446,7 +439,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
 	net->xfrm.policy_bydst[dir].table = ndst;
 	net->xfrm.policy_bydst[dir].hmask = nhashmask;
 
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head));
 }
@@ -463,7 +456,7 @@ static void xfrm_byidx_resize(struct net *net, int total)
 	if (!nidx)
 		return;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
 	for (i = hmask; i >= 0; i--)
 		xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask);
@@ -471,7 +464,7 @@ static void xfrm_byidx_resize(struct net *net, int total)
 	net->xfrm.policy_byidx = nidx;
 	net->xfrm.policy_idx_hmask = nhashmask;
 
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head));
 }
@@ -504,7 +497,7 @@ static inline int xfrm_byidx_should_resize(struct net *net, int total)
 
 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
 {
-	read_lock_bh(&xfrm_policy_lock);
+	read_lock_bh(&net->xfrm.xfrm_policy_lock);
 	si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN];
 	si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT];
 	si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD];
@@ -513,7 +506,7 @@ void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si)
 	si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX];
 	si->spdhcnt = net->xfrm.policy_idx_hmask;
 	si->spdhmcnt = xfrm_policy_hashmax;
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 }
 EXPORT_SYMBOL(xfrm_spd_getinfo);
 
@@ -538,7 +531,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 
 /* Generate new index... KAME seems to generate them ordered by cost
  * of an absolute inpredictability of ordering of rules. This will not pass. */
-static u32 xfrm_gen_index(struct net *net, int dir)
+static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
 {
 	static u32 idx_generator;
 
@@ -548,8 +541,14 @@ static u32 xfrm_gen_index(struct net *net, int dir)
 		u32 idx;
 		int found;
 
-		idx = (idx_generator | dir);
-		idx_generator += 8;
+		if (!index) {
+			idx = (idx_generator | dir);
+			idx_generator += 8;
+		} else {
+			idx = index;
+			index = 0;
+		}
+
 		if (idx == 0)
 			idx = 8;
 		list = net->xfrm.policy_byidx + idx_hash(net, idx);
@@ -630,7 +629,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	struct hlist_head *chain;
 	struct hlist_node *newpos;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
 	delpol = NULL;
 	newpos = NULL;
@@ -641,7 +640,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 		    xfrm_sec_ctx_match(pol->security, policy->security) &&
 		    !WARN_ON(delpol)) {
 			if (excl) {
-				write_unlock_bh(&xfrm_policy_lock);
+				write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 				return -EEXIST;
 			}
 			delpol = pol;
@@ -660,7 +659,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 		hlist_add_head(&policy->bydst, chain);
 	xfrm_pol_hold(policy);
 	net->xfrm.policy_count[dir]++;
-	atomic_inc(&flow_cache_genid);
+	atomic_inc(&net->xfrm.flow_cache_genid);
 
 	/* After previous checking, family can either be AF_INET or AF_INET6 */
 	if (policy->family == AF_INET)
@@ -672,14 +671,14 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 		xfrm_policy_requeue(delpol, policy);
 		__xfrm_policy_unlink(delpol, dir);
 	}
-	policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir);
+	policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index);
 	hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
 	policy->curlft.add_time = get_seconds();
 	policy->curlft.use_time = 0;
 	if (!mod_timer(&policy->timer, jiffies + HZ))
 		xfrm_pol_hold(policy);
 	list_add(&policy->walk.all, &net->xfrm.policy_all);
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (delpol)
 		xfrm_policy_kill(delpol);
@@ -699,7 +698,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
 	struct hlist_head *chain;
 
 	*err = 0;
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_bysel(net, sel, sel->family, dir);
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
@@ -712,7 +711,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
 				*err = security_xfrm_policy_delete(
 								pol->security);
 				if (*err) {
-					write_unlock_bh(&xfrm_policy_lock);
+					write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 					return pol;
 				}
 				__xfrm_policy_unlink(pol, dir);
@@ -721,7 +720,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
 			break;
 		}
 	}
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (ret && delete)
 		xfrm_policy_kill(ret);
@@ -740,7 +739,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
 		return NULL;
 
 	*err = 0;
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = net->xfrm.policy_byidx + idx_hash(net, id);
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, byidx) {
@@ -751,7 +750,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
 				*err = security_xfrm_policy_delete(
 								pol->security);
 				if (*err) {
-					write_unlock_bh(&xfrm_policy_lock);
+					write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 					return pol;
 				}
 				__xfrm_policy_unlink(pol, dir);
@@ -760,7 +759,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
 			break;
 		}
 	}
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (ret && delete)
 		xfrm_policy_kill(ret);
@@ -770,7 +769,7 @@ EXPORT_SYMBOL(xfrm_policy_byid);
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 static inline int
-xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info)
+xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
 {
 	int dir, err = 0;
 
@@ -784,10 +783,7 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi
 				continue;
 			err = security_xfrm_policy_delete(pol->security);
 			if (err) {
-				xfrm_audit_policy_delete(pol, 0,
-							 audit_info->loginuid,
-							 audit_info->sessionid,
-							 audit_info->secid);
+				xfrm_audit_policy_delete(pol, 0, task_valid);
 				return err;
 			}
 		}
@@ -801,9 +797,7 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi
 								pol->security);
 				if (err) {
 					xfrm_audit_policy_delete(pol, 0,
-							audit_info->loginuid,
-							audit_info->sessionid,
-							audit_info->secid);
+								 task_valid);
 					return err;
 				}
 			}
@@ -813,19 +807,19 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi
 }
 #else
 static inline int
-xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info)
+xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
 {
 	return 0;
 }
 #endif
 
-int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
+int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
 {
 	int dir, err = 0, cnt = 0;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
-	err = xfrm_policy_flush_secctx_check(net, type, audit_info);
+	err = xfrm_policy_flush_secctx_check(net, type, task_valid);
 	if (err)
 		goto out;
 
@@ -839,16 +833,14 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 			if (pol->type != type)
 				continue;
 			__xfrm_policy_unlink(pol, dir);
-			write_unlock_bh(&xfrm_policy_lock);
+			write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 			cnt++;
 
-			xfrm_audit_policy_delete(pol, 1, audit_info->loginuid,
-						 audit_info->sessionid,
-						 audit_info->secid);
+			xfrm_audit_policy_delete(pol, 1, task_valid);
 
 			xfrm_policy_kill(pol);
 
-			write_lock_bh(&xfrm_policy_lock);
+			write_lock_bh(&net->xfrm.xfrm_policy_lock);
 			goto again1;
 		}
 
@@ -860,16 +852,13 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 				if (pol->type != type)
 					continue;
 				__xfrm_policy_unlink(pol, dir);
-				write_unlock_bh(&xfrm_policy_lock);
+				write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 				cnt++;
 
-				xfrm_audit_policy_delete(pol, 1,
-							 audit_info->loginuid,
-							 audit_info->sessionid,
-							 audit_info->secid);
+				xfrm_audit_policy_delete(pol, 1, task_valid);
 				xfrm_policy_kill(pol);
 
-				write_lock_bh(&xfrm_policy_lock);
+				write_lock_bh(&net->xfrm.xfrm_policy_lock);
 				goto again2;
 			}
 		}
@@ -878,7 +867,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 	if (!cnt)
 		err = -ESRCH;
 out:
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_policy_flush);
@@ -898,7 +887,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
 	if (list_empty(&walk->walk.all) && walk->seq != 0)
 		return 0;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	if (list_empty(&walk->walk.all))
 		x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all);
 	else
@@ -924,7 +913,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
 	}
 	list_del_init(&walk->walk.all);
 out:
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	return error;
 }
 EXPORT_SYMBOL(xfrm_policy_walk);
@@ -938,14 +927,14 @@ void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type)
 }
 EXPORT_SYMBOL(xfrm_policy_walk_init);
 
-void xfrm_policy_walk_done(struct xfrm_policy_walk *walk)
+void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net)
 {
 	if (list_empty(&walk->walk.all))
 		return;
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */
 	list_del(&walk->walk.all);
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 }
 EXPORT_SYMBOL(xfrm_policy_walk_done);
 
@@ -990,7 +979,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 	if (unlikely(!daddr || !saddr))
 		return NULL;
 
-	read_lock_bh(&xfrm_policy_lock);
+	read_lock_bh(&net->xfrm.xfrm_policy_lock);
 	chain = policy_hash_direct(net, daddr, saddr, family, dir);
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
@@ -1026,7 +1015,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 	if (ret)
 		xfrm_pol_hold(ret);
 fail:
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	return ret;
 }
@@ -1103,8 +1092,9 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir,
 						 const struct flowi *fl)
 {
 	struct xfrm_policy *pol;
+	struct net *net = sock_net(sk);
 
-	read_lock_bh(&xfrm_policy_lock);
+	read_lock_bh(&net->xfrm.xfrm_policy_lock);
 	if ((pol = sk->sk_policy[dir]) != NULL) {
 		bool match = xfrm_selector_match(&pol->selector, fl,
 						 sk->sk_family);
@@ -1128,7 +1118,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir,
 			pol = NULL;
 	}
 out:
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	return pol;
 }
 
@@ -1156,7 +1146,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 	if (hlist_unhashed(&pol->bydst))
 		return NULL;
 
-	hlist_del(&pol->bydst);
+	hlist_del_init(&pol->bydst);
 	hlist_del(&pol->byidx);
 	list_del(&pol->walk.all);
 	net->xfrm.policy_count[dir]--;
@@ -1166,9 +1156,11 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 
 int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
 {
-	write_lock_bh(&xfrm_policy_lock);
+	struct net *net = xp_net(pol);
+
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	pol = __xfrm_policy_unlink(pol, dir);
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	if (pol) {
 		xfrm_policy_kill(pol);
 		return 0;
@@ -1187,12 +1179,12 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 		return -EINVAL;
 #endif
 
-	write_lock_bh(&xfrm_policy_lock);
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 	old_pol = sk->sk_policy[dir];
 	sk->sk_policy[dir] = pol;
 	if (pol) {
 		pol->curlft.add_time = get_seconds();
-		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir);
+		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
 		__xfrm_policy_link(pol, XFRM_POLICY_MAX+dir);
 	}
 	if (old_pol) {
@@ -1204,7 +1196,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 		 */
 		__xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir);
 	}
-	write_unlock_bh(&xfrm_policy_lock);
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (old_pol) {
 		xfrm_policy_kill(old_pol);
@@ -1215,6 +1207,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
 {
 	struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC);
+	struct net *net = xp_net(old);
 
 	if (newp) {
 		newp->selector = old->selector;
@@ -1233,9 +1226,9 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
 		newp->type = old->type;
 		memcpy(newp->xfrm_vec, old->xfrm_vec,
 		       newp->xfrm_nr*sizeof(struct xfrm_tmpl));
-		write_lock_bh(&xfrm_policy_lock);
+		write_lock_bh(&net->xfrm.xfrm_policy_lock);
 		__xfrm_policy_link(newp, XFRM_POLICY_MAX+dir);
-		write_unlock_bh(&xfrm_policy_lock);
+		write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 		xfrm_pol_put(newp);
 	}
 	return newp;
@@ -1281,7 +1274,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
 	xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family);
 	xfrm_address_t tmp;
 
-	for (nx=0, i = 0; i < policy->xfrm_nr; i++) {
+	for (nx = 0, i = 0; i < policy->xfrm_nr; i++) {
 		struct xfrm_state *x;
 		xfrm_address_t *remote = daddr;
 		xfrm_address_t *local  = saddr;
@@ -1311,9 +1304,9 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
 			error = (x->km.state == XFRM_STATE_ERROR ?
 				 -EINVAL : -EAGAIN);
 			xfrm_state_put(x);
-		}
-		else if (error == -ESRCH)
+		} else if (error == -ESRCH) {
 			error = -EAGAIN;
+		}
 
 		if (!tmpl->optional)
 			goto fail;
@@ -1321,7 +1314,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
 	return nx;
 
 fail:
-	for (nx--; nx>=0; nx--)
+	for (nx--; nx >= 0; nx--)
 		xfrm_state_put(xfrm[nx]);
 	return error;
 }
@@ -1358,7 +1351,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl,
 	return cnx;
 
  fail:
-	for (cnx--; cnx>=0; cnx--)
+	for (cnx--; cnx >= 0; cnx--)
 		xfrm_state_put(tpp[cnx]);
 	return error;
 
@@ -1636,20 +1629,22 @@ free_dst:
 	goto out;
 }
 
-static int inline
-xfrm_dst_alloc_copy(void **target, const void *src, int size)
+#ifdef CONFIG_XFRM_SUB_POLICY
+static int xfrm_dst_alloc_copy(void **target, const void *src, int size)
 {
 	if (!*target) {
 		*target = kmalloc(size, GFP_ATOMIC);
 		if (!*target)
 			return -ENOMEM;
 	}
+
 	memcpy(*target, src, size);
 	return 0;
 }
+#endif
 
-static int inline
-xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel)
+static int xfrm_dst_update_parent(struct dst_entry *dst,
+				  const struct xfrm_selector *sel)
 {
 #ifdef CONFIG_XFRM_SUB_POLICY
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
@@ -1660,8 +1655,8 @@ xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel)
 #endif
 }
 
-static int inline
-xfrm_dst_update_origin(struct dst_entry *dst, const struct flowi *fl)
+static int xfrm_dst_update_origin(struct dst_entry *dst,
+				  const struct flowi *fl)
 {
 #ifdef CONFIG_XFRM_SUB_POLICY
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
@@ -1699,7 +1694,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family,
 				xfrm_pols_put(pols, *num_pols);
 				return PTR_ERR(pols[1]);
 			}
-			(*num_pols) ++;
+			(*num_pols)++;
 			(*num_xfrms) += pols[1]->xfrm_nr;
 		}
 	}
@@ -1753,7 +1748,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 	}
 
 	xdst->num_pols = num_pols;
-	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 	xdst->policy_genid = atomic_read(&pols[0]->genid);
 
 	return xdst;
@@ -1837,7 +1832,7 @@ purge_queue:
 	xfrm_pol_put(pol);
 }
 
-static int xdst_queue_output(struct sk_buff *skb)
+static int xdst_queue_output(struct sock *sk, struct sk_buff *skb)
 {
 	unsigned long sched_next;
 	struct dst_entry *dst = skb_dst(skb);
@@ -1896,8 +1891,7 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
 	if (IS_ERR(xdst))
 		return xdst;
 
-	if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0 ||
-	    (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP))
+	if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0)
 		return xdst;
 
 	dst1 = &xdst->u.dst;
@@ -2023,7 +2017,7 @@ make_dummy_bundle:
 	}
 	xdst->num_pols = num_pols;
 	xdst->num_xfrms = num_xfrms;
-	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols);
+	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 
 	dst_hold(&xdst->u.dst);
 	return &xdst->flo;
@@ -2072,7 +2066,6 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 	u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
 	int i, err, num_pols, num_xfrms = 0, drop_pols = 0;
 
-restart:
 	dst = NULL;
 	xdst = NULL;
 	route = NULL;
@@ -2105,12 +2098,7 @@ restart:
 			}
 
 			dst_hold(&xdst->u.dst);
-
-			spin_lock_bh(&xfrm_policy_sk_bundle_lock);
-			xdst->u.dst.next = xfrm_policy_sk_bundles;
-			xfrm_policy_sk_bundles = &xdst->u.dst;
-			spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
-
+			xdst->u.dst.flags |= DST_NOCACHE;
 			route = xdst->route;
 		}
 	}
@@ -2133,7 +2121,7 @@ restart:
 
 		num_pols = xdst->num_pols;
 		num_xfrms = xdst->num_xfrms;
-		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols);
+		memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols);
 		route = xdst->route;
 	}
 
@@ -2152,23 +2140,8 @@ restart:
 
 			return make_blackhole(net, family, dst_orig);
 		}
-		if (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP) {
-			DECLARE_WAITQUEUE(wait, current);
-
-			add_wait_queue(&net->xfrm.km_waitq, &wait);
-			set_current_state(TASK_INTERRUPTIBLE);
-			schedule();
-			set_current_state(TASK_RUNNING);
-			remove_wait_queue(&net->xfrm.km_waitq, &wait);
 
-			if (!signal_pending(current)) {
-				dst_release(dst);
-				goto restart;
-			}
-
-			err = -ERESTART;
-		} else
-			err = -EAGAIN;
+		err = -EAGAIN;
 
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
 		goto error;
@@ -2344,7 +2317,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	if (skb->sp) {
 		int i;
 
-		for (i=skb->sp->len-1; i>=0; i--) {
+		for (i = skb->sp->len-1; i >= 0; i--) {
 			struct xfrm_state *x = skb->sp->xvec[i];
 			if (!xfrm_selector_match(&x->sel, &fl, family)) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH);
@@ -2390,7 +2363,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	pol->curlft.use_time = get_seconds();
 
 	pols[0] = pol;
-	npols ++;
+	npols++;
 #ifdef CONFIG_XFRM_SUB_POLICY
 	if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
 		pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN,
@@ -2402,7 +2375,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 				return 0;
 			}
 			pols[1]->curlft.use_time = get_seconds();
-			npols ++;
+			npols++;
 		}
 	}
 #endif
@@ -2434,7 +2407,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		}
 		xfrm_nr = ti;
 		if (npols > 1) {
-			xfrm_tmpl_sort(stp, tpp, xfrm_nr, family);
+			xfrm_tmpl_sort(stp, tpp, xfrm_nr, family, net);
 			tpp = stp;
 		}
 
@@ -2559,33 +2532,15 @@ static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst)
 	return dst;
 }
 
-static void __xfrm_garbage_collect(struct net *net)
-{
-	struct dst_entry *head, *next;
-
-	spin_lock_bh(&xfrm_policy_sk_bundle_lock);
-	head = xfrm_policy_sk_bundles;
-	xfrm_policy_sk_bundles = NULL;
-	spin_unlock_bh(&xfrm_policy_sk_bundle_lock);
-
-	while (head) {
-		next = head->next;
-		dst_free(head);
-		head = next;
-	}
-}
-
 void xfrm_garbage_collect(struct net *net)
 {
-	flow_cache_flush();
-	__xfrm_garbage_collect(net);
+	flow_cache_flush(net);
 }
 EXPORT_SYMBOL(xfrm_garbage_collect);
 
 static void xfrm_garbage_collect_deferred(struct net *net)
 {
-	flow_cache_flush_deferred();
-	__xfrm_garbage_collect(net);
+	flow_cache_flush_deferred(net);
 }
 
 static void xfrm_init_pmtu(struct dst_entry *dst)
@@ -2820,21 +2775,19 @@ static struct notifier_block xfrm_dev_notifier = {
 static int __net_init xfrm_statistics_init(struct net *net)
 {
 	int rv;
-
-	if (snmp_mib_init((void __percpu **)net->mib.xfrm_statistics,
-			  sizeof(struct linux_xfrm_mib),
-			  __alignof__(struct linux_xfrm_mib)) < 0)
+	net->mib.xfrm_statistics = alloc_percpu(struct linux_xfrm_mib);
+	if (!net->mib.xfrm_statistics)
 		return -ENOMEM;
 	rv = xfrm_proc_init(net);
 	if (rv < 0)
-		snmp_mib_free((void __percpu **)net->mib.xfrm_statistics);
+		free_percpu(net->mib.xfrm_statistics);
 	return rv;
 }
 
 static void xfrm_statistics_fini(struct net *net)
 {
 	xfrm_proc_fini(net);
-	snmp_mib_free((void __percpu **)net->mib.xfrm_statistics);
+	free_percpu(net->mib.xfrm_statistics);
 }
 #else
 static int __net_init xfrm_statistics_init(struct net *net)
@@ -2899,21 +2852,14 @@ out_byidx:
 
 static void xfrm_policy_fini(struct net *net)
 {
-	struct xfrm_audit audit_info;
 	unsigned int sz;
 	int dir;
 
 	flush_work(&net->xfrm.policy_hash_work);
 #ifdef CONFIG_XFRM_SUB_POLICY
-	audit_info.loginuid = INVALID_UID;
-	audit_info.sessionid = -1;
-	audit_info.secid = 0;
-	xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, &audit_info);
+	xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false);
 #endif
-	audit_info.loginuid = INVALID_UID;
-	audit_info.sessionid = -1;
-	audit_info.secid = 0;
-	xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, &audit_info);
+	xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false);
 
 	WARN_ON(!list_empty(&net->xfrm.policy_all));
 
@@ -2950,8 +2896,19 @@ static int __net_init xfrm_net_init(struct net *net)
 	rv = xfrm_sysctl_init(net);
 	if (rv < 0)
 		goto out_sysctl;
+	rv = flow_cache_init(net);
+	if (rv < 0)
+		goto out;
+
+	/* Initialize the per-net locks here */
+	spin_lock_init(&net->xfrm.xfrm_state_lock);
+	rwlock_init(&net->xfrm.xfrm_policy_lock);
+	mutex_init(&net->xfrm.xfrm_cfg_mutex);
+
 	return 0;
 
+out:
+	xfrm_sysctl_fini(net);
 out_sysctl:
 	xfrm_policy_fini(net);
 out_policy:
@@ -2964,6 +2921,7 @@ out_statistics:
 
 static void __net_exit xfrm_net_exit(struct net *net)
 {
+	flow_cache_fini(net);
 	xfrm_sysctl_fini(net);
 	xfrm_policy_fini(net);
 	xfrm_state_fini(net);
@@ -2992,7 +2950,7 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp,
 		audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
 				 ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
 
-	switch(sel->family) {
+	switch (sel->family) {
 	case AF_INET:
 		audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4);
 		if (sel->prefixlen_s != 32)
@@ -3016,15 +2974,14 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp,
 	}
 }
 
-void xfrm_audit_policy_add(struct xfrm_policy *xp, int result,
-			   kuid_t auid, u32 sessionid, u32 secid)
+void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid)
 {
 	struct audit_buffer *audit_buf;
 
 	audit_buf = xfrm_audit_start("SPD-add");
 	if (audit_buf == NULL)
 		return;
-	xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf);
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
 	audit_log_format(audit_buf, " res=%u", result);
 	xfrm_audit_common_policyinfo(xp, audit_buf);
 	audit_log_end(audit_buf);
@@ -3032,14 +2989,14 @@ void xfrm_audit_policy_add(struct xfrm_policy *xp, int result,
 EXPORT_SYMBOL_GPL(xfrm_audit_policy_add);
 
 void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result,
-			      kuid_t auid, u32 sessionid, u32 secid)
+			      bool task_valid)
 {
 	struct audit_buffer *audit_buf;
 
 	audit_buf = xfrm_audit_start("SPD-delete");
 	if (audit_buf == NULL)
 		return;
-	xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf);
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
 	audit_log_format(audit_buf, " res=%u", result);
 	xfrm_audit_common_policyinfo(xp, audit_buf);
 	audit_log_end(audit_buf);
@@ -3069,15 +3026,15 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp,
 	return false;
 }
 
-static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel,
-						     u8 dir, u8 type)
+static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel,
+						    u8 dir, u8 type, struct net *net)
 {
 	struct xfrm_policy *pol, *ret = NULL;
 	struct hlist_head *chain;
 	u32 priority = ~0U;
 
-	read_lock_bh(&xfrm_policy_lock);
-	chain = policy_hash_direct(&init_net, &sel->daddr, &sel->saddr, sel->family, dir);
+	read_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME*/
+	chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir);
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (xfrm_migrate_selector_match(sel, &pol->selector) &&
 		    pol->type == type) {
@@ -3086,7 +3043,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector
 			break;
 		}
 	}
-	chain = &init_net.xfrm.policy_inexact[dir];
+	chain = &net->xfrm.policy_inexact[dir];
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (xfrm_migrate_selector_match(sel, &pol->selector) &&
 		    pol->type == type &&
@@ -3099,7 +3056,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector
 	if (ret)
 		xfrm_pol_hold(ret);
 
-	read_unlock_bh(&xfrm_policy_lock);
+	read_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	return ret;
 }
@@ -3210,7 +3167,7 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate)
 
 int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		 struct xfrm_migrate *m, int num_migrate,
-		 struct xfrm_kmaddress *k)
+		 struct xfrm_kmaddress *k, struct net *net)
 {
 	int i, err, nx_cur = 0, nx_new = 0;
 	struct xfrm_policy *pol = NULL;
@@ -3223,14 +3180,14 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 		goto out;
 
 	/* Stage 1 - find policy */
-	if ((pol = xfrm_migrate_policy_find(sel, dir, type)) == NULL) {
+	if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) {
 		err = -ENOENT;
 		goto out;
 	}
 
 	/* Stage 2 - find and update state(s) */
 	for (i = 0, mp = m; i < num_migrate; i++, mp++) {
-		if ((x = xfrm_migrate_state_find(mp))) {
+		if ((x = xfrm_migrate_state_find(mp, net))) {
 			x_cur[nx_cur] = x;
 			nx_cur++;
 			if ((xc = xfrm_state_migrate(x, mp))) {
diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c
index 80cd1e55b83..9c4fbd8935f 100644
--- a/net/xfrm/xfrm_proc.c
+++ b/net/xfrm/xfrm_proc.c
@@ -52,10 +52,9 @@ static int xfrm_statistics_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
 	int i;
-	for (i=0; xfrm_mib_list[i].name; i++)
+	for (i = 0; xfrm_mib_list[i].name; i++)
 		seq_printf(seq, "%-24s\t%lu\n", xfrm_mib_list[i].name,
-			   snmp_fold_field((void __percpu **)
-					   net->mib.xfrm_statistics,
+			   snmp_fold_field(net->mib.xfrm_statistics,
 					   xfrm_mib_list[i].entry));
 	return 0;
 }
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 68c2f357a18..0ab54134bb4 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -35,8 +35,6 @@
       destination/tunnel endpoint. (output)
  */
 
-static DEFINE_SPINLOCK(xfrm_state_lock);
-
 static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
 
 static inline unsigned int xfrm_dst_hash(struct net *net,
@@ -127,7 +125,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 		goto out_unlock;
 	}
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 
 	nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
 	for (i = net->xfrm.state_hmask; i >= 0; i--)
@@ -144,7 +142,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	net->xfrm.state_byspi = nspi;
 	net->xfrm.state_hmask = nhashmask;
 
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	osize = (ohashmask + 1) * sizeof(struct hlist_head);
 	xfrm_hash_free(odst, osize);
@@ -163,6 +161,7 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock);
 int __xfrm_state_delete(struct xfrm_state *x);
 
 int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
+bool km_is_alive(const struct km_event *c);
 void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
 
 static DEFINE_SPINLOCK(xfrm_type_lock);
@@ -374,8 +373,6 @@ static void xfrm_state_gc_task(struct work_struct *work)
 
 	hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
 		xfrm_state_gc_destroy(x);
-
-	wake_up(&net->xfrm.km_waitq);
 }
 
 static inline unsigned long make_jiffies(long secs)
@@ -386,11 +383,10 @@ static inline unsigned long make_jiffies(long secs)
 		return secs*HZ;
 }
 
-static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me)
+static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 {
 	struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
 	struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
-	struct net *net = xs_net(x);
 	unsigned long now = get_seconds();
 	long next = LONG_MAX;
 	int warn = 0;
@@ -453,27 +449,21 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me)
 	if (warn)
 		km_state_expired(x, 0, 0);
 resched:
-	if (next != LONG_MAX){
+	if (next != LONG_MAX) {
 		tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
 	}
 
 	goto out;
 
 expired:
-	if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) {
+	if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0)
 		x->km.state = XFRM_STATE_EXPIRED;
-		wake_up(&net->xfrm.km_waitq);
-		next = 2;
-		goto resched;
-	}
 
 	err = __xfrm_state_delete(x);
 	if (!err)
 		km_state_expired(x, 1, 0);
 
-	xfrm_audit_state_delete(x, err ? 0 : 1,
-				audit_get_loginuid(current),
-				audit_get_sessionid(current), 0);
+	xfrm_audit_state_delete(x, err ? 0 : 1, true);
 
 out:
 	spin_unlock(&x->lock);
@@ -535,14 +525,14 @@ int __xfrm_state_delete(struct xfrm_state *x)
 
 	if (x->km.state != XFRM_STATE_DEAD) {
 		x->km.state = XFRM_STATE_DEAD;
-		spin_lock(&xfrm_state_lock);
+		spin_lock(&net->xfrm.xfrm_state_lock);
 		list_del(&x->km.all);
 		hlist_del(&x->bydst);
 		hlist_del(&x->bysrc);
 		if (x->id.spi)
 			hlist_del(&x->byspi);
 		net->xfrm.state_num--;
-		spin_unlock(&xfrm_state_lock);
+		spin_unlock(&net->xfrm.xfrm_state_lock);
 
 		/* All xfrm_state objects are created by xfrm_state_alloc.
 		 * The xfrm_state_alloc call gives a reference, and that
@@ -570,7 +560,7 @@ EXPORT_SYMBOL(xfrm_state_delete);
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 static inline int
-xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audit_info)
+xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
 {
 	int i, err = 0;
 
@@ -580,10 +570,7 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audi
 		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
 			if (xfrm_id_proto_match(x->id.proto, proto) &&
 			   (err = security_xfrm_state_delete(x)) != 0) {
-				xfrm_audit_state_delete(x, 0,
-							audit_info->loginuid,
-							audit_info->sessionid,
-							audit_info->secid);
+				xfrm_audit_state_delete(x, 0, task_valid);
 				return err;
 			}
 		}
@@ -593,18 +580,18 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audi
 }
 #else
 static inline int
-xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audit_info)
+xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
 {
 	return 0;
 }
 #endif
 
-int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info)
+int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
 {
 	int i, err = 0, cnt = 0;
 
-	spin_lock_bh(&xfrm_state_lock);
-	err = xfrm_state_flush_secctx_check(net, proto, audit_info);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	err = xfrm_state_flush_secctx_check(net, proto, task_valid);
 	if (err)
 		goto out;
 
@@ -616,18 +603,16 @@ restart:
 			if (!xfrm_state_kern(x) &&
 			    xfrm_id_proto_match(x->id.proto, proto)) {
 				xfrm_state_hold(x);
-				spin_unlock_bh(&xfrm_state_lock);
+				spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 				err = xfrm_state_delete(x);
 				xfrm_audit_state_delete(x, err ? 0 : 1,
-							audit_info->loginuid,
-							audit_info->sessionid,
-							audit_info->secid);
+							task_valid);
 				xfrm_state_put(x);
 				if (!err)
 					cnt++;
 
-				spin_lock_bh(&xfrm_state_lock);
+				spin_lock_bh(&net->xfrm.xfrm_state_lock);
 				goto restart;
 			}
 		}
@@ -636,19 +621,18 @@ restart:
 		err = 0;
 
 out:
-	spin_unlock_bh(&xfrm_state_lock);
-	wake_up(&net->xfrm.km_waitq);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_state_flush);
 
 void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
 {
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	si->sadcnt = net->xfrm.state_num;
 	si->sadhcnt = net->xfrm.state_hmask;
 	si->sadhmcnt = xfrm_state_hashmax;
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 }
 EXPORT_SYMBOL(xfrm_sad_getinfo);
 
@@ -798,10 +782,11 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 	struct xfrm_state *best = NULL;
 	u32 mark = pol->mark.v & pol->mark.m;
 	unsigned short encap_family = tmpl->encap_family;
+	struct km_event c;
 
 	to_put = NULL;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
 	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
 		if (x->props.family == encap_family &&
@@ -842,6 +827,17 @@ found:
 			error = -EEXIST;
 			goto out;
 		}
+
+		c.net = net;
+		/* If the KMs have no listeners (yet...), avoid allocating an SA
+		 * for each and every packet - garbage collection might not
+		 * handle the flood.
+		 */
+		if (!km_is_alive(&c)) {
+			error = -ESRCH;
+			goto out;
+		}
+
 		x = xfrm_state_alloc(net);
 		if (x == NULL) {
 			error = -ENOMEM;
@@ -886,7 +882,7 @@ out:
 		xfrm_state_hold(x);
 	else
 		*err = acquire_in_progress ? -EAGAIN : error;
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	if (to_put)
 		xfrm_state_put(to_put);
 	return x;
@@ -900,7 +896,7 @@ xfrm_stateonly_find(struct net *net, u32 mark,
 	unsigned int h;
 	struct xfrm_state *rx = NULL, *x = NULL;
 
-	spin_lock(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
 	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
 		if (x->props.family == family &&
@@ -918,13 +914,35 @@ xfrm_stateonly_find(struct net *net, u32 mark,
 
 	if (rx)
 		xfrm_state_hold(rx);
-	spin_unlock(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 
 	return rx;
 }
 EXPORT_SYMBOL(xfrm_stateonly_find);
 
+struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
+					      unsigned short family)
+{
+	struct xfrm_state *x;
+	struct xfrm_state_walk *w;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	list_for_each_entry(w, &net->xfrm.state_all, all) {
+		x = container_of(w, struct xfrm_state, km);
+		if (x->props.family != family ||
+			x->id.spi != spi)
+			continue;
+
+		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+		xfrm_state_hold(x);
+		return x;
+	}
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	return NULL;
+}
+EXPORT_SYMBOL(xfrm_state_lookup_byspi);
+
 static void __xfrm_state_insert(struct xfrm_state *x)
 {
 	struct net *net = xs_net(x);
@@ -950,14 +968,12 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 	if (x->replay_maxage)
 		mod_timer(&x->rtimer, jiffies + x->replay_maxage);
 
-	wake_up(&net->xfrm.km_waitq);
-
 	net->xfrm.state_num++;
 
 	xfrm_hash_grow_check(net, x->bydst.next != NULL);
 }
 
-/* xfrm_state_lock is held */
+/* net->xfrm.xfrm_state_lock is held */
 static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
 {
 	struct net *net = xs_net(xnew);
@@ -980,14 +996,16 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
 
 void xfrm_state_insert(struct xfrm_state *x)
 {
-	spin_lock_bh(&xfrm_state_lock);
+	struct net *net = xs_net(x);
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	__xfrm_state_bump_genids(x);
 	__xfrm_state_insert(x);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 }
 EXPORT_SYMBOL(xfrm_state_insert);
 
-/* xfrm_state_lock is held */
+/* net->xfrm.xfrm_state_lock is held */
 static struct xfrm_state *__find_acq_core(struct net *net,
 					  const struct xfrm_mark *m,
 					  unsigned short family, u8 mode,
@@ -1079,7 +1097,7 @@ int xfrm_state_add(struct xfrm_state *x)
 
 	to_put = NULL;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 
 	x1 = __xfrm_state_locate(x, use_spi, family);
 	if (x1) {
@@ -1108,7 +1126,7 @@ int xfrm_state_add(struct xfrm_state *x)
 	err = 0;
 
 out:
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	if (x1) {
 		xfrm_state_delete(x1);
@@ -1123,10 +1141,9 @@ out:
 EXPORT_SYMBOL(xfrm_state_add);
 
 #ifdef CONFIG_XFRM_MIGRATE
-static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
+static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig)
 {
 	struct net *net = xs_net(orig);
-	int err = -ENOMEM;
 	struct xfrm_state *x = xfrm_state_alloc(net);
 	if (!x)
 		goto out;
@@ -1147,6 +1164,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
 	}
 	x->props.aalgo = orig->props.aalgo;
 
+	if (orig->aead) {
+		x->aead = xfrm_algo_aead_clone(orig->aead);
+		if (!x->aead)
+			goto error;
+	}
 	if (orig->ealg) {
 		x->ealg = xfrm_algo_clone(orig->ealg);
 		if (!x->ealg)
@@ -1175,20 +1197,21 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
 	}
 
 	if (orig->replay_esn) {
-		err = xfrm_replay_clone(x, orig);
-		if (err)
+		if (xfrm_replay_clone(x, orig))
 			goto error;
 	}
 
 	memcpy(&x->mark, &orig->mark, sizeof(x->mark));
 
-	err = xfrm_init_state(x);
-	if (err)
+	if (xfrm_init_state(x) < 0)
 		goto error;
 
 	x->props.flags = orig->props.flags;
 	x->props.extra_flags = orig->props.extra_flags;
 
+	x->tfcpad = orig->tfcpad;
+	x->replay_maxdiff = orig->replay_maxdiff;
+	x->replay_maxage = orig->replay_maxage;
 	x->curlft.add_time = orig->curlft.add_time;
 	x->km.state = orig->km.state;
 	x->km.seq = orig->km.seq;
@@ -1198,21 +1221,20 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp)
  error:
 	xfrm_state_put(x);
 out:
-	if (errp)
-		*errp = err;
 	return NULL;
 }
 
-/* xfrm_state_lock is held */
-struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
+struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
 {
 	unsigned int h;
-	struct xfrm_state *x;
+	struct xfrm_state *x = NULL;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 
 	if (m->reqid) {
-		h = xfrm_dst_hash(&init_net, &m->old_daddr, &m->old_saddr,
+		h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
 				  m->reqid, m->old_family);
-		hlist_for_each_entry(x, init_net.xfrm.state_bydst+h, bydst) {
+		hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
 			if (x->props.mode != m->mode ||
 			    x->id.proto != m->proto)
 				continue;
@@ -1224,12 +1246,12 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
 					     m->old_family))
 				continue;
 			xfrm_state_hold(x);
-			return x;
+			break;
 		}
 	} else {
-		h = xfrm_src_hash(&init_net, &m->old_daddr, &m->old_saddr,
+		h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
 				  m->old_family);
-		hlist_for_each_entry(x, init_net.xfrm.state_bysrc+h, bysrc) {
+		hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) {
 			if (x->props.mode != m->mode ||
 			    x->id.proto != m->proto)
 				continue;
@@ -1239,21 +1261,22 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m)
 					     m->old_family))
 				continue;
 			xfrm_state_hold(x);
-			return x;
+			break;
 		}
 	}
 
-	return NULL;
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+	return x;
 }
 EXPORT_SYMBOL(xfrm_migrate_state_find);
 
-struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
-				       struct xfrm_migrate *m)
+struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
+				      struct xfrm_migrate *m)
 {
 	struct xfrm_state *xc;
-	int err;
 
-	xc = xfrm_state_clone(x, &err);
+	xc = xfrm_state_clone(x);
 	if (!xc)
 		return NULL;
 
@@ -1266,7 +1289,7 @@ struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
 		   state is to be updated as it is a part of triplet */
 		xfrm_state_insert(xc);
 	} else {
-		if ((err = xfrm_state_add(xc)) < 0)
+		if (xfrm_state_add(xc) < 0)
 			goto error;
 	}
 
@@ -1283,10 +1306,11 @@ int xfrm_state_update(struct xfrm_state *x)
 	struct xfrm_state *x1, *to_put;
 	int err;
 	int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY);
+	struct net *net = xs_net(x);
 
 	to_put = NULL;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	x1 = __xfrm_state_locate(x, use_spi, x->props.family);
 
 	err = -ESRCH;
@@ -1306,7 +1330,7 @@ int xfrm_state_update(struct xfrm_state *x)
 	err = 0;
 
 out:
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	if (to_put)
 		xfrm_state_put(to_put);
@@ -1357,7 +1381,7 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {
 		x->km.state = XFRM_STATE_EXPIRED;
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(0,0), HRTIMER_MODE_REL);
+		tasklet_hrtimer_start(&x->mtimer, ktime_set(0, 0), HRTIMER_MODE_REL);
 		return -EINVAL;
 	}
 
@@ -1377,9 +1401,9 @@ xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32
 {
 	struct xfrm_state *x;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return x;
 }
 EXPORT_SYMBOL(xfrm_state_lookup);
@@ -1391,9 +1415,9 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 {
 	struct xfrm_state *x;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return x;
 }
 EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
@@ -1405,9 +1429,9 @@ xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
 {
 	struct xfrm_state *x;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	return x;
 }
@@ -1416,17 +1440,17 @@ EXPORT_SYMBOL(xfrm_find_acq);
 #ifdef CONFIG_XFRM_SUB_POLICY
 int
 xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
-	       unsigned short family)
+	       unsigned short family, struct net *net)
 {
 	int err = 0;
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
 	if (!afinfo)
 		return -EAFNOSUPPORT;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/
 	if (afinfo->tmpl_sort)
 		err = afinfo->tmpl_sort(dst, src, n);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	xfrm_state_put_afinfo(afinfo);
 	return err;
 }
@@ -1438,13 +1462,15 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
 {
 	int err = 0;
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	struct net *net = xs_net(*src);
+
 	if (!afinfo)
 		return -EAFNOSUPPORT;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	if (afinfo->state_sort)
 		err = afinfo->state_sort(dst, src, n);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	xfrm_state_put_afinfo(afinfo);
 	return err;
 }
@@ -1476,9 +1502,9 @@ struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
 {
 	struct xfrm_state *x;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	x = __xfrm_find_acq_byseq(net, mark, seq);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return x;
 }
 EXPORT_SYMBOL(xfrm_find_acq_byseq);
@@ -1496,6 +1522,30 @@ u32 xfrm_get_acqseq(void)
 }
 EXPORT_SYMBOL(xfrm_get_acqseq);
 
+int verify_spi_info(u8 proto, u32 min, u32 max)
+{
+	switch (proto) {
+	case IPPROTO_AH:
+	case IPPROTO_ESP:
+		break;
+
+	case IPPROTO_COMP:
+		/* IPCOMP spi is 16-bits. */
+		if (max >= 0x10000)
+			return -EINVAL;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (min > max)
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL(verify_spi_info);
+
 int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 {
 	struct net *net = xs_net(x);
@@ -1525,8 +1575,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 		x->id.spi = minspi;
 	} else {
 		u32 spi = 0;
-		for (h=0; h<high-low+1; h++) {
-			spi = low + net_random()%(high-low+1);
+		for (h = 0; h < high-low+1; h++) {
+			spi = low + prandom_u32()%(high-low+1);
 			x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
 			if (x0 == NULL) {
 				x->id.spi = htonl(spi);
@@ -1536,10 +1586,10 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 		}
 	}
 	if (x->id.spi) {
-		spin_lock_bh(&xfrm_state_lock);
+		spin_lock_bh(&net->xfrm.xfrm_state_lock);
 		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
 		hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
-		spin_unlock_bh(&xfrm_state_lock);
+		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 		err = 0;
 	}
@@ -1551,6 +1601,23 @@ unlock:
 }
 EXPORT_SYMBOL(xfrm_alloc_spi);
 
+static bool __xfrm_state_filter_match(struct xfrm_state *x,
+				      struct xfrm_address_filter *filter)
+{
+	if (filter) {
+		if ((filter->family == AF_INET ||
+		     filter->family == AF_INET6) &&
+		    x->props.family != filter->family)
+			return false;
+
+		return addr_match(&x->props.saddr, &filter->saddr,
+				  filter->splen) &&
+		       addr_match(&x->id.daddr, &filter->daddr,
+				  filter->dplen);
+	}
+	return true;
+}
+
 int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
 		    int (*func)(struct xfrm_state *, int, void*),
 		    void *data)
@@ -1562,7 +1629,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
 	if (walk->seq != 0 && list_empty(&walk->all))
 		return 0;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	if (list_empty(&walk->all))
 		x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all);
 	else
@@ -1573,6 +1640,8 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
 		state = container_of(x, struct xfrm_state, km);
 		if (!xfrm_id_proto_match(state->id.proto, walk->proto))
 			continue;
+		if (!__xfrm_state_filter_match(state, walk->filter))
+			continue;
 		err = func(state, walk->seq, data);
 		if (err) {
 			list_move_tail(&walk->all, &x->all);
@@ -1586,34 +1655,38 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
 	}
 	list_del_init(&walk->all);
 out:
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return err;
 }
 EXPORT_SYMBOL(xfrm_state_walk);
 
-void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto)
+void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto,
+			  struct xfrm_address_filter *filter)
 {
 	INIT_LIST_HEAD(&walk->all);
 	walk->proto = proto;
 	walk->state = XFRM_STATE_DEAD;
 	walk->seq = 0;
+	walk->filter = filter;
 }
 EXPORT_SYMBOL(xfrm_state_walk_init);
 
-void xfrm_state_walk_done(struct xfrm_state_walk *walk)
+void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net)
 {
+	kfree(walk->filter);
+
 	if (list_empty(&walk->all))
 		return;
 
-	spin_lock_bh(&xfrm_state_lock);
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	list_del(&walk->all);
-	spin_unlock_bh(&xfrm_state_lock);
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 }
 EXPORT_SYMBOL(xfrm_state_walk_done);
 
 static void xfrm_replay_timer_handler(unsigned long data)
 {
-	struct xfrm_state *x = (struct xfrm_state*)data;
+	struct xfrm_state *x = (struct xfrm_state *)data;
 
 	spin_lock(&x->lock);
 
@@ -1655,16 +1728,12 @@ EXPORT_SYMBOL(km_state_notify);
 
 void km_state_expired(struct xfrm_state *x, int hard, u32 portid)
 {
-	struct net *net = xs_net(x);
 	struct km_event c;
 
 	c.data.hard = hard;
 	c.portid = portid;
 	c.event = XFRM_MSG_EXPIRE;
 	km_state_notify(x, &c);
-
-	if (hard)
-		wake_up(&net->xfrm.km_waitq);
 }
 
 EXPORT_SYMBOL(km_state_expired);
@@ -1707,16 +1776,12 @@ EXPORT_SYMBOL(km_new_mapping);
 
 void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid)
 {
-	struct net *net = xp_net(pol);
 	struct km_event c;
 
 	c.data.hard = hard;
 	c.portid = portid;
 	c.event = XFRM_MSG_POLEXPIRE;
 	km_policy_notify(pol, dir, &c);
-
-	if (hard)
-		wake_up(&net->xfrm.km_waitq);
 }
 EXPORT_SYMBOL(km_policy_expired);
 
@@ -1762,6 +1827,24 @@ int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address
 }
 EXPORT_SYMBOL(km_report);
 
+bool km_is_alive(const struct km_event *c)
+{
+	struct xfrm_mgr *km;
+	bool is_alive = false;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
+		if (km->is_alive && km->is_alive(c)) {
+			is_alive = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return is_alive;
+}
+EXPORT_SYMBOL(km_is_alive);
+
 int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
 {
 	int err;
@@ -2025,7 +2108,7 @@ int __net_init xfrm_state_init(struct net *net)
 	INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
 	INIT_HLIST_HEAD(&net->xfrm.state_gc_list);
 	INIT_WORK(&net->xfrm.state_gc_work, xfrm_state_gc_task);
-	init_waitqueue_head(&net->xfrm.km_waitq);
+	spin_lock_init(&net->xfrm.xfrm_state_lock);
 	return 0;
 
 out_byspi:
@@ -2038,14 +2121,10 @@ out_bydst:
 
 void xfrm_state_fini(struct net *net)
 {
-	struct xfrm_audit audit_info;
 	unsigned int sz;
 
 	flush_work(&net->xfrm.state_hash_work);
-	audit_info.loginuid = INVALID_UID;
-	audit_info.sessionid = -1;
-	audit_info.secid = 0;
-	xfrm_state_flush(net, IPSEC_PROTO_ANY, &audit_info);
+	xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
 	flush_work(&net->xfrm.state_gc_work);
 
 	WARN_ON(!list_empty(&net->xfrm.state_all));
@@ -2070,7 +2149,7 @@ static void xfrm_audit_helper_sainfo(struct xfrm_state *x,
 		audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s",
 				 ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str);
 
-	switch(x->props.family) {
+	switch (x->props.family) {
 	case AF_INET:
 		audit_log_format(audit_buf, " src=%pI4 dst=%pI4",
 				 &x->props.saddr.a4, &x->id.daddr.a4);
@@ -2100,7 +2179,7 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family,
 		iph6 = ipv6_hdr(skb);
 		audit_log_format(audit_buf,
 				 " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x",
-				 &iph6->saddr,&iph6->daddr,
+				 &iph6->saddr, &iph6->daddr,
 				 iph6->flow_lbl[0] & 0x0f,
 				 iph6->flow_lbl[1],
 				 iph6->flow_lbl[2]);
@@ -2108,30 +2187,28 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family,
 	}
 }
 
-void xfrm_audit_state_add(struct xfrm_state *x, int result,
-			  kuid_t auid, u32 sessionid, u32 secid)
+void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid)
 {
 	struct audit_buffer *audit_buf;
 
 	audit_buf = xfrm_audit_start("SAD-add");
 	if (audit_buf == NULL)
 		return;
-	xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf);
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
 	xfrm_audit_helper_sainfo(x, audit_buf);
 	audit_log_format(audit_buf, " res=%u", result);
 	audit_log_end(audit_buf);
 }
 EXPORT_SYMBOL_GPL(xfrm_audit_state_add);
 
-void xfrm_audit_state_delete(struct xfrm_state *x, int result,
-			     kuid_t auid, u32 sessionid, u32 secid)
+void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid)
 {
 	struct audit_buffer *audit_buf;
 
 	audit_buf = xfrm_audit_start("SAD-delete");
 	if (audit_buf == NULL)
 		return;
-	xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf);
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
 	xfrm_audit_helper_sainfo(x, audit_buf);
 	audit_log_format(audit_buf, " res=%u", result);
 	audit_log_end(audit_buf);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index f964d4c00ff..d4db6ebb089 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -32,11 +32,6 @@
 #include <linux/in6.h>
 #endif
 
-static inline int aead_len(struct xfrm_algo_aead *alg)
-{
-	return sizeof(*alg) + ((alg->alg_key_len + 7) / 8);
-}
-
 static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type)
 {
 	struct nlattr *rt = attrs[type];
@@ -142,7 +137,8 @@ static inline int verify_replay(struct xfrm_usersa_info *p,
 	if (!rt)
 		return 0;
 
-	if (p->id.proto != IPPROTO_ESP)
+	/* As only ESP and AH support ESN feature. */
+	if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH))
 		return -EINVAL;
 
 	if (p->replay_window != 0)
@@ -209,7 +205,8 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 		    attrs[XFRMA_ALG_AUTH]	||
 		    attrs[XFRMA_ALG_AUTH_TRUNC]	||
 		    attrs[XFRMA_ALG_CRYPT]	||
-		    attrs[XFRMA_TFCPAD])
+		    attrs[XFRMA_TFCPAD]		||
+		    (ntohl(p->id.spi) >= 0x10000))
 			goto out;
 		break;
 
@@ -599,9 +596,6 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_state *x;
 	int err;
 	struct km_event c;
-	kuid_t loginuid = audit_get_loginuid(current);
-	u32 sessionid = audit_get_sessionid(current);
-	u32 sid;
 
 	err = verify_newsa_info(p, attrs);
 	if (err)
@@ -617,8 +611,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	else
 		err = xfrm_state_update(x);
 
-	security_task_getsecid(current, &sid);
-	xfrm_audit_state_add(x, err ? 0 : 1, loginuid, sessionid, sid);
+	xfrm_audit_state_add(x, err ? 0 : 1, true);
 
 	if (err < 0) {
 		x->km.state = XFRM_STATE_DEAD;
@@ -678,9 +671,6 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err = -ESRCH;
 	struct km_event c;
 	struct xfrm_usersa_id *p = nlmsg_data(nlh);
-	kuid_t loginuid = audit_get_loginuid(current);
-	u32 sessionid = audit_get_sessionid(current);
-	u32 sid;
 
 	x = xfrm_user_state_lookup(net, p, attrs, &err);
 	if (x == NULL)
@@ -705,8 +695,7 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	km_state_notify(x, &c);
 
 out:
-	security_task_getsecid(current, &sid);
-	xfrm_audit_state_delete(x, err ? 0 : 1, loginuid, sessionid, sid);
+	xfrm_audit_state_delete(x, err ? 0 : 1, true);
 	xfrm_state_put(x);
 	return err;
 }
@@ -877,10 +866,14 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
 static int xfrm_dump_sa_done(struct netlink_callback *cb)
 {
 	struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1];
-	xfrm_state_walk_done(walk);
+	struct sock *sk = cb->skb->sk;
+	struct net *net = sock_net(sk);
+
+	xfrm_state_walk_done(walk, net);
 	return 0;
 }
 
+static const struct nla_policy xfrma_policy[XFRMA_MAX+1];
 static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
@@ -896,8 +889,31 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
 	info.nlmsg_flags = NLM_F_MULTI;
 
 	if (!cb->args[0]) {
+		struct nlattr *attrs[XFRMA_MAX+1];
+		struct xfrm_address_filter *filter = NULL;
+		u8 proto = 0;
+		int err;
+
 		cb->args[0] = 1;
-		xfrm_state_walk_init(walk, 0);
+
+		err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX,
+				  xfrma_policy);
+		if (err < 0)
+			return err;
+
+		if (attrs[XFRMA_ADDRESS_FILTER]) {
+			filter = kmalloc(sizeof(*filter), GFP_KERNEL);
+			if (filter == NULL)
+				return -ENOMEM;
+
+			memcpy(filter, nla_data(attrs[XFRMA_ADDRESS_FILTER]),
+			       sizeof(*filter));
+		}
+
+		if (attrs[XFRMA_PROTO])
+			proto = nla_get_u8(attrs[XFRMA_PROTO]);
+
+		xfrm_state_walk_init(walk, proto, filter);
 	}
 
 	(void) xfrm_state_walk(net, walk, dump_one_state, &info);
@@ -930,6 +946,20 @@ static struct sk_buff *xfrm_state_netlink(struct sk_buff *in_skb,
 	return skb;
 }
 
+/* A wrapper for nlmsg_multicast() checking that nlsk is still available.
+ * Must be called with RCU read lock.
+ */
+static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
+				       u32 pid, unsigned int group)
+{
+	struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
+
+	if (nlsk)
+		return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
+	else
+		return -1;
+}
+
 static inline size_t xfrm_spdinfo_msgsize(void)
 {
 	return NLMSG_ALIGN(4)
@@ -1074,29 +1104,6 @@ out_noput:
 	return err;
 }
 
-static int verify_userspi_info(struct xfrm_userspi_info *p)
-{
-	switch (p->info.id.proto) {
-	case IPPROTO_AH:
-	case IPPROTO_ESP:
-		break;
-
-	case IPPROTO_COMP:
-		/* IPCOMP spi is 16-bits. */
-		if (p->max >= 0x10000)
-			return -EINVAL;
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	if (p->min > p->max)
-		return -EINVAL;
-
-	return 0;
-}
-
 static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct nlattr **attrs)
 {
@@ -1111,7 +1118,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_mark m;
 
 	p = nlmsg_data(nlh);
-	err = verify_userspi_info(p);
+	err = verify_spi_info(p->info.id.proto, p->min, p->max);
 	if (err)
 		goto out_noput;
 
@@ -1189,6 +1196,8 @@ static int verify_policy_type(u8 type)
 
 static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
 {
+	int ret;
+
 	switch (p->share) {
 	case XFRM_SHARE_ANY:
 	case XFRM_SHARE_SESSION:
@@ -1224,7 +1233,13 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
 		return -EINVAL;
 	}
 
-	return verify_policy_dir(p->dir);
+	ret = verify_policy_dir(p->dir);
+	if (ret)
+		return ret;
+	if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir))
+		return -EINVAL;
+
+	return 0;
 }
 
 static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs)
@@ -1236,7 +1251,7 @@ static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs
 		return 0;
 
 	uctx = nla_data(rt);
-	return security_xfrm_policy_alloc(&pol->security, uctx);
+	return security_xfrm_policy_alloc(&pol->security, uctx, GFP_KERNEL);
 }
 
 static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut,
@@ -1404,9 +1419,6 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct km_event c;
 	int err;
 	int excl;
-	kuid_t loginuid = audit_get_loginuid(current);
-	u32 sessionid = audit_get_sessionid(current);
-	u32 sid;
 
 	err = verify_newpolicy_info(p);
 	if (err)
@@ -1425,8 +1437,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	 * a type XFRM_MSG_UPDPOLICY - JHS */
 	excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY;
 	err = xfrm_policy_insert(p->dir, xp, excl);
-	security_task_getsecid(current, &sid);
-	xfrm_audit_policy_add(xp, err ? 0 : 1, loginuid, sessionid, sid);
+	xfrm_audit_policy_add(xp, err ? 0 : 1, true);
 
 	if (err) {
 		security_xfrm_policy_free(xp->security);
@@ -1547,8 +1558,9 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
 static int xfrm_dump_policy_done(struct netlink_callback *cb)
 {
 	struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1];
+	struct net *net = sock_net(cb->skb->sk);
 
-	xfrm_policy_walk_done(walk);
+	xfrm_policy_walk_done(walk, net);
 	return 0;
 }
 
@@ -1640,7 +1652,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 		if (rt) {
 			struct xfrm_user_sec_ctx *uctx = nla_data(rt);
 
-			err = security_xfrm_policy_alloc(&ctx, uctx);
+			err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL);
 			if (err)
 				return err;
 		}
@@ -1662,13 +1674,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 					    NETLINK_CB(skb).portid);
 		}
 	} else {
-		kuid_t loginuid = audit_get_loginuid(current);
-		u32 sessionid = audit_get_sessionid(current);
-		u32 sid;
-
-		security_task_getsecid(current, &sid);
-		xfrm_audit_policy_delete(xp, err ? 0 : 1, loginuid, sessionid,
-					 sid);
+		xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
 
 		if (err != 0)
 			goto out;
@@ -1693,13 +1699,9 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct km_event c;
 	struct xfrm_usersa_flush *p = nlmsg_data(nlh);
-	struct xfrm_audit audit_info;
 	int err;
 
-	audit_info.loginuid = audit_get_loginuid(current);
-	audit_info.sessionid = audit_get_sessionid(current);
-	security_task_getsecid(current, &audit_info.secid);
-	err = xfrm_state_flush(net, p->proto, &audit_info);
+	err = xfrm_state_flush(net, p->proto, true);
 	if (err) {
 		if (err == -ESRCH) /* empty table */
 			return 0;
@@ -1740,11 +1742,11 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct
 		return -EMSGSIZE;
 
 	id = nlmsg_data(nlh);
-	memcpy(&id->sa_id.daddr, &x->id.daddr,sizeof(x->id.daddr));
+	memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr));
 	id->sa_id.spi = x->id.spi;
 	id->sa_id.family = x->props.family;
 	id->sa_id.proto = x->id.proto;
-	memcpy(&id->saddr, &x->props.saddr,sizeof(x->props.saddr));
+	memcpy(&id->saddr, &x->props.saddr, sizeof(x->props.saddr));
 	id->reqid = x->props.reqid;
 	id->flags = c->data.aevent;
 
@@ -1833,7 +1835,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct xfrm_state *x;
 	struct km_event c;
-	int err = - EINVAL;
+	int err = -EINVAL;
 	u32 mark = 0;
 	struct xfrm_mark m;
 	struct xfrm_aevent_id *p = nlmsg_data(nlh);
@@ -1883,16 +1885,12 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct km_event c;
 	u8 type = XFRM_POLICY_TYPE_MAIN;
 	int err;
-	struct xfrm_audit audit_info;
 
 	err = copy_from_user_policy_type(&type, attrs);
 	if (err)
 		return err;
 
-	audit_info.loginuid = audit_get_loginuid(current);
-	audit_info.sessionid = audit_get_sessionid(current);
-	security_task_getsecid(current, &audit_info.secid);
-	err = xfrm_policy_flush(net, type, &audit_info);
+	err = xfrm_policy_flush(net, type, true);
 	if (err) {
 		if (err == -ESRCH) /* empty table */
 			return 0;
@@ -1942,7 +1940,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 		if (rt) {
 			struct xfrm_user_sec_ctx *uctx = nla_data(rt);
 
-			err = security_xfrm_policy_alloc(&ctx, uctx);
+			err = security_xfrm_policy_alloc(&ctx, uctx, GFP_KERNEL);
 			if (err)
 				return err;
 		}
@@ -1958,14 +1956,8 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	err = 0;
 	if (up->hard) {
-		kuid_t loginuid = audit_get_loginuid(current);
-		u32 sessionid = audit_get_sessionid(current);
-		u32 sid;
-
-		security_task_getsecid(current, &sid);
 		xfrm_policy_delete(xp, p->dir);
-		xfrm_audit_policy_delete(xp, 1, loginuid, sessionid, sid);
-
+		xfrm_audit_policy_delete(xp, 1, true);
 	} else {
 		// reset the timers here?
 		WARN(1, "Dont know what to do with soft policy expire\n");
@@ -2001,13 +1993,8 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 	km_state_expired(x, ue->hard, nlh->nlmsg_pid);
 
 	if (ue->hard) {
-		kuid_t loginuid = audit_get_loginuid(current);
-		u32 sessionid = audit_get_sessionid(current);
-		u32 sid;
-
-		security_task_getsecid(current, &sid);
 		__xfrm_state_delete(x);
-		xfrm_audit_state_delete(x, 1, loginuid, sessionid, sid);
+		xfrm_audit_state_delete(x, 1, true);
 	}
 	err = 0;
 out:
@@ -2129,6 +2116,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u8 type;
 	int err;
 	int n = 0;
+	struct net *net = sock_net(skb->sk);
 
 	if (attrs[XFRMA_MIGRATE] == NULL)
 		return -EINVAL;
@@ -2146,7 +2134,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!n)
 		return 0;
 
-	xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp);
+	xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net);
 
 	return 0;
 }
@@ -2253,7 +2241,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	if (build_migrate(skb, m, num_migrate, k, sel, dir, type) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MIGRATE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE);
 }
 #else
 static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
@@ -2316,6 +2304,8 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_TFCPAD]		= { .type = NLA_U32 },
 	[XFRMA_REPLAY_ESN_VAL]	= { .len = sizeof(struct xfrm_replay_state_esn) },
 	[XFRMA_SA_EXTRA_FLAGS]	= { .type = NLA_U32 },
+	[XFRMA_PROTO]		= { .type = NLA_U8 },
+	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
 };
 
 static const struct xfrm_link {
@@ -2363,7 +2353,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	link = &xfrm_dispatch[type];
 
 	/* All operations require privileges, even GET */
-	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||
@@ -2394,9 +2384,11 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 static void xfrm_netlink_rcv(struct sk_buff *skb)
 {
-	mutex_lock(&xfrm_cfg_mutex);
+	struct net *net = sock_net(skb->sk);
+
+	mutex_lock(&net->xfrm.xfrm_cfg_mutex);
 	netlink_rcv_skb(skb, &xfrm_user_rcv_msg);
-	mutex_unlock(&xfrm_cfg_mutex);
+	mutex_unlock(&net->xfrm.xfrm_cfg_mutex);
 }
 
 static inline size_t xfrm_expire_msgsize(void)
@@ -2440,7 +2432,7 @@ static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c)
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
 }
 
 static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event *c)
@@ -2455,7 +2447,7 @@ static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event
 	if (build_aevent(skb, x, c) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_AEVENTS);
 }
 
 static int xfrm_notify_sa_flush(const struct km_event *c)
@@ -2481,7 +2473,7 @@ static int xfrm_notify_sa_flush(const struct km_event *c)
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
 }
 
 static inline size_t xfrm_sa_len(struct xfrm_state *x)
@@ -2568,7 +2560,7 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c)
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
 
 out_free_skb:
 	kfree_skb(skb);
@@ -2659,7 +2651,7 @@ static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt,
 	if (build_acquire(skb, x, xt, xp) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_ACQUIRE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_ACQUIRE);
 }
 
 /* User gives us xfrm_user_policy_info followed by an array of 0
@@ -2773,7 +2765,7 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct
 	if (build_polexpire(skb, xp, dir, c) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
 }
 
 static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c)
@@ -2835,7 +2827,7 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
 
 out_free_skb:
 	kfree_skb(skb);
@@ -2863,7 +2855,7 @@ static int xfrm_notify_policy_flush(const struct km_event *c)
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
 
 out_free_skb:
 	kfree_skb(skb);
@@ -2932,7 +2924,7 @@ static int xfrm_send_report(struct net *net, u8 proto,
 	if (build_report(skb, proto, sel, addr) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_REPORT, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_REPORT);
 }
 
 static inline size_t xfrm_mapping_msgsize(void)
@@ -2984,7 +2976,12 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 	if (build_mapping(skb, x, ipaddr, sport) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MAPPING, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MAPPING);
+}
+
+static bool xfrm_is_alive(const struct km_event *c)
+{
+	return (bool)xfrm_acquire_is_on(c->net);
 }
 
 static struct xfrm_mgr netlink_mgr = {
@@ -2996,6 +2993,7 @@ static struct xfrm_mgr netlink_mgr = {
 	.report		= xfrm_send_report,
 	.migrate	= xfrm_send_migrate,
 	.new_mapping	= xfrm_send_mapping,
+	.is_alive	= xfrm_is_alive,
 };
 
 static int __net_init xfrm_user_net_init(struct net *net)